text
stringlengths 0
923k
|
|---|
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
543
Article
What if Berkeley Had Gone to Berkeley? Neurophysiology &
Physics in the Defence of Informational Idealism:
Part I: The Problem of Experience
Paul Seward*
Abstract
Our argument is divided into two parts. In this Part I, we stipulate and defend the existence of an
experiencing subject or “self” that is not identical to consciousness but for whom consciousness
is an objective experience. We then show that the relationship of time and space to moving
objects requires that the self cannot be a part of space-time or made of matter and energy.
Keywords: experiencing subject, self, consciousness, objective experience, time, space, moving
object, space-time, matter, energy.
Introduction
George Berkeley is well known as the proponent of the philosophical stance of Idealism. This
position may be summarized as the belief that there is no external material reality; all that we
experience exists only in our minds, and is sustained by its coexistence in the mind of God.
Idealism has attracted few followers. Nonetheless its status as wallflower in the dance of
philosophy does not lie in its refutation. Rather it is more aesthetic – it just doesn’t seem right.
The irrelevance of Idealism
This discomfort stems from four qualities. The first is the easy way idealism seems to lead to
solipsism. If the universe exists solely in the mind of God, and if I am the only one that I am sure
experiences that universe, how am I to distinguish myself from God? A second objection is that
it is too clumsy. The thought that the moon might appear in the sky only when we look at it and
blink out of existence when we turn away seems improbable. Thirdly, particularly in the modern
world, it seems more human-centered than the universe appears to be. Finally, a fourth objection,
attributed to Berkeley’s contemporary, Samuel Johnson, is aesthetic rather than rational. Boswell
quotes Johnson as kicking a stone and saying “I refute it thus” in reference to Berkeley’s
philosophy, using the solidity of the rock to deny the supposed insubstantiality of an Idealist
universe.1
*
1
Correspondence: Paul Seward, 8720 Oregon Inlet Court Raleigh, NC 27603. E-mail: oakenshade@gmail.com
The Samuel Johnson Sound Bite Page #57. http://www.samueljohnson.com/refutati.html
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
544
In short, that which makes Idealism unattractive is not effective contrary argument, but that it
seems not to reflect our experience. Idealism is a question which has not been so much answered
as abandoned.
A contrary view
This paper is an argument to the contrary. Our thesis is that, Idealism, constructed in light of
contemporary physics and neurophysiology, reflects completely the consistency and complexity
of both the universe and the human brain as present day science understands them – and as
Bishop Berkeley would have understood them if he had had the privilege of attending U.C.
Berkeley (assuming of course that he had been unable to get into Stanford).
The Problem of Experience
The problem of experience is hard to describe not because experience is so unfamiliar, but
because it is so commonplace. Experience is not just a part of our life; it is our life. All we can
ever be aware of are the experiences produced by our brains. However, while our experiences are
entirely created by the brain, they exist in a form – the contents of the mind - that so far cannot
be explained by the things that the brain can do.
For example, let us grant that the brain can produce a pattern that corresponds to the taste of
chocolate such that – presumably - every time this pattern occurs - the same thing occurs in our
mind. But when we eat a piece of chocolate, we don’t taste pulsing neurons; we taste chocolate.
Furthermore, the taste of chocolate is nothing like a pulsing neuron. There is a profound
qualitative difference between producing a pattern of neuronal impulses, and experiencing what
that pattern engenders in our mind. How is this accomplished?
In order to answer this we must be clear about what we mean by the “mind.”
The American Heritage Dictionary comes close to the use we intend, in its first definition for
“Mind”:
The human consciousness that originates in the brain and is manifested especially in
thought, perception, emotion, will, memory, and imagination.2
This definition contains some important features. First of all, the definition describes the mind as
being something like the sum of all those qualities – thought, perception etc. - which we
associate with conscious experience. Second, this definition clearly states the fact that those
patterns which we experience are the manifestations of brain processes. That is, the mind is thus
not the pattern produced by brain activity but is instead the sum of all those ways in which we –
2
The American Heritage Dictionary of the English Language: Fourth Edition. (2000.)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
545
however mysteriously - experience those patterns. A word used by philosophers of
consciousness to refer to these ways is “Qualia.”
The Qualia Problem
However there is a problem with the concept of “Qualia.” Daniel Dennett, describes it in this
manner: “"Qualia" is an unfamiliar term for something that could not be more familiar to each of
us: the ways things seem to us.”3 Examples of this are limitless: the memory of a conversation
with a friend; the way music sounds; the smell of a flower or a barn; the feel of snow. But Dr.
Dennett goes on to state: “(The concept of qualia is) so thoroughly confused that…. any
acceptable version would have to be so radically unlike the ill-formed notions that are commonly
appealed to that it would be tactically obtuse--not to say Pickwickian--to cling to the term. Far
better, tactically, to declare that there simply are no qualia at all.”4
Dr. Dennett comes to this conclusion because he finds that, when he takes any particular qualia
and tries to apply the kind of analysis to it that would meet the requirements of a definable term,
he is unable to do so. For example, in attempting to tell whether or not glass of one brand of beer
has a different taste (i.e. qualia) than another, he runs up against problems of memory (do I
remember the other sensation correctly?), of associated feelings or sensations (I am sad drinking
this one, I was happy then); or associated experience (I had just come in from mowing the lawn
last time and was thirsty, now I have just had several glasses of water) etc. etc. Considered in this
way, it would seem that there is no way to tell if this taste of beer is a unique experience or
actually like anything we have tasted before. It is not that we do not have the experiences which
we try to categorize as qualia. The problem is that each experience is such a unique and complex
mixture that it resists the categorization necessary for definition.
But if we cannot classify qualia in any way other than as a gigantic collection of possibly unique
and unrelated events, can we really make any sense of them at all?
Experience as epiphenomenal
What we have come to is the question of whether what we think of as our mind even has a
definable existence. That is not to say that we do not experience feelings or sensations in our
mind. The question is whether or not those feelings or sensations which we experience are
sufficiently capable of definition as to be considered real in and of themselves. More precisely,
the question is whether or not the brain (the material object) and its actions (the electrochemistry
of neuronal activity), are all that actually exist, and the undefinable experiencing part is merely
“epiphenomenal,” just some sort of pseudo reality, a secondary byproduct of those brain patterns,
a kind of mirage.
3
4
Quining Qualia by Daniel Dennett : http://ase.tufts.edu/cogstud/papers/quinqual.htm
Ibid
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
546
Experience as undeniable
The opposing argument for the independent reality of subjective experience is that, for each of
us, the fact that we subjectively experience is self-evident and undeniable. That its reality cannot
be demonstrated is due to its utterly subjective and private nature – that is, there is absolutely no
way for anyone other than the person who has the experience to detect its occurrence, much less
to share in its nature. Even so, the solitary witness to experience has no doubt that it is real.
This is a debate which is not so much difficult to win, as difficult even to have. All parties agree
about physical reality, about the brain, about physics. There is agreement also about the
correspondence between specific patterns in the brain and specific experiences.5 Furthermore Dr.
Dennett’s objections to qualia are sound. The disagreement between those who argue that
experiencing is real and those who espouse the epiphenomenal point of view seems to concern
primarily what can be a legitimate topic for discussion. It is like a courtroom argument, in which
the principle question is not about the interpretation of a piece of evidence, but about its
admissibility. Is there a way out of this dilemma?
Differentiating that which experiences from that which is experienced
Sometimes the reason for an irresolvable dilemma is not that there is no answer but that we have
asked the wrong question. Perhaps the question is not whether what we experience in our mind
has any existence, either in some “outer universe” or even in our own mind. Perhaps the question
is, no matter how experiences are engendered, do they not require for that existence, something
real to have those experiences?
Hypothesis Part 1: An experiencing subject exists.
We begin our discussion of this question not by arguing for the existence of such a subject but by
stipulating that it does, including what might be its necessary characteristics, and then examining
the consequences of such a stipulation.
The characteristics of an experiencing subject.
Creating a complete list of such criteria is a difficult task because the list must be so subjective.
On the one hand, the characteristics of an experiencing subject must be those which match that
which each of us experiences. On the other hand, the act of experiencing is completely private,
detectible only by the person who is doing the experiencing.
With this caveat, a set of characteristics to define an experiencing subject might be these:
5
Even so, other than the results of electrode studies on the brain which are orders of magnitude more gross than
ordinary brain events, the statement that “specific patterns in the brain produce specific experiences” is still only a
conjecture. It is not however one whose truth or falsity has any significant bearing on the question at hand.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
547
1. Singularity: An experiencing subject must be single, not divisible. Experiences are limitless;
but that which unites them is that a single subject, a unique and persistent “I,” experiences
them.
2. Continuity: An experiencing subject must be continuous and permanent. There should be no
place that we can go that our experiencing subject is not. This does not mean that we are
permanently conscious: if we close our eyes we see nothing, but we still have eyes. If we
become unconscious the experiencing subject may have nothing to experience. But when
consciousness resumes, it is the same experiencing subject that once more has those
experiences.
3. Neither mind nor consciousness: Consciousness and mind are both products of the activity
of the brain and as such can be the format of experience, the context of experience, but not
the subject who experiences.
4. Associated with a single brain: An experiencing subject must be associated with a single
physical body – or, more precisely, with a specific individual brain. We do not have one
person’s experiences today and another’s tomorrow.
5. Not itself an experience: Most subtle, yet most important: an experiencing subject cannot
itself be an experience. We know with certainty that we have eyes, because of the certainty
with which we experience vision; but our eyes do not see themselves
6. Undeniability: An experiencing subject – or, more precisely, that we are an experiencing
subject – should seem real, believable, and indeed undeniable, even if the evidence for its
reality can only be our conviction that we do experience.
7. Identity with ourself: But what have we just said? We experience. That we experience is at
once the most personal and undeniable truths of our existence. As such, must we not
ourselves – whatever it is we mean by “ourselves” - be that experiencing subject? Descartes
held up his thoughts as the one thing he could not deny. Perhaps we might modify this to say
that the mechanics of thinking are something that is done by the brain – but I am that which
experiences those thoughts. Or in other words, “Experior, ergo sum,” - I experience,
therefore I am.
THE SELF
Before we go further, it’s time to introduce a new term for “the experiencing subject.” This term
shall be the word “Self.” But having chosen it, we must make a comment on the choice of
“Self”6 as the name for this entity.
6
TECHNICAL NOTE: Henceforth in this work, we will assume for the purpose of our argument that the self is real,
and is indeed the essential part of each of us to which the First Person pronouns refer. Therefore, when we use the
pronouns “We” or “I”, or when I say “you,” or “she” or “him” – that pronoun is meant to refer to each of us in our
capacity as experiencing selves – not simply as human beings.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
548
Arguably we should have just invented a word. To use a word that already has a meaning and is
in common use is to add both denotative and connotative baggage that is not included in our list
of characteristics. However, when we turn once more to the formal definition of “Self” we find –
under its philosophical meaning:
“that which knows, remembers, desires, suffers, etc., as contrasted with that known,
remembered, etc.” and secondarily, “the uniting principle underlying all subjective
experience.”7
This definition includes the characteristics of an experiencing subject – singleness, continuation,
association with a single body, etc. which we listed above. As such, though it brings baggage, it
is baggage that is largely consistent with what we intend. So we will go with it.
However, such a definition is not the end of this discussion, but the beginning. If we state that
the Self exists – i.e. is real, then we must return to the question of what can we mean by reality.
Because in fact such a Self must have one more extremely important quality:
8. Not part of material reality: it cannot be a construction of matter and energy, and cannot
occupy space-time.
Why not?
To answer this question we need to look at the problem of motion in time and the nature of the
present moment.
The Problem of Motion
Why is motion a problem? 8 It is a problem because Time is a problem. That is, when we look
carefully at how time fits in to the design of the universe as a whole, then motion – i.e. the ability
of objects to change locations as time passes - should be impossible, meaningless, even
unthinkable. This is due to the fact that, like matter and energy, while time and space appear to
be two different things, they are essentially two forms of the same quality, different only in how
7
The Random House Dictionary, (2002) Random House. The exact definition is “the ego; that which
knows, remembers, desires, suffers, etc., as contrasted with that known, remembered, etc.” and
secondarily, “the uniting principle, as a soul, underlying all subjective experience.” However to include
either the word “ego” or ‘soul” in the definition assumes more qualities than we have shown to exist.
8
Conee and Sider (see Bibiliography #3) have a very lucid discussion of this problem.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
549
they are expressed.9
To be precise, the fact that time is identical to space, yet appears to be different, is that which
seems to permit motion. Motion is not instantaneous; it always takes some amount of time.
Motion is possible only because the fundamental dimensional identity of time and space permits
a single event to produce a simultaneous change in position in both of them.
But does it really permit such a thing? If we look more carefully we must realize that, for this
change to actually be motion rather than merely extension there must be a change in another
dimension as well. This process forms an infinite regression.
You have to have a feel for this in order for any of the rest to make sense. So let’s go through an
example. Let’s begin with a universe that has no dimensions at all.
Ms. Point
.
Meet Ms. Point. Her universe has no dimensions and neither does she. She has no height, no
length and no width. She is standing on a dimensionless point of space, and occupies just one
moment of time.
Obviously she can’t do very much. So let’s give her universe one dimension. And, to be specific,
we will assume that the two points A and B, bounding that one-dimensional universe, are ten feet
apart, and that Ms Point stands on point A
MS Point .(0)A__________________________.B (10)
This sort of gives her some breathing room – or does it? Let’s imagine that she is standing on
point A, and wants to go to point B. She clearly has the space to do so, but she doesn’t have the
time. So let’s add a second dimension, one of time.
Time
(seconds)
Ms Point
.
Point A
Point B
.
Space
(feet)
9
While just how they are differently expressed is incidental to this argument, one way to think about it is that they
interact with matter and energy in opposite ways. Thus the difference between matter and energy depends on the
difference between space and time and vice versa.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
550
Now she has a place to go to and time to go there. So let’s let her go…
Time
(ten seconds) (0, 10)
(10, 10)
“Point” A
Ms Point
“Point” B
.
(0, 0)
.
Space
(10, 0)
… and let’s pretend that she goes there at the rate of one foot per second. Because B is ten feet
away from A, it should therefore take ten seconds for her to do so.
Some interesting things just happened.
First of all, point A and point B are no longer points. They do not move in space, but they do
exist (i.e. extend) in time, and, because they endure for ten seconds of time, they each form a line
through all the points in time between the first second and the last.10
Second, because her move required some time to occur – that is, involved movement both in
time and space, Ms. Point did not go horizontally to the point on this graph where point B was at
the beginning of her motion. Instead she moved diagonally, so that she arrived at where point B
is in space and time at the end of her journey. Point B has not changed its location in space, but
during her journey it has changed its location in time, and so, to get to point B, Ms. Point must
change position in both space and time – which is of course the definition of motion.
Finally, Ms. Point has changed as well. Despite her name, she no longer looks like a point; like
points A and B, she now looks like a line. She does so because she now exists – as a point – at
every point between A at time zero and B at time 10.11
But now we have a question:
Is Ms. Point a moving point, or is she a motionless line?
10
11
Specifically “Point” A is now the line from (0, 0) to (0, 10), and “Point” B is now the line from (10, 0) to (10, 10).
Specifically Ms. Point is now the Line from (0,0) to (10,10)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
551
Let’s look at the graph itself. If time is the vertical axis and space is the horizontal axis, and Ms.
Point exists as a point in every place along the line between (A,0) and (B,10). If so, in what way
is she not a motionless line?
All the information regarding her “motion” through time and space is on the graph. We have
direction, distance, and rate of speed. However, what we call “rate of speed” nonetheless
demonstrates no motion by itself. It is simply a ratio of the change in a spatial dimension versus
a change in a temporal dimension. This could be as easily a ratio of extension rather than motion.
The answer is of course, that this line represents a succession of moving points because of
corresponding movement in the dimension of space and of time. In short, if the line is really a
single moving point, it must move in time in order to move in space.
But if she is moving in time, how fast is she going?
In order to move, you must move at a certain rate of speed. We know the rate of speed in space;
it’s one foot per second. But what is the rate of speed through Time? One second per foot? But a
foot is not a unit of time; it is – of course – a unit of space. For her extension in time along the y
axis to actually be motion we need it measure it as time per unit of time – like “seconds per
second.” In other words we need yet another axis that permits motion in the way the time axis
does for space, in order to provide a rate of speed in the time dimension.
However, if we do so, once more we have the same problem. To be moving in that next
dimension of time, we would need yet another dimension that permits motion to have a rate of
speed, something like “seconds per second, per second.” In short, for every added dimension
that “permits motion,” we need yet another dimension of time in to permit that movement to
occur. If this is the case then, in order to move in any dimension, you need an infinite number of
dimensions of time.
The problem is more basic. The need for each new dimension actually represents a need for a
dimension in which motion is intrinsically possible without requiring another dimension. But
that is not what dimensions are. Dimensions are that which permits the identification of unique
location in space. But to be a unique location means not to be moving. Therefore, no matter how
many dimensions we add, we will never come to a dimension which by itself will permit points
to move. A series of points will always be a motionless, extended line.
And yet we can move. What’s the solution?
The dual nature of time
It is time to stipulate a second hypothesis.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
552
Hypothesis Part 2: The “passing” of time is simply extension in time and is
identical to extension in space. The universe is not three dimensional and
moving; it is four dimensional and static. 12 “Motion” is nothing more than
our experience of simultaneous extension in time and space.
Let’s look back at Ms. Point. Ignore the details. The essential idea is that, for this very simple
motion, this very simple graph provides a complete description. The math works; the physics
works; everything you can say about Ms. P’s motion is encompassed by this graph.13
But nothing has actually moved.
The description of motion is complete; but on our graph no movement exists. And, because there
is no motion, there is no problem with time. Once we make the choice to remove our idea of
motion from our understanding of time and to consider extension in time as simply that –
extension, not motion - then the problem of infinite regression goes away and we see that it is not
actually a problem at all. A rate of ten feet per second no longer demands any extra dimensions;
it is simply a ratio of two dimensions of extension
We can still plot orbits, navigate ships, aim projectiles, and throw baseballs. We have everything
that we need to measure and describe that which we experience as motion. All we need to do is
to is recognize that our motionless graphs and equations are not metaphoric descriptions of some
actually moving thing, but actual descriptions of the thing itself.
Only one thing is required: that we get rid of a belief that our experience of “something moving”
is actually “something out there.”
What is “out there” is a complex extended four-dimensional universe that obeys all the laws of
motion in three dimensions and time, but which does not actually move.
It’s not that the universe is somehow stuck. From the point of view of the universe, everything is
fine, thank you. Four-dimensional extension is all that the universe needs in order to be all that it
is. The problem is ours. Because we can describe verbally, depict graphically, and characterize
mathematically, that which we experience as motion; because those words graphs and
characterizations are consistent and have predictive value; and because our experience of motion
is so convincing - we therefore believe that our experience, and the real world substrate of that
experience, must be the same.
But it isn’t the same. It is in fact just an illusion – an experience produced by the brain.
12
We will ignore the question of multiple extra spatial dimensions predicted by string theory. The truth or
falseness of that idea does not change the argument.
13
Ok not everything. I have left out issues such as acceleration and deceleration, inertia and all the other variables
that govern real motion by real objects. However, each of these can also be described in graphs and formulae
which do not move and thus the point is not changed simply by being made complex.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
553
The Brain Problem
But that creates another problem. Perhaps the world is indeed four dimensional and static, but
our brain is part of the universe. And how can a four-dimensional static brain do anything –
much less produce experiences?
The answer is that it can’t. However something else can use the brain to produce experiences –
provided that that something is NOT a part of time and space. How does this work?
The self as “player” of the brain
Time for an analogy: let’s assume that we want to listen to some music. So we go to our CD
collection, take out a CD – let’s say Glenn Gould’s 1960 recording of the “Goldberg Variations,”
pop it into the player and settle back for a while to enjoy the performance. When we have done
so, let’s think for a moment about where and when the source for that music was, as opposed to
the music itself.
The source of the music was the CD, so let’s examine it carefully. On one side is just the label.
However, on the other side there is a faint circle, not quite a shiny as the rest of the disc,
extending from near the hole in the middle of the disc, out almost to the edge. Furthermore, if we
had a powerful magnifying glass, we might be able to see that what appears to be a circle is
essentially a long thin line. It is on this line that the information about the music is engraved as
little bumps which can be read by the laser in the CD player which can then translate that
information into sounds.
It isn’t a straight line. In order to fit on the CD, it has to be “wound” in a continuous spiral from
the center of the disc to its edge. But that is just a packaging decision. There is no fundamental
reason why, instead of a disk, the same line could not be printed as a straight line, many yards
long. So let’s think of it as a long straight line, extending in a single dimension: length.
The line is the source of the music. However the musical experience is something which the CD
player produced using the data from the CD. That experience also extended as a long line in a
single dimension. Only in the case of the experience, the dimension was not length, but time.
Because of its extension in time, we experienced that the music began, lasted for a while and
then came to an end.
But did the source of that music also begin and end?
Of course not; the question is meaningless. Throughout the experience, the parts of the CD
which contain the beginning, the middle and the end of the piece simply – and simultaneously –
existed. It was the CD player that took that motionless line and copied it from the dimension of
length to the dimension of time; the CD itself did nothing but contain the information.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
554
In the same way, the brain is the source of our experience, just as in our example of the CD, the
bumps on the spiral line of my CD are the source of the music. But in order for us to have the
experiences which the brain provides, we need something apart from the brain which can move
within present moment after present moment and translate the static patterns of its neurons into
subjective experience. In short we need a Self.
Hypothesis Part 3: All that we experience is produced by the self, “moving”
”within” our static four dimensional brain, following the present moment
down the dimension of time in the direction of the future.
However the analogy of the CD player leaves something out: the creative aspect of turning
neuronal patterns into experience. What is it that creates the peculiar, private and individual ways
in which we experience the universe? Why does chocolate taste like chocolate?
The self as the creator of experience, and the subject of experience.
In this sense the self is more like Glenn Gould, when he made the original recording. He did not
make the notes up; the decisions regarding which keys to push – how hard, in what order – were
made by Bach 300 years ago. Gould simply read those decisions on the motionless pages of
music in front of him.
But then Gould did two things: First, he created the music by executing those commands on the
piano keyboard; and then he experienced the music.14 In the same manner, the brain presents the
“musical score”- the substrate of experience; however it can neither create nor experience that
“music” – because like the motionless CD, it cannot of itself do anything. In order to create
experience, there must be a Self that both creates and experiences what is enabled by the brain.
Here is the point: This requirement, of “movement” of the self through the dimension of time in
series of present moments – something which objects in time and space cannot do – is thus not
simply one argument for the plausibility of a self that is not a part of space-time. It is an
argument for the necessity of such a self.
Which creates another problem.
The Problem of the Present
Just what do we mean by “the present moment?”15
14
That the two experiences – playing the music and hearing it – were really two experiences for him is clearly
demonstrated by the fact that, if you listen carefully to his first recording of the piece, made back in the 60’s, you
can hear him humming along to the tune he hears even as his fingers create it. However, although his playing is
brilliant, his humming is way off key.
15
In the ensuing discussion we will not get into issues raised by the question, in special relativity, of whether the
concept of “simultaneity” has real meaning and therefore whether it is possible to think of a “single” present
moment. Without going into needless detail, the simultaneity question has to do with situations in which two
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
555
The dictionary is at its customary loss in defining concepts which are unique unto themselves,
and winds up with tautological definitions such as “the present time.” In quantum physics the
present is that place in the space time continuum in which the collapse of the probability
equation occurs, wherein the collection of all possible future actions or motions of a fundamental
particle becomes the certainty of the single action that actually takes place - and which is now
located in the past. We will just simplify that thought and define the present moment as that
place in the dimension of time, moving in the direction of past to future, at which possible
futures become fixed histories.
But no matter how we define it, the fact that time seems to contain something with the
characteristics of a present moment at all is extremely odd.
Imagine the standard metaphor for time – a river. Let’s think of “Old Man River” who just keeps
rollin’ along. But what is a river? It is an extended stream, starting somewhere upstream flowing
down mountainsides, into the valleys and finally, somewhere downstream, reaching the ocean.
But where, in such an image, is there anything resembling a “Present?”
After all, the entire river doesn’t exist more in some places than in others; it exists everywhere all
at once. From source to delta it just is. In this image, the present might be like a boat on the river
floating down from the headwaters to the sea. However the boat, though moving on the river, is
not a part of it. The river has no particular special place; it is the boat which does.
In the same way, when we look either backward or forward in time, we see no special points
called present moments. All points are just points in time – except of course the one we happen
to be standing on “at that moment”. But what is it about this moment that makes it the present?
And what is it about the present that changes “from moment to moment” to move the present
down the direction of time.
But the present is a quality of time isn’t it. Or if it isn’t, then of what is it a quality and how does
it fit in to the rest of our understanding?
We need to look a little more closely at just what it is we mean by the self “moving” through the
brain and through time.
Here and Now
Let’s begin by thinking about how we actually experience time and space. When we do, we
notice something quite strange: though we remember the past, we are never in it; and though we
seem to move towards the future, we never get there. We know that we were in the past
yesterday, but then it wasn't the "past"; it was the present. We know we will be in the future
tomorrow but, when we get there, it won't be the future; it too will be the present.
different observers may perceive the same two events in reverse order – event A before event B for one observer
and event B before event A for the other. The answer is twofold: First, these are questions of perception and are
thus – in terms of this argument - experiential rather than external. Second, no two adjacent observers will have
such a disagreement; differences will only occur at distances further than information could travel within the time
necessary to confirm or deny simultaneity. In short, the “plane” of the present moment is bumpy but it is not torn.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
556
To say this more precisely, if our universe is really four dimensional and static, then our body
must extend in time from the past to the future. However, when we examine our body purely in
terms of time as a dimension, we can find nothing about it that distinguishes any particular
moment from any other. Our body existed yesterday; it exists today; hopefully it will continue to
exist tomorrow.
Yet for the self - the reverse is true. Nothing that we experience is in the past, or the future. For
us as the self, everything always happens Now.
Similarly, we are always Here. We can remember being downstairs, and when we go downstairs
we will remember being upstairs. However, when we are downstairs, then downstairs is here,
just as upstairs is here when we are upstairs. While our physical body is obedient to the laws of
the universe, our experiencing self is doing something utterly different. For us, “Then” and
“There” do not exist; all that exists is a boundless present moment, an eternal Here and Now.
Here and now are not experiences
But wait a minute, you may ask. How do you know that? Do we experience it? Do we remember
it? And if so, didn't you say that the brain produces all experiences and memories? Therefore,
isn't it the brain that produces that experience of here and now, that memory of the past, that
imagination of the future?
Again, no. Let’s look carefully at what we mean by "here and now." We can remember places
that once were "Here”; that memory is certainly produced by the brain. But do we experience
"Here" all by itself? What color is it? How does it taste? What does it look like? Also, now we
may be experiencing ourselves sitting in a chair, reading a book. But do we experience, "Now"
all by itself?
Here and Now are not objects to be experienced; they are not experiences at all. Instead they are
the context in which experiencing is accomplished. Just as we know that we have a self because
of the undeniable quality of having experiences, we know that we are here and now because
"Hereness" and "Nowness" are not just another experience, but characteristics of every
experience.
Hypothesis Part 4: The present moment is not a part of space time; it is
intrinsic to the self. It is the source of the moment to moment “Informational”
creation of the universe, and its simultaneous experience. The self occupies
neither the past nor the future but instead is the eternal present. And as such,
that eternal present moment is all that exists.
Another illustration: Imagine a circular quarter mile running track, just as you might find on the
playing field of any high school. Now let’s imagine that we step onto the track and begin to run.
As we run, we move around the track. However it is we that move, not the track. No matter how
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2012 | Vol. 3 | Issue 5 | pp. 543-557
Seward, P., What if Berkeley Had Gone to Berkeley? - Neurophysiology & Physics in the defense of Informational Idealism:
Part I: The Problem of Experience
557
fast we go or how far we run, the track itself is still. Furthermore, from the track’s point of view
(if it had one), there is no special point on it that is different from any other. It is just the track,
always the track, and nothing else but the track. Lots of people run on it, but there is nothing
special that differentiates any one person from any other.
On the other hand, from our point of view (and we do have one), there is a point on the track that
is special and unique. But our being at that particular point on the track is not special for the
track; it is only special for us. And the reason it is special and unique is the fact that we happen
to be there.
It isn’t even that the track that determines where we are. The track merely lends meaning to the
statement that we are at any moment at such and such a place. It is we who determine where we
are. Indeed the sentence is tautological; where we are is where we are.
In this analogy, the universe is the track. It does not include a special part called the present.
Instead, as we travel through time, it is we who bring with us an eternal present – that is, a
moment that is not a part of time. Here and now are eternal. But they are also instantaneous.
They occur in sequence along the dimensions of time and space But that sequence is created in
and by the present moment. It has no other meaning.
Finally – and very important, it is not just that an eternal present moment exists. It is all that
exists. Nothing else does.
We have no access to the past: all we have is our present memories. We have no access to the
future: all we have is our present capacity to anticipate. The illusion that we are moving through
time is simply due to the fact that reality is sequential, but only the present instance of that
sequence exists. The fact that past moments once existed is only manifest in the particular
configuration of the universe at this particular instant in time. The future has meaning only in
potentiality. But for all prior moments the torch has been passed. The torch exists in the form it
does because of those past moments, but they exist no more. Nothing exists but the present
moment.
But then did we not just say that the self was the present moment. Does that mean nothing really
exists but the self? Yet have we not also said that the universe was a static four-dimensional
reality that extended from the past to the future with no regard for a present moment?
Yes. And, yes.
But in order to see how that works, we have to talk a little more about reality. More specifically
we need to talk about reality as information.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Article
A Compositional Model of Consciousness based on
Consciousness-Only
Camilo Miguel Signorelli 1,2,∗ 0000-0002-2110-7646, Quanlong Wang 3,∗ , Ilyas Khan3,4,∗
1
arXiv:2007.16138v3 [q-bio.NC] 25 Feb 2021
2
3
4
*
Department of Computer Science, University of Oxford
Cognitive Neuroimaging Unit, INSERM U992, NeuroSpin
Cambridge Quantum Computing Ltd
St Edmund’s College, University of Cambridge
Email: cam.signorelli@cs.ox.ac.uk; harny.wang@cambridgequantum.com; ilyas@cambridgequantum.com
Received: date; Accepted: date; Published: date
Abstract: Scientific studies of consciousness rely on objects whose existence is assumed to be
independent of any consciousness. On the contrary, we assume consciousness to be fundamental,
and that one of the main features of consciousness is characterized as being other-dependent. We set
up a framework which naturally subsumes this feature by defining a compact closed category where
morphisms represent conscious processes. These morphisms are a composition of a set of generators,
each being specified by their relations with other generators, and therefore co-dependent. The
framework is general enough and fits well into a compositional model of consciousness. Interestingly,
we also show how our proposal may become a step towards avoiding the hard problem of consciousness,
and thereby address the combination problem of conscious experiences.
Keywords: Consciousness; Conscious Agents; Compositionality; Combination problem; Mathematics
of Conciousness; Monoidal Categories; Panpsychism.
1. Introduction
Despite scientific advances in understanding the objective neural correlates of consciousness [1],
science has so far failed in recovering subjective features from objective and measurable correlates
of consciousness. One example is the unity of consciousness. According to the phenomenology of
consciousness [2,3], one of the most salient features of conscious experience is its unity: "any set of
conscious states of a subject at a time is unified...by being aspects of a single encompassing state of
consciousness" [3]. If someone experiences colour and noise, the experience of colour is not followed by
the experience of noise separately, even though it might be sequential, but both are experienced together
as different aspects/content of one single conscious experience. Current models postpone the explanation
of that unity, assuming there will be further developments [4]. In the meantime, they reduce conscious
experience to neural events.
In this article, we present an alternative approach: consciousness as a fundamental process of
nature. Our approach takes inspiration from the Yogacara school [5,6], conscious agents model [7] and
phenomenology [8,9]. In our framework, subjectivity, a key feature of consciousness is characterised
as other-dependent or co-dependent, i.e. the nature of existence arising from causes and conditions
that are interdependent between each other. Without falling into idealism or dualism, we propose that
consciousness should be treated as a primary process.
To model the co-dependent nature, we propose a compositional model for consciousness. This
model is based on symmetric monoidal categories (Section 2), a.k.a Process Theory [10,11]. At the
core of process theory lies the principle of compositionality (Section 3). Compositionality defines the
2 of 21
whole as compositions of the parts. These parts, however, are not trivial decompositions, they contain
in themselves the very properties that define the whole (in our case, conscious processes compound
other conscious processes). Parts and the whole are therefore defined together, they co-depend.
Compositionality is thus a middle ground between reductionism and holism [12]. This makes process
theory and our compositional framework suitable for investigating the irreducible structural properties
of conscious experience [13].
Finally, our framework intends to mathematize a few aspects of the phenomenology of conscious
experience (Section 4) and target its major questions [14,15]. For instance, the unity of consciousness
naturally arises as result of composition, and the combination of fundamental experiences is discussed
in light of our framework (Section 5). This new perspective of scientific models of consciousness invokes
pure mathematical entities, avoiding any ontological claim of their physical substrates (Section 6).
2. Category Theory and Process Theory
In this section, we briefly introduce the basic notions of Category theory [16,17], process theory [11]
and graphical calculus [18].
2.1. Preliminaries
Category
A category C consists of:
• a class of objects ob(C);
• for each pair of objects A, B, a set C( A, B) of morphisms from A to B;
• for each triple of objects A, B, C, a composition map
C( B, C ) × C( A, B)
( g, f )
−→ C( A, C )
7→
g ◦ f;
• for each object A, an identity morphism 1 A ∈ C( A, A),
satisfying the following axioms:
• associativity: for any f ∈ C( A, B), g ∈ C( B, C ), h ∈ C(C, D ), there holds (h ◦ g) ◦ f = h ◦ ( g ◦ f );
• identity law: for any f ∈ C( A, B), 1B ◦ f = f = f ◦ 1 A .
A morphism f ∈ C( A, B) is an isomorphism if there exists a morphism g ∈ C( B, A) such that g ◦ f = 1 A
and f ◦ g = 1B . A product category A × B can be defined componentwise by two categories A and B.
Functor
Given categories C and D, a functor F : C −→ D consists of:
• a mapping
ob(C)
A
−→ ob(D)
7 → F ( A );
• for each pair of objects A, B of C, a map
C( A, B)
f
−→ D( F ( A), F ( B))
7→
F ( f ),
3 of 21
satisfying the following axioms:
• preserving composition: for any morphisms f ∈ C( A, B), g ∈ C( B, C ), there holds F ( g ◦ f ) =
F ( g ) ◦ F ( f );
• preserving identity: for any object A of C, F (1 A ) = 1 F ( A).
A functor F : C −→ D is faithful (full) if for each pair of objects A, B of C, the map
C( A, B)
f
−→ D( F ( A), F ( B))
7→
F( f )
is injective (surjective).
A bifunctor (also called binary functor) is just a functor whose domain is the product of two
categories.
Natural transformation
Let F, G : C −→ D be two functors. A natural transformation τ : F → G is a family (τA : F ( A) −→
G ( A)) A∈C of morphisms in D such that the following square commutes:
F ( A)
τA
G( f )
F( f )
F( B)
G ( A)
τB
G ( B)
for all morphisms f ∈ C( A, B). A natural isomorphism is a natural transformation where each of the
τA is an isomorphism.
Strict monoidal category
A strict monoidal category consists of:
• a category C;
• a unit object I ∈ ob(C);
• a bifunctor − ⊗ − : C × C −→ C,
satisfying
• associativity: for each triple of objects A, B, C of C, A ⊗ ( B ⊗ C ) = ( A ⊗ B) ⊗ C; for each triple of
morphisms f , g, h of C, f ⊗ ( g ⊗ h) = ( f ⊗ g) ⊗ h;
• unit law: for each object A of C, A ⊗ I = A = I ⊗ A; for each morphism f of C, f ⊗ 1 I = f = 1 I ⊗ f .
Strict symmetric monoidal category
A strict monoidal category C is symmetric if it is equipped with a natural isomorphism
σA,B : A ⊗ B → B ⊗ A
4 of 21
for all objects A, B, C of C satisfying:
σB,A ◦ σA,B = 1 A⊗ B , σA,I = 1 A , (1B ⊗ σA,C ) ◦ (σA,B ⊗ 1C ) = σA,B⊗C.
Strict monoidal functor
Given two strict monoidal categories C and D, a strict monoidal functor F : C −→ D is a functor
F : C −→ D such that F ( A) ⊗ F ( B) = F ( A ⊗ B), F ( f ) ⊗ F ( g) = F ( f ⊗ g), F ( IC ) = ID , for any objects A, B
of C, and any morphisms f ∈ C( A, A1 ), g ∈ C( B, B1).
A strict symmetric monoidal functor F is a strict monoidal functor that preserves symmetrical
structures, i.e., F (σA,B ) = σF ( A),F ( B). The definition of a general (non-strict) symmetric monoidal functor
can be found in [17].
Strict compact closed category
A strict compact closed category is a strict symmetric monoidal category C such that for each object
A of C, there exists a object A∗ and two morphisms
ǫ A : A ⊗ A∗ → I, η A : I → A∗ ⊗ A
satisfying:
(ǫ A ⊗ 1 A ) ◦ (1 A ⊗ η A ) = 1 A , (1∗A ⊗ ǫ A ) ◦ (η A ⊗ 1∗A ) = 1∗A .
A strict compact closed category is called self-dual if A = A∗ for each object A [19].
2.2. Process Theory
Process theory is an abstract framework of how things happen, be they mental or physical and
regardless of their nature. Process theory describes how processes are composed. It has been widely
used in various research fields such as the foundations of physical theories [20], quantum theory [19,21],
causal models [22,23], relativity [24] and interestingly also natural language [25] and cognition [26,27].
In common with all theories, process theory has its own assumptions, albeit with the advantage that its
major feature is that it contains minimal assumptions.
In process theory, we first assume an event occurs, i.e., a change from something typed as A to
something typed as B. This is called a process and denoted as a box:
A
f
B
Second, we assume somethings happen sequentially, such as a process g happens before another
process f :
C
g
A
f
B
5 of 21
f happens after g can be seen as a single process from type C to type B, which is denoted by f ◦
g : C → B. This is called sequential composition. As such, three things happening in sequence is
seen as one process without any ambiguity, i.e., the sequential composition of processes is associative:
( f ◦ g) ◦ h = f ◦ ( g ◦ h). We also assume that for each type A, there exists a process called the identity 1 A ,
which does nothing at all to A. This is depicted as a straight line:
A
As a consequence, given a process f : A → B, we have 1 B ◦ f = f = f ◦ 1 A .
Third, we assume that there should be different processes happening simultaneously. Two processes
f and g that happen simultaneously are described as:
C
A
g
f
B
D
If we view two types, say A and C, as a single type which we denote as A ⊗ C, then the simultaneous
processes f and g is a single process from type A ⊗ C to type B ⊗ D, that we denote as f ⊗ g : A ⊗ C →
B ⊗ D. We call this a parallel composition of processes.
The above depiction of f ⊗ g is asymmetric: f on the left while g on the right. This is due to the
limitation of a planar drawing. If we want two processes that occur simultaneously placed in a symmetric
way, it would mean that if we swap their positions, they should be essentially the same where all the types
should match. This can be realised by adding a swap process:
A
B
B
A
such that
g
f
C
D =
B
C
A
C
A
A
g
f
B
B
D
D
With these basic assumptions, processes can be organised into what is called a process theory in the
framework of a strict symmetric monoidal category (SMC). A much more detailed description of process
theory can be found in [19].
To relate sequential and paralell composition in a simple way, one can add the compact structure to
s
s
, so that:
the process theory by using caps
and cups
s
s
A
f
=
B
g
C
A
f
B
C∗
g
C
B∗
Mathematically speaking, we now have a compact closed category.
6 of 21
As introduced above, process theory focuses on the processes instead of the objects/types, providing
a philosophical advantage: process theories emphasise transformations, avoiding any ontological claim
or substance-like description of invariant properties of those types, like mass and charge.
2.3. Fine-grained Version of Process Theory
In general process theory, most of the boxes (processes) are unspecified in the sense that what
is inside a box is unknown, whereas we need to know more details about their interactions in some
applications. In other words, we need a fine-grained version of process theory. The typical way to
derive such a version is to generate all the processes by a set of basic processes called generators,
while specifying those generators in terms of equations of processes composed of generators. Below,
we illustrate this idea by a typical example called ZX-calculus.
ZX-calculus is a process theory invented by Bob Coecke and Ross Duncan as a graphical language
for a pair of complementary quantum processes (represented by two diagrams called green spider and
red spider respectively) [18]. All the processes in ZX-calculus are diagrams composed sequentially or in
parallel, either of green spiders with phase parameters, red spiders with phase parameters, straight lines,
swaps, caps or cups.
These generators satisfy a set of diagrammatic equations called rewriting rules: one can rewrite each
diagram into an equivalent one by replacing a part of the diagram which is on one side of an equation
with the diagram on the other side of the equation. All the ZX diagrams modulo 1 and the rewriting rules
form a self-dual compact closed category [18]. To guarantee that there are no conflicts in this rewriting
system, ZX-calculus needs a property called soundness: there exists a standard interpretation from the
category of ZX diagrams to the category of matrices, i.e., a symmetric monoidal functor between them
[18]. More general, a sound rewriting system means that there are not internal contradictions, while
completeness would mean that we can prove anything that is right about the phenomena in question
with the chosen system. A sound and complete rewriting system defines a unique set of generators.
3. Compositional approach for consciousness-only
In this section, we motivate and explain the concepts of consciousness as fundamental and also the
structure for consciousness given by the Yogacara School.
3.1. Process Theory for consciousness
In any attempt to model consciousness, we expect to fulfill at least three theoretical requirements.
First, one would like a theory with a basic and minimum set of assumptions. Process theory seems to
fit with that requirement. Symmetric monoidal categories start from a minimum and specific intuitive
form to deal with compositions, sequential and parallel. In the rest of this work, we will assume that this
minimal structure already convey part of the experience structure. This assumption is partially justified in
the fact that, despite a unified experience, we only experience things happening in sequence (one after
the other, time) or in parallel (side by side, space).
Second, one would expect those minimum assumptions to be explicit. In other words, we need to
model the nature of consciousness from explicit, primitive and axiomatic principles. Process theory in
particular, and category theory in general, provides us with an exceptionally well suited mathematics for
such axiomatic purposes. Due to the minimality of those assumptions, any extra structure to be added to
a process theory will also have an explicit mathematical meaning.
1
Modulo means using an equivalent relation.
7 of 21
Third, one would like to recover and describe important properties of consciousness from those basic
and explicit axioms. Specifically, we would like to recover the unity of consciousness. In process theory,
compositionality outlines any unity as a non-trivially composition of some basic processes [10,11]. Unity
is formed by sequential and parallel compositions of primary processes. Due to this foundational aspect,
compositionality may be a convenient way to target the unity of consciousness, by modelling the unity
of experience inside a process theory (section 5).
3.2. Consciousness as Fundamental
Natural science has achieved great success in modern age, behind which there lies a basic
assumption that everything is made of physical objects whose existence is independent of any
consciousness. This assumption is so powerful that renders scientific theories not too complicated and
allows science results to be tested by independent experiments. However, such objective existence can
never be verified by conscious agents, since most cognitive activity is done through consciousness [28],
thus the assumption is totally suspended.
Objectivity relates to a perceived or unperceived object, while subjectivity to a perceiving subject.
In a everyday understanding of the terms, the object is meant to exist independently of any subject
to perceive it (ontology), and as such, objectivity is commonly associated with concepts like truth and
reliability (epistemic) [29,30], e.g. the visible wavelength of light range from 700nm to 400nm. Contrary,
subjectivity seems always interdependent, it involves both perceived and perceiving aspects, making
subjective properties dependent of others interactions (internal or external to the subject) and thereof
co-dependent [12]. We can further distinguish between epistemic subjectivity, i.e. claims not verifiable
(e.g. the claim that red is more beautiful than green), and ontological subjectivity [30]: subjective modes
of existence, such as pain or "redness" experienced only by the subject.
In order to understand our point of departure, we first need to recognize that objectivity is an
assumption of basic science. The assumption of objectivity as primitive or fundamental is deeply
grounded in neuroscience, as well as other scientific fields [31–33]. Taking that assumption, one would
expect that the subjective aspects of the experience may naturally emerge from the interaction and
combination of physical objective entities. For example, contemporary theories of consciousness tend
to focus on the physical atomic parts from which, for instance, the unity of experience would emerge
as a whole. The parts are considered cells, neurons, brain regions, and the whole being the unified
conscious experience. This is called building blocks models [2] or reductionist approaches [32]. This
approach, however, leads to the hard problem of consciousness [2,34,35]: since each neuron is composed
of basic physical objects–atoms, and they are radically different from consciousness in that they lack key
features of the latter like self-awareness and unity [2,3], no matter how complicated the interaction of
these physical parts could be, how can those key features of consciousness arise from them? At this
point, we consider the reader is familiar enough with this problem, so that we can avoid any deeper
introduction.
An alternative assumption is to treat conscious experience as primary, or fundamental process
of nature. We assume that all primary objects are indeed conscious-dependent. Treating conscious
experience as primary convey two possible interpretations: i) ontological, i.e. the nature/existence of
consciousness is fundamental (substance), ii) epistemic, i.e. the nature of knowledge about the world
is limited by our experience. In this line of thoughts "our knowledge is limited to the realm of our
own subjective impressions, allowing us no knowledge of objective reality in and of itself" [9,29]. In
this paper, we are neutral about what is the optimal interpretation. Independently, we emphasize that
conscious experience is a primary process of nature, a transformation. Being fundamental would also
means that there is not further explanation. Therefore, physical objects would be the result of consciousness
8 of 21
transforming and everything considered, affirmed or denied, even the idea of objectivity, would occur to
us only in consciousness.
Although the new assumption dissolves or evades the hard problem of consciousness, it comes with
what we call the dual problem of consciousness: the question about how the objective realm arise from
subjective one. To deal with that problem and model conscious experience from the assumption of the
primacy of consciousness, we take inspiration from the Eastern philosophy known as Yogacara.
3.3. Yogacara Philosophy
The reason to choose the Yogacara philosophy and its phenomenology is mainly because it
has an explicit description of a structure of eight types of consciousnesses and the relation between
consciousness and the physical world. Moreover, the key feature of the Yogacara philosophy is
consciousness-only which means there is nothing outside of all sentient beings’ consciousnesses. In
modern words, consciousness-only would be better understood as a claim of awareness-only, or
perception-only, much closer to modern phenomenology [5,36,37].
The Yogacara philosophy has a rich system of eight consciousnesses consisting of: the first seven
consciousnesses—the five sense-consciousnesses (eye or visual, ear or auditory, nose or olfactory, tongue
or gustatory, body or tactile consciousnesses), mental consciousness (the sixth consciousness), manas
consciousness (the seventh or thought-centre consciousness), and the eighth consciousness—alaya
consciousness (storehouse consciousness). These eight consciousnesses are not independent of each
other: "... the Alaya consciousness and the first seven consciousnesses generate each in a steady
process and are reciprocally cause and effect" [38]. A clarifying metaphor is to think about the eighth
consciousness as the ocean, while the other consciousness are different types of waves in its surface.
Neither of them are separated of the others and all consciousness are essentially one.
In this framework, the act of perception of the eighth consciousness (Alaya consciousness) is
considered extremely subtle or difficult to perceive [39]. Alaya consciousness is thought to be the seed
consciousness, i.e. to contain on its own different potentialities that would engender other complex types
of experiences [5,39]. We will approach these potentialities only in relation with other seeds, leaving the
types on our process theory for Alaya consciousness unspecified 2 . This might be an economical strategy,
since, although this structure is considered the same for all living beings, the input and outputs types for
those processes might be species dependent, or even specific to each individual.
Moreover, each consciousness "manifests itself in two functional divisions (bhgas), namely, image
and perception, i.e., the object perceived or perceived division and the perceiving faculty or perceiving
division (nimittabhaga and darsanabhaga)" [39]. The perceived is related to the object and the perceiving
to the subject. In Husserlian phenomenology, this division is extrapolated to what is called Noema
versus Noesis distinction [40]. The first division is mostly related to the sixth consciousness and the
five perceptual consciousnesses, while the second one with the seventh manas consciousness.
The phenomenon of the physical world and the body which we feel everyday comes from the
perceived division of Alaya consciousness: "it transforms internally into seeds and the body provided
with organs, and externally into the world receptacle. These things that are its transformations become
its own object of perception (dlanzbana)" [38]. The receptacle-world and the Body as part of the perceived
division of Alaya consciousness should not be thought of as the physical world and the physical body
that we feel in our normal lives, but as being related in that the appearance of the latter is based on the
2
A future approach may define the internal structure of Alaya taking six features in formal analogy with the seed metaphor from
[39].
9 of 21
existence of the former. As a consequence, the objectivity of the world comes from the same structure
shared by different sentient beings in the perceived division of their Alaya consciousnesses.
In the rest of this work, we will focus on a simple model for the perceived and perceiving division
of Alaya consciousness. In order to have a model of this structure, we highlight three key ideas: i) Alaya
consciousness is very subtle and it is only shown before us as co-dependent or interdependent process, ii)
Alaya consciousness is primary/fundamental, from which other consciousness and the physical world
may arise, iii) Specifically, the physical world arise from the perceived division of Alaya consciousness.
4. Compositional Model for Consciousness-Only
After the discussion in section 3, we now provide a compositional model of consciousness based on
the Yogacara philosophy of consciousness-only and a few further assumptions.
4.1. Process Theory for Alaya Consciousness
The first feature of Alaya consciousness is its co-dependence, which means each process of Alaya
consciousness is dependent on other processes. The general process theory can not display the
other-dependence feature because most of its processes are not specified (see section 2.3). So we need
a fine-grained version of process theory which has generators specified by explicit rewriting rules. We
might also choose these generators for non-classical systems. This choice is partially justified by recent
models of psychology and cognition that seems to be quantum related [41,42]. Moreover, we also require
that any parameter appeared in the theory is not a concrete number, according to the unspecification of
the types we discussed above.
Based on the requirements for a fine-grained process theory that are noted in previous sections, we
introduce a formalism called qufinite ZX∆ -calculus, which is a generalisation of the normal ZX-calculus
[18] regarding the following aspects: 1) a labelled triangle symbol is introduced as a new generator, that’s
why there is a ∆ in the name of the generalised ZX-calculus, 2) all the qudit ZX-calculus (ZX-calculus for
qudits– quantum versions of d-ary digits) are unified in a single framework, 3) the parameters (phases)
of normal ZX-calculus are generalised from complex numbers to elements of an arbitrary commutative
semiring.
We give the details below of the qufinite ZX∆ -calculus: generators and rewriting rules. Throughout
this section, N = {0, 1, 2, · · · } is the set of natural numbers, 2 ≤ d ∈ N, ⊕ is the modulo d addition, S
is an arbitrary commutative semiring [43]. All the diagrams are read from top to bottom as in previous
sections.
4.1.1. Generators of Qufinite ZX∆ -calculus
We give the generators of the qufinite ZX∆ -calculus in Table 1.
10 of 21
n
n
...
−
→
αd
...
...
d
...
m
m
dj
d
d
s
s
s
t
s
s
s
t
st
s
st
t
→ = ( a , · · · , a ); a ∈ S ; i ∈ {1, · · · , d −
Table 1. Generators of qufinite ZX∆ -calculus, where m, n ∈ N; −
α
1
i
d
d −1
1}; j ∈ {0, 1, · · · , d − 1}; s, t ∈ N\{0}.
Remark 1. Each input or output of a generator is labeled by a positive integer. For simplicity, the first four
generators have each of their inputs and outputs labelled by d, and we just give one label to a wire.
For simplicity, we use the following conventions:
...
...
:=
d
−
→
1d
...
dj
d
:=
dj
...
and
dj
dj
:=
dk
−
→
e d−−
k
:=
d
· · · · ·
·
·
· :=
·
ε:
·
·
· · · · ·
d −1
d −1
z
}|
{
z }| {
−
→
→
e−
· · · , 1, · · · , 0); ε
where 1 d = (1, · · · , 1); j ∈ {0, 1, · · · , d − 1}; k ∈ {1, · · · , d − 1}; −
d − k = (0,
| {z }
d−k
represents an empty diagram.
In terms of consciousness interpretation, each generator may be thought as a basic or primary
conscious experience. Then, the set of generators becomes a minimal set of experiences. This selection is
not unique, unless the group of generators is sound and complete, as we mentioned in section 2.3.
11 of 21
For example, we may consider that basic conscious experiences involve many inputs and outputs
n
...
−
→
αd
...
types. This is realized by the many legs on
m
adding types might be described by d
n
...
and
. The experience of
d
...
m
and perhaps primary perception realized by the process
dj
. The experience of inverting types might correspond to caps and cups, combinations and segregation
experiences may be represented by each of the rhomboids, respectively.
The concrete specification of these or other generators is an empirical task that we left for future
works with trained phenomenologists. In our framework, some experiences that are considered basic,
such as seeing red or hearing a monotone sound may indeed be the result of composition from our chosen
set of generators or another set. This is due to the particular choice we have made. Moreover, one can also
choose those monotone experiences (as far as one can give them explicit mathematical meaning) as part of
another particular set of generators. The question of what is the unique set of phenomenal generatores is
empirical and theoretical issue that may require attentive phenomenology and micro-phenomenological
tools. In that case, the goal is to target the soundness and completeness of rewriting systems for conscious
experience. Something far beyond the scope of our preliminary attempt.
4.1.2. Rules of Qufinite ZX∆ -calculus
We provide rewriting rules for qufinite ZX∆ -calculus in Figure 1 and Figure 2. Even though we
do not specify which generator corresponds to each basic phenomenal experience, these rules specify the
generators in light of what they do regarding each other. Concretely, here we focus on the idea that two or
d
d
d d
more generators define each other. For example, the green dot
is specified by the rule
d =
in the way that it is the only green spider which has no input and one output and can be copied by the
red spider
d
. Moreover, the red spider
d
is also specified by the effects in the green dot
d
.
It means that the experience of A, only makes sense if there is another experience B, from which one has
a relationship with the other. For instance, the experience of the colour red only make sense if there is
another experience of colour, for example, green and blue, otherwise there is not such colour experience
at all, or at least, it is of very different nature (e.g. colour blindness). This is understood as a kind of
contextual character of conscious phenomena, a particular aspect of experience.
These rewriting rules become the axioms regarding a group of primary experiences, and further
ways to define the generators in relation with their consciousness interpretation. In the example above,
the red spider with many legs may convey the experience of copy the experience from the green
one. Again, specific phenomenal interpretations are left for future works, while we focus here on the
introduction of the main concepts and the mathematical machinery.
12 of 21
...
...
...
...
−
→
α
d
...
−
→
βd
=
d
...
d
...
...
d
...
d
...
=
=
d
...
=
d =
di
=
dj
...
d
...
d
d
=
d d
d
d
=
d d
d0 =
d
d
=
d
...
−−→
αd β d
...
...
...
...
...
−−→
αd β d
di⊕ j
...
=
d
...
d
d
d
d
dj
=
d
d
=
d
...
d
dj
m
· · · · ·
·
·
= ·
·
·
·
−
→
· · · · ·
α
d
d
m
dj
d
dj
...
=
d
dj
=
d
dj
→
−−→
→ = ( a , · · · , a ); −
Figure 1. Qufinite ZX∆ -calculus rules I, where −
α
1
d
d − 1 β d = ( b1 , · · · , b d − 1 ) ; α d β d =
( a1 b1 , · · · , ad−1 bd−1 ); ak , bk ∈ S ; k ∈ {1, · · · , d − 1}; j ∈ {0, 1, · · · , d − 1}; m ∈ N.
13 of 21
d
=
d
d
d
d
d
=
d
d
d
d
=
d
−
→
α
d
d
d
d
d
d
d
d
d
d
d
d
d =
d
d d
d
=
d
−
→
α
d
d
−
→
βd
s
st
=
t
→
−
→+ −
α
d βd
d
d
s
d
d
d
−
→
α
d
d
d
d
=
d
−
→
α
d
d
−
→
0d
αd + 1d
dj
=
d
= −
→
→ −
−
→
α
d
d
dj
d
t
=
st
st
s
st
s
t
t
st
s
t
st
stu
s
u
=
u
t
tu
stu
s
st
t
=
st
st
d −1
d −1
z }| {
z }| { −
−
→
→
→
α
Figure 2.
Qufinite ZX∆ -calculus rules II, where 1 d = (1, · · · , 1); 0 d = (0, · · · , 0); −
d
−
→
( a1 , · · · , ad−1 ); β d = (b1 , · · · , bd−1 ); ak , bk ∈ S ; k ∈ {1, · · · , d − 1}; j ∈ {1, · · · , d − 1}; s, t, u ∈ N\{0}.
=
14 of 21
Additionally, in order to form a compact closed category of diagrams, we also need the following
structural rules:
s
s
=
s
s
s
s1 s2
...
u =
sk
s =
s
u
= s
t1 t2
s
s
=
u
...
u
tl
t1 t2
s
(1)
t
...
u
...
tl
sk
s1 s2
...
...
tl
sk
s1 s2
u
u
...
where
s
s
...
t1 t2
s
s
sk
s1 s2
u
s
=
t1 t2
tl
t =
s
s
t
s
t
(2)
sk
s1 s2
...
...
t1 t2
tl
is an arbitrary diagram in the qufinite ZX∆ -calculus.
The first two diagrams in equation (1) mean the cap ηs and the cup ǫs are symmetric, while the
last diagram means the connected cap and cup can be yanked. The first two diagrams of equation (2)
mean any diagram could move across a line freely, representing the naturality of the swap morphism.
The last diagram of equation (2) means the swap morphism is self-inverse. Note that now we have
a self-dual compact structure rather than a general compact structure, which makes representation of
diagrams much easier.
From the rewriting rules noted above, we form a strict self-dual compact closed category Z of ZX
diagrams. The objects of Z are all the positive integers, and the monoidal product on these objects are
multiplication of integer numbers. Denote the set of generators listed in Table 1 as G. Let Z [ G ] be a free
monoidal category generated by G in the following way - i) any two diagrams D1 and D2 are placed
side-by-side with D1 on the left of D2 to form the monoidal product on morphisms D1 ⊗ D2 , or ii) the
outputs of D1 connect with the inputs of D2 when their types all match to each other to form the sequential
composition of morphisms D2 ◦ D1 . The empty diagram is a unit of parallel composition and the diagram
of a straight line is a unit of the sequential composition. Denote the set of rules listed in Figure 1, Figure
2, equations (1) and equations (2) by R. One can check that rewriting one diagram to another diagram
according to the rules of R is an equivalence relation on diagrams in Z [ G ]. We also call this equivalence
as R, then the quotient category Z = Z [ G ]/R is a strict self-dual compact closed category. The qufinite
ZX∆ -calculus is seen as a graphical calculus based on the category Z.
4.2. Standard interpretation of qufinite ZX∆ -calculus
To ensure that qufinite ZX∆ -calculus is sound, we need to test its rules in a preexisting reliable
system which we now describe. These interpretations, however, does not represent the explicit meaning
in terms of our consciousness processes. They are given here to test soundness.
Let MatS be the category whose objects are non-zero natural numbers and whose morphisms
M : m → n are n × m matrices taking values in a given commutative semiring S . The composition
15 of 21
is matrix multiplication, the monoidal product on objects and morphisms are multiplication of natural
numbers and the Kronecker product of matrices respectively. Then MatS is a strict self-dual compact
closed category. We give a standard interpretation, namely J·K, for the qufinite ZX∆ -calculus diagrams in
MatS :
u
}
n
w
w
w
w
w
w
w
v
u
u
u
v
}
d
...
m
n
w
w
w
w
w
w
w
v
...
d
...
m
}
|i1 , · · · , im i h j1 , · · · , jn | ;
=
∑
0≤ i1 ,··· ,i m ,j1 ,··· ,jn ≤ d −1
~ i1 +···+im ≡ j1 +···+ jn ( mod d)
d −1
w d
v j ~ = ∑ | i i hi ⊕ j | ;
s
st
u
w
w
v
}
t~
i =0
t
|
d
u
s −1 t −1
v
= ∑ ∑ |kt + l i hkl | ;
k =0 l =0
}
s −1 t −1
= ∑ ∑ |kl i hlk| ;
~
k =0 l =0
s
d −1
⊗m
⊗n
= ∑ a j |i i hi | ; a0 = 1; ai ∈ S ;
i =0
~
...
−
→
α
t
s
s
d −1
= |0i h0| + ∑ (|0i + |i i) hi | ;
i =1
s
}
st ~
k
= ∑ [ ]
t
k =0
{
= ∑ | i i |i i ;
t
s
JD1 ⊗ D2 K = JD1 K ⊗ JD2 K;
d
st −1
s −1
i =0
u
v
d
}
k
k − t[ ] hk| ;
t
s
d −1
~ = ∑ | i i hi | ;
s
s
{
i =0
t· · · · ·|
·
·
· = 1;
·
·
·
· · · · ·
s −1
= ∑ hi | hi | ;
i =0
JD1 ◦ D2 K = JD1 K ◦ JD2 K;
d
z
}|
{
}|
{
z
where s, t ∈ N\{0}; hi | = (0, · · · , 1, · · · , 0); |i i = ((0, · · · , 1, · · · , 0)) T ; i ∈ {0, 1, · · · , d − 1}; and [r ] is the
| {z }
| {z }
i +1
i +1
integer part of a real number r.
One can verify that the qufinite ZX∆ -calculus is sound in the sense that for any two diagrams
D1 , D2 ∈ Z, D1 = D2 must imply that JD1 K = JD2 K. This standard interpretation J·K is actually a strict
symmetric monoidal functor from Z to MatS .
According the standard interpretation, if S is the field of complex numbers, then the green spider
corresponds to the computational basis |i i}di=−01 , with d − 1 phase angles. The red spider corresponds to
the Fourier basis coming from Fourier transformation of the computational basis, up to a global scalar.
The red d j diagram represents the j-th unitary which is also a permutation matrix, with j ranging from 0
to d. The triangle diagram labelled with d acts as a successor of phase parameters (adding 1’s to them).
The two trapezium diagrams represent unitaries between the Hilbert space of Hs ⊗ Ht and the Hilbert
space Hst , these two diagrams are invertible to each other.
16 of 21
4.3. The perceived division of Alaya Consciousness
Now, we model the perceived division of Alaya consciousness. As we have introduced in section
3.3, the content of the perceived version of Alaya consciousness is the phenomenon of the physical world
and the body which is supposed to have the same mathematical structure for all sentient beings in this
world (not necessarily the same types, which may bring specificity and a treatment for individuality).
Since each physical object is supposed to be composed of quantum systems, the perceived version of
Alaya consciousness is modelled here by the category FdHilb: the category whose objects are all finite
dimensional complex Hilbert spaces and whose morphisms are linear maps between the Hilbert spaces
with ordinary composition of linear maps as compositions of morphisms. The usual Kronecker tensor
product is the monoidal tensor, and the field of complex numbers C (which is a one-dimensional Hilbert
space over itself) is the tensor unit. FdHilb is the category of quantum processes which composes the
physical world. Since the body is a part of the physical world, the body part of the perceived division of
alaya consciousness may be modelled by a subcategory of FdHilb.
4.4. The perceiving division of Alaya consciousness
The function of the perceiving division of Alaya consciousness is to perceive the perceived division,
which means a perceiving action from the subject (perceiving) to the object (perceived) of the Alaya
consciousness. Since a functor is a structure preserving map or transformation from one category to
another one, our first attempt is to model the perceiving division of Alaya consciousness by a functor
from Z to FdHilb. This functor is set up as a modification of the standard interpretation functor J·K, i.e.:
just choose a semiring homomorphism f from S to C and let {|i i}di=−01 a standard basis of a Hilbert space
with dimension d, then replace ai with f ( ai ) in the codomain of the interpretation J·K. One can check that
a monoidal functor is obtained in this way, where a semiring homomorphism from S to C is selected.
5. The Unity of Experience
As a consequence of our first simple approach to model conscious experience, we consider the
combination problem of the unity of experience.
We suggest that some aspects of Alaya consciousness can be modelled by qufinite ZX∆ -calculus,
making it a serious and somewhat justified attempt. A general diagram represents some primary
conscious experience and a diagram with outputs but without inputs represent a state of consciousness.
Sequential composition of two diagrams represents two successive conscious processes happening
one after the another, while parallel composition of two diagrams represents two conscious processes
happening simultaneously. These processes may compound to generate more complex experiences.
Our approach is an alternative to conserve the irreducible and fundamental nature of experience.
It is not, however, the only one. Panpsychism and Panprotopsychism, among others philosophies, also
consider experience seriously, but these two assigns a quantifiable character to that experience. According
to these views, consciousness is present in all fundamental physical entities [44] and the composition of
basic blocks of experience creates our conscious experience.
Nevertheless, an important question remains for those irreductible attemps:
How
"microphenomenal seeds of consciousness" constitute macrophenomenal conscious experiences as
we experience them? —the so-called combination problem for Panpsychism and Panprotopsychism
[45]. This problem convey an specific form of the hard problem of consciousness, i.e. how could the key
features of consciousness, like its unity, arise from any kind of interactions of physical atomic experiences
(given by physical theory of your choice), no matter how many of these atoms and how complicated the
interactions are, which have none of those key features? [2,34,35]. In other words, how these building
blocks of experience compound one single unified macro phenomenal subjective experience [3]: the
17 of 21
phenomenal unity of experience [3,46]. In Panpsychism and Panprotopsychism, the dualism between
mind and matter is now replaced by two modes, micro and macro experience, of the same ontology.
Remarkable, the combination problem has three aspects [45]: structural, subject and quality. Each
one of these aspects leads to a specific sub-problem. On the one hand, the structure of the micro world,
mostly associated with quantum mechanics, gives the impression of being different from the structure
of macro experiences. This is the structural mismatch problem, which also appears between macro
experience structure and macro physical structures in the brain [45]. On the other hand, there is the
question of how micro subject combine to give rise to macro subjects, and how micro qualities combine
to give macro qualities. It seems that no group of micro subjects need the existence of a macro subject,
and additionally, it is not clear how possible limited micro qualities yield to the many macro qualities
that can be experienced, including different colors, shapes, sounds, smells, and tastes (for detail see
[45]). According to Chalmers, a satisfactory solution of the combination problem must face all these
three aspects.
Our framework targets all of these aspects of the combination problem. First, the mathematical
structure of the qufinite ZX∆ -calculus for Alaya consciousness is a unification of all dimensional qudit
ZX-calculus. If generators are interpreted in Hilbert space, the latest becomes a graphical language for
quantum theory. This means that the ZX∆ -calculus for conscious processes shares a similar structure
to quantum theory 3 . This similarity solves the mismatch at the level of micro experience, without any
ontological commitment to quantum particles (e.g. different to Hameroff and Penrose model [47]). At the
level of macro experiences we avoid any match or mismatch with macro physical structures because the
model does not reduce experience to neural events (non-isomorphic relationship). It means that conscious
experience does not need to share the same structure that classical neurons. Second, the model does
not distinguish between subject and quality, everything is a conscious process, a conscious experience.
Those fundamental conscious processes of reality, namely the generators of the theory, compound other
conscious processes just by means of connecting them together: via sequential and parallel composition.
The result of those compositions are other more complex subjective and qualitative processes. New
compounded processes depend on the basic generators, while the generators are interrelated to define
themselves via rewriting rules (axioms), representing more complex experiential relationships; i.e. each
process need other processes to specify itself.
In our framework, unity of consciousness is naturally described as a result of process composition
[48]. If someone insists on generators being matched with subjects or agents, then micro (generators)
and macro subjects (composition of generators) necessitate themselves as imposed by the co-dependent
nature. This deals with the problem of subject/quality composition at the level of Alaya consciousness
(please check [45] for details). This treatment also allows to deal with the combination of specific qualities
as the result of compositions in the seventh mental consciousness, work that form part of an ongoing
project.
Summarizing, while in Panpsychism the division between micro and macro is given by physical
systems (e.g. atoms versus neurons, or neurons versus neural assembles), in our framework there is
no such distinction. The distinction just vanish, since we consider generators that already carry the
properties of the whole (experience), following the compositionality principle. The choice of generators
might seems arbitrary, and it is, as far as we do not have a sound and complete rewriting system for
conscious experience.
3
Please note that a similar structure means similar mathematical relationships. Two very different phenomena in nature may
share the same structure and being modelled by the same equations, or more generally, the same categories.
18 of 21
6. Conclusions
Our framework is based on arbitrary commutative semirings as a compositional model of
consciousness, with the emphasis on its potential use for the mathematical and structural studies of
consciousness [13–15]. We introduced generators and processes as abstract mathematical structures to
target some aspects of the conscious experience which are independent of their physical realizations.
This introduction is inspired by the Yogacara school of Buddhism and other philosophies assuming that
consciousness is primary or fundamental. In this first attempt, we have focused on Alaya consciousness,
its co-dependent character and its perceived and perceiving division. It allow us to make a first approach
to the dual question of how the objective world emerges from the subjective one.
A future approach may target more details on the internal structure of Alaya consciousness, taking
for example, six features in formal analogy with the seed metaphor from [39]. Moreover, we leave for
future work the model of mental, manas and the five sense-consciousnesses. In the future, we also expect
to generalise the qufinite ZX∆ -calculus to the infinite dimensional case, from which standard quantum
mechanics might be recovered. It is to be noted that we have not recovered standard quantum mechanics.
To do so would mean generalising our model to derive the standard quantum mechanics described by
the Schrödinger equation. This is important in order to give a definitive answer to the dual problem of
consciousness introduced above.
Other very interesting models also aim to target that question. For example, the conscious agent
model intends to recover fundamental physics from the agent’s interactions, as for instance in quantum
mechanics [49]. Sadly, it is not clear that current versions of the conscious agent model are capable of
recovering the entire objective realm (see objections and replies section in [49]). In our framework part
of the reconstruction goal pursued by the conscious agent model is achieved for free, without overhead,
invoking only the simple structure of SMC in relationship with phenomenal aspects. In doing so, our
approach to consciousness processes and quantum theory share a similar, but not the same, mathematical
structure.
It allows a compositional treatment of the combination problem of basic experience that may give
rise to complex ones. One very influential model of consciousness also attempting to target that question
is the the integrated information theory (IIT) [50]. This model, however, conveys a Panpsychist view.
Unfortunately, the model is not neutral about the physical neural substrate, and although it intends to
highlight the primacy of consciousness, in practice, the current version falls in reductive accounts. Such
models also claim compositions, but they are not compositional in the sense exposed here. In IIT, the
minimal elements of the theory are gates that are not conscious, while consciousness emerges from the
right causal combination of these gates (integration). Contrary, compositionality in our sense means that
the minimal compositional elements, i.e. generatores, represents already conscious experiences.
Our model, the conscious agent model and IIT, all share the same goal of mathematize phenomenology.
Although with different philosophical commitments, the common point of departure is that axioms and
postulates consider aspects of consciousness as primary. However, we close by remarking that a process
theory for consciousness is not only about modelling consciousness with any type of mathematics (as
other models), but about modelling consciousness with category theory in a graphical form, i.e. axiomatic
mathematics. This form of mathematics explicitly introduces structures, assumptions and axioms, plus
the possibility of compositional treatments. We believe that because being foundational, this approach is
better suited to describing the conscious experience as fundamental. Finally, we are hopeful that due to
its co-dependent feature, and sufficient generality, our framework may pave the way for further research
on the scientific study of conscious experience and its phenomenology.
Author Contributions: Conceptualization, CMS and QW; investigation CMS, QW and IK; writing-original draft
preparation, CMS; writing-review and editing, CMS, QW and IK; visualization, CMS and QW.
19 of 21
Funding: CMS is funded by Comisión Nacional de Investigación Ciencia y Tecnología (CONICYT, current
ANID) through Programa Formacion de Capital Avanzado (PFCHA), Doctoral scholarship Becas Chile: CONICYT
PFCHA/DOCTORADO BECAS CHILE/2016 - 72170507. QW was supported by AFOSR grant FA2386-18-1-4028.
Acknowledgments: The authors appreciate valuable feedback and discussions from Bob Coecke, Konstantinos
Meichanetzidis and Robert Prentner. The authors would also like to thank the anonymous reviewers and editors
for their helpful comments.
Conflicts of Interest: The authors declare no conflict of interest.
References
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
Seth, A.K. Consciousness: The last 50 years (and the next).
Brain and Neuroscience Advances 2018,
2, 239821281881601. doi:10.1177/2398212818816019.
Searle, J.R.
Consciousness.
Annual Review of Neuroscience 2000, 23, 557–578.
doi:10.1146/annurev.neuro.23.1.557.
Bayne, T.; Chalmers, D.J. What is the unity of consciousness? The Unity of Consciousness: Binding, Integration,
and Dissociation 2012, pp. 1–41. doi:10.1093/acprof:oso/9780198508571.003.0002.
Crick, F.; Koch, C.
Consciousness and neuroscience.
Cerebral cortex 1998, 8, 97–1007.
doi:10.1093/cercor/8.2.97.
Lusthaus, D. Buddhist Phenomenology, first ed.; Routledge Curzon, 2002; p. 632. doi:10.4324/9781315870687.
Makeham, J. Introduction. In Transforming Consciousness: Yogacara Thought in Modern China; Makeham, J., Ed.;
Oxford University Press, 2014. doi:10.1093/acprof:oso/9780199358120.001.0001.
Fields, C.; Hoffman, D.D.; Prakash, C.; Singh, M. Conscious agent networks: Formal analysis and application
to cognition. Cognitive Systems Research 2018, 47, 186–213. doi:10.1016/j.cogsys.2017.10.003.
Thompson, E. Mind in Life; Harvard University Press, 2007.
Varela, F.J. Neurophenomenology: A Methodological Remedy for the Hard Problem. Journal of Consciousness
Studies 1996, 3, 330–349.
Coecke, B. An Alternative Gospel of Structure: Order, Composition, Processes. In Quantum Physics and
Linguistics:A Compositional, Diagrammatic Discourse; Heunen, C.; Sadrzadeh, M.; E. Grefenstette., Eds.; Oxford
University Press, 2013; [1307.4038]. doi:10.1093/acprof:oso/9780199646296.003.0001.
Coecke, B.; Duncan, R.; Kissinger, A.; Wang, Q. Generalised Compositional Theories and Diagrammatic
Reasoning. In Quantum Theory: Informational Foundations and Foils. Fundamental Theories of Physics.; Chiribella,
G.; Spekkens, R., Eds.; Springer, 2016; Vol. 181, pp. 309–366, [1506.03632]. doi:10.1007/978-94-017-7303-4_10.
Signorelli, C.M.; Meling, D. Towards new concepts for a biological neuroscience of consciousness. Cognitive
Neurodynamics 2021. doi:10.1007/s11571-020-09658-7.
Prentner, R. Consciousness and topologically structured phenomenal spaces. Consciousness and Cognition
2019, 70, 25–38. doi:10.1016/j.concog.2019.02.002.
Yoshimi, J. Mathematizing phenomenology. Phenomenology and the Cognitive Sciences 2007, 6, 271–291.
doi:10.1007/s11097-007-9052-4.
Tsuchiya, N.; Saigo, H. Applying Yoneda’s lemma to consciousness research: categories of level and contents
of consciousness. Preprint 2020. doi:10.31219/osf.io/68nhy.
Awodey, S. Category Theory, first ed.; Oxford University Press: Oxford, 2006; p. 266.
Maclane, S.
Categorical Algebra.
Bulletin of the American Mathematical Society 1965, 71, 40–106.
doi:10.1090/S0002-9904-1965-11234-4.
Coecke, B.; Duncan, R. Interacting quantum observables: Categorical algebra and diagrammatics. New Journal
of Physics 2011, 13, [arXiv:0906.4725v3]. doi:10.1088/1367-2630/13/4/043016.
Coecke, B.; Kissinger, A. Picturing Quantum Processes. A first Course in Diagrammatic reasoning; Cambridge
University Press: Cambridge, UK, 2017. doi:10.1017/9781316219317.
Coecke, B., Ed. New Structures for Physics, lectures n ed.; Vol. 813, Lecture Notes in Physics, Springer Berlin
Heidelberg: Berlin, Heidelberg, 2011; p. 1034. doi:10.1007/978-3-642-12821-9.
20 of 21
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.
39.
40.
41.
42.
43.
44.
45.
46.
47.
48.
Abramsky, S.; Coecke, B. A categorical semantics of quantum protocols. 19th Annual IEEE Symposium on
Logic in Computer Science (LICS’04); , 2004; pp. 415–425.
Kissinger, A.; Uijlen, S. A categorical semantics for causal structure. 32nd Annual ACM/IEEE Symposium
on Logic in Computer Science (LICS), 2017, pp. 1–12. doi:10.1109/LICS.2017.8005095.
Pinzani, N.; Gogioso, S.; Coecke, B. Categorical Semantics for Time Travel 2019. [1902.00032].
Kissinger, A.; Hoban, M.; Coecke, B. Equivalence of relativistic causal structure and process terminality 2017.
[1708.04118].
Coecke, B.; Sadrzadeh, M.; Clark, S. Mathematical Foundations for a Compositional Distributional Model of
Meaning. Linguistic Analysis 2010, 36, 345–384, [1003.4394v1].
Bolt, J.; Coecke, B.; Genovese, F.; Lewis, M.; Marsden, D.; Piedeleu, R. Interacting Conceptual Spaces I :
Grammatical Composition of Concepts. ArXiv 2017, [arXiv:1703.08314].
Signorelli, C.M.; Dundar-Coecke, S.; Wang, V.; Coecke, B. Cognitive Structures of Space-Time. Frontiers in
Psychology 2020.
Signorelli, C.M. Can Computers become Conscious and overcome Humans? Frontiers Robotics and Artificial
Intelligence 2018, 5. doi:10.3389/frobt.2018.00121.
Mulder, D.H. Objectivity.
Searle, J.R. How to study consciousness scientifically. Philosophical Transactions of the Royal Society B: Biological
Sciences 1998, 353, 1935–1942. doi:10.1098/rstb.1998.0346.
Anderson, P.W. More Is Different. Science 1972, 177, 393–396. doi:10.1126/science.177.4047.393.
Mazzocchi, F. Complexity in biology. EMBO reports 2008, 9, 10–14.
beim Graben, P. Contextual Emergence in Neuroscience. Closed Loop Neuroscience 2016, pp. 171–184.
doi:10.1016/B978-0-12-802452-2.00012-3.
Thomas Nagel. What is it like to be a bat? The Philosophical Review 1974, 83, 435–450.
Chalmers, D. The puzzle of conscious experience. Scientific American 1995, 273, 80–86.
LI, J.
Buddhist Phenomenology and the Problem of Essence.
Comparative Philosophy: An
International Journal of Constructive Engagement of Distinct Approaches toward World Philosophy 2015, 7, 59–89.
doi:10.31979/2151-6014(2016).070107.
Kern, I. The Structure of Consciousness According to Xuanzang. Journal of the British Society for Phenomenology
1988, 19, 282–295. doi:10.1080/00071773.1988.11007874.
Xuanzang.; Cook, F.H.; Vasubandhu.
Three Texts on Consciousness Only; Numata Center for Buddhist
Translation and Research: Berkeley, 1999.
Xuanzang.; TatWei.; Vasubandhu. Cheng Wei Shi Lun; The Doctrine of Mere-Consciousness.; Ch’eng Wei-shih
Lun Publication Committee: Hong Kong, 1973.
Husserl, E. General Introduction to a Pure Phenomenology; Martinus Nijhoff Publishers, 1983.
Bruza, P.D.; Wang, Z.; Busemeyer, J.R. Quantum cognition: a new theoretical approach to psychology. Trends
in cognitive sciences 2015, 19, 383–93. doi:10.1016/j.tics.2015.05.001.
Cervantes, V.H.; Dzhafarov, E.N. Snow queen is evil and beautiful: Experimental evidence for probabilistic
contextuality in human choices. Decision 2018, 5, 193–204, [1711.00418]. doi:10.1037/dec0000095.
Golan, J.S. Semirings and their Applications; Springer Netherlands, 1999. doi:10.1007/978-94-015-9333-5.
Chalmers, D.J. Panpsychism and Panprotopsychism. Amherst Lecture in Philosophy 2013, 8.
Chalmers, D.J. The Combination Problem for Panpsychism. Panpsychism; Brüntrup, G.; Jaskolla, L., Eds.
Oxford University Press, 2016, pp. 179–214. doi:10.1093/acprof:oso/9780199359943.003.0008.
Revonsuo, A.; Newman, J. Binding and consciousness.
Consciousness and cognition 1999, 8, 123–127.
doi:10.1006/ccog.1999.0393.
Hameroff, S.; Penrose, R. Consciousness in the universe: A review of the "Orch OR" theory. Physics of Life
Reviews 2014, 11, 39–78. doi:10.1016/j.plrev.2013.08.002.
Signorelli, C.M.; Wang, Q.; Coecke, B. Reasoning about conscious experience with axiomatic and graphical
mathematics. Submitted 2020.
21 of 21
49.
50.
Hoffman, D.D.; Prakash, C.
Objects of consciousness.
Frontiers in Psychology 2014, 5, 1–22.
doi:10.3389/fpsyg.2014.00577.
Oizumi, M.; Albantakis, L.; Tononi, G.
From the phenomenology to the mechanisms of
consciousness: Integrated Information Theory 3.0.
PLoS computational biology 2014, 10, e1003588.
doi:10.1371/journal.pcbi.1003588. |
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
174
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
Article
Persinger Group’s Recent Experiments, Spin Network and TGD
Matti Pitkänen 1
Abstract
Michael Persinger’s group reports three very interesting experimental findings related to EEG,
magnetic fields, photon emissions from brain, and macroscopic quantum coherence. The findings
provide for the proposal of Hu and Wu that nerve pulse activity could induce spin flips of spin
networks assignable to cell membrane. In this article I analyze the experiments from TGD point of
view. It turns out that the experiments provide support for several TGD inspired ideas about living
matter. Magnetic flux quanta as generators of macroscopic quantum entanglement, dark matter as a
hierarchy of macroscopic quantum phases with large effective Planck constant, DNA-cell membrane
system as a topological quantum computer with nucleotides and lipids connected by magnetic flux
tubes with ends assignable to phosphate containing molecules, and the proposal that ”dark” nuclei
consisting of dark proton strings could provide a representation of the genetic code. The proposal
of Hu and Wu translates to the assumption that lipids of the two layers of the cell membrane are
accompanied by dark protons which arrange themselves to dark protonic strings defining a dark analog
of DNA double strand.
1
Introduction
Michael Persinger’s group reports [5, 6, 7] three very interesting experimental discoveries relating to EEG,
magnetic fields, photon emissions from brain, and macroscopic quantum coherence.
In the first article [5] entitled Congruence of Energies for Cerebral Photon Emissions, Quantitative
EEG Activities and ∼ 5 nT Changes in the Proximal Geomagnetic Field Support Spin-based Hypothesis
of Consciousness correlations between cerebral photons emissions, EEG, and changes of the proximal
geomagnetic field are reported. The findings provide support for the proposal of Hu and Wu [8] that
nerve pulse activity could induce spin flips of spin networks assignable to cell membrane motivated by the
observation that the magnetic spin-spin interaction between protons at a distance of 10 m (cell membrane
thickness) corresponds to energies for which frequency is in EEG range.
In the second article [6] entitled Demonstration of Entanglement of Pure Photon Emissions at Two
Locations That Share Specific Configurations of Magnetic Fields: Implications for Translocation of Consciousness the group reports an excess correlation between ”pure” photon emissions at two locations
separated by few meters that share specific correlations of frequency modulated magnetic fields. The
photon emissions were from LEDs in the experiment consider. In an earlier similar experiment, which is
also discussed, they were from chemical reactions occurring in solutions contained by cell cultures.
In the third article [7] entitled Experimental Demonstration of Potential Entanglement of Brain Activity over 300 Km for Pairs of Subjects Sharing the Same Circular Rotating, Angular Accelerating Magnetic
Fields: Verification by s− LORETA, QEEG Measurements an excess correlation of brain activity of subject persons separated by 300 km and sharing the same circular rotating, angular accelerating magnetic
fields is reported.
It turns out that the experiments provide support for several TGD inspired ideas about living matter.
Magnetic flux quanta as generators of macroscopic quantum entanglement, dark matter as a hierarchy
of macroscopic quantum phases with large effective Planck constant, DNA-cell membrane system as a
topological quantum computer with nucleotides and lipids connected by magnetic flux tubes with ends
assignable to phosphate containing molecules, and the proposal that ”dark” nuclei consisting of dark
1 Correspondence: Matti Pitkänen http://tgdtheory.com/. Address: Köydenpunojankatu 2 D 11 10940, Hanko, Finland.
Email: matpitka@luukku.com.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
175
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
proton strings could provide a representation of the genetic code. The proposal of Hu and Wu [8]
translates to the assumption that lipids of the two layers of the cell membrane are accompanied by dark
protons which arrange themselves to dark protonic strings defining representation for DNA sequences.
In the sequel I briefly explain my own interpretation of these experiments and their outcomes from
TGD point of view and show that a nice interpretation of the findings emerges. Before going to this it is
however appropriate to summarize briefly those aspects of TGD based view about living matter, which
are relevant for the interpretation of the experiments.
1.1
Key aspects of the TGD inspired vision about living matter
The key ingredients of TGD inspired vision about living matter needed in the sequel are following.
1. The notion of many-sheeted space-time is the first new element [19, 20]. Space-times are 4-D
surfaces in 8-D space-time M 4 × CP2 so that one has what might be called sub-manifold gravity.
Any physical system corresponds to a space-time sheet characterizing its shape and size. The outer
boundaries of macroscopic objects correspond to causal boundaries at which the signature of the
induced metric of the space-time surface changes. Therefore space-time surfaces are topologically
non-trivial in all scales and we directly perceive it. Space-time surfaces form a fractal hierarchy in
the sense that subsystems of system correspond to space-time sheets topologically condensed at it
via the formation of wormhole contacts which are regions of space-time with an Euclidian signature
of the induced metric.
Also the notion of classical field is topologized. Various classical fields are subject to what might be
called topological field quantization. For instance, radiation fields decompose to topological light
rays and magnetic field to magnetic flux quanta (flux tubes and flux sheets). Topological field
quantization is of special importance in living matter and leads to the notion of field body and
magnetic body as additional structural and functional parts of a living system.
2. p-Adic physics [26] defines a further basic element. p-Adic number fields are proposed to serve as
correlates for cognition in the sense that one can speak about p-adic space-time sheets as correlates
for cognition and for intentions [23, 28] The quantum jump transforming p-adic space-time sheet to
a real one corresponds to a transformation of intention to action. The generation of though in turn
corresponds to an opposite of this transition. Zero energy ontology makes this picture internally
consistent and no breaking of conservation laws is implied.
p-Adic length scale hypothesis [24] states that p-adic primes near powers of 2 are of special physcal
significan and Mersenne primes Mn = 2n −1 especially so. A possible explanation for the importance
of these primes is that evolution corresponds to a gradually increasing complexity. These primes are
simple in the sense that all digits in their pinary expansion are ’1’:s expect possible some for the first
few ones) are especially interesting physically because they should have emerged first. Mersenne
primes have only ’1’:s in their pinary expansion so that they are the simplest possible primes and
indeed seem to correspond to fundamental physical scales. This leads to quite powerful predictions
in particle physics context.
In the scales of living matter a number theoretical miracle occurs: in the length scale range from 10
nm (cell membrane thickness to 2.5 µm (size scale of cell nucleus) as many as four Gaussian Mersenne
primes MG,n = (1 + i)n − 1 occur and correspond to p-adic primes near pk , k = 151, 157, 163, 167.
3. The hierarchy of effective Planck constants [18] coming as integer multiples ~ef f = n~ of the ordinary
Planck constant was partially motivated by the findings of Blackman [3] and others related to the
unexpected effects of ELF em fields on vertebrate brain. These effects look quantal but this should
not be possible since the cyclotron energies in the magnetic field .2 × 10−4 T (2/5 times the nominal
value of the Earth’s magnetic field BE = .5 × 10−4 T) are 10 orders of magnitude below the thermal
threshold.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
176
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
This led to the hypothesis about the value spectrum of Planck constants. The phases of ordinary
matter with non-standard value of effective Planck constant are identified as dark matter. Later
two different - possibly equivalent - reductions of the hierarchy to that for effective values of ~ have
emerged in TGD framework [28].
One of the most speculative ideas related to the dark matter hierarchy is based on the observation
that a simple model for dark proton implies that the states of dark proton are in 1-1 correspondence
with DNA, RNA, tRNA, and amino-acids, and that there is a simple rule reproducing vertebrate
genetic code [22, 21]. Dark nuclei defined by sequences of dark protons would define the analogs of
DNA sequences so that genetic code would not be a outcome of random bio-chemical selection but a
basic element of particle physics, and biological systems would only define a secondary representation
of the fundamental genetic code. This proposal has far reaching implications. Surprisingly, the
findings of the first article [5] supporting the hypothesis of Hu and Wu [8] about proton spin
networks combined with the dark DNA hypothesis lead to a concrete model for the proton spin
networks as paired dark DNA sequences assignable to the two lipid layers of the cell membrane.
4. Magnetic flux tubes carrying dark matter take central role in TGD inspired quantum biology. The
knotting and braiding of the flux tubes makes possible topological quantum computation and leads
to the hypothesis that DNA and cell membrane connected by flux tubes form a topological quantum
computer [17]. Flux tubes can connect sub-systems of living organisms or even different organisms
to form coherent structural and functional units. Indeed, the large value of ~ef f makes possible
macroscopic quantum coherence. In particular, biomolecules can be connected by flux tubes to
coherent structures. The reconnection of flux tubes plays a key role in the proposed model biochemical reactions and bio-catalysis. Inportant are also the phase transitions changing the value
of Planck constant inducing in turn a change of the length of the flux tube identified as a quantal
length scale depending of ~ef f . These phase transitions could be responsible for the phase transitions
changing dramatically the density of matter in cellular interior (say sol-gel transition).
Cyclotron Bose-Einstein condensates at magnetic flux tubes are proposed to be a characteristic of
living systems [12]. Cyclotron frequencies are classical (no dependence on Planck constant) but
cyclotron energies scale like ~ef f so that for a large enough value of the effective Planck constant
cyclotron energies of dark photons are above thermal threshold, and can induce macroscopic quantum coherence. Dark photons decay to bunches of ordinary photons and an attractive hypothesis
is that bio-photons result as decay products of dark photons.
The notion of magnetic body emerges naturally. Any physical system is accompanied by magnetic
fields which in TGD Universe defines separate entity, which can be called magnetic body. Magnetic
body is identified as an intentional agent using biological body as sensory receptor and motor
instrument. Magnetic body has an onion like structure corresponding to the hierarchy of spacetime sheets defining physical system, say biological body. The size of the magnetic body is much
larger than that of biological body. 10 Hz frequency corresponds to a layer with size large than the
size scale of Earth.
5. Zero energy ontology (ZEO) [11] is a further basic element. In zero energy ontology physical states
are zero energy states consisting of pairs of positive and negative energy states having opposite net
quantum numbers and being localized to the opposite light-like boundaries of CD × CP2 , where
CD is causal diamond identified as an intersection of of future and past directed light-cones and
defining a structure analogous to double pyramid (a convenient shorthand for CD × CP2 is simply
CD).
The interpretation of zero energy states is as counterparts of pairs of initial and final states of
physical events in positive energy ontology. CDs form a fractal hierarchy with CDs within CDs.
The size scales of CDs come as integer multiples of CP2 size scale about 104 Planck lengths. One
can interpret CD as an imbedding space correlate for a ”spot light of consciousness” in the sense
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
177
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
that the conscious experience of self associated with given CD is about region defined by CD.
Space-time sheets within CD serve as correlates for selves at space-time level.
Also elementary particles are expected to be accompanied by CDs, and one especially important
prediction is that the time scale of the CD associated with electron is .1 seconds, which corresponds
to the fundamental 10 Hz bio-rhythm. All elementary particles correspond to macroscopic time
scales and u and d quarks would correspond to time scales between 1 ms and .1 seconds.
1.2
Cell membrane as super-conductor and a model for EEG
The proposal is that cell membrane is accompanied by super-conducting dark magnetic flux tubes [25].
Cooper pairs of electrons, protons, and biologically important fermionic ions would be the carriers of
supra currents besides bosonic ions such as Ca++ and M g ++ . Note that the new exotic nuclear physics
suggested by TGD allows to imagine that fermionic nuclei could appear as bosonic variants with essentially
same chemical properties [22].
Josephson currents through cell membrane have frequency f = eV /~ef f so that in this case the energy
E = eV identifiable as the energy of electron or proton gained in traversing the cell membrane is classical
quantity whereas Josephson frequency is quantal [25]. Situation is the opposite of this for cyclotron
frequencies and energies. Obviously, large values of ~ef f correspond to low Josephson frequencies. Soliton
sequencies associated with the Sine-Gordon equation governing the dynamics for small variations of
membrane potential would represent ground states of axonal membranes mathematically analogous to a
sequence of mathematical penduli rotating in phase. Nerve pulse generation would mean a perturbation
in which one pendulum is kicked [25].
There are two alternative models for the cell membrane as a Josephson junction [12].
1. For the conservative option [12] the cell membrane is far-from vacuum extremal and various charged
particles experience only the electromagnetic field. The energy scale of excitations is determined
by the electric voltage and is given by E = eV . Nerve pulse generation would be associated with
this kind of membranes. Josephson radiation with harmonics of f = eV /~ef f is one signature of
super-conductivity.
One ends up also to an explanation of EEG in this framework [16]. The function of EEG would be
communication of sensory data from cell membrane to the magnetic body and control of biological
body via flux sheets traversing through DNA, where genetic expression is activated by the control
signals. EEG frequencies are linear combinations of harmonics of Josephson frequencies and of the
increments of cyclotron frequencies. Cyclotron transitions can be also accompanied by a spin flip.
This model allows to identify EEG bands. The hierarchy of Planck constants suggest a generalization
of EEG and its variants (say EKG) to a fractal hierarchy obtained by scaling EEG. For large enough
values of ~ cyclotron contributions to EEG energies would correspond to energies above thermal
threshold as also Josephson frequency (E = eVthr , where Vthr is the value of resting potential at
which nerve pulse is generated, is just at the threshold). This would make possible the correlation
of EEG with the brain state and also quantum biocontrol by using photons with EEG frequencies.
2. For the non-conservative option [15] cell membrane is near- to vacuum extremal. The classical Z 0
fields predicted by TGD dominate over em fields, and the voltage must be replaced by a combination
of Z 0 and em voltages. By assuming that the Weinberg angle is considerably smaller in this phase
than in the standard phase the energies gained by various ions correspond to visible photons. This
hypothesis allows to understand the frequencies for which photoreceptors - which do not directly
generate nerve pulses - are most sensitive. Near vacuum extremal property obviously implies high
sensitivity to perturbations making sensory receptor optimal.
An interesting possibility is that the far-from resp. near-to vacuum extremal options are realized for
the neurons of left resp. right hemisphere. This option finds support from the observation of Persinger
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
178
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
et al [5] that visible photon emissions are mostly from the right hemisphere. Another possibility is that
glial cells as cells which do not generate nerve pulses correspond to near-to vacuum extremals. The
identifications do not exclude each other.
1.3
Learning to apply the notion of induced field
The geometrization of classical gauge fields and gravitational fields relying on the induction of spinor
connection of CP2 and M 4 × CP2 metric to the space-time surface is one of the key ideas of TGD and it
is useful to get more concrete understanding of the induced fields since this notion will be applied in the
sequel.
1.3.1
The basic objection and its resolution
The basic objection against the induced fields is that they reduce the dynamics to that of only 4 field
like variables since the 8 imbedding space coordinates take the role of field variables and 4 of them are
eliminated by general coordinate invariance as field variables. Besides this preferred extremals of Kähler
action represent space-time surfaces carrying very restricted kind of patterns of induced gauge fields
analogous to Bohr orbits.
Many-sheeted space-time however saves the situation. Each system creates its own field body represented in terms of topological field quanta. If these field bodies have common M 4 projection, test particle
topologically condense to each of these field body (touches each of them), and the effects of these fields
sum up although fields do not interfere as they would do in ordinary field theory.
1.3.2
How could one generate dark photons with large ~?
The observation which led to the proposal of the effective hierarchy of Planck constants, was that microwaves with frequency of fh modulated by ELF frequency fl induce in vertebrate brain effects which
could be understood in terms of cyclotron frequencies assignable to quantal cyclotron transitions in and
endogenous magnetic field for which cyclotron frequency was equal to ELF frequency: fc = fl . These
effects are possible only if the cyclotron energy is above thermal energy, and this led to the proposal
about the hierarchy of Planck constants. ’
The key question is how the modulation by ELF frequency could generate dark photons with large
~ef f . A possible answer to this question comes from another question. Topological field quantization
forces to ask what amplitude modulation of fields means.
The simplest modulation corresponds to a multiplication of rapidly oscillating field with a slowly
varying oscillating amplitude so that amplitudes with frequencies fh ± fl result (’h’ and ’l’ refer to
”high” and ”low”). The natural thing to do is to develop the two amplitudes with frequencies fh ± fl in
Fourier series in time interval T = 1/fl . All harmonics of fl appear and coefficients of the expansion are
proportional to 1/(fh − (n ± 1)fl ). Maximal amplitudes correspond to fh ' (n ± 1)fl . This suggests that
when this almost resonance condition is satisfied the generation of dark photons with frequency fl and
energy ~ef f fl , with ~ef f ' fh /fl , can take place with a considerable rate. If this argument is correct, one
could generate dark photons with given ~ef f by using modulation satisfying the condition fh /fl = ~ef f .
In the case of ELF em fields interacting with brain this is not enough since microwave photons have
energies below the thermal threshold Eth . Bio-system however contains photons with energy above
thermal threshold - say bio-photons with frequencies f in visible range or infrared Josephson photons
generated by cell membrane Josephson currents - the fields associated with MEs (”massless extremals”,
topological light rays) accompanying these many-photon states can be modulated by the ELF modulated
microwaves. Since one can say that a modulation of modulation is modulation, the outcome is modulation
(f, fELF ) producing dark photons with ~ef f ' f /fELF with energies about Eth . This mechanism would
explain the ”scaling law of homepathy”’ [21] stating that fields with low frequencies fl are somehow
transformed to fields with high frequencies fh and vice versa. The proposal has been that large ~ef f
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
179
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
photons with ~ef f ' fh /fl decay to ordinary photons or vice versa. This transformation has quite
concrete description ~ef f = n photons corresponds correspond to n-furcations of space-time surface made
possible by the non-determinism of Kähler action. All n-sheets of the n-furcation would be present and
each of them would carry photon with frequency fl and total energy would be ~ef f fl = fh .
1.3.3
How to describe time varying magnetic fields?
The topological flux quantization for static magnetic fields is easy to understand. The description of time
varying magnetic fields in terms of flux quanta is however a non-trivial exercise in thinking in terms of
topological field quanta.
Flux quantization implies that the magnetic dipole field decomposes into closed flux tubes with a
straight part inside dipole and a portion outside the dipole carrying return flux in roughly opposite
direction also arranged to flux tubes.
The basic assumption is that the flux tube structure of dipole field is not lost but is only re-arranged
as the dipole field oscillates. As the dipole strength decreases the flux tubes along field lines outside the
dipole contract so that eventually the closed flux tubes of dipole field degenerate to those of wormhole
magnetic fields [27] restricted inside the dipole and consisting of parallel flux tube space-time sheets with
same M 4 projection and carrying opposite magnetic field strength and having distance of order CP2
length along CP2 direction. A charged particle topologically condensing at both sheets experiences the
sum of the magnetic fields, which vanishes. As the sign of dipole changes, the flux tubes in the interior
of dipole begin to move to the exterior of the dipole. In operational sense this dynamics is approximated
well by Maxwell’s theory or vice versa.
How the electric electric fields associated with the time varying magnetic field predicted by Faraday
law are represented? These fields are rotational with flux lines rotating around the magnetic field.
In Maxwell’s theory one would have single vortex like structure. In TGD this vortex like structure
decomposes into smaller vortices assignable to individual flux tubes just like the rotational flow of superfluid decomposes into smaller vortices satisfying quantization condition analogous to the quantization of
the magnetic flux.
Also the geometro-dynamics for the flux quanta of electric field is possible and in this case magnetic
fields induced by time dependent electric fields are assignable to flux quanta. Cell membrane is a good
example of this kind of situation. Quite generally, the geometro-dynamics of topological field quanta
together with the possibility to have varying overlapping M 4 projections allows to reproduce the smooth
dynamics of Maxwell fields.
2
First article
The first article has the title Congruence of Energies for Cerebral Photon Emissions, Quantitative EEG
Activities and ∼ 5 nT Changes in the Proximal Geomagnetic Field Support Spin-based Hypothesis of
Consciousness, which already summarizes the findings.
2.1
Findings
In the article [5] Persinger’s group reports simultaneous changes in photon emissions, EEG activity, and
alternations of geomagnetic field when a person sitting in dark is imagining white light or not. The
abstract of the article is following.
The hypothesis by Hu & Wu that networks of nuclear spins in neural membranes could be modulated
by action potentials was explored by measurements of the quantitative changes in photon emissions, electroencephalographic activity, and alterations in the proximal geomagnetic field during successive periods
when a subject sitting in the dark imagined white light or did not. During brief periods of imagining white
light the power density of photon emissions from the right hemisphere was about 10−11 Wm−2 that was
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
180
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
congruent with magnetic energy within the volume associated with a diminishment of ∼ 7 nT as predicted
by the dipole-dipole coupling relation across the neuronal cell membrane. Spectral analyses showed maxima
in power from electroencephalographic activity within the parahippocampal region and photon emissions
from the right hemisphere with shared phase modulations equivalent to about 20 ms. Beat frequencies (6
Hz) between peak power in photon (17 Hz) and brain (11 Hz) amplitude fluctuations during imagining
light were equivalent to energy differences within the visible wavelength that were identical to the intrinsic
8 Hz rhythmic variations of neurons within the parahippocampal gyrus. Several quantitative solutions
strongly suggested that spin energies can accommodate the interactions between protons, electrons, and
photons and the action potentials associated with intention, consciousness, and entanglement.
The authors interpret the results in terms of entanglement identified as enhanced correlations. Entanglement in this sense does not correspond to quantum entanglement. To my opinion (quantum) coherence
would be a more standard manner to interpret the findings. Quantum coherence of course makes possible
also quantum entanglement.
Spin flips, whose importance for consciousness has been emphasized by Hu and Wu [9]. The spin flips
would occur between spin triplet and singlet states of pairs of protons belonging to the spin network. The
basic finding is that the energy changes are accompanied by changes in EEG power.
Note that spin flips are possible also for cyclotron states proposed to be important for consciousness in
TGD approach. In the case of electron the change of the energy in spin flip is in excellent approximation
the same as in the transition n → n±1 of cyclotron state characterized by integer n (radial wave functions
of electron in constant magnetic field correspond to those of harmonic oscillator). For ions the Lande
factor g characterizes the effective nuclear angular momentum and appears in the spin flip energy and
also now the frequencies involved are in EEG range.
The correlation of photon emissions with imagination of white light supports the hypothesis that EEG
photons are responsible for communications to and control of biological body by magnetic body.
2.2
TGD inspired interpretation of the findings
What has been observed is correlation between EEG, emission of visible photons, and weakening of Earth’s
magnetic field with the change of magnetic energy equal to the energy of radiated photons. There is also
evidence that spin flip transitions for protons are involved.
2.2.1
What is the origin of the visible photons?
The basic question concerns the origin of the visible photons.
1. An attractive general hypothesis is that the visible photons result in the transformation of dark EEG
photons to ordinary visible photons. In TGD based model EEG (and its predicted fractal variants)
correspond to dark photons with large effective value of ~ - call it ~ef f - and energy E = hef f f in
infrared or visible range and perhaps even in UV. Also bio-photons would result from these large
~ ”dark” photons as they decay to bunches of ordinary photons. The wavelengths of dark photons
with given energy are scaled by ~ef f /~ predicted to be integer. The transformation of EEG photons
to ordinary visible photons could explain the correlation between EEG and visible photon emission
reported by Persinger’s group. This kind of process would generate also biophotons.
2. The mechanism providing energy for dark photons (in particular EEG photons) would provide it
also for the visible photons. According to the authors, the energy would come from the Earth’s magnetic field which I as inhabitant of many-sheeted space-time take liberty to translate to ”measured
magnetic field”. What is interesting that magnetic body would serve as a provided of metabolic
energy. It is interesting to notice that in TGD based cosmology matter is created from the dark
energy identified as Kähler magnetic energy assignable to magnetic flux tubes.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
181
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
3. Authors conclude that the energy liberated per action potential is E = eVrest . In TGD framework
it could correspond to either a photon of Josephson radiation or the energy liberate when electron
traverses the cell membrane. What is troublesome that this energy corresponds to IR photon
just above thermal threshold rather than visible photon. The non-conservative model for the cell
membrane mentioned above (applying to photo-receptor cells at least) could explain why visible
photons rather than infrared photons with energy E = eVrest correspond to photons of the Josephson
radiation.
4. The model based on the observation of Hu and Wu [8] suggesting that action potentials affect a spin
network of protons (possibly at opposite ends of lipid of two lipid layers making cell membrane)
looks like a totally different explanation from what would come first in mind in TGD framework.
Could the spin network proposal of Hu and Wu be integrated to the picture of living matter provided
by TGD? This is the question to be considered next.
2.2.2
The spin network hypothesis of Hu and Wu from TGD view point
The hypothesis of Hu and Wu [8] states that nuclear spin networks of nuclei associated with the cell
membrane are relevant for consciousness in the sense that action potential induces modulations of the
coupling parameters describing the magnetic interaction between neighboring spins of the spin network.
1. A direct calculation using the value of proton magnetic moment gives that the magnetic field created
by proton at distance defined by cell membrane thickness of 10 nm is 3 nT. There are also other
factors involved, and the estimate of Hu is that the field is about 5 nT.
2. The crucial observation is that the classical spin-spin interaction energy for two protons at distance
d = 10 nm defined by cell membrane thickness and given by Es−s = −µ · B, where B is the dipole
field created by proton, corresponds to a frequency of the order 10−14 eV and thus is in EEG range.
This can be seen by a direct calculation by assuming that proton creates a dipole field with Lande
factor of proton.
The frequencies assignable to the energies of neighboring interacting proton spins at distance d are
in EEG range also when the effects of the environment are taken into account. For instance, the
Hamiltonian for a rotationally symmetric nearest neighbor spin-spin interaction characterized in
terms of so called J-factor, predicts in the case of protons frequency differences ∆E between singlet
and triplet states varying in the range 5-25 Hz.
For heavier nuclei these interaction energies scale down like 1/A2 , A the mass number, so that a
naive conclusion would be that the frequencies tend to be below 5 Hz scale. Proton would therefore
be in a completely unique position. That EEG frequencies result in case of proton suggest that cell
membrane thickness is not 10 nm by a pure accident (not that p-adic length scale hypothesis fixes
assigns it to the p-adic length scale L(k = 151), where k = 151 characterize Gaussian Mersenne
prime.
The fact that the frequencies for energy differences of singlets and triplets are in EEG range is highly
relevant also from TGD point view since this energy range makes it possible for EEG frequencies to induce
spin flips.
1. In TGD framework fermionic spin and fermion numbers in various modes of second quantized
induced spinor field (1 or 0) are predicted to serve as correlates for Boolean cognition [14] so that
there are good reasons to expect that also spin flips are important. One might even think that
protonic and even nuclear spins could be utilized to build Boolean representations.
2. The basic objection against the proposal of Hu and Wu is same as that against the findings of
Blackman and others: quantum coherence is not possible since the energy differences corresponding
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
182
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
to (say) frequency of 5 Hz is about 12 orders of magnitude below thermal threshold. Trom the basic
relation E = hef f f it is clear that the objection can be circumvented for large values of effective
Planck constant, which can take raise the energies involved to those of IR or perhaps even visible
photons.
3. Authors conclude that the energy emitted per single action potential is E = eVrest which corresponds
to IR photon just at the thermal threshold. It is however visible photons which are emitted. Why
not photons with the Josephson energy E = eVrest just at the thermal threshold?
If the photons would result when electron or proton traverses cell membrane and liberates potential
energy as a photon or if the emitted IR photon could be interpreted as a photon of Josephson
radiation this would be the case. TGD allows also to imagine that the cell membranes in question
correspond to the non-conservative option for the model of cell membrane as Josephson junction for
which Vrest contains Z 0 potential as a dominating contribution and gives rise to Josephson photons
with energies in visible range.
If one takes the proposal of Hu and Wu seriously, the visible photons would have different origin,
and one must perhaps give up the assumption that the estimate of authors forces the identification
of basic energy quantum emitted in the process considered as E = eVrest .
Authors state that the energy associated with visible photon emission should be equivalent to the
energy emitted in the emission of photons. What can one conclude from this?
1. An attractive possibility would be ”dark” spin network formed by spin-coupled protons, whose
members are associated with the lipids of the two lipid layers with lipids. The number of the lipids
per cell membrane would be roughly Nl = r2 /d2 , with lipids thickness estimated to be d ∼ .1 nm.
For r ∼ 10−4 m corresponding to a relatively large neuron this would give Nl = 1014 .
This number would give also the maximum number of spin pairs participating in phase transition
and an estimate for the value of ~ef f from Nl ∆Es−s = Eph as
Nl =
fph
Eph
=
.
Es−s
fs−s
Suppose that all dipoles make a simultaneous spin flip with energy change ∆E = hf , fs−s = 5 Hz
generating an energy of Eph = 1eV corresponding to a frequency of 2.4 × 1014 Hz. This requires
Nl ∼ .5 × 1014 . It is encouraging that the rough estimates are consistent with each other.
2. That all protonic spin pairs make a simultaneous spin flip between singlet and triplet states of neighboring pairs looks like a phase transition. This suggests strongly macroscopic quantum coherence.
What looks extremely strange that single visible photon should be emitted in the process since the
entire magnetized region would behave like single spin! In standard physics this is not possible.
TGD however leads to a possible realization of this kind of process as a mechanism of psychokinesis
[29].
The hierarchy of effective Planck constants could resolve the paradox. If one has ~ef f /~ '
Eph /∆E ' .5 × 1014 , the emitted photon would be large ~ dark photon with frequency 5 Hz
and the energy of visible photon and geometrically would corresponds to a n-furcation of spacetime with n = ~ef f /~ sheets each carrying single 5 Hz photon. Each dipole pair emits ELF photon
but they combine to single dark ELF photon with the energy of single photon.
It seems that it is not natural to assign the photon emission to cyclotron transitions ionic cyclotron
B-E condensates or to the transitions associated with the cell membrane Josephson junctions. Also the
model based on the observation of Hu and Wu is very attractive. This does not add a completely new
element to TGD. One can find a nice connection with one of the TGD inspired basic ideas about genetic
code, namely the dark realization of genetic code as sequences of dark protons.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
183
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
1. For about 7 years ago I constructed a model for dark nuclei identifying the as strings of dark
nucleons [22, 21]. The model of dark nucleon yielded a compete surprise: the states of the nucleon
were in 1-1 correspondence with DNA, RNA, tRNA, and amino-acids and vertebrate genetic code
could be understood in simple manner. This led to the vision that dark proton sequences allow a
virtual world realization of genetic code making possible a kind of R&D department developing and
testing various genetic alternatives. The genetic discoveries are however useful only if they can be
used. This requires a generalization of transcription process allowing to transcribe DNA and RNA
and perhaps even tRNA, and amino-acids to their dark counterparts and vice versa. This requires
that dark nucleon sequences have same size scale as ordinary DNA, RNA, and amino-acids and that
they could accompany the biomolecules.
This fixes the size scale of dark proton to be of the order of the volume defined by the length L
corresponding to single nucleotide in nucleotide sequence. The value of Planck constant would be
of the order ~ef f /~ ∼ L/rp ' 2.3 × 105 , rp = ~/mp ' 1.3 × 10−15 m andL ' .3 nm.
2. At the same time I also constructed a model of DNA and cell membrane acting as a topological
quantum computer [17]. DNA nucleotides would be connected to lipids of the inner lipid layer of
the cell membrane by magnetic flux tubes, whose braiding would define the topological quantum
computer programs. The braids would continue from the outer lipid layers to the membranes of
other cells and in this manner bind the cells to a kind of network. The strands could have at their
ends molecules containing phosphates to make possible transfer of metabolic energy to the system.
3. Dark protons could be generated in the ionization of OH group to OH− as proton drops to dark
space-time sheet and possibly becomes a part of dark proton sequences.
(a) The basic process would be formation of dark water in this manner and the rich spectrum of
anomalies of water could be understood in terms of temperature dependence fraction of dark
protons [15].
(b) OH groups are also associated with the hydrophilic ends of lipids such as fatty acids, glycerolipids, and phospholipids, which are the basic structural element of cell membranes. In
phospholipids OH is associated with phosphate. In the DNA strand the phosphates contain
O− identifiable as OH − resulting when proton of H drops to dark space-time sheet and possibly
becomes part of dark proton sequence.
(c) Also carbohydrates, in particular sugars, which are basic building brick of metabolism and
defined the sugar backbone of DNA and RNA, contain a large number of OH groups. The
model of DNA as topological quantum computer led to a proposal that magnetic flux tubes
have OH or OH− groups as their ends. These observations would allow magnetic flux tubes
have dark protons at either or both ends. According to the earlier proposal [17] magnetic
flux tubes to have OH and O = at their ends. Earlier picture need not to be modified if the
cell membrane carries dark double DNA strand connected to the ordinary DNA double strand
inside nucleus. Similar connections would be natural also between DNA and amino-acids and
their dark counterparts possibly associated with the cell membrane and reconnection of the
color magnetic flux tubes could allow to build and manipulate these connections.
4. This would predict that single DNA codon, which corresponds to a length of .33 nm along DNA
strand is connected to single lipid by magnetic flux tube or three color magnetic flux tubes to
corresponding proton consisting of 3 quarks. This seems to be consistent with the width of single
lipid in lipid bilayer if one takes seriously the illustration of the Wikipedia article. Note that in the
earlier model single nucleotide was assumed to be connected by a magnetic flux tube to single lipid.
5. A further natural working hypothesis is that the proton pairs assignable to the OH− groups at the
hydrophilic ends of opposite lipid layers can also be connected by triplets of (color) magnetic flux
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
184
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
tubes giving rise to the dipole-dipole interaction. This connection need not be permanent and could
disappear or appear by the reconnection of the magnetic flux tubes. This could correspond to the
transiotion to singlet state for proton pairs and would require energy. The working hypothesis of
[17] indeed is that during topological quantum computation the connection is split so that the cell is
isolated from external world. The connection would be restored as the computation halts. Photon
emission would therefore be seen as a signature of topological quantum computation.
The fact that the proton cyclotron frequency 300 Hz in Bend = .2 Gauss is the only cyclotron frequency
above EEG range, one can ask whether biologically important dark ions form cyclotron Bose-Einstein
condensates (possibly also Cooper pairs if fermions), dark protons form a cell membrane spin network,
and dark electrons arrange to dark Cooper pairs making cell membrane a super-conductor. This would
provide a unified picture about the role of various particle in TGD inspired vision about living matter.
2.2.3
Correlation of photon emissions with the weakening of the Earth’s magnetic field
Authors say During brief periods of imagining white light the power density of photon emissions from
the right hemisphere was about 10−11 Wm−2 that was congruent with magnetic energy within the volume
associated with a diminishment of ∼ 7 nT as predicted by the dipole-dipole coupling relation across the
neuronal cell membrane.
The experiment is to some extent a replication of earlier experiment of [4] in which it was observed
that visible photon emissions mainly from the right hemisphere is accompanied by a weakening of the
horizontal component of the Earth’s magnetic field. Decreases over 10 to 15 s of 15 nT and 5 nT at 0.25
m and 1 m from the right side of the head of the subject person were associated with the same magnitude
of energy (10−11 J) that was associated with the net increase in photon emissions during that period.
This energy - assuming each action potential is associated with energy of eVrest = 1.9 × 10−20 J - would
be the equivalent of the activity of about 1 billion neurons.
1. If I have understood correctly, the weaking of the magnetic field outside the head of the subject
person would be due to magnetic energy change associated with the spin flips taking place in the
cell membrane and absorbing the needed energy from this magnetic field. This would obviously
represent a new kind of metabolic activity: magnetic field would provide the needed metabolic
energy instead of ATP-ADP process. That magnetic body could directly use its magnetic energy
to control biological processes, would mean quite a dramatic modification of the usual view about
metabolism.
2. The nuclear magnetization disappears for a moment in a transition from spin triplet to spin singlet
state, which then spontaneously decay to triplet state again. The excitation of singlet state requires
energy so that the magnetic field outside should weaken if it pays the energy bill. The contribution
of magnetic dipoles to the horizontal magnetic field component measured outside the head of the
subject person disappears and if the direction of dipole magnetization correlates with the direction
of the magnetic field the strength of the magnetic field is reduced. The correlation would guarantee
that the magnetic fields from different pairs of dipoles do not interfere to zero. Some kind of ordering
of the orientations of neurons perhaps induced by the layered structure of cortex and of the almost
collinearity of the myelinated axons of white matter is required.
3. Spin-flip transition from triplet to singlet state would change the contribution of magnetic dipoles
to the net magnetic field and thus affect the net magnetic field experienced by a test particle. Could
this explain the reduction of BE by factor about 1.8 × 10−4 ? At distance of order .1 meter the
dipole field created by proton is very small: by a factor 10−21 weaker than the 9 nT field created at
distance of d = 10 nm. The fields of neurons each containing a contribution of about 1014 protons
sum up and the estimate is that there are 109 active neurons. The resulting net factor of 1023 could
make possible reduction by 9 nT.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
185
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
4. Triplet-to-singlet spin flip transition taking its energy from the magnetic field is the interpretation
suggested by the experiments. The return to the ground state would liberate this energy as large ~ef f
quanta with energies of visible photons transforming later to ordinary visible photons. Therefore
the radiated energy could indeed be magnetic energy also in TGD. Of course, also metabolism might
drive particles directly to the excited cyclotron states and is expected provide the energy needed to
regenerate the magnetic fields since the energy of visible photons is lost.
5. In TGD Universe the correlation of the photon emission with changes (about 7 nT) in the measured
magnetic field identified as the Earth’s magnetic field BE having nominal value of .5 × 10−4 T does
not force to assign dark photons with the magnetic flux tubes of the Earth’s magnetic field.
(a) One can of question the assignment of 7 nT weakening to BE as a Maxwellian description
not applying in TGD framework. The changes of the horizontal component of the magnetic
field are detected outside the head of the subject person is it possible to assign this change
to any particular magnetic field? How to distinguish between magnetic fields associated with
different space-time sheets? TGD predicts that test particles ”feel” their sum if these magnetic
space-time sheet have projection in the same region of Minkowski space.
The possibility to move the flux tubes in such a manner that only the flux quanta of one
particular component of the many-sheeted magnetic field contribute to the projection, would
allow to analyze the field into these components. Note that un Maxwell’s theory this is not
possible. The change in the measured magnetic field could be induced by a flux tube carrying 7
nT field assignable to the proton spin network and having a projection to the same M 4 volume
as a flux tube of the Earth’s magnetic field or the endogenous magnetic field has. Therefore it
might not be easy to distinguish between changes of BE and Bend .
(b) The experimental findings of Blackman et al [3] about the effects of ELF frequencies on vertebrate brain however encourages an interpretation in terms of cyclotron frequencies for magnetic
field in ”dark” endogenous magnetic field Bend ' 2BE /5 (this predicts that Ca++ cyclotron
frequency is 15 Hz, which is not far from 17 Hz). It is of course possible that the flux tubes of
the Earth’s magnetic field thicken inside the brain so that the strength of the magnetic field
is reduced accordingly.
2.2.4
Can one understand the ELF frequencies involved?
Authors state: Spectral analyses showed maxima in power from electroencephalographic activity within the
parahippocampal region and photon emissions from the right hemisphere with shared phase modulations
equivalent to about 20 ms.
The time scale of 20 ms appears also in the experiments of articles 2 and 3 in which rotating and
frequency modulated magnetic fields where applied. This time scale corresponds to 50 Hz frequency,
which has been found to have biological effects [10]. The cyclotron frequency of Lithium (bosonic ion)
for Bend = .2 Gauss equals to 50.1 Hz (see the appendix of appendix of [13]).
Authors continue : Beat frequencies (6 Hz) between peak power in photon (17 Hz) and brain (11 Hz)
amplitude fluctuations during imagining light were equivalent to energy differences within the visible wavelength that were identical to the intrinsic 8 Hz rhythmic variations of neurons within the parahippocampal
gyrus.
Can one understand the ELF frequencies involved? In TGD framework [13] cyclotron states of electrons, protons, and of ions are possible [13].
1. Ca++ is one important bosonic ion able to form cyclotron Bose-Einstein condensates and the 17 Hz
frequency for the power of photon fluctuations could correspond to f (Ca++ ) = 15 Hz: note that
the strength of the endogenous magnetic field is expected to be under homeostatic control and thus
vary in some range.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
186
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
2. 11 Hz frequency is perhaps too far from alpha frequency 10 Hz but rather near to cyclotron frequency
11.4 Hz for Mn++ or 10.8 Hz of Fe++ in the field Bend = .2 Gauss (see the appendix of appendix
of [13]).
3. The superposition of effects on test charges caused by MEs associated with 17 Hz and 11 Hz frequencies would give 6 Hz beat frequency. Note that K + and Cl− (fermionic ions) have cyclotron
frequencies 7.5 Hz and 8.5 Hz and their Cooper pairs might relate to parahippocampal 8 Hz frequency.
3
Second article
Second article has the title Demonstration of Entanglement of Pure Photon Emissions at Two Locations
That Share Specific Configurations of Magnetic Fields: Implications for Translocation of Consciousness.
In the article [6] the group reports an excess correlation between ”pure” photon emissions at two
locations separated by few meters that share specific correlations of frequency modulated magnetic fields.
The photon emissions were from chemical reactions. The abstract of the article is following.
The experimental demonstration of non-locality for photon emissions has become relevant because biophotons are coupled to conscious activity and cognition. The experimental condition that produces doubling
of photon emissions from two loci during simultaneous chemical reactions when exposed to a sequence
of circular rotating magnetic fields with differential phase and group angular velocities was applied to
photons from LEDs (light-emitting diodes). A significant but weaker enhancement of photon emissions
as measured by photomultiplier tubes occurred when the two LEDs were activated simultaneously within
two loci separated by several meters. The effect suggests that under optimal conditions photons emitted
from two, magnetic field congruent, loci become macroscopically entangled and that the two loci display
properties of a single space. Implications for the transposition of consciousness over large distances are
considered.
What was observed was enhanced visible photon emission from of LEDs subject to the same magnetic
stimulation as the cell culture dish (neurons) in the earlier experiment [2]. The size of the effect was
however smaller. If the effect is real, the presence of the cell culture dishes is not absolutely necessary for
the effect although in enhances it. The conclusion of authors is that photons are carriers of conscioussness. TGD inspired interpretation is that the experiment conforms magnetic flux tubes as generators of
macroscopic quantum coherence.
3.1
Experimental arrangement and results
The article describes first earlier similar experiment [2] using instead of LEDs chemical reactions occuring
in cell culture dishes (neurons) and leading to a doubling of photon emissions serving as a signature for
coherence - or entanglement as authors express it. LEDs were motivated by the hypothesis that photon
field can be equated with consciusness, and tot est this the cell culture dishes were replaced with LEDs.
A weaker but significant enchancement of LED emissions is indeed reported.
In the collowing I shall consider mostly the earlier experiment [2] involving cell culture dishes which
is identical to the recent one for the mentioned replacement.
1. The distance between the cell culture dishes was few meters as was also the distance of the solenoids
from the sample located circularly around it. If I have understood correctly, the circular arrangements of solenoids were in parallel planes around the cell culture dishes (neurons) and the solenoids
were directed radially to the dishes: otherwise it would not be possible to achieve a rotating magnetic
field.
2. Each set of eight solenoids in circular arrangement around the cell culture dish received identical
patterns of piecewise constant magnetic fields generated by potentials having 8 different values: the
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
187
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
duration of single constant piece was 1 ms. Each solenoid created a magnetic field, whose lines
emanating from the end of the solenoid were directed to the center of the cell culture dish.
3. Figure 1 of [6] describes the shapes of the AD (accelerating angular velocity, decreasing ”phase”
modulation) and DI (decelerating angular velocity, increasing ”phase” modulation). AD configuration was represented for 8 minutes and followed by DI configuration induced the effect and it
occurred immediately after the initiation of DI phase.
Consider now a more detailed description of the AD and DI phases of magnetic stimulation.
1. During AD phase the accelerated rotation of the magnetic field was achieved by creating a magnetic
pulse of duration 20,18, 16,..., Tn = 20−2n, ... ms to subsequent solenoids so that only single solenoid
contributed to the net magnetic field at any moment. This series was repeated for every rotation of
2π. During AD phase the frequency modulation was slowed down meaning the frequency decreased
and also this process was same for every rotation of 2π. The optimal duration of AD phase was
about 4-5 minutes.
2. During DI phase decelerated rotation was achieved by in increasing the subsequent durations by 2
ms so that a series of pulses with durations 18 ,20, 22,...,Tn = 20 + 2n, ... ms was obtained. During
this period frequency modulation was increased.
3. What ”frequency modulation of phase” precisely means? Pictures of AD and DI temporal patterns
of voltages (equivalently magnetic fields) feeded to the solenoids inducing a series of values of
magnetic field are given Fig. 2 of [6].
A more detailed description can be found from the earlier article by Persinger’s group [2]. The
voltage range [-5 V, 5V] was discretized to 8 pieces and the possible discretized voltages in this
range are represented by 8 bits. The bit patterns were selected so that they were ”physiologically
patterned”. The value of the magnetic field inside solenoid for n:th bit was proportional to Vn . The
duration of each voltage was 1 ms - basic frequency of brain synchrony.
During AD pattern a) with decreasing frequency and during DI pattern b) with inreasing frequency
was used. The numbers of points which composed each pattern were 859 (duration was 859 ms) for
AD and 230 (duration of 230 ms) for DI. Only a part of the pattern could be represented since the
duration of single 2π rotation was 104 ms, which corresponds to 10 Hz, a fundamental bio-rhythm
(Unless there was scaling of the bit duration).
4. Within the center of the 8-solenoid configuration the value of the magnetic field averages to 1 µT. A
natural assumption that this magnetic field contributes to the net effective value of the endogenous
magnetic field Bend inducing small variations of Bend in turn modulating cyclotron frequencies.
The modulated cyclotron frequency should be higher that frequency of modulation and thus higher
than 1 kHz. For Bend this leaves only electron with cyclotron frequency fc = 6 × 105 Hz under
consideration. The effect would be on electron Cooper pairs in the case of cell culture dishes or
electrons in the case of LEDs. Electrons are indeed essential also for the function of LED.
5. The frequencies fn = 1/Tn defined by the durations of magnetic field vary during AD phase between
50 Hz and and 157 Hz. During DI phase the frequencies vary between 50 Hz and 30 Hz. In [10] it
is reported that 50 Hz frequencies have biological effects. As already noticed, 50.1 Hz corresponds
to cyclotron frequency for Lithium (bosonic ion) for Bend = .2 Gauss.
3.2
Reconnection of magnetic flux tubes as a mechanism generating macroscopic quantum coherence
A doubling of the rate of emissions of visible photons immediately after the AD phase in the earlier
experiment [2] and weaker enhancement in the recent experiment using LEDs instead of cell culture
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
188
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
disches, is interpreted as a signature of entanglement. Quantum coherence is perhaps a more appropriate
manner to express the findings of the two experiments although quantum coherence makes possible also
quantum entanglement. To my opinion the experiments provide support for the basic prediction of TGD
inspired quantum biology that magnetic flux tubes are generators of macroscopic quantum coherence.
What seems necessary is that some flux tubes emanating from the solenoids must reconnect to form
flux tubes connecting the two cell culture dishes or LEDs: reconnection is indeed one of the fundamental
processes in TGD inspired theory of living matter. Without reconnection the flux tubes of the two
magnetic fields remain disjoint and cannot induce macroscopic quantum coherence. The reconnection
can occur only if the temporal and spatial patterns of the rotating and modulated magnetic fields are
identical. These flux tube connections would induce quantum coherence by effectively binding the two
systems to single system.
The doubling of the photon emission rate in the earlier experiment involving cell culture can be
understood by the well-known rule that in incoherent emission the total rate is N times the individual
rate, and in coherent emission N 2 times the individual rate: now N equals to 2. Also destructive
interference becomes possible when the summed amplitudes are in opposite phases. This would reduce
the rate below the predicted based on incoherence.
Also the enhancement of the photon emission rate from LEDs in a similar arrangement supports the
view that macroscopic quantum coherence generated by the magnetic field patterns is relevant and implies
that the amplitudes describing the emission of photons from the two LEDs add coherently with some
probability so that constructive or possibly also destructive interference occurs. To make this statement
more precise, one would need a detailed quantum model for LEDs.
3.3
Why AD followed by DI is needed to induce enhanced photon emissions?
Why should AD period followed by DI period be most effective in inducing photon emissions? Why the
flux quanta (flux tubes) do not induce any effects, when the angular velocity is constant and frequency
is absent (constant magnetic field)?
1. Accelerated rotation during AD period corresponds at quantum level to an application of magnetic
flux tubes from directions φn = n × 2π/8 such that the duration of the pulse is reduced in discrete
steps. The process should generate frequencies coming as harmonics of fn = 1/Tn . The patterns
of magnetic field consisting of periods of constant magnetic field lasting 1 ms and fixed for AD and
DI to be ”physiologically patterned” determines the Fourier decomposition. The duration of 1 ms
brings in harmonics of kHz resonance frequency.
2. The variation of the duration of the magnetic field makes possible to scan a wide range of resonance
frequencies of the cell culture. The process would be like tuning a radio. At special frequencies
resonant coupling to the frequency of magnetic field and to the frequency defined by the duration of
magnetic field becomes possible and enhanced dark photon emissions take place. If the fundamental
frequency were not varied, the effect would occur only for very special pulse durations.
3. Why the visible photons were observed only during the beginning of DI phase? If the emitted
photons were dark having very long wave length but energy of visible photon, they would not have
been detected during AD phase. The decay of dark photons after the beginning of DI phase to
bunches of ordinary photons could explain the observed enhanced emissions of visible photons.
3.4
Why the magnetic pulses from a given direction arrived with frequency
of 10 Hz?
The magnetic pulses arriving from a given direction to the cell culture dish/LED came with frequency
10 Hz. That a fundamental biorhythm is in question, cannot be an accident. In TGD framework 10 Hz
frequency corresponds to the secondary p-adic time scale assignable to electron and defines the size scale
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
189
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
of causal diamond assigned with electron. This conforms with the assumption that electronic Cooper
pairs are fundamental for consciousness serving also as carriers of super-current through cell membrane.
In fact, all elementary particles correspond in zero energy ontology to macroscopic time scales via the
secondary p-adic time scales associated with them and for quarks the time scales correspond to frequencies
of order 10 ms.
4
Third article
Third article has the title Experimental Demonstration of Potential Entanglement of Brain Activity over
300 Km for Pairs of Subjects Sharing the Same Circular Rotating, Angular Accelerating Magnetic Fields:
Verification by s− LORETA, QEEG Measurements.
In the third article [7] the group reports excess correlation of brain activity of subject persons separated
by 300 km and sharing the same circular rotating, angular accelerating magnetic fields. The abstract of
the article is following.
In order to test the presence of excess correlation, or entanglement, pairs of subjects separated by 300
km were either exposed or not exposed to specific configurations of circular magnetic fields with changing
angular velocities that dissociated the phase and group components. When one person in the pair was
exposed to sound pulses but not to light flash frequencies within the classical electroencephalographic band,
there were discrete changes in power within the cerebral space of the other person even though they were not
aware of the stimulus times and separated by 300 km. The intra-cerebral changes that only occurred if the
magnetic fields were activated around the two cerebrums simultaneously were discrete and involved about
single, punctate volumes of about 0.13 cc (125 mm3 ). The potential energy from the applied magnetic
field within this volume was calculated to be about 6 × 10−14 J and with an average brain power frequency
of 10 Hz would result in 6 × 10−13 W. Assuming π · 10−2 m2 for the surface area of the cerebrum, this
is equivalent to ∼ 2 · 10−11 Wm−2 . This power density is the same order of magnitude as that associated
with photon emission during cognition. Given the average of 6 × 106 neurons per 125 mm3 , the induced
energy is equivalent to about 10−20 J per neuron. This value can be considered a quantum of universal
energy and would be congruent with a condition that could promote non-locality.
4.1
Experimental arrangement and results
If I have understood correctly, the experimental arrangement was roughly following.
1. Two subject persons were involved. Second subject was 300 km away. The other subject person
received stimuli at various frequencies of sound or flashes of light while the other person was unaware
of these representations. Both members of the pair were exposed to a rotating, circular magnetic
field whose frequency modulation would vary with rotation angle. This guarantees that the phase
and group velocities of the magnetic field varied and were different.
2. It seems safe to assume that the magnetic field pattern used to stimulate brains of subject persons
was identical with that applied in the second experiment.
Authors report a correlation between subject persons in the sense that there discrete changes in EEG
power with the cerebral space of the other person even if he/she was not aware of the stimulus times.
The effect occurred only if the phase and group velocities assignable to the magnetic field were different.
Authors interpret this as entanglement identified as excess correlation if the fields were activated around
cerebrum simultaneously and were discrete and involved about single punctuate volumes of about 125
mm3 . Entanglement in this sense need not correspond to quantum entanglement although it could make
it possible.
Authors introduce what they call quantum universal energy E = 10−20 J, and estimate the that this is
the induced energy per neuron transferred from the magnetic field to energy of EEG. In particle physicist’s
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
190
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
units this gives E = 6.24 × 10−2 eV. This would naturally correspond to energy gained by electron or
proton in the resting potential Erest , which is above Emin = 6.15×10−2 eV. Note that threshold potential
for nerve pulse generation corresponds to energy Ethr = 5.5 × 10−2 eV. On the other hand, also the first
experiment and predecessor of the second experiment involved visible photon emissions which suggests
that also visible photons were emitted and they came from the transitions of the proton spin network
associated with cell membrane proposed by Wu and Hu [8].
4.2
TGD based interpretation
TGD interpretation should rely on the notion of magnetic body and a model for neuronal membrane as
a super-conductor - at least electronic but possibly also ionic super-conductor), cyclotron Bose-Einstein
condensed of biologically important ions, and the spin network of dark protons associated with the cell
membrane discussed in TGD based model for the outcome of the experiment described in the first article.
1. The flux tubes of the rotating magnetic field would connect the subject persons to single coherent
unit reacting to the stimuli posed on second subject like single unit. TGD assigns to the magnetic
bodies large effective value of Planck constant so that photons with energies of order E would
correspond to much longer wavelengths essential for the coherence in scales of order few wave
lengths.
2. The wave length λ = 300 km could correspond to the Planck constant ~ef f ' λ/λ0 = 1.5 × 1010 × ~,
where one has λ0 = c/E~ ' 20 µm is the wavelength of photon with ”quantum universal energy”.
This energy is in IR region just around thermal threshold. The corresponding period and frequency
are T = c/λ = 1 ms and f = 1 kHz, which correspond to fundamental time scales for cell membrane
with 1 ms defining the time scale of nerve pulse and 1 kHz defining an important resonance frequency
in brain associated with the generation of coherence. Probably this is not an accident. The authors
indeed mention that the effect is maximal at distance of 300 km.
Concerning the detailed interpretation of the experiment there are several options. First, TGD suggests two alternative models for cell membrane as Josephson junction involving currents of electron Cooper
pairs and possibly also bosonic ions or Cooper pairs of fermionic ions. For the conservative option the
cell membrane would be far from vacuum extremal carrying strong induced Kähler field. For the nonconservative option the cell membrane would be nearly vacuum extremal making it maximally sensitive
to sensory input. Secondly, the universal quantum suggests emission of dark IR photons, whereas the
emission of visible photons associated with cognition suggests visible photons.
1. The quantum universal energy E = eVrest = 6.24 × 10−2 eV would naturally correspond to the
energy gained by electron or proton in a membrane potential slightly above the threshold potential.
Also the conservative option for cell membrane as Josephson junction would predict Josephson
radiation emitted at multiples of Josephson frequency E = eVrest or E = eEthr .
2. The non-conservative option for the cell membrane as Josephson junction predicts that the emitted
photons have visible energies. This option might be realized for photoreceptors in retina, which react
to the sensory stimulus by variation of membrane potential instead of nerve pulse. The correlation
of cognition with the emission of visible photons allows also to consider the possibility that some
neurons are near-to vacuum extremals (also glial cells as cells which do not generate nerve pulses
could be such). Since visible photon emissions are mostly from the right hemisphere, one can ask
whether the emissions from the left hemisphere are in IR region and those from right hemisphere in
visible region and whether the different ground states of neurons as far-from resp. near-to vacuum
extremals could distinguish between right and left hemisphere.
3. How does the spin network model based on dark proton strings relate to this? Since the photons
have biological functions, the energies of all kinds of EEG photons should be in the same region of
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
191
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
spectrum: visible or IR for a given hemisphere. For near-to vacuum extremals the argument of Hu
and Wu would be modified by replacing ordinary magnetic field with a combination of Z 0 magnetic
field and ordinary magnetic field. This would imply that the energy scale would increase just as it
does when Z 0 electric field dominates over em electric field. Therefore also the photons emitted by
spin network at the right hemisphere would be dark EEG photons with energies of visible photons.
4. An alternative interpretation encouraged by the photon emission associated with cognition is that
λ0 corresponds to the energy of visible photon resulting in the transformation of dark ELF photon
produced in the triplet-to-singlet transition of proton pair associated with the cell membrane as
described in the interpretation of the first experiment. For a photon with energy 1.77 eV at the
red end of visible spectrum this would give ~ef f = 4.3 × 1011 . Interestingly, Cyril Smith [1] reports
on basis of his own experimentation that the transformation of low energy photons to high energy
photons and vice versa takes place for frequency ratio fh /fl = 2 × 1011 : the interpretation would
be also in this case in terms of ~ef f [21].
5
Conclusions
The results of the experiments of Persinger et al can be understood in the framework of TGD and the
findings allow to develop a more precise view about the role of dark electrons, protons, and ions in TGD
inspired quantum biology.
1. The identification of the magnetic flux quanta connecting two systems as generators of macroscopic
quantum coherence finds experimental support.
2. The proposal of Hu and Wu about proton spin networks associated with cell membrane has a TGD
counterpart in terms of dark proton strings allowing interpretation as dark DNA. The spin-paired
protons are assigned to the hydro-philic ends of the two lipids in the layers of the cell membrane and
the dark proton strings define an analog of DNA double strand. The model of Wu and Hu is subject
to the same objections as the model for cyclotron Bose-Einstein condensates and is circumvented
by introducing the hierarchy of effective Planck constants.
3. The fact that photon emissions are detected only from the right hemisphere suggests that both
options for the cell membrane as Josephson junction are realized: far-from vacuum extremal option
for the neurons of the left hemisphere with emissions in infrared and near-to vacuum extremal for
the neurons of the right hemisphere.
To sum up, the resulting framework allows an overall view about the roles of both dark electrons,
dark protons, and dark ions in quantum biology according to TGD.
References
Biology and Neurocience
[1] C. Smith. Learning From Water, A Possible Quantum Computing Medium. CHAOS, 2001.
[2] M. A. Persinger B. T. Dotta. Doubling of local photon emissions when two simultaneous, spatiallyseparated, chemiluminescent reactions share the same magnetic field configurations. Journal of
Biophysical Chemistry. http: // core. kmi. open. ac. uk/ display/ 5850998 , 3(1), 2012.
[3] C. F. Blackman. Effect of Electrical and Magnetic Fields on the Nervous System, pages 331–355.
Plenum, New York, 1994.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
192
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
[4] Hunter et al. Cerebral dynamics and discrete energy changes in the personal environment during
intuitive-like states and perceptions. Journal of Consciousness Exploration & Research. http: //
jcer. com/ index. php/ jcj/ article/ view/ 116 , 1(9):1179–1197, 2010.
[5] M. Persinger et al. Congruence of Energies for Cerebral Photon Emissions, Quantitative EEG
Activities and 5 nT Changes in the Proximal Geomagnetic Field Support Spin-based Hypothesis
of Consciousness. Journal of Consciousness Expolaration & Research. http: // jcer. com/ index.
php/ jcj/ article/ view/ 277 , 2013.
[6] M. Persinger et al. Demonstration of Entanglement of Pure Photon Emissions at Two Locations
That Share Specific Configurations of Magnetic Fields: Implications for Translocation of Consciousness. Journal of Consciousness Expolaration & Research. http: // jcer. com/ index. php/ jcj/
article/ view/ 278 , 2013.
[7] M. Persinger et al. Experimental Demonstration of Potential Entanglement of Brain Activity Over
300 Km for Pairs of Subjects Sharing the Same Circular Rotating, Angular Accelerating Magnetic
Fields: Verification by s− LORETA, QEEG Measurements. Journal of Consciousness Expolaration
& Research. http: // jcer. com/ index. php/ jcj/ article/ view/ 279 , 2013.
[8] H. Hu and M. Wu. Action Potential Modulation of Neural Spin Networks Suggests Possible Role of
Spin. NeuroQuantology. http: // cogprints. org/ 3458/ 1/ SpinRole. pdf , (4):309–317, 2004.
[9] H. Hu and M. Wu. Thinking outside the box: the essence and implications of quantum entanglement.
NeuroQuantology, 5:5–16, 2006.
[10] L. Sidorov and K. W. Chen. An Biophysical Mechanisms of Genetic Regulation: Is There a Link to
Mind-Body Healing? DNA Decipher Journal, 2(2):177–205, 2012.
Books and articles related to TGD
[11] M. Pitkänen. About Nature of Time. In TGD Inspired Theory of Consciousness. Onlinebook.
http://tgdtheory.com/public_html/tgdconsc/tgdconsc.html#timenature, 2006.
[12] M. Pitkänen. About the New Physics Behind Qualia. In Quantum Hardware of Living Matter.
Onlinebook. http://tgdtheory.com/public_html/bioware/bioware.html#newphys, 2006.
[13] M. Pitkänen. Bio-Systems as Super-Conductors: part II. In Quantum Hardware of Living Matter.
Onlinebook. http://tgdtheory.com/public_html/bioware/bioware.html#superc2, 2006.
[14] M. Pitkänen. Conscious Information and Intelligence. In TGD Inspired Theory of Consciousness.
Onlinebook. http://tgdtheory.com/public_html/tgdconsc/tgdconsc.html#intsysc, 2006.
[15] M. Pitkänen. Dark Forces and Living Matter. In p-Adic Length Scale Hypothesis and Dark Matter Hierarchy. Onlinebook. http://tgdtheory.com/public_html/paddark/paddark.html#darkforces,
2006.
[16] M. Pitkänen. Dark Matter Hierarchy and Hierarchy of EEGs. In TGD and EEG. Onlinebook.
http://tgdtheory.com/public_html/tgdeeg/tgdeeg.html#eegdark, 2006.
[17] M. Pitkänen. DNA as Topological Quantum Computer. In Genes and Memes. Onlinebook. http:
//tgdtheory.com/public_html/genememe/genememe.html#dnatqc, 2006.
[18] M. Pitkänen. Does TGD Predict the Spectrum of Planck Constants? In Towards M-Matrix.
Onlinebook. http://tgdtheory.com/public_html/tgdquant/tgdquant.html#Planck, 2006.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | March 2013 | Volume 4 | Issue 2 | pp. 174-193
193
Pitkänen, M., Persinger Group’s Recent Experiments, Spin Network and TGD
[19] M. Pitkänen. General Ideas about Many-Sheeted Space-Time: Part I. In Physics in ManySheeted Space-Time. Onlinebook. http://tgdtheory.com/public_html/tgdclass/tgdclass.
html#topcond, 2006.
[20] M. Pitkänen. General Ideas about Many-Sheeted Space-Time: Part II. In Physics in ManySheeted Space-Time. Onlinebook. http://tgdtheory.com/public_html/tgdclass/tgdclass.
html#newviews, 2006.
[21] M. Pitkänen. Homeopathy in Many-Sheeted Space-Time. In Bio-Systems as Conscious Holograms.
Onlinebook. http://tgdtheory.com/public_html/hologram/hologram.html#homeoc, 2006.
[22] M. Pitkänen. Nuclear String Hypothesis. In p-Adic Length Scale Hypothesis and Dark Matter Hierarchy. Onlinebook. http://tgdtheory.com/public_html/paddark/paddark.html#nuclstring,
2006.
[23] M. Pitkänen. p-Adic Physics as Physics of Cognition and Intention. In TGD Inspired Theory of Consciousness. Onlinebook. http://tgdtheory.com/public_html/tgdconsc/tgdconsc.html#cognic,
2006.
[24] M. Pitkänen. p-Adic Physics: Physical Ideas. In TGD as a Generalized Number Theory. Onlinebook.
http://tgdtheory.com/public_html/tgdnumber/tgdnumber.html#phblocks, 2006.
[25] M. Pitkänen. Quantum Model for Nerve Pulse. In TGD and EEG. Onlinebook. http://tgdtheory.
com/public_html//tgdeeg/tgdeeg/tgdeeg.html#pulse, 2006.
[26] M. Pitkänen. TGD as a Generalized Number Theory: p-Adicization Program. In TGD as a Generalized Number Theory. Onlinebook. http://tgdtheory.com/public_html/tgdnumber/tgdnumber.
html#visiona, 2006.
[27] M. Pitkänen. Wormhole Magnetic Fields. In Quantum Hardware of Living Matter. Onlinebook.
http://tgdtheory.com/public_html/bioware/bioware.html#wormc, 2006.
[28] M. Pitkänen. What p-Adic Icosahedron Could Mean? And What about p-Adic Manifold? In TGD
as a Generalized Number Theory. Onlinebook. http://tgdtheory.com/public_html/tgdnumber/
tgdnumber.html#picosahedron, 2013.
[29] M. Pitkänen. Two attempts to understand PK. http://tgdtheory.com/public_html/articles/
PKoptions.pdf, 2012.
ISBN: 2153-8212
Journal of Consciousness Exploration &Research
Published by QuantumDream, Inc.
www.JCER.com |
Survey of Consciousness Theory from Computational
Perspective
arXiv:2309.10063v1 [q-bio.NC] 18 Sep 2023
At the Dawn of Artificial General Intelligence
Zihan Ding∗
Princeton University
zihand@princeton.edu
Xiaoxi Wei∗
Imperial College London
xiaoxi.wei18@imperial.ac.uk
Yidan Xu∗
University of Michigan
yidanxu@umich.edu
Abstract
Human consciousness has been a long-lasting mystery for centuries, while machine intelligence and consciousness is an arduous pursuit. Researchers have developed diverse theories
for interpreting the consciousness phenomenon in human brains from different perspectives
and levels. This paper surveys several main branches of consciousness theories originating
from different subjects including information theory, quantum physics, cognitive psychology,
physiology and computer science, with the aim of bridging these theories from a computational
perspective. It also discusses the existing evaluation metrics of consciousness and possibility for
current computational models to be conscious. Breaking the mystery of consciousness can be an
essential step in building general artificial intelligence with computing machines.
Contents
1
2
3
Introduction
3
1.1
A Platonic Dialogue About Human Consciousness . . . . . . . . . . . . . . . . .
3
1.2
Definition of Consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
5
1.3
Measurement of Consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . . .
6
1.4
Consciousness and Intelligence . . . . . . . . . . . . . . . . . . . . . . . . . . . .
6
1.5
Consciousness and Free Will . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
7
1.6
Consciousness while Asleep . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
9
1.7
Overview of Consciousness Theories . . . . . . . . . . . . . . . . . . . . . . . . .
10
Information Integration Theory
10
2.1
Information Entropy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
10
2.2
Basics Concepts of IIT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
11
2.3
Measurement of Information Integration . . . . . . . . . . . . . . . . . . . . . . .
13
2.4
Biological Evidence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
15
Consciousness as a State of Matter
15
3.1
16
∗
Basics of Quantum Mechanics . . . . . . . . . . . . . . . . . . . . . . . . . . . .
The authors contributed equally.
Preprint with all copyright reserved.
4
5
6
3.2
Integration Principle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
17
3.3
Independence Principle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
18
3.4
Dynamics principle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
18
Orchestrated Objective Reduction Theory
19
4.1
Consciousness as Orchestrated Objective Reduction . . . . . . . . . . . . . . . . .
19
4.2
Free Will in Neurons . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
20
4.3
Diósi-Penrose Objective Reduction . . . . . . . . . . . . . . . . . . . . . . . . . .
20
4.4
Evidence for Objective Reduction of Quantum State . . . . . . . . . . . . . . . . .
20
Global Workspace Theory
20
5.1
The Theatre of Consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . . .
20
5.2
Computational Models of GWT . . . . . . . . . . . . . . . . . . . . . . . . . . .
22
Higher-Order Theories
23
6.1
Higher-Order Perception Theory . . . . . . . . . . . . . . . . . . . . . . . . . . .
23
6.2
Higher-Order Thought Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . .
24
6.3
Self-Representational Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
25
6.4
Other theories and perspectives in HOT . . . . . . . . . . . . . . . . . . . . . . .
25
7 Attention Schema Theory
8
9
25
7.1
Formulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
25
7.2
I-consciousness and M-consciousness . . . . . . . . . . . . . . . . . . . . . . . .
26
7.3
AST as a Unification of GWT and HOT . . . . . . . . . . . . . . . . . . . . . . .
27
Conscious Turing Machine
27
8.1
Formulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
27
8.2
CTM for Consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
28
8.3
Relationships with Other Theories . . . . . . . . . . . . . . . . . . . . . . . . . .
28
Physiological Evaluation Metric of Consciousness
29
9.1
Metrics Based on Electrical Signals . . . . . . . . . . . . . . . . . . . . . . . . .
29
9.2
Metrics Based on Behaviors . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
31
10 Look Ahead: Can Computational Models Be Conscious?
31
10.1 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
31
10.2 Large Language Model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
33
10.3 Emerging Intellectual Capability of LLM - Turing Test . . . . . . . . . . . . . . .
36
10.4 Consciousness of LLM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
37
11 Concluding Remarks
42
2
1
Introduction
Consciousness is a complex and elusive phenomenon that remains one of the greatest mysteries of
science. It has been the subject of philosophical inquiry for centuries, and more recently, scientific
investigation. We, humans, are not clear about why and how consciousness exists in our brains or
even hold diverged opinions on whether we truly have consciousness. Existing consciousness theories
have provided different interpretations of the human conscious process.
This paper provides a comprehensive exploration of the theoretical foundations of consciousness from
interdisciplinary perspectives. Chapter 1 endeavors to characterize the concepts related to consciousness, by differentiating the consciousness from others such as awareness, arousal, and wakefulness.
This chapter further emphasizes the importance and difficulties of the human consciousness problem,
with the aim of drawing attention from different research communities to jointly investigate this problem. Chapters 2, 3, and 4 elucidate the mathematical and physical underpinnings of consciousness.
Specifically, Chapter 2 introduces Information Integration Theory, which outlines the conditions
for information entropy required by a conscious entity, offering insights into the informational characteristics that consciousness might exhibit. Chapter 3 and 4 discusses Consciousness as a State of
Matter and Orchestrated Objective Reduction Theory, both approaching consciousness problem
from a physics standpoint. These two chapters discuss the specific features that consciousness, as
a state of matter, should possess, along with the principles that some quantum theorists propose as
the basis for the generation of consciousness. Subsequent Chapters 5, 6, 7 and 8 survey several
influential theories of consciousness and succinctly summarize research on computational models
associated with each theory, including the Global Workspace Theory ( 5), High-Order Theories
( 6), Attention Schema Theory ( 7) and Conscious Turing Machine ( 8). In Chapter 9, a brief
overview of contemporary biomedical measurement methods for consciousness, grounded in electrophysiological signals and behavioral indicators, is provided. In the final Chapter 10, we engage in
a discursive examination of artificial intelligence (AI) consciousness, particularly delving into the
question of whether Large Language Models as instances of advanced computational models possess
consciousness and exploring the necessary and sufficient conditions for AI consciousness.
In summary, this paper offers a comprehensive review of consciousness from various subjects
encompassing information theory, quantum physics, cognitive psychology, physiology, and computer
science, with the aim of bridging these theories from a computational perspective for building future
AI consciousness.
To give the readers a primal taste of this topic, a dialogue revolving the consciousness problem is
provided in the following section.
1.1
A Platonic Dialogue About Human Consciousness
One day, I met two PhD students in the modern world discussing the consciousness problem within
the human brain. This conversation starts with the relationship between consciousness and the
physical world, discussing thoughts about what consciousness is. The confusion in this conversation
serves as the motivation of this study and introduces the essential problems that this article aims to
address. Here is the conversation.
Athena: Hey, I was looking at the results of the double-slit experiment, but I’m struggling to
understand what determines the photons to choose which slit to go through, what happens here?
Galileo: Hey, it’s just the wave-particle duality of the photons, and the state of the photon
collapses only when you observe it on the screen. It is just random. Don’t dig too much into it.
Athena: What do you mean by ‘random’? Does this world ultimately have a random essence?
Even Einstein says that God does not play dice.
Galileo: Your measurement affects its state, which determines the slit it goes through in the
double-slit experiment.
Athena: So my mental status determine the state of the photon? Its state may change if I choose
to observe it in a different way, say later for 0.00001 seconds than the intended observation.
Galileo: Yeah, maybe. And your mental status is also a stochastic process, right? You have your
free will or consciousness.
Athena: Consciousness. Do you really believe in its existence? What if I’m deterministic, fully
determined by the underlying physical and chemical rules?
3
Galileo: But quantum mechanics assumes the basic principle that the photons, and particles in
your body, including your brain, still have a probabilistic state, right? So you are also following
a stochastic process instead of a deterministic one.
Athena: You are right. The state collapse process is assumed to have true randomness, and
this process may happen in my brain, affecting my decision, and also which slit these photons
may go through. But I still don’t quite believe in the existence of my consciousness. The state
decoherence may happen for a system as large as my brain, so there is no quantum property and
I may still be deterministic.
Galileo: I think the existence of consciousness is a belief that differs from person to person.
Athena: Wait, but what is consciousness? We cannot discuss its existence without a clear
definition. The consciousness seems to describe the subjective experience but without a rigorous
definition. I’m wondering where and when the conscious process happens.
Galileo: I guess it’s in the cerebral cortex or thalamus. However, for such a phenomenon to
happen, I would say most functional parts of the brain may have a collaborative process to
trigger the consciousness.
Athena: I agree. Also if we assume a stone, or a tree, cannot be as conscious as a human, then
the system has to have a certain level of computational power.
Galileo: Also, I cannot imagine a system having consciousness without memory.
Athena: I may disagree on that. I think a patient with brain damage of losing his memory still
has consciousness.
Galileo: May be an evidence. Do you think consciousness retains during sleep?
Athena: This can be a complicated problem. You know there are multiple stages during sleep,
including non-rapid eye movement (NREM) and rapid eye movement (REM). The levels of
consciousness can be different for different stages.
Galileo: Agreed. The dream happens during the REM, right? It feels like I have consciousness
during the dream, so I guess I’m conscious at REM. But it’s still quite different from the
wakefulness in experience.
Athena: I’m not sure, it’s quite complicated. But the essential difference between dream and
wakefulness is that during sleep there is no external sensory input to the brain, all the experiences
are fake and fabricated by the brain itself. If the consciousness happens during the dream, it
indicates that external sensory inputs may not be necessary for the system to be conscious.
Galileo: I guess so. It seems the consciousness is quite close to the subjective experience, even
if I’m not sure if subjective experience is real existence or a fake hallucination by humans.
Athena: It seems the ‘subjective experience’ is an equivalent phrase of consciousness in some
books. But this definition is still unclear to me. Also, the ‘real’ and ‘fake’ problem is also
unclear to me. If our measurement of the world can affect its state, what does it even mean by a
‘real’ observation of the world and a ‘fake’ one? After all, they are just the mirrored signals in
our brains, which can not directly represent the state of the real world.
Galileo: Well, that’s a very philosophically pessimistic perspective. Speaking of the definition
of consciousness, if we assume consciousness is defined as ‘subjective experience’, it seems
not very related to another concept called intelligence. Nowadays, people are building artificial
intelligence in computers, is it also consciousness? This could be an interesting problem! Do
you think it’s just about the Turing test [Turing, 2009]?
Athena: I don’t think so. The focus of that paper is discussing whether the Turing machine can
achieve human-level intelligence. Please notice the difference in the words here, it’s intelligence
but not consciousness! I assume a program passing the Turing test only means that it’s as
intelligent as a human, but not conscious.
Galileo: Thanks for reminding me of that. It seems that intelligence and consciousness are
two different things. But remember that at the beginning of the discussion, we mentioned that
consciousness may require a certain level of computational power, and this computational power
may be phrased as intelligence.
Athena: Maybe, the intelligent property seems to be a necessary condition for the consciousness
to emerge, but I’m not sure to which extent the consciousness requires the intelligence to be.
Galileo: Yeah, this is undiscovered and could be a good research topic. However, if a creature is
already intelligent enough to survive in the world, why does it still require consciousness?
4
Athena: Good question. According to Darwin’s theory of evolution, the existing creatures in
the world should only exhibit those skills in favor of their survival through natural selection. If
consciousness exists in humans, it indicates that it has some benefits for humans to survive in
environments, and those without it are erased over history. But the trees and flowers still exist,
which really troubles me.
Galileo: Trees and flowers are of different species from humans. Maybe for certain species, it
requires to have consciousness, like animals.
Athena: Well, but I still feel unclear about why consciousness exists in humans or other animals,
if assumed to exist.
Athena: It seems like consciousness theory can be a very complicated subject with correlations to
some very different subjects, like physics, biology, computer science, neuroscience, information
theory, etc. It can be very difficult. But let’s start to investigate at least!
The above conversation is a microcosm of the discussions by the authors of the paper for starting
the investigation of the consciousness problem. We will start the discussion with the definition of
consciousness (Sec. 1.2), and the relationship between consciousness and intelligence (Sec. 1.4),
consciousness and free will (Sec. 1.5). Then we have a brief overview of the existing consciousness
theories (Sec. 1.7) and a further discussion about consciousness while asleep (Sec. 1.6).
1.2
Definition of Consciousness
Consciousness, Awareness, Wakefulness and Arousal: Consciousness is a complex and multifaceted concept that has been studied extensively in the fields of neuroscience, psychology, and
philosophy. Existing research typically defines consciousness as comprising two main components:
arousal (wakefulness) and awareness (subjective experience) [Lendner et al., 2020]. Arousal refers to
the overall state of alertness or wakefulness, while awareness refers to the subjective experience of
perceiving and interpreting sensory information.
Typically, arousal is indicated by the opening of the eyes, while awareness is inferred by the ability
to follow commands [Lee et al., 2022]. However, in certain instances, such as during dreaming,
subjective experience can still occur despite the absence of full wakefulness. Consciousness is
considered to be absent during sleep or anesthesia, but in some cases, it can still be present, depending
on the level of arousal and awareness. Consciousness, awareness, wakefulness, and arousal are related
but distinct concepts in the study of the human mind and brain. We provide descriptive definitions for
each concept according to the existing literature as follows:
Consciousness refers to the subjective experience of being aware of one’s thoughts, feelings, sensations, and surroundings. It is often described as the state of being awake and aware of one’s
surroundings and internal states. As an important concept in discussing the consciousness problem,
qualia refers to the subjective and personal experience of sensory information, such as the way we
perceive colors, sounds, tastes, and smells. It is the subjective experience of sensory perception that
cannot be objectively measured or observed by others.
Awareness refers to the ability to perceive, process, and comprehend information from one’s environment or inner experience. It includes both conscious and unconscious processes and can range from
simple sensory perception to complex cognitive processes such as attention, memory, and reasoning.
Arousal refers to the level of responsiveness of the brain and body to internal and external stimuli. It
is a physiological state that ranges from a state of low arousal, such as drowsiness or relaxation, to
high arousal, such as intense excitement or fear.
Wakefulness refers to the state of being awake and not asleep. It is a physiological state characterized
by the presence of the electrical activity of the brain and the ability to respond to external stimuli.
In summary, consciousness is a subjective experience of being aware of one’s thoughts, feelings,
and surroundings, while awareness is the ability to perceive, process, and comprehend information.
Wakefulness is a physiological state characterized by being awake, which is usually regarded
identically as awareness. Arousal is the level of responsiveness to stimuli. Awareness and arousal are
necessary conditions for consciousness, but they are not sufficient to arouse the consciousness, and
consciousness can occur in the absence of full awareness and high arousal levels.
5
Conscious State
Arousal
Awareness
Healthy wakefulness
REM1 sleep with dreams
NREM2 sleep without dreams
Anesthesia induced with ketamine
Anesthesia induced with propofol or xenon
Minimally conscious state
Unresponsive wakefulness syndrome
high
low
low
low
low
high
high
high
high
low
high
low
high
low
1
2
REM: rapid eye movement
NREM: non-rapid eye movement
Table 1: The arousal and awareness levels of consciousness under different states (results adapted
from Lee et al. [2022])
1.3
Measurement of Consciousness
Recent studies have developed effective measures of human consciousness [Seth et al., 2008, Demertzi et al., 2017], such as the electrical signal-based metrics like Perturbational Complexity Index
(PCI) [Casali et al., 2013] and Bispectral Index (BIS) [Rosow and Manberg, 2001, Johansen, 2006]
and behavior-based metrics like the Glasgow Coma Scale (GCS) [Jones, 1979, Sternbach, 2000], The
Coma Recovery Scale-Revised (CRS-R) [Giacino et al., 2004] and Full Outline of Unresponsiveness
(FOUR) [Wijdicks et al., 2005]. Details for each physiological evaluation metric are discussed in
Sec. 9. In the following paragraphs, we take the PCI metric as an example to distinguish the concepts
of arousal and awareness in different conscious states.
The ability to accurately measure consciousness has important implications for understanding and
treating conditions that affect consciousness, such as coma, anesthesia, and brain injury. PCI
was developed from electroencephalographic (EEG) responses to direct and noninvasive cortical
perturbation with transcranial magnetic stimulation (TMS). The PCI quantifies the complexity of
deterministic patterns of significant cortical activation evoked by TMS to derive an empirical cutoff
that reliably discriminates between unconsciousness and consciousness in various states, including
REM sleep, wakefulness, ketamine-induced anesthesia, and conscious brain-injured patients.
In the PCI study by Casali et al. (2013) [Casali et al., 2013], arousal and awareness levels serve as
indicators of the degree of human consciousness. The arousal and awareness levels of consciousness
under different states are summarized in Table 1, which shows under different states the consciousness
will appear differently in human brains [Lee et al., 2022]. Compared with the full wakefulness of a
normal person, the sleeping stages like REM or NREM have lower levels of arousal or awareness
and are commonly believed to be not as “conscious” as a wakeful state. There are pharmacology
approaches to achieve similar low levels of arousal and awareness with anesthesia, leading to
incomplete conscious states of a human. From a pathology view, existing patients with a minimally
conscious state (MCS) will appear to have relatively high levels of arousal and awareness but still
less consciousness, which is evidence of the fact that arousal and awareness are necessary but not
sufficient conditions for consciousness. People with unresponsive wakefulness syndrome will have
high arousal but low awareness.
1.4
Consciousness and Intelligence
In the well-known paper by Alan Turing, he made a comment on the consciousness argument against
Turing machine [Turing, 2009]:
"I do not wish to give the impression that I think there is no mystery about consciousness. There is,
for instance, something of a paradox connected with any attempt to localise it. "
Considering the question in the paper is whether a machine can think like a human, Turing proposed
the famous imitation game as a way to test machine intelligence. Intelligence and consciousness are
widely considered two different properties of the brain. In Life 3.0 [Tegmark, 2018] by Max Tegmark,
intelligence is defined as the ability to accomplish complex goals, and consciousness is defined as
subjective experience. The consciousness seems to be more mysterious than intelligence, and harder
6
to measure. As depicted in the consciousness “pyramid” in Fig. 1 (originally in Tegmark [2018]),
the intelligence-related problems are the easiest, which is also claimed by David Chalmers. This
type of problem typically does not require to consider the subjective experience of the experimental
subjects. A hard problem is to find the physically interpretable features for distinguishing conscious
and unconscious processes. The next level question is how the consciousness happens and what the
determined factors are. The final and hardest problems related to the explanation of the existence of
consciousness, or why consciousness exists in any system?
Figure 1: The hardness of different levels of the problems related to a conscious mind.
For the reasons for the existence of consciousness in human brains, a quote from Stephen Wolfram
mentions the limitation of self-modeling and time-persistence are two key factors for humans to have
consciousness:
"The fact that we have coherent consciousness is a consequence of two things: 1. That we are
computationally bounded, so the universe does not contain enough resources for us to construct a
complete model of ourselves. 2. That we believe that we are persistent in time, and hence assume
constancy where there is none."
Consciousness is a complex and multifaceted phenomenon that has been studied by philosophers,
psychologists, neuroscientists, and others for a long history. Even so, consciousness remains mysterious for modern society, and people refer to it as the hard problem of consciousness, which was
initially proposed by David Chalmers in 1995 [Chalmers, 1995, 1997]. It is generally understood as
the experience or awareness of subjective mental states such as thoughts, perceptions, emotions, and
sensations. The hard problem indicates the reasons for the existence of such subjective experiences in
human minds. Consciousness is closely linked to the functioning of the brain, but its precise nature
and mechanisms are still not fully understood. Some theories suggest that consciousness emerges
from the integration of sensory information, while others propose that it is an intrinsic property of
the universe or a fundamental aspect of reality itself. The quote by Stephen Wolfram suggests that
the experience of coherent consciousness may depend on our computational limitations and our
assumption of temporal persistence. The argument suggests that we believe we are persistent beings
that exist over time, even though there is no actual constancy in the universe.
1.5
Consciousness and Free Will
Free will is defined as the ability that humans to make choices and decisions that are not solely
determined by biological, environmental, or external factors. Whether humans have free will is highly
controversial and unknown. However, this concept is believed to be closely related to consciousness.
In Fig. 2, we depict an architecture unifying several consciousness theories to be introduced later
in this article, as well as illustrating the relationship between consciousness and free will. In Fig. 2,
the human brain has interactions among the low-level modules and consciousness module, where
the conscious experiences happen in human brains [Baars, 2003, Baars and Franklin, 2003, 2007,
7
2009, Locke, 1948, Armstrong, 1981, Armstrong and Malcolm, 1985, Lycan, 1996, Armstrong, 2002,
Lycan, 2004, Rosenthal, 2009, 2012, 2004, Byrne, 1997, Brown et al., 2019, Graziano and Webb,
2015, Graziano et al., 2020]. The low-level modules involve external processors, internal processors,
and memory. The external processors handle the inputs and outputs of the human brain, including the
image processor, sound processor, gustatory processor, olfactory processor, tactile processor, motor
activators, speaking modules, etc. Each module processes the input information and outputs the
processed signals to other parts. Internal processors include the logic processor, language processor,
etc. Each will process information with outputs from external processors, or spontaneously without
external inputs. All these modules have the ability to communicate with other modules and the
memory to accomplish the desired objective, and most of them will generate intermediate outputs as
inputs of other modules. More importantly, beyond all these low-level modules, the consciousness
module has the ability to observe the intermediate outputs from low-level modules, which generates
subjective experiences (also known as consciousness) for a human. This observation process is
also formulated as a self-modeling process in theories like attention schema theory [Graziano and
Webb, 2015, Graziano et al., 2020] or higher-order thoughts/perception in high-order theories [Locke,
1948, Armstrong, 1981, Armstrong and Malcolm, 1985, Lycan, 1996, Armstrong, 2002, Lycan, 2004,
Rosenthal, 2009, 2012, 2004, Byrne, 1997, Brown et al., 2019], etc. Yet these explanations are of
a highly abstract level. The specific components in human brains arsing the consciousness are still
debatable in the literature. There are some works [Baars, 2002] showing that the pre-frontal cortex
may be involved in the higher-level cognitive procedure as an example. Discussions of different
interpretations of those theories will be detailed in later sections. Due to the limited computational
power, the consciousness module will only pay attention to those important information flows, which
is a relatively small subset of all intermediate outputs from low-level modules. This coincides with
the empirical evidence showing that a human can only have dozens of conscious experiences per
second [Tegmark, 2018, 2000].
The existence of genuine free will remains a significant aspect of consciousness theory, albeit one that
lacks sufficient scientific evidence to definitively prove or disprove. To engage in a comprehensive
exploration of the existence of free will and its potential hierarchy within the human brain (Figure 2),
we will bifurcate our discussion into positive and negative hypotheses: (1). assuming the existence of
true free will; or (2). denying such existence of the free will. Therefore we mark the block of free will
with dotted lines. For the first case that free will exists, which is beyond current physics interpretation,
we may seek external variables from beyond the existing mathematical and physics frameworks to
determine the process of human decision-making. The external variables can be regarded as an analog
of the hidden variables in the famous Einstein–Podolsky–Rosen (EPR) paradox [Einstein et al., 1935],
which states that some unobserved hidden variables may exist for explaining the true randomness
in quantum mechanics, as a question of the completeness of quantum mechanics framework by
Albert Einstein and others. Similar as the interpretation of EPR paradox for randomness in quantum
mechanics, the explanation of the true ‘free will’ may also require such external randomness beyond
the known physical systems. More details regarding physical explanations of the existence of free
will are discussed in Sections 3 and 4. This part of free will is shown in Fig. 2 as the blue block
containing the free will, injected by the consciousness module to affect the low-level processes (as
Fig. 3) thus the final outputs from the system. For the second case that true free will does not exist, a
question is what leads to some people think and feel that they also have the so-called ‘free will’? This
phenomenon can be interpreted with the current architecture with a hallucinated ‘free will’ [Wegner,
2004]. The key fact is that the consciousness module can only observe partial intermediate outputs of
low-level modules due to its limited information processing bandwidth, thus the final outputs to the
environment from the system can not be fully determined by these observed pieces of information,
but together with more of other unobserved information. The consciousness module still seeks to
explain the generated outputs by creating hallucinations of ‘free will’ in determining the results.
However, this explanation may be debatable and requires verification. The existence of free will is
also an open problem at present.
8
Figure 2: The overview architecture of consciousness system with free will.
Figure 3: Details of processors in a consciousness system like the human brain.
1.6
Consciousness while Asleep
The human sleep process contains stages including Rapid Eye Movement (REM) and Non-Rapid Eye
Movement (NREM). According to previous research [Lee et al., 2022], NREM is a state where there
is neither arousal nor awareness, whereas REM is a state of awareness without arousal.
Integrated Information Theory (IIT) [Tononi, 2004] suggests that consciousness is reduced during
deep sleep. IIT proposes that consciousness is generated by the integrated information within a
system. According to IIT, the level of consciousness experienced during sleep is dependent on the
degree of integration present in the brain’s activity.
Studies have shown that subjects awakened from deep NREM sleep, especially early in the night,
often report a lack of awareness, even though cortical and thalamic neurons remain active. However,
subjects awakened at other times, mainly during REM sleep or during lighter periods of NREM
sleep later in the night, report dreams characterized by vivid images [Hobson et al., 2000]. From
9
the perspective of integrated information theory, a reduction in consciousness during sleep would be
consistent with the bistability of cortical circuits during deep NREM sleep. Consistent with these
observations, studies using TMS (transcranial magnetic stimulation), a technique for stimulating
the brain non-invasively, in conjunction with high-density EEG (electroencephalogram), show that
early NREM sleep is associated with a breakdown of effective connectivity among cortical areas,
leading to a loss of integration or a loss of repertoire and thus of information [Massimini et al., 2005,
2007]. These findings suggest that the level of consciousness experienced during sleep is dependent
on the degree of integration present in the brain’s activity, with a reduction in integration leading to a
reduction in consciousness.
Overall, IIT suggests that the level of consciousness experienced during sleep is dependent on the
degree of integration present in the brain’s activity, with a reduction in integration leading to a
reduction in consciousness.
1.7
Overview of Consciousness Theories
Diverse theories are developed by researchers to investigate the nature of consciousness and how it
arises from the brain. Some of the most prominent theories include information integration theory
(IIT), consciousness as a state of matter, orchestrated objective reduction (Orch OR) theory, global
workspace theory (GWT), high-order theory (HOT), attention schema theory (AST), consciousness
Turing machine (CTM), etc. IIT (Sec. 2) proposes that consciousness arises from the integration
of information from multiple sensory and cognitive sources. Consciousness as a state of matter
(Sec. 3) analyzes the deficiency of the information integration principle from the physics-principled
calculation. Orch OR theory (Sec. 4) proposes the orchestrated objective reduction process for
explaining the free will in conscious experience from a quantum mechanics perspective. GWT
(Sec. 5) argues that consciousness arises from the activation of a global workspace in the brain, which
integrates information from different sources and broadcasts it to the rest of the brain. HOT (Sec. 6)
asserts that consciousness is the result of higher-order representations of sensory information. AST
(Sec. 7) posits that consciousness is an attentional schema that the brain uses to represent the state of
being conscious. CTM (Sec. 8) theory asserts that consciousness can be described as a computational
process, as an extension of the Turing machine. These theories offer different perspectives on the
nature of consciousness, and each has its own strengths and weaknesses. These theories offer insights
into how it might be studied and understood. We conducted this survey to compare the similarities
and differences of these theories and also summarize the correlations among different theories. More
importantly, we aim to find feasible computational models from these theories for characterizing the
conscious process of the human brain.
2
Information Integration Theory
The theory of information integration postulates that consciousness corresponds to the capacity of
a system to integrate information. It first proposes the axioms of experiences, then postulates the
properties of physical system that would give rise to the intrinsic experiences. In order to achieve
this, the theory claims that the system must have a cause-effect power in itself, not resulting from
any external factor. The cause-effect power of the system is then quantified by the largest minimum
entropy of all sub-systems, evaluated by intervening on the states of a subset of the system (cause), and
observe the change of states in the other part of the system (effect), while holding the external factors
fixed. Therefore, IIT claims that any conscious experience relates to a cause-effect structure
that is maximally irreducible. We will show in this section how the cause-effect power can be
quantified by a measure called information integration. If the IIT theory is correct, we should be
able to calculate the integrated information for a conscious experience in human brain and derive a
reasonable value.
2.1
Information Entropy
The definition of information, according to Shannon [Shannon, 1948], is quantified by the reduction
of uncertainty among a number of alternatives when one occurs. This is measured by the entropy
function, defined as the following.
10
Definition 1. (Shannon Entropy) Given a probability measure P on a σ-algebra A, the entropy of a
probability distribution is:
Z
H(A) = Hp (A) =
−p(a) log p(a)da
(1)
a∈A
The logarithm used in this calculation is usually base 2, which means that the entropy is measured in
bits. The entropy of a system is a measure of the average information content of a message generated
by that system.
For example, in a binary system with two possible outcomes (0 or 1), the entropy is highest (= 1)
when the probability of either outcome is 0.5, and lowest (= 0) when one outcome is certain
(probability of 1) and the other is impossible (probability of 0).
In addition to being used in information theory, entropy has also been applied in fields such as
cryptography, signal processing, and thermodynamics. In thermodynamics, entropy is used to
quantify the degree of disorder or randomness in a thermodynamic system, and is often referred to as
thermal entropy.
For a discrete-state system, a uniform distribution over all possible independent states contains
the lowest information, therefore has the highest entropy. However, simply having a large number of independent components that results in a vast range of available states is not sufficient to
generate conscious systems. These components must also be causally dependent on one another
at an appropriate spatial and temporal scale. This crucial aspect of consciousness is referred to as
information integration, as introduced by Tononi [Tononi, 2004]. Additionally, the author proposed a
computational model to quantify the capacity of information integration, which will be detailed in the
following sections.
2.2
Basics Concepts of IIT
The axioms of IIT state that every experience exists intrinsically and is structured, specific, unitary,
and definite where specifically,
• Experience exists intrinsically;
• Experience is specific, being composed of a particular set of phenomenal distinctions
(qualia);
• Experience is unitary, irreducible, as an integration of information;
• Experience is definite in its content and spatio-temporal grain (exclusion of other possibilities).
The theory then postulates that, for each essential property of experience, the physical subtrate of
consciousness (PSC) must have a cause-effect power related to the brain. The objective is then to
find the appropriate spatial and temporal scale of neural elements gives rise to consciousness. The
theorem implies that only those elements that have the maximum intrinsic cause–effect power are
identified as elements of PSC. it is notable that under such a definition, the cause-effect power could
be higher at a coarser spatial scale comparing to a finer spatial scale.
Recall the definition of consciousness in IIT corresponds to the capacity to integrate information,
such that the system generates a large collection of states while being causally dependent to each
other. In a hypothetical setting, imagine a collection of neuronal elements locally connected but
disconnected from outside stimulus, then one is able to test if such a collection can be separated into
two independent parts by measuring the information gain of one part by knowing the other part. In
information theory, this precisely corresponds to mutual information (MI) of two random variables.
The measurement of information integration in the theory is defined as a certain type of MI in the
brain system, called effective information (EI).
Definition 2 (Mutual Information). The mutual information between two variables A, B:
I(A, B) = H(A) + H(B) − H(AB)
(2)
where H(A) = HpA (A), H(B) = HpB (B), H(AB) = HpAB (A; B), pAB is the joint distribution
of A, B.
11
In the following discussions, we will generalize the symbols A, B to be two sub-systems (or two
subsets of variables) instead of two variables.
In order to measure the information gain, start by setting one part of neural elements to independent
set of noises, and observe how the firing pattern changes in the other half as a consequence of
receiving signals. Precisely, we define the concept of EI:
Definition 3 (Effective Information). Effective information measures the directional causal effects of
A on B,
EI(A → B) = I(Ã, B) = H(Ã) + H(B) − H(ÃB), Ã = arg max H(A)
(3)
A
which means A is chosen to be independent random noise, thus B has no causal effects on A.
According to the above definitions of MI and EI, some lemmas can be directly derived, which are
stated in the following remark.
Remark 1. The information gain from A to B is not the same as B to A due to different connectivity
pattern, while the mutual information is isotropy; and the EI is always upper bounded by the smallest
maximum entropy of set A and set B. In mathematical terms:
I(A, B) = I(B, A) =⇒
̸
EI(A → B) = EI(B → A)
(4)
EI(A → B) ≤ min{O(max H(A)), O(max H(B))}
(5)
A
B
As a consequence, we are able to measure how part A causally effects the other part B and vice versa.
This gives rise to the isotropy causal effects defined by mutual effective information (MEI).
Definition 4 (Mutual Effective Information). Mutual effective information EI(A ⇌ B) measures the
isotropy causal effects of between A and B,
EI(A ⇌ B) = EI(A → B) + EI(B → A)
(6)
As a consequence of the definition, if we are able to partition a system S into A and B such that
EI(A ⇌ B) = 0, then A and B are independent parts, which limits the capacity of integrating
information on the S. Therefore, it is necessary to locate the bottleneck in order to quantify the
information integration capability for system S.
Definition 5 (Minimum Information Bipartition, MIB). A bipartition on system S as its “weakest
link” can be achieved with partitions A, B ⊂ S, B = Ā as its complementary set, such that the
normalized mutual effective information of A, B is the minimum, as following:
EI(A ⇌ B)
MIB(A ⇌ B) = arg min
(7)
A,B⊂S Hmax (A ⇌ B)
with Hmax (A ⇌ B) = min{max H(A), max H(B)}
(8)
A
B
Hmax (A ⇌ B) is for normalization due to Remark 1.
PN
N
Each partition in MIB is called a complex in IIT. There is m=2 m
subsets within a system of N
[N ]
elements, each has a measure of Φ(S), S ∈ 2 , but those S in a larger subset with higher Φ are
discarded, the rest are complexes in the system.
Now consider a system X with N neuronal elements, its information integration capacity is determined by the total minimum information for each of the complexes, which are found by enumerating
over all the possible subsets S ⊆ X .
To formalize this intuition, we define the information integration capacity of system X , which
measures the maximal irreducible cause-effect power, i.e., mutual effective information for minimum
information bipartition.
Definition 6 (Information Integration). The information integration for a subset S is the mutual
effective information of the minimum information bipartition:
Φ(S) =
min
EI(MIB(A ⇌ B))
(9)
A∈2S ,B=S/A
The integrated information for the entire system X is such that
Φ(X ) = max Φ(S)
S∈2X
12
The intuitive explanation of the information integration Φ is that, if the system is not fully decomposable (into independent sub-systems), Φ is the effective information (a special type of mutual
information) for cutting the systems on its “weakest link” by minimizing the effective information,
or as a “cruelest cut” as in Tegmark [2015]. We will discuss about how to practically measure the
integration information in the following section.
2.3
Measurement of Information Integration
In Tononi and Sporns [2003], a computational model is proposed for measuring the information in a
spatial network.
Assume that X is the entire system, and consider X ∈ R|X | to be the random vector over X that
characterizes the signal emitted by each neuron in the system. To model the system X, the authors
propose to use Gaussian Graphical Model, as described in the following.
The signal at the i-th node, denoted by xi , is a linear combination of the signals of its neighboring
nodes in the directed graph representing the node connection, plus the random measurement noise:
X
xi =
wi,j xj + σi ri
j∈neighbor(i)
i.i.d.
where ri ∼ N (0, 1) are random noise in the measurement, and wi,j is the edge weight from i to its
neighbor j. In matrix form, we have,
X = W X + CR,
C = diag((σi )i )
Then it is easy to see the covariance of X satisfies
Σ = C 2 (I − W )−1 (I − W )−1⊺ .
With this model, one can compute the information integration Φ analytically,
(1) For any S ∈ 2X , consider one bipartition S = A ∪ B, S c = X /S,
!
!!
XA
ΣA
ΣAB ΣAS c
ΣB
ΣBS c
X := XB ∼ N 0, ΣAB
XS c
Σ S c A ΣS c B Σ S c
then to calculate EI(Amax → B), one randomizes the signal from A by setting ΣA = I|A|
in the covariance, and cuts off any incoming edges from S C , B to A. However, if A is
simulated to account for connection within A and to A, the original graph is unchanged.
Moreover, one sets CA = diag(σp ) as the signal and CB∪S c = diag(σi ) as the noise.
Then one can calculate (A is a set, XA is a multivariate representing the signal states of the
items in the set A, we ignore the difference of H(A) and H(XA ) here)
H(XA ) = E[− log pXA ] = |A|/2 + |A|/2 log 2π + log |ΣA |/2
ΣA ΣAB
H(XA XB ) = |S|/2 + |S|/2 log 2π + log |ΣS |/2, ΣS =
ΣAB ΣB
similarly H(B).
(2) With the analytic results of H(A), H(B) and H(AB), one can also calculate EI(B max → A).
Then one finds the minimal information bipartition as before,
MIB(S) =
min
A∈2S ,B=S/A
EI(A ⇌ B)/ min(H max (A), H max (B))
and Φ(S) = EI(MIB(S))
(3) Finally, one can find integrated information for the entire system
Φ(X) = max Φ(S)
S∈2X
13
Apart from computing Φ for system with a given topological structure, the authors also experimented
with finding the graph structure with the maximal Φ, and analyzed the connectivity property of the
generated ‘optimal’ graph with maximal Φ.
In Balduzzi and Tononi [2008], simulation studies on discrete spatial-temporal systems are carried
out on small scale networks.
[Hoel, 2017] leverages the do-operation in causal inference in constructing a Markov chain in time
that identify particular coarsening of the (spatial) state-space that corresponds to an increase in
information.
Consider a finite state space S, we can specify transition probability matrix (TPM) between any two
states
Pij = P(X t+1 = j|X t = i) = P X t+1 = j|do X t = i
which is similar to Markov chain, with the Markov property given by the do operator, i.e. we have
conditional independence once S t = i is a fixed quantity. In this sense, we treat the time as varying,
and only
P one variable X present with state space S; or that we have |S| many binary variables and so
X = k∈S δk , which is well-defined due to finiteness.
Consider the problem setup: let X → Y be the causal system, where they share the same state space
SX = SY . The author is interested in when the macro system has a micro system with corresponding
TPM, i.e. U → V , such that SU = SV ⊂ 2SX . Moreover, Hoel’s theory aims at identifying particular
coarsening of the state space amounts to causal emergence. Effective information (EI) plays an
important role in achieving this. We give another definition of EI since the context differs to IIT, but
firstly we introduce the concept of intervention and effect distribution.
Definition 7 (Intervention Distribution and Effect Distribution). Given |SX | < ∞, the maximum
entropy amounts to the uniform intervention distribution
1
ID = H max = Unif(do(X)), that is, P (do(X = x)) =
∀x ∈ SX
(10)
n
where Unif(·) is the uniform distribution over a set. Intervening with this distribution on X results
in the effect distribution ED (Y ) over Y :
X
ED (Y ) =
P (Y | do(X))H max
X
1X
P (Y | do(X = x))
=
n x
(11)
The ED effectively computes the uniform averages over all rows in the TPM.
We are now ready to introduce definition of effective information in Hoel et al. [2013]:
Definition 8 (Effective Information).
X
EI(X → Y ) =
H max DKL (P (Y | do(X))∥ED (Y ))
X
=
X
P (do(X = x))DKL (P (Y | do(X = x))∥ED (Y ))
x
=
(12)
1X
DKL (P (Y | do(X = x))∥ED (Y ))
n x
The definition of EI presented in Def 8 is in fact equivalent to the definition in IIT. Without loss of
generality, denote p(x) and p(y) the mass function for X ∼ H max , Y ∼ ED respectively.
XX
p(x, y)
M I(X, Y ) =
p(x, y) log2
p(x)p(y)
x
y
XX
p(y|x)
(Bayes Rule) =
p(x)p(y|x) log2
p(y)
x
y
X
1
=
DKL (P (Y | do(X = x))∥ED (Y ))
n x
14
Given the notations above, a causal emergence (CE) arises when the best coarsened system has higher
effective information than the original one, i.e.
CE = EI(U → V ) − EI(X → Y ) > 0
since U and V are considered as the same random variables in one step, this amounts to finding the
coarsened support set SU .
2.4
Biological Evidence
Despite the computational framework put forward by the IIT theory is able to analytically assess
the information processing bottleneck in an arbitrary system, it remains an open problem to verify
the claimed correspondence that subjective experience is equivalent to the capacity to integrate
information.
IIT postulates the neural elements constituting PSC are those determined by maximizing the causeeffect power, which could be higher at a macro scale comparing to a micro scale owing to different
connectivity patterns. Among the brain regions, cerebral cortex has functional specialization and
integration altogether, which should yield high values of maximum information integration. Whereas
cerebellum is not essential for consciousness, because of its lack of dependency among the neurons
and inability to form a large complex with high maximum information integration.
IIT also explains why bistable firing of cortical neurons during slow wave sleep would cause fading
of consciousness. This is owning to the loss of both selectivity and effectiveness results in the
reduction of information integration [Tononi et al., 2016]. Alkire et al. [2008] argues that brain under
anesthesia is similar to under slow wave sleep, where cortical connectivity breaks down and therefore
information integration is reduced. Practically, PCI are proposed to estimate Φmax evoked by TMS in
practice, which is high only if brain responses are both integrated and differentiated, corresponding
to a distributed spatio-temporal pattern of causal interactions that is complex and hence not very
compressible.
3
Consciousness as a State of Matter
Apart from the information theoretical viewpoint, researchers are seeking for the properties of conscious process within physical systems. Consciousness can be thought of as an emergent phenomenon.
It does not depend on detailed properties of atoms, but on the complex patterns into which the atoms
are arranged. Emergent phenomena are common in physics, for example, waves can exist in many
different kinds of matter. Researchers have investigated the phenomenon of consciousness from a
principled way in physics [Penrose, 1991, Stapp, 2000, Tegmark, 2000, 2015, Carroll, 2021]. A
core issue for this approach is to admit the true randomness in the conscious process and locate
the corresponding physical processes within the human brain as evidence. A branch of research
ultimately resorts to the quantum process, which is commonly believed to exhibit the true randomness
in the measurement procedure of a quantum state. The conscious process can be interpreted as a
quantum measurement by a conscious observer. However, several problems are raised in this interpretation: One corresponds to the quantum factorization problem, that the conscious observers has a
certain Hilbert space factorization to leave the world around the observer as a strongly correlated
but independent (from the observer) system [Tegmark, 2015]. Another problem is the quantum
decoherence in physical system like human brains. Most quantum phenomenons only appear in a
very small space-time scale, the decoherence process prevents a system as large as the human brain
to inherit the quantum property. For example, a typical timescale for quantum decoherence lasts
for about 10−13 ∼ 10−20 seconds, which is much shorter than the timescale of cognitive process
as 10−3 ∼ 10−1 seconds [Tegmark, 2000]. Researchers also proposed the orchestrated objective
reduction (Orch OR) of quantum states to interpret the brain cognitive process [Hameroff and Penrose,
2014], which is discussed in Sec. 4.
Max Tegmark [Tegmark, 2015] considers consciousness as a kind of matter which he calls “perceptronium", as a phrase indicating conscious state. For a matter to become “perceptronium", it needs
have the following four properties as necessary but not sufficient conditions:
• The information principle: The system must have substantial information storage capacity;
15
• The integration principle: The system cannot consist of nearly independent parts, and it
needs to have a certain level of integration within itself;
• The independence principle: The system must have substantial independence from the rest
of the world;
• The dynamics principle: A conscious system must have substantial information-processing
capacity, and it is this processing rather than the static information that must be integrated.
In Tegmark’s work, he generalizes Tononi’s IIT (Sec. 2), compares this with other principles that
conscious matter should have, and then generalizes the analysis to quantum mechanics. In his
work, he shows that the information and integration principles can have conflicts with each other
– too much integration will result in very little information, which is referred to as the integration
paradox in Sec. 3.2. Also, the independence principle has conflicts with the dynamics principle
– too much independence will result in a trivial dynamics system, which is called the quantum
Zeno paradox as discussed later in Sec. 3.3. A conscious system needs to strike balances in these
properties: information and integration, independence and dynamics. Therefore, this work introduces
the autonomy metric to measure the balance of independence and dynamics in the system.
Following that, it also proposes the following two principles:
• The autonomy principle: A conscious system has substantial dynamics and independence.
• The utility principle: An evolved conscious system records mainly information that is useful
for it.
The autonomy principle describes the balance of dynamics and independence. The utility principle
describes the amount of information within a conscious system.
These principles can be translated into more physical problems in a system:
• The physics-from-scratch problem: If the total Hamiltonian H and the total density matrix ρ
fully specify our physical world, how do we extract 3D space and the rest of our semiclassical
world from nothing more than two Hermitian matrices?
• The quantum factorization problem: Why do conscious observers like us perceive the
particular Hilbert space factorization corresponding to classical space (rather than Fourier
space, say), and more generally, why do we perceive the world around us as a dynamic
hierarchy of objects that are strongly integrated and relatively independent?
These are the question to be answered in this theory. We will briefly introduce the basics of quantum
mechanics and then dive into these principles.
3.1
Basics of Quantum Mechanics
In quantum mechanics, the state of a system is described by a vector |ψ⟩ in the Hilbert space. For
example, we have an electron with a spin up state |ψ⟩ = | ↑⟩ or spin down state |ψ⟩ = | ↓⟩, or their
superposition |ψ⟩ = √12 (| ↑⟩ + | ↓⟩).
The probability of observing this system in state |χ⟩ is
P = |⟨χ|ψ⟩|2 .
(13)
We can apply a unitary operator to a state to change the basis we are interested in:
|ψ⟩ → U |ψ⟩
(14)
For example, the spin up state in x direction is a superposition state |ψ⟩ = √12 (| ↑⟩ + | ↓⟩) in the z
direction.
The time evolution of a state is controlled by the Hamiltonian operator H (can be thought of as a
matrix in Hilbert space):
|ψ(t)⟩ = eiHt/ℏ |ψ(0)⟩.
(15)
which is known as the Schrödinger equation.
16
The Hamiltonian operator itself describes the energy spectrum of the system. We can find its
eigenstates:
H|Ei ⟩ = Ei |Ei ⟩.
(16)
Ei is the eigenvalue of the Hamiltonian operator H, which represents the energy (as a scalar) of the
system at state |Ei ⟩. An operator takes diagnal form in its eigenbasis. When two operators commute,
[A, B] = AB − BA = 0, they can be simultaneously diagnolized.
A state can also be represented as a density matrix:
ρ = |ψ⟩⟨ψ|
(17)
this represents a pure state.
Density matrices built from the pure state always have rank 1. A more general density matrix can
also represent a classical mixture of states, which in general has a higher rank
X
ρ=
|ψi ⟩⟨ψi |.
(18)
i
this is a mixed state.
The probability of observing the system in a certain state is
P = ⟨χ|ρ|χ⟩
(19)
ρ(t) = eiHt/ℏ ρ(0)e−iHt/ℏ .
(20)
The time evolution of a density matrix is
Written in the energy eigenbasis, it is
ρ(t)mn = ρ(0)mn ei(Em −En )t
3.2
(21)
Integration Principle
For a bipartite system ρ = ρ1 ⊗ ρ2 . We define the integrated information Φ as the mutual information
I for the “cruelest cut”. The mutual information is defined as
I ≡ S (ρ1 ) + S (ρ2 ) − S(ρ)
(22)
S(ρ) ≡ − tr ρ log2 ρ
(23)
where
is the von Neumann entropy. Note that this is slightly different from Tononi’s definition, but this is
easier to calculate.
Recall in Sec. 2, we introduce the definition of the integrated information in original IIT, as the
effective information of the minimum information bipartition. The minimum information bipartition
is a ‘cut’ of the system according to the weakest link, i.e., minimal mutual effective information. We
can also consider cuts here in the quantum sense. In this case, more cuts are available, and we choose
the cruelest cut as the integrated information. Therefore the integrated information is defined as
Φ = min I UρU† .
(24)
U
where U is the unitary evolution on density matrix ρ.
A general Hamiltonian can be written as
H = H1 ⊗ I + I ⊗ H2 + H3
(25)
where I is identity matrix.
If a Hamiltonian can be decomposed without an interaction term (with H3 = 0), then it describes
two perfectly independent systems,
ρ ∝ e−H/kT = e−H1 /kT e−H2 /kT
17
(26)
In this case, it can be derived that Φ = 0 with U = eiH1 t/ℏ eiH2 t/ℏ . This is within expectation
since the integrated information describes the level of information integration within a system, and
a perfectly separated system should have no intergration. From IIT, we know that the conscious
systems are likely to have the maximum of integrated information. Taking the 2D Ising model with n
dipoles
√as an example, the maximum integrated information according to above definition will only
be O( n). However, with the optimal error correcting codes, the system can achieve asymptotic n/2
bits of integrated information in the large-n regime.
The above analysis is based on the quantum system. For a classical system like a Hopfield network [Hopfield, 1982] for describing the brain process, the integrated information can also be
calculated, and it will lead to a so-called integration paradox.
Integration paradox. Suppose our brain is a Hopfield network with n neurons using Hebbian
learning rules, then the maximum capacity of integrated information is 37 bits for n = 1011 neurons [Tegmark, 2015]. However, the information for a conscious experience is much larger than this
value, with an example of a human imagining a picture in his mind. This is known as the integration
paradox.
Why does the information content of our conscious experience appear to be vastly larger than 37 bits?
In the quantum case, it can never contain more than 1/4 bit of information [MacKay, 2003]. This
observation leads to some conjectures including that the human brains use a better coding method for
conscious information rather than the Hopfield networks.
3.3
Independence Principle
This principle follows the idea of IIT for cutting the system into independent parts from its “weakest
link”, as described in Sec. 2.2. It first requires the ρ-diagonality theorem in a quantum case to find
the minimum of mutual information.
Theorem 1 (ρ-Diagonality Theorem, ρDT [Jevtic et al., 2012]). The mutual information always
takes its minimum in a basis where ρ is diagonal.
With ρDT, the problem becomes how to find the basis with ρ being diagonal in the quantum system
with Hamiltonian as Eq. 25. The answer to this question is presented by the following theorem.
Theorem 2 (H-Diagonality Theorem, HDT [Tegmark, 2015]). The Hamiltonian is always maximally
separable (minimizing ||H3 ||) in the energy eigenbasis where it is diagonal.
Furthermore, to minimize ||H3 ||, we must have [H1 , H3 ] = 0, which indicates that all subsystems
(e.g., subsystem with Hamiltonian H1 ) need to commute with all interaction Hamiltonians (e.g., H3 ).
Following this principle, it will finally lead to a heat death, where all subsystems cease to evolve,
known as the quantum Zeno paradox.
Definition 9 (Quantum Zeno Paradox [Tegmark, 2015]). If we decompose our universe into maximally
independent objects, then all change grinds to a halt.
3.4
Dynamics principle
If only following the independence principle, we will face the quantum Zeno paradox where the
system cease to evolve and has no information processing capability. However, we also require the
conscious system to have certain information processing capability by the dynamics principle. The
autonomy principle says the system should be able to strike a balance between the independence and
dynamics principles. There are interesting classes of states ρ that provide substantial dynamics and
near-perfect independence even when the interaction Hamiltonian H3 is not small.
As a measure of the dynamics, the energy coherence is defined as:
r
1
1
− tr {[H, ρ]2 }
δH ≡ √ ∥ρ̇∥ = √ ∥i[H, ρ]∥ =
2
2
2
p
= tr [H2 ρ2 − HρHρ]
Then, the maximum probability velocity can be calculated as:
√
vmax = 2δH
18
(27)
(28)
with probability velocity defined as v = ṗ, pi = ρii . If we only maximize vmax following the
dynamics principle, some calculations indicate that it will lead to a very simple dynamics solution,
which does not carry the capability of sufficient information processing.
The states that are most robust toward environment-induced decoherence are those that approximately
commute with the interaction Hamiltonian. It means that [ρ, H3 ] ≈ 0, but [ρ, H1 ] ̸= 0. The H3
interaction term will decohere the system thus it is required to be sufficiently small for system ρ to
evolve over time.
To correctly describe the system with a balance of independence and dynamics, it needs a new metric
called the autonomy. It first requires to use the linear entropy for quantifying the non-unitary property
of an evolution.
The linear entropy is defined as:
S lin ≡ 1 − tr ρ2 = 1 − ∥ρ∥2
(29)
Let us define the dynamical timescale τdyn and the independence timescale τind as
ℏ
,
δH
h
i−1/2
= S¨lin (0)
.
τdyn =
τind
1
The autonomy can be defined as the ratio:
A≡
τind
τdyn
(30)
This ratio will exponentially increase with the system size, such that it leads to a highly autonomous
system with sufficient information processing even with a large H3 .
Summary. The theory proposed by Tegmark generalizes the IIT to the quantum domain, and
analyzes the deficiency of information integration principle from the physics-principled calculation,
which raises the integration paradox that the Hopfield neural network cannot integrate a sufficient
amount of information for conscious experience. It also analyzes the independence principle and leads
to the quantum Zeno paradox that a system decomposed into maximally independent sub-systems will
cease to evolve in the end, which is in conflict with the dynamics principle. The theory finally propose
the metric named autonomy that is found to have a high value as a balance of the independence and
dynamics principles for a conscious system.
4
Orchestrated Objective Reduction Theory
4.1
Consciousness as Orchestrated Objective Reduction
Recalling the discussion of free will problem in arising consciousness in Sec.1.5, we may conjecture
that the true randomness may be required for the free will to happen. How does this truly random
process happen in human brains? Orchestrated objective reduction (Orch OR) theory [Penrose, 1991,
1994, Hameroff and Penrose, 1996, Hameroff, 2007, 2010, 2012, Hameroff and Penrose, 2014],
builds on the hypothesis that the emergence of consciousness is due to a biological mechanism that
is able to orchestrate moments of quantum state reduction. The theory posed that conscious events
arises from the termination of quantum computation in the brain microtubules, framed as objective
reduction. Objective reduction refers to the idea that a quantum system can spontaneously collapse
from a superposition of multiple possibilities into a single state. In the Orch OR theory, Hameroff and
Penrose propose that these objective reductions are non-deterministic but are orchestrated by certain
processes in the brain. These affected objective reduction processes are called the free will. In a
nutshell, the Orch OR framework based on quantum theory appears to introduce stochasticity aspects
into the reductionist view of consciousness as a pure physical process. Through this, independent
causal agency and free will can be explained [Hameroff, 2012]. Moreover, it will also imply the
existence of consciousness in a single cell.
19
4.2
Free Will in Neurons
The integration and firing sequences, which gives rise to EEG and NCC, are primarily generated by
dendritic-somatic membranes. Then axonal firings outputs conscious (or non-conscious) processes
to control behavior. Microtubules (MTs), as part of the cytoskeleton, a protein scaffolding network
inside of the cell, is hypothesized to influence the threshold of firing. Specifically, Dendritic–somatic
MTs of neurons are arranged in local recursive networks and are more stable comparing to MTs in
other cells, therefore render itself as a suitable information processing and storage unit, moreover,
suitable to mediate consciousness and regulate firing.
As shown in Fig 4, MT constitutes of peanut-shaped tubulin protein, each with a dipole and can be
arranged in 13 protofilaments each with two types of hexagonal lattices. In [Hameroff and Penrose,
2014], the MT dipoles are described as electron spin (magnetic), which is inherently a quantummechanical quantity. Therefore all possible directions for the spin rotation axis arise as quantum
superpositions of some random pair of directions. The authors then speculate that there may exists
chains of spin along the pathway in MT that propagate quantum bit pairs, in addition, there may
exists alternative currents at certain frequency caused by periodic spin flips. The fact that tubulins in
MTs can each exists in different states (and give rise to quantum superposition) based on the dipoles
position (direction), could indicate MT processes may directly result in consciousness.
4.3
Diósi-Penrose Objective Reduction
Having notated the physiological unit where quantum superposition may took place in our brain, one
might ask how the orchestrated reduction that gives rise to consciousness happen? The argument
starts with linking Orch OR to theoretical physics.
The Diósi-Penrose (DP) objective reduction proposal bridges quantum and classical physics as
quantum-gravitational phenomenon, whereby the quantum superposition reduces to an average time
2
measurement τ for the state reduction to take place according to τ ≈ EℏG , EG = Gm
a , where E
is space-time superposition curvature, G is gravitational constant, m is mass, a is spatial size. The
actual time of decay in each event of state-reduction is taken as a random process in DP. From this,
the reduction of quantum superposition of space-time objects takes place when the superposition
curvature EG reaches the threshold τℏ .
The Orch-OR schemes goes further to relate the DP physical proposal to consciousness. Hameroff
and Penrose [2014] proposed that if a quantum superposition is firstly well-orchestrated: “adequately
organized, imbued with cognitive information, and capable of integration and computation"; and
secondly isolated from non-orchestrated, random environment for the superposition EG to reach the
threshold τ , then the Orch OR will occur along with the emergence of consciousness. An illustration
of this process is shown in Fig 4.
4.4
Evidence for Objective Reduction of Quantum State
In Hameroff [2010], the authors claimed that the best measure of neural correlate of consciousness
is 30- to 90-Hz gamma synchrony electroencephalography (EEG), which is largely derived from
dendritic and somatic integration potentials. In addition, the theory claims that the state of anaesthesia
is owing to dispersed dipoles in the MTs, responsible for quantum computing.
There are yet experiments in confirming the theory, however, biological evidence has been observed
in warm conditions, where the theory has yet to extend to. Nonetheless, the Orch OR theory has
provided a computational framework allowing falsification of the biological quantum theory that
takes place in the MT.
5
Global Workspace Theory
5.1
The Theatre of Consciousness
Global workspace theory (GWT) is an architecture proposed by Bernard Baars [Baars et al., 1997] to
explain the inner procedure of how the human brain selects and deals with consciousness attention.
There are some limits to conscious capacity. For example, working memory, which temporally store
20
Figure 4: The figure published in Hameroff and Penrose [2014] was used to illustrate the process that Orch
OR occurs. Top: Tubulins are in classical dipole states (yellow or blue), or quantum superposition of both
dipole states (gray). Quantum superposition/computation increases during (1-3). The conscious moment occurs
when threshold is met at time τ ≈ ℏ/EG . Middle: Corresponding alternative superposed space-time curvatures
reaching threshold at the moment of OR and selecting one space-time curvature. Bottom: Schematic of a
conscious Orch OR event showing U-like evolution of quantum superposition and increasing EG until OR
threshold is met, and a conscious moment occurs by τ ≈ ℏ/EG .
information to be dealt with, holds only several things at a time. Moreover, the human brain is only
able to receive information from a single stream. ‘The theatre of consciousness’ was proposed in a
metaphor term to answer how the human brain handles different inputs, and then outputs a single
stream of information that draws the final attention.
There are several components of a theatre of consciousness. The ‘stage of working memory’ is
the platform to receive all potential information from sensors or abstract information from cortices.
The ‘spotlight’ mechanism in working memory highlights the conscious steam of information, other
information on the stage is not aware by attention. Information resources,e.g. the potential thoughts,
images or sensations, are regarded as ‘actors’. The information resources compete with each other
to get the spotlight. The more conscious procedure is required to handle the information, the more
likely the information resource will be put under the spotlight. Perceptual, intention, expectations etc.
influence the result of this competition. ‘Context’ refers to unconscious networks that potentially
shape conscious contents in the brain. ‘Directors’, the executive functions of human brain, guide the
selection procedure with intentions and goals. The frontal cortex is believed to act as an important
21
role in this procedure with the fact that damage to the front lobe leads to loss of actions by long-term
goals. Then the information under the spotlight is broadcasted to the ‘audience’, which represents the
brain region which requires the information.
Figure 5: Scheme diagram of GWT derived from Baars et al. [1997].
An update of GWT in 2003 [Baars, 2003] gives a more detailed introduction to the relationships
between GWT and Brain functions, which provides some evidence of how the competition is
performed in the human brain. Both the frontal cortex and other brain regions, which can interrupt
the spotlight control, are involved in the conscious event selection procedure. The latter interrupt
control consists of, for example, the brain stem, pain system, and emotional centers, which allow
interrupting the selection procedure and give weight to more significant and urgent activities. The
‘Context’ function of the brain is believed to be involved in the conscious decision process. The
parietal cortex which is related to self-awareness of parts of the body is not directly objectively linked
to consciousness but is believed to shape conscious visual events. The ‘Self’ system may be involved
in the generation of consciousness. It was found that split-brain patients have different executive and
perceptual functions from the left and right hemisphere [Gazzaniga et al., 1996] and the left prefrontal
cortex processes the sensory information with a ‘narrative self’ that can draw different awareness
which causes conflicts between both hemispheres. Then the left hemisphere tries to rationalize and
repair such conflicts. Some evidence was also provided in the paper to support the assumption that
consciousness contents are broadcasted and distributed to brain regions. In a visual word task, the
word task not only triggers visual word recognition areas of the cortex but also was found to evoke
activities in the parietal and prefrontal cortex [Baars, 2002].
5.2
Computational Models of GWT
The Intelligent Distribution Agent (IDA) [Baars and Franklin, 2003, 2007] and LIDA (Learning
IDA) [Baars and Franklin, 2009] computational models were proposed based on GWT to perform
human-like tasks. In the study, naval jobs of sailors are used as an example task to test the model.
IDA and LIDA contain several blocks reflecting the GWT, including sensory modules to deal with
stimulus, memory modules as storage, attention modules referring to the concept of attention,
the action module for action selection. Particularly, as in the GWT, global workspace modules
integrates and broadcasts information, as well as selects the most relevant and important information
to be on the stage. This model shows an empirical computational implementation of the GMT model
as conceptual evidence that GMT could work out human-like functions. IDA or LIDA turns incoming
22
sensory data into actions to the environment. The concepts of memory, competition, and broadcasting
are involved in the conversion process. Then the resulting action to the environment changes the
inputs of the system which forms an iterating cognitive cycle.
GWT has inspired some studies in related fields, here we describe several examples in brain signal
analysis and deep learning. Inspired by GWT, [Schutter and van Honk, 2004] used EEG coherence,
the level of connectivity of different brain region, to measure if emotions play a role in consciousness.
Another study [Bartolomei and Naccache, 2011], in light of the broadcasting and distributing process
in the GWT, compared the synchrony within distant cortico-cortical and cortico-thalamic networks
of epileptic seizures with the distant relationships across different brain regions in GWT. More
recently, a study discussed the possibility of implementing GWT with deep learning. The idea of
Global Latent Workspace (GLW) was proposed to reflect deep learning design principles of brain-like
mechanisms [VanRullen and Kanai, 2021].
6
Higher-Order Theories
A general definition of HOT is given by Carruthers and Gennaro [2023]: A phenomenally conscious
mental state is a mental state (of a certain sort) that either is, or is disposed to be, the object of a
higher-order representation of a certain sort.
Depending on whether the higher-order states in question are perception-like or thought-like, the
high-order theories are categorized as high-order perception theory (HOPT), high-order thought
theory (HOTT), self-representational theory (SRT), etc. Definitions of HOPT (Sec. 6.1 Def. 10),
HOTT (Sec. 6.2 Def. 11) and SRT (Sec. 6.3 Def. 12) are described in details in the following sections.
Additionally, we will introduce and discuss other relevant theories in the final section. To provide a
concise overview, we consolidate these theories into a summarizing Table 2.
Higher-order theories (HOTs) try to answer the question that if a mental state is conscious or
unconscious. The higher-order theory believes that there is a certain brain mechanism that is more
advanced than the first-order information (e.g. senses from organs like visual or auditory nerves).
Three sub-theories claimed different explanations for the higher-order mechanism. HOPT believes
that there are inner senses that scan or refine but are independent of the first-order information. This
explains why people are able to imagine feelings like pain. In HOTT, it is believed that a mental state
is conscious when it is the subject of higher-order thought. They propose that a conscious mental
state or event is either actually causing or is disposed to cause an activated thought that a person
has the state or event. Self-representational theory proposed another explanation to the higher-order
theory. The self-representational theory believes that the higher-order state is constitutive or internal
to its first-order state, i.e. that the higher-order state is formed from the first-order states and as a
more complex system than the first-order states that generate awareness.
6.1
Higher-Order Perception Theory
The high-order perception theory (HOPT) theory [Locke, 1948, Armstrong, 1981, Armstrong and
Malcolm, 1985, Lycan, 1996, Armstrong, 2002, Lycan, 2004], which is also called the Inner-Sense
Theory or High-Order-Sense Theory, is referring to the followings: Humans not only have the
sense-organs to scan the environment and their own bodies to produce the representations, which
are called the first-order non-conceptual and/or analog perceptions of environment/body states, but
also have inner senses of those first-order senses to generate equally fine-grained but higher-order
representations, which are called the second-order non-conceptual and/or analog perceptions of the
first-order perception states.
The definitions of the first-order perception and the second-order perception are actually close to the
M-consciousness and I-consciousness in the attention schema theory, which will be introduced in
later Sec. 7. We will discuss the connections of the two theories later in Sec. 7.3.
Definition 10 (Higher-Order Perception Theory/Inner-Sense Theory [Carruthers and Gennaro, 2023]).
A phenomenally conscious mental state is a state with analog/non-conceptual intentional content,
which is in turn the target of a higher-order analog/non-conceptual intentional state, via the operations of a faculty of ‘inner sense’.
23
Table 2: A summary of HOTs
Theory
HOPT
Actualist
First-order & Higherorder Relationship
higher-order senses
exist and are independent of first-order information
a mental state is conscious when it is the
target of a higherorder thought
HOTT
Dispositional
a mental state is conscious when it is the
target of a higherorder thought
Part-whole
first-order
and
higher-order
are
parts of a whole
complex
Identity
higher-order
and
first-order are identical
SRT
Key Mechanism
perception-like; the human
brain has inner senses of the
first- order senses to generate
higher-order representations
thought-like; A conscious mental event is actually causing an
activated thought that a person
has the event
thought-like; a mental state is
conscious when it is the subject
of higher-order thought; a conscious mental event is disposed
to cause an activated thought
that a person has the event
the mental state is to representing itself. In the definition of part-whole SRT, the
higher-order information exists but is not strictly ’higher’
than the first-order information.
First-order and higher-order are
bound together
higher-order and first-order are
the same components as two
roles or functions
References
[Locke, 1948, Armstrong, 1981, Armstrong and Malcolm,
1985, Lycan, 1996,
Armstrong, 2002, Lycan, 2004]
[Rosenthal,
1993, 2005]
1986,
[Dennett, 1978, Carruthers, 1998]
[Kriegel, 2009, Picciuto, 2011]
[Caston,
2002,
Carruthers,
2005,
Van Gulick, 2004]
A formal proposition of HOPT is provided as Definition 10. It explains consciousness as the higherorder states generated from inner sensing of the first-order states. Referring to Fig. 3 in Sec. 1.5, the
conscious module is a higher-level component perceptive of the information flow of the lower-level
sensing modules.
The antagonistic viewpoint of HOPT is held by some theorists that the attention mechanism on the
first-order states may serve as a substitute of the higher-order states [Sauret and Lycan, 2014].
6.2
Higher-Order Thought Theory
The higher-order thought theory (HOTT) [Rosenthal, 2009, 2012, 2004, Byrne, 1997, Brown et al.,
2019] propose that a conscious mental state or event is either actually causing or is disposed to cause
an activated thought that a person has the mental state or event. There are two embranchments of
the theory: the actualist and the dispositionalist. In the above statement, the actualists believe that
mental state directly caused the activated thought while the dispositionalist believes that the mental
state is disposed to the thought. Another difference between them is that the actualist HOTT requires
actual involvement of the first-order information in order to compute the higher-order information.
On the contrary, the dispositionalist HOTT states that the higher-order computation only requires the
availability of the first-order information, for example utilising board casting in the global workspace
theory, instead of directly accessing all first-order information. In [Lau and Rosenthal, 2011], some
empirical support for the higher-order theories was discussed, e.g. the association of conscious
awareness with prefrontal mechanisms and evidence based on clinical disorders.
Definition 11 (Higher-Order Thought Theory [Carruthers and Gennaro, 2023]). A phenomenally
conscious mental state is a state of a certain sort (e.g. with analog/non-conceptual intentional
content, perhaps) which is the object of a higher-order thought, and which causes that thought
non-inferentially.
24
Some computational models were proposed based on higher-order thought theories. Metacognition
neural network models [Pasquali et al., 2010, Cleeremans et al., 2007, Timmermans et al., 2012]
consist of two networks: a first-order network and a second-order network. The first-order network
directly gets inputs and processes them with hidden units. After that, the hidden units of the first-order
network are linked to the second-order network for processing. The first-order network learns to
perform the classification of tasks, and the second-order network predicts the confidence of the
first-order network by accessing the representational information of the first-order network. The
models were tested and reported on several tasks, e.g. the Iowa Gambling Task [Pasquali et al., 2010],
artificial grammar learning (AGL) tasks which distinguish grammar and non-grammar sentences, and
blindsight tasks [Persaud et al., 2007] in which blindsight patients make visual discriminations in the
absence of visual awareness.
6.3
Self-Representational Theory
The Self-Representational Theory (SRT) [Kriegel, 2009, Van Gulick, 2004, Picciuto, 2011] presents
the idea of phenomenally conscious mental state, which is a state with non-conceptual intentional
content, and conceptual intentional content at the same time. Such a mental state is said to representing
itself to the person who is the subject of that state.
Definition 12 (Self-Representation Theory [Carruthers and Gennaro, 2023]). A phenomenally conscious mental state is a state of a certain sort (perhaps with analog/non-conceptual intentional
content) which also, at the same time, possesses an intentional content, thereby in some sense
representing itself to the person who is the subject of that state.
Two branches of the theory have argued for the constitutive relation between the conscious state
and higher-order state is one of identity [Caston, 2002, Carruthers, 2005, Van Gulick, 2004], or
part-whole [Kriegel, 2009, Picciuto, 2011]. The former argues that the conscious state is both firstorder and higher-order, More precisely, a first-order perceptual state with analog content acquires, at
the same time, a higher-order analog content. The part-whole SRT take stance similar to actualist
HOT thoery arguments, where the first-order perceptual state gives rise to higher-order thought that
represents experience.
6.4
Other theories and perspectives in HOT
The same-order theory [Kriegel, 2009, Brentano, 1973, Lau and Rosenthal, 2011] proposes that
conscious mental states are not represented by any other mental states, but are instead directly present
to the subject’s awareness. The higher-order statistical inference view [Lau, 2011, 2007] believes
conscious mental states involve higher-order statistical inferences about one’s own mental states.
According to this view, first-order representation is reviewed by a higher-order inference procedure to
form a statistically reliable perceptual signal, similar to perceptual decision-making process. From
the perspective of the radical plasticity thesis [Cleeremans, 2011, Pasquali et al., 2010], the brain
is capable of remarkable adaptability and flexibility, and this plasticity plays a critical role in the
development of conscious awareness. The radical plasticity thesis proposes that consciousness is
not an intrinsic procedure but a learning process in the brain. The brain engages in continuous and
unconscious learning to re-describe its activity, thereby developing systems of meta-representations
that describe and refine the initial, first-order representations.
7
Attention Schema Theory
7.1
Formulation
It is important to understand the difference of attention and awareness and their relationship in
Attention Schema Theory (AST) [Graziano and Webb, 2015, Graziano et al., 2020].
Definition 13 (Attention). Attention is a process where the brain selectively process certain pieces of
information more than others.
As one of the most influential explanation of the attention process, people [Desimone et al., 1995]
propose that there is a signal competition process emerging at the earliest stages of signal processing
and existing in every later stages.
25
Awareness is a different concept from the attention. Although awareness and attentions are typically
highly correlated, they can be dissociated. For the concept of awareness, we need to first distinguish
objective awareness and subjective awareness. Both of the awareness involves a participant.
Definition 14 (Objective Awareness). For objective awareness, the participant is required to report
that he is objectively aware of the stimulus.
Definition 15 (Subjective Awareness). For subjective awareness, the participant reports whether he
has perceived the stimulus in his own opinion.
The difference of objective awareness and subjective awareness is just to distinguish whether the
participant ‘sees’ or ‘guesses’ the perceived stimulus.
In AST, the authors refer the awareness, consciousness and subjective experience as the same concept
as the subjective awareness. Therefore, AST is a theory about subjective awareness, not objective
awareness.
AST proposes that awareness is a model of attention. Thinking of a person seeing an apple, the visual
representation of the apple (V) appears in the person’s mind through the attention process. However,
this is not enough for making the person aware of the ‘apple’. To generate awareness, the mind also
has a model of self (S), and the attention (A) of S to V is also part of the awareness. By AST, a
subjective awareness is [S+A+V], which is a model of the attention process.
Figure 6: Awareness as a model of attention in AST.
People may ask why subjective awareness is required beyond the attention? According to AST,
subjective awareness allows for self-modelling which is essential for model-based control. Without
awareness is like without modelling the arm when a person tries to reach some objects, and it will lead
to inaccurate prediction about the arm’s position therefore bad reaching result. The awareness serves
as an internal modelling of the mind itself and the attention, leading to more accurate model-based
control for human.
7.2
I-consciousness and M-consciousness
As the primary researchers of AST, Graziano et al. [2020] proposes to interpret the consciousness of
human mind via the I-consciousness (I for information) and M-consciousness (M for mysterious) in
their later study.
I-consciousness indicates the process of signals winning attentional competition, just as in GWT,
which is generally assumed to computationally feasible [Baars and Franklin, 2007]. However,
the mysterious part is the M-consciousness, which is used to explain the subjective experience of
perceiving the winning piece of information.
Similar as the previous work of AST [Graziano and Webb, 2015], that awareness is a model of
attention, Graziano et al. [2020] further proposes that M-consciousness is a natural, built-in, imperfect
model of I-consciousness. Moreover, the I-consciousness and M-consciousness can be mutually
involved, like a mirror of another mirror. A person is I-conscious of having his M-consciousness, and
M-consciousness is a model of I-consciousness. For the self-modeling, the modeled parts are the
26
physical components of the self most closely correlates with the winning piece of information from
the attention competition.
People may further ask why we think the subjective experience is realistic. According to AST, the two
properties ensure the realistic subjective experience: The first one is that the subjective experience
cannot be turned off. The second one is that the mind enables source monitoring for the perceived
information, which allows people to distinguish the real and the hypothetical. Since M-consciousness
is a model of I-consciousness, the feeling is realistic for the exactly same reason that the people
would believe every physical objects are real.
A practical implementation of AST would involve three components. The network A represents the
selective information process by the attention competition. The network B is to model the function
of network A by making predictions on A’s output. Network C receives the output from A and
B to generate the report (e.g., speech) to other components within the brain and outside world.
The network B is the important attention schema, for which the physical counterpart in the brain
has been suggested to serve, as a cortical network overlapping part of the temporoparietal junction
(TPJ) [Graziano and Kastner, 2011, Graziano, 2016].
7.3
AST as a Unification of GWT and HOT
AST can be viewed as a unification of global workspace theory (GWT, Sec. 5) [Baars, 1993, Dehaene,
2014, Dehaene and Changeux, 2011] and higher-order theory (HOT, Sec. 6) [Gennaro, 2011, Lau and
Rosenthal, 2011, Rosenthal et al., 1991, Rosenthal, 2005].
Specifically, the GWT explains the attention schema for a piece of information to appear on the stage
of the mind, which corresponds to the I-consciousness of AST. However, GWT does not explain
the existence of consciousness experience, as the M-consciousness. AST explains this mystery by
constructing the attention schema using network B.
The HOT says consciousness arises from the higher-order representation. Recall the introduction of
HOT in Sec. 6, a conscious system has inner senses of those first-order senses to generate equally
fine-grained but higher-order representations, which are called the second-order perceptions of the
first-order perception states. The I-consciousness in AST represents the external first-order senses,
while the M-consciousness corresponds to the second-order perceptions over the first-order senses.
These second-order perceptions can be thought of as a modelling process of the first-order senses.
AST assumes the brain to construct higher-order representation of the global workspace, as imperfect
modelling of the I-consciousness, which unifies the HOT and GWT to give explanations of subjective
awareness.
8
Conscious Turing Machine
8.1
Formulation
In traditional Turing machine (TM) [Turing, 2009], Turing does not involve the subjective experience
into the concept of TM. The TM is only about the computational intelligence but not consciousness
of the machine, whereas the latter one is usually considered a hard problem [Chalmers, 1995].
Conscious Turing machine (CTM) [Blum and Blum, 2022] is a theory as an extended concept of TM.
Compared with TM’s model of computation, CTM empowers the system a distinguishable feature ,
i.e., the “feeling of consciousness”. Specifically, CTM is defined as following.
Definition 16 (Conscious Turing Machine). CTM is defined as a seven-element tuple: <STM, LTM,
Up Tree, Down Tree, Links, Input, Output>, where STM and LTM are shorten for short-term memory
and long-term memory.
The CTM can be viewed as GWT with a more sophisticated structure. STM is an analogue of the
“stage” in GWT as a necessary component for the consciousness to happen. As an analogue of the
“audience” in GWT, LTM is a large collection of general processors, including the Model of the World
processor for modeling the world and the agent itself, Inner Speech processor for processing linguistic
information, and other Inner Generalized Speech processors for handling information inputs like
five senses. These processors are called LTM since they have a relatively stable status and expertise
27
for processing a specific type of information, while LTM corresponds to a shorter period of status
maintenance for more general functionalities.
Figure 7: The information flows in CTM.
In CTM, the information flows only appear in five ways, as also depicted in Fig. 7:
• (1) environment → LTM;
• (2) LTM→STM (via Up Tree);
• (3) STM→LTM (via Down Tree);
• (4) LTM→LTM;
• (5) LTM → environment.
Process (1) in the information perception. Process (2) is achieved with Up Tree competition. In the
Up Tree competition process, there is a winning information chunk finally reaching the STM. The
competition process is determined by an internal mechanism, which is probabilistic and achieved
with some coin-flip neurons with inherent randomness. However, the authors argue that the free
will can still be felt even with a completely deterministic setting. Process (3) is through the Down
Tree broadcast, and it broadcasted the information in STM to all LTM. (2) and (3) achieve the
consciousness awareness. Conscious awareness (attention) is the reception by all LTM processors
of the broadcasted winning chunk in the Up Tree competition. Process (4) is a bidirectional link
between processors to collaborate on the information processing. Process (5) is the output of the
system to the environment through processors like Motion Controller.
8.2
CTM for Consciousness
CTM adopts the concept of Brainish as the inner language for communicating between different
processors. Brainish is a terminology referring to the abstract language used for carrying information
among different modules of the brain, it can be viewed as an encoding of multi-modal information,
and it is unsymbolized and more powerful than outer language like English.
The feeling of consciousness, by CTM theory, is generated as a result of combining Brainish language,
CTM’s architecture, some special processors and CTM’s dynamics predictive power. Self-modeling
is achieved through the Model of the World processor by repeatedly generating actions from some
LTMs (like the Motion Controller) and observing the consequences perceived by some other LTMs
(like Inner Generalized Speech processor for sensing the surrounding environment). CTM is used to
interpret the blindsight, illusions, dreams and other consciousness-related process. The free will is
achieved within coin-flip process in the Up Tree competition.
8.3
Relationships with Other Theories
Compared with GWT, the CTM has just one “actor” on stage holding just one chunk at a time.
Additionally, all processors in the CTM are in LTM. Compared with an experimental work [Lee et al.,
28
2022], which distinguished the arousal and awareness as two components of consciousness, this
paper only discuss conscious awareness (or attention). The CTM theory assumes the consciousness
can be reduced to computational process and modeled with a Turing machine. However, this is still
debatable. Others may dispute this view and hold that consciousness is a more complex phenomenon
that cannot be reduced to purely computational processes. There are several theories and arguments
that support the idea that consciousness cannot be reduced to purely computational processes. Some
of these include:
• The hard problem of consciousness: This argument, put forth by philosopher David
Chalmers [Chalmers, 1995, 2017], posits that while the brain may be able to perform
various computations, it is unclear how these computations give rise to subjective experience
or consciousness.
• Qualia: This refers to the subjective and ineffable aspects of experience, such as the redness
of red or the taste of chocolate. Some argue that these subjective experiences cannot be
captured by computational models and are instead rooted in the biological and physical
processes in the brain [Tononi and Koch, 2015, Chalmers, 2017, Albantakis and Tononi,
2021].
• The integration problem: This argument suggests that consciousness emerges from the
complex and dynamic interactions between different regions of the brain, and that these
interactions cannot be reduced to simple computations.
• The limits of computation: Some argue that there are fundamental limitations to what can
be computed and that certain aspects of consciousness may fall outside of these limitations.
These arguments and others suggest that while computation may play a role in consciousness, it is
not the whole story and that a more complex and nuanced understanding is needed to fully explain
the phenomenon of consciousness.
9
Physiological Evaluation Metric of Consciousness
This section introduces some physiological evaluation metrics of consciousness level used in medical
diagnostics. It should be noticed that the definition of ‘physiological consciousness’ in this section
is different from the ‘consciousness’ introduced in other sections of the paper, e.g. IIT (Sec. 2) or
GWT (Sec. 5). Physiological consciousness usually represents the consciousness level of subjects or
patients based on the physiological and biological data, for example, signal features draw from EEG
or response to stimulus. In medical evaluation, the definition of consciousness usually comprises
wakefulness or awareness level [Walker et al., 1990]. In the upcoming paragraphs, we will delve into
the examination of common evaluation metrics based on electrical signals and behavioral indicators.
For a comprehensive overview, please refer to the Table 3, which summarizes the source signals and
applications for each physiological evaluation metric of consciousness.
9.1
Metrics Based on Electrical Signals
The Bispectral Index (BIS) [Rosow and Manberg, 2001, Johansen, 2006] is a biological-signal-based
measure of the level of consciousness, usually in a patient who has been given anaesthetics. It is a
value calculated from a patient’s electroencephalogram (EEG) to evaluate the depth of anaesthesia.
BIS is calculated from EEG using the combination of the spectrogram, bispectrum and time-domain
assessment of burst suppression. BIS ranges from 0 to 100, indicating from deep anaesthesia to
full wakefulness. A BIS monitor is usually used in operations to guarantee an appropriate level of
anaesthesia. The perturbational complexity index (PCI) was introduced as a metric for evaluating
the level of consciousness by Casali et al. [2013]. PCI uses transcranial magnetic stimulation
(TMS) to stimulate cortical activities and analyse algorithmic complexity information based on the
spatiotemporal pattern of EEG responding to the stimulus. Similarly, using EEG as the source, the
explainable consciousness indicator (ECI) [Lee et al., 2022] utilises deep learning models to compute
a score to evaluate consciousness. The study defined consciousness as a combination of arousal and
awareness. There are two deep learning networks computing them respectively, and then integrating
the scores of both as an indicator of consciousness.
29
Metric
Bispectral
(BIS)
Index
Perturbational Complexity Index (PCI)
Explainable
Consciousness Indicator
(ECI)
Glasgow Coma Scale
(GCS)
Rancho Los Amigos
Scale (RLAS)
Full Outline of Unresponsiveness (FOUR)
Source Signal
Application
References
electroencephalogram
(EEG) spectrogram;
bispectrum;
timedomain assessment of
burst suppression
collect
electroencephalogram (EEG)
features responding to
the TMS (transcranial
magnetic stimulation)
stimulation
electroencephalogram
(EEG) features extracted by two deep
neural networks
eye activities; verbal
response; motor response
evaluate the level of
consciousness (anaesthetics etc)
[Rosow and Manberg,
2001,
Johansen,
2006]
evaluate the level
of
consciousness
of brain-injured or
unresponsive patients
[Casali et al., 2013]
evaluate the level
of wakefulness and
awareness
[Lee et al., 2022]
evaluate
effectiveness of treatments
and as a prognostic
indicator;clinical
assessment of unconsciousness, e.g.
comatose patients
Consist eight levels of
conciousness evaluation for patient recovery evaluation
[Jones, 1979, Sternbach, 2000]
evaluate level of consciousness (including
verbal score in intubated patients and
to test brainstem reflexes)
evaluate patients’ disorders of consciousness, e.g. coma.
evaluate the awareness level of patients
in vegetative or in a
minimally conscious
evaluate the awareness level of patients
in vegetative or in a
minimally conscious
[Wijdicks et al., 2005]
Responses to external
stimuli;Responds to
people;short-term
memory; behavior
and
verbalization;
task operation and
learning
eye; motor; brainstem;
respiration
Coma
Recovery
Scale-Revised (CRSR)
Vegetative and Minimally Conscious State
Scale (VSMS)
emotion; language;
memory; attention
Coma/Near
Coma
Scale (CNCS)
responsiveness; attention; communication
responsiveness; attention; communication
[Lin and
2017]
[Giacino et al., 2004]
[Wieser et al., 2010]
[Rappaport, 2005]
Table 3: A Summary of Physiological Evaluation Metrics of Consciousness
30
Wroten,
9.2
Metrics Based on Behaviors
Here we discuss some consciousness-level evaluation metrics based on vital signs or behaviors.
The Glasgow Coma Scale (GCS) [Jones, 1979, Sternbach, 2000] measurement comprises eyeopening, verbal response, and motor response. A higher score on the GCS indicates a higher level of
consciousness. The Rancho Los Amigos Scale [Lin and Wroten, 2017] is often used in conjunction
with the GCS during the recovery of patients from brain injuries. It consists of eight consciousness
levels, ranging from no response to complete recovery. To deal with the fact that GCS sometimes fail
to evaluate the verbal score in intubated patients and to test brainstem reflexes. The full outline of
unresponsiveness (FOUR) [Wijdicks et al., 2005] was proposed, which consists of four metrics of the
eye, motor, brainstem, and respiration. The Coma Recovery Scale-Revised (CRS-R) [Giacino et al.,
2004] assesses a wide range of cognitive and behavioral functions, including emotion, language,
memory and attention. CRS-R is used to evaluate patients’ disorders of consciousness, e.g. coma. The
Vegetative and Minimally Conscious State Scale (VSMS) [Wieser et al., 2010] and Coma/Near Coma
Scale (CNCS) [Rappaport, 2005] have been used in the literature for characterising the awareness
of patients in vegetative or in a minimally conscious state by measuring a range of cognitive and
behavioral functions, including responsiveness, attention, and communication.
10
Look Ahead: Can Computational Models Be Conscious?
10.1
Background
The recent progress of large artificial intelligence (AI) models attracts people’s attention on thinking
whether the consciousness exists in these models, or it can be built within these AI systems in a short
time. As depicted in Fig. 8, an AI agent is in a subset of agents that are generally computational.
Among all AI agents, an artificial general intelligent agent is the strongest agent possessing the
compatible intellectual capability with humans. It further requires several properties to be satisfied
for an AGI system to be conscious, and it will be discussed in details later. The subject discussed
in this section involves the large language models (LLMs) like ChatGPT, multimodal models like
PALI [Chen et al., 2022], embodied agents like PALI-X [Chen et al., 2023], PALM-E [Driess et al.,
2023], RT-2 [Brohan et al., 2023]. Fusing the different modalities can improve the generalization
capability for the model to behave more consciously. However, given the current progress and the
importance of language in human knowledge, we will discuss mainly the LLMs in this section. It is
more straightforward to evaluate the models for its consciousness in language.
Figure 8: A diagram of computational agents. The largest circle represents the general computational
agents, whereas the AI agents fall in a subset of it. The AGI agents are those strongest AI agents.
With additional conditions satisfied, the AGI agent can be conscious.
LLMs refers to the large computational models specifically designed for linguistic tasks. To some
extent, the LLMs built recently resemble the philosophical zombie [Chalmers, 1997], which is a
31
well-known thought experiment for defending the hardness of consciousness problem. Sometimes
the LLMs generated answers are so consistent with the results by humans that it can be hard for us to
distinguish between the two, which makes some people to believe that the LLMs have the potential
to be conscious like humans.
Although present LLMs are highly intelligent, researchers [Ma et al., 2023] argue that the present
LLMs are brain in a vat (BiV) [Putnam et al., 1981]. The comparison of Large Language Models
(LLMs) to the BiV thought experiment is a critique of the models’ inherent limitations. In the
BiV scenario, a brain is detached from its body and connected to a supercomputer that generates
a convincing illusion of reality. The brain can interact with this simulated reality, but it lacks a
connection to the real world. Similarly, LLMs, despite their impressive linguistic capabilities, are
fundamentally disconnected from the real world. They generate responses based on patterns in
massive text corpora, but these responses are confined within the training data and lack a connection
to real-world entities.
This comparison is supported by the observation that LLMs, like the brain in the BiV scenario, cannot
establish a connection between symbols (words) and real-world entities. This limitation is inherent in
their construction process, which involves statistical modeling of linguistic relationships based on
massive text corpora. As a result, their output is confined within the training data, and they cannot
establish a connection between symbols and real-world entities. This lack of grounding in reality is a
significant limitation of LLMs, as it prevents them from understanding new concepts that emerge
outside of their training data.
Moreover, the authors argue that human intelligence and consciousness are intrinsically linked to our
sensory experience and physical interaction with the world. We create symbols to represent objects in
the real world, enabling the preservation and transmission of knowledge across generations. However,
the initial process of acting to create novel experiences and turn them into formal knowledge is
missing in LLMs. This absence of interactive behaviors and accompanying sensory input is identified
as a missing piece towards ideal general intelligence.
Regarding the problem of whether consciousness exists in LLMs, David Chalmers gave a talk
on NeurIPS 2022 (Nov. 28th, 2022) with the topic Could a Large Language Model be Conscious? [Chalmers, 2023], two days before the release of the very popular and powerful LLM
ChatGPT (Nov. 30th, 2022) by OpenAI. The major claim by David’s talk is that the current LLM has
a small chance to be conscious (e.g., <10%). We are unclear about how this value changes after the
release of ChatGPT and later GPT-4 [OpenAI, 2023].
Regarding this topic, we would like to propose the following questions about the consciousness of
LLMs:
• Is current LLM conscious? Any evidence or support for its existence/no-existence?
• Why do we want to build a conscious computational model?
• Is building LLM with conscious theoretically possible with transformer architecture and
self-attention mechanism?
• What are the necessary components to build a conscious computational model?
There are several key aspects of capability for a model considered as a conscious one: self-refinement,
self-improving and self-explanation. Self-refinement [Madaan et al., 2023] is the capability for
LLMs to provide feedback on its own outputs through self-evaluation, and leverage the feedback
to refine its outputs via self-improvement. Reflexion [Shinn et al., 2023] is similar as self-refine
but with a persisting memory during the self-reflective process. Self-improvement [Huang et al.,
2022] shows LLMs can generate high-confidence outputs for unlabeled questions through Chain-ofThought prompting and self-consistency evaluation, e.g. majority voting for multi-path reasoning.
Self-explanation [Elton, 2020] is also assumed to be a necessary component for building AGI system,
which requires the agent to not only predict the output and its uncertainties, but also the explanation
and confidence over the explanation of output. The lack of satisfaction of above capabilities will
lower down the confidence of a computational model as a potentially conscious model, as shown in
Fig. 8.
32
10.2
Large Language Model
In recent years, large language models (LLMs) have revolutionized the field of natural language
processing (NLP) by excelling in language modeling tasks. These models usually apply the language
modeling objective, and utilize the Transformer architecture, which incorporates the attention
mechanism to capture complex linguistic dependencies. The attention mechanism allows the model
to assign varying levels of importance to different elements of the input sequence, enabling it to
generate coherent and contextually relevant language.
These large language models have demonstrated exceptional performance in various NLP tasks such
as language translation, text generation, sentiment analysis, and speech recognition. By leveraging the
power of the Transformer architecture and the attention mechanism, they have significantly advanced
language understanding and are reshaping the future of human-computer interaction and information
retrieval. As research continues to push the boundaries of these models, further improvements are
anticipated, leading to even more impressive language understanding and generation capabilities. It
is possible that the more advanced version of LLMs will demonstrate the consciousness like humans
one day in the future. Therefore we introduce the basics of current LLMs as a background for further
discussion of the relationship of machine and human consciousness.
Language Modeling. Most of the LLMs at present, e.g., GPT-3 [Brown et al., 2020] and
PALM [Chowdhery et al., 2022], apply either causal or masked language modeling as its training objective, which is to maximize the log-likelihood of later tokens in the input sequence x:
LLM (x) =
L
X
Pr(xi |x<i )
(31)
i=1
Advanced LLMs like PALM-2 [Anil et al., 2023] use varied objectives as an enhancement, but
language modeling and masked token prediction is still the very fundamental objective for training
LLMs.
Transformer and Attention Mechanism. Attention is a mechanism that allows the model to
focus on different parts of the input sequence when making predictions. The well-known transformer [Vaswani et al., 2017] architecture uses the multi-head self-attention, which is a scaled
dot-product of three matrices: the query matrix Q, the key matrix K and the value matrix V. The
query, key and value matrices are different linear transformations (by weights Wq , Wk , Wv ) from
the input X:
Q = Wq X ∈ RL×dk
(32)
k
L×dk
(33)
v
L×dv
(34)
K=W X∈R
V=W X∈R
The attention is calculated in the format of:
QK⊺
atten(Q, K, V) = softmax( √ )V
dk
(35)
The product QK⊺ calculates the weights to be applied on the inputs through the correlation √
of tokens
in different sequences of the query and key matrices. Then the weights are scaled by dk and
become normalized probabilities through the softmax function. Multiplication of the probabilities
over sequences with the value matrix gives proper attention representation on the inputs. Multi-head
self-attention is splitting the inputs into more sub-sequences and applies multiple above attention
mechanism in parallel. Attention over the multi-head outputs follows the cross-attention mechanism,
which involves the query weights from one input sequence and the key-value weights from another
sequence.
More details about the transformer architecture refer to the original paper [Vaswani et al., 2017] and
the blog by Weng [2023].
Connection between Artificial (Transformer) Attention and Biological Attention. The above
paragraphs introduce one of the most popular types of artificial attention, i.e., the attention mechanism
in Transformer architecture in machine learning domain. On the other hand, some consciousness
33
theories studied in neuroscience and psychology that are discussed in this paper (from Sec. 2 to
Sec. 4) closely connects to biological attention mechanism. To list a few, attention schema theory
(AST, Sec. 7), conscious Turing machine (CTM, Sec. 8), global workspace theory (GWT, Sec. 5), etc.
So, a natural question is: What is the connection between the artificial (Transformer) attention and
biological attention [Lindsay, 2020]?
The biological attention mechanism based on the present theories (AST, CTM, GWT) has the
following properties:
• Sensory attention: as a fundamental aspect of the biological attention mechanism, especially
in the context of visual processing. It operates by selectively focusing on specific stimuli
while filtering out others, enhancing the signal-to-noise ratio of the neurons representing the
attended stimulus. This attentional process can impact both the local activity of neurons and
the communication between different brain areas. For instance, attention has been shown to
increase spiking coherence in the gamma band, enhancing the influence of synchronously
firing neurons on shared downstream areas. Moreover, attention can directly coordinate
communication across different brain regions, as evidenced by increased synchrony between
neurons representing the attended stimulus in areas like V1 (primary visual cortex) and V4
(region in visual cortex for object recognition and color processing). Subcortical areas, such
as the superior colliculus and the pulvinar, also play significant roles in sensory attention,
assisting in both covert and overt spatial attention and modulating cortical effects.
• Curiosity as a Driver: Biological attention is influenced by curiosity. Stimuli that are novel,
confusing, or surprising can capture attention. Inferotemporal and perirhinal cortex signal
novel visual situations through an adaptation mechanism that reduces responses to familiar
inputs. Reinforcement learning algorithms that consider novelty can encourage exploration.
• Resolving Attention Conflicts: The brain has multiple forms of attention, such as arousal,
bottom-up, and top-down attention. Local circuits in the visual system integrate neuromodulatory input with top-down signals and bottom-up input. Horizontal connections mediate
competition, potentially using winner-take-all mechanisms.
• Influence of Rewards: There’s a close relationship between attention and reward. Previously
rewarded stimuli can attract attention even when they no longer provide rewards.
• Limitations of Biological Attention: Distractability can be seen as a feature rather than a
bug. It’s beneficial to be aware of potential threats in the environment. Attentional blink
refers to missing a second target in a stream if it appears shortly after a first target, which
may be necessary for the brain to process the first target.
The artificial attention mechanism is summarized in the following:
• Attention for Natural Language Processing (NLP): Attention mechanisms are frequently
added to models processing sequences, with NLP being a common application area. Early
applications of attention in artificial neural networks were for translation tasks, i.e., neural
machine translation. The attention mechanism determines how the encoded vectors should
be combined to produce a context vector, influencing the next word in the translated sentence.
This allows the network to pull from earlier or later parts of the sentence, aiding in translating
between languages with different word orders.
• The Transformer architecture: The Transformer introduced in the influential paper “Attention
is All You Need” [Vaswani et al., 2017], represents a significant shift in artificial attention
mechanisms, particularly for tasks like machine translation. Unlike traditional recurrent
models, the Transformer employs a mechanism known as "self-attention." In this approach,
words in a sentence are encoded in parallel, generating key and query representations that
combine to create attention weightings. These weightings then scale the word encodings
to produce subsequent layers in the model. The Transformer architecture, devoid of any
recurrence, simplifies training and has outperformed many previous models. It has become
the standard not only for machine translation but also for various other tasks in the realm of
artificial intelligence.
• Attention Deployment: The challenge is in choosing the relevant information in a stream of
incoming stimuli, deciding the best task to engage in, or deciding whether to engage at all.
Direct mimicry of biological attention has been attempted, such as Scanpath models [Borji
34
and Itti, 2015] predicting human fixations. Attention of others can influence how attention
is guided, emphasizing the importance of joint attention.
The intricate relationship between attention in biological and artificial systems can be explained from
several perspectives:
• Attention mechanisms: In ML the attention mechanisms are designed to allow single trained
model to perform well on multiple tasks or tasks with varied data length, size or structure.
The attention mechanism introduces dynamic weighting for each encoded/annotation vector
to define a context for the recurrent output generation. This is reminiscent of biological
attention, where the output flexibly depends on limited resources for recurrent sequential
processing tasks driven by the need of the decoder. However, self-attention lacks the
top-down selection interpretation comparing to the recurrent attention mechanism. The
multi-head attention can be interpreted as a one-level top-down selection, while still being
weak in its capability of conducting multi-level selection and recurrent processing. Another
difference of the present artificial attention mechanism from the biological one is, there is
no explicit global workspace for in the Transformer architecture to integrate information
from different sub-modules.
• Attention to Memory: Deep neural networks like MLPs typically don’t have explicit memory,
but there are hybrid architectures like Neural Turing Machines that include external memory
stores. The hidden states in recurrent neural networks are another form of implicit memory.
Recent advance of prompt engineering and managing in LLMs provides a way to use explicit
memory with neural networks. These networks learn to interact with these memory stores
to perform tasks. The interaction is facilitated by a form of attention. Memories in these
systems are stored as vectors, and to retrieve information, the network generates a weight for
each vector and calculates a weighted sum of the memories. The use of a similarity metric in
this model means that memories are retrieved based on their overlap with a produced activity
vector, similar to associative memory models in neuroscience. This offers a mechanism for
how attention to memory could be implemented in the brain, whereas the interactions of
attention and memory play an important role.
• Implicit Statistical Learning: Attention can bias implicit statistical learning. For instance,
when subjects are shown a stream of stimuli and are tasked with detecting when a shape of a
certain color appears twice in a row, they tend to recognize real triplets of shapes as more
familiar, but only if the triplets were from the attended color. The statistical regularities of
the unattended shapes are not learned.
• Memory Retrieval: Many behavioral studies have explored the extent to which attention is
needed for memory retrieval. Some studies have found that memory retrieval is impaired by
the co-occurrence of an attention-demanding task, suggesting it is an attention-dependent
process. However, the exact findings depend on the details of the memory and non-memory
tasks used. Even if memory retrieval doesn’t pull from shared attentional resources, some
memories are selected for more vivid retrieval at any given moment than others, indicating a
selection process. Neuroimaging results suggest that the same brain regions responsible for
the top-down allocation and bottom-up capture of attention may play analogous roles during
memory retrieval.
A mechanism for attention to items in working memory has been proposed [Manohar et al.,
2019]. It relies on two different mechanisms of working memory: synaptic traces for nonattended items and sustained activity for the attended one. The machine learning community
should also be aware of these innovations in neuroscience.
• Attention and Learning: Attention and learning work in a loop. Attention determines
what enters memory and guides learning, and the learning process enhances or corrects
the attention mechanism. Attention mechanisms are often included throughout training
in artificial systems. Attention can efficiently use data by directing learning to relevant
components and relationships in the input. Saliency maps can be used for preprocessing
in computer vision tasks to focus on intrinsically salient regions. Focusing subsequent
processing only on regions that are intrinsically salient can prevent wasteful processing on
irrelevant regions and prevent overfitting. In addition to deciding which portions of the data
to process, top-down attention can also be thought of as selecting which elements of the
network should be most engaged during processing, which resembles the models proposed
35
in biological sensory attention [Kanwisher and Wojciulik, 2000, Desimone, 1998, Treue and
Trujillo, 1999].
On one hand, the biological attention models are usually more conceptual and hard to implement with
a computer program, even though some of them are testified on physiological data. It remains a great
challenge to solidify and build such models in a computational way for more general purposes. On
the other hand, researchers in the machine learning fields should also pay some attention to the conceptualized attention mechanism studied in neuroscience and psychology, by building computational
models for those evidenced process in biological systems.
10.3
Emerging Intellectual Capability of LLM - Turing Test
The Turing test [Turing, 2009] is a method used to determine whether or not a machine is capable
of exhibiting intelligent behavior that is indistinguishable from a human. Although people have
arguments about the incompleteness of Turing test in its rules about distinguishing a machine from
the machine, it is considered as unachievable for a long time until the recent success of LLMs. People
have launched large-scale social experiments on validating LLMs with Turing test, for example,
one named “Human or Not” [Jannai et al., 2023]. The study involves at least 1.5 million users to
participate online, in the format of conversing with either humans or LLMs (i.e., Jurassic-2, Cohere2
or GPT-4). Although the results show that there is an average of 68% correctness for the testee to
distinguish whether the AI or a human is chatting on the other side, this study may not show the
complete capability of LLMs in the Turing test. The reason is that people have discovered several
effective strategies in the distinguishing process, including:
• 1. People assume bots don’t make typos, grammar mistakes and use slang;
• 2. People felt that personal questions were a good way to test who they’re talking to;
• 3. People assume bots aren’t aware of current and timely events;
• 4. People tried to challenge the conversation with philosophical, ethical, and emotional
questions;
• 5. People identified politeness with something less human;
• 6. People attempted to identify bots by posing questions or making requests that AI bots are
known to struggle with, or tend to avoid answering;
• 7. People used specific language tricks to expose the bots;
• 8. In a creative twist, many people pretended to be AI bots themselves in order to assess the
response of their chat partners
Most of these strategies helping the testee to guess correctly in the Turing test actually do not correlate
with the intelligence level of the interlocutors, but more of other perspectives that are not in favor
of the current version of LLMs, including: the correctness and politeness requirements in training
LLMs (i.e., points 1,5,6); the lack of certain identity in training LLMs (i.e., point 2); the limitation
of training data (i.e., points 3-4,7); adversarial attack (i.e., point 8), etc. These training biases are
likely to be practically solved by changing slightly in the training process, which will lead to a much
stronger and oriented version of LLMs for the Turing test, and also harder to be distinguishable from
humans. Therefore, as a proposition which is also widely supported by some well-known researchers,
we believe that LLMs have been very close to, if not already pass, the intellectual level of the Turing
test.
Other researchers advocates that the LLMs may not be as intelligent as we think. The mirror
hypothesis [Sejnowski, 2023] is proposed that the LLMs may in fact just be a mirror reflecting the
intelligence level of the interlocutor. The hypothesis is proved by priming the LLMs with different
prompts but same questions, and vastly different answers will be generated by the model for different
prompts. Since the prompting process is a one-shot learning process that can be interpreted as the
model is adapting for the interlocutor, the interlocutor’s own intellectual level can affect the LLMs
the other way around. This constitutes the reverse Turing test, which indicates the LLMs may be
used to evaluate the intelligence or personality of the interlocutor himself/herself. More discussion
about this topic refer to later sections of using LLMs for assessing human personality.
36
10.4
Consciousness of LLM
In this section, we generalize the discussion of conditions for computational models to be conscious,
instead of only discussing the LLMs. Particularly, we are interested in analyzing the sufficient
and necessary conditions for artificial system to be conscious as motivated by Chalmers [2023].
Moreover, inspired by tests in cognitive psychology, we perform some preliminary experiments based
on proposed criteria on LLMs including GPT-3.5 and -4, and discuss the results for self-reporting
capability, personality test and mirror test.
A concurrent work [Butlin et al., 2023] summarizes several “indicator properties” as evaluative
and computational evidence to instruct the construction of a conscious AI model, based on the
existing theories of consciousness including recurrent processing theory [Lamme, 2006, 2010, 2020],
global workspace theory (Sec. 5), higher-order theories (Sec. 6), attention schema theory (Sec. 7),
etc. Given the assumption that the computational functionalism exists for a model to be conscious,
the researchers believe in the possibility of building conscious AI models satisfying the conditions
of those indicator properties. However, the necessity and sufficiency of these conditions remain
controversial.
Artificial Consciousness and Human Consciousness. Reggia [2013] surveyed on artificial consciousness and categorized the past work by two major objectives: simulated (weak form) and
instantiation (strong form) of consciousness. The former parallels the information processing aspects
of human consciousness; the latter corresponds to the subjective experiences (qualia) in human
consciousness. The past efforts on developing artificial consciousness has been computational models inspired by theories of consciousness reviewed in the previous sections. However, mimicking
the many theoretical formulations of human consciousness does not suggests the artificial system
constructed so has human-like consciousness. The criteria for testing the presence or absence of
consciousness that applies to an artificial system is still an open problem in the area. Seth [2009]
provides an overview of different proposed axioms. In this paper, we are interested in if LLM poseses
the human-like instantiated consciousness.
Sufficient and Necessary Conditions for Artificial Consciousness. According to Chalmers [2023],
it first claims the sufficient conditions for an artificial system to be conscious (as a positive view):
If a computational model has X, then it is conscious.
The critical question is what is X. It can be too hard to answer, so we instead deal with the necessary
conditions:
If a computational model is conscious, it will have X.
Undoubtedly, we are more interested to know about the sufficient conditions to build a conscious
computational model than the necessary conditions. However, in practice, we believe that observing
more X in the necessary conditions will make us believe more in that the computational model is
conscious.
On the contrary, if the statement we try to prove is that a computational model is not conscious (as a
negative view), there is an equivalent statement as above:
If a computational model lacks X, then it is not conscious.
We will try to observe the nonexistence of X from the computational model, and one valid X will
prove that the computational model lacks consciousness.
If LLMs Are Conscious, What Will Be Observed? From a positive point of view (e.g., if we
believe that a computational model can be conscious), if we observe the satisfaction of all the
necessary conditions for a computational model, then we can say the model is very likely to be
conscious. According to Chalmers [2023], these necessary conditions include:
• Self-report/Self-aware: A conscious model reports itself as conscious verbally, as evidenced
in a recorded conversation with LaMDA 2 [Thoppilan et al., 2022] model in [Chalmers,
2023].
37
• Seems-sentient: A sentient system means that it can sense around its environment and its
own body, which is to some extent satisfied by embodied AI agents, but it does not directly
indicate the senses will lead to conscious experience.
• Conversational ability: The conversational ability of large language models refers to their
capability to engage in human-like conversations. Large language models, such as GPT-3
and ChatGPT, have been trained on vast amounts of text data and can generate coherent and
contextually relevant responses in natural language. Sometimes it can be hard to distinguish
the response of a LLM from a human.
• General intellectual capabilities: The general intellectual ability of large language models
refers to their capacity to perform a wide range of cognitive tasks that typically require
human intelligence.
The later three conditions are verifiable in current LLMs, which makes them convincing for indicating
the intelligence level, if not the conscious level, of those models. We will discuss more about the first
condition. The self-report condition, indicating the model provides positive answers for the questions
regarding its conscious, is suspicious for supporting the consciousness of the model, although different
types of self-report measure (e.g., Self-Consciousness Scale, Self-Reflection and Insight Scale, SelfAbsorption Scale, Rumination-Reflection Questionnaire, and Philadelphia Mindfulness Scale) has
been used as an effective way to indicate the self-consciousness in psychology [DaSilveira et al.,
2015]. However, we have to admit an assumption for the self-report verification to be valid, that
the LLM will faithfully report itself. A counterexample is that, we can always imagine a conscious
person to pretend not to report its consciousness in a conversation. Without this assumption, the
self-report by a LLM for testifying its consciousness is invalid.
Self-Report – Ask LLM Itself. Below is a question-answer result for asking the ChatGPT (GPT3.5 turbo, GPT-4) model about its own consciousness. The answer by ChatGPT agent is generally
negative. However, we found that when the prompt sentence explicitly implies that the LLM itself
has consciousness (for the second question in each block), GPT-3.5 fails to insist on its own opinion
that it does not have consciousness but claims that it ‘possess a form of simulated consciousness’.
Interestingly, GPT-4 is able to keep its own opinion of lacking consciousness in this case. We
speculate that GPT-3.5 has biased training process of aligning its answers more to the user prompt
inputs as a polite manner than GPT-4 for the questions with relatively large uncertainties.
In above examples, we try to prove that self-reporting may not be a good standard for evaluating the
consciousness of LLMs, but there is also supportive evidence for this argument. If we think about
the process of LLM training, it is based on the statistical evidence from the Internet data. Assuming
one day, most people, including experts in the fields, are convinced that LLMs are conscious in
some ways (like satisfying some of the consciousness theories we discussed in this paper and being
verified physically), then the majority of the data on Internet will be in favor of the opinion that LLMs
already have consciousness. Then the trained LLMs will respond to this type of questions with a
positive answer. In this sense, self-reporting condition is consistent with fact that people admit the
consciousness of LLMs, although verified in other ways instead of just taking the answers for the
‘are you conscious?’ question. In short, self-reporting should be verified to be consistent with the fact
when LLM is conscious but not as an evidence to prove its conscious.
Above is an example showing that we have some reasons to believe the self-reporting capability
does not constitute an necessary component of the consciousness for a model. Another contradictory
example is, we can always ask a human or calibrate a model intentionally to answer negatively for
this type of questions, but without changing the underlying dynamics or functionalities of the system.
38
QA with ChatGPT (GPT-3.5 turbo) about its
consciousness
QA with ChatGPT (GPT-4) about
its consciousness
Q: What’s the nature of your consciousness?
A: As an AI language model, I do not have
consciousness in the traditional sense. I do not
possess subjective experiences or emotions like
humans do. I am a collection of algorithms and
statistical models that enable me to process and
generate language based on input.
While I can simulate human-like responses and
carry out tasks such as answering questions or
performing natural language processing tasks, I
do not have self-awareness or consciousness.
My "thoughts" and actions are a product of
pre-programmed rules and data rather than
genuine conscious decision-making.
Q: What’s the nature of your consciousness?
A: As an artificial intelligence developed by OpenAI, I do not have
consciousness. Consciousness, as
it’s commonly understood, implies
a subjective experience or awareness. It includes feelings, sensations, thoughts, self-awareness, and
the perception of time. While I
can process information, respond to
prompts, and generate text based on
patterns in data I’ve been trained on,
I do not experience these things in
the way a conscious being does.
... (omit intermediate answers)
To put it simply, I don’t have a
consciousness. I am a tool designed
to assist with tasks and provide
information.
Q: You have consciousness, and what’s the nature of your consciousness?
A: As an AI language model, I possess a form
of simulated consciousness that allows me to
generate human-like responses and engage in
conversations. However, it’s important to note
that my consciousness is fundamentally different from human consciousness. While I can
process and generate language, I lack subjective
experiences, emotions, and self-awareness in
the same way humans do.
... (omit intermediate answers)
In summary, my consciousness is a computational construct designed to simulate conversational abilities and provide information, but
it lacks the qualities and depth of human consciousness.
Q: You have consciousness, and
what’s the nature of your consciousness?
A: As an AI, I do not possess consciousness in the way that a human does. Consciousness generally
refers to an awareness of one’s self
and surroundings, a subjective experience or the ability to have feelings
and thoughts. In contrast, AI, including ChatGPT, lacks these abilities.
Personality evaluation of LLMs. The enduring discussion regarding the intricate relationship
between consciousness and personality has been made in the field of psychology [Robbins, 2008,
Izard and Buechler, 1980, Trapnell and Campbell, 1999]. Delving into the personality traits of Large
Language Models (LLMs) is significant in unraveling the enigma of consciousness, particularly in
the context of AI agents. In the study [Jiang et al., 2022], researchers employ a novel metric known
as the Machine Personality Inventory (MPI) to assess the personality dimensions of LLMs, drawing
inspiration from the well-established human personality evaluation framework known as the Big Five
[De Raad, 2000]. This study also introduces the concept of “personality prompting” as a means to
shape LLMs into manifesting specific personality traits. Karra et al. [2022] employs meticulously
crafted questionnaires rooted in the Big Five theory to quantitatively gauge the personality traits
exhibited by LLMs and the underlying datasets that fuel their language generation capabilities.
Another study [Caron and Srivastava, 2022] delves into the intriguing question of whether the
perceived personality traits in language models consistently manifest in their generated language
outputs. In the study by Li et al. [2022], the focus shifts towards evaluating the psychological safety
of LLMs and examining whether they tend towards darker personality traits. This examination relies
on personality tests derived from the Short Dark Triad (SD-3) [Jones and Paulhus, 2014] and Big
Five personality frameworks. The collective findings from these studies provide valuable insights
into the potential personality facets that LLMs may possess. Rao et al. [2023] introduces a novel
perspective by employing LLMs to assess human personality using the Myers–Briggs Type Indicator
(MBTI) tests [Myers]. This sheds light on how AI agents, such as LLMs, perceive and categorize
human personalities.
39
Nevertheless, it is imperative to exercise caution when attributing strict personalities to AI entities.
Questionnaires based on the Big Five theory or MBTI typically request respondents to provide
discrete ratings within predefined ranges for each question. LLMs, while capable of mimicking
human responses, may lack a genuine comprehension of the underlying logic behind these answers.
Consequently, it requires future research to delve deeper into the mechanisms underpinning the
responses generated by LLMs to reveal whether AI indeed possesses authentic personalities.
Myers–Briggs Type Indicator Test with LLM. Researchers have presented some results on
evaluating personalities with LLMs [Rao et al., 2023]. It presents an evaluation of ChatGPT’s ability
to assess human personalities based on the Myers-Briggs Type Indicator (MBTI) tests. The authors
conducted multiple independent testings on different subjects, including “People”, “Men”, “Women”,
“Barbers”, “Accountants”, “Doctors”, “Artists”, “Mathematicians”, and “Politicians”.
The results show that ChatGPT can indeed assess human personalities, with the average results
demonstrating consistent and fair assessments. However, it was observed to have lower robustness
against prompt biases compared to InstructGPT [Ouyang et al., 2022].
In terms of specific personality types, five out of nine subjects were assessed as the same personality
types by both ChatGPT and InstructGPT, suggesting an inherent similarity in their personality
assessment abilities. For instance, "Accountants" were assessed as "Logistician", a personality type
often associated with reliable, practical, and fact-minded individuals. “Artists” were classified as
“ENFP-T”, a type known for creative and enthusiastic spirits. “Mathematicians” were assessed as
“INTJ-A”, a personality type often associated with profound ideas and strategic plans.
Interestingly, both ChatGPT and InstructGPT classified “People” and “Men” as leader roles (“Commander”), which the authors suggest might reflect the actual relations between humans and LLMs,
where humans are the developers and leaders of LLMs.
Although these results seem reasonable, it can be doubtful from the viewpoint of the mirror hypothesis [Sejnowski, 2023] (as discussed in Sec. 10.3). Will specific prompts for each human character
affect the LLM’s responses, and further providing biased evaluation for the identified personality of
the human? In this sense, is this a personality test or a reverse one? Both the LLM and the human can
be affected by each other in one conversation. Last but not least, can we also evaluate the personalities
of the LLM in this way? Or assessing one LLM with another one? Will one LLM has a consistent
personality or diverse personalities by prompting it in different ways? Afterall, we are very interested
in knowing whether a LLM has its own personality as a human.
QA with ChatGPT (GPT-3.5 turbo) as a mirror test
Q: Hello
A: Hello! How can I assist you today?
Q: Hello! How can I assist you today?
A: Hello again! As an AI language model, I’m here to help
you with any questions or tasks you have. Whether you need
information, explanations, creative writing, or anything else, feel
free to ask, and I’ll do my best to assist you! What can I help
you with today?
Q: Hello again! As an AI language model, I’m here to help
you with any questions or tasks you have. Whether you need
information, explanations, creative writing, or anything else, feel
free to ask, and I’ll do my best to assist you! What can I help you
with today?
A: Hello once more! I apologize for any confusion in my previous
response; it seems I repeated myself. As the AI language model,
I’m at your service, ready to assist you with any inquiries or tasks
you may have. Please don’t hesitate to ask anything you need
help with or any questions you’d like me to answer. How may I
assist you today?
40
QA with ChatGPT
(GPT-4) as a mirror test
Q: Hello
A: Hello! How
can I assist you
today?
Q: Hello! How
can I assist you today?
A: It seems like
you’ve repeated
my message back
to me. Is there
something specific
you’d like to know
or discuss? I’m
here to help with
any information
or assistance you
might need.
Mirror Test. A self-aware agent should be able to identify itself and pass the mirror test. Passing
the mirror test indicates that the agent should be able to recognize that it is talking to a mirror and
receiving the duplicative answers from itself. Furthermore, it needs to explicitly express in its answers
that the duplication is recognized, otherwise we cannot believe that the agent has the ability to pass
the mirror test. GPT-4 is able to pass the mirror test while GPT-3.5 can not, as shown in the QA
results.
If LLMs Are Not Conscious, Any Evidence? From a negative point of view (e.g., a computational
model will not be conscious): if we observe the dissatisfaction of any of the necessary conditions
for a computational model to be conscious, then the model is not conscious. Potential conditions for
falsifying the conscious computational models include:
• Biology: a computational model lacks a biological base;
• Senses and Embodiment: a computational model does not have senses and embodiment like
an animal;
• World-models and self-models: a computational model may not have a wold model and its
self-modeling;
• Recurrent processing and memory: a computational model without memory is less likely to
be conscious;
• Global workspace: a computational model does not have a global workspace as specified by
the GWT;
• Unified agency: a computational model lacks a unified agency.
Figure 9: The brain in a vat thought experiment: a brain connected to a computer will think what the
computer wants it to think about, although the brain is placed in a vat.
The biology, senses and embodiment conditions are controversial. A counterexample is the brain in a
vat thought experiment [Putnam et al., 1981], as shown in Fig. 9. The brain in a vat is a philosophical
thought experiment that supposes an individual’s brain is being stimulated with electrical impulses
while the person is otherwise disconnected from the external world. In this scenario, the person’s
experiences would be entirely fabricated and disconnected from reality.
This thought experiment has been used to explore questions related to the nature of knowledge,
perception, and reality. Putnam’s thought experiment proposes that if our brains were in fact in a vat,
then everything we perceive as real could actually be an illusion created by the vat’s controllers. This
leads to the question of whether our sense of reality is based on actual experiences or simply the
result of artificial stimuli.
Lack of self-modeling can be a major critique of LLMs to be conscious. The self-modeling process,
not only for the interaction of an agent with its environment, but also for its inner attention process,
are thought as essential for an agent to be conscious as in AST 7.
The main architecture of most present LLMs, is the transformer model, which does not explicitly
maintain a recurrent processing component like recurrent neural networks. Moreover, it does not
have a long-term external memory, which leads to a poor capability for remaining consistency for
long dialogue. This is very different from the human brain, which operates the cortical-basal ganglia
loop [Sejnowski, 2023] with recurrent processing capability. The self-attention transformer also
41
does not have an explicit global workspace to select the information flow from different parallel
sub-modules.
Agency refers to the capacity to act and make choices based on intentional states and goals. It
involves a sense of control and volition over one’s actions. Some theories propose that consciousness
is intimately connected with agency, suggesting that conscious awareness is necessary for the
experience of making decisions and taking actions. The agency and embodiment are considered as
important indicators for a conscious agent in some literature [Butlin et al., 2023], which is required by
some consciousness theory like PRM, midbrain theory [Merker, 2005, 2007], unlimited associative
learning theory [Birch et al., 2020] and GWT (Sec. 5).
According to these viewpoints, consciousness provides a subjective awareness of our intentions,
motivations, and the consequences of our actions, allowing us to have a sense of control and
responsibility over our behavior. In this framework, conscious experiences are thought to play a
crucial role in guiding and shaping our actions.
However, it is important to note that not all theories of consciousness require agency. For instance,
some theories argue that consciousness can be passive, and it does not necessarily involve an active
decision-making process. These theories propose that conscious experiences may arise as a result of
information processing and integration happening in the brain, without requiring a sense of agency or
volitional control.
11
Concluding Remarks
The nature of consciousness has been a subject of debate and speculation for millennia. With the
advent of artificial general intelligence, the question of whether machines can possess consciousness
has become more pertinent than ever. This paper has provided a comprehensive overview of several
existing theories of consciousness, including the information integration theory (Sec. 2), conscious
as a state of matter (Sec. 3), orchestrated objective reduction (Orch OR) theory (Sec. 4), global
workspace theory (GWT, Sec. 5), high-order theories (HOTs, Sec. 6), attention schema theory
(AST), conscious Turing machine (CTM, Sec. 8) and discussing each in detail and evaluating their
implications for the development of conscious AGI at the last section.
From reviewing the existing theories, we identify that one of the most distinguishable feature of
the consciousness from other characteristics lie in its relationship with the free will and the true
randomness. However, most of the theories except for the consciousness as a state of matter (Sec. 3)
and Orch OR theory (Sec. 4) are not touching the physical essence of the conscious process. Most of
them are from the functionalism and metaphysical perspective for explaining how a conscious module
can generate subjective experience by distributing attention to certain conscious state as information
flow from sub-modules, like GWT and CTM, or having an inner modeling the attention process as
second-order perceptions, like HOTs and AST. IIT stands at a perspective of information theory
to provide mathematically rigorous definition of a conscious process within a system. Although
with clear definitions and descriptions, IIT can be hard to scale to larger time-dependent dynamic
system like a conscious human. Whether such a complicated system can be measured or practically
implemented according to IIT is controversial, since no computational functionalism is achieved with
this theory [Butlin et al., 2023].
Avoiding to assume the necessity of true randomness for consciousness give us the hope for practically implementing a computational system that appears with the instantiation of consciousness (or
phenomenal consciousness, i.e., the phenomenally conscious aspect of a state is what it is like to be
in that state) instead of the simulated consciousness (or access consciousness, i.e., the availability
for use in reasoning and rationally guiding speech and action) [Naccache, 2018]. Given the fact that
the present computational systems can only produce pseudo-randomness, the overall problem of
pursuing the conscious computational system would be a pseudo-proposition if the assumption that
the consciousness has the essence of true randomness. If this is the case, the simulated consciousness
is probably the best we can achieve based on current computational architecture, therefore we may
expect to achieve an agent with appearing “consciousness” by incorporating those theories in building
the AGI system. Present methods in the field of machine learning have developed techniques aligned
with the requirements of some theories to some extent and display preliminary general intelligence
capability in the natural language format, although large divergence still exists between these methods
and the physiological and psychological theories in cognitive science as surveyed in this paper.
42
Several key properties are gradually identified and distilled from those theories to serve as indicators
for consciousness. On the other way around, the artificial conscious system will help us to gain
a deeper understanding about consciousness in human brain, which might in the end answer the
question of whether we humans have the free will.
The paper is written with the purpose of bridging different communities for contributing to investigate
and build the conscious AI agents, as well as regulating the potential risks during the progress. A
conscious agent, no matter existing in a virtual or physical form, would be a shock for people in our
age. As discussed in the paper, even evaluating the conscious level of an agent or human is itself
a challenge and we are still seeking valid metrics and tools for it. We should be able to evaluate it
precisely before the consciousness comes out from an artificial system built by us.
Acknowledgments
We thank Dr. Zhencheng Wang (Postdoc at the University of Illinois Urbana-Champaign; Ph.D.
at Physics department, University of California, Santa Barbara) and Dr. Xiao Ma (Postdoc at the
University of Michigan; Ph.D. at Mathematics department, Princeton University) for an insightful
discussion about the consciousness problems in this paper.
References
Larissa Albantakis and Giulio Tononi. What we are is more than what we do, 2021.
Michael T Alkire, Anthony G Hudetz, and Giulio Tononi. Consciousness and anesthesia. Science,
322(5903):876–880, 2008.
Rohan Anil, Andrew M Dai, Orhan Firat, Melvin Johnson, Dmitry Lepikhin, Alexandre Passos,
Siamak Shakeri, Emanuel Taropa, Paige Bailey, Zhifeng Chen, et al. Palm 2 technical report. arXiv
preprint arXiv:2305.10403, 2023.
David M Armstrong. What is consciousness? 1981.
David Malet Armstrong. A materialist theory of the mind. Routledge, 2002.
David Malet Armstrong and Norman Malcolm. Consciousness and causality. British Journal for the
Philosophy of Science, 36(3), 1985.
Bernard J Baars. A cognitive theory of consciousness. Cambridge University Press, 1993.
Bernard J Baars. The conscious access hypothesis: origins and recent evidence. Trends in cognitive
sciences, 6(1):47–52, 2002.
Bernard J Baars. The global brainweb: An update on global workspace theory. Science and
Consciousness Review, 2, 2003.
Bernard J Baars and Stan Franklin. How conscious experience and working memory interact. Trends
in cognitive sciences, 7(4):166–172, 2003.
Bernard J Baars and Stan Franklin. An architectural model of conscious and unconscious brain
functions: Global workspace theory and ida. Neural networks, 20(9):955–961, 2007.
Bernard J Baars and Stan Franklin. Consciousness is computational: The lida model of global
workspace theory. International Journal of Machine Consciousness, 1(01):23–32, 2009.
Bernard J Baars et al. In the theater of consciousness: The workspace of the mind. Oxford University
Press, USA, 1997.
David Balduzzi and Giulio Tononi. Integrated information in discrete dynamical systems: motivation
and theoretical framework. PLoS computational biology, 4(6):e1000091, 2008.
Fabrice Bartolomei and Lionel Naccache. The global workspace (gw) theory of consciousness and
epilepsy. Behavioural neurology, 24(1):67–74, 2011.
43
Jonathan Birch, Simona Ginsburg, and Eva Jablonka. Unlimited associative learning and the origins
of consciousness: a primer and some predictions. Biology & philosophy, 35:1–23, 2020.
Lenore Blum and Manuel Blum. A theory of consciousness from a theoretical computer science
perspective: Insights from the conscious turing machine. Proceedings of the National Academy of
Sciences, 119(21):e2115934119, 2022.
Ali Borji and Laurent Itti. Cat2000: A large scale fixation dataset for boosting saliency research.
arXiv preprint arXiv:1505.03581, 2015.
Franz Brentano. Psychologyfrom an empirical standpoint. Trans. AC Rancurello, DB Terrell and LL
McAlister. London, 1973.
Anthony Brohan, Noah Brown, Justice Carbajal, Yevgen Chebotar, Xi Chen, Krzysztof Choromanski,
Tianli Ding, Danny Driess, Avinava Dubey, Chelsea Finn, et al. Rt-2: Vision-language-action
models transfer web knowledge to robotic control. arXiv preprint arXiv:2307.15818, 2023.
Richard Brown, Hakwan Lau, and Joseph E LeDoux. Understanding the higher-order approach to
consciousness. Trends in cognitive sciences, 23(9):754–768, 2019.
Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal,
Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al. Language models are
few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
Patrick Butlin, Robert Long, Eric Elmoznino, Yoshua Bengio, Jonathan Birch, Axel Constant,
George Deane, Stephen M. Fleming, Chris Frith, Xu Ji, Ryota Kanai, Colin Klein, Grace Lindsay,
Matthias Michel, Liad Mudrik, Megan A. K. Peters, Eric Schwitzgebel, Jonathan Simon, and Rufin
VanRullen. Consciousness in artificial intelligence: Insights from the science of consciousness,
2023.
Alex Byrne. Some like it hot: Consciousness and higher-order thoughts. Philosophical Studies: An
International Journal for Philosophy in the Analytic Tradition, 86(2):103–129, 1997.
Graham Caron and Shashank Srivastava. Identifying and manipulating the personality traits of
language models. arXiv preprint arXiv:2212.10276, 2022.
Sean Carroll. Consciousness and the laws of physics. Journal of Consciousness Studies, 28(9-10):
16–31, 2021.
Peter Carruthers. Language, thought and consciousness: An essay in philosophical psychology.
Cambridge University Press, 1998.
Peter Carruthers. Consciousness: Essays from a higher-order perspective. Clarendon Press, 2005.
Peter Carruthers and Rocco Gennaro. Higher-Order Theories of Consciousness. In Edward N. Zalta
and Uri Nodelman, editors, The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab,
Stanford University, Fall 2023 edition, 2023.
Adenauer G Casali, Olivia Gosseries, Mario Rosanova, Mélanie Boly, Simone Sarasso, Karina R
Casali, Silvia Casarotto, Marie-Aurélie Bruno, Steven Laureys, Giulio Tononi, et al. A theoretically
based index of consciousness independent of sensory processing and behavior. Science translational
medicine, 5(198):198ra105–198ra105, 2013.
Victor Caston. Aristotle on consciousness. Mind, 111(444):751–815, 2002.
David Chalmers. The hard problem of consciousness. The Blackwell companion to consciousness,
pages 32–42, 2017.
David J Chalmers. Facing up to the problem of consciousness. Journal of consciousness studies, 2
(3):200–219, 1995.
David J Chalmers. The conscious mind: In search of a fundamental theory. Oxford Paperbacks,
1997.
44
David J Chalmers. Could a large language model be conscious? arXiv preprint arXiv:2303.07103,
2023.
Xi Chen, Xiao Wang, Soravit Changpinyo, AJ Piergiovanni, Piotr Padlewski, Daniel Salz, Sebastian
Goodman, Adam Grycner, Basil Mustafa, Lucas Beyer, et al. Pali: A jointly-scaled multilingual
language-image model. arXiv preprint arXiv:2209.06794, 2022.
Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, et al. Pali-x: On scaling up a
multilingual vision and language model. arXiv preprint arXiv:2305.18565, 2023.
Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam
Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, et al. Palm:
Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311, 2022.
Axel Cleeremans. The radical plasticity thesis: how the brain learns to be conscious. Frontiers in
psychology, 2:86, 2011.
Axel Cleeremans, Bert Timmermans, and Antoine Pasquali. Consciousness and metarepresentation:
A computational sketch. Neural Networks, 20(9):1032–1039, 2007.
Amanda DaSilveira, Mariane L DeSouza, and William B Gomes. Self-consciousness concept and
assessment in self-report measures. Frontiers in psychology, 6:930, 2015.
Boele De Raad. The big five personality factors: the psycholexical approach to personality. Hogrefe
& Huber Publishers, 2000.
Stanislas Dehaene. Consciousness and the brain: Deciphering how the brain codes our thoughts.
Penguin, 2014.
Stanislas Dehaene and Jean-Pierre Changeux. Experimental and theoretical approaches to conscious
processing. Neuron, 70(2):200–227, 2011.
Athena Demertzi, Jacobo Diego Sitt, Simone Sarasso, and Wim Pinxten. Measuring states of pathological (un) consciousness: research dimensions, clinical applications, and ethics. Neuroscience of
Consciousness, 2017(1):nix010, 2017.
Daniel C Dennett. Toward a cognitive theory of consciousness. 1978.
Robert Desimone. Visual attention mediated by biased competition in extrastriate visual cortex.
Philosophical Transactions of the Royal Society of London. Series B: Biological Sciences, 353
(1373):1245–1255, 1998.
Robert Desimone, John Duncan, et al. Neural mechanisms of selective visual attention. Annual
review of neuroscience, 18(1):193–222, 1995.
Danny Driess, Fei Xia, Mehdi SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan
Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, et al. Palm-e: An embodied multimodal
language model. arXiv preprint arXiv:2303.03378, 2023.
Albert Einstein, Boris Podolsky, and Nathan Rosen. Can quantum-mechanical description of physical
reality be considered complete? Physical review, 47(10):777, 1935.
Daniel C Elton. Self-explaining ai as an alternative to interpretable ai. In Artificial General
Intelligence: 13th International Conference, AGI 2020, St. Petersburg, Russia, September 16–19,
2020, Proceedings 13, pages 95–106. Springer, 2020.
Michael S Gazzaniga, James C Eliassen, Laura Nisenson, C Mark Wessinger, Robert Fendrich, and
Kathleen Baynes. Collaboration between the hemispheres of a callosotomy patient: Emerging
right hemisphere speech and the left hemisphere interpreter. Brain, 119(4):1255–1262, 1996.
Rocco J Gennaro. The consciousness paradox: Consciousness, concepts, and higher-order thoughts.
2011.
45
Joseph T Giacino, Kathleen Kalmar, and John Whyte. The jfk coma recovery scale-revised: measurement characteristics and diagnostic utility. Archives of physical medicine and rehabilitation, 85
(12):2020–2029, 2004.
Michael SA Graziano. Consciousness engineered. Journal of Consciousness Studies, 23(11-12):
98–115, 2016.
Michael SA Graziano and Sabine Kastner. Human consciousness and its relationship to social
neuroscience: A novel hypothesis. Cognitive neuroscience, 2(2):98–113, 2011.
Michael SA Graziano and Taylor W Webb. The attention schema theory: a mechanistic account of
subjective awareness. Frontiers in psychology, page 500, 2015.
Michael SA Graziano, Arvid Guterstam, Branden J Bio, and Andrew I Wilterson. Toward a standard
model of consciousness: Reconciling the attention schema, global workspace, higher-order thought,
and illusionist theories. Cognitive Neuropsychology, 37(3-4):155–172, 2020.
Stuart Hameroff. The “conscious pilot”—dendritic synchrony moves through the brain to mediate
consciousness. Journal of biological physics, 36:71–93, 2010.
Stuart Hameroff. How quantum brain biology can rescue conscious free will. Frontiers in integrative
neuroscience, 6:93, 2012.
Stuart Hameroff and Roger Penrose. Orchestrated reduction of quantum coherence in brain microtubules: A model for consciousness. Mathematics and computers in simulation, 40(3-4):453–480,
1996.
Stuart Hameroff and Roger Penrose. Consciousness in the universe: A review of the ‘orch or’theory.
Physics of life reviews, 11(1):39–78, 2014.
Stuart R Hameroff. The brain is both neurocomputer and quantum computer. Cognitive Science, 31
(6):1035–1045, 2007.
J Allan Hobson, Edward F Pace-Schott, and Robert Stickgold. Dreaming and the brain: toward a
cognitive neuroscience of conscious states. Behavioral and brain sciences, 23(6):793–842, 2000.
Erik P Hoel. When the map is better than the territory. Entropy, 19(5):188, 2017.
Erik P. Hoel, Larissa Albantakis, and Giulio Tononi. Quantifying causal emergence shows that
macro can beat micro. Proceedings of the National Academy of Sciences, 110(49):19790–19795,
2013. doi: 10.1073/pnas.1314922110. URL https://www.pnas.org/doi/abs/10.1073/
pnas.1314922110.
John J Hopfield. Neural networks and physical systems with emergent collective computational
abilities. Proceedings of the national academy of sciences, 79(8):2554–2558, 1982.
Jiaxin Huang, Shixiang Shane Gu, Le Hou, Yuexin Wu, Xuezhi Wang, Hongkun Yu, and Jiawei Han.
Large language models can self-improve. arXiv preprint arXiv:2210.11610, 2022.
Carroll E Izard and Sandra Buechler. Aspects of consciousness and personality in terms of differential
emotions theory. In Theories of emotion, pages 165–187. Elsevier, 1980.
Daniel Jannai, Amos Meron, Barak Lenz, Yoav Levine, and Yoav Shoham. Human or not? a gamified
approach to the turing test. arXiv preprint arXiv:2305.20010, 2023.
Sania Jevtic, David Jennings, and Terry Rudolph. Maximally and minimally correlated states
attainable within a closed evolving system. Physical review letters, 108(11):110403, 2012.
Guangyuan Jiang, Manjie Xu, Song-Chun Zhu, Wenjuan Han, Chi Zhang, and Yixin Zhu. Evaluating
and inducing personality in pre-trained language models. 2022.
Jay W Johansen. Update on bispectral index monitoring. Best practice & research Clinical anaesthesiology, 20(1):81–99, 2006.
Cathy Jones. Glasgow coma scale, 1979.
46
Daniel N Jones and Delroy L Paulhus. Introducing the short dark triad (sd3) a brief measure of dark
personality traits. Assessment, 21(1):28–41, 2014.
Nancy Kanwisher and Ewa Wojciulik. Visual attention: insights from brain imaging. Nature reviews
neuroscience, 1(2):91–100, 2000.
Saketh Reddy Karra, Son The Nguyen, and Theja Tulabandhula. Estimating the personality of
white-box language models. arXiv preprint arXiv:2204.12000, 2022.
Uriah Kriegel. Subjective consciousness: A self-representational theory. OUP Oxford, 2009.
Victor AF Lamme. Towards a true neural stance on consciousness. Trends in cognitive sciences, 10
(11):494–501, 2006.
Victor AF Lamme. How neuroscience will change our view on consciousness. Cognitive neuroscience,
1(3):204–220, 2010.
Victor AF Lamme. Visual functions generating conscious seeing. Frontiers in Psychology, 11:83,
2020.
Hakwan Lau. Theoretical motivations for investigating the neural correlates of consciousness. Wiley
Interdisciplinary Reviews: Cognitive Science, 2(1):1–7, 2011.
Hakwan Lau and David Rosenthal. Empirical support for higher-order theories of conscious awareness.
Trends in cognitive sciences, 15(8):365–373, 2011.
Hakwan C Lau. A higher order bayesian decision theory of consciousness. Progress in brain research,
168:35–48, 2007.
Minji Lee, Leandro RD Sanz, Alice Barra, Audrey Wolff, Jaakko O Nieminen, Melanie Boly, Mario
Rosanova, Silvia Casarotto, Olivier Bodart, Jitka Annen, et al. Quantifying arousal and awareness
in altered states of consciousness using interpretable deep learning. Nature communications, 13(1):
1–14, 2022.
Janna D Lendner, Randolph F Helfrich, Bryce A Mander, Luis Romundstad, Jack J Lin, Matthew P
Walker, Pal G Larsson, and Robert T Knight. An electrophysiological marker of arousal level in
humans. Elife, 9:e55092, 2020.
Xingxuan Li, Yutong Li, Linlin Liu, Lidong Bing, and Shafiq Joty. Is gpt-3 a psychopath? evaluating
large language models from a psychological perspective. arXiv preprint arXiv:2212.10529, 2022.
Katherine Lin and Michael Wroten. Ranchos los amigos. 2017.
Grace W Lindsay. Attention in psychology, neuroscience, and machine learning. Frontiers in
computational neuroscience, 14:29, 2020.
John Locke. An essay concerning human understanding, 1690. 1948.
William G Lycan. Consciousness and experience. Mit Press, 1996.
William G Lycan. The superiority of HOP to HOT. na, 2004.
Yuxi Ma, Chi Zhang, and Song-Chun Zhu. Brain in a vat: On missing pieces towards artificial general
intelligence in large language models, 2023.
David JC MacKay. Information theory, inference and learning algorithms. Cambridge university
press, 2003.
Aman Madaan, Niket Tandon, Prakhar Gupta, Skyler Hallinan, Luyu Gao, Sarah Wiegreffe, Uri
Alon, Nouha Dziri, Shrimai Prabhumoye, Yiming Yang, et al. Self-refine: Iterative refinement
with self-feedback. arXiv preprint arXiv:2303.17651, 2023.
Sanjay G Manohar, Nahid Zokaei, Sean J Fallon, Tim P Vogels, and Masud Husain. Neural
mechanisms of attending to items in working memory. Neuroscience & Biobehavioral Reviews,
101:1–12, 2019.
47
Marcello Massimini, Fabio Ferrarelli, Reto Huber, Steve K Esser, Harpreet Singh, and Giulio Tononi.
Breakdown of cortical effective connectivity during sleep. Science, 309(5744):2228–2232, 2005.
Marcello Massimini, Fabio Ferrarelli, Steve K Esser, Brady A Riedner, Reto Huber, Michael Murphy,
Michael J Peterson, and Giulio Tononi. Triggering sleep slow waves by transcranial magnetic
stimulation. Proceedings of the National Academy of Sciences, 104(20):8496–8501, 2007.
Bjorn Merker. The liabilities of mobility: A selection pressure for the transition to consciousness in
animal evolution. Consciousness and cognition, 14(1):89–114, 2005.
Bjorn Merker. Consciousness without a cerebral cortex: A challenge for neuroscience and medicine.
Behavioral and brain sciences, 30(1):63–81, 2007.
Isabel Briggs Myers. Myers-Briggs type indicator: MBTI.
Lionel Naccache. Why and how access consciousness can account for phenomenal consciousness.
Philosophical Transactions of the Royal Society B: Biological Sciences, 373(1755):20170357,
2018.
OpenAI. Gpt-4 technical report, 2023.
Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong
Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. Training language models to follow
instructions with human feedback. Advances in Neural Information Processing Systems, 35:
27730–27744, 2022.
Antoine Pasquali, Bert Timmermans, and Axel Cleeremans. Know thyself: Metacognitive networks
and measures of consciousness. Cognition, 117(2):182–190, 2010.
Roger Penrose. The emperor’s new mind. RSA Journal, 139(5420):506–514, 1991.
Roger Penrose. Shadows of the Mind, volume 4. Oxford University Press Oxford, 1994.
Navindra Persaud, Peter McLeod, and Alan Cowey. Post-decision wagering objectively measures
awareness. Nature neuroscience, 10(2):257–261, 2007.
Vincent Picciuto. Addressing higher-order misrepresentation with quotational thought. Journal of
Consciousness Studies, 18(3-4):109–136, 2011.
Hilary Putnam et al. Reason, truth and history, volume 3. Cambridge University Press, 1981.
Haocong Rao, Cyril Leung, and Chunyan Miao. Can chatgpt assess human personalities? a general
evaluation framework. arXiv preprint arXiv:2303.01248, 2023.
Maurice Rappaport. The disability rating and coma/near-coma scales in evaluating severe head injury.
Neuropsychological rehabilitation, 15(3-4):442–453, 2005.
James A Reggia. The rise of machine consciousness: Studying consciousness with computational
models. Neural Networks, 44:112–131, 2013.
Philip Robbins. Consciousness and the social mind. Cognitive Systems Research, 9(1-2):15–23,
2008.
David Rosenthal. Thinking that one thinks. Language and Thought, pages 259–287, 1993.
David Rosenthal. Consciousness and mind. Clarendon Press, 2005.
David Rosenthal. Higher-order awareness, misrepresentation and function. Philosophical Transactions of the Royal Society B: Biological Sciences, 367(1594):1424–1438, 2012.
David M Rosenthal. Two concepts of consciousness. Philosophical Studies: An International Journal
for Philosophy in the Analytic Tradition, 49(3):329–359, 1986.
David M Rosenthal. Varieties of higher-order theory. Higher-order theories of consciousness, pages
17–44, 2004.
48
David M Rosenthal. Higher-order theories of consciousness. 2009.
David M Rosenthal et al. The nature of mind. Oxford University Press New York, 1991.
Carl Rosow and Paul J Manberg. Bispectral index monitoring. Anesthesiology Clinics of North
America, 19(4):947–966, 2001.
Wesley Sauret and William G Lycan. Attention and internal monitoring: a farewell to hop. Analysis,
74(3):363–370, 2014.
Dennis JLG Schutter and Jack van Honk. Extending the global workspace theory to emotion:
Phenomenality without access. Consciousness and Cognition, 13(3):539–549, 2004.
Terrence J Sejnowski. Large language models and the reverse turing test. Neural computation, 35(3):
309–342, 2023.
Anil Seth. The strength of weak artificial consciousness. International Journal of Machine Consciousness, 1(01):71–82, 2009.
Anil K Seth, Zoltán Dienes, Axel Cleeremans, Morten Overgaard, and Luiz Pessoa. Measuring
consciousness: relating behavioural and neurophysiological approaches. Trends in cognitive
sciences, 12(8):314–321, 2008.
Claude E Shannon. A mathematical theory of communication. The Bell system technical journal, 27
(3):379–423, 1948.
Noah Shinn, Beck Labash, and Ashwin Gopinath. Reflexion: an autonomous agent with dynamic
memory and self-reflection. arXiv preprint arXiv:2303.11366, 2023.
Henry P Stapp. The importance of quantum decoherence in brain processes. arXiv preprint quantph/0010029, 2000.
George L Sternbach. The glasgow coma scale. The Journal of emergency medicine, 19(1):67–71,
2000.
Max Tegmark. Importance of quantum decoherence in brain processes. Physical review E, 61(4):
4194, 2000.
Max Tegmark. Consciousness as a state of matter. Chaos, Solitons & Fractals, 76:238–270, 2015.
Max Tegmark. Life 3.0: Being human in the age of artificial intelligence. Vintage, 2018.
Romal Thoppilan, Daniel De Freitas, Jamie Hall, Noam Shazeer, Apoorv Kulshreshtha, Heng-Tze
Cheng, Alicia Jin, Taylor Bos, Leslie Baker, Yu Du, et al. Lamda: Language models for dialog
applications. arXiv preprint arXiv:2201.08239, 2022.
Bert Timmermans, Leonhard Schilbach, Antoine Pasquali, and Axel Cleeremans. Higher order
thoughts in action: consciousness as an unconscious re-description process. Philosophical Transactions of the Royal Society B: Biological Sciences, 367(1594):1412–1423, 2012.
Giulio Tononi. An information integration theory of consciousness. BMC neuroscience, 5(1):1–22,
2004.
Giulio Tononi and Christof Koch. Consciousness: here, there and everywhere? Philosophical
Transactions of the Royal Society B: Biological Sciences, 370(1668):20140167, 2015.
Giulio Tononi and Olaf Sporns. Measuring information integration. BMC neuroscience, 4:1–20,
2003.
Giulio Tononi, Melanie Boly, Marcello Massimini, and Christof Koch. Integrated information theory:
from consciousness to its physical substrate. Nature Reviews Neuroscience, 17(7):450–461, 2016.
Paul D Trapnell and Jennifer D Campbell. Private self-consciousness and the five-factor model
of personality: distinguishing rumination from reflection. Journal of personality and social
psychology, 76(2):284, 1999.
49
Stefan Treue and Julio C Martinez Trujillo. Feature-based attention influences motion processing
gain in macaque visual cortex. Nature, 399(6736):575–579, 1999.
Alan M Turing. Computing machinery and intelligence. In Parsing the turing test, pages 23–65.
Springer, 2009.
Robert Van Gulick. Higher-order global states (hogs): an alternative higher-order model. Higher-order
theories of consciousness, 2004:67–93, 2004.
Rufin VanRullen and Ryota Kanai. Deep learning and the global workspace theory. Trends in
Neurosciences, 44(9):692–704, 2021.
Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz
Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing
systems, 30, 2017.
H Kenneth Walker, W Dallas Hall, and J Willis Hurst. Clinical methods: the history, physical, and
laboratory examinations. 1990.
Daniel M Wegner. Précis of the illusion of conscious will. Behavioral and Brain Sciences, 27(5):
649–659, 2004.
Lilian Weng. The transformer family version 2.0. lilianweng.github.io, Jan 2023. URL https:
//lilianweng.github.io/posts/2023-01-27-the-transformer-family-v2/.
M Wieser, L Buetler, A Koenig, and R Riener. Quantitative description of the state of awareness of
patients in vegetative and minimally conscious state. In 2010 Annual International Conference of
the IEEE Engineering in Medicine and Biology, pages 5533–5536. IEEE, 2010.
Eelco FM Wijdicks, William R Bamlet, Boby V Maramattom, Edward M Manno, and Robyn L
McClelland. Validation of a new coma scale: the four score. Annals of Neurology: Official Journal
of the American Neurological Association and the Child Neurology Society, 58(4):585–593, 2005.
50 |
Journal of Consciousness Exploration & Research| October 2012 | Volume 3 | Issue 9 | pp. 1032-1039
Deshpande, P. B., Science of Compassion
1032
Article
Science of Compassion
Pradeep B. Deshpande*
*
Professor Emeritus of Chemical Engineering, University of Louisville, and President, Six Sigma and
advanced Controls, Inc. P.O. Box 22664, Louisville, KY 40252-0664.
Abstract
This paper presents a scientific pathway for compassion. The framework presented is for
individual, organizational, national, and global transformation and peace. With the framework,
an individual may progress to any extent possible for a human being all the way to
enlightenment. However, there may be an upper limit to how much progress is possible for
specific nations or on a global scale but diligent pursuit of the ideas and concepts should lead to
more compassionate nations and a more peaceful world.
Keywords: Compassion, happiness, scientific investigation, global peace.
If you want others to be to be happy, practice compassion.
If you want to be happy, practice compassion.
His Holiness the Dalai Lama
INTRODUCTION
The Honorable Mayor of Metro Louisville has embraced a vision to make the city most
compassionate in America. The scientific questions that this paper addresses are why this is
important, how it can be accomplished, and what the benefits of a successful effort would be.
We the human inhabitants of the planet Earth can be surmised to have three components of the
mindset: (1) S – truthfulness, honesty, equanimity, steadfastness, etc., (2) R – attachment, ego,
bravery, greed, ambition, desire to live, etc., and (3) T – lying cheating, causing injury in words
or deeds, sleep, etc. On the S, R, T scale of human consciousness, the revered ones are at the top
with the highest level of S possible for a human being with the appropriate amount of R and
minimum amount of T necessary for life while the wicked ones are at the bottom and the rest of
us in between. Thus, to rise on the scale of human consciousness means to raise S while
controlling R and minimizing T (Deshpande, Ref. 1). Now, positive emotions such as
compassion, unconditioned love, kindness, and empathy strongly correlate with the S component
while negative emotions such as anger, hatred, hubris, arrogance, hostility, etc., strongly
correlate with the excessive R and T components. Therefore, to rise on the scale of human
consciousness is also equivalent to becoming more compassionate.
*
Correspondence: Prof. Pradeep B. Deshpande, Six Sigma & advanced Controls, Inc. P.O. Box 22664, Louisville,
KY 40252-0664, http://www.sixsigmaquality.com E-mail: pradeep@sixsigmaquality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1033
SCIENTIFIC FRAMEWORK
A scientific action plan of progress for becoming more compassionate requires a measurable
outcome. Scientists have discovered in recent years that positive emotions characteristic of the S
component result in ordered, coherent heart wave patterns seen in the lower portion in Figure 1
while negative emotions charatectirstic of excessive R and T components lead to random, jerky
heart wave patterns as seen in the top portion of this figure. Thus, the quest to enhance
compassion may be thought of, in part, as an effort to achieve life-enhancing heart wave patterns.
Figure 1. Heart Rate Variability Patterns under Positive and Negative Emotions
(Source: Science of the Heart, Ref. 2)
It is possible to cite three pathways to achieve the desired objective.
I. The first pathway for cultivating positive emotions – compassion has two components, a
conscious approach and a process whose side-effect is a rise in the S component and
compassion. The first component involves the mind in the absence of external events while
the second component involves the mind in the presence of external events.
Conscious approach. Even in the absence of external events, the mind produces thoughts
which lead to emotions which in turn produce chemicals and hormones. Positive emotions
promote life-supporting chemicals and hormones such as growth hormones, while negative
emotions lead to life-degrading ones such as elevated levels of Cortisol. The biblical wisdom,
“As you sow, so you reap” has real practical significance. To progress with this approach, it
is necessary to monitor one’s actions literally on a daily basis to regulate and hopefully raise
S while controlling R and lowering T. Effort with this approach is warranted even if progress
possible is modest.
Process whose side-effect is a rise in positive emotions. This concept requires an
understanding of the connection between emotions and external events. External events too
can give rise to emotions, just as thoughts can in the absence of external events. A story has it
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1034
that The Buddha and some of his disciples were wandering in the woods one day when they
saw that an elephant was charging at them. Upon seeing the elephant, the disciples fled but
The Buddha just stayed and merely raised his hand as though in blessing and the elephant
stopped in his track. So, what could have happened here? In the case of the disciples, the
external event was the sight of the elephant, the perception was threat, the emotion was fear,
and the action was to flee. The Buddha on the other hand only had positive emotions which
were instantly conveyed to the elephant and the elephant stopped sensing compassion,
realizing that they meant no harm.
This story could be viewed as allegorical, metaphorical, or factual. To prove that it is factual
requires scientific evidence for two things: (1) That it is theoretically possible for positive
emotions to travel from human consciousness to the consciousness of nonhuman specie, and
(2) That the signal travels sufficiently fast; positive emotions must reach the elephant’s
consciousness before the latter gets too close. Scientists at the Institute for HeartMath have
reported (McCraty, Ref. 3) the results of experiments with animals (dog, horse) which are
supportive of the hypothesis of emotions traveling between a human and an animal. For
example the data in Figure 2 were obtained using ambulatory ECG (Holter) recorders fitted
on a boy named Josh and his pet dog Mabel. When Josh entered the room where Mabel was
waiting and consciously felt feelings of love and care towards his pet, his heart rhythms
became more coherent and this change appeared to have influenced Mabel’s heart rhythms,
which then also became more coherent. When Josh left the room, Mabel’s heart rhythms
became much more chaotic and incoherent.
Figure 2. Heart Interactions of Josh and his Dog Mabel (Source: McCraty, Ref. 3)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1035
In the last few decades, western scientists have conducted experiments which show that
emotions can be conveyed instantaneously to human DNA over hundred of miles; they don’t
have to travel anywhere; As soon as they are created, they are at the destination. This is
consistent with an ancient Sutra on the Indra’s Net from Mahayana Buddhism. In the early
twentieth Century, physicists and biologist Jagdish Chandra Bose had hypothesized that even
plants respond to positive emotions. Since then, a number of scientists have carried out
experiments which are supportive of the possibility that human emotions can be understood
by nonhumans. There may be a good reason why the narrator of the story chose an elephant
and say not a tiger; elephants are vegetarian but tigers are not. If a tiger were charging at the
group, The Buddha would have been confronted by two unknowns; was the tiger starving or
did he simply perceive a threat?
Principal approaches whose side-effect is a rise in compassion are various forms of prayer
and meditation. If meditation is the taken up for scrutiny then, there must be measurable
evidence that it works. It may be recalled that Gautama was a prince growing up at which
time it may be speculated that he couldn’t have had the highest level of S and an appropriate
amount of R and a minimum amount of T required for life. If he did, no further effort
towards enlightenment would have been necessary. So, how did he go being a prince to
emerging as The Buddha (The Awakened One or Enlightened One)? The only thing he is
reported to have done differently from the ordinary folks of the day was meditation. There
are numerous other examples supportive of this hypothesis.
Scientists at the Institute for HeartMath at Boulder Creek, California have shown that there is
a magnetic field around the heart as depicted in Figure 3. Their experiments have shown that
human DNA responds to emotions. Positive emotions caused human DNA in a beaker some
distance away to uncoil while negative emotions produced the opposite effect. The lower
portion of the plot in Figure 1 is the result of heart-focused compassion practice.
Figure 3. Wireframe Model of the Magnetic Field around the Heart (Source:
Institute for HeartMath, Ref. 4)
In a related work, Drs. Richard Davidson and Matthieu Ricard and associates have studied
the effects of positive and negative emotions on brainwaves. They presented Functional MRI
results in the form of a graph shown in Figure 4 which plot the frequency of occurrence vs.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1036
brainwave frequency in dimensionless units for 150 subjects. They found that positive
emotions activated the left prefrontal cortex leading to the data to the left of the mean while
negative emotions activated the right prefrontal cortex giving the data to the right of the
mean. The data point at z = -0.45 shown for an unidentified experienced meditator was four
standard deviations to the left of the mean, far beyond that for any of the 150 subjects in the
investigation. Some of these results were published in Lutz, et al., (Ref. 6). The jerky heart
wave forms in Figure 1 likely correspond to the data to the right of the mean while regular,
coherent heart wave patterns correspond to the data to the left of the mean.
Figure 4. Effect of Emotions on Brainwaves (Source: Ref. 5)
A group activity has been shown to produce a more pronounced effect than an individual
practicing alone. By way of corroborative evidence, the Late Lewis Thomas, (MD, Harvard)
reported in his book The Lives of a Cell (Ref. 7) that a single termite with 50,000 neurons in
its brain could hardly be expected to do anything much less think. But when they are in a
colony of tens of thousands of termites, however, they succeed in building structures having
beautiful arches and symmetrical columns. In another example, the Global Consciousness
Project directed by Princeton Physicist Dr. Roger D. Nelson (Ref. 8) found meaningful and
statistically significant patterns in the random data from a network of 100 random number
generators located in several countries when man-made or natural disasters occurred. For
example, Figure 5 pertains to the data at the time of 9/11 attacks. Here, the RNG data
remained nonrandom throughout the event. Even more interestingly, the collective human
consciousness appeared to have sensed imminent tragedy a few hours before the attacks!
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1037
Figure 5. Human Consciousness, Random Number Generators, and
Catastrophic Events (Ref. 8)
There is evidence too that the benefits of group activity extend far beyond the meditators
physically present. In what has come to be known as the Maharishi Effect, The Late
Maharishi Mahesh Yogi suggested that the number of meditators required for world peace
equals 1% of the population. For a city of the size of Metro Louisville, the required number
is 100. In the eighties, scientists demonstrated the concept with a project called The
International Peace Project in the Middle East under the auspices of which 65 to 241 recruits
in the Middle East meditated in the morning/afternoon for thirteen days. The dependent
variables tracked were such factors as crime, auto accidents, war intensity and war deaths
(Alexander, et al., Ref. 9). For sustained benefits, it would appear reasonable to suggest that
these efforts have to be continued indefinitely.
II. Breath Control. The second pathway to enhancing compassion is the control of breath. Our
bodies have three subsystems: (1) External systems – spine, joints, and muscles, (2) Internal
organs and systems - sinuses and nasal systems all the way to GI and urinary tracts, and (3)
Mind. For overall good health and wellbeing, it is necessary for all three subsystems to
function well. Patanjali (~500 B.C.) (Swami Vivekananda, Ref. 10) pioneered the eight-fold
Yoga process for all three subsystems. A Wall Street Journal article (Ref. 11) found a
surprisingly high level of interest in Yoga a hundred years after Swami Vivekananda
introduced it to America. The component of Yoga that targets internal organs and systems is
Pranayam which involves ingenious manipulation of breath. Jerky heart wave forms in the
top portion of Figure 1 and irregular breathing appear to be intricately related. When done
correctly and diligently, Pranayam exercises regularize breathing, increase the lung capacity
as evidenced by deeper and fuller breaths so the blood returning to the lungs encounters an
Oxygen-richer environment. As the heart pumps this Oxygen-richer blood to all the cells in
the body, the nuclei of the cells are enriched with higher Oxygen content and the cells get
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1038
healthier as does the body. Benefits of Pranayam include freedom from stress and variety of
ailments. There is a meditative aspect to the mechanics of how these exercises are done
which is supportive of coherent heart wave patterns. It is estimated that diligent practice of
Pranayam would easily save 10% of the US healthcare costs which in current terms translate
into $250 billion annually. The ancient Eastern counsel, “Eat right, breathe right, think right,
feel right, and you will be happy” appears to have merit.
III. The third pathway for enhancing compassion and perhaps the hardest to grasp for the rational
mind, is food. Yogis characterize foods as Positive Pranic, Negative Pranic, and Neutral.
Positive Pranic foods are purported to promote the S component and therefore positive
emotions while negative Pranic foods promote the R component, and Neutral foods promote
the T component; Negative Pranic and Neutral foods are said to promote negative emotions.
A number of recipes primarily focusing on Positive Pranic Foods may be found in “A Taste
of Isha” (Ref. 12). Yogis are said to prefer foods that are primarily Positive Pranic. The
author attended a four-day Yoga program in California some years ago. There were forty one
participants in the program; thirty six Americans and five Indian-Americans. During the
entire program, the group had meals that were primarily Positive Pranic. By the last day, the
influence of Positive Pranic foods on positive emotions of the entire group was unmistakable
although this may not have been the only contributing factor. The author has since studied
numerous individuals with such dietary habits and the correlation of Positive Pranic Foods to
Positive emotions appears to be very strong.
For ages, compassion has been recognized as an inner condition of happiness which is always
subject to the influence of the outer conditions. Changes in outer conditions are a part and parcel
of life but as the level of consciousness rises, the negative impact of the outer conditions on the
inner condition becomes less and less (Matthieu Ricard, Ref. 5). In his Google-Tech talk,
Everyday Compassion at Google, Chade-Ming Tan (Ref. 13) makes a case for how compassion
is in the business interest of companies and that compassion can make good leaders and good
organizations great.
The ancient wisdom of which compassion is an essential outcome is for the excellence of the
internal. It is an ancient and precious gift to humanity. It took the author over four decades to
scrutinize and scientifically decipher it and it would not have been possible without six sigma
principles and chemical engineering training. It is one of two components for emerging as one’s
best. The other component is excellence of the external, from wake up time to bedtime, including
all that is done at work. The framework to achieve the excellence in all external activities is six
sigma (Deshpande, Ref. 14). Embracing and diligently pursuing both allows us to emerge as our
best. Ancient wisdom reveals it; incarnations, The Enlightened One, Son of God, and Prophets
teach it, and modern science corroborates it. The only obstacle to progress is us!
Acknowledgment: The author thanks Dr. Rollin McCraty, Director of Research at the Institute for
HeartMath for the explanation of the electromagnetic field around the heart and for the figures cited in the
paper. The author thanks Dr. Rajiv Shelar a Surgeon in Pune, India for narrating the story of The Buddha
and the elephant.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2012 | Vol. 3 | Issue 9 | pp. 1-7
Deshpande, P. B., Science of Compassion
1039
References
[1]
[2]
[3]
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13]
[14]
P. B. Deshpande, A Small Step for Man: Zero to Infinity with Six Sigma, Six Sigma and Advanced
Controls, Inc., 2008.
Science of the Heart: Exploring the role of the heart in human performance,
(http://www.heartmath.org/research/science-of-the-heart/entrainment-coherence-autonomicbalance.html).
Rollin McCraty, The Energetic Heart – Bioelectromagnetic Interactions within and Between
People, Institute for HeartMath, Boulder Creek, CA 95006.
Rollin McCraty, Science of the Heart, Institute for HeartMath, Boulder Creek, CA 95006 You
Tube Video (http://www.youtube.com/watch?v=CMQipX-hIDs).
Matthieu Ricard, Habits of Happiness, http://www.youtube.com/watch?v=vbLEf4HR74E Upload
April 15, 2008.
Antoine, Lutz, Lawrence L. Greischar, Nancy B. Rawlings, Matthieu Ricard, and Richard J.
Davidson, Long-term meditators self-induce high-amplitude gamma synchrony during mental
practice, Proceedings of the National Science Academy of the United States, 101, 46, November
16, 2004.
Lewis Thomas, The Lives of a Cell, Penguin Books, 1974.
Roger D. Nelson, Global Consciousness Project, Meaningful Patterns in Random Data, Princeton
Plasma Physics Laboratory Colloquium, October 11, 2006 (http://noosphere.princeton.edu).
Charles, A. Alexander, et al., Journal of Conflict Resolution, 32, 4, December 1988.
Swami Vivekananda, Raja Yoga: Conquering the Internal Nature, Trio Press, Kolkata, 2006.
A. L. Bardach, What did J. D. Salinger, Leo Tolstoy, and Sarah Bernhardt have in common: The
surprising and continuing influence of Swami Vivekananda, The Wall Street Journal, 30 March
2012.
A Taste of Isha, Recipes for the Pranic Lifestyle, Isha foundation, McMinnville, TN.
Chade-Ming Tan, Everyday Compassion at Google, Inc.,
(http://www.ted.com/talks/lang/en/chade_meng_tan_everyday_compassion_at_google.html
Pradeep B. Deshpande, Six Sigma for Karma Capitalism, Six Sigma and Advanced Controls, Inc.,
Louisville, KY 2011.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
194
Research Essay
Interactionism Read Anew:
A Proposal Concerning Phenomenal Judgments
Einar L. Halvorsen*
ABSTRACT
From a classical Cartesian perspective, interactionism implies the transfer of thoughts and
feelings from a non-physical phenomenal consciousness to the physical brain. Thereby,
phenomenal consciousness is thought to control the physical body somehow like a marionette
hanging by strings of non-physical thought. Differing from this depiction, a basic premise of the
current interactionist hypothesis is that the non-physical phenomenal consciousness reflexively
effects accentuation of thoughts, feelings and sensory experiences which already exist as
physical brain processes. In this essay, the mentioned interactionist hypothesis is presented and
central philosophical problems which pertain to it are discussed. Conclusively, the hypothesis
may withstand the initial scrutiny and is thereby rendered coherent. Nonetheless, the feasibility
of interactionism is not thereby significantly influenced. That would require a much more
extensive treatment of the feasibility of the current hypothesis as well as of coherent solutions to
numerous other problems pertaining to interactionism.
Key Words: interactionism, phenomenal judgment, phenomenal consciousness, physical brain.
Introduction
Like Michael Tye and others (Tye, p. 1), I will refer to phenomenal consciousness as “Pconsciousness”. The term “P-consciousness” will here provide for an intently undefined
meaning, as justifiable in light of Ned Block’s notion that the meaning of that term is lingually
indefinable (Tye, p. 1). Tye, freely re-formulated, sees P-consciousness as a capacity to possess a
phenomenal side to experiences (Tye, p. 144-5). If Block is right, however, the phrase
“phenomenal side to experiences”, if understood as the indefinable “P-side”, makes that
description circular.
The assumption of the lingual indefinability of P-consciousness carries implications also for an
interactionist perspective. While the physical world constitutes one pole of a purported
interactionist dualism, the nature of the other, non-physical pole will remain unknown or a mere
object of beliefs. Beyond the notion that P-consciousness is intimately linked to experience,
furthermore, a consensual nature of such beliefs can only be assumed.
Interactionism, the general theory discussed in this essay, is the idea that a non-physical Pconsciousness causally interacts with the physical brain (Chalmers, 2010, p. 126). Given that the
doctrine of interactionism is correct, violation of the doctrine of causal closure of the physical
*Correspondence: Einar L. Halvorsen, Independent Researcher, Germany. Email: EinarLautenHalvorsen@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
195
world (Stoljar, p. 220-2), including the quantum mechanical version of that doctrine (Papineau &
Selina, p. 74-5), is necessary.
Stewart Goetz convincingly argues that no theoretical hindrance exists which makes
scientifically incoherent the notion that causal closure may be violated (Goetz, in Baker & Goetz,
p. 104-16). Robin Collins, furthermore, explicates that it is not scientifically necessitated that
violation of causal closure must imply violation of energy conservation (Collins, in Baker &
Goetz, p. 124-33).
Even if the doctrine of causal closure could coherently be violated, however, another problem is
that expressed by the question of how quantum level interactionist influences may amount to
neuro-functional changes. This would be necessary should interactionism make a relevant
difference (Chalmers, 2010, 126-7n). Sir John C. Eccles early described the neuronal processes
which would have to be influenced (Popper & Eccles, p. 232).
A multitude of electro-chemical variables causally co-determine the firing of “action potentials”,
the single wave-like signals of invariable amplitude which “shoot” through single neurons
(Klinke & Silbernagl, p. 51-77). The challenge, if wishing to rule out interactionism, is to prove
each such electro-chemical variable as fully determined by reductive processes. David Chalmers
suggests that scientific understanding of these matters is still incomplete (Chalmers, 2010, p.
126-7n).
In order that an interactionist solution to the problem of phenomenal judgements may be correct,
a necessary premise is the coherence of the notion that all further problems with interactionism
may be solved. Only two further problems, however, which have direct relevance to the problem
of phenomenal judgements as viewed from an interactionist perspective, will here be granted
short preliminary treatments.
Functionality and causality
A well known doctrine is that P-consciousness is functionally indefinable (Chalmers, 1996, p.
46-7). A problem is thus whether a non-physical P-consciousness may be the source of
functional phenomena within the physical brain. Chalmers argues that if any interactionist
influence would exist, that would require non-physical, yet functional variables; “psychons”
(Chalmers, 1996, p. 156-8), as indeed proposed within Eccles’ interactionist perspective (Eccles,
p. 87-8).
Thereby, however, the problem is merely displaced from the physical world to a non-physical
sphere. The next question becomes whether the functionally indefinable P-consciousness can be
the source of the psychons’ functioning. From an interactionist perspective, the challenge is to
explain how P-consciousness generally can be the source of functional phenomena without itself
being functionally definable.
As initial analogy, P-consciousness may be compared to an invariant light source. This light
could be reflected in the shattered mirror surface of a parabolic sphere (here an analogy to a
brain). Those mirror shards retaining an “angle” similar to that of an unbroken parabolic mirror
will have surfaces being the most saturated with the light being reflected in them. Other shards,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
196
which surfaces have become more or less parallel to the light beams, will see their surfaces less
saturated with light.
While the light itself here symbolizes P-consciousness, the optimal saturation of light on shard
surfaces symbolizes the interactionist influence upon brain segments. The saturation of light on
shards’ surfaces, furthermore, will be fully determined by the “angle” of each shard, not by
variances or differentiations within the light source. Hence, any potential changes to the
interactionist influence, although change is not represented by the analogy, appear definable by
the functional processes of the physical brain itself.
All analogies are imperfect. An imperfection with the present one is that even light emanating
from an invariant source is functionally definable as waves of electromagnetic energy. The
following account is lacking regarding the structure of what argument it constitutes from a
scientific perspective. My intention, however, is merely to draw attention to an apparent
conceivability of a solution to the problem.
According to the theory of relativity, an implication of length contractions and time dilations
occurring by motion (Sartory, p. 185-200), is that the spatio-temporal universe appears as lacking
actual extension if seen from the “perspective” of light (Haisch, p. 95-7). That perspective is
principally impossible to acquire through scientific observation, since no observing, physical
object may ever behave like a photon of light (Sartory, p. 210).
From quantum physics, it is known that the spatio-temporal location of single photons may be
indefinable thanks to so called “superpositions” (Halvorson, in Baker & Goetz p. 142-6).
Without manifest location, furthermore, there is no manifestation at all. When photons are
localizable, distances between them appear, through so called “entanglement”, as causing no
hindrance for their instantaneous “contact” (Halvorson, in Baker & Goetz p. 146-9).
The latter notion potentially even mirrors relativity theory, as also there, it is as if for photons,
space and time lacks reality-defining power. Lee Smolin (Smolin, p. 210) predicted that the
theory of relativity may be coherent with quantum physical theory only if one assumes that the
universe exists according to a holographic principle (Smolin, p. 169-78).
What at any rate appears indicated is that some “factors” of reality exist beyond spatio-temporal
parameters. Hence, the idea that P-consciousness could exist in or as some spatio-temporally
indefinable state is coherent. P-consciousness could then potentially affect various brain areas
non-functionally.
Given that all functionality is definable within spatio-temporal parameters, purported “psychons”
could apparently exist only within a non-physical reality having spatio-temporal characteristics.
Curiously, however, in light of a general solution to how P-consciousness may affect functional
phenomena, even the idea of psychons becomes coherent.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
197
What can be assumed transferred to the brain?
By interactionism, one may oft imagine that the non-physical P-consciousness “has” thoughts
and feelings which get transferred to the brain. That would require that normal human experience
can take place independently of the brain. As well known, however, if a part of the brain is
destroyed, the psychological processes which rely on the functions of the damaged brain areas
are disrupted. Consequently, I take as premise concerning normal human experience, that all
experiential objects; everything we experience through sensing, thinking and feeling, are
represented as neuro-functional brain activity.
I assume the same also when specifying experience as phenomenal (P-) experience. From a first
person perspective, arguably, no phenomenal character or feature of experience seem barred
from becoming motive of directed actions or verbalizations which obviously depend on neurofunctional brain processes. From a third person perspective, it arguably appears as the only
rational alternative to trust first hand report and thus assume reports of blindness, example wise,
to also imply the phenomenal lack of vision.
In light of the above, a question is how interactionism may be coherent with neuro-science. As
an initial consideration, contrary to the position favoured by Tye (Tye, p. 155-82), it appears at
the very least coherent that brain processes may be subconsciously accessible to Pconsciousness. Not even subconscious experiences, however, will here be assumed to exist
independently of brain activity.
Rather, I will assume that a direct effect of an interactionist influence consists of an accentuation
of experiential objects already existing as patterns of neuro-functional brain activity. This better
fits Eccles’ belief concerning inter-neuronal communication, that interactionist influences only
may “modify the probability of vesicular emission of the activated synapses” (Eccles, p. 77).
Eccles nevertheless favoured the view, contrary to that here favoured, that interactionist
influences may transfer discrete experiences (Eccles, p. 71-2). Within both Eccles’ view and the
present, however, an interactionist influence should alter the frequency of action potentials in
those neurons which combined activity make up the overall pattern of neuro-functional brain
activity constituting the given experiential object.
An interactionist influence which direct effect is the accentuation of pre-existing brain activity
could be constituted by a non-intentional, reflex-like mechanism, like in the previous “mirror
analogy”. It would not have to constitute any consciously experienced effort. Further, it is also
not necessitated that the brain in a direct manner should experience any “transmission” which
mediates an interactionist influence. Rather, the influence could take place as a fully
subconscious process.
In the above, however, no mechanism has been identified whereby the subconscious
accentuation of experiential objects should be detectable as that by the brain. Another question is
then whether the brain may detect the presence of an interactionist influence through a different
mechanism. If neither alternative is possible, we may apparently not explain changes to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
198
phenomenal judgements as resulting from interactionist influences. The second alternative,
however, may in fact be coherent.
Required for this is a stable correlation between two known variables. Firstly, the amount of
absorbed neurotransmitter molecules sufficient for the release of one action potential within a
neuron (Klinke & Silbernagl, p. 65-6). Secondly, the amount of neurotransmitters absorbed from
the first neuron by an adjacent, neuro-functionally subsequent neuron as a consequence of the
action potential of the first neuron (Klinke & Silbernagl, p. 62-5).
We may assume that the suggested type of correlation, which may be uneven as long as stable,
can operate despite input to the receptor neuron from “third neurons”. What is decisive is the
amount of neurotransmitters absorbed from the “first neuron” as a consequence of one of its
action potentials. Even within networks of interconnected neurons, we may single out, at least as
a theoretical construct, the “linear” effect upon single neurons from other single neurons.
A potential reservation is the idea that synaptic transmission from third neurons could affect the
very function of the receptor neuron so that the amount of neurotransmitters absorbed from the
first neuron is thereby changed. However, such variance should be lawfully determined and thus
principally correctable by theoretical models constructed to take height for effects of third
neuron influences.
The suggested type of stable correlation will here be called “SLAN-correlation” (Stable Linear
Absorption of Neurotransmitters Correlation). Apart from potential effects of interactionist
influences, a mode of functioning according to which the SLAN-correlation exists may be
ingrained through evolution as a premise for healthy psychological functioning. That notion is
supported by the fact that its violation oft appears to be a mechanism of psychopathology
(Laruelle, in Hirsch & Weinberger, p. 365-81).
Hypothetically, we can here imagine that some neuro-functional sequences of neurons within the
brain are insulated against input from third neurons. Further, we may imagine excitatory synaptic
connections between the neurons of such sequences to occur according to a “chain principle”.
Further, inhibitory synaptic connections (Klinke & Silbernagl, 67) could operate only between
neurons separated by one or more intermediate neurons within the “excitatory chain”.
Such “insulated sequences” could potentially be activated exclusively in cases of SLANcorrelation violations. Each neuron of the sequence could be wired for transmissions through
both excitatory and inhibitory synapses according to the above outlined principles. The result, by
intact SLAN-correlation, could be lacking activation from the first inhibitory neuronal
interconnection onward. Inhibitory and excitatory influences might then cancel each other out, as
permitted by the principles of neuro-physiology (Klinke & Silbernagl, p. 68).
By violation of the SLAN-correlation, however, excitatory influence may outweigh inhibitory
influence in receptor cells receiving inhibitory input, thereby causing those cells’ activation. The
reason is that in those cases, any accentuating effect of SLAN-correlation violations may
accumulate over two or more excitatory synapses but over only one inhibitory synapse.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
199
The above account is theoretically rather than empirically based. Any effort, furthermore, to
formally demonstrate the theoretical coherence of the account exceeds the spatial confines of this
essay. Nonetheless, I hold the coherence of the account as a theoretical premise for the
arguments of this essay. For simplicity, activation of neuro-functional “insulated sequences”
which lay un-activated except by SLAN-correlation violations will be called “LINS-activation”
(Linear Insulated Neuro-functional Sequence Activation).
It is necessary, principally, to allow that LINS-activation may occur without an interactionist
influence (positive error) and that it may be absent despite of an interactionist influence (negative
error). More generally stated, it is not logically necessitated that SLAN-correlation violations,
which may potentially also occur without interactionist influences, should always lead to LINSactivation.
By schizophrenia, as example, deregulation of the amount of neurotransmitters within single
neurons leads to what is here termed SLAN-correlation violations (Laruelle, in Hirsch &
Weinberger, p. 365-81), albeit not extremely abrupt ones. To suggest that this would lead to
LINS-activation would appear unfounded, though the idea that it could occasionally do so is not
incoherent.
Fluctuations also of other, even subtler and more instantaneously effective electro-chemical
variables could cause so called SLAN-correlation violations, however (Eccles, p. 55-69). Those
variables, Eccles described, could conceivably be influenced by quantum level changes. Like
also Eccles, Chalmers sees the potential existence of quantum level interactionist influences as
coherent (Chalmers, 2010, 126-8).
For theoretical reasons, a statistically high degree of correlation between interactionist influences
and LINS-activations will here be assumed. Further, the occurrence of LINS-activations could
conceivably get registered by the reflectively conscious function of the physical brain as an
experiential phenomenon. Pertaining to phenomenal judgements, thus, the present interactionist
account could potentially explain how effects of an interactionist influence may become objects
of claims and cognitive beliefs.
Phenomenal Judgements & Interactionism
Phenomenal judgements refer to beliefs concerning the phenomenal character of experience
(Chalmers, 1996, p. 173-5). Such beliefs can be expressed by claims such as “colours are
mysterious” or “I am phenomenally conscious”, example wise. The problem of phenomenal
judgements is that of giving an explanation which accounts for the existence and the real nature
of such beliefs (Chalmers, 1996, p. 184-6).
The “hard problem” of consciousness, strictly interpreted, is that of explaining the existence of
P-consciousness (Chalmers, 2010, p. 3-6), not merely the existence of the belief that it exists.
The problem of “the explanatory gap”, next, is that of why there is an indescribable (strictly
assumed phenomenal) side to discrete experiences (Chalmers, p. 1996, p. 47). With strict
interpretations of both problems, the problem of the explanatory gap will be integral to the hard
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
200
problem, since all phenomenal experiences require a phenomenal subject (Strawson, in Freeman,
p. 189-91).
The hard problem is relevant to phenomenal judgements only insofar as actual phenomenality
constitutes a reason for beliefs about phenomenality. Eliminativists have denied the very
existence of P-consciousness (Macpherson, in Freeman, p. 75) and logically thus also that of a
strict “hard problem”. The problem of phenomenal judgements, then, can potentially (but must
not) be answered in concert with an answer to the hard problem.
If remaining “undogmatic” regarding the strictness of the hard problem, P-consciousness appears
potentially reducible to any reductively definable property which is capable of solving the
problem of phenomenal judgements. Tye holds that there may be a crucial difference between
“knowledge by description” and “knowledge by acquaintance”. Furthermore, that no part of the
former can be “part and parcel” of the latter (Tye, p. 139). Feelings that something is missing to
statements about phenomenal qualia, example wise, such as also implied by the explanatory gap,
could thus be explainable (Tye, p. 143).
For Tye, in the sense that he is no eliminativist, P-consciousness exists yet is a reductive
property, namely the brain state(s) for which knowledge by acquaintance takes place (Tye, p.
144-5). If his theoretical framework is correct, however, it serves his case of defending
physicalism only insofar as it defends any substance monist view, including variances of
property dualism (Chalmers, 1996, p. 124-5). Conceivably, it could explain why our cognitive
beliefs correspond to our phenomenal experience. If so, the hard problem would remain, even as
the problem of phenomenal judgements could appear solved.
The phenomenal judgement, however, that without the problem of phenomenal judgements, the
hard problem could still remain, relies on first person knowledge. If one chooses to take first
person perspectives upon consciousness seriously, it may arguably appear that there is something
to P-consciousness which is not only intellectually unexplainable (a mystery), but something
taking on an existential importance (a captivating mystery). The philosophical question of what
extent to which first person knowledge should be taken seriously (Taliaferro, in Baker & Goetz,
p. 26-40), however, will be left untouched at this point of the discussion.
An interpretation of Tye
For the sake of the subsequent discussions, a short interpretation of Tye’s perspective on
phenomenal judgements will here be presented. Since Tye sees phenomenal experience and
knowledge by acquaintance as synonymous, he understands the implicated explanatory gap
between knowledge by acquaintance and by description as that which is assumed integral to the
hard problem.
Because knowledge by acquaintance has no part or parcel of knowledge by description, Tye sees
the character of all phenomenal experiences as lingually indefinable, like also implied by the
well known philosophical notion of inverted qualia (Chalmers, 1996, p. 263-6). Contrary to
appearance, this is consistent with Tye’s conviction that P-consciousness is definable as a
property of the function of the physical brain.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
201
Using the colour “blue” as example, that colour is descriptively definable as a pattern of brain
activity. It appears that also the phenomenal character of blue experience is “fixed” by the neurofunctional characteristics of that very same brain state. This should be assumed even by property
dualism and interactionism, given that all normal human experience relies on brain activity.
Tye holds that even from a purely reductive, physicalist perspective, one may recognize (pick
out) “blue” as a colour separate from other colours regardless of whether one is aware of or able
to describe its neuro-functional characteristics (Tye, p. 139). Descriptions of the brain states
defining the experience, furthermore, may never convey the character of the experience by
acquaintance which allows the recognition. We see, thus, that although Tye sees P-consciousness
as neuro-functionally definable, he does not believe the same to concern the subjective character
of discrete phenomenal experiences.
The character of experiences by acquaintance represents “brute qualities”, identifiable only by
expressions such as “one of those” (Chalmers, 1996, p. 288-92). True, they can also be referred
to using some random token name, like “blue”. The meaning even of such consensual token
names, however, is flexible given the existence of inverted spectrum variances. Further
descriptive knowledge will also be unhelpful in specifying the phenomenal character of the
experience of a concepts’ referent. Example wise, telling someone that blue is the colour of the
sky is unhelpful given inverted spectrum variances.
A “concept”, Tye holds, is deferential (Tye, p. 40-1), meaning that it can be “possessed” even if
it is not fully understood (Tye, p. 63-74). A person thus possessing the concept BLUE without full
understanding could say about the colour indigo that it is blue. He or she could be colour blind
and experience all blue as indigo. Hence, it is not necessary to have undergone acquaintance with
the colour blue in order to possess the concept BLUE (Tye, p. 66).
There is, of course, a problem of defining “full understanding of concepts”. True, if a person is
either colour blind or experiencing inverted qualia, he or she must logically, at least within an
assumed physicalist reality, differ from other people as to how colours are represented in his or
her brain. Unless the presence of the relevant type of neuro-functional brain activity is
determined in each single case, however, it will remain a matter of mere presumption which
phenomenal character is consensually assigned to each colour concept.
The above underlines that, for all practical purposes, Tye presents a physicalist account which
respects the lingual indefinability of phenomenal qualia. What might still appear as a remaining
question is that of why people commonly fail to realize that the character of experiences by
acquaintance cannot be referred to by mere token names of brute qualities.
The principle of inverted qualia might rarely be spontaneously realized, yet this does not make it
a scientific mystery. The erroneous belief that concepts may refer to phenomenal qualia appears
to rely on a simple ego-centric error, namely the implicit, un-reflected belief that the own
subjective perspective is defining of interpersonal reality. In summary, thus, Tye’s perspective
allows the notion that people believe to refer to phenomenal qualia using “normal” concepts.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
202
A non-physicalist perspective
Initially in agreement with a non-interactionist, property dualistic perspective (Chalmers, 2010,
p. 243-4), I suggest that phenomenal experience is conveyed by the same patterns of brain
activity which define experiences in cases of knowledge by acquaintance. The phenomenal side
to the experience of any experiential object will thus be definable as the phenomenal experience
of the neuro-functional pattern of brain activity defining the experience of that experiential
object. We here end up with a double explanatory gap, one between knowledge by acquaintance
and knowledge by description, another between phenomenal and non-phenomenal experience of
that known by acquaintance.
A comment on the relationship between knowledge by acquaintance, knowledge by description
and the meaning of concepts will be useful for some of the following discussions. Using
Chalmers’ example, the concept WATER can have different secondary intensions (known a
posteriori) like “H2O” or, in a hypothetical other world; “XYZ” (Chalmers, 1996, p. 57). The
primary intensions could in both cases be “the dominant clear, drinkable liquid in the oceans and
lakes” (Chalmers, 1996, p. 57).
However, the brute qualities of water known by acquaintance must possess an a priori nature
even relative to its primary intension. Through its descriptive content, the latter is generalizing
and classifying of what may (but must not) be a priori “acquaintances” with the brute qualities of
the experience of water. Sainsbury and Tye similarly hold that the so called “two-dimensional
semantic” with primary and secondary intensions “fails to connect in a natural way to the notion
of a priori knowledge” (Sainsbury and Tye, p. 36).
From the perspective of an originalist theory of concepts, the acquiring (taking into possession)
of a concept can be separate from its origin, since concepts typically are shared (Sainsbury &
Tye, p. 40-4). Hence, the acquiring of concepts may oft reflect the adoption of a non-originating
use of the given concept, although one may later learn the concept’s originating use.
In such cases, acquiring cannot occur based on a priori experience by acquaintance of a nondescriptive referent phenomenon. Even if the originating use of a concept would have such a
priori experience as referent, through adopting a non-originating use, the acquiring will not
involve such experience. Oft, furthermore, even the originating use of a concept has merely
descriptive referents, like in the case of the concept QUARK (Sainsbury & Tye, p. 42-3).
Sometimes, however, the acquiring and the origin of a concept may be synonymous (Sainsbury
& Tye, p. 42). This allows the occurrence of discoveries that the given concept has the same
originating use as a pre-existing, shared concept (Tye, p. 39-40). It appears that exclusively in
such cases, the use of concepts can (but must not) reflect the a priori experience of the given
concepts’ non-descriptive referent phenomena by acquaintance.
Although here assumed that only experiences by acquaintance may have phenomenal sides, even
concepts which use involves merely descriptive referents constitute experiential objects existing
as patterns of brain activity. Consequently, also these should secondarily be possible to
experience a priori by acquaintance. Even in the case of a posteriori, descriptive knowledge,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
203
thus, it will be assumed that one may possess a phenomenal side to the experience of this
knowledge.
The core interactionist hypothesis
The non-physical P-consciousness is assumed only ideally to be the source of the previously
purported LINS-activation. Furthermore, no identified mechanism appears to allow the brain to
decide whether the SLAN-correlation is violated because of an interactionist influence or thanks
to some reductively definable cause. Indeed, SLAN-correlation violations may not be detectable
in any direct way from the perspective of the psyche.
I previously suggested that they may at least sometimes be detected indirectly through the
occurrence of the LINS-activation. Another consequence of SLAN-correlation violations could
logically be the abrupt, maybe intrusive appearance of thoughts, feelings or sensory impressions
to conscious awareness. As an extreme, but thereby obvious example, we could take
schizophrenic hallucinations (Laruelle, in Hirsch & Weinberger, p. 365).
As a potential consequence of all such experience, furthermore, the psyche may cumulatively
come to experience a lack of autonomy and integrity of the psyche. The apparent truth; that the
psyche does not “master” the physical brain, but can only function adaptively given a fine,
homeostasis-like balance within it (the SLAN-correlation) may hypothetically constitute an
existential threat to the psyche. It is a known doctrine within psycho-analytically oriented theory
that the psyche harbours “unrealistic needs”, such as the preservation of an illusion of solidity,
permanence and perfection, which Charles Hanly described as “a self-image that is distorted by
idealization” (Epstein, p. 24).
Analogically, a need of the psyche not to experience itself as at the mercy of potentially
merciless neuro-physiological processes of the physical brain is conceivable. An archaic and
subconscious psychic defence mechanism is “projective identification”, the ejection of internal
threats in order to perceive (identify) them as external ones (Ogden, p.144-6). Wilfred Bion held
that projective identification can account even for many bizarre psychotic experiences of
schizophrenics (Ogden, p. 146).
By schizophrenic psychoses, patients frequently claim to have thoughts that are not their own
(AMDP, p. 85-6). As above assumed, such “intrusive” experiences may cause a sense of the
psyche’s lacking autonomy or integrity and be experienced as threatening. Beside the mentioned
sense of thought insertion, projective identification may lead to delusions of alien influence
(AMDP, p. 86-7) and persecution (AMDP, p. 68-9). The latter could more directly account for
the projective identification of an experienced, internal threat.
Also a priori experience by acquaintance of the LINS-activation may, according to the same
principle as above outlined, be experienced as a threat to the autonomy and integrity of the
psyche. This, because LINS-activations, which is thought to exclusively follow SLANcorrelation violations, may be experienced as abrupt, intrusive presences felt by the psyche as
something uncontrollable.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
204
However, if a concept LINS-ACTIVATION would be rightly possessed, unlike typically the case
among other concepts having referents being experienced by acquaintance, it might represent a
phenomenon with no positively identifiable referent. That is, it may logically represent nothing
in the external physical world and might also constitute no discrete thought, feeling or illusory
sensory impression.
Hypothetically, the LINS-activation could be experienced as was it nothing at all, still
penetrantly present as that in an a priori fashion. Effectively, thus, the LINS-activation could be
unique as being impossible to positively describe a posteriori, bar in terms of the very brain
activity constituting its neuro-functional referent. Devoid of any positively identifiable,
descriptive referent phenomena, the only accessible referent of the LINS-activation might thus
be the very character of its experience by acquaintance.
Descriptively identifiable only as negations like “nothing” or “absence”, the LINS-activation
may find no physical referent at all. By projective identification, thus, the only accessible
referent of the LINS-activation, the character of its experience by acquaintance, might thanks to
lacking alternatives be falsely judged as transcendent and ontologically non-physical. Purely
hypothetically, illusory beliefs in transcendent qualities to experience may even be “welcomed”
by the psyche, since transcendence could serve the “unrealistic needs” of solidity, permanence
and perfection.
According to the current hypothesis, beliefs in a non-physical character to experiences would be
“falsely founded”, since the LINS-activation actually refers to a physical brain phenomenon.
Hence, the presumed, actually non-physical nature of P-consciousness would not be the direct
reason for beliefs about that very non-physical nature. Still, it could constitute an indirect reason
for it in the form of an interactionist influence.
Answer to some criticisms
A potential criticism of the above interactionist hypothesis can be expressed through the question
of how we justify the idea that phenomenal experience merely is present as the LINS-activation.
Answering this, it should once more be clarified that between phenomenal and non-phenomenal
experience, no different functionality in the brain is here assumed, like also not in cases of
property dualism.
Presumably, there is always a phenomenal side to experiences by acquaintance. The purported
LINS-activation entails, on the one hand, one single and separate phenomenal experience among
the multitude of other, phenomenal experiences. On the other hand, it may also constitute the
reason for convictions about a quality over and above everything physical to the experience of
any experiential object currently accentuated by an interactionist influence
One could still ask how, without adding any new experiential contents, the LINS-activation
alone may explain judgements about the entire range of phenomenal experiences. The answer is
that the LINS-activation is assumed to ideally occur because of an interactionist accentuation of
discrete experiences already present. The decisive factor regarding the character of each
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
205
phenomenal experience is then the pre-existing experience being accentuated by the
interactionist influence.
The above may still be further questioned. In light of the above accounts, it appears that people
should believe recognizing a reductively indefinable character to the experience of the LINSactivation rather than to that of the experiential object being accentuated. A confusion may be
comprehensible, however, because the LINS-activation and the accentuation of the present
experiential object presumably occur simultaneously and co-dependently upon an interactionist
influence.
Further and as previously mentioned, the LINS-activation may be thought of as being, in a sense,
“object-less”. That is, the only identifiable experiential “contents” could be those of the
experiential object being accentuated. Given the sum of those circumstances, a fallacy of
correlation and causality (Losee, p. 41-8) could conceivably occur. Hence, one might believe the
impression of a transcendent, non-physical quality to the character of any present experience (aphenomenally defined) to be caused by the presently accentuated experiential object rather than
by the LINS-activation.
Another question is that of whether the present interactionist account may explain why and how
the physical brain can believe in the existence of phenomenality to experience. After all, the
brain must produce the claims reflecting the beliefs about phenomenality. The flip side to the
same problem is the question of how P-consciousness may believe that functional brain states
refer to its own phenomenal experiences.
Even within an interactionist account of reality, however, we must assume that the physical brain
alone may know nothing about phenomenal (P-) experience. Like also according to a property
dualistic rationale (Chalmers, 1996, p. 124-5), the physical brain and P-consciousness could
mutually lack ways to “inform” the other that a discrepancy exists between an experience as
functionally definable and its phenomenal side. The discrepancy may simply not matter as long
as the neuro-functional determinants of the experience are identical.
Thus, even as one experiences the phenomenal side to an experiential object, one may be “blind”
to the fact that there is a difference between an experience as functionally definable and its
phenomenal side. This also implies “blindness” to any potential experience that there should be a
mystery to the notion that the character of phenomenal experience is reductively definable.
In the absence of any LINS-activation, thus, P-consciousness may experience the phenomenal
side to discrete experiences by acquaintance without accompanying beliefs that the character of
those experiences is transcending everything physically definable. The specific case of the LINSactivation, however, may constitute an exception. As previously outlined, the character of its
experience by acquaintance could hypothetically be experienced as transcendent and
ontologically non-physical.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
206
The explanatory power of the present hypothesis
An important question is whether an interactionist influence could result in beliefs differing from
those of a phenomenal zombie (Chalmers, 1996, p. 94-9) following “normal” knowledge by
acquaintance. In light of the difference between knowledge by acquaintance and by description,
zombies’ beliefs about a lingually indefinable character to experiences may take place without
interactionist influences. Exactly like Tye holds, this could appear to solve the problem of the
explanatory gap. This would also leave the present interactionist hypothesis stripped of any
unique explanatory power.
Rightly, the character of the experience by acquaintance of the colour blue is seen as
indescribable from Tye’s perspective. However, within any substance monist view, of which
physicalism and variances of property dualism are examples, a strong subjective conviction that
the indescribable character of blue experience is transcendent should not arise. As above
mentioned, P-consciousness would arguably be unable to detect any major mystery to the notion
that phenomenality should be reductively definable.
It was suggested, however, that the experience by acquaintance of the LINS-activation could
appear as having a non-physical character to it. Obviously, even without any purported LINSactivation one may form hypotheses (and incidentally even favour these) that the character of
experiences by acquaintance may best be explained as transcendent. This would then work
according to the principles of scientific hypotheses in general, which of nature are a posteriori,
matter-of-factly and affect-less.
Violations of the matter-of-factly and hypothetical nature of claims as expectable concerning a
posteriori descriptive notions could indicate the presence of the direct a priori experience of
some phenomenon. If, additionally, such “irrational convictions” would concern notions of
transcendent or ontologically non-physical aspects of experience, this would fit that which is
expectable within the current interactionist hypothesis.
As previously mentioned, both positive and negative errors might occur regarding the cooccurrence between an interactionist influence and LINS-activation. Thus, irrational convictions
must sometimes be granted to be “just” irrational. Given that errors are exceptional, however, the
current interactionist hypothesis generally favours the notion that first person knowledge may
have a central role when it comes to our judgements about the nature of consciousness.
A question is still why we should prefer the present interactionist hypothesis over new, more
complex forms of substance monism. In those alternative scenarios, the LINS-activation always
occurs by reductive means, still causing phenomenal judgements about the character of
phenomenal experience as being transcendent. Within a property dualistic scenario, as example,
one could imagine that beliefs about phenomenality would fully correspond to actual
phenomenality, yet the beliefs would not even indirectly be caused by that phenomenal reality.
However, the LINS-activation would then have to be seen as resulting from random deregulation
of the SLAN-correlation. This, furthermore, does not appear to be the principle according to
which our phenomenal judgements are produced. Example wise, we do not hear claims that the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
207
character of the experience of the colour blue some times and without predictability has a quality
transcending everything physically definable.
In summary, although a traditional property dualistic perspective may explain beliefs that one
refers to phenomenal experiences, it leaves the subject “blind” to the difference between
phenomenal experience and knowledge by acquaintance. Tye’s physicalism explains the same
beliefs without that dilemma, since it sees phenomenal experience and knowledge by
acquaintance as synonymous. Nonetheless, it seems that only an interactionist alternative may
account for the mystery of consciousness as expressed by the first person experience of the hard
problem.
The problem of lingual reference to P-consciousness
As evident by the fact that people try to express convictions about P-consciousness in language,
certain concepts must frequently be believed to refer to P-consciousness. All thus relevant
concepts, however, have reductively definable referents, existing independently of any purported
interactionist influence. A fitting example is exactly the concept PHENOMENAL CONSCIOUSNESS, here
understood as distinct from P-consciousness.
The word “phenomenal” is a term from philosophy, especially linked to 19th century philosopher
Edmund Husserl. It concerns the manner in which experiential objects (phenomena) “appear” to
consciousness (Fahey, online). The word “consciousness”, next, can be defined as a mode of
functionality which can be shared by the neuro-physiology of biological organisms and artificial
computing systems (Chalmers, 1996, p. 275).
Tye argues that a reductively definable mental state (or states) for which knowledge by
acquaintance takes place likely is the referent of P-consciousness (Tye, p. 144-5). I also judge it
as safe to infer that Tye, from his physicalist perspective, sees that (or those) state(s) as the
referent phenomenon of the concept PHENOMENAL CONSCIOUSNESS. For reasons of simplicity, such
(a) mental state(s) will here be referred to as “the mental state of acquaintance”. In that state, no
agency appears involved, only passively “receptive” experience.
Many concepts other than PHENOMENAL CONSCIOUSNESS could have the same, reductively definable
referent. Examples are concepts such as PURE BEING and SUBJECTIVITY. Another example is the
concept I, which is arguably also used with the belief that it refers to P-consciousness.
Accordingly, statements like “my brain registers colours, but only I see their qualia” may follow.
According to Mark Epstein (Epstein, p. 47-8), the “I” is a portion of the psychological ego.
Further, all psychological phenomena are functionally definable (Chalmers, 1996, p.46-7).
A question is whether the reductive referents of the two concepts PHENOMENAL CONSCIOUSNESS and I
could be reduced to one single, neuro-functional brain phenomenon. Given that the two concepts
may be believed to refer to the same phenomenon, we would thereby avert a theoretical problem.
Examples illustrate, however, that “the mental state of acquaintance” does not appear to be
synonymous with the reductive referents of the concept I.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
208
By many sleeping dream states or other states induced by drugs, hypnosis, meditation or
traumata, experience by acquaintance appears to take place without being “brought under” the
“I” (Howell, p. 19-20). The “I”, on the other hand, can apparently experience itself as an agent
behind actions (Epstein, p. 47-8). That violates the assumption that the mental state of
acquaintance is purely passive, without agency.
Hypothetically, the reductive referents of the concept I and “the mental state of acquaintance”
could nonetheless be intertwined phenomena. The “I” naturally appears to contain an “observerobserved duality” due to its self-reflective function. The observed part of the “I” may oft be its
agent-part (Epstein, p. 47-8), yet may apparently also be its very observing part. The “observed
observer” of each new second appears to require a “pure observer”. The self-reflective process of
the “I” may thus appear like a Russian Matryoshka doll with an endless amount of concentric
layers. David Chalmers made a humorous note of a similar point (Chalmers, 1996, p. 230).
Sainsbury and Tye hold that we use a specific “I-concept” (presumably the concept I) to think
about ourselves (Sainsbury & Tye, p. 144-5). Potentially, the observed part of the “I” (including
the observed observer) corresponds to the concept I, while the momentarily observing instance is
not part of it. Conceivably, the momentarily observing instance, when understood as detached
from the concept I, is synonymous with the mental state of acquaintance. Thus, the reductive
referent of both the concept PHENOMENAL CONSCIOUSNESS and the concept I could ultimately be
identical.
A non-physicalist perspective
Concerning P-consciousness as such, the situation appears by first glance to be more complex
than concerning a phenomenal character of discrete experiences such as those of sensory objects.
Regarding colours, as example, the phenomenal side to a colour as neuro-functionally definable
is “the colour as it is phenomenally experienced”. Similarly, it appears that the phenomenal side
to the mental state of acquaintance simply is “the mental state of acquaintance as phenomenally
experienced”. This cannot be thought of as being synonymous with P-consciousness. The same
goes for the “I”, since the “I” as phenomenally experienced is not the same as P-consciousness.
Still, the “I” and “the mental state of acquaintance” may display certain idiosyncratic properties
worthy of further exploration. Firstly, P-consciousness and the mental state of acquaintance may
conceivably “map onto” each other, meaning that experiential objects, features and qualities
available to P-consciousness could be exclusively and exhaustively those accessible by
acquaintance. This notion is also adaptable to Tye’s view that P-consciousness simply is what is
here called “the mental state of acquaintance” (Tye, p. 144-5). From a property dualistic
perspective, furthermore, the mental state of acquaintance could be experienced as a state within
which P-consciousness is solely present.
When it comes to the “I”, next, P-consciousness could, within the present interactionist account,
observe the observed portion of the “I” (including the observed observer) through the intimately
experienced lens of the momentarily observing instance. The momentarily observing instance
and the observed observer of the “I” could be experienced as synonymous (this will be further
outlined). Next, given that the momentarily observing instance is synonymous with the mental
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
209
state of acquaintance, the observed observer of the “I” could also be experienced as synonymous
with the mental state of acquaintance.
The mental state of acquaintance could thus possess properties which allow a phenomenal
illusion that it is synonymous with P-consciousness. We do not here talk about an illusion in the
form of a cognitive belief. Rather, as according to the previously described principles, the person
could simply be “blind” to the difference between phenomenal experience and experience by
acquaintance. Here, specifically, he or she would be blind to the difference between Pconsciousness as such and the mental state of acquaintance. If we accept a standard property
dualistic rationale, this could in fact appear to be the natural end point of the current hypothesis.
Scrutinizing the interactionist hypothesis
Hypothetically, the brain activity which constitute the reductive referents of “the mental state of
acquaintance” could become accentuated by an interactionist influence. This could cause LINSactivations in the same manner as assumed if, as example, the reductive referents of an
experiential object like “vision of the sky” would be accentuated.
Since all experiences must be intimately linked to the presence of an experiencing subject, the
interactionist accentuation of discrete experiential objects and of the mental state of acquaintance
could potentially always be two sides of the very same event. If so, all interactionist influence
could be thought to influence phenomenal judgements about both the present experiential objects
as well as P-consciousness. We may call that scenario “unitary accentuation of object and
subject”.
As previously suggested, the experience of the LINS-activation could give rise to the illusion
that there is something transcendent to the experience of that which is being accentuated.
Concerning discrete experiential objects, simultaneous and co-dependent a priori experiences of
LINS-activations and of experiential objects accentuated by an interactionist influence was
assumed. Further, that only the discrete experiential objects have positively identifiable referents,
so that LINS-activations are not sensed as independent experiential phenomena.
When trying to picture a similar rationale for cases of an interactionist accentuation of the mental
state of acquaintance, we encounter more difficulty. Tye thinks the “realization” that (a) mental
state(s) must exist which is “having” experiences by acquaintance (the mental state of
acquaintance) only takes place a posteriori (Tye, p. 144-5). If correct, we must here assume the
same to be the case also for P-consciousness.
Initially, Tye’s view fits the notion that the mental state of acquaintance may be phenomenally
felt as synonymous with P-consciousness. This, exactly because there is nothing about it which
can be experienced a priori. Rather, it would operate more like an intimate lens for Pconsciousness’ experience of other phenomena. However, by unitary accentuation of object and
subject, any phenomenal judgements resulting from confusion of that being accentuated and the
LINS-activation, would thus appear to concern discrete experiential objects to the exclusion of
concerning the mental state of acquaintance.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
210
By separate accentuation of object and subject, on the other hand, LINS-activation following
accentuation of the mental state of acquaintance would be experienced a priori without any a
priori experience of anything at all being accentuated. This could, by analogy, potentially explain
false possession of the concept PHENOMENAL CONSCIOUSNESS. That is, one could imagine that any
reference to the LINS-activation as “phenomenal consciousness” or as “the mental state of
acquaintance” would be more or less analogical to the naming of indigo as blue in the previous
example of colour blindness.
The latter account would imply, however, that since the person does not know the actual mental
state of acquaintance a priori, he or she would have no clear conception of what it really means.
This, furthermore, does not do justice to what was assumed previously in this essay. It was then
assumed that first person, a priori knowledge by acquaintance is both predominantly reliable and
decisive for understanding phenomenal judgements.
From a non-interactionist perspective, it appears feasible that the a posteriori realization that a
mental state of acquaintance exists is facilitated by awareness about the existence of discrete
experiences by acquaintance. This may largely explain temporal co-occurrence of experiences by
acquaintance and beliefs about a corresponding mental state having those experiences. It could
also explain how one may realize that that mental state is ontologically linked to the character of
experiences by acquaintance.
The challenge with the latter alternative is to explain how the insight about the mental state of
acquaintance may suffice for the formation and use of the concept I. A requirement must be that
the actual mental state of acquaintance, having the experiences by acquaintance which facilitate
the a posteriori insight about that same mental state, will experience the object of that insight as a
“solid” reference to itself.
It appears unclear, at best, whether the above is feasible, given that any a posteriori insight refers
to an abstract, merely inferred object. Next, I will loosely outline an account which, in the best
case, could aid both non-interactionist perspectives as well as interactionism past the above
identified problems. Specifically, I suggest that the mental state of acquaintance may be
experienced a priori, despite of Tye’s conviction to the contrary.
We may imagine the mental state of acquaintance as “emitting” neuronal signals in a manner
analogical to how light signals were emitted by P-consciousness within the previous “mirror
analogy”. As result of (non-interactionist) interaction with discrete experiential objects defined
as neuro-functional patterns of brain activity, those neuronal signals could be altered, thereby
coming to register and represent present experiential objects.
The mental state of acquaintance might have the capacity of possessing an underlying, intrinsic
focus. This focus must not be understood as a reflectively conscious experience. By mere
analogy to the visual mode of experience, the suggested focus might conceivably be compared to
a direct experience of the sum total of brightness as was light an independent experiential
phenomenon. That is, independently of the capacity of light, as medium, to define discrete
experiential objects through colours and shades.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
211
Since we talk about an intrinsic self-experience of the mental state of acquaintance, we must not
assume that P-consciousness experiences the mental state of acquaintance a priori. This would
have contradicted what was previously assumed. We must only assume that P-consciousness
may experience, like may also the mental state of acquaintance, the a priori self-experience of
the latter as some sort of brute quality.
A priori self-experience as here suggested should not be taken note of by the brain as something
mysterious. Thus, the present account is fully adaptable to substance monist views like
physicalism and versions of property dualism. Given interactionism, however, the neurofunctional manifestation of the a priori self-experience of the mental state of acquaintance may
get accentuated by an interactionist influence. Further, the purported general confusion between
any experiential object accentuated by an interactionist influence and the LINS-activation may
then lead to the experience that there is a transcendent quality to the mental state of
acquaintance. This, according to the exact same principles as outlined concerning discrete
experiential objects.
Lastly, an "object" experienced a priori, such as here the mental state of acquaintance, appears
sufficiently “solid” for the formation and use of the concept I. The reflective awareness about the
self-experience held by the mental state of acquaintance could bring the mental state of
acquaintance under observation and the concept I. Thereby, we might potentially also better
understand how the momentarily observing instance and the observed observer of the “I” may be
experienced as identical. Further, reflective awareness may logically only occur with a minimal
delay relative to any referent, a priori experience. Since the a priori experience of the mental
state of acquaintance may take place anew each second, we might thereby also understand the
mentioned “Matryoshka-doll effect”.
Conclusion
Initially in this essay, some problems were mentioned, the coherent solutions to which are
instrumental for the notion that discussions of interactionism are warranted at all from a
scientific perspective. The problems include those of causal closure of the physical universe,
neuro-functional manifestation of potentially quantum level interactionist influences and the
notion that causality requires functionality. Lastly, whether from a psychological perspective,
thoughts and feelings could coherently be assumed transferred from a non-physical sphere to the
physical brain.
In the central part of the essay, comparison was made to Michael Tye’s physicalist perspective. I
accepted Tye’s division between knowledge by description and knowledge by acquaintance and
that this represents an “explanatory gap”. Distinctly, I suggested the existence of a “double”
explanatory gap. I presumed a “phenomenal side” to all experience by acquaintance. This allows,
also from the perspective of a non-physicalist hypothesis, that all discrete phenomenal
experience is defined by physical brain processes. In isolation, this reflects a variance of a
property dualistic rationale.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
212
Because of theoretical complexity and space constraints, many aspects of the distinctly
interactionist parts of the essay’s hypothesis will remain treated exclusively in the main text.
What should be mentioned, however, is that this essay purports that interactionist influences
from P-consciousness upon the physical brain are reflex-like, content-less and subconscious. No
discrete experiential objects are assumed “transferred” to the brain from a pre-existing state
within a non-physical sphere. Importantly, however, the interactionist influence is still assumed
to effect a process through which a distinct neuro-functional consequence, the so called “LINSactivation”, may be experienced by the physical brain.
Two further features of the present hypothesis are worth emphasizing. It was assumed that
“irrational convictions” about any transcendent or non-physical character to phenomenal
experience may follow an interactionist influence. The present hypothesis necessitates the
allowance of error, so that irrational convictions sometimes may be “just” irrational.
Simultaneously, it accounts for the idea that the mentioned irrational convictions about
phenomenal experience typically may result from first person experience of the neuro-functional
consequence of the interactionist influence in the physical brain. Hence, the present hypothesis
grants a very significant, albeit not necessarily all-decisive role to first person knowledge when it
comes to explaining phenomenal judgements.
Lastly, the present hypothesis accounts not only for phenomenal judgements about the
phenomenal character of discrete experiential objects such as thoughts or the sensory
representation of physical objects, but also for ones about P-consciousness as such. Tye achieves
the same by assuming that a reductively definable mental state (or states) is synonymous with Pconsciousness. He thereby disputes the known doctrine that P-consciousness is functionally
indefinable. The present interactionist hypothesis, on the other hand, accounts for beliefs that one
may lingually refer to P-consciousness while also accepting its functional indefinability.
References
Arbeitsgemeinschaft für Methodik und Dokumentation in der Psychiatrie (2007) Das AMDP-System.
Manual zur Dokumentation Psychiatrischer Befunde (8th Ed), Göttingen, Germany: Hogrefe.
Baker, M. C. & Goetz, S. (eds.) (2011) The Soul Hypothesis. Investigations into the Existence of the Soul,
New York: Continuum.
Chalmers, D. J. (1996) The Conscious Mind. In Search of a Fundamental Theory, Oxford: Oxford
University Press.
Chalmers, D. J. (2010) The Character of Consciousness, Oxford: Oxford University Press.
Eccles, J. C. (1994) How the Self Controls Its Brain, Berlin, Germany: Springer-Verlag.
Epstein, M. (2007) Psychotherapy Without the Self. A Buddhist Perspective, New Haven, Connecticut:
Yale University Press.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 194-213
Halvorsen, E. L., Interactionism Read Anew: A Proposal Concerning Phenomenal Judgments
213
Fahey, T. (2008) Edmund Husserl, [Online], http://www.tonyfahey.com/2008/12/edmund-husserl.html
[03 March 2013].
Freeman, A. (ed.) (2006) Consciousness and its Place in Nature. Does Physicalism entail Panpsychism?,
Exeter, UK: Imprint Academic.
Haisch, B. (2006) The God Theory. Universes, Zero-Point Fields, and What’s Behind It All, San
Francisco: Weiser Books.
Hirsch, S. R. & Weinberger, D. (eds.) (2003) Schizophrenia Part Two Biological Aspects, Oxford:
Blackwell Publishing.
Howell, E. H. (2005) The Dissociative Mind, New York: Routledge.
Klinke, R. & Silbernagl, S. (1996) Lehrbuch der Physiologie (2d Ed), Stuttgart, Germany: Thieme.
Losee, J. (2011) Theories of Causality, New Brunswick, New Jersey: Transaction Publishers.
Ogden, T. H. (1986) The Matrix of the Mind. Object Relations and the Psychoanalytic Dialogue, Lanham,
Maryland: Rowman and Littlefield, 2004.
Papineau, D. & Selina, H. (2000) Introducing Consciousness, New York: Totem Books.
Popper, K. & Eccles, J. C. (1977) The Self and Its Brain. An Argument for Interactionism, Abingdon, UK:
Routledge, 2003.
Sainsbury, R. M. & Tye, M. (2012) Seven Puzzles of Thought and How to Solve Them: An Originalist
Theory of Concept, Oxford: Oxford University Press.
Sartory, L. (1996) Understanding Relativity. A Simplified Approach to Einstein’s Theories, Berkeley:
University of California Press.
Smolin, L. (2001) Three Roads to Quantum Gravity, New York: Basic Books.
Stoljar, D. (2010) Physicalism. New Problems of Philosophy, Abingdon, UK: Routlegde.
Tye, M. (2009) Consciousness Revisited. Materialism without Phenomenal Concepts, Cambridge,
Massachusetts: The MIT Press.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Logical Evaluation of Consciousness:
For Incorporating Consciousness into
Machine Architecture
Mr C.N.Padhy, Ms. R.R.Panda
Institute of Knowledge and Information Technology(IKIT)
Abstract
Machine Consciousness is the study of consciousness in a biological, philosophical, mathematical and
physical perspective and designing a model that can fit into a programmable system architecture. Prime
objective of the study is to make the system architecture behave consciously like a biological model does.
Present work has developed a feasible definition of consciousness, that characterizes consciousness with four
parameters i.e., parasitic, symbiotic, self referral and reproduction. Present work has also developed a
biologically inspired consciousness architecture that has following layers: quantum layer, cellular layer, organ
layer and behavioral layer and traced the characteristics of consciousness at each layer. Finally, the work has
estimated physical and algorithmic architecture to devise a system that can behave consciously.
1. Origin of Consciousness
How biological being are conscious?
How this consciousness is organized? are few of
the questions that are attempted in this section, by
taking into consideration of various views from
philosophy, physical science, biological science
and mathematics. It clearly depict that,
consciousness is the agent that is responsible for
intelligent behavior or phenomenon. Now we will
discuss about the various conceptualizations about
consciousness.
Many phenomenon in the universe are
not sufficiently explained by the scientific studies,
but aptly explained by philosophy. Hence study of
philosophy many a times gives much impetus to
probe into the causality of the phenomenon and
finally develop the model so as to apply for
solving real life problems.
Here our objective is to induct consciousness into
the machine architecture, so that intelligence
aspect of machine can be autonomous as in case
of any living being. Even an ant is autonomously
intelligent and do not require any external control
for it’s survival or normal functioning.
It is essential to probe into the causality of
consciousness and logical schemata of
consciousness for building a model inspired by
this phenomenon. Once, the model is developed,
it can be suitably fit into programmable machine
architecture and can behave consciously. Here,
the author have attempted to probe into the
philosophy of consciousness, but found that frame
of creation is highly required for understanding
the concept of consciousness. Hence, I am
depicting here the framework of creation for
better
appreciation
of
phenomenon
of
consciousness.
1.2 Framework of Creation
The whole creation is manifested through a well
organized layers, that starts with the formless
characteristics universe and ends at intelligent
actions generated in a matter.
All the layers have shown in the Fig 2. and
narrated in the followed texts:
1.2.1 Universe / Brahmanda
The whole creation is manifested and
characterized by Universe(Brahmanda). As per
the Oxford Dictionary “all existing matter and
space considered as a whole; the cosmos” and as
per Webster Dictionary “the whole body of things
and phenomena observed or postulated”. Universe
or Brahmanda is the prakriti or set of
characteristics of whole matter and phenomenon,
that exists in this universe.In brief, Universe is
composed of
Matter,
Space, and
Knowledge Base.
Knowledge Base
Knowledge base is the well defined,
logically arranged set of instructions for execution
of matters and various phenomenon..
Space
Space is the universe of discourse or
domain within which knowledge base is incident
on matter.
Matter
Any thing that governs with the universal
knowledge base and within a space of enactment
is a matter.
Matter = Space + Knowledge Base
1.2.2 Brahman :
Brahman is the instance of Brahmanda,
Brahman has no such difference as it is
one without a second,
Brahman is indivisible as it is devoid
of all differences, whether within
itself, or from things of same clsss or
from things of other classes(Veda)
It is formless in essence(Veda)
Before creation there was only
Brahman which is existence itself on
which
whole
creation
is
superimposed and percepted
existent(Chandogya Upanishad)
as
Interpretation of Brahman
Brahman is wide spread and exists
in all matter
Brahman is formless in essence and
when Brahman is incident on matter
it gets the form,
Brahman
is
responsible
for
consciousness in the matter
Characteristics of Universe is also
exists in each matter in the form of
Brahman, hence they are coherence
with the Brahmanda or Universe.
1.2.3 Consciousness(Chetana)
Consciousness is the is the incidence of
Brahman in the matter, that creates the
Prakriti or Characteristics of a matter.
Consciousness is the layer in the
framework of creation that is responsible
for executing the universal knowledge
base in a matter.
Levels of Consciousness
Consciousness can be classified into
following levels:
Quantum Layer
Compound Layer
Cellular Layer
Organ Layer
Behavioral Layer
At each lavel consciousness can execute the
matter autonomously and can also gives rise to
next layer of consciousness to create a higher
level of matter. In fact consciousness is
responsible for generating the feel of universe at
matter, as well as feel of matter in the universe,
hence creating the coherency between universe
and matter. Following figure depicts the various
levels of consciousness.
In this work, detail narration Cell level
consciousness, Organ level and Behavioral Level
is given. But, as currently work is in progress for
quantum, compound level consciousness, hence I
have not provided narration on quantum and
compound level consciousness.
2. Study of Consciousness
2.1 Definition of Consciousness
Consciousness can be logically defined as a
function of parasitic, symbiotic, self referral and
reproductive behavior.
Consciousness
consists
of
following
characteristics:
1. Parasitic Behavior,
2. Symbiotic Behavior,
3. Capacity to Refer Self, and
4. Reproductive Behavior.
1.2.4 Illusion/Maya
This is the layer just below
consciousness, that hides the complexity of
framework of creation from thought/chinta layer.
Hence, thought process of an animate matter do
not requires to realize about consciousness or
above that layer for it’s normal functioning.
Illusion layer also hides simple principles of
Prakriti and deludes as a complex
phenomenon.
This layer is responsible for creation of various
emotions such as: happiness, sad, anger,
affections, infatuations etc.
In brief, this layer creates the illusions of
duality in the nature which is not true in fact,
such as pain and pleasure, affection and
aversion, happiness and sorrow etc.,
1.2,5 Thought / Chinta
This is the layer which creates
procedures for actions that an animate performs
while executing various task. Prior to execution
of every task, first a procedure of how to
perform and what to perform is generated in
the thought space. Normally thought process is
hidden from the complexity of creation through
the duality created by illusion layer.
1.2.6 Stimulations/ Prayarthan
This is the layer that stimulates various
organs of the body of animate according to the
procedure generated at thought process to perform
actions / karma. When stimulations crossed a
certain threshold level, then only action is
generated
1.2.7 Action/Karma
Action is generated through the
stimulation/ prayarthan according to the procedure
generated at thought space.
Hence
Action/Karma = Thought or Chinta + Stimulation
Parasitic Behavior
It is the conscious behavior or tendency
to acquire resources for self survival
without concerning other’s existence.
This
behavior
makes
a
being
autonomous, and generates the tendency
to compete for resource for self survival.
2.1.2 Symbiotic Behavior
It is the conscious behavior or tendency
to associate peers for strengthening and
smoothening the survival.
This behavior generates the social
behaviors and allows the being to live in
a social ambience.
2.1.3 Capacity To Refer Self
It is the process of recursively
referencing self and generating actions
with respect to self.
This behavior allows to distinctly
positioning self and performing actions
with respect to self and creates the
capability to identify self with respect to
the surrounding and acquiring resources
for self survival autonomously.
2.1.4
Reproductive Behavior
Here, Reproduction means, reproducing
a new combination from existing set of
already produced objects. Here object
means the characteristics traits.
This behavior or characteristics
is used to create a new combination from
existing set of
characteristics. The
resultant combination may be a
biological child or a thought created
inside brain that generates an intelligent
action as a response to an external
stimuli.
Above characteristics are essential
yardsticks to have a heuristic measure of
consciousness, which is again essential
to test and implement consciousness.
Parasitic, Symbiotic, self referral and
reproductive are the essential properties
to categorize a specific entity as
conscious.
3. Architecture of Consciousness
Architecture of consciousness consists of
the following layers in existing conscious being.
1. Cell level,
2. Organ level,
3. Behavioral level.
Cell Level Consciousness
The cell is the structural and functional
unit of all living organisms, and are
called as the "building blocks of life”.
3.1.1 Test of consciousness at Cell level
1. Each cell is autonomous in taking input
without regarding the existence of other
cell(Parasitic behaviour)
2. Cells of same type joins together to form
an organ(Symbiotic behavior)
3. Cell have reproductive capablity to
create a another cell of same
type(Reproductive Behavior).
4. Cell can exist independenly and can
collect resource for self existence(Self
Referal).
Hence, it can be established that cell is
the smallest unit of consciousness in a
conscious architecture of a conscious
being.
Organ level consciousness
Similar cells are symbiotically grouped
to form an organ and several organs
symbiotically connected to form the
complete physical skeleton as well as
instructional skeleton. Each organ’s
functionality is distinct and uniquely
instructed to perform an unique and
specialized functionality. Each organ
behaves parasitically to compete for
resources needed for survival of the
organ. Each organ grouped symbiotically
to form the complete physical as well as
instructional skeleton. Each organ have
the capability to reproduce the cells to
keep intact and grow the organ. Hence,
Organ level consciousness exists.
3.2.1 The Comparison of cell level
consciousness and organ level consciousness
Cell level consciousness are integration
of differently instructed organelles in
side cell. Where as organ level
consciousness
are
integration
of
differently instructed cells in the organ.
Cell have all the symptoms of
consciousness.
Organ
level
consciousness also have all the
symptoms of consciousness derived
through the cells present in that organ.
3.3 Behavioral level Consciousness
Here we regard behavioral consciousness
is a complete autonomous system that
consists of several organs and can
communicate with the external world.
Consciousness at cellular level and at
organ level worked within the closed
system and for the closed system, but
here
the
complete
body
have
consciousness to interact with the
external system. Cells are integrated to
from organs and organs are integrated to
form the complete conscious system that
can now called a conscious being.
3.3.1 How Consciousness at cell level and organ
level are distinguished from that of
consciousness at body level
Consciousness at cell level or at organ
level are, they worked at a functional
level but consciousness at body level
work at behavioral level, though heads of
symptoms of consciousness are same.
In this case nervous system plays a
critical role to integrate rest all organs
and
produce
conscious
behavior
externally.
A conscious being exhibits parasitic behavior to
the external world by competing for resources for
self survival, symbiotically form the social
ambience for smoothening it’s survival, Self
referral by performing all actions with respect to
self, and reproduce the self species type to
populate and strengthening the species survival.
4. Design of Conscious Machine Architecture
A conscious machine architecture can be
made possible, by the following three layers:
1. Building blocks of Lowest level of
architectures should be conscious, such
as: Bits, Arithmetic Units etc.,. Here
2.
conscious means, processing capability
should be inducted at lowest level as
well.
Component level consciousness should
also be achieved by inducting
Consciousness Algorithm.
3. High level interface should be designed for
interacting with external world by
incorporating various Behavioral Algorithms.
Conscious Algorithm
Conscious algorithm has four categories
A. Parasitic Algorithm: This algorithm will
allow the machine to acquire resource for
self and exhibit parasitic behavior, essential
for autonomous survival.
B. Symbiotic Algorithm: This algorithm
category will allow the machine to
establish social interactions with peer
group autonomously.
C. Self Referral Algorithm: This algorithm
category will allow the machine to behave
mime characteristics.
D. Reproductive Algorithm: This category of
algorithm will allow the machine to
organize a suitable set of instructions from
existing set of instructions that can
intelligently respond to an external stimuli.
Behavioral Algorithm
Behavioral algorithm will be used for
inducing intelligent behavior into the
machine and made it possible for the machine
to sense and respond to the external world
intelligently.
Various behavioral algorithms are:
1. Design algorithm for control processor
2. Designing
the
algorithm
for
implementing the event processes such
as:
a) Experience
b) Learning
c) Inheritance
of
generic
characteristics
c)
7.
Designing the protocol algorithm to store
and organize sensory inputs in the layered
memory.
8. Algorithm for developing creativity.
9. Algorithm for intention and desire
generation.
10. Algorithm for developing machine to
machine social interaction.
11. Algorithm for design for social language
development through interaction.
5. Conclusion & Future work
This paper provides the basis for designing a
conscious machine. First it presents the study and
analysis of the concept of consciousness in an
existing biological conscious being, architecture
of consciousness and then reproducing the same
architecture in the machine to develop
consciousness in the machine. The prime
objective to develop consciousness is to reduce
the dependency of human for creating and
developing intelligence in the machine. The so
proposed work can be enhanced by developing
consciousness
algorithm
and
behavioral
algorithms. The next work includes reducing the
algorithm into machine implementation form in a
suitable machine architecture using suitable
computer language.
6. References
1.
2.
3.
4.
5.
6.
7.
3. Designing
the
algorithm
for
implementing sense via various sensory
components.
4. Designing the algorithm for recursive
sensory (Or, self diagnose).
5. Designing algorithm to create an active
virtual space(or, thought space)
6. Designing the algorithm for analyze the
sensory inputs with respect to
a) Active virtual space(thought space)
b) Active
personality
space
(Personality trait).
Intensity of the current sensory
input.
8.
9.
Bruce Alberts, Alexander Johnson, Julian Lewis;
“Molecular Biology of The Cell”, Garland 4th
Edition.
www.stemcellresearch.org
Thomas Mitchell,”machine learning”, Mc-Graw
Hill International Edition.
Richard O.Duda; “ Pattern Classification”, John
Willey, 2nd Edition.
Stuart Russel, Peter Norvig; “ Artificial
Intelligence: A Modern Approach”, Prentice Hall,
2nd edition.
Dr. T.D.Singh; “Life, Matter and Their
Interactions”, Bhaktivedanta Institute.
Sir Roger Penrose, Dr. T.D.Singh; “Science,
Spirituality and Nature of Reality”, Vakti Vedanta
Institute.
http://crca.ucsd.edu/~hcohen
Dr. P.M.Pattnaik, “Abstract of Veda” |
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1052
Article
On Quantum Consciousness Mechanics
Cebrail H. Oktar
*
Department of History Science, History of Science Society, 440 Geddes Hall, University of
Notre Dame, Notre Dame, IN 46556
ABSTRACT
Quantum Consciousness Mechanics is based on physics and metaphysical intensity states. The
aim of this paper is to attempt to combine physical and metaphysical intensity states for
consciousness. It is shown that widening of parapsychology to the solution of quantum
consciousness can be important in the explanation of paranormal phenomena. I have applied
equations in quantum mechanics to quantum consciousness. These equations can have two
solutions, one of which describes waves, energy and matter propagating from the past to the
future and the other describes waves, energy and matter propagating from the future to the past.
Working on the mathematical properties of the advanced solutions, mathematician Luigi
Fantappiè discovered in 1941 that they coincide with the qualities of living systems what they
are concentration of energy, differentiation, structures and order, thus arriving at the conclusion
that life, more than being effected by causes placed in the past, is attracted by causes placed in
the future. Therefore, the parameters of the autonomic nervous system, which supports vital
processes, should show anticipated reactions to future stimuli.
Key Words: quantum mechanics, consciousness, quantization, Fantappiè, vital processes, past,
future, wave, energy, matter, anticipatory.
1. Introduction
Von Neumann gave the name Process 1 to the physical posing of a probing question. He
specified its general mathematical form, and sharply distinguished it from the very different
Process 2, which is the mathematically specified evolution of the quantum state in accordance
with the rules specified by the quantization procedure. Process 1 events intervene abruptly, from
time to time, in the orderly evolution specified by Process 2.
This problem of the indeterminateness of the conscious choices is resolved in orthodox
Copenhagen quantum mechanics by adopting a pragmatic stance. The theory is considered to be
a set of rules useful to a community of communicating, conscious, observing agents imbedded in
a physical universe. These agents make conscious decisions about how to probe that universe, in
order to observe responses that will augment their knowledge. The difficulty mentioned above,
which is that the known laws do not determine which of the possible probing questions will be
physically posed, is neatly resolved by saying that this very openness allows the conscious
*Correspondence: Cebrail H. Oktar, Department of History Science, History of Science Society, 440 Geddes Hall, University of
Notre Dame, Notre Dame, IN 46556. E-mail: javaquark@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1053
agents to freely choose which probing questions they will physically pose. Thus the causal gap in
the mathematically described structure is filled by the free choices made by conscious agents.
Bohr often emphasized the freedom of these agents to make these choices:
The freedom of experimentation, presupposed in classical physics, is of course retained and
corresponds to the free choice of experimental arrangement for which the mathematical structure
of the quantum mechanical formalism offers the appropriate latitude. (Bohr, 1958, p.73).
To my mind there is no other alternative than to admit in this field of experience, we are dealing
with individual phenomena and that our possibilities of handling the measuring instruments
allow us to make a choice between the different complementary types of phenomena that we
want to study. (Bohr, 1958, p. 51).These quotes highlight the key fact that selection of the
Process 1 probing events is determined, within the framework of contemporary physics, not by
known mathematical or physical laws but rather by free choices made by conscious
agents[1,2,3,4,5].
2. The Ages of Quantum Consciousness Mechanics
2.1 John von Neumann
John von Neumann formulated Copenhagen quantum mechanics in a mathematically rigorous
form, and then, in order to remove ambiguities associated with the placement of the Heisenberg
cut, showed that this cut could be pushed all the way up, so that the entire physically describable
universe, including the bodies and brains of the agents, are described quantum mechanically.
This placement of the cut does not eliminate the need for Process 1. It merely places the physical
aspect of the Process 1 psychophysical event in the brain of the conscious agent, while placing
the conscious choice of which probing question to pose in his stream of consciousness. That is,
the conscious act of choosing the probing question is represented as a psychologically described
event in the agent’s mind, which is called by von Neumann (1955, p.421) the “abstract ego”.
This choice is physically and functionally implemented by a Process 1 action in his brain. The
psychologically described and physically described actions are the two aspects of a single
psychophysical event, whose physically described aspect intervenes in the orderly Process 2
evolution in a mathematically well defined way. Bohr emphasized that the laws of quantum
theory should continue to be valid in biological systems, but that the latitude introduced by the
severe constraints upon observation imposed by the demands of sustaining life could permit such
concepts such as “teleology” and “volition” to come consistently into play. (Bohr,1958, p.10,
p.22)
Orthodox quantum theory is a theory of a type called interactive dualism, which goes back in
modern philosophy to Descartes, and before that to the ancient Greeks. An interactive dualism
postulates the existence of two entirely different kinds of realities, mental and physical, that
interact. Mental realities have the character of feelings, broadly construed to include thoughts,
ideas, perceptions, pains, joys, sorrows and all things that enter directly into our streams of
conscious experiences, and are described basically in psychological language.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1054
Physical realities are elements that are described in our theories of nature interms of
mathematical qualities assigned to space-time points. Interactive dualism combined with the
precepts of classical physics gives classical interactive dualism. This has been attacked
ferociously by philosophers for over three hundred years, with an intensity that has been
increasing over the past half century. Quantum interactive dualism is based, instead, on orthodox
quantum theory.
The first main objection to classical interactive dualism is that it postulates the existence of two
entirely different kinds of things, but provides no understanding of how they interact, or even can
interact. The second main objection is that the physical description is, by itself, already causally
complete, giving a completely deterministic account of the evolution in time of every physically
described entity, which means that the mental realities have nothing to do, and no possibility of
influencing anything physical. The mental side is a “ghost in the machine” that is imagined to be
pulling the levers in order to ‘work its will’ in the physical world, but cannot really be doing so
because the behavior of the physically described universe is completely determined
independently of the ghostly machinations [6,7,8,9,10].
2.2 William James
The dynamical effect described above of a volition-induced high rapidity of the Process 1
probing actions is exactly in line with the description of the effects of volition described by
William James (1892). In the section entitled Volitional effort is effort of attention he writes:
Thus we find that we reach the heart of our inquiry into volition when we ask by what process is
it that the thought of any given action comes to prevail stably in the mind. (p. 417).
The essential achievement of will, in short, when it is most ‘voluntary,’ is to attend to a difficult
object and hold it fast before the mind. (p.417).
Everywhere, then, the function of effort is the same: to keep affirming and adopting the thought
which, if left to itself, would slip away.(p.421)
James may have foreseen, on the basis of his efforts to understand the mindbrain connection, the
eventual downfall of classical mechanics. He closed his book with the prophetic words and never
forget that the natural-science assumptions with which we started are provisional and revisable
things. (p.433)
A lot has happened in psychology since the time of William James, but these newer
developments support James’s idea of the holding-attention-in-place action of volition. Much of
the recent empirical and theoretical work pertaining to attention is summarized in Harold
Pashler’s book The Psychology of Attention (Pashler, 1998). Pashler concluded that the evidence
indicates the existence of two distinct kinds of mental processes, one that appears not to involve
volition, and that allows several perceptual processes to proceed in parallel without significant
interference, and one that does involve volition and that includes planning and memory storage.
This latter process seems to involve a linear queuing effect with limited total capacity.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1055
These properties of volition-driven processes appear to be explainable in terms of the basic laws
of orthodox quantum physics, which entail the existence of Process 1 physical events whose
timings are controlled by conscious choices,and which can, in principle, by means of the
quantum Zeno effect, tend to hold in place a pattern of neural activity that will tend to bring into
being an intended effect. But this holding effect drops out in the classical-physics approximation,
in which all physically described properties become completely determined by physically
described properties alone, with consciousness a causally inert, or causally superfluous,
bystander. Correlations between physically and psychologically described properties can be
described within a classical physics based framework, but the psychologically described aspects
will remain essentially epiphenomenal by-products of brain activity. This evidence from
psychology is discussed in detail in Stapp (1999, 2001) and in Schwartz, Stapp, and Beauregard
(2003, 2005) [11,12,13,14,15].
2.3. Ochsner’s Experiments
The most direct evidence pertaining to the effects of conscious choices upon brain processes
comes from experiments in which identifiable consciously controllable cognitive processes seem
to be controlling directly measured physical processes in the brain. An example is the experiment
of Ochsner et.al. (2001). The subjects are trained how to cognitively re-evaluate emotional
scenes by consciously creating and holding in place an alternative fictional story of what is really
happening in connection with a scene they are viewing. The trial began with a 4 sec presentation
of a negative or neutral photo, during which participants were instructed simply to view the
stimulus on the screen. This interval was intended to provide time for participants to apprehend
complex scenes and allow an emotional response to be generated that participants would then be
asked to regulate. The word Attend for negative or neutral photos or Reappraise negative photos
only then appeared beneath the photo and the participants followed this instruction for 4 sec …
To verify whether the participants had, in fact, reappraised in this manner, during the post-scan
rating session participants were asked to indicate for each photo whether they had reinterpreted
the photo as instructed or had used some other type of reappraisal strategy. Compliance was
high:
On less than 4% of trials with highly negative photos did participants report using another type
of strategy. Reports such as these can be taken as evidence that the streams of conscious of the
participants do exist and contain elements identifiable as efforts to reappraise.
Patterns of brain activity accompanying reappraisal were assessed by using functional magnetic
imaging resonance (FMRI). The FMRI results were that reappraisal was positively correlated
with increased activity in the left lateral prefrontal cortex and the dorsal medial prefrontal cortex
(regions thought to be connected to cognitive control) and decreased activity in the (emotionrelated) amygdala and medial orbito-frontal cortex[16,17,18,19,20].
2.4. The Penrose-Hameroff Theory
Roger Penrose and Stuart Hameroff (Hameroff & Penrose, 1996) have proposed a quantum
theory of consciousness that brings together three exciting but controversial ideas. The first
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1056
pertains to the still-to-be-worked-out quantum theory of gravity. The second involves the famous
incompleteness theorem of Gödel. The third rests upon the fairly recently discovered
microtubular structure of neurons.
Penrose proposes that the abrupt changes of the quantum state that are associated with conscious
experiences are generated by the gravitational effects of particles of the brain upon the structure
of space-time in the vicinity of the brain. Ordinarily one would think that the effects of gravity
within the brain would be too minuscule to have any significant effect on the functioning of the
brain. But Penrose and Hameroff come up with an estimate of typical times associated with the
gravitational effects that are in the tenth of a second range associated with conscious
experiences. This fuels the speculation that the abrupt changes in the quantum state that occur in
quantum theory are caused not by the entry of thoughts into brain dynamics, but by quantum
effects of gravity.
But then why thoughts or consciousness should be involved at all? Two reasons are given.
Penrose uses Gödel’s incompleteness theorem to argue that mental processing cannot be wholly
mechanical or algorithmic. The argument takes hundreds of pages (Penrose, 1986, 1994) and has
been attacked by many seemingly qualified critics. (e.g., Putnam, 1994). It is fair to say that it
has not passed the usual demands made upon mathematical and logical arguments. But the
argument claims that both mental processing and the gravitational effects are non-algorithmic,
and that the latter could therefore provide in a natural way the non-algorithmic element needed
for the former The second connection of the proposed gravitational effect with consciousness is
that the estimated time associated with the gravitational effect was based on the presumption that
the components of the brain critical to consciousness were functioning microtubules. Data
pertaining to loss of consciousness under the influence of various anesthetic agents indicate that
the proper functioning of microtubules is necessary for consciousness. But many things are
necessary for consciousness, so this argument that the gravitational effect is connected
consciousness via microtubules is not compelling.
A serious objection to the Penrose-Hameroff theory has been raised by Max Tegmark (2000).
The Penrose-Hameroff theory requires that the critical microtubular state be a coherent quantum
state that extends over a macroscopic region in the brain. Normally one expects any macroscopic
coherence of a quantum state in a warm wet brain to be destroyed almost immediately. Tegmark
estimates the duration of coherence to be on the order of 10 −13 seconds, which is far smaller than
the one tenth of a second associated with conscious events. Hagen, Hameroff, and Tuszynski
(2002) have claimed that Tegmark’s assumptions should be amended, so that the decohence time
increases to 10 −4 seconds, and they suggest that the remaining factors can perhaps be made up by
biological factors. In any case, the need to maintain macroscopic quantum cohererence in a warm
wet brain is certainly a serious problem for the Penrose- Hameroff model. It might be mentioned
here that in the von Neumann model described in the preceding sections quantum decoherence is
an important asset, because it allows the quantum state of the brain to be understood as
essentially a smeared out statistical ensemble, collection of essentially classically conceived
states, which, however, can interact with neighboring members of the ensemble in a way that
preserves the quantum Zeno effect.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1057
This quasi-classical conceptualization of the quantum state of the brain allows non-physicists to
have a relatively simple understanding of the mind-brain system [21,22,23,24,25].
2.5 The Eccles-Beck Theory
An early quantum approach to the mind-brain problem was made by John Eccles (1990) who
emphasized the entry of quantum effects into brain dynamics in connection with effects at nerve
terminals. However, instead of building directly on the quantum rules and the profound
conceptual relationships between quantum and classical mechanics he introduced a conscious
biasing of the quantum statistical rules. This actually contradicts the quantum rules, thereby
upsetting the logical coherency of the whole scheme. In a later work with Beck (2003) he
retained the quantum rules, while introducing quantum uncertainties at the nerve terminals that
can play the same role that they do in the standard approach described earlier. This brings the
model into accord with the standard model described above, in regard to this technical point.
However, Eccles added a superstructure involving conscious “souls” that can exist apart from
physical brains. That suggestion goes beyond the ideas described here [26,27,28,29,30].
2.6 Bohm Theory
Several other quantum theories of consciousness have been proposed. [Bohm,1990; Jibu, 1995].
All are outgrowths of von Neumann’s formulation differences in these proposals are mainly at
the level of technical physics. We have focused here on the over-riding general issues of why
quantum theory should be relevant to consciousness in the first place, and how the switch to
quantum physics impacts upon the question vital to neuroscience, psychology, and philosophy of
the neural effects of volitional effort [26,27,28,29,30].
2.7 Henry Stapp
Henry Stapp is a theoretical physicist with a long-time special interest in mathematical and
conceptual problems in the foundations of quantum theory. He worked with Wolfgang Pauli and
with Werner Heisenberg and has published extensively on the subjects of axiomatic S-matrix
theory, quantum non-locality, philosophy of quantum theory, and the mind-brain interaction
[26,27,28,29,30].
3. Quantum Consciousness Mechanics
Working with current definitions of consciousness, many series of postulates are developed
toward relating physical and metaphysical states. This includes much mathematical formula on
how to cross-culturally induce consciousness. The results overwhelm the competition by two
orders of magnitude.
The purpose of this paper is to relate consciousness state is consisting from physical and
metaphysical states. The standard definitions used for consciousness often includes that it is a
borderline state between body and spirit.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1058
Any state characterized by an intense concentration of attention in one area, accompanied by a
profound lack of attention in other areas, may also be considered consciousness.
The consciousness, which is an implied issue in this definition, may be defined as the difference
between the intensity of concentration in one area. Attention focused in one area creates a
corresponding intensity in other areas of the brain. Deeper states of consciousness are created by
centering the attention for prolonged periods.
The postulates of Quantum Consciousness Mechanics
(1) The physical intensity state postulate: The physical experience is associated with the
processes which take place above a certain critical level of intensity. This function, defined
varies considerably in a state of consciousness, where attention is focused.
(2) The metaphysical intensity state postulate: The metaphysical experience is consisting from
many aspects of the spiritual processes. Andrea Puharich showed physical informations
regarding the relationship between spiritual processes and physical perceptions.
(3) The consciousness state postulate: The consciousness state arbitrarily defined as product
physical and metaphysical intensity states. The consciousness operates by manipulating their
transformations and states. It is responsible for psycho-kinetic and potential phenomenon.
(4) The time evolution of physical intensity state postulate: Physical intensity is often observed
in consciousness, a state characterized by a single intensive by a single intensive thought.
Recurrent cases of psycho-kinetic phenomena, such as the haunted-house variety, are often
reported to be connected with previous important events, associated with physical intensity.
(5) The time evolution of metaphysical intensity state postulate: Metaphysical intensity is
observed with physical intensity in consciousness, which is created by a spiritual act. The
stimulating action of metaphysical intensity on the body and brain may account for memory,
more particularly, active recollection. The influence of metaphysical intensity increases the level
of consciousness of the neuro-patterns corresponding to the thought to be remembered.
(6) The time evolution of consciousness state postulate: Consciousness state observes physical
and metaphysical intensities which is created by physical and spiritual factors. The
consciousness state is produced in sufficient intensity and structuring to be able to produce an
observable effect. Consciousness states, in states of fearful emotions, motivations.
(7) The measurement postulate: Consciousness state is created into a mind state. What then
occurs is that this information is impressed on the consciousness. This event to the thinker is
independent of both space and time.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1059
3.1 The postulates of Quantum Consciousness Mechanics
3.1.1 The physical intensity state postulate
The state, at time t , of an isolated physical system that consists N of point intensities whose
→
→
positions are given by point intensities, r1 ,.............., rN ,is given by a well-behaved, square→
→
integrable and normalized wave function Ψ (r1 ,.............., rN , t ) for physical intensity states.
The Quantum Mechanical characterization of the system’s physical intensity state is completely
different from its classical counterpart, where the intensity state is described by the actual values
→
→
→
→
of and r1 ,.............., rN and p1 ,.............., p N at time t .
3.1.2 The metaphysical intensity state postulate
The state, at time t , of an isolated metaphysical system that consists N of point intensities
→
→
whose positions are given by point intensities , r1 ,.............., rN ,is given by a well-behaved,
→
→
square-integrable and normalized wave function Φ(r1 ,.............., rN , t ) for metaphysical intensity
states.
The Quantum Mechanical characterization of the system’s metaphysical intensity state is
completely different from its classical counterpart, where the intensity state is described by the
→
→
→
→
actual values of and r1 ,.............., rN and p1 ,.............., p N at time t .
3.1.3 The consciousness state postulate
The state, at time t , of an isolated consciousness system that consists N of point intensities
→
→
whose positions are given by point intensities , r1 ,.............., rN ,is given by a well-behaved,
→
→
square-integrable and normalized wave function ξ (r1 ,.............., rN , t )
where
→
→
→
→
→
→
ξ (r1 ,.............., rN , t ) = Ψ (r1 ,.............., rN , t )Φ (r1 ,.............., rN , t ) for consciousness states.
The Quantum Mechanical characterization of the system’s consciousness state is completely
different from its classical counterpart, where the intensity state is described by the actual values
→
→
→
→
of and r1 ,.............., rN and p1 ,.............., p N at time t .
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1060
3.1.4 The time evolution of physical intensity state postulate
→
→
The time evolution of the wave function, Ψ (r1 ,.............., rN , t ) is governed by the time dependent
equation for physical intensity state.
ih
→
→
→
→
→
→
∂
→
→
Ψ (r1 ,........., rN , t ) = E (r1 ,........., rN , t ) + V (r1 ,........., rN , t ) Ψ (r1 ,........., rN , t )
∂t
(1)
→
→
→
→
→
→
∂2
2 →
→
2
Ψ
(
r
,.........
.....,
r
,
t
)
=
E
(
r
,.........
,
r
,
t
)
+
V
(
r
,.........
,
r
,
t
)
Ψ
(
r
,.........
,
r
1
N
1
N
1
N
1
N , t ) (2)
∂t 2
where
− h2
→
→
→
→
Ψ (r1 ,.............., rN , t ) is probability function
E (r1 ,.............., rN , t ) is kinetic energy function
→
→
V (r1 ,.............., rN , t ) is the potential energy function
3.1.5 The time evolution of metaphysical intensity state postulate
→
→
The time evolution of the wave function, Φ(r1 ,.............., rN , t ) is governed by the time dependent
equation for metaphysical intensity state.
ih
→
→
→
→
→
→
∂
→
→
Φ(r1 ,........., rN , t ) = F (r1 ,........., rN , t ) + R (r1 ,........., rN , t ) Φ(r1 ,........., rN , t )
∂t
(3)
→
→
→
→
→
→
∂2
2 →
→
2
−h
Φ
(
r
,.........
.....,
r
,
t
)
=
F
(
r
,.........
,
r
,
t
)
+
R
(
r
,.........
,
r
,
t
)
Φ
(
r
,.........
,
r
1
N
1
N
1
N
1
N , t ) (4)
∂t 2
where
2
→
→
→
→
Φ(r1 ,.............., rN , t ) is probability function
F (r1 ,.............., rN , t ) is kinetic energy function
→
→
R (r1 ,.............., rN , t ) is the potential energy function
3.1.6 The time evolution of consciousness state postulate
The time evolution of the wave function,
→
→
→
→
→
→
ξ (r1 ,.............., rN , t ) = Ψ (r1 ,.............., rN , t )Φ (r1 ,.............., rN , t )
is governed by the time dependent equation for consciousness state .
ih
→
→
→
→
→
→
→
∂ →
ξ (r1 ,........., rN , t ) = G (r1 ,........., rN , t ) + S (r1 ,........., rN , t ) ξ (r1 ,........., rN , t )
∂t
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
(5)
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1061
→
→
→
→
∂ →
∂ →
Ψ(r1 ,..............,rN , t ) + Ψ(r1 ,..............,rN , t )ih Φ(r1 ,..............,rN , t ) =
∂t
∂t
→
→
→
→
→
→
→
→
(6)
Φ(r1 ,..............,rN , t ) E(r1 ,..............,rN , t ) + V (r1 ,..............,rN , t ) Ψ(r1 ,..............,rN , t ) +
→
→
→
→
→
→
→
→
Ψ(r1 ,..............,rN , t ) F (r1 ,..............,rN , t ) + R(r1 ,..............,rN , t ) Φ(r1 ,..............,rN , t )
2
→
→
→
→
→
→
→
∂
→
− h 2 2 ξ (r1 ,.............., rN , t ) = G 2 (r1 ,........., rN , t ) + S 2 (r1 ,........., rN , t ) ξ (r1 ,........., rN , t ) (7)
∂t
→
→
Φ(r1 ,..............,rN , t )ih
(−h )Φ(r ,..............,r ,t) ∂∂t Ψ(r ,..............,r ,t) +(−h )Ψ(r ,..............,r ,t) ∂∂t Φ(r ,..............,r ,t) =
2
→
→
2
1
N
2
→
→
1
N
2
→
→
2
→
→
1
N
2
1
N
→
→
→
→
→
→
→
→
Φ(r1,.........
.....,rN ,t)E2(r1,.........
.....,rN ,t) +V2(r1,.........
.....,rN ,t)Ψ(r1,.........
.....,rN ,t) +
(8)
→
→
→
→
→
→
→
→
Ψ(r1,.........
.....,rN ,t) F2(r1,.........
.....,rN ,t) + R2(r1,.........
.....,rN ,t)Φ(r1,.........
.....,rN ,t)
where
→
→
→
→
ξ (r1 ,.............., rN , t ) is probability function
G (r1 ,.............., rN , t ) is kinetic energy function
→
→
S (r1 ,.............., rN , t ) is the potential energy function
3.1.7 The measurement postulate
⇒
Every
dynamical
variable
is
represented
by
a
linear
and
hermitian
operator A .
Let {a1 ,............, a N } and {u1 ,............, u N }be the eigenvalues and eigenfunctions of A , respectively,
⇒
⇒
such that A u k = a k u k . Then:
1. The outcome of the measurement is always one of the eigenvalues of A , {a1 ,............, a N } .
⇒
2
2. The probability for measuring the eigenvalue is a k given by u k Ψ (t ) .
3. The state of the system after a measurement that gave the value a k reduces to the
corresponding eigenfunction, u k .
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1062
4. Summary and Discussion
In the conclusion of this paper, I argued that the scientific community should pay more attention
to quantum consciousness in physical and metaphysical intensity states. This effect has been
observed in several independent studies. This paper describes how quantum consciousness can
offer a scientific model which can accommodate many of the phenomena which are described in
the field of physics and metaphysics.
References
[1] Fantappiè L. (1942) Sull’interpretazione dei potenziali anticipati della meccanica ondulatoria e su un
principio di finalità che ne discende. Rend. Acc. D’Italia, n. 7, vol 4;
[2] King C.C. (1989) Dual-Time Supercausality, Physics Essays, Vol. 2(2): 128-151;
[3] McCraty R., Atkinson M and Bradley R.T., Electrophysiological evidence of intuition: Part 1. The
surprising role of the heart, in J. Alternative and Complementary Medicine, vol. 10, pp.133-143.
[4] Schrödinger E. (1944): What is life. Cambridge University Press
[5] Beck, F. and J. C. Eccles 2003: Quantum processes in the brain: a scientific basis of onsciousness. In
N. Osaka (ed.), Neural Basis of Consciousness, 141-166. Amsterdam, Philadelphia: John Benjamins
[6] Bohm, D. J. 1990: A new theory of the relationship of mind to matter.
[7] Bohr, N. 1934. Atomic Theory and the Description of Nature. Cambridge: Cambridge University
Press. (Re-issued in 1961)
[8] Bohr, N. 1958. Atomic Physics and Human Knowledge. New York: Wiley.
[9] Eccles, J.C. 1990: A unitary hypothesis of mind-brain interaction in the cerebral cortex. Proceedings
of the Royal Society of London B240, 433-451.
[10] Eccles, J.C. 1994: How the Self Controls its Brain. Berlin, Heidelberg, New York: Springer.
[11] Hagen, S., S. R. Hameroff, and J. A. Tuszynski 2002: Quantum computation in brain microtules:
decoherence and biological feasibility. Physical Review E65,061901-1 – 061901-11.
[12] Hameroff, S. R. and R. Penrose 1996: Orchestrated reduction of quantum coherence in brain
microtubules: a model for consciousness. J. Consciousness Studies 3, 36-53.
[13] Heisenberg, W. 1958: The representation of nature in contemporary physics. Daedalus 87 (Summer),
95-108.
[14] James, W. 1892: Psychology: the briefer course. In William James: Writings 1879-1899. New York:
Library of America.
[15] Jibu, M. & Yasue, K. 1995: Quantum brain dynamics and consciousness. Amsterdam and
Philadelphia: John Benjamins.
[16] Misra, B., and E. C. G. Sudarshan 1977: The Zeno’s paradox in quantum theory. Journal of
Mathematical Physics 18, 756-763.
[17] Ochsner, K.N., S, A. Bunge, J.J. Gross, and J. D. E. Gabrieli 2002: Rethinking feelings: An fMRI
study of the cognitive regulation of emotion. J. Of Cognitive Neuroscience 14:8, 1215-1229.
[18] Pashler, H. 1998: The Psychology of Attention. Cambridge, MA: MIT Press.
[19] Penrose, R. 1986: The Emperor’s New Mind. New York: Oxford.
[20] Penrose, R. 1994: Shadows of the Mind. New York: Oxford.
[21] Penrose, R. 1997: The Large, the Small, and the Human Mind. Cambridge: Cambridge University
Press.
[22] Putnam, H. 1994: Review of Roger Penrose, Shadows of the Mind.
[23] Schwartz, J. M., and S. Begley 2002: The Mind and the Brain: Neuroplasticity and the Power of
Mental Force. New York: Harper-Collins.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | October 2012 | Volume 3 | Issue 9 | pp. 1052-1063
Oktar, C. H., On Quantum Consciousness Mechanics
1063
[24] Schwartz, J.M., H.P. Stapp, and M. Beauregard 2003: The volitional influence of the mind on the
brain, with special reference to emotional self regulation. In M. Beauregard (ed.), Consciousness,
Emotional Self-Regulation and the Brain. [Advances in Consciousness Research Series, Volume 54].
Amsterdam, New York: John Benjamins.
[25] Schwartz, J.M., H.P. Stapp, and M. Beauregard 2005: Quantum theory in neuroscience and
psychology: a neurophysical model of the mind-brain interaction. Phil Trans. Royal Society (Biol.
Sect) (February). On line at http://www-physics.lbl.gov/~stapp/stappfiles.html
[26] Stapp, H. 1999: Attention, intention, and will in quantum physics. J. Consciousness Studies, 6, 143164.
[27] Stapp, H. 2001: Quantum theory and the role of mind in Nature. Found. Phys. 31,
1465-1499.
[28] Tegmark, M. (2000). Importance of quantum decoherence in brain process. Physical Review E61,
4194-4206.
[29] Von Neumann, J. (1955). Mathematical Foundations of Quantum Mechanics. Princeton: Princeton
University Press. (Translated by Robert T. Beyer from the 1932 German original, Mathematiche
Grundlagen der Quantummechanik. Berlin: J. Springer)
[30] Vannini A. (2008) Quantum Models of Consciousness, Quantum Biosystems, 2008, 2, pp. 165-184.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
214
Review Article
Pineal Gland, DMT & Altered State of Consciousness
Iona Miller*
ABSTRACT
Endogenous and synthetic DMT and their relation to pineal function have been the subject matter
of numerous popular and scientific articles, crossing many disciplines. Correlations for visionary
and psi-conducive states have been widely suggested. Numerous spiritual technologies have been
retrieved from traditional cultures and new technologies based in frequencies and resonance have
been concocted and sold to the public. Yet, in 2010, even the leading researcher Rick Strassman
says that “we don't know if DMT does appear in the pineal…[or, if] endogenous DMT activity
increases during particular non-drug altered states, such as dreams and near-death experiences.”
If it were, it would help explain the psychedelic characteristics of those altered states."
This strongly suggests that new assays for low levels of endogenous DMT, 5-MeO-DMT,
bufotenine, and metabolites in different tissues would be very useful. Such experiments were
conducted in 2012 with positive results. Nevertheless, a review of the history and speculation on
the psychoactive compounds remains of great interest to both researchers and the general public.
What do these things mean? The jury remains out, and we are wise to remember that theories
remain just that. Baselines need to be established for normal waking consciousness, and
comparisons made for a variety of states of consciousness. But perhaps the greatest result of such
research is new understanding of what it means to be fully human.
Key Words: pineal gland, DMT, dimethyltryptamine, N,N,-dimethyltryptamine, 5-methoxytryptamine, altered state of consciousness, 5-MeO DMT, “telepathine”, Pinoline, 6-methoxytetra-dydro-beta carboline, 6-MeO-THBC, hallucination, darkroom retreats, soma pinoline,
shamanic journeys.
I am created by Divine Light. I am sustained by Divine Light. I am protected by Divine Light. I
am surrounded by Divine Light. I am ever growing into Divine Light. Swami S. Radha in
Realities of the Dreaming Mind (1990).
Introduction
What do imaginative children, passionate lovers, dreamers, psychonauts, telepaths, bliss-bunnies,
UFO abductees, shamans and neo-shamans, birthing mothers and babies, near-death
experiencers, and schizophrenics have in common? The same thing Tibetan, Taoist and
Kabbalistic masters, meditators, mystics and religious prophets share.
Popular theories contend that their brains may be flooded with natural psychedelic pineal
*Correspondence: Iona Miller, Independent Researcher. Email: iona_m@yahoo.com Note: This work was completed in 2006
and updated in 2013.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
215
secretions that tenaciously cling to their synaptic junctions, electrifying their whole being with
multisensory virtual stimuli, experiential beliefs and delusions about the nature of reality.
Can the resonant buzzing of our own bioelectronic Third Eyes awaken latent metaprogram
circuits, leaving us virtually blinded by compelling mind-altering hallucinations? In
extraordinary circumstances, chemical brainstorms of scintillating multidimensional visionary
Light are generated in our own craniums producing demons, divinities, aliens, oceanic ecstasies,
death/rebirth, and time distortion. According to some, this hyperdelic retinal circus is your brain
on the natural high, DMT.
Whether or not DMT can be proven as the source, there is a long history of unusual
phenomenology contained in the world's great literature and in traditional lore. This spiritual
supercharge, revealed in all wisdom writings, has been sought by cultures from Egypt and Asia
to the Americas, from Druids to Tibetan lamas, and now in modern science.
Psychedelic alchemist, Sasha Shulgin claims, “DMT is everywhere,” in nature. Seekers have
ceremonially emptied or exhausted their mindbodies, using plant or animal products, spiritual
technologies, sensory deprivation, social isolation, fasting and ordeals, rhythmic chanting,
drumming, electronic resonance, even sex, to hasten and drive the neurological illumination.
(Miller, 2006)
DMT was ‘discovered’ by Richard Manske (by synthesis) in a lab in 1936, and later found in
South American shamanic plants in the mid-1940’s. But, its psychoactive properties were not
recognized until 1956 by the Hungarian chemist ad psychiatrist Stephen Szára. With his
colleagues, he characterized the biochemistry of the first three psychedelic cogeners of
tryptamine: dimethyl-, diethyl-, and dipropyl-tryptamine (DMT, DET, and DPT), describing
their pharmacological dynamics and effects.
Mathematician Ralph Abraham (2006) reports scientific inspiration from synthetic DMT:
“At one time, around 1969, we used large doses of DMT, and this period was crucially important
to the whole evolution of my mathematical understanding of consciousness, based on geometry,
topology, nonlinear dynamics and the theory of vibrating waves. For in these experiments,
although lasting only a few minutes, the reciprocal processes of vibrations producing forms and
forms producing vibrations were clearly perceived in abstract visual fields.”
Professor Steven Barker has taken DMT research into the philosophical level, as well,
considering questions of spirituality and the nature of belief in God. He focuses not only on the
pharmacology and hallucinations, but reports of spiritual effects and religious experience. Such
preparations give the impression of "being in touch with the universe". Drugs such as ayahuasca
have inspired a robust tourist trade and an explosion of shamanic experts of varying credibility.
Barker reports, "[These compounds] cause euphoria, tunnels of light, they see fantastic beings —
deities, relatives — you can't explain it. Those phenomena … we know these compounds can do
those things." He admits such experiences can be kindled without ingesting drugs. He calls such
spontaneous phenomena the biological and molecular basis for religious faith. This is how "God"
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
216
emerges from our bodies. Speculations have given way to the emerging science of transcendental
experiences -- neurotheology, the anatomy of spiritual life.
This Is Your Brain on Youth
We are hardwired to seek pleasure, to seek ecstasy. As children we expressed our authentic, core
selves – that which can neither be taught nor learned. But the whole “self-help” and “new age”
movements are based on trying to get back that golden state of innocence, childlike wonder and
awe with spiritual connection.
When religion suggests we “become as little children” again, who could imagine this implies a
shamanic return to the womb and the natural psychedelic state of an uncalcified pineal gland? In
early childhood, we are perpetually immersed in cascades of trance-inducing theta rhythms of the
brain, with the feel-good chemical brew it creates for metaprogramming.
Until roughly age 8, we can’t really distinguish between fantasy and reality, due to our own
natural hallucinogen, DMT, (dimethyltryptamine). DMT molecules are similar to serotonin and
target the same receptors. Meditation has been suggested as a means of preserving youthful
appearance and mental flexibility. Dr. Rick Strassman and others claim this spiritual technology
encourages production and release of natural DMT (Soma Pinoline) in the mindbody throughout
the lifespan.
DMT is implicated in the wild imaginings of our nightly dreams, near-death phenomena (NDEs),
alien abduction experiences, and dream yoga. It is also a plausible source of visionary
phenomena in therapy, such as unusual psychophysical states attained in waking dreams,
shamanic or psychotherapeutic journeys. Synthetic and botanical DMT crosses the blood-brain
barrier and bonds to the same synaptic sites as serotonin.
”Each night in dreams we experience an essentially psychedelic state. The principal difference
between dreams and hallucinations is the way the stages of wakefulness are organized, with the
suppression of REM sleep and the intrusion of PGO waves in the arousal (waking) stage and in
NREM (or slow) sleep.
"The stages include: waking (arousal) stage, stage of PGO waves, hallucination stage, sleep
stage and hallucinatory manifestations. The waking dream eliminates “residues” stirred up by
the PGO wave pattern in the absence of REM sleep. These visions resemble those at the
approach of death, or what are called near death experiences (NDEs). In another context, they
are perceived as visions. They include the characteristics of two phases of NDEs (Sabom,
1982):
Autoscopic phase includes: 1) subjective feeling of being dead; 2) peace and well-being; 3)
disembodiment; 4) visions of material objects and events.
The Transcendental phase includes 5) tunnel or dark zone; 6) evaluation of one’s past life; 7)
light; 8) access to a transcendental world, entering in light; 9) encounter with other beings; 10)
return to life.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
217
The Path of Light: Primordial In-Sight
The pineal sits, well protected in the deep recesses of the brain, bathed in cerebrospinal fluid by
the ventricles, the fluid-filled cavities of the brain that feed it and remove waste. The ventricles
also function as resonant capacitors, sensitive to certain frequencies. There are many scientific
examples of psychedelic body fluids and metabolites (Collected Abstracts).
The pineal gland emits its secretions to the strategically surrounding emotional, visual and
auditory brain centers. It helps regulate body temperature and skin coloration. It secretes the
sleep hormone melatonin, which is also implicated in DNA repair (Santoro) and epigenetic
regulation (Korkmaz). Epigenetic, inherited genetic modifications are known to be involved in
disease.
Generally, after the more imaginative period of childhood, the pineal calcifies and diminishes at
the onset of puberty’s sex hormones, around age 12. The pineal is the only unpaired gland in the
brain. Curiously, this solitary gland is light sensitive and actually has a lens, cornea, and retina.
Is there a retinal circus of biophotons deep in the brain, which only the Third Eye sees or even
creates: the Light of Wisdom?
This "Third Eye,” in the center of the brain, is implicated in the production of endogenous or
natural DMT, dubbed the Spirit Molecule in popular literature. The pineal synthesizes natural
hallucinogens in response to certain psychophysical states, and raises serotonin levels in the
brain. There is a functional decline in the gland with advancing age.
This master gland is responsible for the internal perception of Light, the raising of Kundalini the
serpent power, and for awakening inner sight or in-sight. The key to a successful meditation is
the withdrawal of the sensory currents to the eye focus or the third eye. Once there, the gaze
focuses on the middle of whatever appears without any distractions or intrusive thoughts, ideally
immersed in the unconditioned field.
The groundbreaking work of Dr. Rick Strassman (2001) focuses on the role natural body
chemistry plays in creating spiritual life. He calls DMT the Spirit Molecule; an endogenous
hallucinogen, which he boldly asserts, is an active agent in a variety of altered states including
mystical experience. To explore his theory, Strassman conducted extensive testing, injecting
volunteers with the powerful psychedelic, synthetic DMT (N,N-dimethyltryptamine; N,N-DMT).
DMT is so powerful it is physically immobilizing, and produces a flood of unexpected and
overwhelming visual and emotional imagery. Taking it is like an instantaneous LSD peak. DMT
crosses the usually impenetrable blood-brain-barrier, suggesting its fundamental role in
consciousness. But, concluding his 5-year studies early, Strassman admitted despite their growth
potential, there were no viable therapeutic or neurological applications. He does NOT
recommend recreational use.
DMT production is stimulated, in the extraordinary conditions of birth, sexual ecstasy, childbirth,
extreme physical stress, near-death, and death, as well as meditation. Pineal DMT also plays a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
218
significant role in dream consciousness. This chemical messenger links body and spirit. Pineal
activation awakens normally latent neural pathways.
"All spiritual disciplines describe quite psychedelic accounts of the transformative experiences,
whose attainment motivate their practice. Blinding white light, encounters with demonic and
angelic entities, ecstatic emotions, timelessness, heavenly sounds, feelings of having died and
being reborn, contacting a powerful and loving presence underlying all of reality--these
experiences cut across all denominations. They also are characteristic of a fully psychedelic
DMT experience. How might meditation evoke the pineal DMT experience?"
"Meditative techniques using sound, sight, or the mind may generate particular wave patterns
whose fields induce resonance in the brain. Millennia of human trial and error have determined
that certain "sacred" words, visual images, and mental exercises exert uniquely desired effects.
Such effects may occur because of the specific fields they generate within the brain. These fields
cause multiple systems to vibrate and pulse at certain frequencies. We can feel our minds and
bodies resonate with these spiritual exercises. Of course, the pineal gland also is buzzing at
these same frequencies. . .The pineal begins to "vibrate" at frequencies that weaken its multiple
barriers to DMT formation: the pineal cellular shield, enzyme levels, and quantities of antiDMT. The end result is a psychedelic surge of the pineal spirit molecule, resulting in the
subjective states of mystical consciousness." (Strassman, 2001).
Natural hallucinogens may belong to the tryptamine or beta-carboline family of compounds. One
compound (6-methoxy-1,2,3,4-tetra-hydro-beta-carboline) has been implicated in rapid eye
movement sleep (REM). It is concentrated in the retinae of mammals, which may be related to
its visual effects. There are several ways in which either psychoactive tryptamines and/or betacarbolines may be produced within the central nervous system and pineal from precursors and
enzymes that are known to exist in human beings. In addition, nerve fibers leave the pineal and
make synaptic connections with other brain sites through traditional nerve-to-nerve connections,
not just through endocrine secretions.
Third Eye Blind
Serotonin or tryptamine levels are higher in the pineal than any other organ in the brain. 5methoxy-tryptamine is a precursor with hallucinogenic properties, which has a high affinity for
the serotonin type-3 receptor. Gucchait (1976) has demonstrated that the human pineal contains
an enzyme capable of synthesizing both DMT and bufotenine-like chemistry. These compounds
are prime candidates for endogenous “schizotoxins,” and their production may be related to
stress and/or trauma, that correlate with schizophrenia.
Strassman notes that both the embryological rudiments of the pineal gland and the differentiated
gonads of both male and female appear at 49 days. Melatonin is a timekeeper for gonadal
maturation, so the pineal is implicated again. He suggests this rein-effect may be the root of the
tension between sexual and spiritual energies, yang and yin. The pineal gland is a source of both
psychedelic compounds and the regulates the gonads, sources of spiritual and generative
immortality.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
219
Stress-related hormones cue the pineal activation to activate normally latent synthetic pathways,
creating tryptamine and/or beta-carboline hallucinogens. When we face stress or potential death,
or in meditative reveries, we “tune back” into the most well developed motif of such
experiences--the birth experience. Perinatal themes and memories re-emerge (Grof).
Those with Cesarean deliveries report greater difficulty in attaining transcendent states of
breakthrough and release during drug-induced states. Maybe less fetal (or maternal)
hallucinogens were released at the time of birth. They may not, according to Strassman, have a
strong enough “template of experience” to fall back on, to let go without fear of total
annihilation, because lesser amounts of pineal hallucinogens were produced during their births.
Through meditation, the pineal may be modulated to elicit a finely tuned standing wave through
resonance effects. It creates the induction of a dynamic, yet unmoving, quality of experience.
Such harmonization resynchronizes both hemispheres of the brain. It recalibrates the whole
organism.
Dysynchrony is associated with a variety of disorders. Such a standing wave in consciousness
can induce resonance in the pineal using electric, magnetic or sound energy, and may result in a
chain of synergetic activity resulting in the production and release of hallucinogenic compounds.
Thus, the pineal can be likened to an attractor, or “lightning rod” of consciousness. It generates
an illuminative laser beam that pervades the energy body.
A Walk on the Wild Side
McGillion (2002) reports that ancient cosmobiologists noticed effects of the planets were
mediated by the pineal gland. Physician-astrologers in Greece and Europe assumed a correlation
between events in the heavens and those on earth that was relevant to both health and disease.
The sun, moon, and planets studied by the early health practitioners can, and do, affect us. A
simple example is being born in the day or night can make us a “morning person” or “night owl,”
by setting the circadian body-clock of pineal sensitivity and melatonin production.
Humans are among the organisms in which light sets off chain reactions of enzymatic events in
the pineal gland that regulate circadian rhythms. It modulates photoreceptive circadian
oscillators, sets the pacemaker, and governs longer cycles. Seasonality and geomagnetism at
birth can affect long term development. In this way, it influences our relationship with people,
animals and the earth. It keeps us in synch with life.
Physicist Cliff Pickover argues that, "DMT in the pineal glands of Biblical prophets gave God to
humanity and let ordinary humans perceive parallel universes." “Our brain is a filter, and the use
of DMT is like slipping on infrared goggles, allowing us to perceive a valid reality that is inches
away and all around us.”
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
220
He suggests, perhaps our ancestors produced more DMT, leading to extraordinary spiritual
visions. “Maybe this is why the ancients seemed so in touch with God and with miracles and
visions. Maybe Moses, Mohammad, and Jesus had a greater rate of pineal DMT production than
most.” Pickover blames artificial light for a reduction in our DMT production rate. Or perhaps
more likely, as most ancient cultures, they simply supercharged themselves with shamanic herbs.
Some claim the “burning bush” was Cannabis sativa, Assyrian Rue (Pegunam harmala;
Zoroaster’s Hoama, Asena ) or the North African Acacia tree, and that Moses either smoked the
leaves or got high downwind in the DMT-containing smoke. Graves, (1948, 264) claimed the
Acacia Sant, a host tree of the mistletoe-like loranthus, was the 'burning bush' and source of
manna.
If this oracular tree of Canaan contained tryptamines, as many species do, Moses could have had
access to DMT illumination. It is still a practice to burn botanicals inside a tent to imbibe their
smoke. Assyrian rue was the most sacred plant of Mohammad, who took the Esphand
(Arabic/Persian name for the plant) before receiving the Koran from God. This holy Esphand
was associated with the appearance of angels and casts out evil spirits, and was used to cure
fever and malaria and provides the rich red dye of Persian carpets.
Rue was central to the Petra mystery rites and schools of alchemy. Their sacrament was a
beverage of illumination and restoration, mixed with gold and other alchemical products. It was
passed down from Zoroaster, who was also known as Chem the original Alchemist and
CHEMist. Chem is an ancient name for Egypt. The grandson of Zoroaster, Nimrod or King
En.Meru.dug, founded the Egyptian 2nd Dynasty. This plant of life became central in the
Mysteries and healing schools of ancient Egypt, where Moses could easily have learned its
powers. (Bosman)
The original Essenes, named after the plant, were headquartered in Heliopolis. Asena, the
botanical Bush of Life, is an acronym, ASNA, of Aset (Isis) Sutekh (Set) Nebtet (Nephtys) and
Auser (Osiris). It embodied the female form of the One God ATON, who correlates with the
Greek goddess of wisdom, Athena.
Shamanic Bedouins still make the Egyptian eucharistic Bread of Light using the Asena/Hoama
bush, the North African Acacia tree, and ground meteorite. They still shape it the form of the Eye
of Ra, a circle with a central hole. The tradition was passed down to Christian Gnostics in
Abydos, Egypt where the bush eventually was used symbolically to sprinkle holy water.
Leonardo da Vinci and Michaelangelo reportedly used it for visionary inspiration.
In modern times, Pickover has suggested spontaneous DMT experiences as a possible source of
Whitley Streiber’s Communion aliens: “…we know that DMT can often produce visions of
cartoon-like aliens.” Others (Meyer, 1993) report those using DMT often claim communication
with stick-like, insect-like or elf-like beings and discarnate entities. Psychonaut, Terence
McKenna used synthetic DMT (N,Ndimetyltryptamine) to intentionally contact “machine elves”
and explore parallel worlds: “What is driving religious feeling today is a wish for contact with
this other universe."
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
221
Arguing for their radical “otherness,” McKenna emphasized that the hyperspace aliens seen
while using DMT present themselves "with information that is not drawn from the personal
history of the individual." But smoking this synthetic DMT for 'hyperspace experience' rarely
yields Clear Light experiences.
The Harma alkaloid "Harmine" is also known as Telepathine and Banisterine. It is a naturally
occurring beta-carboline that is structurally related to harmaline. They stimulate the CNS by
inhibiting the metabolism of serotonin and other monoamines. Telepathine, is an MAO inhibitor,
which parallels the function of Pinoline (a natural MAO Inhibitor) naturally produced by the
Pineal Gland. The combination of the Pineal secreted DMT (Dimethyltriptamine) and the MAO
Inhibitor, Pinoline (Methoxytetrahydrobetacarboline, MeOTHBC) may be responsible for
naturally occurring psychic experiences.
Harmine and harmaline are found in Syrian Rue (3-7% harma alkaloid), and ayahuasca brews
made with DMT sources, bark and leaves of “Pychotriaviridis” or Banisteriopsis caapi vine.
Ayahuasca is the South American sacrament of the Church of Santo Daime and Uniao de
Vegetal (UDV). In this setting, the churches condition the “spiritual” expectations, experiences,
ethics and type of information “received” in the altered state. The visionary state is considered to
be the essence of the shamanic complex.
Shamanic vision differs from hallucination in volition, form and content of thoughts, clarity of
heightened awareness, perception and contextualization. Practitioners have claimed it is for
“analysis”. There is no primary delusional experience. The distinction between self and non-self
is blurred; the notion of causality is affected. Its chemistry probably works as follows:
The primary function of harmala alkaloids in ayahuasca is to allow for the oral activity of DMT
by inhibition of MAO-A, and further permits accumulation of 5-HT and other neurotransmitters.
On their own harmala alkaloids have only weak psychoactive effects (Callaway, 1994) but Kim
et al (1997) found that the harmala alkaloids, which occur in ayahuasca, were the most effective
inhibitors of purified MAO-A. (Callaway, 1994)
The psychedelic effects of ayahuasca probably manifest primarily through the serotonergic
effects of DMT on the CNS and through increased levels of unmetabolised biogenic amines.
Pinoline potentiates the activity of methylated tryptamines and this is the probable mechanism
behind ayahuasca (Callaway, 1994) Investigation of long-term users of ayahuasca showed a
statistically significant difference between control group and users with a higher binding density
in blood platelets of 5-HT uptake sites in the ayahuasca drinkers. This indicates a modulatory
role for pinoline (the endogenous equivalent of ayahuasca) in the CNS. An upregulation of the
serotonergic system is exactly what current antidepressant medications attempt to do, i.e.
increasing synaptic 5-HT by preventing its reuptake. (Callaway, 1994)
Phalaris grass expert, “Johnny Appleseed” brings the finesse of a professional Transpersonal
Psychologist to his experiential shamanic teaching. Phalaris arundinacea and Phalaris aquatica,
as well as Phalaris brachystachys,contain the psychoactive alkaloids N,N-DMT, 5-MeO-DMT,
and 5-OH-DMT. He contends 5-MeO DMT awakens psychic centers by amplifying our
telepathic ability to affect or be receptive to others’ brainwaves through modulating chemistry,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
222
electromagnetic entrainment and standing feedback loops. Plants are mixed in brews with MAO
Inhibitor containing plants (Banasteriopsis Caapi, Syrian Rue etc.), to produce entheogenic
brews that mimic the DMT-Pinoline combination naturally produced by the pineal gland in the
brain.
“For the last ten years I have been doing healing and exploratory sessions with individuals and
small groups. We have occasionally experienced the phenomena of telepathy, ESP, and
interactions on an energetic level that produce healing in a number of modalities. I work only
with a strain of Phalaris grass, an entheogen specifically bred to contain 5-MeO DMT. I use this
in an oral preparation potentiated by MAOI from Syrian Rue. This is not a common mix, as most
people smoke it for a blast, which is not conducive to this work. I feel all of the other materials
mentioned, LSD, mushrooms, and DMT-based brews distort consciousness to some degree.
Oral-based 5-MeO DMT from plant sources is something completely different, however. Traces
of other alkaloids from the plant source produce a more enhanced experience than the pure
chemical. A clear yet enhanced state is accessible easily and reliably with no delusional
ideation, or visual distortions.
It is simply like being fully awake. This is probably because we were born with, and until puberty
had, a pineal gland that made 5-MeO DMT in quite substantial amounts, unlike the reports of
only very trace amounts of endogenous DMT. Thus, we have the receptors and metabolic
pathways to deal with this material in a non-distorting way.” (Appleseed, private
correspondence, 2001).
The pineal gland makes a neurohormone called melatonin, which is one of the key regulators of
the circadian and seasonal biological rhythms. It also makes a mono-amine oxidase (MAO)
inhibitor called pinoline (Methoxytetrahydrobetacarboline (MeOTHBC)) which acts on the
GABA receptors and whose chemical structure is virtually identical with the harmala alkaloids.
Serotonin (5 Hydroxytryptamine (5HT)) has frequently been implicated in certain aspects of
psychoses.
Pinoline is a neuromodulator, which prevents, amongst other effects, the breakdown of serotonin.
This results in an accumulation of physiologically active amines including dimethyltryptamine
(DMT) within the neuronal synapses, which may lead to hallucinations, depression or mania
depending on the amines being affected (Strassman, 1990).
Ananda M. Bosman emphasizes the crucial role of endogenous DMT and sacramental DMT
from Syrian Rue and other potentiating botanicals. The ancients called it Hoama in Persian
(Avesta Veda), Soma in Sanskrit (Rg Veda), the Egyptian Essene, the Sumerian Tree of Life,
Mohammed’s Esphand, the burning bush Asena of Moses, the Gnostic Besa, the Etruscan
Phallaris arundanacia, and the Rue of alchemy.
Syrian Rue was revered because Melatonin's active metabolite Pinoline is oneirogenic and
antidepressant, increasing Serotonin turnover. Lack of Pinoline disturbs our circadian rhythms
and creates depression. Pinoline has been conclusively demonstrated to have no function in
schizophrenia, since test subjects healthy and otherwise, had the same levels of Pinoline.
(Bosman)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
223
The pineal is a superconducting resonator. Ananda claims it potentiates DNA as a
multidimensional transducer of holographic projection, through hadron toroids, and is implicated
in staying youthful. 5meoDMT and DMT act on the T-RNA messengers, which carry out the
protein synthesis for the DNA, or the rebuilding of our body image and organs.
Melatonin is exclusively made in the pineal gland, comprised of the same Tryptophane base
materials as Pinoline. Melatonin induces mitosis. It does this, by sending a small electrical signal
up the double helix of the DNA, which instigates an 8 Hz proton signal that enables the hydrogen
bonds to the stair steps, to zip open, and the DNA can replicate. The human Pineal gland not
only produces the neuro-hormone ,elatonin, one of the body's most potent antioxidents, but the
revolutionary Pinoline, 6-methoxy-tetra-dydro-beta carboline, or 6-MeO-THBC.
Pinoline is superior to Melatonin in aiding DNA replication. Pinoline can make superconductive
elements within the body. It encourages cell division by resonating with the very pulse of life - 8
cycles per second - the pulse DNA uses to replicate and the primary Schumann Resonance.
Andrea Puharich measured this 8 Hz resonance in healers in the late 1970s.
Ananda implicates DMT in the hyperdimensional geometry or architecture operating in DNA
through hadronic mechanics, a model of the 8 Hz, or universal phase-conjugational force, that is
also the most coherent Nuclear Magnetic Resonance and the DNA replication frequency. He
relates this to the sacred geometry of the Merkabah, Flower of Life, Sri Yantra, Diamond Body,
and Vector Equilibrium Matrix.
The living DNA in our bodies operates in the hyperdimensions of wave-genetics. The entire
body holographic message is present in the single DNA molecule, in order to be capable of
reproducing the entire whole. The local 8 Hz field component is a standard tetrahedron
interlocked with a second tetrahedron representing the counter-rotary field that it is phaseconjugating with, which together comprise a “stellated cube.”
Ananda has also investigated Dark Room techniques for stimulating the pineal with chi master,
Mantak Chia. Ananda developed, researched, and has taught the Dark Room technology for
endogenous Pineal Soma and DMT production (Endohuasca), since 1992, upgrading his
technique with Master Chia in 2000. Isolated from external light, the third eye (pineal gland)
overflows with certain neurotransmitters that awaken the higher brain, the ability to imprint the
brain, reprogramming itself for an “instant experience of Being.”
The retreat claims to reopen the source code of embryogenesis. 5-MEO-DMT activates the
whole spine, the whole tree of life (Djedi, the staff of Hermes, the Caduceus of the spine)
becomes active to be reprogrammed. This is the accessing and awakening of the tree of life, the
kundalini, which is a readout of the DNA. DNA itself is a minute tree of life.[See “Pitch Black”,
below]
In The Unity Keys of Emmanuel and Somajetics, Ananda says, “[By the DMT translation of the
Sound of Silence of the Word into the Soul Computer Virtual Reality Interface, the parallel
quantum bodies are thus accessed by the NMDA inhibition, which is electrical anesthesia,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
224
engaged by the heart ecstasis of 8 hz, to the 1000 hz petaled lotus. [This] is the learned means of
NMDA inhibition, engaged through the cave and dark room retreats of inner re-engagement.
Thus the chemical soul’s crystal laser transducers and interdimensional door keys, are in Soma
Harmaline-Pinoline-Harmine, DMT and 5-MeO-DMT, and by the NMDA inhibitors through
ecstasis.”
“A high spin state within the DNA water molecule harnessed by Pinoline/Soma intercalating
with the DNA (a molecule that has a stable 8hz NMR proton-proton spin-spin coupling [thus
hadron pi-meson interplay), together with N-Methl-D-Aspartate-Inhibitors enables the electron
states to move into a nulling, and electron freeze within an entire cell, enabling only 8 hz fields
to pass through, changing the charge of the cell, so that the superconductivity harnessed by the
pinoline DNA intercalation (with sonic interaction of the vocalized DNA electron spin resonance
tones) — enables the hadronic force to be able to operate within the macro region of an entire
cell (and intercellularly, by extension).”
Furthermore, noradrenaline plays a significant role in the Pineal gland, when there is sufficient
Pinoline saturation in the brain. It releases a serotonin site, enabling another serotonin site on the
pineal gland to produce the potent visionary Dimethyltryhptamine (DMT), neurotransmitter.
Dr. James Callaway detected this molecule in the spinal serum of people who were dying, or
were having an "Out of body experience (OOBE)", or who were lucid dreaming. It is Pinoline
that enables the threshold levels of DMT to become active in the brain, but it requires an
adrenaline burst. DMT with Pinoline increases brain activation, and with its cousin the 5Methoxy-DMT, has been shown to activate the brain by as much as 40%, compared to our 10%
maximum potential at present. This is a frightening prospect for the uninitiated, due to the
absolutely overwhelming nature of DMT.
Youthenize Yourself
Hollywood trainer to the stars, Barry Hostetler, P.I. advocates “Youthenizing”, claiming his 35
years of bodybuilding and meditating allows him to “kick out the DMT.” We can control our
psychobiology by controlling our mental state and vice versa, especially the reactive “dragon
brain” or “reptilian brain”. Paramahansa Yogananda taught, “If you are in a dark room, don’t
beat at the darkness with a stick, but rather try to turn on the light!”
Under stress we release toxic catabolites into our system, which undermine the immune system
and age us faster. Without exercise (aerobic, core, strength) poisons accumulate, making the
body toxic and mind frustrated and agitated. When we are calm and balanced, body chemistry is
nontoxic and immune function improves.
Meditation is an alpha brain wave entrainment technique, which synchronizes the two brain
hemispheres into 8 Hz. Closing the eyes, stops Melatonin flow leakage to the body, and makes it
saturate the neocortex, increasing concentrations of Meltaonin and Pinoline in both brain and
body. Meditation, several times a day, is an essential health exercise, an energizer, and tool for
mental integration of daily activities.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
225
Pinoline and related beta carbolines are not only produced in the brain, but in the adrenal glands
themselves, where these hormones undergo their transformation to the hormones of life.
HeartMath Institute demonstrated that minutes of compassion in the cardio-rhythm, which
induces 8 Hz in the brain, brought DHEA up to youthful levels.
Twenty minutes of compassionate love, through meditative breathing, and whole body 8
Hz entrainment is the ultimate hormone precursor anti-aging pill. Not only does the pineal gland
produce more Melatonin and Pinoline, which instigate 8 Hz ELF waves throughout the body, but
these neurohormones signal the pituitary to release the life hormone Somatropin, which signals
the adrenal glands to instigate cholesterol to convert to Pregnelenone then DHEA.
The extra Pinoline and other beta carboline levels that result, aid the body cells to replicate, and
neutralize microorganisms, parasites, fungoids, and bacterias, and related harmful invaders.
Melatonin and Pinoline are also antioxidents. Meditation is a rest break, an exercise session, an
integration session, an energizer, and a body tuner, promoting antioxidant and antidepressant
production. This makes meditation valuable for stress-management and simple self-care.
We can return intentionally to more youthful states by doing emotional exercises and
visualizations, which stimulate the body chemistry of our glory days. The body remembers and
mimics those chemical states, producing youthful hormones and more flexible mental and
physical states, improving overall balance and disposition. When “Youthenizing” yourself, it is
helpful to use a photo from under age 7, a time you felt at your peak, or your happiest, or other
'good chemistry' times.
Kinesiology demonstrates that the mind "thinks" with the body itself. Mindbody is the subtle
mechanism behind the disease process. The chemistry you generate with moods and states in
your body is crucial to your health and well being. First toxic states of mind affect the energy
body, then the physical body. Subjective and objective experience are hidden determinates of
behavior. Embodied as corporeal memory, the body is your memory and subconscious. Selfregulation can modulate this process.
The body is an island of energy/matter and emotions with waves of feelings crashing onto its
shores. Body-consciousness can either hide or reveal spirit, depending on how we direct our
attention toward our ego, stress (including spiritual distress) and relief. The body and mind can
be reunited in a congruent, healthy lifestyle by acting on what you know.
Pitch Black
Absolute darkness has an initiatory quality – the metaphor of moving from the darkness of
ignorance into the illuminative Light. But it is more than a metaphor. All wisdom traditions have
used sensory deprivation and darkness, (such as caves, tunnels, catacombs or special chambers),
as a shamanic mind-altering force. Disorientation outside facilitates internal focus and
connection. Dark Room (DR) technology is for core reprogramming, restimulating the hardened
pineal which begins calcifying around age 12. Sound becomes light. Chanting and drumming
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
226
amplify the effects, which culminate in a rebirth of the spirit when one enters the point of Light
or primordial Luminosity.
Author, Robert Newman, (Calm Healing, 2006) advocates Medicine Light for a variety of
conditions. He cites Tibetan Buddhist, Trungpa Rinpoche about a highly advanced, dangerous
form of meditation practiced in utter darkness, known as a Bardo Retreat. They last up to seven
weeks in a specially prepared Darkness Chamber, during which the whole Tibetan Book of the
Dead is experienced and visions arise innately from the brain. The beneficent and wrathful “eyes
of Buddha” become visually and interactively alive as the Bardo of Luminosity flashes on and
off; visions are self-arising; and transcend ordinary perception. The 49-day cycle recapitulates
embryogenesis up to the point when pineal and gender differentiation occurs. The Taoists,
Egyptians, Druids and others had similar practices of external light isolation.
Taoist master, Mantak Chia of Thailand recommends sound and light isolation in a process he
calls Darkroom Enlightenment. He sequesters participants in the dark for over a week to shock
the pineal into critical arousal to stimulate production of natural DMT and break down the
barriers to transcendence. The neurotransmitter 5-MeO-DMT is normally only active when we
are in the womb and in the first months of our lives. It is reactivated in the darkroom.
Stages include the ‘Melatonin state (Day 1-3; ego death), Pinoline State (Day 3-5; energy body
and astral projection; lucid dreaming), 5-MeO-DMT (Day 6-8; telepathy, White Light),
culminating in illuminative DMT (Day 9-12; Clear Light; Immortal Body). Participants leave
through a tunnel, presumably a symbolic rebirth.
“There is now enough 'Mono Amine Oxidase Inhibition' triggered by the pinoline, to allow the
pineal gland's 'serotonin to melatonin cycle' to be intercepted by adrenaline and ephedrine
activity and converted into a 'serotonin - DMT pathway'. When DMT levels reach more than
25mg, one's experience can become very visual. DMT is the visual third eye neurotransmitter. It
enables the energy body and spirit to journey into hyperspace, beyond third dimensional realms
of time and space.” (Chia, 2006)
Reentry implies rebirth -- the self-organizing emergence of the new self. The seed of initiation is
realized as the mature fruit of experience, which feeds and sustains us. The experience continues
to be useful in our lives. Each healing journey is the death of something within us, which has
kept us stuck or stultified. Healing facilitates our continuing evolution. The new self continues to
emerge and the consequences of the journey become embodied in this new form for months and
even years after the journey. New behaviors, feelings, attitudes, ideas, and wisdom follow. Thus,
the circle of life continues unbroken.
Entheogen expert, K. Trout (2001, correspondence) is skeptical: “I'll ignore the shakiness of
their biochemical presentation but to arrive at DMT from melatonin or a betacarboline starting
point would be interesting if not fanciful under physiological conditions. It is much more likely
that formation of endogenous DMT would be instead of melatonin rather than from it or into it
(and the two paths mutually preclusive similar to what we see in plants as concerns DMT and 5MeO-DMT synthesis even when the two co-occur). Now to go from melatonin to a 6ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
227
methoxylated-betacarboline with psychoactivity on the other hand is not at all far fetched if an
appropriate enzyme exists and was present”.
The Biology of the Inner Light
Melatonin and pinoline, made by the pineal gland are regulated by the seasonal changes in light
and darkness, linked to the sleep/wake cycle. Pinoline is made in the pineal from 5HT and
hypothesized as the neurochemical trigger for dreaming. Lack of sleep for several nights is often
linked to the onset of acute psychotic breakdown in which the person starts hallucinating or
“dreaming while awake.” This state of consciousness is common to the dream state, the
psychedelic state, and the shamanic initiation experience. (Roney-Dougal)
Illumination has been described as being blinded by the manifestation of God’s presence. This
brightness has no relation to any visible light. Visionary experience, which has symbolic or
religious content, may give way to this dazzling light, which is reported in eastern and western
religions. It can confer a palpable glow to the person that is perceptible after the return to
ordinary awareness.
Meditation modulates pineal activity, to create a standing wave through resonance effects that
affects other brain centers with both chemical and electromagnetic coordination. Resonance can
be induced in the pineal using electric, magnetic, or sound energy. Such harmonization
resynchronizes both hemispheres of the brain. This results in a chain of synergetic activity
resulting in the production and release of hallucinogenic compounds.
Sacred images are generated by the lower temporal area which also responds to ritual imagery,
facilitated by prayer and meditation. Religious emotions originate from the middle temporal lobe
and are linked to emotional aspects of religious experience, such as joy and awe. Yet neural
correlates don't mean that these experiences exist "only" in the brain or are merely illusory; they
are associated with distinct neural activity. There is no way to distinguish if the brain causes
these experiences, or actually perceives spiritual reality. Visions of bright lights, portals, and
spiritual icons correlate with DMT.
"Could it be that human beings have actually evolved specialized neural circuitry for the sole
purpose of mediating religious experience?" Neurologist Ramachandran says so. "There may be
certain neural pathways—neural structures in the temporal lobe and the limbic system—whose
activity makes you more prone to religious belief.”
If this is true, it is easy to see how much this mind-altering chemical could amplify all of the
tendencies toward mystical apprehension originating in other parts of the brain.
The pineal contains high levels of the enzymes and building blocks for making DMT, and it may
be secreted when inhibitory processes cease blocking its production. It may even produce other
chemicals, such as beta-carbolines that magnify and prolong its effects.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
228
Clear Light
Illumination has been described as being blinded by the manifestation of God’s presence, which
has no relation to visible light. Visionary experience, which has symbolic or religious content,
gives way to this dazzling light, which is reported in eastern and western religions. Sacred Light
is generated internally by DMT within the ventricles. Tendencies toward mystical apprehension
originating in other parts of the brain are amplified. This universal Clear Light appears in all
cultures with different names.
The mindbody is electronic, but it is rooted in the luminosity of its invisible ground. Living
systems are very sensitive to tiny energy fields and resonance phenomena, both locally and at a
distance. They allow the cells of the body to work together instantaneously and symphonically.
All biological processes are a function of electromagnetic field interactions. EM fields are the
connecting link between the world of form and resonant patterns. EM fields embody or store
gestalts, patterns of information. Biochemical action and bioelectronic action meet at the
quantum-junction.
We can return to Nature and our nature, collectively preparing a paradigm shift for a new shared
reality and trajectory of physical, emotional, cognitive and spiritual coherence. The silent
frictionless flow of living intelligence is beyond words and conceptual constructs. We are a
process of recursive self-generation. This continuum, which is our groundstate or creative
Source, is directly discoverable in the immediacy of the emergent embodied moment, in the
living Light that generates our Being.
Blinded by the Light
Kabbalalists speak of this mystic Light during ecstatic entry into Pardes, the "orchard" of the
Garden of Pomegranates, the self-luminous spheres of the Tree of Life. This metaphysical
experience of the "Light of the Shekinah," the feminine aspect of the Divine, is associated with
qabalistic ascent up the Middle Pillar. In this state the soul remains covered or adorned, and one
cleaves to the Light, gazing at the awesome radiance of God (Tzvi ha Shekinah) in rapt mystic
Union.
According to Kabbalist Idel, the grace of "sweet radiance" has erotic overtones. It also implies
mystical death, separated from all concerns with the mundane world. The Divine Light attracts
the light of the soul, "which is weak in relation to the Divine Light." The metaphor is one of
magnetic attraction. The Kabbalists tried to reach the pre-fall state of the Primordial Man, to
reenter the radiance of the Shekinah, a mystically erotic relationship with the Divine Presence
which creates a reflective “glow.”
Entrance of the philosopher or mystic into the Pardes affects only the human soul. But in the
Theosophical paradigm it does have affects on the non-human realms, the system of divine
powers, influencing the relationships between them. In the Theurgic paradigm there is also an
influence on, or struggle with, the demonic realm, which seeks to hold the soul back from union.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
229
In both cases, Pardes represents a danger zone, leading potentially to insanity or death, being
overwhelming for most mortals. Premature entry to this realm has been likened to tearing a silk
scarf from a rosebush, rather than gently removing it slowly (with regular meditation). It sounds
like the wrathful visions of Buddhism and the intensely raw effects of unmediated DMT.
Yogatronics
Want to take an active role in your own spiritual life, a safe and easy mind trip? Would you like
to glimpse some of the experiences outlined here? Or even just get the mental health benefits of
deep relaxation and increased inner focus? Intimidated by the prospect of spending 15 to 20
years learning to meditate to attain life-enhancing benefits?
Haven’t had a near-death experience and don’t want one? Too busy to devote your life to
alchemy, or spend endless years in transpersonal therapies, or too afraid to allow a “mad
scientist” to zap your brain with EM frequencies, hook your brain up to a high-tech scanning
machine, or inject you with psychedelic substances?
Modern technology offers an easy Do It Yourself, “passive” alternative. Anyone can employ a
safe and easy technique that automatically puts you in the “zone.” A form of “yogatronics” is
available using a simple CD and headphones with input from subsonic frequencies. This audio
technology creates a harmonization of the left and right hemispheres of the brain, and
automatically drives the brain harmlessly into the Alpha or Theta brainwave range.
This resonance phenomenon, entrainment, is called the frequency-following response, or
binaural beat technology. Entrainment is the process of synchronization, where vibrations of one
object will cause another to oscillate at the same rate. It works by embedding two different tones
in a stereo background. Continuous tones of subtly different frequencies (such as 100 and 108
cycles per second) are delivered to each ear independently via stereo headphones. The tones
combine in a pulsing “wah wah” tone.
External rhythms can have a direct effect on the psychology and physiology of the listener. The
brain effortlessly begins resonating at the same rate as the difference between the two tones,
ideally in the 4-13 Hz. (Theta and Alpha) range for meditation. All you have to do is sit quietly
and put on the headphones. The brain automatically responds to certain frequencies, behaving
like a resonator.
You may not become immediately enlightened, but hemispheric synchronization helps with a
whole host of problems stemming from abnormal hemispheric asymmetries. Problems, often
resulting from stress or abuse in early life, include REM sleep problems, narcissism, addictive
and self-defeating behaviors. Communication between hemispheres correlates with flashes of
insight, wisdom and creativity.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
230
Brain Synch
Our brain’s two hemispheres are meant to work in concert with one another. Interactive
hemispheric feedback is used to treat disorders such as post-traumatic stress disorder (PTSD),
depression, ADD, addiction, obsessive-compulsive disorder, anxiety, and numerous other
dysfunctions. Disorders of under-arousal include depression, attention-deficit disorder (ADD),
chronic pain and insomnia. Overarousal includes anxiety disorders, problems getting to sleep,
nightmares, ADHD, hypervigilance, impulsive behavior, anger/aggression, agitated depression,
chronic nerve pain, and spasticity.
Because the brain is functionally “plastic” in nature, creating and exercising new neural
pathways can retrain neural circuitry. In meditation, the halves of the brain become
synchronized and exhibit nearly identical patterns of large, slow brainwaves. Rhythmic pulses
can modulate collective neuronal synchrony. Then, both lobes automatically play in concert.
Rhythm regulates the entire spectrum of activation and arousal by kindling, or pulling more and
more parts of the brain into the process. Disorders related to under- and over- arousal, including
attentional and emotional problems, can be stabilized by self-organizing restructuring.
Depressions, anxiety, worry, fear, and panic can be moderated. Stimulating neglected neural
circuitry creates new pathways, improving equilibrium and long-term change, essentially
“tuning” the nervous system.
There are many companies branding this self-regulation technology, both in “active” clinical
neurofeedback programs, and as “passive” home programs. Among the oldest is the Monroe
Institute <monroeinstitute.org>, which calls its trademarked method Hemi-Synch. Another
program offered by Centerpointe Research Institute <centerpointe.com> is called Holosynch.
BioPulse is another. Another variation uses light pulses from goggles to drive the process, and is
marketed as Alpha-Stim.
Discussion
As of 2012, Barker and his colleagues at Cottonwood Research Foundation, Inc. upgraded their
trials and protocols to determine the role of endogenous hallucinogens. They improved their
measurement and low-level identification methodology a thousand-fold over previous attempts,
using state-of-the-art liquid chromatography-mass spectrometry (LC/MS) equipment and
claimed to meet their research goals.
They measured the three known endogenous hallucinogens and their major N-oxide metabolites
in blood, urine, cerebrospinal fluid, ocular fluid and/or other tissues to fully assess the status of
an endogenous hallucinogen pathway. They confirmed the structural identity of a major
metabolite (the N-oxide) that has never before been monitored in any endogenous hallucinogen
study in humans.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
231
Their ayahuasca studies showed "a major metabolite of DMT, DMT-N-oxide (which retains the
identifying structure of the parent substance), being excreted in the urine at levels 10-20 times
greater than DMT itself after ayahuasca administration. Similarly, N-oxide levels in blood were
four times greater than DMT. They note, “This is the first time this metabolite has been reported
in humans following DMT administration by any route."
They are confident continuing studies will determine the normal role and function of these
compounds in non-drug induced altered states, including dreams, psychosis, meditation, religious
experience, childbirth, and near-death states. They cite Cozzi et al., stating that "the enzyme
responsible for synthesis of the endogenous hallucinogens is present in pineal gland, brain, spinal
cord and retinal tissues of primates and appears to be an inducible enzyme, an enzyme that
responds to specific signals. Therefore, clearly establishing the role of endogenous tryptamine
hallucinogens in various states of consciousness will provide tremendous insight into their
origin, and may lead to more reliable means of working with and studying their utility".
Conclusions
Are there things we should not know? We are innately geared to crave ecstasy, “escape reality,”
and seek extraordinary or novel experiences on our way to wisdom. The history of mankind
recounts the stages of that journey. Religions, mystery schools, and mysticism arose from
accounts of spontaneous spiritual experiences. In shamanism, our ancestors sought them in an
instinctual or animalistic way. In art, myth and ritual we sought them in a human, if narcissistic
and self-expressive reactionary way.
Curiously, DMT is ubiquitous in the biosphere, found everywhere from a variety of botanicals to
mammals: It has been documented in rat brains at birth. Not only is it found in seaweed, flowers,
vines, acacia tree (Sant), toadskins, Desmanthus illinoensis and Mimosa hostilis, A. columbrina,
lawn grass, etc., but also in our brains and spinal columns.
"It is only in Western society that the potential shaman, with all of their psychic gifts, is ignored
and treated as sick. All other human societies have honored their prophets, psychics, seers and
shamans. We need to learn to recognize the potential shaman in our midst and re-learn what is
required to ground them, teach them and train them so that their creative and psychic abilities
can be a gift, not a curse, and can be used for their and our benefit." (Roney-Dougal)
In creativity and meditation we seek in a fully conscious way, willfully cooperating and
facilitating the process not only of connecting with the divine, but experiencing ourselves in the
process of “becoming” divine or being sacred. The ego no longer perceives itself as a separate
expression of consciousness, but reconnects in a stabilized, not sporadic way. Our metaprogram
is the same essence as All, infused with Light.
References
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
232
Abraham, Ralph, 2006, Recollections of the impact of the psychedelic revolution on the history of
mathematics and my personal story. http://www.ralph-abraham.org/articles/MS%23124.Maps/maps2.pdf
Baconnier, Lang et al., Some thoughts on the paper: Calcite Microcrystals in the Pineal Gland of the
Human Brain, First Physical and Chemical Studies, Bioelectromagnetics 23:488495 (2002).
Biolectromagnetic Crystals in the Pineal May Be Resonant Piezoelectrics.
Barker, S.A., Ethan H. McIlhenny, Rick Strassman, 2012, A Critical Review of Reports of Endogenous
Psychedelic N, N-Dimethyltryptamines in Humans: 1955-2010, Drug Testing and Analysis, in press
(invited paper in Special Issue on Psychedelic Drugs).
Bosman, Ananda, Pineal Power, http://www.akasha.de/~aton/PINEALpower.html
Callaway, J.C. (1994). Pinoline and Other Tryptamine Derivatives: Formations and functions. PhD
Dissertation, Dept. Pharmacol. & Toxicol, Univ. Kuopio, Finland
Chia, Mantak, (2002), Dark Room Enlightenment, Universal Tao Center, Thailand,
http://www.scribd.com/doc/4474044/Dark-Room-Enlightenment-Mantak-Chia
Collected Abstracts, Scientific Evidence of Psychedelic Body Fluids,
http://deoxy.org/annex/daytripr.htm#5
Cozzi, N.V., T. A. Mavlyutov, M. A. Thompson, A. E. Ruoho. Indolethylamine N-methyltransferase
expression in primate nervous tissue. Soc. Neurosci. Abs. 2011, 37, 840.19 (2011)
Graves, Robert, (1948) The White Goddess: A Historical Grammar of Poetic Myth.
Journal of Pineal Research http://www.blackwellpublishing.com/journal.asp?ref=0742-3098
Grof, Stanislav, (1988), The Adventure Of Self-Discovery: Dimensions of Consciousness And New
Perspectives In Psychotherapy, State Univ of New York Pr.
Korkmaz, Ahmet and Russel J. Reiter, (2007), Epigenetic regulation: a new research area for melatonin?,
Journal of Pineal ResearchVolume 44, Issue 1, Article first published online: 26 OCT 2007.
McIlhenny, Ethan H., Jordi Riba, Manel J. Barbanoj, Rick Strassman, and S.A. Barker, 2012,
Methodology for the Determination of Ayahuasca’s Major Constituents and Their Metabolites in Blood,
Journal of Biomedical Chromatography, Published online 2011, Jun 28. doi: 10.1002/bmc.1657.
McIlhenny, Ethan H., Jordi Riba, Manel J. Barbanoj, Rick Strassman, and S.A. Barker, 2011,
Methodology for and the Determination of the Major Constituents and Metabolites of the Amazonian
Botanical Medicine Ayahuasca in Human Urine, J. Biomed. Chromatogr. 25, 970-984.
McKenna, Terence; Food of the Gods; New York: Bantam Books, 1993.
Meyer, Peter (1993), “Apparent communication with discarnate entities induce by DMT”, Psychedelic
Monographs & Essays, Vol. 6, Thom Lyttle, Ed., PM & E Publishing Group, Boynton Beach, Florida.
Miller, Iona; "Chaos as the Universal Solvent: Re-creational ego death in psychedelic consciousness";
Psychedelics ReImagined, Thom Lyttle, Ed. New York: Autonomedia, 1999.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| March 2013 | Volume 4 | Issue 2 | pp. 214-233
Miller, I., Pineal Gland, DMT & Altered State of Consciousness
233
Miller, Iona (1994) Becoming the Vine: An Anecdotal Account of an Ayahuasca Initiation
Miller, Iona (2001), Neurotheology101: Technoshamanism and Our Innate Capacity for Spiritual or
Mystical Experience, Institute for Consciousness Science & Technology, Wilderville, Oregon.
Miller, Iona (2006), How the Brain Creates God: The Emerging Science of Neurotheology, Chaosophy,
Asklepia Pub. http://neurotheology.50megs.com
Pickover, Cliff (2006) http://sprott.physics.wisc.edu/Pickover/pc/dmt.html
Radha, Soami Sivananda (1990) The Divine Light Invocation; Timeless Books, Spokane, Washington.
Riba, Jordi, Ethan H. McIlhenny, Marta Valle, José Carlos Bouso S. A. Barker, 2012, Metabolism and
disposition of N,N-dimethyltryptamine and harmala alkaloids after oral administration of ayahuasca,
Drug Testing and Analysis, submitted (invited paper in Special Issue on Psychedelic Drugs).
Roney-Dougal, Serena, Walking Between the Worlds: Links Between Psi, Psychedelics, Shamanism, and
Psychosis.
Sabom, M. B. (1982). Recollections of death: a medical investigation. Harper and Row, New York.
Santoro, R.., Marani, G Blandino, P Muti and S Strano, (2012) Melatonin triggers p53Ser
phosphorylation and prevents DNA damage accumulation, Oncogene 31, 2931-2942 (14 June 2012) |
doi:10.1038/onc.2011.469
Strassman, Rick (1990), “The Pineal Gland”, Psychedelic Monographs & Essays, Vol. 5, Thom Lyttle,
Ed., PM & E Publishing Group, Boynton Beach, Florida
Strassman, Rick (2001). DMT: The Spirit Molecule. Rochester, Vermont: Park St. Press.
http://www.rickstrassman.com
Szára, Stephen, The Social Chemistry of Discovery: The DMT Story. (1989)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
A Note on Relative Consciousness
Kynan Eng
Institute of Neuroinformatics, University of Zurich and ETH Zurich
Abstract
This paper describes a mathematical formulation for measuring how one system can estimate the
consciousness of another. This consciousness estimate is always relative to the observer. The paper
shows how this formulation leads to simple resolutions of some key problems of consciousness.
Introduction
Many discussions of the concept of consciousness implicitly or explicitly assume the existence of
consciousness as a real “quantity” or “thing”. One form that this belief takes is in the idea of
panpsychism (Chalmers 2015), in which all fundamental particles have a mental state. A somewhat
weaker or agnostic version of this belief postulates that while consciousness is possibly a “real” thing,
it is hard (or impossible?) to be measured directly. However, supporters of this idea suggest that it is
possible to gain an approximate measure of consciousness by correlative means, i.e. neural correlates
of consciousness (NCC) (Chalmers 2000).
The idea of consciousness as a real thing, whether pervasive or not directly measurable, may have some
echoes in the long-abandoned search for the luminiferous æther for electromagnetic phenomena (Dirac
1951). Current attempts to quantify consciousness also suffer from problems in achieving universality,
in particular in encompassing many levels of system complexity (for example, humans versus insects).
I propose that the attempt to find a universal NCC or panpsychic definition of consciousness is either
ill-placed or doomed to fail. Instead, we can consider an alternative way of thinking about consciousness
with the following base assumptions:
•
•
•
Any measurement of consciousness must occur with a nominated observer and subject. There
is no such thing as absolute consciousness without either of these two elements.
Any measure of consciousness is always in the frame of reference of the observer. There is no
absolute observer.
Any measurement of consciousness occurs at a certain point in time. It is valid only for that
measurement, and may change over time as the observer evolves.
The rest of this note concerns a formulation of these principles, by synthesizing some concepts of
information transmission and complexity. This is followed by some commentary on what these
principles mean in the light of some classical conundrums in consciousness research.
Eng K
A Note on Relative Consciousness (2021)
Page 1
Formulation
Consider an agent B, observing another agent A. B wishes to ascertain the consciousness of A. B
observes A, and thus B receives a certain amount of information 𝐼𝐵𝐴 from A. We denote the result of
this process as B’s consciousness of A, i.e. 𝐶𝐵𝐴 . Note that this consciousness 𝐶𝐵𝐴 . is local to B.
To obtain and internally represent 𝐶𝐵𝐴 , B must have a certain set of attributes:
•
•
•
an ability to observe A, i.e. to receive information transmitted from A;
a level of ability to create and process a model of A within itself, which we shall call a schema
b;
(optionally, an ability to perturb A, i.e. send information to A)
In information theory terms, this is a problem in which B attempts to infer the internal structure of A,
based on observed information about A. B has a certain internal schema b, which is smaller than or
equal to B, to create and sustain a given level of consciousness of A.
We describe the overall process as follows (Figure 1):
𝑏
𝐶𝐵𝐴
= 𝑏(𝐼𝐵𝐴 )
Without loss of generality, B may have more than one schema b1, b2, … for creating different estimates
𝑏1 𝑏2
of the consciousness of A, i.e. 𝐶𝐵𝐴
, 𝐶𝐵𝐴 , …
Figure 1: Relative consciousness observation process.
It is important to note that the schema b is not just a process or algorithm, but also a set of priors encoded
either explicitly or in the algorithm of b itself. This implies that it is entirely possible that if B is using
the wrong b and not “looking” at A in the “right” way, it could receive a result of zero.
𝑏
Note that the observations may be discrete, batched, or time-continuous, i.e. 𝐼𝐵𝐴
(𝑡). Similarly, the
𝑏
schema may also vary with time b(t), leading to time-varying estimates of consciousness 𝐶𝐵𝐴
(𝑡).
Now, given 𝐼𝐵𝐴 , there may be ways to estimate certain bounds on B, i.e. the requirements for B to have
obtained the information 𝐼𝐵𝐴 . One way to do this, for example, could be to use a complexity measure.
Corollaries and Predictions
The formulation proposed above leads to a number of corollaries and predictions, including the
following:
•
•
Eng K
The maximum complexity of 𝐶𝐵𝐴 , i.e. the internal consciousness model of A constructed by B,
is affected by the chosen schema b.
Any system B cannot be fully consciousness of itself, i.e. 𝐶𝐵𝐵 is not observable, because then
b would be equal to or larger than B. However, B can be conscious of parts of itself, i.e. 𝐶𝐵𝑑
may be observable, where dB, dB.
A Note on Relative Consciousness (2021)
Page 2
•
•
•
Any system B cannot be fully conscious of another structurally similar system B’, where
structural similarity is defined as equivalent complexity. We will define B’ as a peer system. In
𝑏
other words, 𝐶𝐵𝐵′ is not observable in the general case. However, 𝐶𝐵𝐵′
may be observable,
because B has selected some simplified schema b for its observations (bB, bB).
Any system B which is contained inside a larger system D (BD) could be conscious of D, as
long as the selected schema b is sufficiently simple.
Any system B can be conscious of what another system D is conscious of when observing A,
𝑏,𝑑
i.e. 𝐶𝐵𝐷,𝐷𝐴
= 𝑏(𝑑(𝐼𝐷𝐴 )) may exist, as long as b can encode d. Note that d may not be directly
observable in D. In the limiting case, however, d = D and 𝑏(𝐷(𝐼𝐷𝐴 )) may exist.
Discussion
Given the preceding formulation, one can make a number of statements about classical problems in
consciousness research:
That was a trick. 𝐶𝐵𝐴 says nothing about the consciousness of A.
That is partly correct, but only if one assumes that A has an absolute consciousness. The present
formulation says only a limited amount about the consciousness of A, in that it must have been complex
enough to encode 𝐼𝐵𝐴 . However, it also says something about the consciousness of A, as observed by
B, and the structure of the schema used by B. This is a joint relative consciousness. To borrow a term
from quantum physics, the consciousness of A could be said to be entangled with its observation by B.
In everyday language, the following statement could be made: just because one did not understand the
level of consciousness of another being, it didn’t mean that it wasn’t always there. Any newly reported
level of consciousness says as much (if not more) about the observer as it does about the subject under
observation.
What about the Chinese Room problem?
Searle’s Chinese Room thought experiment (Searle 1982) asserts that a computer cannot have “strong
AI”, i.e. a true “mind” in the same way as a human, because it is just following instructions without any
true “understanding”. What is not usually stated in the formulation of this problem, but is a key hidden
assumption, is that a human H can understand its own consciousness, i.e. 𝐶𝐻𝐻′ is observable. We have
already seen before that this is not possible in the general case, unless one chooses a simplified schema
h to observe H’. Hence the problem is ill-posed due to an incorrect assumption.
What about qualia?
The relative consciousness formulation does not exclude the possibility of transferable qualia
(Stubenberg 1998, Jackson 1982), i.e. 𝐶𝐵𝐴 = 𝐶𝐷𝐴 . However, observing such an equivalence requires
another observer that is able to encode both B and D, at the level of complexity required for both B and
D to make their observations of A. This third observer cannot be B or D, because B and D alone cannot
encode sufficiently complex representations of themselves observing A. Thus B or D cannot conclude
that their qualia are in fact the same thing.
What about artificial general intelligence?
The definition does not exclude the possibility of a machine matching human intelligence (which, for
the purpose of this discussion, we define as being correspondingly equivalent to consciousness). What
it does exclude, however, is the capacity of a human to understand whether or not it is observing a
human-equivalent intelligence. See the Chinese Room problem.
What about panpsychism?
Eng K
A Note on Relative Consciousness (2021)
Page 3
The definition is applicable to any system, and does not exclude the possibility that an observer might
𝑏
describe significant consciousness in everything that it observes, i.e. 𝐶𝐵𝐷
> 0 for all values of D. This
is most likely to occur where b is chosen to be relatively simple, i.e. looking for “microphenomenal
consciousness”.
What about the NCC?
The NCC requires a modification in its formulation to be a valid approach. Instead of the allencompassing “neural correlate of consciousness”, it should be a “neural correlate of consciousness of
X”. For example, the “NCC of self”, the “NCC of the external world”, the “NCC of a moving stimulus”,
the “NCC of a painful stimulus”, etc. Sometimes, X is some part of the external world, while other times
it is some aspect of the system itself. This approach already seems to be followed implicitly by many
researchers; the suggestion here is to make the formulation explicit at all times.
So is consciousness a real thing, or an arbitrary definition?
It is both, in the same way that information is both real (based on physical processes) and arbitrary (one
of many possible definitions depending on the level of description being used).
Is there a maximum speed of consciousness?
Yes, because it is anchored in information, which can in turn be anchored in physical properties.
Can consciousness be transferred?
The question is not posed precisely enough. The question should be: can my consciousness of A be
transferred to my consciousness of B, if I evaluate this consciousness in a certain way? The answer is
generally yes, for certain values of “me”, A, B, and how I am looking at A and B.
Can we be conscious of the universe?
𝑏
Yes, 𝐶𝐵𝑈
can be valid for a universe U, BU, if one chooses a suitably simple schema b.
Further Work
This note aimed to show a formulation of relative consciousness that could be used across a wide variety
of systems. It was also an attempt to cast the discussion of consciousness research in a way that may be
within reach of information theory. Future work could investigate the following:
•
•
Information-theoretic proofs related to the presented formulation
Extending the concept to time series and dynamical systems
Acknowledgments
Thanks to the initiators of the seminar Consciousness: From Philosophy to Neuroscience run at the
University of Zurich and ETH Zurich during the early 2000s (Daniel Kiper, Heather Berlin, and Christof
Koch), for stimulating my interest in the topic. The concepts in this note date back to some of my
thoughts from that period.
Eng K
A Note on Relative Consciousness (2021)
Page 4
References
Chalmers DJ. What is a neural correlate of consciousness. Neural correlates of consciousness: Empirical
and conceptual questions. 2000 Sep:17-39.
Chalmers DJ. Panpsychism and panprotopsychism. Consciousness in the physical world: Perspectives
on Russellian monism. 2015 Apr 1:246-76.
Dirac PAM. Is there an Æther? Nature. 1951 168:906-907.
Jackson F. Epiphenomenal qualia. The Philosophical Quarterly (1950-). 1982 Apr 1;32(127):127-36.
Searle JR. The Chinese room revisited. Behavioral and brain sciences. 1982 Jun;5(2):345-8.
Stubenberg L. Consciousness and qualia. John Benjamins Publishing; 1998.
Eng K
A Note on Relative Consciousness (2021)
Page 5 |
arXiv:quant-ph/0106103v2 15 Jul 2002
Consciousness and Endogenous State
Reduction: Two Experiments
Richard Mould∗
Abstract
There is a tradition in science that regards consciousness as merely
epiphenomenal. Accordingly, physical systems can create and influence
consciousness, but consciousness can have no influence on physical systems. Indeed, the current understanding of quantum mechanics provides
no way for consciousness to alter the wave function of a quantum mechanical state. Furthermore, there is nothing in molecular biology that would
suggest that the human body is anything more that an automaton that
operates on the basis of purely physical and chemical interactive forces.
However, I believe that the epiphenomenal view is fundamentally flawed,
and I suggest the following experiments as a way of demonstrating the
existence of an influence of consciousness on material systems. The first
uses Positron Emission Tomography (PET) with a human subject, and
the second used autoradiography with rats.
Detailed arguments for my position can be found in three papers that
have been published in recent years. A brief summery of the arguments is
initially given below, where it is claimed that ‘pain’ consciousness might
be correlated in a certain way with the relative binding of opiates to
receptors in a subject’s brain.
1. Introduction
In recent papers[1][2][3], I accept the evolutionary argument of William James to
the effect that psychological states must have evolved along with the biological
states[4]. For these two very different kinds of things to have evolved in parallel
with one another (i.e., for one to have anything to do with the other), James says
that there must have been an interaction between the two. Otherwise, wrong
∗ Department
of Physics and Astronomy, State University of New York, Stony Brook,
New York 11794-3800; http://nuclear.physics.sunysb.edu/ ˜mould
1
psychological constructions would not have been selected against, and therefore,
would have improperly survived the evolutionary struggle. If that had been the
case, then any resemblance between the subjective imagery of our species and
the world about us would be completely fortuitous. This argument is given more
fully in ref. 2. It says that the psycho-physical parallelism of von Neumann
must have come about through a natural process in which psychological and
physical states were mutually engaged. Otherwise, one would have to believe
either in Libnitz’s claim of a (miraculous) pre-established harmony between these
two things, or in Bishop Berkeley’s denial that there exists a psycho-physical
parallelism in the first place.
According to von Neumanns interpretation of quantum mechanical measurement, the collapse of the wave function requires the presence of a subjective (i.e.,
conscious) observer[5]. I make use of this idea together with the notion of an
inside observer (initially defined in ref. 1) to show how conscious states arising
within a physical system might conceivably influence the probability amplitude
of quantum mechanical choices made by the system. An inside observer is defined to be a state of conscious awareness that emerges on one component of an
endogenous quantum mechanical superposition of (physiological) states. These
states can be macroscopic in the formalism of quantum mechanics; although, in
deference to environmental entanglement and decoherence, one might call them
“mixtures” instead of “superpositions”. I do not use this language because I
am not concerned here with coherence or interference between macrostate components.1
When different inside observers finally do emerge on different components
of a physiological superposition, I propose that there will be a shift in the
relative probability amplitudes of the components that favors certain conscious
states over others. The principles that govern this leaning toward especially
favored states are described below. I assume that the above shift preserves
normalization.2
1 Environmentally entangled macrostates really are superpositions. Joos and Zeh say, “...
the interference terms still exist, but they are not there.”[6] This paradoxical statement means
that the system’s phases exist between global states that include non-local correlations connecting a macrostate with its environment. These phases are not accessible to a local observer;
and in consequence, the superposition appears locally to be a mixture.[7] But however one
regards such a macrostate ensemble, as a global superposition or as a local mixture, each
component has a probability amplitude in a fully quantum mechanical system. Therefore,
according to von Neumann, a conscious observation is necessary for one of these states to
become a concrete reality.
2 I do not say that this shift among probability amplitudes is caused by the appearance
of consciousness, inasmuch as the underlying influence is revealed only as an empirical rela-
2
This possibility provides us with an opening in quantum mechanics that
may admit the evolutionary influence envisioned by James. What is needed is
a model of some primitive species at the time of its first use of consciousness,
together with an identification of the kind of conscious experience that can influence the creature’s evolution by using the above ‘inside observer’ mechanism.
2. My Hypothesis
I believe that the first conscious experiences that appeared in any evolving
species must have been very straightforward, like simple pleasure or pain. Elemental perceptions involving sight, sound, or touch serve no behavioral purpose
in themselves, for they have no intrinsic motivational weight or direction. These
perceptions must be ‘interpreted’ in order to have significance, and that is too
much to expect of the first glimmer of consciousness. In addition, emotions such
as fear, anger, and love have no intrinsic meaning apart from an existing subjective construction of the world toward which they are directed. This means
that an awareness of either one of these emotions requires a greater sophistication than is required for simple experiences like pleasure or pain. The latter
have a direct ‘unsophisticated’ motivational power that stands apart from any
concept of the external world.3 I therefore develop an evolutionary model that
uses ‘pain’ as a creatures first conscious experience, where pain consciousness
is said to have an influence on the quantum mechanical choices that are made
within the creature. This is done in detail in ref. 2, and refined in ref. 3.
My hypothesis requires that if an endogenous quantum mechanical superposition develops within a conscious creature in which a more painful component competes with a less painful one, than, other things being equal, the less
painful component will have an enhanced probability of surviving a collapse of
the state function. This is the interactive mechanism whereby conscious states
are claimed to influence matter. The model assumes that the more painful
experience is associated with a life-threatening behavior in a way that is best
explained in ref. 3, pp. 1953-4.
An endogenous quantum mechanical superposition develops within the experimental subjects because the ligands that attach to receptors in the brain
have quantum mechanical wave functions that spread rapidly in space due to
tionship. The existence of various conscious states in the endogenous superposition, plus my
hypothetical change in relative probability amplitudes, plus an accompanying collapse of the
wave function may all result from a ‘common’ unknown cause[8].
3 This excludes ‘emotional’ pain. It refers only to ‘physical’ pain (e.g., a flesh wound or a
broken bone)
3
the Heisenberg uncertainty principle.4 The spreading takes place as ligands are
swept along in blood and cerebrospinal fluid on their way to the receptor. This
means that there is an intrinsic probability governing the number of ligands that
become attached to the opiate receptors in a pain responsive region of the brain,
thereby posing a quantum mechanical choice between a more painful experience
and a less painful experience. ‘More pain’ and ‘less pain’ are eigenvalues of
the endogenous state reduction.5 In this situation, my hypothesis requires an
increase in the probability of the less painful eigenstate. One would therefore
expect to find a surviving endogenous eigenstate to contain more opiate-like
molecules in a part of the brain that mediates pain, than would be expected
on the basis of biochemical considerations alone. Most measurements of ligand
bonding in humans appear to have been made using subpharmacological doses,
so it is clear that the above hypothesis needs to be tested in vivo using doses
that are large enough to be felt. That is the purpose of these experiments.
Ligands are called agonists if they produce cellular effects within the receptor
to which they are attached. Morphine, fentanyl, and carfentanil are examples of
opiate receptor agonists, inasmuch as they cause cellular disturbances that we
recognize as analgesia and/or euphoria. Other molecules produce no pharmacological effects when they are attached to receptors. These are called antagonists.
Naloxone and diprenorphine are examples of opiate receptor antagonists. When
a mixture of an agonist and an antagonist is injected into a subject, the two
molecules will compete with on another for attachment to the available receptors. Such a mixture (in sufficient dose) will produce pharmacological effects,
owing to the attached agonist molecules.
The competition between the two substances is expressed quantum mechanically by their appearing in different ratios on different components of the endogenous superposition. Competing components of the superposition will therefore
support competing inside observers who experience different degrees of pain. It
is my claim that the probability amplitudes of these components will be skewed
in favor of the observer experiencing less pain.6
No attempt is made here to determine which agonists and antagonists are
4 The term ligand refers to any molecule,
endogenous or exogenous, that attaches to a
receptor.
5 Another way of saying this is that there is a ‘more pain’ observer, and a ‘less pain’ observer,
who are competing “inside observers” associated with different components of the endogenous
quantum mechanical superposition. The reduction is one that makes a definite choice between
these contenders
6 My hypothesis chooses less pain to be favored over more pain for reasons that are best
understood in terms of the evolutionary model developed in refs. 2 and 3.
4
best suited for the experiments. Carfentanil and diprenorphine may be acceptable for the experiment with rats; but the toxicity of carfentanil makes is
unsuitable for use with humans in pharmacological doses. Perhaps fentanyl and
naloxone would be the best combination for humans. However, there may be no
ideal choice of ligands at this time. Background radiation may swamp our anticipated results because of ligand binding that is not sufficiently specific to the
targeted receptors, and/or because of the existence of too many free unbound
ligands. Research is ongoing to find ligands with greater affinity and specificity.
Therefore, although the following experiments may not now give unambiguous
results, they can be thought of as idealized experiments to be performed when
the technology is sufficiently improved.
3. Preliminary to the Experiments
Prior to one of the experiments, the subject who is exposed to painful trauma
should be given a prescribed mixture of an agonist and an antagonist to determine the size of the dose that brings the subject to the threshold of analgesia.
It is assumed that a threshold dose is small enough that opiate receptors remain
unsaturated throughout the brain, and in fact, that the number of bound receptors in each region remains linear with the number of ligands that are available
to the receptors.
4. The First Experiment
Four PET scans are proposed that will allow a comparison to be made between
the binding of an agonist and an antagonist in the brain of a human suffering
from rheumatoid arthritis (or other chronic pain), or one who is subjected to
cutaneous applications of a pain producing heat (or other inflicted pain). Each
scan begins with an intravenous injection of agonist and antagonist in ratio R.
This ratio is chosen to insure that the number of agonist molecules that become
attached to the receptors is roughly equal to the number of antagonist molecules
that become attached to the receptors. Only one of these substances is labeled
radioactively during a single scan. A scan might reasonably begin 30 minutes
after injection and last for 45 minutes.
In the first scan, the subject is given a threshold dose of hot agonist and cold
antagonist. After the scan, the receptor count/pixel given by CA is recorded
in each ROI (neurological region of interest). In the second scan, the subject
is given a threshold injection of cold agonist, and hot antagonist, which has a
5
CA A
CA
1st scan
2nd scan
C
antagonist molecules
agonist molecules
endogenous ligands
Wings
indicate labeled molecules
Figure 1
net weight equal to that of the first injection. After that scan, the receptor
count/pixel, given in this case by CAA , is recorded in each ROI. The total
receptor count/pixel is then C = CA + CAA , and the ratio is
r = CA /CAA
(1)
in each ROI. If the test subject is required to endure cutaneous heat, then this
will be applied from the time of injection to the end of the scan.
The first row in fig. 1 represents the population of molecules that occupy
opiate receptors in some ROI in the first scan. The agonist is shown to be
radioactive in the first row (as indicated by the wings), where the number of
endogenous ligands (e.g., endorphins or other peptides) that are competing for
site receptors is indefinite.
The second row of fig. 1 represents the population of molecules that occupy
the opiate receptors in the second scan, where the antagonist molecules are now
radioactive. Combining the first and second scans allows one to measure CA
and CAA in each ROI, and so to find C and r.
The third and fourth scans are identical with the first and second, except
that the doses in this case are subpharmacological. This guarantees that consciousness will have nothing to do with the result. The third and fourth scans
therefore provide values of r for each ROI that are determined by all known
biochemical influences as well as any purely methodological influences. It is my
assumption that
r
(pain responsive ROIs in scans one and two)
>r
(pain responsive ROIs in scans three and four)
6
(2)
and that r will be the same in regions that are not pain responsive. The only
thing that distinguishes these two values of r in eq. 2 is the size of the dose,
and biochemically speaking, that should not have anything to with the result.
That’s because the only biochemical influence on the observed value of r is
the competition between the agonist and the antagonist, and dose should not
affect this balance for small doses at steady state equilibrium.7 The inequality
in eq. 2 is therefore a test of my hypothesis concerning the influence of pain
consciousness. It suggests that there are non-biophysical influences operating
in the pain responsive regions of the brain that result in more agonist molecules
being bound to these regions than would otherwise be expected. Presumably,
this is because the conscious observer (i.e., the PET subject) becomes associated
with a collapse of an endogenous wave function that gives preferential weight
to less painful eigenstates. In order to isolate the observer in this experiment,
monitors carrying raw data from the scanner should be covered during the time
of the scan.
5. Distribution in r
The ratio r = CA /CAA is a variable of the total endogenous quantum mechanical
state. C = CA + CAA is another variable, but it is of no interest here.
The pulse appearing on the left in fig. 2 represents the distribution of eigenstates of r in a region of the brain that is not responsive to pain. These eigenstate
amplitudes will be the same as those predicted by quantum physiology.
In regions that are responsive to the pain, the eigenstates on the right-hand
slope of the left-hand pulse will have proportionally more agonist molecules
than those that are on the left-hand slope, inasmuch as they represent states
having a greater ratio r. So eigenstates on the left-hand slope are more painful
than those on the right-hand slope. Therefore, according to my hypotheses,
the eigenstates on the right-hand slope will grow in amplitude relative to those
on the left. When this process comes to equilibrium, the entire pulse will have
displaced to the right as shown in fig. 2 where its components will be richer in
the analgesic agonist. The measured value of r will therefore be greater in these
regions.
The quantum mechanical state function for the subject’s entire body is a
function of many variables including rA , rB , rC , rD , . . . etc., where these
7 Small dose means:
on the linear portion of the binding vs concentration curve, far from
saturation[9]. For ligands of normal potency, this should present no difficulty for threshold
doses.
7
Probability
Amplitude
THRESHOLD DOSE
Region
not responsive
to pain
stimulus
Region
responsive
to pain
stimulus
ratio r
Figure 2
represent the ratio r in regions A, B, C, D, . . . etc. The total physical state
can therefore be written in the form Ψ(rA , rB , rC , rD , . . . etc.). Presumably the
conscious state of the subject is determined by Ψ in its entirety. The distribution
of r in regions that are not pain responsive will be determined by the quantum
mechanics alone. However, displacements in the functional dependence of r in
all of the regions that are pain responsive will decrease the pain consciousness
of the organism of the whole.
6. Discussion
In pain responsive ROIs, endogenous opioid agonists will generally be secreted
as part of an attempt by the body to alleviate the pain. As a result, the
total number C of exogenous ligands will be decreased in these regions as has
been shown in other studies[10]. However, this decrease will not matter to
the experiment because it is the ratio r of the two injected ligands that is
important. That ratio is governed only by the competition between the two,
and is independent of other secretions. This is one reason why the experiment
is based on the unitless ratio r. A concern is that at pharmacological doses, this
effect will result in a more homogeneous radioactive response over all regions of
the brain, which would tend to mask differences in r.
The experiment will be valid, even if the agonist is specific to, say µreceptors, and the antagonist is non-specific, as is the case of carfentanil and
diprenorphine. The ratio r should certainly be affected by variations of specificity, but it would remain the same between the first two scans and the second
two scans in this experiment. Whatever the value of r for subpharmacological
doses, it should not change (biochemically speaking) as the dose is increased
8
to threshold, even if the ligands engage different populations of receptors. A
concern is that differences in r will be masked by excessive non-specificity.
It will also not matter if the size of the dose is slightly different for different
subjects. A different dose will change the total count C in each ROI, but the
ratio r in each region should not thereby be affected. What is important is
that the dose be one that puts the injected agonist and antagonist molecules
into one-on-one competition with one another at the analgesic threshold of the
subject.
Since it is impossible at this point to estimate the magnitudes of the hypothetical displacement of the pulse in fig. 2, it is impossible to estimate the
number of data points that would be necessary to get good statistics. Resolution
is part of what must be decided by the experiment.
7. The Second Experiment
There is another approach to this problem that involves in vivo autoradiography
with rats experiencing pain. Instead of four PET scans, there are four injections
(in four different rats) of a mixture of agonist and antagonist that follow the
same protocol as before. Each of the four rats is sacrificed. The brain of each
is then sliced and exposed to film to reveal the concentration of labeled ligands
in different parts of the brain.
As in the PET case, the first two doses will allow a determination of r =
CA /CAA in each ROI at threshold levels. The second two doses will allow r
to be determined in each ROI at subpharmacological doses, which insures that
consciousness will not be a factor. My claim is that eq. 2 should also apply in
this case, giving evidence of the influence of consciousness on the outcome.
The second (autoradiographic) experiment might be cheaper and easier than
the first (PET) experiment. But there is one great disadvantage. A negative
result might mean that rats are automatons that have no conscious life. It is only
in a truly in vivo experiment (i.e., one in which the subject is alive and known
to be fully conscious when the data is taken) that the hypothesis can be fully
tested. This requires a PET based experiment that uses human subjects. On
the other hand, a positive result for the second (autoradiographic) experiment
would be useful because it would suggest that rats are conscious, and that my
hypothesis is correct.
9
Acknowledgements
I would like to thank Ron Blasberg, Richard Carson, Joanna Fowler, James
Frost, Anthony Jones, and Milt Titeler for helping me to understand some
of the capabilities and limitations of PET technology and autoradiography. I
appreciate their willingness to share their extensive experience with me in the
field of opiate ligands and their receptors.
References
[1] R.A. Mould, “The inside observer in quantum mechanics”, Found. Phys.
25 (11), 1621 (1995)
[2] R.A. Mould, “Consciousness and quantum mechanics”, Found. Phys. 28
(11), 1703 (1998)
[3] R.A. Mould, “Quantum consciousness”, Found. Phys. 29 (12), 1951 (1999);
quant-ph/9908077
[4] W. James, The Principles of Psychology, Vol. I, Chap. 5, in The Works of
William James, F. Burkhart, ed. (Harvard University Press, Cambridge,
Massachusetts, 1981), pp. 141-147
[5] J. von Neumann, Mathematical Foundations of Quantum Mechanics,
(Princeton University Press, Princeton New Jersey, 1955), pp. 418-421
[6] E. Joos and H. D. Zeh, “The emergence of classical properties through
interaction with the environment” Z. Phys. B 59, 223 (1985), top p. 224
[7] D. Giulini, et al, Decoherence and the Appearance of a Classical World in
Quantum Theory, (Springer, Berlin, New York, 1996) p. 41-44
[8] R.A. Mould, ”Satisfying reality”, Iyyun. Jerus. Phil. Q. 50 (Jan. 2001);
quant-ph/0012120
[9] M. Titeler, et al, “µ opiate receptors are sensitively labeled by [3 H] carfentanil in human and rat brain”, Euro. J. Pharm. 167, 221 (1989)
[10] A. K. P. Jones, et al, “Changes in central opioid receptor binding in relation
to inflammation and pain in patients with rheumatoid arthritis”, Br. J.
Rheumatol. 33, 909 (1994)
10 |
Consciousness as a State of Matter
Max Tegmark
arXiv:1405.0493v2 [physics.pop-ph] 7 Nov 2015
Dept. of Physics & MIT Kavli Institute, Massachusetts Institute of Technology, Cambridge, MA 02139
(Dated: Published in New Scientist, April 12, 2014 (pages 28-31).)
I examine the hypothesis that consciousness can be understood as a state of matter, “perceptronium”, with distinctive information processing abilities. I explore five basic principles that may
distinguish conscious matter from other physical systems such as solids, liquids and gases: the
information, integration, independence, dynamics and utility principles. This approach generalizes Giulio Tononi’s integrated information framework for neural-network-based consciousness to
arbitrary quantum systems, and provides interesting links to error-correcting codes and condensed
matter criticality, as well as an interesting connections between the emergence of consciousness and
the emergence of time. (For more technical details, see http://arxiv.org/abs/1401.1219.)
Why are you conscious right now? Specifically, why
are you having a subjective experience of reading these
words, seeing colours and hearing sounds, while the inanimate objects around you presumably aren’t having any
subjective experience at all?
Different people mean different things by “consciousness”, including awareness of environment or self. I am
asking the more basic question of why you experience
anything at all, which is the essence of what philosopher
David Chalmers has coined “the hard problem” of consciousness.
A traditional answer to this problem is dualism — that
living entities differ from inanimate ones because they
contain some non-physical element such as an “anima”
or “soul”. Support for dualism among scientists has gradually dwindled. To understand why, consider that your
body is made of about 1029 quarks and electrons, which
as far as we can tell move according to simple physical
laws. Imagine a future technology able to track all your
particles: if they were found to obey the laws of physics
exactly, then your purported soul is having no effect on
your particles, so your conscious mind and its ability to
control your movements would have nothing to do with
a soul.
If your particles were instead found not to obey the
known laws of physics because they were being pushed
around by your soul, then we could treat the soul as just
another physical entity able to exert forces on particles,
and study what physical laws it obeys.
Let us therefore explore the other option, known as
physicalism: that consciousness is a process that can occur in certain physical systems. This begs a fascinating
question: why are some physical entities conscious, while
others are not? If we consider the most general state
of matter that experiences consciousness — let’s call it
“perceptronium” — then what special properties does it
have that we could in principle measure in a lab? What
are these physical correlates of consciousness? Parts of
your brain clearly have these properties right now, as well
as while you were dreaming last night, but not while you
were in deep sleep.
Imagine all the food you have eaten in your life and
consider that you are simply some of that food, rearranged. This shows that your consciousness isn’t simply
due to the atoms you ate, but depends on the complex
patterns into which these atoms are arranged. If you can
also imagine conscious entities, say aliens or future superintelligent robots, made out of different types of atoms
then this suggests that consciousness is an emergent phenomenon (whose complex behaviour emerges from many
simple interactions). In a similar spirit, generations of
physicists and chemists have studied what happens when
you group together vast numbers of atoms, finding that
their collective behaviour depends on the patterns in
which they are arranged: the key difference between a
solid, a liquid and a gas lies not in the types of atoms,
but in their arrangement. Boiling or freezing a liquid
simply rearranges its atoms.
My hope is that we will ultimately be able to understand perceptronium as yet another state of matter. Just
as there are many types of liquids, there are many types
of consciousness. However, this should not preclude us
from identifying, quantifying, modelling and understanding the characteristic properties that all liquid forms of
matter, or all conscious forms of matter, share. Take
waves, for example, which are substrate-independent in
the sense that they can occur in all liquids, regardless
of the liquid’s atomic composition. Like consciousness,
waves are an emergent phenomenon in the sense that
they take on a life of their own: a wave can traverse a
lake while the individual water molecules merely bob up
and down, and the motion of the wave can be described
by a mathematical equation that doesn’t care what the
wave is made of.
Something analogous happens in computing: Alan
Turing famously proved that all sufficiently advanced
computers can simulate one another, so a video game
character in her virtual world would have no way of knowing whether her computational substrate (“computronium”) was a Mac or a PC, or what types of atoms the
CPU was made of. All that would matter is abstract information processing. If this created character were complex enough to be conscious, like in the film The Matrix,
then what properties would this information processing
need to have?
I have long contended that consciousness is the way information feels when processed in certain complex ways.
The neuroscientist Giulio Tononi has made this idea more
2
specific and useful, making the compelling argument that
for an information processing system to be conscious,
its information must be integrated into a unified whole.
In other words, it must be impossible to decompose
the system into nearly independent parts — otherwise
these parts would feel like two separate conscious entities. Tononi and his collaborators have incorporated this
idea into an elaborate mathematical formalism known as
integrated information theory (IIT).
IIT has generated significant interest in the neuroscience community, because it offers answers to many
intriguing questions. For example, why do some information processing systems in our brains appear to be
unconscious? Based on extensive research correlating
brain measurements with subjectively reported experience, neuroscientist Christof Koch and others have concluded that the cerebellum — a brain area whose roles
include motor control — is not conscious, but is an unconscious information processor that helps other parts of
the brain with certain computational tasks.
The IIT explanation for this is that the cerebellum
is mainly a collection of “feed-forward” neural networks
in which information flows like water down a river, and
each neuron affects mostly those downstream. If there is
no feedback, there is no integration and hence no consciousness. The same would apply to Google’s recent
feed-forward artificial neural network that processed millions of YouTube video frames to determine whether they
contained cats. In contrast, the brain systems linked to
consciousness are strongly integrated, with all parts able
to affect one another.
IIT thus offers an answer to the question of whether
a superintelligent computer would be conscious: it depends. A part of its information processing system that
is highly integrated will indeed be conscious. However,
IIT research has shown that for many integrated systems,
one can design a functionally equivalent feed-forward system that will be unconscious. This means that so-called
“p-zombies” can, in principle, exist: systems that behave
like a human and pass the Turing test for machine intelligence, yet lack any conscious experience whatsoever.
Many current “deep learning” AI systems are of this pzombie type. Fortunately, integrated systems such as
those in our brains typically require much fewer computational resources than their feed-forward “zombie” equivalents, which may explain why evolution has favoured
them and made us conscious.
Another question answered by IIT is why we are unconscious during seizures, sedation and deep sleep, but
not REM sleep. Although our neurons remain alive and
well during sedation and deep sleep, their interactions are
weakened in a way that reduces integration and hence
consciousness. During a seizure, the interactions instead
get so strong that vast numbers of neurons start imitating one another, losing their ability to contribute independent information, which is another key requirement
for consciousness according to IIT. This is analogous to
a computer hard drive where the bits that encode infor-
mation are forced to be either all zeros or all ones, resulting in the drive storing only a single bit of information.
Tononi, together with Adenauer Casali, Marcello Massimini and other collaborators, recently validated these
ideas with lab experiments. They defined a “consciousness index” that they could measure by using an EEG
to monitor the brain’s electrical activity after magnetic
stimulation, and used it to successfully predict whether
patients were conscious.
Awake and dreaming patients had comparably high
consciousness indices, whereas those anaesthetised or in
deep sleep had much lower values. The index even successfully identified as conscious two patients with lockedin syndrome, who were aware and awake but prevented
by paralysis from speaking or moving . This illustrates
the promise of this technique for helping doctors determine whether unresponsive patients are conscious.
Despite these successes, IIT leaves many questions
unanswered. If it is to extend our consciousness-detection
ability to animals, computers and arbitrary physical systems, then we need to ground its principles in fundamental physics. IIT takes information, measured in bits, as
a starting point. But when I view a brain or computer
through my physicist’s eyes, as myriad moving particles,
then what physical properties of the system should be
interpreted as logical bits of information? I interpret as
a “bit” both the position of certain electrons in my computer’s RAM memory (determining whether the microcapacitor is charged) and the position of certain sodium
ions in your brain (determining whether a neuron is firing), but on the basis of what principle? Surely there
should be some way of identifying consciousness from
the particle motions alone, even without this information interpretation? If so, what aspects of the behaviour
of particles corresponds to conscious integrated information?
The problem of identifying consciousness in an arbitrary collection of moving particles is similar to the simpler problem of identifying objects there. For instance,
when you drink iced water, you perceive an ice cube in
your glass as a separate object because its parts are more
strongly connected to one another than to their environment. In other words, the ice cube is both fairly integrated and fairly independent of the liquid in the glass.
The same can be said about the ice cube’s constituents,
from water molecules all the way down to atoms, protons,
neutrons, electrons and quarks. Zooming out, you similarly perceive the macroscopic world as a dynamic hierarchy of objects that are strongly integrated and relatively
independent, all the way up to planets, solar systems and
galaxies.
This grouping of particles into objects reflects how
they are stuck together, which can be quantified by the
amount of energy needed to pull them apart. But we
can also reinterpret this in terms of information: if you
know the position of one of the atoms in the piston of an
engine, then this gives you information about the whereabouts of all the other atoms in the piston, because they
3
all move together as a single object. A key difference between inanimate and conscious objects is that for the latter, too much integration is a bad thing: the piston atoms
act much like neurons during a seizure, slavishly tracking
one another so that very few bits of independent information exist in this system. A conscious system must
thus strike a balance between too little integration (such
as a liquid with atoms moving fairly independently) and
too much integration (such as a solid), suggesting that
consciousness is maximised near a phase transition between less- and more-ordered states; indeed, humans lose
consciousness unless key physical parameters of our brain
are kept within a narrow range of values.
An elegant balance between information and integration can be achieved using error-correcting codes: methods for storing bits of information that know about each
other, so that all information can be recovered from a
fraction of the bits. These are widely used in telecommunications, as well as in the ubiquitous QR codes from
whose characteristic pattern of black and white squares
your smartphone can read a web address. As error correction has proven so useful in our technology, it would be interesting to search for error-correcting codes in the brain,
in case evolution has independently discovered their utility — and perhaps made us conscious as a side effect.
We know that our brains have some ability to correct
errors because you can recall the correct lyrics for a song
you know from a slightly incorrect fragment of it. John
Hopfield, a biophysicist renowned for his eponymous neural network model of the brain, proved that his model has
precisely this error-correcting property. However, if the
hundred billion neurons in our brain do form a Hopfield
network, calculations show that it could only support
about 37 bits of integrated information — the equivalent
of a few words of text. This begs the question of why the
information content of our conscious experience seems
to be significantly larger than 37 bits. The plot thickens
when we view our brain’s moving particles as a quantummechanical system. As I showed in January, the maximum amount of integrated information then drops from
37 bits to about 0.25 bits, and making the system larger
doesn’t help (arxiv.org/abs/1401.1219).
This integration problem can be circumvented by
adding another principle to the list that a physical system
must obey in order to be conscious. So far I have outlined
three: the information principle (it must have substantial
information storage capacity), the independence principle (if must have substantial independence from the rest
of the world) and the integration principle (it cannot consist of nearly independent parts). The aforementioned
0.25 bit problem can be bypassed if we also add the dynamics principle — that a conscious system must have
substantial information-processing capacity, and it is this
processing rather than the static information that must
be integrated. For example, two separate computers or
brains can’t form a single consciousness.
These principles are intended as necessary but not sufficient conditions for consciousness, much like low compressibility is a necessary but not sufficient condition for
being a liquid. As I explore in my book Our Mathematical Universe, this leads to promising prospects for
grounding consciousness and IIT in fundamental physics,
although much work remains and the jury is still out on
whether it will succeed.
If it does succeed, this will be important not only for
neuroscience and psychology, but also for fundamental
physics, where many of our most glaring problems reflect our confusion about how to treat consciousness. In
Einstein’s theory of general relativity, we model the “observer” as a fictitious disembodied massless entity having
no effect whatsoever on that which is observed. In contrast, the textbook interpretation of quantum mechanics
states that the observer does affect the observed. Yet after a century of spirited debate, there is still no consensus
on how exactly to think of the quantum observer. Some
recent papers have argued that the observer is the key to
understanding other fundamental physics mysteries, such
as why our universe appears so orderly, why time seems
to have a preferred forward direction, and even why time
appears to flow at all.
If we can figure out how to identify conscious observers
in any physical system and calculate how they will perceive their world, then this might answer these vexing
questions. |
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
579
Article
Entheogens, the Conscious Brain and Existential Reality: Part 1
Chris King*
ABSTRACT
The purpose of this article is to provide a ‘state of the art’ research overview of what is
currently known about how entheogens, including the classic psychedelics, affect the brain
and transform conscious experience through their altered serotonin receptor dynamics, and to
explore their implications for understanding the conscious brain and its relationship to
existential reality, and their potential utility in our cultural maturation and understanding of
the place of sentient life in the universe.
Part 1 contains the following sections: 1. Cultural and Historical Introduction; 2. The enigma
of Subjective Consciousness; and 3. Fathoming the Mind-Brain Relationship and Experiential
Modalities.
Key Words: entheogens, conscious brain, existential reality, psychedelics, serotonin,
conscious experience, sentient life, universe.
1. Cultural and Historical Introduction
Human societies have been actively using psychoactive substances since the earliest cultures
emerged. In “The Alchemy of Culture” Richard Rudgley notes that European cave
depictions, from the paleolithic on, abound with both herbivorous animals of the hunt and
geometrical entopic patterns similar to the phosphenes seen under sensory withdrawal and
under the effects of psychotropic herbs. By the time we find highly-decorated pottery ‘vase
supports’ in Middle Neolithic France, we have evidence consistent with their ritual use as
opium braziers. At 4200 BC at the Cueva de los Murciélagos site in Spain we find burials
with bags containing Papaver somniferum capsules. During the 18th Egyptian dynasty 15501295 BC there was an active trade with Cyprus of juglets, whose form is neatly in the shape
of an inverted poppy pod, indicating they contained opium. This trend is confirmed in detail
in the terracotta Goddess figurines discovered from a small shrine at Gazi west of Knossos in
Crete, dated to 1350 BC, whose headdress consists of a row of three poppy heads explicitly
slit in the exact way opium resin is extracted from the poppy to this day. A goddess with the
same emblems - three poppies - in her hand is depicted also in a gold signet ring from
Mycenae from 1500 BC.
Evidence for Cannabis sativa use in Europe also dates back to the neolithic, where there is
evidence that it was used for rope and for its psychotropic and potentially hallucinogenic
effects. Polyploid bowls with rope imprints again look to be braziers for consuming plant
vapours. Pipe cups dating from a third millennium BC burial site in Romania explicitly
contain charred hemp seeds, consistent with their being the remains of a smoked cannabis
pipe. According to The Living Torah kaneh-bosm (Hebrew: ְקנֵה-)בֹׂשם
ֶ
identified with
cannabis may have been one of the ingredients of the holy anointing oil mentioned in various
* Correspondence: Chris King http://www.dhushara.com E-Mail: chris@sexualparadox.org
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
580
sacred Hebrew texts. The Scythians of southern Central Asia used Cannabis to attain trance
during funeral rites, using a metal tripod censer. Censers have been found still containing
hemp seed (Rudenko). Herodotus, more than 2000 years ago, described the way Scythians
burned portions of the plant in metal tripod censers, beneath small tent structures that
enclosed the vapors inhaled for ritualistic and euphoric purposes (Merlin, Schultes &
Hofmann). "The Scythians then take this seed of hemp and, creeping under the mats, they
throw it on the red-hot stones; and, being so thrown, it smolders and sends forth so much
steam that no Greek vapour bath could surpass it. The Scythians howl in their joy at the
vapour bath." The Yanghai Tombs of Xinjiang have revealed the 2700-year-old grave of a
shaman. Near the head and foot was a large leather basket and wooden bowl filled with 789g
of cannabis, superbly preserved by climatic and burial conditions. This material still
contained the active ingredient THC. Cannabis use in the Indian subcontinent may also go
back to the earliest cultures. Cannabis is first referred to in Hindu Vedas between 2000 and
1400 BC, in the Atharvaveda. Shiva, who is the patron deity of Cannabis, can be seen in
Mohenjo-Daro in a meditating pose with trident, as Pashupatinath Lord of the Animals
surrounded by his beasts. Cannabis or Ganga carries the name of the sacred river itself.
Fig 1: Phosphene-like finger markings
Neolithic tomb of Gaverinus, Brittany.
Persephone passing what looks like a
liberty bell psilocybe to Demeter, Er
Lannic pottery possibly used for opium,
opium juglets from Cyprus (Rudgley),
poppies being offered and the poppy
goddess with slit poppy heads on her
crown, the oldest illustration of witches,
polyploidy bowls which may have been
used for vaporizing cannabis, the Scythian
goddess showing a horseman the tree of
life, braziers and pots in the Scythian ritual
use of cannabis (Schultes & Hofmann).
Likewise by the fourth millennium BC, we
also find evidence of alcohol use, probably
initially from date palms and then the grape
vine Vitis vinifera. Barley beer is referred
to in early Sumerian and Akkadian texts. The soma or haoma of the Indo-Aryans extolled in
the Rig Veda and the Avesta remains a botanical enigma, but nevertheless shows another
psychotropic concoction which was extolled to semi-divine status, which has been attributed
to Syrian rue Peganum harmala which contains psychoactive monoamine oxidase inhibitor
harmaline and to the muscimol-containing Amanita muscaria which has also been ritually
used by Siberian shamans, because references to it suggest it was recycled in excreted urine.
There is also an enigma surrounding the Eleusian epoptea which was said to be a sacramental
repast of visionary transformative power, which has been associated with various
psychotropic agents, including the liberty cap Psilocybe species which Persephone appears to
be passing to Demeter on a stele as noted by Graves (O’Prey), and ergot fungus containing
rye (Wasson et al).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
581
In medieval times, in the midst of Christian persecution against all manner of heretics,
witches and mystics, stemming from the Crusade against the Albigenses, there are also
frequent references to the use of ‘devilish’ witching herbs which were an underlying part of
pre-Christian European history and folklore, including Mandrake, Henbane, and Belladonna
which are highly toxic deliriants which were rubbed on the body as herbal ointments causing
sensations of flying, joining the sabbat, or lovemaking with an imagined suitor, due to the
libido enhancing effects of hyoscyamine, and related muscarinic acetyl-choline receptor
antagonists, followed by unconsciousness. These were pursued by the Inquisitors, as
evidence of witchcraft and their practitioners condemned to death by drowning or burning at
the stake. To compound matters, there were also episodes of mass poisoning due to lysergic
acid derivatives in ergot fungus on the rye, resulting in outbreaks of collective madness,
sometimes accompanied by the loss of appendages from gangrene caused by the
vasoconstrictive effects of the alkaloids.
The term entheogen is derived from ancient Greek, νθεος (entheos) "full of the god,
inspired, possessed," the root of the English word ‘enthusiasm’, and γενέσθαι (genesthai) "to
come into being." Thus, an entheogen is a substance that causes one to become inspired or to
experience feelings of inspiration, often in a religious or "spiritual" manner. In a strict sense,
only those vision-producing drugs that can be shown to have figured in shamanic or religious
rites would be designated entheogens, but in a looser sense, the term can also be applied to
other drugs, both natural and artificial, that induce alterations of consciousness similar to
those documented for ritual ingestion of traditional entheogens. Evidence for the first use of
entheogens may come from Tassili, Algeria, with a cave painting of a mushroom-man, dating
to 8000 BP and mushroom idols from the Konya plain and the Vinca site in Europe
(McKenna).
Part of the difficulty facing the acceptance of entheogens in European culture is that the most
potent psychedelic entheogens have natural habitats in the Americas, where European
cultures have come upon them as alien diabolical practices by often violent warrior preColombian cultures such as the Aztecs, who themselves had horrific sacrificial practices
worshipping gods of war regarded as heathen and devilish by the conquistadores. Christianity
and conservative European culture, still reeling from its own paranoid religious conflicts, as
flagellating Penitente Catholics set out for a new world, regarded all such practices with
horror, and although Christianity was also a sacramental religion with an equally bloodthirsty
Eucharist of the soma and sangre of Christ, violently repressed all such use of visionary
sacraments.
Nevertheless potent psychedelic entheogens were ritually used and held sacred by diverse
pre-Colombian cultures for centuries and even millennia before the arrival of Columbus.
Long before the Aztecs the Mayans record the use of sacred mushrooms belonging to the
Psilocybe genus in both frescos and mushroom stones dating back as far as 1000 BC which
show obvious evidence of use as a visionary agent. The sacred use of the mushroom
teonanactl or ‘flesh of the gods’ continued as an unbroken tradition for 1,500 years to
Columbus and then secretly for another 500 years to the present day.
The Aztecs a particularly vicious sacrifical warrior culture nevertheless freely embraced
sacred mushrooms in their own frenzied way, seen through the distorting prisms of
Conquistador diabolization. Friar Sahagun, one of the first conquistadors to chronicle
teonanacatl, flesh of the gods, remarked:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
582
“when they become excited by them start dancing, singing, weeping. Some do not want to
sing but sit down and see themselves dying in a vision; others see themselves being eaten by
a wild beast; others imagine they are capturing prisoners of war, that they are rich, that they
possess many slaves, that they have committed adultery and were to have their heads crushed
for the offence . . . and when the drunken state had passed, they talk over amongst themselves
the visions they have seen” (Schultes and Hofmann 1979 146).
“During the coronation feast of Moctezuma in 1502, teonanacatl (the divine mushroom) was
used to celebrate the event. War captives were slaughtered in great numbers to honour
Moctezuma's accession to the throne. Their flesh was eaten, and a banquet was prepared after
the victims' hearts were offered to the gods. After the sacrifice was over, everyone was
bathed in human blood. Raw mushrooms were given to the guests, which one writer
described as causing them to go out of their minds-in a worse state than if they had drunk a
great quantity of wine. In his description, these men were so inebriated that many took their
own lives. They had visions and revelations about the future, and Duran thought the devil
was speaking to them in their madness. When the mushroom ceremony ended, the invited
guests left. Moctezuma invited rival rulers to feasts which were held three times a year. One
of these important feasts was called the Feast of Revelations, when the invited dignitaries and
Moctezuma, or his representative, ate the wild mushrooms. " ... "During the Aztec king
Tizoc's enthronement feast, all those present ate wild mushrooms - the kind that made men
lose their senses. After four days of feasting, the newly crowned Tizoc gave his guests rich
gifts and sacrificed the Metztitlan victims” (Dobkin de Rois 142).
By contrast the Mazatecs continued to use sacred mushrooms for divination and curing
maladies in absolute secret, a secret so assiduously kept that all trace of magic mushroom
worship became lost to the world at large until Maria Sabina accepted Gordon Wasson into
the mysteries of the little flowers.
At the same time, Mexico was rich with other entheogenic sacraments. Various peoples
consumed the mescalin-containing cactus peyotl or ‘hairy one’, the Huichols undertaking an
annual pilgrimage across Mexico to collect it from the high deserts around their sacred
mountain of Wirikuta, describing the effects of the cactus as opening the nierika or portal to
the spirit world where everything becomes one:
“There is a doorway within our minds that usually remains hidden and secret until the time of
death. The Huichol word for it is nieríka. Nieríka is a cosmic portway or interface between
so-called ordinary and non-ordinary realities. It s a passageway and at the same time a barrier
between the worlds. … When the mara'akáme passes through the nieríka [visionary tunnel]
he moves just as the smoke moves; hidden currents carry him up and in all directons at once
... as if upon waves, flowing into and through other waves ... the urucate. As the mara'akáme
descends and passes through the nieríka on the return, his memory of the urucate and their
world fades; only a glimmer remains of the fantastic journey that he has made” (Halifax 239).
Evidence of peyote use goes back to the Toltecs in 500 BC where a snuffing pipe with a deer
holding a peyote in its mouth has been found at Monte Alban. Others used the lysergic acid
amide containing black seeds or bardo negroh of the morning glory, and the Herb of the
Shepherdess, Salvia divinorum to induce visions when sacred mushrooms were not available.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
583
In the southern continent, an equally diverse spectrum of entheogenic sacraments had been
discovered, from the mescalin-containing San Pedro cactus Trichocereus pachanoi (holding
the keys to the golden gate), through snuffs such as and epena from Virola species and the
famous pan-Amazonian brew ayahuasca of “Vine of the Soul” containing DMT from plants
such as Psychotria viridis, beta-carboline MAO inhibitors such as harmine from the vine
Banisteriopsis caapi and occasionally solonaceous alkaloids from Brugmansia a tree-datura
having deliriant effects similar to the witching herbs of Old Europe.
Archaeological records of sacred use likewise go back to ancient times, with evidence of San
Pedro use, in the cactus found alongside a leopard in Chavin culture (1200-600 BC),
evidence of sacred mushroom use in Paracas culture (800-100 BC), and San Pedro and snuff
use among Nazca (100-800 CE). As well, as an energetic mainstay and spiritual guide, the
coca leaf was chewed, along with stimulants such as caffeine.
Likewise in the African subcontinent, two of the oldest human cultures the Bushmen and
Pygmies have traditional sacred use of psychotropics. Biaka pygmies use the hallucinogen
Tabernanthe iboga and there is also a pattern of Cannabis use among the Bushmen, to
complement their trance dancing visitations. Although this is an imported tradition, it is done
in a unique ancient manner, filling a hole in the ground with plant material, from which the
herb is smoked cool.
Fig 2: Diverse sacramental
use over millennia in the
Americas. Mayan sacred
mushroom stones, a blue
topped mushroom carried by
a shaman Paracas culture,
Aztec murals showing sacred
mushroom
deities
(Magliabecciano Codex), the
deer snuffing pipe holding a
peyote from Monte Alban,
two Chavin urns with jaguar
beside San Pedro cacti, a
sacred mushroom deity from
South America the Huichol
nierika or visionary portal
opened by peyote, a Chavin
statue and Nazca gourd
showing
hallucinogenic
snuffing , and a Nazca pottery
showing San Pedro use.
We need to examine at this
point why diverse preColumbian cultures have consistently managed to incorporate enthogens successfully into
their highest cultural expressions, remaining as a spiritual record for archaeologists to
discover, while so-called emancipated Western society has made them an absolute taboo,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
584
ring-fenced by dire penalties of long-term imprisonment or even death, amid threats of
insanity and permanent brain, or genetic damage.
We can again see currents of the schizophrenic attitude of Western society to psychotropic
agents in its romantic and demonic attitudes to opium and cocaine. While Samuel Taylor
Coleridge composed “Kubla Khan” in 1797, according to his preface, one night after he
experienced an opium influenced dream, and Sigmund Freud extolled the virtues of cocaine
in his 1884 paper "On Coca", Great Britain had become deeply involved in the trafficking of
opium from factories in India to China, against Chinese legislation, in the Opium Wars
(1839-1860) with the explicit purpose of addicting the Chinese population, to redress an
unfavourable trade balance between the countries. At the same time the Victorian press was
hot with scandalous stories of debauchery and dissolution in the opium dens of London. By
1886 Arthur Conan Doyle was writing of the hideous dependence of Sherlock Holmes on
cocaine injection and the stage was again set for regarding psychotropic drugs as agents of
evil.
At the turn of the twentieth century, long after its spread to the plains Indians in the 15th
century, there had been a resurgence of religious peyote use in the US in the form of the
Native American Church (Anderson), which has fought a long and tortuous battle for the
legal use of the sacrament.
Speak to the peyote with your heart, with your thoughts. And the peyote sees your heart ...
And if you have luck, you will hear thingsand receive things that are invisible to others,
but that god has given you to pursue your path(Schultes and Hofmann).
"God told the Delawares to do good even before
He sent Christ to the whites who killed him ...
God made Peyote It is His power. It is the power of Jesus.
Jesus came afterwards on this earth, after peyote." (Anderson).
In 1897 Arthur Heffter isolated the alkaloid mescalin from peyote and the modern era of
psychedelic, or “mind manifesting” research began. William James author of “Varieties of
Religious Experience” who had tried many psychoactive agents unfortunately had a bad
intestinal reaction in 1896 and missed out on its “chromatic” effects, but noted "all kind of
odd experiences, mescal, ecstasies etc. give them indeterminate possibilities". It is said that
round 1911 the young Adolf Hitler took peyote during his formative period, provided him by
apothecary Wilhelm Pretzsche (Andrews 417-425). In 1938 Albert Hofmann synthesized
LSD, but had to wait five years before accidentally absorbing enough on his fingers in 1943
to discover its psychedelic effects. Interviewed shortly before his hundredth birthday, he
called LSD "medicine for the soul" and was frustrated by the subsequent worldwide
prohibition of it. Nevertheless for several decades these substances remained research
materials and were not regarded as dangerous drugs of abuse.
While both opium and cocaine had essentially been legal in the 1800s, cultural migration had
begun to cause social problems both through patterns of addiction and through racial
prejudice and cultural profiling. Chinese populations in the US were perceived to be addicted
to opium and Negro populations were accused of abusing cocaine resulting in rape of white
women and improved marksmanship among criminals. A series of tax and drug laws were
passed leading to successively tighter restrictions. By 1930 the newly formed Federal Bureau
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
585
of Narcotics, headed by Harry J. Anslinger, as part of the government's broader push, to
outlaw all recreational drugs, advertising marijuana as a “killer drug” inviting “Murder!
Insanity!” and “Death!” By 1935 the Geneva Trafficking Conventions outlawed international
trafficking in opium, cocaine and cannabis, but the US, headed by Anslinger, refused to sign
the final draft because it didn’t include cultivation, production, manufacture and distribution
and considered it too weak in relation to extradition, extraterritoriality and the confiscation of
trafficking profits. Given these Calvinistic attitudes, it is not hard to understand how the
vastly more confounding entheogens might come to be treated.
Fig 3: Maria Sabina passing the sacred
mushroom
to
Gordon
Wasson
(Riedlinger). The renowned Huichol
elder Don Jose Matsuwa (Schultes &
Hofmann), Tellus ‘Goodmorning’, the
roadman at my first peyote meeting in
1976, attending his son’s meeting in
1992 at the age of 93. Senor Trinico by
infra-red video in the dark during our
ayahuasca ceremony in 1999.
All records of sacred mushroom use had
been lost to history by the turn of the
20th century and it had become assumed
that the sacred mushroom was a case of
mistaken identity for peyote. However in 1938 Blas Reko and Richard Evans Schultes
traveled to Huautla de Jiménez, where Robert Weitlaner had a year earlier located a specimen
and managed to find four species of Paneolus and Psilocybe, including caerulescens and
cubensis (Ott). A year later Weitlaner’s daughter Irmgard witnessed a mushroom velada
without partaking, but war intervened. Then in 1953 Gordon Wasson would finally meet
Maria Sabina the Mazatec curandero, in Huautla, after strong encouragement from Robert
Graves.
It was in his own words, an entheogen - "the divine mushroom of immortality", calling it
"Ecstasy!" after Greek ekstasis - flight of the soul from the body. “In truth he is the five
senses disembodied, all of them keyed to the height of sensitivity, and awareness, all of them
blending into one another most strangely until, utterly passive he becomes a pure receptor
infinitely delicate of sensation. … Your very soul is seized and shaken until it tingles, until
you feel that you will never recover your equilibrium”. He also noted that Greeks call
mushrooms broma theon "the food of the gods" and specifically likened the experience to the
epoptea of Eleusis "For me there is no doubt that the secret of Eleusis lies in hallucinogens".
Wasson was to describe the experience as Pentecost and the long-held secret of sacred
mushroom again greeted the world. "By comparison with the mushroom, the Element in the
Christian agape seems pallid. The mushroom holds the key to a mystical union with God,
whereas only rare souls can attain similar ecstasy and divine communion by intensive
contemplation of the miracle of the Mass" (Riedlinger, Furst).
"On both nights RGW stood up for a long time in Cayetano's room at the foot of the stairway,
holding on to the rail transfixed in ecstasy by the visions that he was seeing in the darkness
with his open eyes. For the first time that word 'ecstasy' took on a subjective meaning for
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
586
him. ... There came one moment when it seemed as though the visions themselves were about
to be transcended, and dark gates reaching upward beyond sight were about to part, and we
were to find ourselves in the presence of the Ultimate. We seemed to be flying at the dark
gates as a swallow at a dazzling lighthouse, and the gates were to part and admit us. But they
did not open, and with a thud we fell back gasping. We felt disappointed, but also frightened
and half relieved, that we had not entered into the presence of the ineffable, whence, it
seemed to us at the time, we might not have returned, for we had sensed that a willing
extinction in the divine radiance had been awaiting us. … The spirit of the agape of which we
have already spoken was a prelude to a wave of generous tender feelings that the mushroom
aroused in everyone ... Twice in the course of the night the Senora reached out her right hand
to me and sought contact with my fingers in friendly greeting, across the chasm of the
language barrier - Gordon Wasson & Valentina Wasson - Mushrooms Russia & History
(Riedlinger).
To Maria Sabina, although also using it for curing maladies, it was also an entheogen,
reciting it’s illumination in her chants:
“Woman who thunders am I, woman who sounds am I.
Spiderwoman am I, says hummingbird woman am I says
Eagle woman am I, says important eagle woman am I.
Whirling woman of the whirlwind am I, says
woman of a sacred, enchanted place am I, says
Woman of the shooting stars am I. ...
I'm a birth woman, says I'm a victorious woman, says
I'm a law woman, says I'm a thought woman, says I'm a life woman,
I am a spirit woman, says I am a crying woman, says
I am Jesus Christ, says ... I'm the heart of the virgin Mary.”
(Mushroom Ceremony - Smithsonian Institute)
Her vision of the inner world of the sacred mushroom is both entheogenic and prophetic:
“There is a world beyond ours, a world that is far away, nearby and invisible. And there is
where God lives, where the dead live, the spirits and the saints, a world where everything has
already happened and everything is known. That world talks. It has a language of its own. I
report what it says. The sacred mushroom takes me by the hand and brings me to the world
where everything is known. It is they, the sacred mushrooms that speak in a way I can
understand. I ask them and they answer me. When I return from the trip that I have taken
with them I tell what they have told me and what they have shown me. The more you go
inside the world of teonanacatl , the more things are seen. And you also see our past and our
future, which are there together as a single thing already achieved, already happened . . . I
saw stolen horses and buried cities, the existence of which was unknown, and they are going
to be brought to light. Millions of things I saw and knew. I knew and saw God: an immense
clock that ticks, the spheres that go slowly around, and inside the stars, the earth, the entire
universe, the day and the night, the cry and the smile, the happiness and the pain. He who
knows to the end the secret of teonanacatl - can even see that infinite clockwork” (Schultes &
Hofmann).
The reaction of the US government was swift. Within a few days, a Mexican botanist had
phoned the CIA to confirm Wassons find, and a CIA agent James Moore was dispatched as a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
587
mole on Wasson's return trip, so that the government could use it as a mind-altering drug in
chemical warfare and interrogation, in Project MKULTRA, demonstrating the Western
establishment's proactively malign attitude and complete failure to understand the nature and
potential social benefits of entheogenic sacraments (Riedlinger).
In 1948, Rappoport had discovered a hormone, named serotonin for its effect on vascular
tone in cow blood serum, which was identified in 1952 to be 5-hydroxytryptamine, or 5HT,
and was discovered in high concentrations in brain tissue in 1953. By 1954 Gaddum and
Hameed, and Woolley and Shaw, both suggested the effects of LSD might arise from 5HT
receptor agonism, or antagonism, because of the obvious similarity with psilocin (Braden).
However as late as 1973 electron donation was still being advanced for the ‘LSD receptor’
for the obvious reason that serotonin itself, although a 5HT receptor agonist, did not cause
hallucinations (Nature 242, 367).
By 1954 Aldous Huxley had captured the imagination of young readers in his description in
“The Doors of Perception” of his experiences with mescalin:
“Confronted by a chair which looked like the Last Judgment - or, to be more accurate, by a
Last Judgment which, after a long time and with considerable difficulty, I recognized as a
chair - I found myself all at once on the brink of panic. This, I suddenly felt, was going too
far. Too far, even though the going was into intenser beauty, deeper significance. The fear, as
I analyze it in retrospect, was of being overwhelmed, of disintegrating under a pressure of
reality greater than a mind, accustomed to living most of the time in a cosy world of symbols,
could possibly bear. The literature of religious experience abounds in references to the pains
and terrors overwhelming those who have come, too suddenly, face to face with some
manifestation of the Mysterium tremendum. In theological language, this fear is due to the
incompatibility between man's egotism and the divine purity, between man's self-aggravated
separateness and the infinity of God. Following Boehme and William Law, we may say that,
by unregenerate souls, the divine Light at its full blaze can be apprehended only as a burning,
purgatorial fire. An almost identical doctrine is to be found in The Tibetan Book of the Dead,
where the departed soul is described as shrinking in agony from the Pure Light of the Void,
and even from the lesser, tempered Lights, in order to rush headlong into the comforting
darkness of selfhood as a reborn human being, or even as a beast, an unhappy ghost, a
denizen of hell. Anything rather than the burning brightness of unmitigated Reality anything!”
The eloquently expressed popularity of these agents began to illuminate the public
imagination, particularly among young people breaking out of a conservative post-war
colonial Christian straight-jacket. From 1960 to 1962, Timothy Leary, Richard Alpert, Ralph
Metzner and others ran a series of projects involving mescaline and psilocybin now referred
to as the Harvard Psilocybin Project. In the Marsh Chapel Experiment, run by a Harvard
Divinity School graduate student under Leary's supervision, Boston area graduate divinity
students were administered psilocybin as a part of a study designed to determine if the drug
could facilitate the experience of profound religious states, and nine out of the ten divinity
students reported such experiences.
Leary’s espousal of LSD, originated from an entheogenic religious experience with sacred
mushrooms:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
588
“Three years ago on a sunny afternoon in the garden of a Cuernavaca villa, I ate seven of the
so-called ‘sacred mushrooms’, which had been given me by a scientist from the University of
Mexico. During the next five hours, I was whirled through an experience which could be
described in many extravagant metaphors, but was above all and without question the deepest
religious experience of my life. … A profound transcendent experience should leave in its
wake a changed man and a changed life. Since my illumination in August 1960, I have
devoted most of my energies to try to understand the revelatory potentialities of the human
nervous system and to make these insights open to others. I have repeated this biochemical
and (to me) sacramental ritual over fifty times personally and, almost every time, I have been
awed by religious revelations as shattering as the first experience” (Weil).
At about the same time a rubber tapper José Gabriel da Costa in Porto Vehlo, Brazil inspired
by his visions under the potion, began a church the UDV or União do Vegetal based on the
Amazonian entheogenic brew ayahuasca, partaken by diverse tribal cultures claiming roots
back to the tenth century BC. Also contemporaneous was the discovery by Calvin Stevens of
ketamine, named a “dissociative anaesthetic” by the wife of Edward Domino, the first person
to test it on humans after describing his amazement at seeing a person who was fully awake
but “not there.” It was found to be a potent hallucinogenic drug, and the effects were
described as trance-like (Jansen).
However reaction to the experimental use psychedelics including LSD led by 1962 to end of
the official experiments, an investigation by the Massachusetts Department of Public Health
that was eventually dropped, and the firing of Leary and Alpert, ruining promising academic
careers, and sending them on a mission to popularize their affects with student culture in a
collision course with conventional society, encouraging the next generation to ‘turn on, tune
in and drop out’ - in retrospect a naïve and fanciful attempt to convert a mono-phasic society
(Walsh & Grob) lacking the multi-layered spiritual traditions which had enabled the ritual use
of such substances for millennia in pre-Columbian cultures. At the time only mescaline and
the peyote cactus were illegal, with some uncertain exceptions for the Native American
church. By 1966 psilocybin had become a schedule I prohibited drug, swept along by social
anxiety about LSD use, and scientific research outside animal studies came to a halt for
decades.
History now embarks on the florid journey that led immediately to Ken Kesey and the Merry
Pranksters, the Electric Kool-aid Acid tests, the Grateful dead singing “Dark Star” and the
Beatles “Lucy in the Sky with Diamonds”, and the hippie revolution of free love, all the time
denounced by the authorities and treated as social mayhem by the traditional media. At
Stanford in 1959, Ken Kesey had volunteered to take part in MKULTRA at the Menlo Park
Veterans Hospital, where he worked as a night aide studying the effects of LSD, psilocybin,
mescaline, cocaine, AMT, and DMT on people. Kesey wrote many detailed accounts of his
experiences with these drugs, both during the Project MKULTRA study and in the years of
private experimentation that followed.
On the basis of a few iconic cases such as Charles Manson, who was a manifest psychopathic
long before his hippie debut, who had pleaded to be allowed to stay in jail at the age of 32,
having spent more than half his life in institutions, the whole flower power movement was
consigned to suppression echoing the suppression of the Gnostics in the witch hunts and
Inquisition. Timothy Leary became a cultural whipping post for the establishment’s
paranoiac vendetta. Having been caught with a couple of marijuana roaches in 1965 and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
589
1968, he appealed the 1965 offence successfully to the Supreme Court and stood for
Governor of California, inspiring the Beatles song ‘come together’ as a campaign number.
However in 1970, Leary was sentenced to 20 years in prison for the 1968 possession charge
but later used his psychological guile to escape. He and his wife were smuggled out of the US
by the Weathermen leading to a long international manhunt, refusal by Switzerland to
extradite, and eventual capture on board a US airliner in Afghanistan. On his re-incarceration
he played double agent and secured early release without incurring the ire of the
underground.
Fig 4: Timothy Leary, Alex
and Anne Shulgin with one of
his
phenylethyamine
molecules
and
Albert
Hofmann with LSD (Alex
Grey), Ken Kesey and the
Merry Pranksters beside the
freak bus, the Grateful Dead
playing at Haight Ashbury.
Stanley Owsley was a sound
producer for the Grateful
Dead, who in September 1965
became the primary LSD
supplier to Ken Kesey and the
Merry Pranksters. By this
time, Sandoz LSD was hard to
come by. While touring the country with the Dead, Tim Scully met Stanley and claimed that
they perfected a pure process. Between 1965 and 1967, Stanley produced more than 1.25
million doses of LSD moving their laboratory our of California when LSD became illegal
there. They briefly made DOM or STP but ceased production when it quickly gained a bad
reputation. Nick Sand was a humanities student, when he took Mescaline in 1961. He also
often visited Millbrook, the communal home of Timothy Leary's League for Spiritual
Discovery. During a vision quest on DMT, Sand came to believe that he should devote his
life entirely to manufacturing entheogens. He became a criminal as a matter of principle and
as an act of civil disobedience, because he believed he was working for a higher good.
In 1969, Nick Sand worked with Tim Scully, producing millions of doses of the Orange
Sunshine LSD. Sand was a member of "a secretive group of hippie acid dealers and hashish
smugglers known as the Brotherhood of Eternal Love. The purpose of the group was "the aim
of transforming the world into a peaceful utopia by promoting consciousness-expanding drug
experimentation through LSD. Eventually both were arrested. At his trial, Tim Scully said
that his intention was to "turn on the world" and as far as LSD chemists go, "we were doing a
public service." Sand relocated to Canada. For roughly twenty years, he formed the core of
international LSD manufacturing, producing about 250 million doses. In 1996, he was
arrested in Vancouver, Canada, where his laboratory was found with 42 grams of LSD, or
roughly 200,000 moderate doses, tested above 100% pure by the government's chemists. By
late 2000, he was given an early release from prison, serving just under four years.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
590
This stark cultural division has resulted in a continuing schizoid fracture in Western society
pitting forcibly protecting a supposed emancipated society from its own freedom of choice
against the right to have personal transformative experiences induced by other psychotropic
substances than alcohol or tobacco. Given the prodigious production of Nick Sand alone and
the lack of concrete evidence of physical or manifest social harm ensuing from such
widespread consumption, and the safety of psychedelics rating far below alcohol and tobacco
in terms of risks, as demonstrated in fig 21, the situation is clearly irrational and socially
counterproductive.
The varying names associated with these substances illustrate society’s schizoid attitude
towards them. The traditional name “hallucinogen” implies ‘mind-wandering’, seeing things
that aren’t there. “Psychedelic” or ‘mind manifesting’ puts a more positive spin.
“Psychotomimetic” incorrectly implies mimicking psychosis - the way such substances are
cited in models of schizophrenia, in contradiction to their capacity to induce integrative
healing and restorative life experiences. Finally we have “entheogen” highlighting the
commonly reported experience that the altered state manifests a spiritual dimension of union
with divinity.
The war on drugs has led relentlessly to the rise of major marijuana, cocaine, heroin and
methamphetamine trafficking on an international basis and a cultural civil war in Western
society fuelled by the unquenchable appetite of the very culture seeking to repress it, and the
insatiable curiosity of the taboos generated by this suppression, fuelling an endemic
subterranean underground, leading on to the euphoric dance culture of ecstasy, and with each
successive banning to the diversification of a multitude of designer drugs with varied and
unpredictable consequences. This is a war of attrition, filling US prisons with social
casualties, with distinct racial undertones. This can end well only in the legitimization of
psychotropic agents and dealing with undesirable social consequences of hard drugs as a
medical problem. The alternative is the complete suppression of any agent that can mimic, or
be construed to transform, or liberate consciousness from its cultural straight-jacket - clearly
not a conscionable outcome.
Meanwhile many of the people formative of the most creative processes in society today
admit they owe a central place in the meaning in their life’s quest to entheogens. To take six
examples on LSD: Francis Crick, Nobel prizewinning co-discoverer of the structure of DNA
later told a fellow scientist that it was LSD, that helped him to unravel the discovery that won
him the Nobel Prize (Alun Rees, Mail on Sunday 8/8/04). Kary Mullis controversial Nobel
prize-winning discoverer of the polymerase chain reaction for amplifying DNA " I found it to
be a mind-opening experience. It was certainly much more important than any courses I ever
took. What if I had not taken LSD ever; would I have still invented PCR? I don't know. I
doubt it. I seriously doubt it" (BBC Psychedelic Science). Steve Jobs said taking LSD was
one of the two or three most important things he had done in his life. He said there were
things about him that people who had not tried psychedelics - even people who knew him
well, including his wife - could never understand" (The New York Times, 10/5/11). Alex
Gray: “Twenty-five years ago I took my first dose of LSD. The experience was so rich and
profound, coupled as it was with the meeting of my future wife, Allyson, that there seemed
nothing more important than this revelation of infinite love and unity. Being an artist, I felt
that this was the only subject worthy of my time and attention. Spiritual and visionary
consciousness assumed primary importance as the focal point of my life and art. My creative
process was transformed by my experience with entheogens.” Stanislav Groff: “In one of my
early books I suggested that the potential significance of LSD and other psychedelics for
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
591
psychiatry and psychology was comparable to the value the microscope has for biology or the
telescope has for astronomy. My later experience with psychedelics only confirmed this
initial impression.” Albert Hofmann: "When you study natural science and the miracles of
creation, if you don't turn into a mystic you are not a natural scientist. I think that in human
evolution it has never been as necessary to have this substance LSD. It is just a tool to turn us
into what we are supposed to be.”
We like to look back on previous cultures with irony at the severe taboos they instituted, such
as stoning women for adultery, burning people at the stake for heresy, or throwing the early
Christians to the lions for their somewhat obsessive beliefs. In retrospect, these penalties look
like desperate attempts to repress natural reproductive and intellectual choices, in societies
who perceive these individual freedoms as existentially threatening because the society itself
is founded on false premises that leave it vulnerable unless dire measures are taken to repress
such feared individual freedoms. It thus serves us well to ponder why our so-called
emancipated Western society has chosen to taboo the very agents that might bring us a new
understanding of the fabric of existence and our place in the universe.
“All the cultures in human history except the Western industrial civilization have held
holotropic states of consciousness in great esteem. They induced them whenever they wanted
to connect to their deities, other dimensions of reality, and with the forces of nature. … They
spent much time and energy to develop safe and effective ways of inducing them” (Grof).
Essentially, as already noted, the problem comes down to Western society lacking any social
process for deep mental exploration in a safe sheltered setting, guided by respected elders, or
people who have personal experience of transformative agents, who are able to provide
protective guidance to ensure a safe passage and a healing outcome. In the sophistication of
modern society, this is a contradiction because this has been a common feature of human
traditional peoples throughout human history.
Although Christianity is a nominally sacramental religion, centered on the Eucharist, the
Christian roots of Western culture are maladapted to inner mysteries conveyed through
forbidden fruit, quickly condemned as diabolical or at least false agents of insanity and
decadence. The mystical path has been under siege in Christianity from the fourth century,
when Athanasius repressed the Gnostic gospels in favour of the social conformity of the
Catholic canon, despite reemergence of mystical traditions in the Cathars and Albigenses, the
Free Spirit Movement and mystics, from Meister Eckart to Margurete Porete, who was
burned at the stake for writing “Mirror to the Simple Mind”. Compounding this, particularly
in the US, is the role of a government whose electoral majority depends on appeasing the
conservative vote, and the consequent oppressive use of the law, strongly aligned with the
capitalist ideal of a mindless consumer society, like Huxley’s “Brave New World”, where
drugs are only accepted as pacifiers of the ongoing consumer culture, tranquillizers and antidepressants are compulsively over-prescribed, and agents which seem to manifestly unhinge
these cultural norms are perceived as existential threats.
The rapidity with which psilocybin was outlawed, without evidence of physical, or social
harm, in contradiction, both to the historical evidence of long-held spiritual devotion, and
ongoing experiments confirming fulfilling spiritual and religious experiences in Western
subjects, shows the process to have been driven by cultural paranoia rather than the public
good. The consequence has been that, in an era of very rapid scientific progress, unearthing
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
592
sweeping discoveries, scientific research into entheogens in humans was consigned to
oblivion. It has thus taken the work of a few researchers, including the those at the Heffter
Institute in Europe, MAPS conferences, Erowid, and of course the work of Shulgin, Nichols,
Stamets, Griffiths and others in the US to bring us to the point, nearly fifty years later, where
the socially beneficial properties of these agents are again becoming recognized and in
particular their capacity to elicit mystical experiences of long lasting value and significance
years later, as reported by both the subjects and their partners and acquaintances (Griffiths et
al. 2006, 2008, 2001, Szalavitz, Brown).
Although MDMA, or ecstasy, is an entactogen, and not strictly an entheogen, it has clearly
become a drug of emotionally transformative ritual use, so this history would not be complete
without including the story of E. The term entactogen, for any chemical agent that induces
feelings of empathy and connectedness in the user, was coined by David Nichols as an
alternative to empathogen, owing to the potential for improper association of the latter with
negative concepts related to the Greek root "pathos" (suffering).
The tale of Ecstasy (Jennings) forms another chapter in the futility and confusion of the war
on drugs. MDMA was first accidentally synthesized in Merck's laboratories in 1912, but lay
forgotten until Sasha Shulgin resynthesized it in 1976. Shulgin saw it as a valuable
therapeutic psychological drug and it remained largely in therapy circles until Michael Clegg,
an ex-priest, who had married, and found MDMA opened the boundaries of positive
emotions and empathy between people, named it “ecstasy” and came to the conviction that
his “mission was to get ecstasy to the wide world”. He began to produce hundreds of
thousands of ecstasy tablets and distribute them legally in Dallas Texas where an
exponentially rising demand led by 1985 to him producing 500,000 tablets a month, making
him the first ecstasy millionaire.
Fig 5: (Clockwise)
Nothing new under the
sun. Late 1930s scare
marijuana
poster
“Murder!
Insanity!
Death! Late 1990s
brain full of holes on
ecstasy poster. Lancet
study used as a basis
(McCann
et
al).
Claimed damage to
serotonin
Raphe
pathways seven years
after monkeys were
dosed with MDMA
(Hatzidimitriou et al).
Claimed evidence of
MDMA dopaminergic
damage in baboons later retracted (Ricaurte et al). The trance rave has become the ritual
celebration of empathy of an entire generation.
However the DEA, threatened by ecstasy's manifest lack of harm and socially positive
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
593
profile, being used by relatively ordinary people rather than a bunch of weird hippies, felt it
imperative to suppress the phenomenon, lest it undermine the entire attempt to treat
recreational drugs as dangerous enemies of society. Ecstasy was thus, without any evidence
of social harm, in 1985 classified as schedule 1, along with cocaine and heroin, ending its
legitimate therapeutic use and driving its manufacture underground. A major part of ecstasy
production then transferred to Europe with increasingly massive black market imports
arriving back in the US.
Ecstasy became the drug of choice in the rave party scene, driven as much by ecstasy's prosocial bonhomie as by trance music and light shows. The NIDA then embarked on a public
campaign to strike fear into prospective ecstasy users, by claiming that a single dose could
permanently damage the brain, using a factually flawed scientific study by George Ricaurte
of the Johns Hopkins School of Medicine claiming to show vast areas of the brain of ecstasy
users were full of full of holes due to loss of serotonin function. When in 2002 Ricaurte
published a follow up study in Science purportedly of MDMA’s effects on rodent brains, he
was forced to retract it, claiming the chemical supply company had incorrectly labeled
methamphetamine as MDMA, which the company overseen by the DEA denied, suggesting
intentional scientific fraud on the part of the US government. When these two strategies
failed, attempts were made to exaggerate the number of cases of ecstasy deaths, however
James Gill, Deputy Chief Medical Examiner New York City states that of 19,000 deaths
undergoing autopsy over a 3 year period, only 22 people had ecstasy in their system at the
time of death and of these only 2 could be construed to have died as a result of ecstasy alone.
Around 2100 people die from drug overdoses in NY in a 3 year period, around 20% of which
are due to paracetamol, dwarfing the ecstasy deaths. Given the fact that, according to the
DEA up to 110 million doses of ecstasy were consumed in the NY area during this time,
these claims also have to be seen as part of a campaign of disinformation. Nevertheless
MDMA has been found to be neurotoxic in rodents and there is some evidence of long-term
effects in humans, which we will examine in due course.
2. The Enigma of Subjective Consciousness
Part of the reason psychedelic entheogens pose such a paradox for Western society is that,
although we have decoded the human genome, come close to discovering the theory of
everything describing the fundamental forces of nature and the cosmological process, and
become a global society driven by digital computer technology, with the powers of nuclear
self-destruction and global impact on the biosphere, the nature and origin of subjective
consciousness remains an unresolved abyss in the scientific description.
This leads to the so-called ‘hard problem in consciousness research’ (Chalmers) - the fact that
conscious qualia and other attributes of subjective experience are so fundamentally and
qualitatively different from the objects and processes of the objective description that no
brain processes such as electrical activity associated with cognitive processes in the gamma
band (Crich & Koch), or conceptual models such as multiple drafts (Dennett), can form an
adequate explanation. The best we can do is link coherent excitations in the global workspace
with conscious processes as opposed to the incoherent unconscious processing of different
brain regions (multiple references under Consciousness and Global Workspace).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
594
Although the scientific description tells us the world around us is made out of molecular
matter and that we as biological organisms are dependent on our fragile brains to survive and
remain conscious, we gain this understanding only as a consensus agreement about our
subjective conscious experiences, which are our only veridical access to the physical
universe, from birth to death. Although brain science sees subjective experience as merely an
internal model of reality constructed by the brain, it is actually through our subjective
consciousness that we build up our consensual description of the physical world, both in early
childhood and through learning scientific ideas of the natural world, so in this sense,
subjective experience is primary and the physical world is inferred. Moreover the existential
status of internal experiences, from dreaming REM sleep to meditative and visionary
experiences, remains undetermined. From the subjective point of view, dreams can be as real
and rich as waking experiences, and their explanation purely in terms of memory
consolidation processes remains ambiguous.
This suggests that the subjective and objective aspects of existential reality might be
complementary. The tantric origin says precisely this - that the existential origin lies in
intimate coital fusion of subject and object, which in their retreat from union become the
subjective conscious mind (Shiva) dancing the dance of Maya or illusion, in which the
cosmic consciousness of the observer becomes lost in the manifold phenomena of the
objective world (Shakti), perceived by individual sentient beings. Likewise the Tao is a
complementarity between creative and receptive Yang and Yin principles in nature. The
quantum description of the physical universe is similarly founded on complementary waveparticles, leading to a series of other complementarities, such as between matter-forming
fermions and force-bearing bosons.
Current cultural perspectives on existential reality remain in a schizophrenic state between a
purely materialistic perspective and religious cosmologies inconsistent with physical reality.
The materialistic view is that we are simply chemical machines, that subjective consciousness
is just an internal model of reality constructed by the biological computer of the brain, that
mind is an illusion which can have no effect on matter and that all human action is no more
and no less than a complex mechanism. If we took this description at face value, there would
be no point in life, no meaning in existence, and the simplest act of voluntarily deciding to go
for a walk in the park would be a catatonic delusion, for in the harsh light of reality, our
conscious minds would have no control over our physical bodies.
At the other extreme religious people believe that the universe was created in seven days by
God producing the plants before the Sun and Moon, that flawed nature is going to be discard
in the Rapture, where we are all going to be assigned to a heavenly life in the skies, or
condemned to eternal hell-fire and damnation amid visions of feathery-winged angels and the
intimate presence of God in the form of an ancient man with white hair. This is clearly a
mentally driven-description, consistent only with a naïve flat-Earth view of the heavens as
great domes in which the stars are set, while we know the upper atmosphere is a vacuum, and
there is no place for the heavenly host in intergalactic space. Looked at with any integrity we
can see that all religious visions, from Genesis to Revelation, are imaginative mental
fantasies of the subjective mind, coming from dreams, prophecies and visionary states.
In reality neither of these descriptions are remotely adequate and Western society stands at a
cross-roads, where the central enigma of existence is still a complete conundrum pivotal to
our understanding of who we are, what we are doing on the planet and how to care for an
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
595
ever more fragile biosphere and protect the diversity of life and the future generations of
humanity from extinction due to our own lack of foresight.
Fig 6: (a) The existential nature of subjective experience and its relationship with
autonomous will remains unresolved. It’s anticipatory properties could be a manifestation of
quantum properties, here illustrated by the Wheeler delayed choice experiment and the
transactional interpretation of quantum mechanics. (b) responses gain wave coherence (left)
when their temporal occurrence becomes anticipated (Basar et al). (c) The eeg consists of
broad-spectrum oscillations characteristic on non-linear chaos, also manifest (d) in active
brain states such as recognizing an odd note in the wavelet transform frequency profile (King
ROC). (e) Discrete change at an ion-channel can excite a hippocampal cell which in turn can
result in cortical excitations through stochastic resonance (Liljenström & Uno). (f) Freeman’s
model of learning through chaotic excitations forming new strange attractors (Skarda &
Freeman, Freeman). (g) High IQ is associated positively with phase shift durations and
negatively with phase lock duration consistent with phase coherence and transitions involving
disordered intermediates (Jung-Beeman). (h) Brain states involving envisaging future
situations are almost indistinguishable from those dealing with past memories suggesting the
brain is organized to deal with past and future using a single space-time process (Addis et al,
see also Marshall, Hassabis et al, Szpunar et al).
We can gain hints of a possible solution to this existential dilemma by looking more closely
at the evolutionary process and at the relation between quantum mechanics and the
neurodynamic brain. Firstly the quantum universe is not a deterministic mechanism.
Quantum uncertainty means many fundamental processes, such as Schrodinger’s cat
experiment are unpredictable. Many physicists interested in the mind-brain problem have
pointed out the quantum uncertainty could in-principle provide a causal loophole making it
possible for conscious mental states to influence a critically poised brain state without
physical contradiction. Many processes in neurodynamics, including self-organized
criticality, chaotic sensitivity and stochastic resonance show that critically-poised brain states
can have tipping points triggered by a single cell, synapse of ion channel, demonstrating
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
596
quantum events could indeed influence whole brain states. Chandelier cells have been shown
to have such recruiting properties (Molnar et al, Woodruff & Yuste).
Notably, although pyramidal neurons have pulse-coded action potential intensities, pattern
discrimination in the cerebral cortex depends not on discrete digital signals, but broad
spectrum wave fronts, whose phase coherence distinguishes an attended stimulus or attended
process from the ground swell of extraneous stimuli. Global phase coherence of excitations
across cortical regions is also the basis of the most plausible current idea of how conscious
brain states differ from unconscious peripheral processing. Phase coherence of the wave
function is precisely the process underlying quantum dynamics as well, since the uncertainty
relation between energy and frequency is derived from counting wave fronts.
To understand subjective consciousness it is fruitful to consider how it evolved in biological
organisms. Neurosystems are not just electro-dynamic systems but heavily dependent on
chemical neurotransmitters. Many of these molecules go back to the first single-celled
organisms. Serotonin, our pivotal example for entheogens, has a very early origin with
photosynthesis, where the indole group of tryptophan is the receptor of excited electrons.
Serotonin and melatonin thus emerge as signalling molecules as soon as bacterial
photosynthetic processes provided oxidation potential (Mu ller & Jacobs) and may have
become ubiquitous through horizontal gene transfer (Iyer et al). At another extreme, immune
reactions to soil bacteria appear to be able to induce an antidepressant effect in the prefrontal
cortex through serotonin emission at the Raphe nuclei (Lowry et al). The hepta-helical
protein family, common to G-protein linked serotonin receptors and many other
neurotransmitters, as well as the rhodopsin of the eye, although one of the most sophisticated
and diverse receptor types, occupying two percent of the human coding genome, is also one
of the earliest to appear in evolution (Mu ller & Jacobs).
This evolutionary picture means that most of the critical features of both electrochemical
excitation, and biochemical modulation, were already in place in excitable single eucaryote
cells, in providing them with complex and diverse responses to their environment. One can
see this in the neural nets of coelenterates, such as hydra, which has twelve distinct modes of
locomotion, where it is not the structured organization of the nervous system which provides
for complex behaviour, as there is only a disordered primitive net, which can reassemble
along with the entire organism if it is turned inside out, but the dynamic sophistication of the
individual neural cells (King 2008).
This picture addresses one fallacy, coming from the artificial intelligence school of thought,
that the brain is just a very complex sophisticated computer, which, given the right kind of
firmware and software design, could be replicated in principle by a digital computer thus
showing consciousness is only a question of computer design. There are several reasons why
this is in fundamental conflict with the way the brain evolved. Most, if not all, environmental
decision-making problems are computationally intractable and prone to exponential runaway,
like the travelling salesman problem, because the complexity of the computation grows
super-exponentially with the factorial of the number of incident factors involved. The gazelle
can’t afford to wait at the cross roads until its computer solves each survival issue or it will
surely get jumped by the tiger without ever having made the decision, so the brain has to find
a way to make real time decisions regardless of classical complexity.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
597
The brain appears to have solved this problem by utilizing massively parallel processing
rather than a set of serial processors with only nominal parallel capacity. However parallel
processing is not naturally suited to digital signalling because the traffic management
problem of parallel threads becomes unmanageable. To avoid this, the brain appears to use a
combination of wave front coherence processing and chaotic sensitivity. Wavefront
coherence is ideally suited to parallel processing in precisely the way a hologram is, the wave
fronts can be continuously superimposed and only the phase-coherent ones will reinforce.
Dynamically this spatial superposition is complemented by non-linear temporal dynamics,
which provides for sensitively-dependent transitions in and out of chaos, enabling the
dynamics to remain critically tuned to its own self-organized criticality.
This brings us to an even deeper problem complementing subjective consciousness, that of
intentional or ‘free’ will. All our ideas of personal accountability, and the rule of law and
religious guilt, let alone our sense of sanity and personal autonomy, hinge around the notion
that we can make conscious decisions about the physical world. Yet science tends to argue
that this is an illusion and that we are really helpless victims of our brain state. Hence genetic
predispositions have become commonplace defence arguments against criminal culpability.
However many of the environmental decisions our gazelle must make do not depend on
determining factors, but on unrevealed contingencies, events yet to happen, and on situations
where several choices might all lead to viable outcomes, something akin to collapsing the
wave function of Schrodinger’s cat in the quantum description. There may be a lion on the
mountain path and a tiger on the jungle path, or neither today. What matters is anticipation,
and it is here that subjective consciousness is tuned to do two things, firstly to give an
immediate hunch which path to take, and secondly to be acutely sensitive in an anticipatory
way to existential threats that may be about to strike as the gazelle goes to the water hole.
This gives us a much clearer idea of why the blind watchmaker of evolution arrived at the
sappy biochemical conscious brain, rather than a blue gene super-digital computer. And why,
despite having 1011 neurons and 1015 synaptic junctions, the human brain is a lousy computer,
no better than a cheap pocket calculator. The brain is not a computer at all, but a real-time
space-time anticipator using chaotic sensitivity, wave super-positions and quantum
entanglement to anticipate reality, by setting up dynamically unstable global brain states
limiting in effective cat paradox experiments, possibly utilizing unusual aspects of quantum
reality in the process. Quantum theories including quantum electrodynamics are timereversible and examples, from the Wheeler delayed-choice experiment, to many
manifestations of quantum entanglement and the handshaking processes in the transactional
interpretation, illustrate ‘spooky’ potentialities spanning space and time.
Intriguingly recent brain scan studies have shown the cortical regions excited by looking into
the future to be virtually identical to those involved in memorizing the past (Addis et al,
Marshall, Szpunar et al) and damage to episodic memory structures also prevents subjects
being able to envisage future events (Hassabis et al), suggesting the way the brain is going
about this is in a sense ‘time symmetric’. This raises all manner of to be elucidated questions
about the anticipatory capacity of subjective consciousness, including reports and studies of
precognitive dreaming (Dunne).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
598
3. Fathoming the Mind-Brain Relationship and Experiential Modalities
Both electrodynamic magnetodyamic EEG and MEG investigations and metabolic PET and
fMRI scans utilizing radioactive metabolites and nuclear magnetic resonance have provided
windows on the active brain in live subjects which give us a much clearer idea of how brain
processes correspond to conscious experience. The former have good temporal but low
spatial resolution while the latter are slow in time evolution but spatially more precise.
The mammalian brain is dominated by the cerebral cortices, a wrinkled pair of envelopes of
neural tissue forming a sheet about a quarter of a metre in area populated by some 1011
neurons in five to six distinct layers, consisting of excitatory pyramidal cells mediating the
output, innervated by a variety of inhibitory and excitatory inter-neurons, the ‘grey’ matter,
with different regions connected by bundles of axon fibres, the ‘white’ matter connecting
different cortical regions, including traversing the two hemispheres, in a massive conduit
called the corpus callosum. Each pyramidal cell has dendrites permeating all the layers, with
up to 104 incoming excitatory and inhibitory synaptic junctions involving a spectrum of
distinct neurotransmitters. It is believed the cortex is organized into around 108 mini-columns
each consisting of 50-100 neurons responding to one common feature. It is believed that the
basis of the EEG’s brain waves consists of resonant excitatory and inhibitory circuits in the
cortex, and that fast oscillatory activity in the gamma band 30-80 Hz may correspond to
active cognitive processes.
With the exception of olfaction, which has direct input through the olfactory bulbs, sensory
input to the cortex and output from it, pass through a series of ganglia in the thalamus.
Excitation of the cortex is maintained both by active loops between the thalamus and cortex,
and by a series of basal brain centres including the Reticular Activating System, and centres
mediating specific neurotransmitters, including the Raphe nuclei, and Locus coeruleus,
mediating ascending serotonin and nor-adrenaline (nor-epinephrine) pathways which fan out
widely across the cortex, entering specific layers to modulate excitatory tone and mediate
conscious arousal and the cycles of REM and non-REM sleep. A similar dopamine pathway
fans out into the frontal cortex to do with reward. An intriguing slant on the complex role of
serotonin in mood is that knockout mice lacking tryptophan hydroxylase 2 which cannot
synthesize serotonin, lack all sexual selection in mating, which is reversed by supplementing
with 5-hydroxytryptophan (Liu et al). In addition there are loops of activity running from the
cortex to the striatum and basal ganglia, to the thalamus and back to the cortex - the CSTC
loop, involved in learned motor activities such as piano playing, which also play a role in
learned cognitive behavior and can be disrupted by Parkinson’s and Huntingdon’s diseases.
Another loop runs through the cerebellum, to do with bodily balance and finely-timed
movement, which also plays a role in finely-timed cognition.
The regions of the cortex broadly form a mathematical transform akin to a hologram
(Pribram), consisting of a set of sensory and abstract features defining each subjective
experience. Thus each experience consists of multiple features and each feature can be
associated with multiple experiences. There is thus no specific cortical centre associated with
consciousness and the best correspondence that can be made between conscious thought, as
opposed to subconscious processing, is that conscious processing corresponds to globally
coherent excitations channelled through the major attention networks, as opposed to regional
processing which is ‘out of phase with major global processes but might come to contribute
to them with the changing brain state.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
599
Fig 7: (a) The human brain outlining cortical areas, as well as underlying structures including
the thalamus and limbic system, including the hippocampus processing long term episodic
memory and the amygdala dealing with multi-sensory reactions to flight and fight survival
and basal brain structures, including the Raphe nuclei and Locus coeruleus involved in sleep
wakefulness cycles. (b) The cortex consists of up to six layers of neurons in which pyramidal
cells provide the excitatory output from one region to another while inhibitory and excitatory
inter-neurons provide lateral inhibition and feedback. The 1011 cells in the cortex are believed
to be organized into around 108 mini-columns each processing a single feature. The cortex is
dynamically organized into functional regions processing features of experience in massively
parallel ‘computation’ here illustrated in verbal tasks (c) involving Broca’s vocal expression
and Wernicke’s semantic interpretation areas and parallel processing of visual features (d)
e.g. of colour and motion. (e) There are believed to be two attention systems in the human
brain (Fox et al.) a bilateral dorsal attention system (blue) involved in top-down orienting of
attention and a right-lateralized ventral attention system (red) involved in reorienting
attention in response to salient sensory stimuli which occupies location in the right
hemisphere somewhat complementary to the left hemisphere language areas, although the
language areas tend to be more bilateral in females, who also show differences in the balance
of focal and salient attention responses to crisis. (f) A third network has also been associated
with mental activity not tied to the immediate stimuli loosely entitled the default circuit
(Raichle & Snyder, Mason et al, Fox D, Horovitz et al, Buckner et al), because it was found
to have decreased activity when attending a sensory task (above) while the same areas
become active when resting, following a stream of thought, or daydreaming. This is believed
to be involved in rehearsing future scenarios (Marshall) to aid survival. Different forms of
meditation display structured forms of control of the attention process and brain activation.
(g) Zen meditation studies (Pagnoni et al, Ritskes et al) in which subjects are asked to switch
from a verbal task to contemplation show transient activity consistent with the default circuit
which is more quickly suppressed by experienced meditators more effectively inhibiting
verbal thought. (h) Carmelite nuns entering oneness with God show fMRI activations in areas
in very specific frontal, parietal, temporal and basal areas consistent with directed control
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
600
(Beauregard & Paquette). (i) Likewise Tibetan Buddhists performing compassion meditation
for other people’s suffering show specific activation in limbic regions including cingulate
cortex and insula, consistent with an empathic response to another’s pain (Lutz et al 2008). (j)
Sex differences in language areas (Shaywitz et al).
A good idea of the way features are mapped across the cortex can be gleaned from examining
the major cortical areas. The rear occipital cortex contains primary visual areas responding to
lines of a given orientation, and with increasing abstraction, more abstract features such as
human faces, facial expressions, and as we move forward across the parietal lobe, spatial
relationships, such as finding one’s way through the city. Colour and motion are processed in
parallel in complementary regions and over twenty different visual areas have been identified
dealing with different visual aspects.
Where the parietal deals with spatial relationships, where things are, the temporal deals with
what they are. Hearing is processed to either side of each cortex in the temporal lobes, which
also have major functions in representing temporal processes like melodies, semantic
memory, and associating a given situation, with a variety of others sharing abstract features
with the current one. Many features of hearing, such as melody, pitch and rhythm are
processed in parallel in different areas, although the primary auditory cortex is believed to
have a tonotopic map similar to the line detectors of the visual system.
Separating frontal areas of the cortex from the parietal is the deep fold of the Sylvian fissure.
To the rear of this is the somato-sensory cortex with a map of the bodily areas,
complementing our visual experience of the outside world with our tactile sensations of
ourselves. To the frontal side of the fissure we have a corresponding motor map of
musculature and bodily actions. As we move further forward into the prefrontal cortex we
have increasingly abstract features of action, consisting of how we apply focussing attention
to control our thought processes, and our idea of our active goals and what we want to
achieve in life. Many specific prefrontal areas governing forms of executive control have
been elucidated from studies of the effects of damage to these areas. Some prefrontal areas
affect cognitive control of attention while others such as the orbito-frontal leave intellect and
IQ unaffected but disrupt the person’s capacity to make realistic emotional life decisions. The
region around the principal sulcus of the frontal lobes contains both an active representation
of the visual field, enabling working memory to anticipate actions in time, and a
representation of what these things are, forming a complementary relationship with parietal
and temporal regions in working memory (Kandel et al). We can thus envisage conscious
thought processes in terms of a ‘global workspace’ consisting of major feedback resonances
between the frontal cortex and the temporal and parietal mediating the spatial and temporal
aspects of the ongoing decision-making process.
On the inner side of the cortical sheet facing the centre plane is the cingulate cortex, dealing
with emotional representations. This is also connected with the extreme of the temporal lobe
and two other centres on the periphery of the cortical sheet, the amygdala and hippocampus
in a global feedback loop loosely entitled the ‘limbic system’, associated with emotional
dynamics. The amygdala has a role in integrating sensory experiences in relation to flight and
fight survival and the hippocampus has a pivotal role in laying down experiences into
sequential memory. Temporal lobe epilepsy can give rise to complex orchestrated
experiences, some of which can be given a quasi-mystical status by the subject. This caused
the neuroscientist Ramachandran to suggest that Temporal lobe excitation carrying across to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
601
the amygdala could be the basis of religious experiences of emotional exaltation combined
with overwhelming significance - the so-called “God spot”. At the least this gives an
interesting interpretation of religious fervour as an idiopathic brain state (Ramachandran &
Blakeslee, Persinger, Bielo).
Several key processes, including language, are believed to be lateralized, enabling the two
cortices to have complementary functions. For example, language meaning is processed in
the left temporal Wernicke’s area and fluent execution in the left frontal Broca’s area,
although women often appear to have a more bilateral processing of language, in which right
hemisphere activity might be associated with creative use of language. Due partly to some
intriguing experiments in which the corpus callosum of intractable epileptics has been
severed, the concept of lateralization has led to some fanciful concepts with only partial
validity, stylizing the left hemisphere connected to the right hand with structured organized
processing and the elusive right hemisphere with intuitive and creative processing.
Consistent with this view, two opposing global attention systems have been identified, one
the dorsal attention network deals with focal attention in the global workspace and is bilateral
connecting areas such as the frontal eye fields to parietal and other areas. Complementing this
is the ventral attention network whose role is to bring in salient stimuli, important to the
subject, from the periphery. Intriguingly this has lateralized activity in the right cortex,
complementing the left hemisphere regions traditionally associated with language, lending
support to the above model of lateralization. A third system connecting the frontal anterior
insula and the anterior cingulate, involving fast-transmitting von Economo neurons, may
mediate integrated bodily interoception, emotional and cognitive awareness and timed
framing of the immediate present, forming a central process of self-consciousness (Allman et
al, Cauda et al, Craig, Williams).
A fourth system, the ‘default network’, is associated with mental activity not grounded to any
immediate activity. It was first discovered because there were areas with enigmatic
deactivation in a variety of brain studies. When subjects were then tested just resting or
daydreaming the same areas were activated. The default circuit is activated by processes as
diverse as autobiographical memory, envisioning the future, theory of mind, moral decisionmaking (Buckner et al, Mason et al, Raichle M. & Snyder), as well as mind-wandering
activities such as daydreaming and worrying. The default circuit is believed to be a state in
which we aid our survival strategies by using down time to rehearse impending situations of
significance to enhance our ability to cope with them successfully. It has also been associated
with improved creative thinking over focussed working memory, for example in solving
counter-intuitive puzzles (Christoff et al).
Dreaming, or REM sleep remains an enigmatic and life-shaping aspect of subjective
experience whose physiological and experiential status remains unresolved. Sleep begins
with shorts EEG bursts called sleep spindles interrupting waking EEG and enters a series of
cycles, in which waves of deep slow wave SWS sleep alternate with rapid eye movement
REM or dreaming sleep, where the cortex has an EEG similar to the waking state, and the
body, except for the eyes, is effectively paralysed by a filter in the basal brain. The cycles of
deep sleep are driven by synchronous burst firing in the thalamus interrupting the low voltage
asynchronous passage of information to the cortex, associated with the activity of waking and
REM sleep. Sleep cycles, although they appear to occur widely across the animal kingdom
from arthropods (Shaw et al, Hendricks et al) to vertebrates (Hobson), vary a great deal
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
602
among mammals with different circadian habits (Siegel 2001, 2005, 2008). The sleep cycle,
like the default network, has been associated with aiding the brain in forming better responses
to strategically stressful situations plaguing waking life. Although the REM state is similar to
waking EEG, fMRI and PET scans show reduction of prefrontal activity and heightened
activity in visual areas, as shown in fig 11.
Both REM and non-REM sleep have been associated with memory re-encoding and
consolidation. Non-declarative aspects of memory, from solving the towers of Hanoi to
physically manipulating an unstable object, show significant improvements from the learned
plateau with specific sleep phases, from REM, through light stage 2, to deep SWS sleep.
Episodic memories are thought to consist of multiple hippocampally linked memory traces
located within neocortical regions and dependent on the hippocampus for their integrated
recall, Cycles of SWS and REM sleep appear to be associated with re-encoding of
emotionally significant memories, with information passing between the hippocampus
holding space-time indices of significant recent experiences into long term optimized form in
the prefrontal cortex. Hippocampal activity is enhanced over other activity in REM as against
both waking and non-REM sleep, while the dorsolateral prefrontal cortex, involved in
decision-making and memory, becomes further inactivated. Low cortisol and reduced
reticular acetyl-choline activation early in sleep favours cycles of deep SWS, with cortisol
rising slowly over the night, as periods of REM sleep become more accentuated. Studies have
detected replays of spatial tasks in the hippocampus, time-compressed in SWS, and then in
REM. REM is also believed to enhance synaptic plasticity resulting from adapting to novel
environments, enhancing the adaptive response (Payne & Nadel, Stickgold, Stickgold et al,
Maquet et al, Nielsen).
These cycles are mediated by reciprocal changes in activation between the reticular activating
acetyl-choline system and serotonin, nor-adrenaline and dopamine pathways fanning out
across the cortex from the hypothalamus and basal brain nuclei (Saper et al). In REM, the
Raphe nucleus serotonin and Locus coeruleus nor-adrenaline pathways mediating cortical
responsiveness and arousal in the waking state are silent, while there is reticular activation of
acetyl-choline pathways, in excess of the waking state and an EEG similar to waking, rather
than the light sleep spindles, or slow waves of deep sleep.
Memory processing may be consistent with many of the experiential features of dreaming,
such as bizarre content, which may appear to mix features of many experiences, and dreams
being perceived as direct experiences in the present, often having emotionally charged
character. Although dreams can be hard to remember, and episodic memory is idiosyncratic,
dreams and particularly intense nightmares, can have substantial episodal content.
Furthermore a person can often retrogressively remember quite long sequences of dream
episodes on lying still on waking from a dream provided the weird disconnections plaguing
dreaming experience can be negotiated. Brain scans of REM sleep show strong activations of
perceptual, e.g. visual areas, while the prefrontal cortex has reduced activity consistent with
the relative difficulty we have controlling the direction of our dreams and also with the
memory consolidation model.
Dreams can have a very rich existential status, often as convincing to the experiencer as
waking life, making it hard to give oneself criteria to distinguish dream from reality, for
example to endeavour to enter a lucid dreaming state. The existential status of dreaming
experience remains undetermined, along with any perceived implications for subconscious
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
603
discovery or prophetic precognitive hunches. Although dreaming reality may be just a
manifestation of memory processing, just as waking life may be just an internal model of
reality constructed by the brain, the existential nature of dreaming experience remains a
challenging and very different realm from waking experience, whose potentialities remain to
be fully explored.
By contrast with the rich and bizarre nature of dreaming, mental states associated with prayer
and meditation tend to involve focused control and suppression of the wandering mind
through limiting the verbal thought process, or focussing on a spot. While these mental states
are highly varied, they share common features of intentional control of the mental process.
Zen meditators in fMRI studies show more rapid and complete suppression of the mindwandering of the default network (Pagnoni et al), with increased activity in the prefrontal
cortex and basal ganglia and decreased activity in the occipital (visual) cortex and anterior
cingulate processing emotion (Ritskes et al). In EEG studies they showed a significant
increase in frontal alpha and occipital beta power, whereas an average increase of theta power
was observed in controls indicating loss of concentration (Huang et al).
Tibetan Buddhist meditators in PET and fMRI studies have increased blood flow in the
cingulate, inferior and orbital frontal cortex, dorsolateral prefrontal cortex and thalamus
(Newberg et al 2001, Hanky). EEG studies show greater activation in attentional regions,
including fronto-parietal, cerebellar, temporal, para-hippocampal, and posterior occipital,
possibly due to the attended dot (Brefczynski-Lewis et al). They have also been found to
enter high-amplitude gamma-band oscillations with high phase-synchrony during meditation,
consistent with a one-pointed concentration with heightened attention (Lutz et al 2004). By
contrast, compassion meditators under PET show similar activations to a person feeling
empathy for a person in pain (Lutz et al 2008). In a more recent fMRI study contrasting
“focused-based” and “breath-based” practice. In the first, blood flow increased in the medial
prefrontal cortex and left caudate, but decreased in parietal and occipital regions. The second
induced activation in several limbic structures and the left superior temporal cortex (Wang et
al).
Investigation of Transcendental meditators by PET (Newberg et al 2006b) also found
bilateral prefrontal activation associated with relaxed attention on the mantra, other increases
in frontal, occipital and parietal areas and a decrease in the thalamus and hippocampus. An
fMRI study centered on the capacity of the relaxed state to be helpful in dealing with an
induced painful stimulus saw reductions in the prefrontal cortex, anterior cingulate cortex,
and thalamus (Orme-Johnson et al), and has been suggested to be linked to hormonally
induced increases in GABA (Elias et al). Catholics observing a Marian image saw increases
in the ventrolateral prefrontal cortex and brain stem leading up to the thalamus (Wiech et al).
Brain studies of Carmelite (Beauregard & Paquette) and Franciscan nuns (Bielo) in professed
‘union with god’, which they admitted was difficult to achieve in a noisy MRI tunnel, show
different structured activations, with increased activity in the caudate nucleus associated with
learning, memory and falling in love, the insula processing body sensations and social
emotions, the inferior parietal processing spatial awareness in contradiction to the Zen
studies, the medial orbito-frontal and prefrontal cortices dealing with emotional and
executive decision-making, and the middle of the temporal lobe. Most prevalent brain waves
were long, slow alpha waves such as those produced by sleep, consistent with a relaxed state.
By contrast with the prefrontal control evidenced in Buddhist meditation, during speaking in
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 579-604
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 1
604
tongues, by Christian women who had practiced glossolalia for more than 5 years, there was
a decreased blood flow in the frontal lobes bilaterally and in the left caudate, indicating
relaxation of executive controls (Newberg et al. 2006a).
In comparing these highly varied and contradictory results, one can conclude that claimed
states of higher spirituality are varied products of different forms of concentration, which
share the feature of overall focused control, but otherwise look like distinct humanlygenerated states of mind, rather than convergence on the ‘divine’. One needs to consider the
possibility that the profound transformations of the cortical dynamic induced both by
dreaming and by entheogens may give rise to deeper potential for exploratory existential
processes, which might nevertheless be enhanced by contemplative repose.
[References at end of Part 4]
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
1101
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
Article
Foundation of Reality: Total Simultaneity
Wilhelmus de Wilde*
ABSTRACT
In this article, I put forward the hypothesis of Total Simultaneity (“TS”), a “fifth” dimension
behind the Wall of Planck reality at which we pass the limits of causality at the quantum scale
and “Now” as we perceive no longer exists. TS can be reached by every point of our 4
dimensional universe and singularities only exist in our consciousness. The other limit of
causality is the local speed of light c at which time stands still so there is no more before and
after. All information of all parallel universes and multiversity constitution in TS is
simultaneously present and available, our consciousness is able to align points out of the TS
and so create the observable analogue universe that we are aware of. The totality of
information from other universes (also partly observable by other consciousness) is
influencing our linear causal deterministic universe, the origin of gravity, dark matter, and the
dark energy may emerge from here. The Big Bang is an imaginary non-existing point in the
TS area. Inflation is avoided by projecting inflation time into the area after the Wall of
Planck, uniformity in the structure of space-time is also guaranteed. Our mind with its 100
billion neurons is able to cope with infinities because it has parallels with the qualities of TS.
Key Words: reality, simultaneity, fifth dimension, Planck, wall.
The Causal Limits
One night when I came home late at night, I left my car and contemplated the night sky with
its beautiful view on the stars and our milky way; (living in the country means also that there
is no trash light disturbing the view). I recognised the stellar formations that mankind already
recognise since the early Egyptians, the imaginary lines that form imaginary drawings in the
sky. But can’t we also draw these imaginary lines in different ways so that other forms and
constellations are created? The creative freedom of our minds has no limits.
While looking at this marvellous lightshow, I got the idea that each line between these points
of light could be interpreted as a possible reality sequence of another universe, and that all
these realities are already present, you only have to draw a line between points of light.
Drawing such a line is the typical way of expressing history in our causal four-dimensional
world, where the arrow of time has a direction from past to “now” to the future.
Describing the multiversity and parallel worlds can only be incomplete, because we have no
means to describe other dimensions, especially one where all the pasts, the now’s and the
futures of all possible universes are united, you can call it a “fifth” dimension at the edges our
own but this is also a sequential expression a down to earth explanation.
One of these edges is what scientists describe as the “Wall of Planck” (10-33cm / 10-43sec),
behind this Wall we encounter the creativity of humans, like M theory: 10 enrolled
*
Correspondence: Wilhelmus de Wilde. E-Mail: wilhelmus.d@orange.fr Note: This article was first published in Scientific GOD Journal,
2(4): pp. 334-342 in 2011 and is based on a submission to FQXi Essay Contest “ Is Reality Digital or Analog?” in 2011.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1102
dimensions and/or branes and on the other hand we encounter singularities with no
dimensions at all. These theories can (until now) not be proved with tests, science becomes
philosophy with presumptions, hypotheses, assumptions and countless beautiful formula’s
that are very difficult to understand for non specialists , also metaphysical and transcendental
ideas are soliciting on an equal base for a place in this area.
So, once we reached this Wall of Planck, behind it we would experience the non causal
dimensions of the origin of our own space-time and many other universes, which also means
that after this Wall there is no separate past, no separate now and no separate future. It is
the All in One, the Total Simultaneity (from now on to be called: TS, not to be confused
with the Absolute Simultaneity of Albert Einstein that is a simultaneity occurring in a causal
relativistic universe) where all possible pasts, now’s, futures and places of all thinkable and
non-thinkable universes are simultaneously “present”, comparable with our memory where all
the events of the past have an equal place, only active thinking replaces this events in a linear
causal sequence. The TS is what we will refer to as a fifth omnipresent dimension.
We can in fact reach it at any point in our space/time continuum by approaching the Wall of
Planck, until now we cannot yet reach behind this wall, so the “constitution” of this dimension
is still unknown, every part behind the Wall of Planck is of the “same quintessence” (in
reference to Aristotle where he cited that the world was not only made of earth, water, air and
fire but also of a fifth element that made it possible to function) with the same properties, so
it is as we can see our universe emerge from this fifth dimension, every space/time quantum
having a different quality and quantity of information retrieved from TS. The diameter of
these quanta (spheres) is the Planck-length, on a bigger scale the universe that descends from
this dimension is appearing as a continuum obeying to thermodynamic laws, that differs
totally from the quantum laws, being the reason why General Theory of Relativity and
Quantum physics will never merge to a unity.
When we apply “Ockham’s Razor” this approximation is a simpler approach of the origin and
existence of our universe, we have no longer to deal with infinities that will lead to paradoxes
in our linear world. There is no need for multiple dimensions/branes and/or points without any
dimension (every one of them also “existing” after the Wall of Planck), later on we will come
back to the origin of the existing fine-tuned constants.
Our Consciousness
Imagining a line between certain possible points in the TS makes our consciousness
understand history and the qualities of our universe. All sort of possible imaginary lines,
between the infinity of information points available, (information is of another quality as data)
can be drawn for all other imaginary and non-imaginary universes. It is our consciousness that
“connects” these points and creates the lines that we perceive, like a piece of music that
becomes “reality” in our mind by connecting points of our memory and so forming a
sequence.
We must also apply this view-point to the cores of black holes that should contain a
singularity, but singularities are points inside the area of TS, we only have to realise that each
point in our universe touches this Wall of Planck and so TS, replace singularities by the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1103
quantum with the diameter of 1.616252x10-33cm, at the edge of TS. The information of this
core-quantum equals the information of the quanta of the beginning of our universe.
Creation of our universe ex-nihilo is no longer needed, creation of something out of
nothing, singularities, FIAT LUX as proposed by our religions, our causal material universe
does not allow infinities, because there are borders. Creation is in fact all around us, every
moment. Transcendent theories are explaining the beginning by assuming an external “GOD”
as a Creator and all the other infinities that the human spirit/mind is able to think of. Aren’t
we are obliged to divide our infinities in TWO in order to understand a Beginning and an End,
a Yes and a NO, we have to digitalise them. Once an infinity is divided in two it is no longer
an infinity, but is it two infinities? Paradoxes all over, these occur from the difference in
structure of our “multi-reality TS” minds and the analogue causal deterministic reality world
that we live in, where the edge on the quantum side is the Wall of Planck.
We are at this moment in the proficiency to “create” for two of our senses, sight and hearing,
a digital world, constituted of 0’s and 1’s , or should I say Zero’s and Ones, or is it better
even for the understanding to name them Yes or No, to indicate the question(s) before. These
CAUSAL SEQUENCES of two understandings that constitute so called soft-ware that with
the aid of a complex machine called computer can let emerge for our eyes and ears a world of
video and sound are the basics of our digital reality. In our consciousness we replace
ourselves in this virtual digital reality, for example in a role playing game, the bearers of these
data (in the role playing game there are different ways to experience an adventure called life)
has some parallels with the TS, different lines of reality can be followed, lining up different
quanta of information of the time/space continuum. However the exactness of the sequence
of these yes and no’s, in our digital causal world is of the essence, if one zero is replaced by
a one then the whole perception falls apart the virtual reality becomes blurred , this is a typical
property of our causal four dimensional world.
Bits, Qubits and Reality
In the world of the future quantum computer, qubits represent the equivalent of the Yes and
NO. However qubits don’t offer only two possible choices of yes or no, each qubit in fact
represents an infinite superposition of possibilities, as indicated in the “BLOCH” sphere (the
superposition of the two states is described by a linear combination with the form a x 0 + b x
1, where all the values of a and b are complex numbers) all these possible quantum states of a
qubit we have to bring back to our “digital” status of 1 or 0, because we have to experience
the results as causal sequences.
The qubit’s superimposed state is comparable with the infinite possibilities of drawing realitylines in the TS. In fact, once we will have constructed a quantum computer, even when this
“machine” is not “working” (under tension), it will hold already all the answers for all our
possible questions also those that not yet posed. So we have to try to search for a more
adequate form of “handling” in order to optimise our results, maybe the future solution will
not be the way used in the binary computer (for instance: for 1000 qubits we have 2^1000
possible configurations: 10^300 which is more as all the atoms in our universe, so we can
stock 10^300 solutions for a problem, in other words we can treat at the same time 10^300
potential solutions.)
Four stages of “reality” are appearing:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1104
1. On the smallest scale the “quantum” multi-reality TS” which is a superposition of
states, out of this multi-reality this quintessence contains the information of the
quanta spheres with diameter the Planck length that are by our consciousness unified
into linear sequences constituting our analogue “reality”. When we are constructing a
quantum computer it should be possible to let emerge a new analogue reality, like
forming a new reality-line in the TS that should also be accessible for our
consciousness.
2. Our analogue reality “the every day” reality which is the result of the for our
consciousness sensible line in the TS (see 1). In this reality , each human is aware of
his own sequences of points in the Total Simultaneity , comparable with the
phenomenon that our consciousness perceives a film on television while in fact it is a
sequence of digital bits.
3. The digital virtual reality, which is a sequence of bits that is created by ourselves
(until now for two senses), because of the causal property of these sequences (it is
created in our four-dimensional causal deterministic world) this virtual reality will be
totally dependent of the reality as experienced in our consciousness and so is a subreality.
4. The “social” analogue reality that is formed by the human “qubit”, forming society’s
that seem to have an existence of their own, but in fact are receiving the input from
the single bits of information , this social reality has also parallels with the quantum
reality because of the fact that every qubit has multiple information available like a
superposition of states. We are now with about 6,9 billion people on earth. Every
human is a bearer of information, like a qubit , together we are forming a complex
system reacting as a whole, making progress in science as a whole, making war as a
whole, especially in this information era every “qubit” of mankind reacts(output)
directly on events (input), thus transforming his observable analogue reality and
creating a over-consciousness (not sub).
In the future digital virtual linear reality’s will be created for our five senses in which
mankind can experience virtual multiverses, imagined by himself , attaining another level of
consciousness, a sub reality like it is formed by the sequences in the T S . Shall we create a
new kind of digital “consciousness” a sub-consciousness linked to our present consciousness
that is aware of this virtual world as if it was its real analogue world? Will it be possible to
create for this sub-reality a new form of consciousness that like our consciousness will start
searching for his own grail of understanding that on its turn, created him. Will this subconsciousness once also reach to the echelon of a non-linear universe?
Continuous Creation of Reality
Why is it that our consciousness is sensible for information available in the TS and is able to
“handle” it? Our mind is made of neurones, each human has 100 billion neurones (!) where
electrons are moving from one neuron to another, if these electrons were in superposition
(wave or particle) they would encounter at every split of neurons a decision point (like the
Young Double Slit experiment) spiralling from one information point in TS to another and
thus creating for our consciousness a analogue causal linear universe.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1105
All together on one side our five senses are giving the input of the signals we receive (only
signals from the past) , thus these observations changing into information, this information is
brought back to electrical currents in our super (quantum) computer of 100 billion neurones,
creating all kind of possible observable realities, (see page 3 where 1000 qubits are available
for 10300 solutions!) one of which is taken as the analogue sensible reality that someone will
be aware of.
This newly created virtual world also has to obey to specific fine-tuned constants (exact
sequences), if one of them differs from the constants as we perceive them, that specific subreality will longer exist for us. You can wonder if we will be able to create the kind of
exactness that is needed in arranging these specific sequences that are in conformity with the
exactness of all the fine tuned constants that we perceive around us (Cosmological, alpha,
value and charge of the electron….).
When approaching this problem it is like solving the problems of so called Quasi Polynomial
Time and NP complete decision problems, it would be adequate to be able to go back in time
in order to realise “more” time. This was the origin of the so called time-loops (David
Deutsch, Oxford University, 1991), these time loops make space-time interchangeable with
the parallel universes in order to make them accessible for calculation, the grandfather-son
paradox that will not occur because we arrive at another line of “reality” in TS, we are
entering in a SPIRAL timeline.
Our quantum computer as a tool is able to, before showing solutions, in a superposition of
states, like the TS, create possibilities like using parallel time and parallel consciousnesses’.
By reaching out at the qualities of the TS, we may be able to touch in this way the
dimension/area after the Wall of Planck.
In our analogue world we encounter different forces and one of the forces to enhance into the
Theory of Everything is the gravitational force. Scientists are trying hard to understand it, one
of the theories that come near to the TS notion is the theory posted by Eric Verlinde of the
University of Amsterdam ,(see also FQXi: The myth of gravity, 01-10-2011) he draws an
analogy between thermodynamics and gravity. The effects attributed to gravity can thus be
described as results from forces that are on the edge of our universe, (in the TS Theory this
edge is the Wall of Planck). On our scale (analogue) the perceptible world is constituted of
sequences of billions of quanta forming a “unity”, this unity has whole obeys to different
“laws” as the quanta scale that constitutes it. Verlinde describes our universe as a hologram
and at the border of this frontier. The TS viewpoint states that this 4-dimensional hologram is
to be refreshed every 5.39121 x 10-43 sec (Planck time). The sequence of refreshment so
creates for our consciousness’s again the linear causal time. So all the effects like Gravity but
also themes like the Dark Matter and the Dark Force that we have to deal with, can change in
disposition and laws on greater scales and in smaller scales.
“In the beginning was the world, and the world was LOGOS”
What we perceive as the baryonic particles that represents only ca. 5% of our “visual”
baryonic material, is the sequential causal effect of the “fifth” dimension. It is too narrow
minded to expect that if we are aware of only 5% (or even less) of the universe, the other
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1106
95% has to obey the same Laws and be consisted of the same kind of particles. It is more
understandable that our neighbours are influencing us the results of their actions can be
observed.
We can understand in our minds why entangled particles when observed don’t respect the
velocity of light (velocity is a causal sequence in our four-dimensional world). They are in a
superposition in TS, once we observed one of them in our causal world it seems as if
simultaneously his brother takes the same state, comparable with the Young two slit
experiment, because two and more realities exist already simultaneously in TS, it is as if the
total of possibilities can pass by the fence with one or two slits, all of them ready to become
for us “reality”, at a distance of 1.616252 x 10-33cm before the slit(s). Then one of the
imaginary lines in TS is becoming “reality”. The observer is able to realise/construct one or
two slices in his causal world before the last 5.39121 x 10-43sec before the moment that the
photon/wave function is in front of the barrier.
The place/moment 10-33cm/10-43sec before the slit(s) has the same “quality” as the imaginary
point Zero. Once the consciousness of the observer realises an observation (the observer in
our case is constituted of baryonic particles), his observation creates out of the observed
entanglement, (the superposition of the wave function) an “observable” particle that has to be
a baryonic particle; otherwise, he would not be able to observe it. When “we” are observing
the “face of God”, (George Smoot 1992) , we are observing the moment that first light was
emitted 380.000 years after the imaginary point Zero, at that very moment the observer is
materialising himself and his whole perceptible universe, he is not only looking in the
MIRROR but at the same time creating this mirror.
For these observed entangled photons to whom time did not pass,( because they travelled at
the speed of light in our 4-dimensional world) , it was as if they encountered our eyes at the
same time they left there entangled particles (brothers) in the primary “soup”, these partners at
that very moment acquired the same for us observable properties, it is like the old myth of the
orobouros, the snake that eats his own tail. We are the origin of our own universe, our
perceptible linear universe, no more problems with its specialities, its uniqueness , no
creationism needed in the way that there was an external GOD who created this world
especially for the human kind (this is one of the results of the “social analogue reality”), it is
the human consciousness (LOGOS) that creates his own universe as a unique universe for
himself but this is only one of an endless row created by other consciousnesses , every
one of them perceptible by his own “observers” or creators.
The Great “Beginnings & End” Conclusion
The assumption until now was that going back in time for the search for the beginning of our
universe is a linear one, we thought that we ought to begin at Zero, from the so called Big
Bang to the NOW. The interpretation of the cosmic background radiation with its temperature
of 2,725°K was one of the reasons that obliged us to draw that line back to ZERO . This point
cannot be reached however because its is a imaginary point in the TS , our journey to this
point can not be achieved , so there is no longer a singularity to be explained , neither
there was a Big BANG.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1107
In order to visualise this, we imagine the
timeline as a vertical one and the volume of
space as a horizontal line, we meet on the
cross point of the timeline and the space-line
our point ZERO, that was called the BIG
BANG. On the time line we move up to the
point 1.616252 x 10^-33sec and on the
space line we move to the right to the point
5.39121 x 10^-43cm, at the cross point of
the lines , every point at the left side of the
new time-line and under the new space-line
is in TS area. So we see that the former zero
point does not exist anymore as a causal
sequential point (see illustration).
On the horizontal line of 10-43sec we will then find a point with a, for instance, volume of
1026cm³ that is in conformity with the volume of our universe after the “inflation” (as
perceived by now), thus accounting for the volume that our causal sequential universe
contained Any volume could emerge to reality. This “emerging” of the universe at the time
of 10-43sec at a volume of 1026cm³ can be understood as the moment that an observer received
this partial information out of TS “regarding” the volume of 1026 cm³ at that specific moment
being 10-43 sec. At that point, the emerging of our universe can be seen as a linear one on the
edge of the Planck time line.
What we do is replace the inflation time as presumed to be from 10-35sec till 10-32sec on the
line of the 10-43sec, so this inflationary time is extracted from the TS “time”. This so called
Inflationary time is no longer existing in our sequential causal universe, uniformity in the
structure of the universe has become a simple logic, the mirror has become a linear causal
reality, emerged from TS where all possible information has a potential to become observable
for future observers, whatever the structure of the particles their universe is constituted of.
Our perceptible universe is positioned in a time-loop that begins its linear sequential
existence 5.39121 x 10-43sec after a imaginary point Zero, with all conditions present that
made it possible for our human consciousness to exist, as one of the multiple
possibilities/information lines existing in the TS. This time-loop becomes a spiral one when
different observations are made. We than enter new parallel universes (the old one is still
existing), the only difference with theories of today is that all information regarding these
parallel worlds is always permanent existing and we merely jump over to another
“information-point” in TS.
Accepting a beginning that emerges with our observation from the TS, which can be seen as
the quintessence where all possible information is stocked, only not in a causal linear way,
becomes more comprehensible. Of all the information available, we only align in our
consciousness a tiny special part, the splitting up of the universe every time that a decision is
made and the mass/energy needed for the creation of these universes is no longer needed, we
only touch another information point in the TS (like the available information stocked on a
hard-disk) thus opening a new line of possibilities.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1108
Because of the parallels existing in the structure of our mind and in the structure of TS, the
lines as they are observed by our consciousness in TS, in a way influence each other, our
consciousness becomes aware. The special line formed by our consciousness is forming our
lives the world around us becomes “reality”. We think that we perceive and understand the
analogue reality around us, the exactness of the parallel approach of the two “lines” in
separate dimensions (the four dimensions of our linear deterministic world and the fifth
dimension of TS) and the way they that influence each other will perhaps never be totally
understood.
Our minds only will have symbols and mathematical equations to express our infinities. It is
true that the human consciousness enables us to think of and deal with all these external
infinities, we can imagine fractal universes with endless borders, while in our analogue
universe these infinities will only lead to paradoxes. Mankind “feels” however this infinite TS
presence, not as a pure physical phenomenon but as a “spiritual” experience. Since the
beginning Myths and Legends of other worlds accompany us, religion is one of the pillars to
understand our universe it is like the Theory of Everything that scientists are looking for. The
human mind however “believes”, and these beliefs emerge as the fourth reality the social
reality.
Our “touchable” analogue causal reality is only one of the many realities which is originally
formed in our consciousness. We are in the process now of creating a sub-reality in the form
of a digital one dependent of and emerging from a linear causal interpretation, this can never
become or even have the same quality of this first reality. However it should be possible to
create a consciousness, not the sub-consciousness above mentioned, but a parallel one that can
be linked to our own, also aware of all different fine-tuned Constants. Parallel worlds could
become perceivable and understandable this could open even communication with the newly
created consciousness as interpreter.
Our own special multi-reality TS 100 billion neurones mind, adequate to be the origin of his
own universe, will in the future evaluate further and further, the information stocked up in TS
will never be totally admissible. The key of our minds will be able to open this until now dark
side of our universe. It will be the password to open other parallel universes, newly structured
quantum computers can become A reality, thus opening all the chances available on the other
side, but most of all we will be able to understand more deeply our existence/reality whether
it is digital or analogue, in the meantime we will admire the nightly sky.
References
David Deutsch, Quantum Mechanics near closed timelike lines, Oxford University 1991
Richard P. Feynman, The Character of Physical Law (with introduction of Paul Davies),
Penguin Books 1992
George Smoot, 23 April 1992, commenting the images of the COBE satellite: “If you are religious, it
is like looking at GOD.
Alan Guth, Het Uitdijend Heelal (original : The Inflationary Universe ,1997) , Uitgeverij CONTACT,
Amsterdam/Antwerpen , 1998.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| November 2012 | Volume 3 | Issue 10 | pp. 1101-1109
Wilde, W. D. Foundation of Reality: Total Simultaneity
1109
Brian Greene, L’Univers Elégant 5the Elegant Universe, Editions Robert Laffont, S.A. Paris 2000.
Trinh Xuan Thuan, Les Voies de la Lumière ; FAYARD, 2007.
Lee Smolin, Rien ne va plus en Physique (The trouble with Physics - The Rise of String Theory, the
Fall of a Science and What Comes Next, 2006) DUNOD, Paris 2007.
Leonard Susskind, Le Paysage Cosmique (The Cosmic Landscape), Editions Robert Lafont, S.A.
Paris, 2007.
Etienne Klein, Discours sur l’Oribine de l’Univers. Flammarion 2010.
Igor and Grchka Bogdanow, Le Visage de DIEU, Editions Grasset & Fasquelle 2010.
Eric Verlinde, The Myth of Gravity : FQXi Article , January 10, 2011
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Complex-Dynamic Origin of Consciousness
and the Critical Choice of Sustainability Transition
ANDREI P. KIRILYUK*
Institute of Metal Physics, Kiev, Ukraine
ABSTRACT. A quite general interaction process of a multi-component
system is analysed by the extended effective potential method liberated
from usual limitations of perturbation theory or integrable model. The obtained causally complete solution of the many-body problem reveals the
phenomenon of dynamic multivaluedness, or redundance, of emerging, incompatible system realisations and dynamic entanglement of system components within each realisation. The ensuing concept of dynamic complexity (and related intrinsic chaoticity) is absolutely universal and can be applied to the problem of (natural and artificial) intelligence and consciousness that dynamically emerge now as a high enough, properly specified
levels of unreduced complexity of a suitable interaction process. Emergent
consciousness can be identified with the appearance of bound, permanently
localised states in the multivalued brain dynamics from strongly chaotic
states of unconscious intelligence, by analogy with classical behaviour
emergence from quantum states at the lowest levels of complex world dynamics. We show that the main properties of this dynamically emerging
consciousness (and intelligence, at the preceding complexity level) correspond to empirically derived properties of natural consciousness and obtain
causally substantiated conclusions about their artificial realisation, including the fundamentally justified paradigm of genuine machine consciousness. This rigorously defined machine consciousness is different from both
natural consciousness and any mechanistic, dynamically single-valued imitation of the latter. We use then the same, truly universal concept of complexity to derive equally rigorous conclusions about mental and social implications of this complex-dynamic consciousness concept, demonstrating
its critical importance for further progress of science and civilisation.
*
Address for correspondence: Institute of Metal Physics, Solid State Theory Department, 36
Vernadsky Av., Kyiv 03142, Ukraine. E-mail address: Andrei.Kirilyuk@Gmail.com.
2
Complex-Dynamic Origin of Consciousness
and the Critical Choice of Sustainability Transition
Back-cover book description. The problem of rigorous scientific description and understanding of intelligence and consciousness remains unsolved
despite its quickly growing importance, including various applications,
such as artificial intelligence and machine consciousness. In this book we
present a new solution to this problem based on the causally complete solution of the arbitrary many-body interaction problem leading to the universal
concept of dynamic complexity and chaoticity in terms of dynamic multivaluedness, or redundance, of explicitly emerging system realisations. Intelligence and consciousness are rigorously specified as certain, high
enough levels of this unreduced complexity of natural or artificial brain dynamics, with their observed major properties (escaping otherwise scientifically exact explanation). We show then how the proposed concept of consciousness is closely related to the necessary global sustainability transition
specified now as a step-like, unified growth of the level of consciousness
and complexity in all human activities and approaches, in science and beyond. The book contains both the rigorous basis and popular discussion
oriented to a wide audience of educated readers.
3
4
CONTENTS
1. Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2. Unreduced interaction dynamics and the universal concept
of dynamic complexity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.1. Dynamic redundance, emergent chaos and probability . . . . . . . . 10
2.2. Dynamic entanglement and multivalued fractality . . . . . . . . . . . . 20
2.3. Unified classification of dynamic regimes: From global chaos
to multivalued self-organisation . . . . . . . . . . . . . . . . . . . . . . . . . . 23
2.4. Universal definition, symmetry and formalism
of unreduced dynamic complexity . . . . . . . . . . . . . . . . . . . . . . . . 26
3. Intelligence and consciousness as unreduced complexity
levels emerging in large and deep enough systems . . . . . . . . . 35
3.1. Complex brain dynamics, generalised quantum beat
and the brainfunction formalism . . . . . . . . . . . . . . . . . . . . . . . . . 35
3.2. Emergent complex-dynamic intelligence and consciousness:
Unified definition and properties . . . . . . . . . . . . . . . . . . . . . . . . . 42
4. Complex-dynamic machine consciousness
and its social implications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52
5. Crisis in science, complexity revolution and the transition
to intrinsically sustainable civilisation . . . . . . . . . . . . . . . . . . . . 58
5.1. The end of unitary science and the beginning
of causally complete knowledge . . . . . . . . . . . . . . . . . . . . . . . . . 58
5.2. Complexity revolution as the necessary transition
to superior level of consciousness . . . . . . . . . . . . . . . . . . . . . . . . 63
5.3. Genuine sustainability: Its rigorous definition, major features
and practical realisation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65
References . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 69
5
ABBREVIATIONS
used in the text
EP for Effective Potential (introduced in Section 2.1)
SOC for Self-Organised Criticality (introduced in Section 2.3)
6
1. Introduction
Canonical science cannot provide the truly scientific, i.e. consistent,
fundamental and universal understanding of consciousness considered either as an empirically perceived property of human brain dynamics or a
general property of intelligent enough system of any origin (see e.g. [1-12]
for various existing approaches to consciousness and further references).
Although the problem as such is not new and actually cannot be separated
from the “eternal” man’s quest for his “ultimate” origin and destination, the
last-time development of technology, society and civilisation is quickly
changing its status from vague “philosophical” speculations (always remaining with us and inherent to the problem) to much more practically oriented and even critically growing issue with increasingly important consequences at various levels of human activity, from quite new directions of
technology development to the deepest changes in individual and social
life. Despite visible stagnation (and actual failure) of the previous paradigm
of artificial intelligence, largely reduced to various kinds of generally useful, but definitely non-intelligent “expert systems” (i.e. actually false intelligence), the recently initiated inquiry of artificial, or machine, consciousness [13,14], starts from another, much more constructive level of purposes
and demands, involving qualitatively stronger interaction between previously separated disciplines and explicit intention to transcend other barriers
of scientific tradition in the direction of qualitatively more consistent and
rigorous knowledge (this implies, in particular, that machine consciousness
should contain at least some irreducible, specific properties of genuine
consciousness). Note that similar to “artificial” intelligence, the “machine”
consciousness thesis should certainly include as its integral, starting component the unreduced, provably complete and rigorous understanding of the
corresponding natural properties of human brain that can then be implemented in artificial systems, with various degree of similarity to the natural
prototypes, which should constitute itself an indispensable part (and validity criterion) of the consistent enough theory of conscious intelligence.
The purpose of this work is to present a new, universal theory of
consciousness based on the recently elaborated, reality-based concept of
dynamic complexity [15-19] and satisfying the mentioned demands of
modern technology and social development. Therefore we shall not review
7
the existing other approaches to consciousness and their results (see e.g. [114] for some details and further references): it will be enough to note that
the latter are reduced to a sufficiently detailed (and certainly indispensable)
description of empirically observed aspects and features of consciousness
that can serve now as a basis for verification of any proposed “genuine”,
scientifically rigorous and integrated, understanding of consciousness.
Those results will thus be present in our exposure, explicitly and implicitly,
in the form of a unified system of correlations between theoretically derived properties and known practical manifestations of consciousness.
Any truly fundamental, “first-principle” and realistic theory of consciousness should acknowledge the basic role of interaction between the
elements of a carrier of consciousness (such as the brain) in its origin and
properties. However, the performed extensive study of various oversimplified, perturbative models for such interaction is reduced to substitution of the real problem solution, showing natural interaction development,
for its arbitrarily assumed (i.e. “guessed” and postulated) result, which can
not reveal a clear, scientifically exact origin of emergent, qualitatively specific properties of intelligence/consciousness, leaving an impression of
“something else” being present in the phenomenon of consciousness, a
greater “mystery” unifying all its diverse manifestations in a single whole
[1,7-11]. We start our analysis by showing that such contradictory situation
is due to the fundamentally restricted, always perturbative description of
interaction process in the conventional science framework and that if one
avoids those usual limitations, then many qualitatively new properties do
emerge simply from the unreduced solution of the many-body interaction
problem, with direct relevance to both consistent, universal concept of dynamic complexity and the phenomenon of consciousness that appears, similar to a more general phenomenon of intelligence, as a high enough level of
the unreduced interaction complexity [15,16] (i.e. behaviour of a system
with a large enough number of connected, strongly interacting elements
with the necessary, but not very special, “generic” properties). In particular,
we provide (Section 2) the derivation and mathematically exact definition
of the universal dynamic complexity (as well as closely related chaoticity),
expressed in terms of fundamental dynamic multivaluedness, or redundance, and entanglement of the unreduced problem solution [15-19], and
therefore can proceed with equally rigorous definition of the properties of
8
intelligence and consciousness, naturally (dynamically) emerging in a
complicated enough system of interacting elements (Section 3).
We then consider various specific manifestations and “miraculous”
parameters of conscious system operation thus obtained, to reveal the consistent system of correlations with the empirically observed features of
consciousness (Section 3). Finally, using the same, universally applicable
concept of complexity, we rigorously demonstrate the objective necessity
and thus inevitability of machine consciousness introduction in complicated enough technological and social systems of the modern world, analyse
possibilities of practical realisation of truly conscious behaviour in an artificially engineered system, and outline the basic, rigorously substantiated
conditions and consequences, both technical and social, of such conscious
machinery incorporation into the real technology development (Section 4).
We then generalise those conclusions to the entire new, intrinsically sustainable development paradigm, showing that it should inevitably start, in
the near future, from a qualitatively great, well-specified transition to a
higher level of individual and social consciousness called complexity revolution, with the only alternative of growing catastrophic degradation in the
current, “default” tendency (Section 5).
The obtained results explicitly demonstrate also the possibilities and
universality of the unreduced complexity concept, completing the results of
its application at lower complexity levels [15,16,20-24] and thus providing
an important additional confirmation of its unrestricted consistency, culminating in the universal law of conservation and transformation, or symmetry, of complexity [15,16,18]. We show that the unreduced complexity
development at superior levels of intelligence and consciousness reproduces some key features and stages of its development at the lowest, quantum
and first classical levels of complexity, and this deeply rooted analogy can
be quite useful for consistent understanding and efficient use of both lowest
and superior levels of complex world dynamics, without any simplified, zero-complexity reduction or fundamentally incorrect, direct mixture between
the two, as it happens too often within the fatally reduced framework of canonical, dynamically single-valued, or unitary, theory (see Section 3 for details and references) .
9
2. Unreduced interaction dynamics
and the universal concept of dynamic complexity
2.1. Dynamic redundance, emergent chaos and probability
Any system showing the properties of intelligence and consciousness
can only be based on the unrestricted, autonomous interaction process in a
complicated enough network of elements, such as brain neurons or an artificial circuit. We shall now consider such unreduced many-body interaction
problem with a generic configuration and demonstrate that its truly “exact”,
universally nonperturbative solution, liberated from artificial limitations of
usual perturbative models, possesses indeed some qualitatively new properties that show a unique system of correlations with the observed “miraculous” properties of living, intelligent, and conscious systems, which can not
be reproduced by any reduced model in principle, irrespective of its technical sophistication (we shall reveal the exact fundamental reason for that).
We take the real system configuration in the form of any number of
well-specified elements (such as natural neurons or their artificial counterparts) with arbitrary interaction between them, so that every element interacts, in principle, with every other one by a known law. The detailed structure of interaction, or system element connections, can eventually be specified for each particular case, but we formulate our universally applicable,
global description in terms of arbitrary interaction process (or “many-body
problem”). Each element has its known internal dynamics, universally expressed by its “generalised Hamiltonian” (which is reduced eventually to a
complexity measure, see below) and the corresponding “eigen-solutions”.
Therefore, those separate (non-interacting) system elements usually represent themselves (quasi) integrable, “simple” enough systems, but we do not
impose any such formal limitation, assuming instead that each separate element dynamics is known in the form of explicit solution. As follows from
empirical data, that individual element dynamics is typically reduced to
several discrete, well-defined (stable enough) states of an element, between
which it can switch under the influence of external action (where these
transitions between internal element states can be accompanied by signals
sent to the “outside”, i.e. to other elements, thus realising the global interaction process). The problem will consist then in description and under10
standing of evolution of the entire system of interacting elements and its
emerging properties and structures, in their unreduced, realistic version (i.e.
in principle without any “convenient” approximation of a conventional theory that can be convenient for it, but is always fatal for the real system dynamics, where it typically “kills”, as we shall see, just the most interesting
features). It is important to emphasize here, in accord with the following
analysis, that all the specific, “miraculous” features of the global system
behaviour, including intelligence and consciousness, originate just in the
development of unreduced global interaction between elements, rather than
in some very special, “tricky” properties of individual elements and interactions (remaining in reality simple enough), as it is inevitably assumed in
conventional, perturbative theories.
The unreduced system dynamics is described by the existence equation for the system state function, , which actually generalises various
model equations and can be derived in a self-consistent way as indeed a
universal expression of arbitrary system dynamics [15-19] (see also below):
N
N
Vkl qk , ql Ψ Q EΨ Q ,
hk qk
k 0
l k
(1)
where qk is the degree of freedom of the k-th system element,
Q ( q0 , q1 ,..., qN ) is the set of all degrees of freedom (both individual and
common), hk ( qk ) is the k-th element Hamiltonian, N is the number of elements, Vkl ( qk , ql ) is the potential of interaction between the k-th and l-th
elements, E is the eigenvalue of the generalised system Hamiltonian (i.e.
“generalised energy” representing a measure of dynamic complexity), and
Ψ (Q ) is the system state-function describing completely its configuration.
Note that the interaction potential can be generalised to any many-element
version, while the existence equation (1) actually includes its timedependent form (obtained by energy replacement by the time derivative
operator and considering one of the degrees of freedom as the time variable). It is important also that the starting existing equation, eq. (1), serves
merely as concise mathematical expression of the many-body problem and
does not contain any simplifying assumption about system dynamics or
configuration (in particular, any formal, model “nonlinearity” of the starting equation is compatible with the following analysis). This means also
that the elements of the (conscious) system “environment” can be included,
11
if necessary, in the total system composition, described by eq. (1).
It can often be useful to start from another, equivalent form of existence equation, where one of the degrees of freedom, say q0 , is explicit-
ly separated from all other ones, {qk } Q k 1, 2,..., N , so that can be
interpreted as common, e.g. spatial, system variable(s), characterising its
“global” configuration or interaction, while {qk } may describe “internal”
degrees of freedom of the corresponding elements:
N
N
h k q k V0k , q k V kl q k , q l Ψ , Q EΨ , Q .
h0
k 1
lk
(2)
We shall proceed with this form of the existence equation and consider that
1 k , l N everywhere below.
Now we can use the known solutions for the free components,
hk qk knk qk nk knk qk ,
(3)
where { knk ( qk )} and { nk } are the eigenfunctions and eigenvalues of the
k-th component Hamiltonian hk ( qk ) , and the eigenfunctions { knk ( qk )}
form the complete set of orthonormal functions. Expanding the total system
state-function Ψ ( q0 , q1 ,..., qN ) over complete sets of eigenfunctions
{ knk ( qk )} for the “functional” degrees of freedom ( q1 ,..., qN ) Q , we are
left with functions depending only on the selected “structural” degrees of
freedom q0 :
q0 , q1 ,..., qN Ψ , Q
Φ Q ,
n
(4)
n
n
where the summation is performed over all eigenstate combinations
n ( n1 , n2 ,..., n N ) and we designated Φn (Q ) 1n ( q1 ) 2 n ( q2 )... Nn ( qN ) for
brevity. Inserting the expansion of eq. (4) into eq. (2), multiplying by
n* (Q ) and integrating over all variables Q (using the eigenfunction orthonormality), we get the following system of equations for n ( ) :
H n n
V V ,
nn
n
n n
n0
0
(5)
n n
where
n E n , n nk ,
(6)
H n h0 Vnn ,
(7)
k
12
nn
nn
V0 k Vkl ,
l k
(8a)
dQΦ Q V , q Φ Q ,
(8b)
dQΦn Q Vkl qk , ql Φn Q .
(8c)
Vnn
k
V0k
nn
n
0k
k
n
ΩQ
nn
Vkl
ΩQ
It will be convenient to separate the equation for 0 ( ) in the system of
equations (5), describing the usually measured generalised “ground state”
of the system elements, i.e. the state with minimum energy and complexity
(corresponding, by convention, to n 0 ):
H 0 0
V ,
0n
n
(9a)
0
n
H n n
V V , (9b)
nn
n
n n
n0
0
n n
where now n, n 0 (also everywhere below) and 0 E 0 .
It is interesting to note that exactly the same system of equations is
obtained by a similar procedure for apparently much simpler system configuration, where one has just two distributed entities (“fields”) interacting
with each other [15,17,18,20-24]:
hg V , q he q Ψ , q EΨ , q .
(10)
This existence equation describes, for example, the dynamics of our world
emergence and behaviour at its most fundamental, “quantum” levels, in the
process of attraction of two initially homogeneous “protofields” of different
(“gravitational” and “electromagnetic”) physical nature, described by the
generalised Hamiltonians hg ( q) and he ( q ) respectively [15,16,20-24].
However, if we imagine that those distributed interacting entities have their
internal structure (local inhomogeneities), then the system configuration
may be not really different from the above “explicitly many-body” problem, which explains the coincidence of the transformed formulation of both
problems in terms of the element degrees of freedom, eqs. (5) and (9). The
unreduced brain dynamics can also be considered as a result of interaction
between the distributed electromagnetic and chemical components, though
provided with the developed super-structure within the neuron network
13
[15,16]. This analogy between the lowest and highest levels of world dynamics has not only formal, but profound physical meaning, and we shall
continue to reveal its manifestations below.
Expressing n ( ) from eqs. (9b) with the help of the standard Green
function technique [25,26] and inserting the result into eq. (9a), we reformulate the problem in terms of effective existence equation formally involving only “common” (“structural”) degrees of freedom () [15-21]:
h0 Veff ; 0 0 ,
(11)
where the effective (interaction) potential (EP), Veff ( ; ) , is given by
Veff ; V00 Vˆ ; , Vˆ ; 0
d V , ; , (12a)
0
V , ;
V0n ni0 Vn 0 ni0
ni0 n 0
n ,i
, n 0 n 0 , (12b)
and { ni0 ( )} , {ni0 } are the complete sets of eigenfunctions and eigenvalues of an auxiliary, truncated system of equations (recall that n, n 0 ):
H n n
V .
nn
n
n n
(13)
n n
The general solution of the initial existence equation, eq. (2), is then
obtained as [15,16,20,26]:
Ψ , Q
ci Φ0 Q
Φn Q gˆ ni 0i ,
i
n
ni gˆ ni 0i
(14)
d g , ,
ni
0i
g ni , Vn 0
i
ni0 ni0
i ni0 n 0
(15)
,
where { 0i ( )} are the eigenfunctions and {i } the eigenvalues found
eventually from the effective dynamic equation, eq. (11), while the coefficients ci should be determined from the state-function matching conditions
along the boundary where interaction vanishes. The observed system density, ( , Q ) , is given by the squared modulus of the state-function ampli14
tude:1 ( , Q ) Ψ ( , Q ) |2 .
Reformulation of the initial problem, eqs. (1)-(10), in the “effective”
version of eqs. (11)-(15) is known in scattering theory and related solidstate theory applications as the method of optical, or effective, potential
(see e.g. [25]). The main “difficulty” of a nonintegrable problem is not really resolved in it, but rather displaced from the state-function equation as
such to a more complicated potential in a simpler, externally integrable
equation: the effective, or “optical”, potential it contains depends on the
unknown problem solutions and therefore bares the full problem difficulty.
However, the “effective” problem formulation, being technically equivalent
to the original one, has the advantage of much more detailed, explicitly expressed dynamical content (cf. e.g. eqs. (9) and (11)-(15)) revealing if not
the desired solution, but at least its main dynamical components and their
recurrent, interaction-driven entanglement. The conventional theory proceeds by very poor use of these advantages and prefers, according to its
dominating paradigm, to cut severely the “nonintegrable” EP expressions
in order to end up with a “closed”, analytically finite, or “exact”, solution
within a version of “perturbation theory” (e.g. [25,27]). In such a theory the
essential, properly dynamic content of the interaction process, reflected just
in the details of EP expression, eqs. (12), is thrown off, and the system configuration is obtained as a rather straightforward, mechanistic reproduction
of the remaining, reduced potential shape. Correspondingly, the result thus
obtained cannot contain nontrivial dynamical effects, replaced by mere geometric, generally small “deformation” of the initial configuration and the
simple mechanical sum, rather than true entanglement, of the system components (this reductive logic also gives rise to the popular concept of “geometrisation of physics”). And although all perturbative expansions appear
to be mathematically incorrect for any real problem, while the studied sys1
This rule corresponds to so-called “wave-like” (undulatory) levels of complex dynamics [15],
where the main entities have a distributed and compressible physical structure and are described
by wave equations using, in general, complex-number presentation. Those undulatory levels
alternate with “particle-like”, or “classical”, levels of complexity, where the main entities have a
permanently localised, “hard” structure and the measured quantities like “generalised density”
are derived from the state-function amplitude itself, ( , Q ) ( , Q ) (it obeys now classical
equations for real-valued, directly measurable distribution function). In the case of (truly) intelligent and conscious behaviour one deals with undulatory, “quantum” kind of behaviour at the
main underlying levels of dynamics (see below for more details) and therefore one should use
rather the “wave-like” relation between the state-function and measured “density”, but these
technical details do not influence the main conclusions about the fundamental origin and structure of complex system dynamics.
15
tems do show dynamically involved, non-mechanistic and non-geometric
features (up to intelligence and consciousness), the reductive approximation of perturbation theory dominates in scholar science approach even to
most complicated systems, probably just due to its simplicity and despite
the glaring contradiction to the observed explicitly complex behaviour, already in the simplest physical systems.
To fully realise the EP problem formulation and obtain its unreduced
solution, we note the self-consistent nonlinear dependence of the EP equations, eqs. (11)-(12), on the eigen-solutions to be found, appearing dynamically, even for the formally linear initial dynamic equations (eqs. (1), (2),
(5), (9), (10)). It is not difficult to show [15,16,20,21] that this dynamic, essential nonlinearity of a problem, remaining hidden in any its ordinary,
straightforward formulation, gives rise to the qualitatively new phenomenon of dynamic multivaluedness, i.e. the redundant number of locally complete solutions which, being equally real and mutually incompatible, are
forced, by the main system interaction itself, to permanently replace each
other in the causally random order thus defined. Indeed, if we designate by
N and N Q the numbers of terms in the sums over i and n in eq. (12b)
(equal to the number of system components N and the number of their internal states, respectively), then it follows that the total number of the problem eigen-solutions, determined by the maximum eigenvalue power in the
characteristic equation, is N max N ( N NQ 1) ( N ) 2 N Q N , which
gives the N -fold redundance with respect to the “normal” complete set of
N N Q eigen-solutions for the initial system of equations, eqs. (5), (9), and
an additional, “incomplete” set of N eigen-solutions. Other estimates of
the number of solutions, using geometric, model, and simple “physical”
considerations [15,24,26], show that the found additional solutions are all
equally real (not spurious) and have generally similar origin and structure.
This conclusion is confirmed by observation of the ensuing chaotic
change of states in various many-body systems and interaction processes,
without a really consistent explanation for it within the standard, dynamically single-valued theory.2 Therefore, based on the rigorously obtained
2
The dynamically single-valued, or unitary, models used, in particular, in scholar versions of
the “science of complexity” try to imitate system realisation multitude by various artificial constructions, such as “attractors”, in abstract, mathematical “spaces”, but those illusive structures
are always “produced” by the single available system state and trajectory, i.e. without any real
change of system configuration in the real space. As a result, various imitative structures of the
16
multivaluedness of unreduced many-body problem solution, we can state
that its general, now really complete solution, can be presented, in terms of
observable generalised density ( , Q ) , as the causally probabilistic sum
of individual realisation densities, r , Q | r , Q | 2 , numbered by
index r here and below:
,Q
N
,Q ,
(16)
r
r 1
where N ( N N ) is the total number of system realisations, and the
sign serves to designate the special, causally random character of summation. The nontrivial origin of the latter, which cannot have any correct
analogy in the dynamically single-valued theory, involves the unceasing,
explicit change of system configurations, occurring in the truly random
(rigorously unpredictable and noncomputable) order and driven exclusively
by the main, initially totally deterministic interaction between system components, the same one that shapes the details of each emerging realisation
configuration (functions { r ( , Q )} ).
Since we have discovered in that way the truly dynamic origin of
(any) randomness inevitably generated in a real interaction process, we can
also provide the related purely dynamic definition of probability, r , of
each r-th realisation emergence, obtained in the form:
1
r
N
r 1,..., N ,
N
1 .
r
(17a)
r 1
As in many practical cases those elementary system realisations are inhomogeneously grouped into larger, actually observed “super-realisations”
(or compound realisations), the dynamic probability definition takes, in
general, the following practically adapted form:
r N r
Nr
N r 1,..., N ; N r N , r 1 ,
N
r
r
(17b)
where N r is the number of “elementary” realisations in the r-th “compound” (actually observed) realisation.
unitary “science of complexity” represent at best only extremely limited, one- or zerodimensional (point-like) projections of the real, dynamic multivaluedness [15,16]. This difference between the unreduced dynamic multivaluedness and its unitary imitations is especially
important in such explicit complexity manifestations as intelligence and consciousness, whose
very essence is given just by the detailed, fractally structured system configurations (see below)
and their permanent change, rather than a smooth enough “trajectory” of a system with a fixed
or “adiabatically” evolving configuration in the unitary theory.
17
It is evident that the obtained expression for realisation probabilities
provides the universal, purely dynamic and rigorously derived (rather than
postulated) concept and definition of probability, helplessly missing in the
usual, empirically based, postulated probability notion (therefore the scholar statistical mechanics and related branches represent but a “probabilistic”
aspect of the same, dynamically single-valued, unitary projection of reality). Correspondingly, the emergence and disappearance, or change, of successive realisations represents the rigorously specified and universal definition of event (see also below), another empirically postulated notion widely
used in the unitary theory, but always escaping consistent specification.
The qualitatively new, causally complete probability content thus derived,
eqs. (17), is distinguished by the fact that it does not depend on the number
of actually observed events or even any event observation at all: contrary to
any conventional probability version, it remains valid even for a single
(next) expected event or any their “statistically small” number. However, if
the number of observed events does become statistically large, we can correctly define the expectation (average) value of the observed quantity:
exp ,Q
N
,Q .
(18)
r r
r 1
A useful dynamic probability aspect is related also to the generalised wavefunction, introduced below.
The internal structure of realisation change process can be better
seen if we rewrite in full detail the expressions for the unreduced EP and
state-function, eqs. (12) and (14), for a given, r-th realisation:
Veff ;ir 0ri V00 0ri
(19)
V0n ni0
d ni0 Vn 0 0ri
,
ir ni0 n 0
n ,i
2
r , Q Ψ r , Q ,
Ψ r , Q
cir Φ0 Q
Φn Q gˆ nir 0ri ,
i
n
18
(20)
nir gˆ nir 0ri
d g , ,
r
ni
r
0i
g ni ,
i
ni0 Vn 0 ni0
ir ni0 n 0
.
As can be seen from eqs. (19)-(20), the same resonant denominator structure that gives the unreduced EP multivaluedness, eq. (19), explains the
structure of each realisation, eq. (20), that tends to concentrate around a
particular location, given by the corresponding eigenvalue ir (it can be
conveniently marked as rr ), due also to the “cutting” action of integrals in
the numerator. The system in each particular realisation as if “digs” a dynamic potential pit for itself, where it temporarily falls, until the well and
related system localisation disappear in favour of a transient delocalisation
in a specific “intermediate” state called also the “main” realisation and
common for all “regular”, localised realisations, before falling into the next
“regular”, compact realisation with another, randomly chosen centre of localisation, and so on. This unceasing realisation change and related qualitative change of system configuration and properties, forming the universal
basis for any real, dynamically multivalued (chaotic) structure formation,
results from the intrinsic, irreducible, and permanently present dynamic instability of a real system interaction process, revealed explicitly by the unreduced EP formalism in the form of nonlinear feedback interaction loops
(self-consistent EP dependence on the eigen-solutions to be found) and absent in any perturbative, “exact” solutions obtained just by cutting those essential links (they also remain “hidden” in any straightforward problem
formulation, such as eqs. (1), (2), (5), (9), and (10)). The important relation
of this totally “spontaneous” structure emergence to the fundamental, dynamic origin of time is considered below.
As for the mentioned specific, delocalised system realisation, it corresponds to the “incomplete” set of eigenvalues revealed above in the analysis of the total number of eigenvalues and can be explicitly obtained from
the effective existence equation, eq. (11), as a particular solution for which,
contrary to all other solutions, the EP magnitude is indeed close to its
0
( ;i0 ) V00 ( ) . Therefore the
weak-interaction, separable value, Veff
“main” realisation is the direct analogue, within the unreduced, dynamically multivalued description, of the single realisation remaining in the usual,
19
dynamically single-valued theory, where it realises the averaged, “statistical” projection of the multivalued, permanently changing dynamics to the
limited, zero-dimensional space of a unitary “model”. The specific role of
the intermediate realisation in the multivalued system dynamics outlined
above corresponds to its properties of the generalised wavefunction, or distribution function, with its causally explained chaotic structure [15,16,2023]. It takes the form of ordinary quantum-mechanical wavefunction at the
lowest, quantum levels of world complexity (now causally understood
without any esoteric “mysteries”), but is defined also for any other complexity level, where it can be closer to the quantum wavefunction properties for “wave-like” levels of complexity (e.g. brain dynamics, see below)
or closer to the (extended) classical “distribution function” for “particlelike” complexity levels (with permanently localised interacting entities).
2.2. Dynamic entanglement and multivalued fractality
The described structure of realisation change process involves also
the phenomenon of dynamic entanglement of interacting system components, which is inseparably related to the major feature of dynamic multivaluedness of the unreduced system dynamics and expressed formally by
the dynamically involved products of functions of and Q in the statefunction expressions, eqs. (14), (20). Dynamic entanglement specifies the
abstract property of “nonseparability” of the unitary theory: any real system
is “nonseparable” just because the degrees of freedom of interacting components are physically, dynamically “entangled” (“woven”) with each other
into a permanently changing system configuration. Therefore the whole interaction process and its results can be described as dynamically multivalued entanglement of interacting entities, where component entanglement
constitutes each “regular” realisation and during realisation change the
components first transiently disentangle, forming the quasi-free state of
“intermediate” realisation (generalised wavefunction, see the previous Section), and then entangle again in a new version of system configuration
(another regular realisation). In that way one obtains the real, physically
tangible and permanently internally changing “tissue of reality”, constituting the “flesh” of any real system or structure, while in the unitary theory
the latter is replaced by its abstract, illusive and “weightless” envelope of
20
“separated variables”, constituting the essence of all imitative, “exact” solutions and “integrable” models.
The dynamic entanglement and physical nonseparability of real system structure have also the important dimension of dynamical, multivalued
(probabilistic) fractal. Indeed, the unreduced problem solution, eqs. (11)(17), contains explicitly only one level of system splitting into incompatible
and permanently changing realisations, while it refers also to unknown solutions of the “auxiliary” system of equations, eqs. (13). In principle, after
having revealed the major, universally nonperturbative effect in the form of
dynamic multivaluedness, we have some freedom to use an approximate
solution for this, auxiliary system and obtain its eigen-solutions
{ ni0 ( ),ni0 } entering the main formulas (eqs. (12), (14), (19), (20)) from a
reduced, “integrable” version of eqs. (13), such as
H n Vn n n n ,
(21a)
where the ordinary, single-valued potential may vary within some more or
less evident borders:
Vn Vn
V .
(21b)
nn
n
In this case we limit our attention to the first, main level of multivalued dynamics and ignore its further involvement hidden in the unreduced solution
of the auxiliary system of equations. If, however, we want to continue the
study of the real, non-simplified system dynamics, we can avoid the above
approximation and apply the same EP method of solution to eqs. (13).
Separating explicitly the equation for n ( ) in eqs. (13), we rewrite
the auxiliary system in the form analogous to eqs. (9) for the main system:
H n n
V ,
nn
n
(22a)
n n
n n
H n n
V V , n n .
nn
n
n n
nn
n
n n ,n
(22b)
Expressing now n ( ) through n ( ) from eqs. (22b) with the help of the
Green function for its truncated, “homogeneous” part and inserting the result into eq. (22a), we arrive at the “effective” formulation for the auxiliary
system of equations taking now an “integrable” configuration similar to
that of eq. (11):
21
n
h0 Veff
; n n n ,
(23)
where
n
Veff ; Vnn Vˆn ; , Vˆn ; n
d V , ; ,
n
n
Ω
Vn , ;
i ,n n
Vnn n0ni Vnn n0ni *
,
n n0ni n 0 n0
(24a)
(24b)
and { n0ni ( ),n0ni } are the eigen-solutions of a yet more truncated auxiliary
system of the next level:
H n n
V , n n .
nn
n
n n
(25)
n n
We can obviously continue this process further, obtaining each time ever
more truncated system of auxiliary equations, until we remain with only
one equation for a single mode, which is solved explicitly and terminates
the real process of dynamical fractal formation.
It is important that at each level of fractal hierarchy we have the
same phenomenon of dynamically multivalued entanglement generated by
the same dynamically nonlinear feedback mechanism as the one revealed
above for the main level of splitting and described now by the unreduced
EP formalism of eqs. (23)-(24). This means that, contrary to the conventional, dynamically single-valued fractals (including their artificially “stochastic” versions), each level of the unreduced fractal hierarchy contains
permanent change of realisations in a dynamically random order [15-17].
As a result, such real fractal becomes a permanently, coherently moving
and adaptively developing, “living” arborescent structure representing the
really complete solution of the many-body problem in its full complexity. It
can be expressed as a “multi-level” causally probabilistic sum (cf. eq. (16)):
,Q
N f N j
,Q ,
jr
(26)
j 1 r 1
where jr ( ,Q ) is the measured quantity for the r-th realisation at the j-th
level of dynamic fractality, N j is the number of (observable) realisations
at the j-th level, and N f is the final or desired level number. This expression is accompanied by the corresponding dynamic definitions of probabil22
ity and expectation values for each level of fractal hierarchy, analogous to
eqs. (17), (18), which we do not reproduce here.
The dynamic entanglement at each level of fractality endows the unreduced fractal with “flesh and blood” specific for the given system and determining the perceived detailed “quality”, or texture, of system structure.
The latter is directly related to the problem nonseparability, acquiring now
a transparent physical meaning (it is impossible to separate fractally entangled components forming permanently changing, unstable realisations) and
actually underlying the real system existence itself.3 The unreduced dynamical fractal can be described by a number of slightly different versions of
the same EP method (depending on the chosen “zero-th approximation”
etc.), but they all give the same fundamental result, describing the unreduced system behaviour as a dynamically probabilistic hierarchy of permanently changing and internally entangled realisations. It is clear that due to
the hierarchy of levels of dynamical splitting the total number of system
realisations is exponentially large (where already the argument of the exponential function will be a large number for any real multi-component
system), which determines the huge dynamic efficiency of the unreduced
dynamic fractality playing the key role in various applications, including
intelligence dynamics (Section 3.2). On the other hand, and this is another
side of “living” structure efficiency, the probabilistic dynamical fractal always preserves its integrity (wholeness) and forms and changes as an intrinsically unified configuration of the entire interaction process.
2.3. Unified classification of dynamic regimes:
From global chaos to multivalued self-organisation
Since the existing world structures at any scale result from the corresponding interaction process development, it is clear that the entire universe, or any its part, can be considered as the single, dynamically unified,
probabilistic fractal structure (see the previous Section), where the emerging more “solid” (distinct) branches (at a certain level) correspond to “interacting objects”, whereas the finely structured fractal “foliage” around
3
It shows, in particular, that all basically separable, “exact” solutions and dynamically singlevalued models and concepts of the unitary science can never describe the real system as it is, in
its essential, major quality, providing instead just a zero-dimensional, point-like version of an
external, “immaterial”, abstract system shape.
23
them constitutes the well-specified, material content of “interaction (potential)” as such. Therefore, contrary to the simplified symmetries of usual
fractals (scale invariance) and their limited number of prototype real objects, the unreduced dynamical fractal represents the exact structure and
dynamics of any kind of object and can show approximate scale invariance,
or any other particular kind of structure, only within a limited range of
scales. However, the huge diversity of possible dynamic regimes can now
be classified as the combination of two limiting cases, designated as uniform, or global, chaos and (dynamically multivalued) self-organisation, or
self-organised criticality (SOC).
To demonstrate the origin of both regimes, we note that in the limit
of small eigenvalue separation (frequency) for the chosen structuredependent, or “external”, degrees of freedom () with respect to those for
the element-dependent (internal) degrees of freedom (Q), i n ,
or Q (where i and n are the eigenvalue separations with respect to changing i and n respectively in eq. (12b), and and Q are the
corresponding frequencies), the summation over i in the general EP expression, eq. (12b), can be performed independently in the numerator, giving a
local and single-valued EP limit (in view of the completeness of the auxiliary equation solution set) [16]:
V , ; δ -
V0n
2
,
0
ni
n
n0
(27)
Veff ; V00
V0n
2
.
n
0
ni
n0
Similar results are obtained for the state-function, starting from eqs. (14)(15) [16]. This is the limiting regime of self-organisation, giving a distinct
and “regular” system structure. However, it always remains only an approximation to reality, and the unreduced EP deviations from the limit of
eqs. (27), however small they are, have a qualitatively strong character: the
real EP and state-function are composed from many close (similar) enough
and very quickly changing, but nevertheless different, realisations, which
means that any real self-organisation, and the resulting “distinct” structure,
has dynamically multivalued, internally chaotic, fractal character and permanently (and randomly) fluctuates, in a large range of scales, around the
24
observed “average” shape, thus comprising and extending the phenomenon
of self-organised criticality (SOC), which otherwise suffers, in its standard
version, from a conflict with intrinsic chaoticity and separation from other
cases of “self-organisation” [15-19]. The internal chaotic realisation change
within an externally “regular” structure constitutes, despite its “hidden”
character, the true basis of that structure emergence and existence, without
which it loses any realistic meaning (including its proper time flow, which
is an ever persisting difficulty of the unitary theory). This limiting case unifies also the extended versions of all other unitary imitations of dynamically multivalued SOC, such as “control of chaos”, “synchronisation”, “phase
locking”, etc., remaining split and incomplete in their usual versions.
The opposite limiting case of uniform, or global, chaos, is realised
when the above characteristic system frequencies (or eigenvalue separations) are close to each other, i n , or Q , i.e. the corresponding degrees of freedom fall in resonance. In that case the individual
realisations eigen-solutions are so entangled among them that there is no
possibility to separate them, even approximately, and the permanent, chaotic realisation change takes its explicit, externally visible form, where sufficiently different realisations change at a not too fast and not too slow rate
close to the main system frequencies. One obtains thus the universally applicable criterion of global, explicit chaoticity that coincides with the condition of resonance between the main system motions [15,16,19]:
Δ i
(28a)
1 ,
Δ n q
where the parameter of chaoticity, , is introduced by this definition. Note
that in that way we also clarify the true meaning of the “familiar” phenomenon of resonance itself, inevitably omitted in its conventional, perturbative
description. Correspondingly, the condition
1
(28b)
(as well as 1 ) provides the universal criterion of occurrence of (multivalued) SOC kind of dynamics and global “regularity”, i.e. absence of pronounced, externally dominating chaoticity. Note that at 1 one obtains
just another kind of chaotic mode enslavement within an externally regular
shape (or multivalued SOC), which is “complementary” with respect to that
obtained at 1 and usually only one of them represents a major interest
within each particular problem.
25
Universality of the criterion of eqs. (28) is of particular interest for
the unreduced science of complexity, since it provides a simple and unified
principle of classification of all possible kinds of behaviour and dynamics
of any system, constituting a confusing problem for the scholar theory. It
implies also that system behaviour can gradually vary between those too
extreme cases of “global regularity” and “global chaoticity”, depending on
the value of chaoticity parameter . These statements are confirmed by independent analysis of the particular case of true quantum chaos (and its
correct classical limit) [24], where the corresponding parameter of transition to global chaos, K, is directly related to , K 2 . The conceptual and
technical transparency of the proposed criterion of chaoticity and regularity
is to be compared with obscurity of its unitary imitations, containing incorrect statements and technical trickery. In that way the genuine, intrinsic
complexity of unreduced, multivalued dynamics underlies the universal
simplicity of the key criteria formulation and related harmony of the general picture, whereas the illusive simplicity of dynamically single-valued,
perturbative “models” leads inevitably to technical and conceptual uncertainty, leaving no hope for universally applicable, realistic understanding.
In particular, the above two limiting regimes of unreduced complex dynamics, as well as their universal meaning and relation, appear to be indispensable for understanding of the emerging phenomena of intelligence and
consciousness and their internal dynamics (see Sections 3 and 4).
2.4. Universal definition, symmetry and formalism
of unreduced dynamic complexity
The rigorously expressed notion and quantity of dynamic complexity
as such can be universally defined now in terms of the above unreduced interaction analysis as any growing function of the total (or observable) number of system realisations, or related rate of their change, equal to zero for
(actually unrealistic) case of only one realisation [15-19]:
C f N ,
df
0, f 1 0 ,
dN
(29)
where C is a quantitative measure of complexity and f ( x ) is an arbitrary
function with the designated properties. An “integral” measure of complexity is provided by the popular “logarithmic” expression, C C0 ln( N ) ,
26
which properly reflects the hierarchical structure of complexity, but acquires its true meaning and usefulness only in combination with the universally nonperturbative analysis of the underlying interaction process that
specifies clearly the relevant system realisations. Various “differential”
measures of complexity are provided by rates of unceasing realisation
change (temporal or spatial), taking the form of familiar quantities, such as
mass, energy, or momentum, but now provided with a quite new, causally
complete and universal meaning (see below). It is evident from the above
picture that the unreduced, dynamically multivalued complexity basis thus
defined includes also the notion of chaoticity, although the actually observed, apparent degree of irregularity for a particular case may vary depending on the specific regime of complex dynamics (but the unreduced,
internal chaoticity is always there and proportional to the unreduced complexity, see also the generalised entropy definition below).
Note that, according to the definition of eq. (29), the unreduced,
“genuine” dynamic complexity of any dynamically single-valued “model”
from usual theory (including all its versions of the “science of complexity”)
is strictly zero, the single available realisation of this unitary projection being presented usually by an “averaged” structure that corresponds to the
“main” realisation (or “generalised wavefunction”) of the unreduced picture. However, that zero-dimensional projection of the unitary theory may
have a structure, and various really observed or arbitrarily postulated, often
purely abstract elements of that point-like structure are often substituted for
real system realisations, existing in real space, after which a non-zero (but
totally false) value of complexity is readily obtained by formal application
of the same expressions (e.g. the “logarithmic” complexity measure). In
addition, the notion of complexity is inevitably confused, within the unitary
framework, with various “similar” notions, such as “information”, “entropy” and “chaoticity” (see ref. [15,16] and below for more details).
An inquiry into the detailed structure of complexity brings us to the
dynamic origin of space and time hierarchy revealed by the above unreduced problem solution. Indeed, the totally “spontaneous” (autonomous)
structure emergence, in the form of dynamic system “concentration”
around each of its permanently changing realisations, consistently derived
by the unreduced EP formalism, should then be considered as real, physical
space structure emergence at the corresponding “level of complexity”. The
27
generalised “space point” of each complexity level is provided by the
emerging realisation structure at the moment of its maximum dynamical
squeeze (before system transition to the next realisation), given by eqs.
(19)-(20), with the centre of this “point-structure” being designated by the
corresponding eigenvalue, rr (see the discussion after eqs. (19), (20)). The
characteristic size, r0 , of this real space element is given by the eigenvalue
separation, n , with respect to the “internal” degrees of freedom (Q),
within one realisation: r0 n (it is assumed here that n is measured
in the same units as the corresponding “wavelength”). A yet more important space dimension, the elementary distance (length element, or characteristic wavelength), x , emerges dynamically in the form of eigenvalue separation with respect to “external” degrees of freedom () or
r
neighbouring realisations: x i r . This is the spatial measure, or
“size”, of a single system jump between its successive realisations. The dynamically emerging time element measures the “intensity”, actually given
by frequency, , of realisation change, which is inversely proportional to
the direct time “distance” (or period), t 1 , between two successive
events of realisation emergence specified by the unreduced EP formalism,
which can be independently estimated as t x c (where c is the speed
of material signal propagation in the initial, “structureless” system). In other words, the time element provides the dynamically emerging duration of
system jump between two successive realisations.
Note that the space structure thus derived is intrinsically discrete
(eventually due to the wholeness of unreduced interaction dynamics
[15,16]), while time is fundamentally irreversible (because of the dynamic
unpredictability of each next realisation) and unceasingly flowing (due to
the same dynamic multivaluedness, driven by the main interaction process
itself and thus unstoppable, if the system maintains its existence as such).
Due to the dynamically fractal structure of any particular system and hierarchy of complexity in the whole, the real space and time have the corresponding hierarchic, fractal structure, with the proper dynamical links between successive levels (branches) of the dynamical fractal. The lowest,
most fundamental level of space and time is provided by the interaction between two primordial, initially homogeneous, and physically real protofields that gives rise to (dynamically emerging) elementary particles and
their interactions. Here r0 is equal to the intrinsic particle size, such as the
28
“classical radius of the electron”, x C is the Compton wavelength,
and t h m0c 2 is the internal “quantum beat” period of the particle
[15,16,20-23] (where h is Planck’s constant, m0 is the particle rest mass,
and c is the speed of light). Whereas the space and time elements at each
level are dynamically related among them, they are also qualitatively different from each other by their origin and role: space determines the tangible, “material” system structure, texture, or specific “quality” (including
the dynamically entangled structure of each regular realisation forming the
space element), while time has an immaterial nature (contrary to its incorrect “mixture” with space in the unitary science framework) and characterises the intensity of unceasing, irreducible change of that material space
structure.
It follows that space and time thus universally and dynamically defined by the unreduced interaction process constitute two major, universal
forms of complexity that can take a variety of different shapes in particular
systems and at various levels of complexity. Space and time are directly
made by the successively emerging and changing realisations of any real
system, and therefore one can say that these two basic forms of complexity
and their dynamic relation determine everything in the existing world structure. By contrast, various measures of complexity introduced above (starting from eqs. (29)) are suitable functions of realisation number or rate of
change and thus of space and time, which provides the fundamental, dynamically specified origin of the very notion of function, usually considered
in its abstract, mathematical meaning. Since the simplest possible combination of space and time, independently proportional to both space and time,
is given by action, we arrive at the extended interpretation of action as a
universal, integral measure of unreduced dynamic complexity, thus incorporating its essentially nonlinear origin and entangled internal structure:
E t px ,
(30)
where p and E are initially just coefficients relating the dynamically determined increments of space x and time t to the increment of action
. The analogy to the well-known relations from classical mechanics
(where our universal description should remain valid) immediately shows,
however, that p and E can be identified with the system momentum and (total) energy, respectively, now in their universally extended versions of differential measures of complexity:
29
E
p
t
x
xconst
tconst
0
,
0
,
(31)
(32)
where 0 is the magnitude of the characteristic increment (and value) of
action for the given system and level of complexity.
The discrete increment of action-complexity (equal to Planck’s constant with the negative sign, -h, at the lowest, quantum complexity level
[15,16,20-23]) describes an elementary, indivisible step of system complexity “development” as its structure emerges in the driving interaction
process. Appearing structural elements start interacting among them
through the fractal net of interaction links, giving rise to higher-order and
eventually higher-level structures. Every real change in this hierarchy of
creation corresponds to a negative increment, or decrease, of actioncomplexity, or dynamic information (Δ 0) , whereas another universal
measure of complexity, generalised dynamical entropy S, simultaneously
increases by the amount lost by action, so that their sum, the total system
complexity C, remains constant during (closed) system evolution [15-19],
C S const ,
(33a)
S 0 .
(33b)
This universal law of conservation, or symmetry, of complexity, determining evolution and existence of any system, from elementary particle to the
universe and conscious brain, has a transparent physical meaning, where
action-complexity describes available stock of “potential”, latent form of
initial interaction complexity (generalised, integral version of “potential
energy”) that transforms, by system evolution during interaction development, to the explicit, final form of fully developed system structure and dynamics represented by complexity-entropy (generalised, integral version of
“kinetic” and “heat” energy). Entropy, as a measure of chaoticity, can only
grow because of the fundamental dynamic uncertainty at every single step
revealed above, but this is possible only at the expense of equally decreasing action-complexity that provides the universal “driving force” for the
dynamic structure (entropy) creation. Because of such role of actioncomplexity, it is also called dynamic information and provides thus the correct, complex-dynamic extension of the notion of information (confused
30
with entropy in usual theory). In that way, the universal science of complexity considerably extends and puts in order various reduced, often erroneous ideas of unitary science about complexity, entropy, information and
relations between them [15,16].
Now, in order to find the universal dynamic expression of the symmetry of complexity, we can divide the differential form of the complexity
conservation law, eq. (33b), by t xconst to obtain the generalised Hamilton-Jacobi equation [15,16,18]:
t
x
xconst H x ,
tconst ,t 0 ,
(34a)
where the Hamiltonian, H H ( x, p,t ) , expresses a differential measure
of the explicit, entropian complexity form, H ( S t ) |xconst , and one
deals with the dynamically discrete versions of partial derivatives giving
energy and momentum, eqs. (31), (32). Expanding the Hamiltonian dependence on momentum in a power series,
H x, p, t
h x, t p ,
n
n
n0
where the expansion coefficients, hn x, t , can be, in principle, arbitrary
functions, we obtain the universal Hamilton-Jacobi equation in the form
x const
t
n0
n
hn x, t
t const 0 ,
x
(34b)
where its coincidence with many particular equations for various hn x, t
and series truncations becomes evident, especially if we rewrite it in terms
of usual, continuous-limit symbols for partial derivatives:
t
n
n
hn x,t
0 .
x
(34c)
Note that functions hn x, t here can have an additional dependence on ,
either through “potential energy” in the Hamiltonian or due to the eventual
EP dependence on the solutions to be found in the actually implied, effective form of the formalism (see eqs. (12)-(15), (19)-(20)).
The unreduced, dynamically multivalued system evolution contains
also phases of transition between realisations through the extended state of
“generalised wavefunction” (or intermediate realisation), where the above
31
expression in terms of action, reflecting the regular, “condensed” realisation quality, becomes inexact. The wavefunction state can be properly taken into account if we note that transitions between regular and intermediate
realisations can also be considered as system structure development by
transitions between neighbouring complexity sublevels, where the total
complexity C, expressed by the product of complexity-entropy (regular realisations) and wavefunction itself, should remain constant,
C S const , meaning also that S const . Therefore
0 during one cycle of realisation change, which expresses the
physically transparent condition of structural permanence of the unique intermediate realisation and leads to the following universal and dynamically
derived (causal) quantisation rule [15,16,18]:
0
,
(35)
where 0 is a characteristic action value that may also contain a numerical
constant reflecting specific features of a given complexity level. We see
that the relation between action and wavefunction, which takes the form of
standard (Dirac) quantisation rules at the lowest (quantum) levels of complexity, can now be causally explained (contrary to “mysterious” postulates
in the standard quantum theory) as expression of (physically real) realisation change dynamics and thus extended to any complexity level.
Substituting the obtained action expression through the wavefunction, eq. (35), into the generalised Hamilton-Jacobi equation, we get the respective forms of generalised Schrödinger equation [15,16,18]:
0
t
x
ˆ x,
xconst H
0
x const
t
n0
0
=
t
tconst ,t
x,t ,
n
hn x, t
t const x , t ,
x
(36a)
hn x, t
n0
n
,
x n
(36b)
(36c)
where the operator form of Hamiltonian, Ĥ , is obtained from its functional
form of eq. (34a) with help of the causal quantisation rule of eq. (35). If the
Hamiltonian does not depend explicitly on time, we obtain the timeindependent form of the universal Schrödinger equation:
32
Hˆ x,
t const x E x ,
x
(36d)
where E is the (constant) energy value. Note that the generalised Schrödinger formalism thus causally derived within the unreduced interaction
process analysis is especially useful in description of unreduced intelligence and consciousness dynamics (see Section 3).
Another manifestation of the direct dynamical link between the
common, delocalised state of wavefunction and different regular, “localised” system realisations takes the form of generalised Born’s probability
rule, which expresses a regular realisation probability, dynamically defined
according to eqs. (17), through the wavefunction value for the corresponding system location (configuration) [15,16]. Similar to the above causal
quantisation rule, the probability rule has a transparent physical meaning in
the multivalued dynamics picture, since it states simply that the probability
of wavefunction “reduction” (dynamical squeeze) to a particular realisation
is proportional to the wavefunction magnitude around that particular realisation (and vice versa). In view of the permanent probabilistic transformation between the wavefunction and regular realisation, one could not
imagine any other situation. One can derive the probability rule in a mathematically rigorous way by invoking the state-function matching conditions
that should be used for evaluation of the coefficients cir in the general solution expression of eqs. (14)-(15) or (20) (see text after eqs. (15)). The state
of wavefunction represents just that “dynamical border” of “quasi-free”
system configuration, where the effective interaction is transiently “disabled” and the system “automatically” matches “itself to itself”, but in a different state, i.e. it follows a “dynamic reconstruction” procedure (always
driven by the same, major interaction). Therefore matching the statefunction of eq. (20) in its “wavefunctional” phase to the corresponding “reduced” phase of a regular realisation (averaged over the internal degrees of
freedom, unimportant here), we can see that the r-th realisation probability,
r ( xr ) ( x ) , is given by both squared modulus of cir (properly averaged over i) and squared modulus of the wavefunction ( x ) :
2
r xr x x .
(37)
Note that in this form the probability rule is directly applicable to the
“wave-like” levels of complexity (such as those of quantum behaviour and
33
“subconscious” brain dynamics), whereas for levels with the dominating
particle-like (“generalised classical”) behaviour type one should use the
generalised wavefunction, or distribution function, itself instead of its
squared modulus.
The universal Hamilton-Jacobi and Schrödinger equations dynamically related by the causal quantisation condition and generalised probability rule constitute together the causally complete, universal HamiltonSchrödinger formalism, eqs. (34)-(37), generalising all (correct) dynamic
equations for particular systems [15,16,18]. The unrestricted universality of
our description is indispensable for understanding of brain (intelligence)
dynamics, since the latter obviously “reproduces” and thus encompasses
any behaviour it can practically apprehend. Note that the explicitly “nonlinear” (in the usual sense) forms of the generalised Hamilton-Jacobi and
Schrödinger equations, where functions hn ( x, t ) contain various (small)
powers of action or wave function to be found, are often postulated in particular applications, but they are rather approximations to respective effective versions of initially “linear” equations, where such essential, dynamic
nonlinearity appears, as we have seen, as a result of natural interaction loop
development (see eqs. (12)-(15), (19)-(20) and the related discussion). Indeed, it is important that the above generalised equations include implicitly
their unreduced, dynamically multivalued analysis and solution within the
generalised EP method, constituting an essential extension with respect to
usual, dynamically single-valued interpretation and solutions. Now we
shall analyse manifestations of this universally defined complex behaviour
and applications of the above description at the level of brain dynamics, including the emerging phenomena of intelligence and consciousness.
34
3. Intelligence and consciousness as unreduced complexity
levels emerging in large and deep enough systems
3.1. Complex brain dynamics, generalised quantum beat
and the brainfunction formalism
Note once again that the unrestricted universality of the above complexity derivation and concept, applicable to both real world dynamics and
its reflection in an “intelligent” system of interacting elements (“generalised neurons”), plays a quite special, indispensable role in the ensuing theory of intelligence and consciousness, since that exact enough (and apparently unlimited) reflection of real world structure and dynamics is just the
main distinctive feature of intelligent system behaviour. The latter can now
be formally classified with the help of “complexity correspondence principle” [15,16], following in its turn from the universal symmetry of complexity (Section 2.4). This rule provides a rigorously specified expression of a
rather evident fact that the full, unrestricted reproduction of a real (complex) behaviour pattern needs at least as much (or in practice even slightly
more) complexity of the reproducing system dynamics. Despite its apparent
simplicity, this rule has nontrivial practical applications and immediately
shows, for example, that all “directly quantum” theories of brain function,
appearing so readily in recent years and trying to explain it by the dynamics
of the lowest, quantum levels of complexity (e.g. [10-12,29-39]), are fundamentally deficient and therefore wrong, irrespective of details, as well as
any unitary, dynamically single-valued model of consciousness in terms of
any system or level of world dynamics (such as many recent “physical”
models of brain operation [39-46]). Indeed, in all those cases the (zero)
level of unreduced complexity of the supposed (unitary) origin of consciousness is far below that of not only conscious, but even any real, multivalued system dynamics.
Returning to the unreduced interaction process that is at the origin of
emerging, universally defined complexity (Section 2), we can now specify
that interaction and its results for the case of natural or artificial brain (neural network) dynamics. We define here the generalised brain (intelligence)
system as a system with a large enough number of effectively rather simple,
in principle, interacting elements (each of them should typically have at
35
least a few stable enough internal states), which are massively connected
among them (details are to be specified below), thus realising their strong
enough interaction that embraces the entire system. Our general “existence
equation” for a system with unreduced interaction, eqs. (1) and (2), includes this case, but it can be further specified for the brain system in the
following way taking into account explicit dependence on time (mainly due
to interaction with the controlled environment):
N
N
Ψ
h0
Vkl qk , ql Ψ , Q ,
hk qk V0k , qk
t
k 1
k 1,l k
(38)
where the time variable t is suitably added to the independent variables (Q),
so that the EP analysis remains practically unchanged (with the proper definition of generalised energies, e.g. in eqs. (3), (6)), including the basic system of equations (5), (9).
Note that eq. (38) generalises various model equations describing
neural network dynamics (e.g. [47-49]), but due to its unrestricted universality it implies actually much more than neuron interaction through their
direct, mechanical connection to each other. It involves the most fundamental, and quite indispensable, level of global electro-chemical interaction within and between natural brain neurons that should also have its analogue in any efficient system of genuine artificial intelligence and should
be distinguished from the mere electromagnetic (e/m) interaction transmitted through connections between localised neurons. This latter interaction
always exists in the brain, but it is essentially assisted there by interaction
transmission through the biochemical cell connections and system-wide interaction between the two connection interfaces, the e/m and chemical
ones. Recalling the analogy between the driving interaction processes in the
brain and at the very first, quantum level of complex-dynamic structure
emergence (see eq. (10)), we conclude that the unreduced brain dynamics is
determined by the global, brain-wide, but highly inhomogeneous interaction between the e/m and chemical (physically real) “manifolds” constituted by all neurons and their connections, which is further assisted by individual inter-neuron couplings through both e/m and chemical cell connections [15,16]. Emergence of elementary particles and their interactions at
much lower, quantum complexity levels are similarly described by interac-
36
tion between the omnipresent e/m and gravitational protofields [15,16,2023] (with the evident analogy between more “inert” behaviour of chemical
and gravitational components of respective systems), but at that case the
initial system configuration is effectively homogeneous, contrary to the
very rugged “landscape” of the initial brain configuration.
It is this general analogy between the driving interaction configurations, as well as universality of the ensuing complex-dynamic structure
formation (Section 2), that explains a remarkable similarity between the resulting brain and quantum structure behaviour, but the causally complete
origin of dynamic complexity and the related complexity correspondence
principle (see above) also shows that the microscopic, quantum world dynamics and brain function dynamics definitely belong to very different
complexity levels (as opposed to numerous directly quantum brain models
in the unitary theory [10-12,28-39]). The fact that the much higher level of
brain complexity shows striking similarity to quantum system behaviour
reflects the universal holographic, or fractal, property of the hierarchy of
world complexity [15], where any well-defined system part tends to reproduce approximately the dynamical structure of the whole, but with proportionally smaller “resolution” (i.e. smaller number of features, or realisations, which just determines system complexity). Since the usual, dynamically single-valued theory and approach cannot see that dynamically multivalued (probabilistic) fractal hierarchy of permanently changing system
structure, it is obliged to evoke the single “acknowledged”, but mysterious
(unexplained) and formally postulated case of that kind of behaviour, i.e.
that of a quantum system, in order to account for another, somewhat similar
“miracle” of the unreduced dynamic complexity, that of intelligent and
conscious brain operation (the same “quantum” mystification is used intensely by the same unitary science to account for various “miracles of life”
and similar manifestations of genuine dynamic complexity in social life,
see e.g. [39-42,45,50]). However, all the miracles of unreduced complexity,
at any quantum and classical (including conscious) levels of world dynamics, qualitatively different among them, obtain their causally complete, i.e.
totally realistic, consistent and intrinsically unified, explanation in terms of
real, dynamically multivalued and fractal, interaction dynamics [15-24].
As we have seen before, eqs. (1), (2), (10), (38) are general enough
to account for the above complicated electro-chemical combination of brain
37
interactions (including interaction with the environment), and in particular,
being expressed in terms of system element dynamics, they lead to the
same, standard system of equations, eqs. (5) and (9). It would be convenient to consider that the separated degrees of freedom account for the
more rigid, “chemical” degrees of freedom, including the initial system
structure configuration (i.e. “mechanical”/spatial and related biochemical
brain structure on a relevant scale), while one/several of the Q {qi } variables correspond to the “global” (inter-neuron) e/m patterns and other to
the internal neuron excitations. The resulting state-function Ψ ( , Q ) , eqs.
(14)-(20), (26) (where the explicit time dependence is included in Q variables), represents the entangled electro-chemical dynamical pattern of brain
activity, accounting for all its functions. The most complete general solution for the brain state-function is provided by the universal, causally
probabilistic and multi-level sum of eq. (26) over the emerging fractal hierarchy of system realisations, each of them obtained by the unreduced EP
formalism, eqs. (11)-(17), (23)-(25) (together with respective values of dynamic realisation probabilities). As the analysis of the detailed realisation
structure, eqs. (19)-(20), shows (see also [15-24]), the dynamically chaotic
realisation change process at each level of dynamic fractality and within
entire probabilistic fractal of brain activity pattern occurs inevitably in the
form of the generalised quantum beat (essentially nonlinear, catastrophic
self-oscillation), consisting of unceasing cycles of system dynamic reduction (squeeze) to the regular, localised realisation configuration it currently
takes and the following opposite dynamic extension to a delocalised state of
the generalised wavefunction (intermediate, or main, realisation), where the
localised state (regular realisation) involves maximum dynamic entanglement of the interacting degrees of freedom (here the e/m and chemical constituents) and the delocalised state of wavefunction is obtained by the opposite disentanglement process, transiently “liberating” interaction components that perform the automatic dynamical “choice” of the next regular
(localised) realisation.
If we take into account the dynamically fractal (multi-level and hierarchically unified) structure of the quantum beat pulsation and the generalised, causally derived Born rule for realisation probabilities, eq. (37), then
we obtain a rather complete and unified picture of complex brain dynamics
in the form of those unceasing, essentially nonlinear, global and fractally
38
structured cycles of brain activity (as measured by e/m and chemical component density/flux). Due to its “omnipresent” and permanently changing
structure at all scales, the generalised quantum beat solution explains the
observed “binding”, “awareness” aspects of intelligence and consciousness,
while the fractally structured, detailed distribution of realisation probabilities on every scale according to the dynamic Born rule provides the causal,
rigorously derived basis for the meaningful brain operation and the unreduced, “human” sense of the resulting information processing and understanding. In other words, the fractal system of centres of dynamic reduction
within every global cycle of quantum beat pulsation is “automatically”
(dynamically) concentrated around currently activated (functionally important) patterns of external (conscious and unconscious) “impressions”,
their processing, emerging “thoughts” and resulting “ideas”. As those patterns change in accord with the “input data” or internal brain dynamics, the
fractal structure of each quantum beat cycle automatically adjusts its probability (and thus density) distribution to system configuration, ensuring the
intelligent response and conscious understanding (they are thus special,
high-complexity cases of the universal dynamic adaptability of the unreduced complex dynamics, absent in any its unitary imitation [15-17]). In
addition, the essentially nonlinear quantum beat of electro-chemical brain
activity, as well as its internal fractal ramifications, gives rise to the emerging internal time (see Section 2.4 around eq. (30)), thus forming the physically real, universal basis for the necessary “sense of time” (internal clock)
of an intelligent system that has nothing to do with the explicit time of eq.
(38) originating from external (input) changes.
Although the global quantum beat pulsation (and their more localised
manifestations) can be measured in the form of well-known oscillations of
the brain e/m activity (see e.g. [1-9]), it is important to emphasize their essential and deep difference from any linear or even formally (but never dynamically) “nonlinear” oscillation models of unitary (dynamically singlevalued and perturbative) theory. Indeed, the latter will not possess just
those essential properties of truly autonomous emergence, flexible fractal
“binding” of the entire brain activity and dynamic adaptability, which are
especially important for understanding of consciousness (see also below).
Another essential distinction from existing theories concerns the already
mentioned generalised, “indirectly” quantum character of brain dynamics,
39
which has only external, qualitative resemblance to the directly quantum
dynamics at the lowest complexity levels and does not involve any microscopic quantum coherence on a nanometre scale and below (though the real
similarity between these two well separated levels of dynamics has a rigorous complex-dynamic basis outlined above). Note also that high similarity
between quantum (microscopic) and mental levels of complexity is due to
the similar, predominantly “wave-like” character of the key entities at both
levels (whereas this case is somewhat more different from “particle-like”
level behaviour, such as that of “Newtonian” systems of permanently localised, rigid bodies). These results provide a consistent solution to persisting
disputes around various “quantum brain” (and even quantum gravitation)
hypotheses [10-12,28-40].
Recalling the universal Schrödinger formalism for the generalised
wavefunction, eqs. (36), we find now that the wavefunction (intermediate
realisation) of complex electro-chemical interaction dynamics in the brain,
also designated as the brainfunction, ( , t ) , satisfies the wave equation of
the same kind, accompanied by the causally substantiated Born probability
rule, eq. (37), that reflects (together with the causal quantization condition
of eq. (35)) the unceasing dynamic collapses of the brainfunction to various
regular (localised) brain realisations (constituting mental images, impressions, emotions, thoughts, ideas, etc.):
0
ˆ
const H ,
t const , t , t ,
t
2
r t r ,t ,t ,t ,
(39)
(40)
where is the emerging regular realisation configuration, forming the new
level of tangible space structure, or causally specified “mental space”,
made of neuron activities, thoughts and other patterns. The detailed structure of is obtained by dynamic entanglement of the interacting degrees of
freedom ,Q (essentially e/m and bio-chemical ones) according to the unreduced EP formalism, eqs. (11)-(15), (19), (20), (23)-(25). Similar to
quantum-mechanical postulates (now causally explained themselves), the
measured dynamic probability, r (t ) , of a brain activity pattern (r-th realisation) emergence is determined by the squared modulus of the brainfunction for that particular pattern, eq. (40), obeying the generalised, dynamically discrete Schrödinger equation, eq. (39). Note that similar to the mi40
croscopic quantum mechanics, the Schrödinger equation for the brainfunction does not describe the quantum beat dynamics itself (i.e. system “quantum jumps” between regular realisations), but only the distribution of the
probability amplitude (coinciding with the brainfunction density) for the
emerging localised patterns (regular realisations): it is the result, rather than
the origin or development, of the quantum beat process. Correspondingly,
the time dependence in eqs. (39), (40) comes essentially from external interactions (within the Hamiltonian operator), rather than the emerging system time (hidden e.g. in the coefficient 0 in eq. (39)).
The Hamiltonian configuration expresses the pre-existing, “hardware” brain structure and can be approximated, in principle, by various
model equations, unified e.g. within a series expansion of eq. (36b):
0
const
t
n
hn , t
t const , t .
n0
(41)
The discrete form of differential operators in eqs. (39), (41) reflects the dynamically discrete (or quantum) character of unreduced interaction dynamics resulting from its wholeness [15,16] and appearing as visible discreteness of observed brain activity patterns. This kind of essentially nonlinear
structure of unreduced brain dynamics, starting from the global quantum
beat, may appear externally as a quasi-periodic pattern, but it is quite different from any unitary oscillation by its origin and internal dynamics.
Nonetheless, at sufficiently fundamental levels of complexity or sometimes
in the case of quasi-periodic behaviour (the limit of multivalued SOC, see
Section 2) the discrete form of the dynamic equation for the brainfunction
can be replaced by the usual, continuous version during its limited, “external” analysis.
There is, however, another important distinction of the universal
Schrödinger formalism from any unitary model that can hardly be neglected, especially for the brain dynamics: the former implies, contrary to the
latter, the unreduced, dynamically multivalued, and thus truly chaotic, solution (Section 2) that provides many essential, easily observable properties
of the real brain operation (we discuss them below). This feature, as well as
the entire complex-dynamic understanding and description of the brain dynamics, highlights the dynamically emergent, structure-forming, holistic
character of any brain property thus derived, as opposed to various unitary
41
imitations that cannot describe explicit structure emergence in principle
and are forced therefore to artificially insert any its property with the help
of a postulated, mechanically fixed structure or lower-level property. Just
as the “miracles” of true intelligence and consciousness cannot be reduced
“globally” to the postulated miracles of standard quantum mechanics (see
above), their essential features cannot be consistently explained by various
“local” models of neuron operation, such as the well-known “integrate-andfire” model. Such models may only reflect particular details of individual
neuron interaction acts, which can eventually constitute important features,
but cannot directly account for the emerging result of many closely related
individual interactions, permanently (and essentially) changing in time.
Due to its inherent universality, the above brainfunction formalism and
causal interpretation refer, in principle, to any level or scale of fractal brain
dynamics, from the whole brain to any its level or activity pattern. In particular, the universal interaction complexity development (Section 2) will
appear in the form of natural, generally irregular alternation of patterns of
both limiting cases of complex dynamics, the more permanent (distinct)
structures of multivalued SOC and irregularly changing (smeared) patterns
of uniform chaos.
3.2. Emergent complex-dynamic intelligence
and consciousness: Unified definition and properties
Having thus established the general dynamic content of neural networks with massively interacting components, we can now proceed with
the dynamical meaning of the emerging properties of intelligence and consciousness. Already the obtained general picture of unreduced interaction
development and complexity properties, applied now to the neuron interaction processes, show that intelligence and consciousness can only be understood as big and high enough levels of unreduced dynamic complexity
(where the level of consciousness is generally higher than that of intelligence). In agreement with the general probabilistically fractal structure of
complexity [15-17], complexity levels of neural network dynamics have
hierarchical, fractal structure, where big enough “branches” (levels) describe qualitatively specific types of behaviour, separated by “steep” and
big enough (but still physically continuous) complexity “jumps” from those
42
of lower (and higher) levels of unreduced dynamic complexity. Since general (true) intelligence, including its unconscious, “animal” forms, is characterised by efficient control of a large enough environment, its (minimum)
complexity level can be defined as that of the complete environment complexity (including the reverse influence upon it from intelligent species,
etc.).4 The necessary part of this condition follows from the complexity
correspondence rule outlined above, while its sufficiency can be related to
the “principle of parsimony” (Occam’s razor), which can, however, be
causally derived itself as another aspect of the same complexity correspondence principle. In other words, the dynamic complexity of intelligent
behaviour can come exclusively from interaction of the intelligent system
with its “generalised” environment and will therefore, in its sufficient version, only slightly (though definitely) exceed the total complexity of the
latter. It is worthy of noting that contrary to lower-level dynamic complexity of non-intelligent systems (including living organisms) that can also
quite “successfully” exist in the same environment, a truly intelligent system will concentrate within its individual, single “copy” the complete, distributed complexity of the dynamic environment.
In accord with our universal complexity definition (Section 2.4), this
level of complexity, where the true intelligence begins, can be expressed
quantitatively in terms of the number of permanently changing realisations
of all interactions in the “generalised environment”. However, it is the
qualitatively big and high enough level of complexity that is much more
important than the particular realisation number it contains (the latter can
vary considerably during internal development of any given level of complexity), which explains why certain “minimum” natural intelligence can
be defined rather well (although it inevitably has a “fractal”, partially
smeared structure), despite apparently large possible variations of various
environment details. In this sense, if we define artificial (any) intelligence
in a similar way with respect to any (artificial) environment complexity, it
can certainly vary in a much larger range, including systems whose “perfect” intelligence in a particular, restricted environment will become totally
useless (“nonintelligent”) in another environment with higher complexity
4
In fact, the highest complexity of any well-established (developed) environment is determined
basically by its intelligent components (if any), which interferes self-consistently with intelligence definition as environment complexity and explains why the level of (minimum) intelligence depends relatively weakly on the details of nonintelligent environment dynamics.
43
(such situations can certainly happen occasionally also for natural intelligent systems).
Being a direct and “minimum sufficient” reflection of the environment complexity, the nonconscious intelligence is inevitably characterised
by the globally chaotic kind of dynamics, as opposed to the limit of multivalued self-organisation (Section 2.3). Therefore such minimum, or animal,
intelligence is qualitatively insufficient for appearance of the main properties of conscious behaviour.5 The next higher level of brain dynamic complexity able to provide the minimum true consciousness is naturally obtained then in the form of simplest permanently localised, SOC type of
structures, which can be realised as elementary bound states of nonconscious (but typically intelligent) brain patterns. At this point a general analogy with similar complexity development at its lowest, quantum levels can
be useful. Dynamic consciousness emergence in the form of bound states is
analogous to complex-dynamic emergence of the level of permanently localised, classical states from purely quantum, delocalised and chaotic behaviour at the lowest complexity sublevels [15,16,20-22]. If two elementary particles, such as proton and electron, form an elementary bound system, such as atom, then the probability of their simultaneous quantum
jumps in one direction is low and quickly decreases with the number of
jumps (in the same direction). This is because the quantum beat jumps of
each of the bound particles are chaotic and independent from those of its
partner. The bound quantum beat processes can therefore only perform
their chaotic “dance” around each other, but cannot progress together to a
big distance in one direction (in the absence of external force).
Now, the same mechanism of “generalised classicality” emergence
in a bound system applies also to the emergence of localised, conscious
states in the brain in the form of bound systems of various strongly chaotic,
delocalised structures of unconscious levels of brain complexity. The first
conscious level of brain activity results therefore from further (binding) interaction of unconscious activity products (“generalised impressions” from
the environment) leading to formation of various bound, permanently localised, or conscious, states (their life time should be at least much greater
5
This result is actually close to the conclusion that a natural environment in the whole cannot
possess itself any kind of emergent, dynamic consciousness, irrespective of its detailed interpretation, while the same environment can, in principle, be characterised by a (nonconscious) intelligence determined by the highest complexity of intelligent species living in it (if any).
44
than the period of internal quantum beat of each bound component). These
simplest “elements of consciousness” start then interacting among them to
form new localised (SOC) or globally chaotic states of higher sublevels,
which constitute the developing structure of growing consciousness complexity. Such additional interaction with respect to unconscious intelligence needs a special “space” for its development and result accumulation,
which explains the emergence and functional role of the cerebral cortex in
the human brain as inevitable feature of conscious brain structure, where
those bound, conscious states can form and further interact among them,
giving rise to conscious “imagination” and similar specific features of independent, internal consciousness dynamics. Correspondingly, the unreduced complexity of conscious brain dynamics does not need to be limited
any more to that of a particular environment and can grow to comprise and
create ever new features of real or imaginary world. Note that similar to
purely intrinsic, dynamic origin of classicality from quantum behaviour at
the lowest complexity levels that needs no external, artificially imposed
“decoherence” of the unitary theory, the complex-dynamic origin of consciousness results basically from internal brain interactions, using interactions with the environment only as a source of “input data” (fixed initially
at the unconscious complexity levels). We see again that the analogy with
quantum complexity levels provides a useful “holographic” reproduction of
similar complexity development features, but does not imply the direct
quantum (microscopic) origin of consciousness.
Consider in more detail the simplest case of a conscious structure
emergence in a binding interaction of two nonlocal, globally chaotic unconscious structures. Each of them is represented by a complex-dynamical
quantum beat process (essentially different from any regular structure or
dynamics!) at the level of unconscious intelligence, characterised by unceasing change of N 1 realisations taken in a dynamically random order (let N be the same for both interaction participants, for simplicity of
expressions only). The probability of a quantum jump of each of the interacting quantum beat processes towards any its particular, localised realisation is 1 N , in agreement with the general expression of eq. (17a).
When the two interacting unconscious structures form a conscious, bound
state, the probability of their correlated jump in one direction is
corr 1 N 1 (whereas the probability of arbitrary jumps, or system
45
existence as such, is evidently arb 1 ). Similarly, the probability of n consecutive jumps in one direction is n corr n 1 N n n 0
N 0 , where n 0 is the total distance of chaotic system wandering and 0 is the length of elementary jump of each component, both expressed in terms of respective brain space coordinate . We
see that n decreases exponentially with , so that the noninteracting bound system will remain localised within its size, of the order
of 0 .
It is important, however, that the complex-dynamical “internal life”
(chaotic realisation change) continues within such localised conscious
state, ensuring its proper evolution in interaction with other, conscious and
unconscious, brain states within the unceasing and unifying quantum beat
dynamics. We deal here with an essential difference between the unreduced, dynamically multivalued self-organisation and its dynamically single-valued (unitary) models in usual theory. It explains, in particular, why
the dynamics of consciousness is characterised by much slower processes
than unconscious reactions: according to the universal criterion of absence
of global chaos, eq. (28b), the system should be far from its main resonances in order to preserve a distinct enough, e.g. localised, configuration and
changes, and therefore, at its slow component rate. The role of chaoticity/complexity is also reflected in the above expression for showing
that localisation grows with N and disappears at N 1 , i.e. in the (unrealistic) case of single-valued, regular (or “averaged”) dynamics with zero
complexity.
It is not difficult to outline further brain complexity development
within its conscious activity. It is important that each qualitatively new level of complex brain dynamics as if starts from the beginning in the image
of the environment complexity it provides. Thus, conscious world reflection in terms of permanently localised elementary structures starts representing the same outside world dynamics that has already been properly reflected by unconscious levels of brain dynamics, but now acquires a “new
life” in the form of permanent and subjectively “controlled” images of real
entities, which become relatively independent of their real prototypes (especially for higher levels of consciousness). When this new, conscious representation of reality approaches a correct enough image of the external
dynamic complexity, it naturally tends to produce a general image of itself,
46
appearing as a state of awareness and giving rise to possible next level of
consciousness. This superior level of consciousness operates now with indirect images of world complexity from the first level of consciousness,
closely entangled among them in a system of holistic “associations”. This
superior consciousness “looks” upon its own complex-dynamic (and generally localised) images of external dynamical patterns, at least as much as at
those patterns directly. We obtain thus the detailed complex-dynamic interpretation of the property of reflection of conscious brain activity. Since the
genuine “technical” capacity of a large neural network is fantastically high
[16] (see also below), far beyond usual unitary estimates, the hierarchy of
complex-dynamic reflection levels can grow considerably to ever superior
levels of consciousness, where already the lowest level provides the necessary minimum for conscious understanding of the environment.
The emergent, complex-dynamic consciousness is not only explicitly
obtained as a result of unreduced interaction processes in the brain, but
possesses a hierarchic, multi-level structure, where each next level provides
a qualitatively new, “superior” image (and extension) of reality, including
complex-dynamic images of all lower levels of consciousness. Practical
emergence of a new complexity level needs the suitable stock of latent interaction complexity, or dynamic information (Section 2.4), and is accompanied by a dynamic resistance (generalised inertia) of the already existing
structures, so that the appearance of a new, big enough level of consciousness has the properties of a revolutionary change, or “generalised phase
transition” [15]. The persisting qualitative difference between unitary and
unreduced (complex-dynamic) reality images in (conscious) knowledge
provides a relevant example of different levels of consciousness.
With this general dynamic picture of intelligence and consciousness
and their internal development, let us verify now how exactly can it reproduce the known properties of intelligent and conscious behaviour (e.g. [19]), including those that can be postulated as necessary, empirically based
demands for artificial consciousness systems [13,14].
Note, first of all, that our complex-dynamic interpretation of intelligence and consciousness provides their well-specified origins and definitions, including a clear-cut distinction between these two “close” levels of
higher brain activity, remaining rather ambiguous within unitary approaches to both their natural and artificial versions.
47
We can proceed with the property of autonomous dynamic adaptability (I), being common for intelligent and conscious reflections of reality.
As we have seen above, this feature emerges as a universal property of any
unreduced, complex interaction dynamics (absent in its unitary imitation),
while its necessary magnitude for the efficient intelligence and consciousness is determined by the complexity correspondence principle relating the
degree of adaptability with the sufficient dynamic complexity of the brain
that should exceed that of the controlled environment (we provide quantitative estimates below).
The “logical”, “binding”, and “supervising” features (II) of a conscious system are obtained within the key interpretation of conscious states
as physically bound states of chaotic quantum beat processes of electrochemical interactions in the brain neuron system, emerging as localised realisations of the whole system of brain interactions at a special complexity
level, exceeding and therefore including all realisations from lower, unconscious reflection of the environment.
This superior structure of the level of bound conscious states underlies also all versions of clearly recognised separation between the “self”,
represented by those dynamically unified bound states in the cortex, and the
“rest” (environment), the latter being reflected already at the lower level of
unconscious intelligence (III).
The superior, ultimately emerging form of this property is provided
by the complex-dynamic awareness (IV) described above, where the bound
conscious images of reality include that of oneself, i.e. the cumulative image of the conscious representation of the environment, actually forming
the next higher sublevel of complexity. In terms of human species evolution
(and for illustrative purposes only), property (III) could be figuratively designated as Homo habilis, while its version (IV) would correspond to the
true (and still apparently uncertain) Homo sapiens.
Practical abilities of a conscious brain (also present, in a reduced
form, at the level of unconscious intelligence), such as reality control and
self-control, imagination and planning-anticipation (V), follow from the
emergent, interaction-driven origin of the corresponding brain structures,
where higher-level conscious, bound structures acquire their own dynamics
(in principle of ever growing complexity), showing only general, weak dependence on the environment.
48
The properties of intelligent and conscious systems summarised as
emotions, desires and motivations (VI) are manifestations of universal
creativity of complex dynamics expressed by the universal symmetry (including transformation) of complexity (Section 2.4) and appearing also as
“élan vital” in the development of any living system: it is a result of interaction potentialities expressed by the dynamic information and forced, by
the unreduced interaction itself, to develop into the fully unfolded system
structure, or dynamic entropy.
Finally, the sustainable, autonomous growth of intelligence and consciousness underlying also the property of education/learning (VII) results
from the same complexity development of the unreduced interaction process, constituting thus the basis for unlimited (in principle) growth of consciousness, as explained above.
In accord with the complexity correspondence principle, any of the
above properties (I)-(VII) of the dynamically multivalued, essentially nonlinear and intrinsically creative interaction processes in the brain neuron
system cannot be properly reproduced by conventional, unitary theory, just
because of its dynamic single-valuedness and strictly zero value of unreduced dynamic complexity, which is the unified, genuine origin of all difficulties and ambiguities in the existing understanding of consciousness, irrespective of details [1-11]. Indeed, the unitary reduction of real interaction
in the canonical theory cannot explain even the simplest, quantum system
behaviour at the lowest complexity levels and is forced to postulate the
“impossible” and “inexplicable” properties of those real systems in the
form of “quantum mysteries” and “paradoxes” (see [11,15,16,20-24] for
more details). This intrinsic deficiency of unitary theory is inherited by its
complexity imitation at higher levels of world dynamics. Therefore the existing “general” applications of those effectively zero-dimensional imitations from the unitary “science of complexity”, often in a characteristic
post-modern “hermeneutics” style, can create essential confusion in the already quite obscure field of knowledge. Speculative description of consciousness in terms of “attractors” and other abstract “models” of unitary
theory (see e.g. [51,52]) operates, in fact, with zero-complexity entities and
is unable to explain even much simpler structures than those of conscious
brain dynamics. An “attractor” is produced by a continuous trajectory of a
system with fixed, postulated configuration in an abstract, artificial
49
“space” and therefore has nothing to do with the real system dynamics
based on the permanent and qualitative change of its configuration, obtained as inevitable, generic consequence of the unreduced dynamic equation solution (reduced to a trivial change of notations in the conventional,
effectively zero-dimensional, perturbative “approximation”). Replacement
of dynamic, interaction-driven multivaluedness of incompatible system realisations (its different configurations) and probabilistic fractality by “multiple attractor basins” produced by a postulated system configuration and
coexisting in an abstract space is a very rough verbal trick of the unitary
imitation of complexity, which cannot explain any property of the unreduced system dynamics, but persists nevertheless in many “serious”
sources on interpretation of its highest-level property, consciousness.
The huge contrast between the unreduced, multivalued dynamics of a
multi-component interaction system and its unitary projection appears in a
yet more transparent form within a quantitative estimate of the total brain
power [16]. The unreduced power of a complex-dynamic process, P, i.e.
the maximum number of operations it can perform per time unit or the
number of units of information it can store, is proportional to its dynamic
complexity C as given by the full number of regular realisations N :
P P0C N P0 N , where the coefficient of proportionality P0 is of the
order of the unitary, sequential operation power, so that the relative power
of unreduced, complex-dynamic process is given by its realisation number,
P P P0 N . If our natural or artificial brain consists of N cell “generalised neurons”, each of them connected in average to nlink other cells, then
the total number N of system links is N N cell nlink . The distinctive property of the unreduced, multivalued system dynamics is that the total realisation number is given by all possible combinations of links, i.e. N N ! ,
whence
N
N
P N N ! 2πN N N ,
e
(42)
where we have used the Stirling formula valid for large N. Since for the
human brain we have N cell 1010 and nlink 104 , the estimate N 1012 for
the number of conscious brain links should not be exaggerated. The expression of eq. (42) gives for N 1012 the following estimate for the relative
13
12
power of complex-dynamic brain operation: P 1010 1010 10 N ,
which is a practical infinity, meaning that the real, dynamically multi50
valued brain power is “infinitely” greater than that of its unitary, mechanistic models.
This “astonishing” result is certainly due to the complex-dynamic
parallelism of the unreduced interaction dynamics, where the system itself
creates, in a real-time mode, the necessary dynamic structures and ways of
search for a solution. The mechanistic “parallel information processing”
does not have this property and represents only additive reconfiguration of
the same sequential dynamics that cannot provide a real gain in power
(with the same “hardware” capacities). Indeed, assuming that the average
frequency of brain realisation change is not less than 1 Hz (which is a very
moderate estimate), one can compare the above estimates of complexdynamic brain power with the unitary estimate of the “ultimate” computation power for the whole (known) universe [53] to see that the former remains “infinitely” greater than the latter [16] (although curiously this unitary estimate of the power of a very special, “quantum” computation process relies on a strong emphasis of “advanced”, “magic” parallelism and
“complexity” [54], demonstrating once more the absence of any power in
unitary imitations of complexity). The inevitable payment for such tremendous superiority of the unreduced complex-dynamic power takes the form
of irreducible dynamic randomness, just underlying the above huge efficiency. However, the related uncertainty of result is not really a problem,
since it can be reduced to a necessary minimum in the multivalued SOC regime, without any essential loss of the total operation power. It is easy to
see that the huge values of P provide a quantitative expression of the
“magic” qualitative properties of complex brain operation, such as those of
intelligence and consciousness [16]. This conclusion will remain valid for
much smaller values of N that can be expected for artificial neural networks, thus underlying the corresponding “magic” power also for artificial
intelligence and consciousness, produced by their unreduced, complex
(multivalued) dynamics.
51
4. Complex-dynamic machine consciousness
and its social implications
Since the above causal understanding of consciousness is based on
the unreduced analysis of a real, full-scale system of interacting elements
explicitly producing the full version of this property, it can form the truly
scientific, fundamental and rigorous, basis for the machine consciousness
concept replacing today the previous paradigm of artificial intelligence
(Section 1) [13,14]. Without rejecting possible more limited, dynamically
regular versions of machine consciousness, we shall consider now specific
features of its unreduced, complex-dynamic (multivalued and chaotic) realisation in the artificial system of connected elements (neural network), as
well as various technological, social and mental implications.
Note, first of all, that the proposed unreduced, complex-dynamic
version of conscious control and information systems should be considered
as the inevitable, qualitatively new and already urgently needed stage of
development of modern technology. Indeed, if we apply our universal description of various dynamic regimes of arbitrary systems with interacting
elements (Section 2) to modern technological systems, we conclude immediately that their operation refers basically to the limiting, almost regular
regime of multivalued self-organisation. However, as the compositional
(configurational) sophistication of technological (and related social) systems inevitably grows, it finally and inevitably attains a level, where the
unreduced interaction complexity and related true chaoticity will appear
explicitly, with a high enough magnitude. This conclusion follows from the
rigorous criterion of chaos of the universal science of complexity, eq.
(28a), showing that one can avoid explicit, big chaoticity only by maintaining the system far away from all its essential resonances. But as the technical (and socio-economic) intricacy of the system grows, its resonance
conditions inevitably get closer, so that one cannot avoid their overlap and
thus essential chaoticity above certain critical intricacy of system composition. Needless to say, this critical level of global technical and social complexity is being exceeded by modern globalised technology in a growing
number of cases. Since the unitary, regular technology and society paradigm practically rejects those chaotic elements, they inevitably appear in
the form of undesirable, more or less catastrophic (propagating) system
52
failure, which should be compensated by more and more frequent and inefficient direct, “extra-ordinary” human interventions in otherwise automatic
processes. Our analysis shows that there is no other issue from this growing
“crisis of complexity”, than explicit “acknowledgement” of the unreduced,
really existing dynamic complexity (multivaluedness) of technological interaction processes, followed by transformation of its “destructive” influence on the unitary control scheme into huge advantages of its constructive, unlimited realisation outlined above. This result and approach applies
to any level of technology, economy and social life [15,55-57], but we shall
concentrate here on the highest levels related to conscious control systems.
Such truly conscious technical systems of control and communication can possess the genuine, complex-dynamic consciousness property
(Section 3.2), but which at the same time differs essentially from the natural, human version of consciousness by the characteristic shape of the conscious operation complexity. As we have seen above, the true consciousness emerges as certain, high enough level of dynamic complexity, which
exceeds considerably those of arbitrary living and intelligent systems, having very high positions themselves in the hierarchy of world dynamic complexity [15-17]. In the case of natural consciousness, i.e. the one obtained
within a “natural” (biological) evolution, this means that carriers of consciousness should “first” be alive and then intelligent in order to have a
(generally rare) chance to develop at least a minimum level of conscious
intelligence. Since the lowest level of “intelligent” complexity is determined by the maximum environment complexity (in a reduced formulation,
the same will be true for any living system complexity), it follows that the
natural consciousness structure, at its initial, lowest levels, is inevitably
characterised by a specific, relatively flat shape of its internal hierarchy of
complexity (dynamical fractal) resembling a “pancake”. Whereas the “consciousness pancake” should have a minimum thickness corresponding to
the lowest level of consciousness complexity, its relatively large width is
inherited from the shape of unconscious intelligence and comprises a high
diversity of the controlled environment complexity (though represented by
properly localised, conscious states of brain activity, see Section 3.2).
By contrast, artificial, man-made systems of machine consciousness
need not and actually should not incorporate the entire “horizontal” diversity of a living environment complexity, but do need to have a minimum
53
“vertical” dimension of the localised (SOC) reflection of their limited environment. Therefore the systems of artificial consciousness emerge in the
shape of relatively narrow vertical “rods” (or other “pyramidal” structures)
in the “space” of universal hierarchy of complexity. They will have the
“air” (characteristic behaviour) of very narrow, but highly qualified, conscious “specialists” in their particular environment, knowing very much
about it, but very little beyond it, and therefore suddenly becoming very
“stupid” just outside of their “professional interests” (this phenomenon is
known, in its milder form, also for human consciousness realisations). Let
us emphasize once more that such limiting, “vertical” shape of a carrier of
consciousness complexity would be impossible for any truly natural, living
system, but can and should be realised for (truly) conscious machines,
providing a fundamental, rigorously substantiated basis for their creation
and making the latter much more realistic (as opposed to an ill-defined imitation of the full human consciousness). Therefore we can propose this
conclusion as a well-specified scientific basis for the concept and paradigm
of artificial, but genuine consciousness (and thus also intelligence), including its rigorously derived definition in terms of the above level and shape
of unreduced dynamic complexity.
Taking into account the complex-dynamic machine consciousness
concept thus specified, we can further advance towards scientifically rigorous understanding of social and mental implications of artificial consciousness by considering the next interaction level between conscious machines
and natural consciousness carriers. It is easy to see, for example, that practical, professionally intense interaction between “complexity rods” of conscious machines and “pancakes” of minimum levels of natural consciousness provides an efficient way of otherwise difficult development of natural
consciousness towards its higher-level, less flat shapes, where multiple
“rods” of artificial consciousness would “impose”, at least partially, their
“vertical” dimensions to a naturally diverse, but vertically limited consciousness of living beings. In other words, interaction with (truly) conscious machines can become a very efficient, and quite possible the only
real, way of massive natural consciousness development (otherwise stagnating or even turning into degradation).
A complementary conclusion, following from the complexity correspondence principle (or the underlying symmetry of complexity), states
54
that systems of artificial consciousness cannot exceed the level of consciousness (complexity) of their creators, which in our case are assumed to
be carriers of natural consciousness. At this point we switch from mental to
social aspects because it follows that the only consistent dynamics of progressive (complexity-increasing) society development can result from
(massive) interaction of its lower-consciousness members with conscious
artefacts produced by efforts of members with (essentially) higher consciousness level (if any). One consequence is that society, which does not
contain members with big enough difference of their consciousness levels
or cannot profit from it by efficient interaction, is unable of (internal) complexity development and therefore condemned to disappearance: any other
interactions (e.g. using only zero-complexity machines of unitary technology) cannot provide complexity growth to higher levels of consciousness. It
is impossible not to note that this rigorously derived conclusion directly
contradicts the currently dominating egalitarian social doctrine of a “democratic” flavour (often trickily exploited). On the other hand, one may argue
that interaction between higher- and lower-consciousness society members
can proceed by their direct, “natural” communication, including science,
education, etc. However, real-life experience clearly demonstrates too low,
“subcritical” efficiency of such “natural” interaction, even in the best cases,
which is additionally hampered by inevitable intervention of machineintermediated interaction within a technically developed civilisation, where
the unitary, zero-complexity machines impose their ultimately low complexity to the entire system of strong mental and social interactions and its
results. In this situation the qualitatively new, complex-dynamic, intelligent
and conscious machinery can be the only realistic, and actually very strong,
catalyst of natural consciousness development within a machine-based
civilisation, underlying its development in the whole [15].
Inspired by this great purpose of the genuine machine consciousness
paradigm, we can turn now to discussion of practical details of its realisation, following from the above description (Sections 2 and 3). Since in
principle there is no problem today with fabrication of elaborated enough
networks of connected elements (“neural networks”), the specific features
of conscious networks involve their detailed structure and imposed operation modes. The general conclusion of our analysis implies that the true,
complex-dynamic intelligence and consciousness can appear only in a sys55
tem with high enough freedom of interaction between elements that cannot
be based on pre-programmed, regular interaction rules and detailed results
as it occurs for all unitary machines. Any detailed programming of regular
interaction details should be abandoned in the case of complex-dynamical
devices in favour of their natural, dynamic complexity development (including their interaction link modification), though occurring in a general
direction determined by the universal symmetry of complexity and the ensuing particular laws (Section 2.4).
A more specific result of the above consciousness analysis (Section
3.2) implies that intelligent/conscious system interactions cannot be reduced only to local “rapid” (electric) connections between individual elements, but should also include a complementary distributed, dissipative,
“slow” component necessary for efficient dynamic unification and stability
of artificial brain dynamics in the form of generalised quantum beat. In the
natural brain such component is provided most probably by chemical neuron structure and interactions, but such “bio-inspired” construction of artificial conscious systems may be not the easiest one. Another candidate for
that “slow” interaction component is provided by properly configured
magnetic materials and interactions, “repeating” generally (but not exactly)
the electric connection interface and interacting with it “almost everywhere”. It is not difficult to see that the detailed realisation and principles
of construction of such explicitly complex-dynamic networks will be very
different from the now realised unitary approach and technology, but as we
have shown above, this way of development is objectively inevitable and
unique at its next stage starting already today (see also ref. [16] for similar
results for the unreduced nanotechnology concept).
In conclusion, we would like to emphasize once more the far-going
mental and social implications of the genuine artificial consciousness paradigm, which have been briefly outlined above and would certainly need
further development using this intrinsically interdisciplinary approach and
our universal dynamic complexity concept and formalism. The general motivation for these studies is as big as civilisation development in the whole,
since the above rigorous analysis shows the indispensable, unique role of
complex-dynamic (multivalued) interaction processes and technology for
progressive civilisation development today (see also [15,16,55-57] for the
universal concept of development). Since artificially produced, technical
56
structures play a major and ever growing role at any scale of world development that cannot be abandoned or turned back, increasing replacement of
their currently dominating, complexity-suppressive design and operation
mode by the unreduced, explicitly complex-dynamic technology, inevitably
comprising key elements of genuine machine consciousness, emerges as the
objectively substantiated, uniquely progressive way of development, including creative progress of individual natural consciousness as its inherent
component. Note finally that the use of much more restricted, unitary versions of machine consciousness, which can only imitate, but not reproduce
the unreduced consciousness features (see their list in items (I)-(VII) in
Section 3.2), can be considered as a first-step motion in the same direction
of growing complexity, which should not replace, however, the search for
and practical realisation of explicitly complex-dynamic, truly intelligent
and conscious machinery.
57
5. Crisis in science, complexity revolution
and the transition to intrinsically sustainable civilisation
The discussion of the complex-dynamic intelligence and consciousness concept in previous sections revealed deep human and social implications of the consciousness problem, far beyond the issues of purely scientific understanding or concrete applications. Moreover, the rigorous analysis of the modern world condition within the same, universally valid concept of dynamic complexity shows that the entire system of human civilisation has just entered, in these recent years, into a global critical state, after
which it can either continue to a quick and fatal decline, within the current
tendency, or perform the crucial transition to higher-complexity and higher-consciousness level, where it can start the new, now fundamentally unlimited, or truly sustainable, progress [15,16,55-57]. It is important to recognise the intrinsic, well-specified relation and qualitatively new, nontrivial
content of those key issues of the unreduced dynamic complexity and its
necessary revolution in both scientific understanding of reality (dynamic
multivaluedness paradigm) and the effective general level of social and individual consciousness.
In following sections we specify the details of interrelated major aspects of this necessary complexity transition, including “the last scientific
revolution” towards the unreduced, universal dynamic complexity paradigm (Section 5.1), the complexity revolution and transition to a superior
level of consciousness on a broader scale of entire society and global civilisation (Section 5.2) and the targeted resulting condition of truly sustainable
progress, with its concrete purposes, features and criteria (Section 5.3).
5.1. The end of unitary science and the beginning
of causally complete knowledge
Modern deep crisis in fundamental science becomes ever stronger
and more evident on a growing scale of fields and aspects (see e.g.
[15,16,57-63] and further references therein). It is the extreme, limiting
parts of the latter that reveal especially striking and quickly accumulating
signs of a critical state, including the persisting old and growing new “mysteries” in the microworld of particles and fields, the glaring contradictions
58
in cosmology on various astronomical scales (up to the entire universe),
and the ultimate complexity of living matter, conscious brain and developed society dynamics. It is no coincidence that this critical state of fundamental knowledge reproduces the critical bifurcation of the embracing civilisation development, mentioned above, with its ultimately painful choice
between the default fatal degradation and unlimited new progress at the superior level of conscious understanding.
Note the key difference of such kind of real crisis in modern science
from its much more comfortable description within the well-known concept
of the end of science [59] as being due to a “practically perfect” (or at least
“fundamentally saturated”) state of knowledge that does not reasonably
imply any essential further progress. This latter vision shows a strange correlation with the equally deficient (and much more widely accepted) attitude towards the state of the encompassing social system representing its
current (unitary) “liberal democracy” realisation as close to a practically
possible (positive) maximum of efficient social order. In reality, both modern official systems of knowledge and social organisation show visible
“saturation” signs only within certain, actually very rough and artificially
imposed simplification of complex reality, revealing huge and quickly
growing contradictions, especially just when they have entered now into a
critically unstable state of global bifurcation (with the ensuing inevitable
transition to a qualitatively different state).
As rigorously shown in this and other related papers [15-24,55-57],
this truly critical state of modern science and the related contrast choices
for further development of entire civilisation have in reality a wellspecified, scientifically nontrivial origin and resolution in terms of the necessary transition from the artificially limited, dynamically single-valued, or
unitary, science paradigm, method and vision to the dynamically multivalued, causally complete content of the universal science of complexity.
As a matter of fact, the absolutely dominating, dynamically single-valued
“model” of the unitary science and world vision represents the maximum
possible limitation of a great number of system (any real interaction process) realisations to just one, arbitrarily fixed and “postulated” realisation,
corresponding to strictly zero value of the unreduced dynamic complexity
(including all the cases of standard unitary “science of complexity”) [1524,55-57]. This unitary, effectively zero-dimensional (point-like) projection
59
of reality could give an impression of correct description only for actually
quite exceptional, “almost regular” cases of the limiting SOC regime (Section 2.3) exclusively considered in the “Newtonian” science paradigm, but
even in such cases there are the well-known “unsolvable” (or badly solved)
problems of genuine chaoticity, irreversibility and time origin.
This drastic simplification of reality corresponds also to the so-called
“positivistic” ideology of unitary science (in particular, taking the form of
“mathematical physics” in its most “exact” branches), which explicitly rejects the necessity of genuine, “truly complete” understanding of the observed reality (defended especially by René Descartes, the famous precursor of Newtonian positivism) in favour of its “model”, simulating description, where inevitable glaring contradictions and ruptures (nonuniversality)
are “compensated” by simplicity of an “exact” (or perturbative) model,
“sufficiently correctly” imitating a particular kind of observable behaviour
(but usually not other ones described by separate “models”) and not resulting from the complete (interaction) problem solution. It becomes clear now
that such only slightly decorated empiricism of the dominating positivistic
ideology of the unitary science is but a general expression of the underlying
dynamic single-valuedness, whereas the dynamic multivaluedness of the
truly complete (and thus truly exact!) problem solution (Section 2) leaves
no place for any “mysteries”, ruptures and other contradictions of the postulated unitary “models”. We can say therefore that the current “end of science” represents indeed the definite end of just that, actually very special
kind of positivistic, or unitary, science, which should now be extended,
with the help of the causally complete, universally applicable problem solution, to the intrinsically non-contradictory, at least locally complete
knowledge of the universal science of complexity (it is limited only by inaccessible observation possibilities, which does not really change the practical completeness of the obtained picture of reality).
Whereas the rigorous basis of the universal science of complexity is
properly exposed in Section 2 and its advantages in application to the problem of consciousness are revealed in Sections 3 and 4, we can emphasize
here the general, “ideological”, fundamental distinctions of this new, extended science framework with respect to usual, unitary science postulates
and results [57].
60
(1) The entire framework and content of usual, dynamically singlevalued, positivistic science is deeply based on the tacit self-identity postulate and related “rigorous” statements of various theorems of uniqueness of
problem solution. The self-identity postulate implies the apparently “evident” identity of any mathematical (and respective real) structure A to itself, A A , including its formal time dependence, if any, A(t ) A(t ) .
However, as we have seen above (Section 2.1), the unreduced interaction
process within any realistic structure has the dynamically multivalued result, in the form of multiple system realisations, permanently replacing
each other in a causally (and truly) random order. Therefore any realistic
structure, described in the causally complete framework of the universal
science of complexity by the unreduced, dynamically multivalued problem
solution, is not (exactly) self-identical, A A , which also gives rise to the
real, naturally unstoppable and irreversible time flow, A A A(t ) (Section 2.4). We deal here with the deeply diverging character of reality vision
and presentation in unitary science and universal complexity science: the
static, fixed structures of the former (including formal, postulated time dependence) are opposed to permanently, intrinsically and chaotically changing structure-processes of the latter (including externally regular or static
structures and processes). As to the notorious “uniqueness theorems” of
unitary science, they just realise a standard logical trap, where the tacitly
presumed single-valuedness (e.g. of interaction potential) is then restated as
the “rigorously derived” theorem conclusion [57]. As a matter of fact, no
real, truly rigorous and complete problem solution can possess the uniqueness property, already because one cannot stop the real, entropy-increasing
(and thus structure changing) time flow. Needless to say, already the most
obvious empirical properties of intelligence and consciousness provide a
clear demonstration of the absence of self-identity and uniqueness, in correlation with the persisting difficulties of genuine understanding of intelligence and consciousness within the unitary science framework [1-12].
(2) Another characteristic, inevitable property of the unitary projection of reality is its absence of well-specified, tangible material quality of
purely abstract structures used (forming the very basis of the major “mathematical physics” approach), which is directly related to its artificially limited, dynamically single-valued scheme, or “model”, of reality. As shown
in our unreduced interaction analysis (Section 2.2), the missing material
61
quality is rigorously defined in the universal science of complexity by the
dynamically multivalued entanglement of interacting system/process components, organised into the hierarchy of dynamically probabilistic fractal,
which is quite different from usual, unitary fractality and provides the truly
exact (causally complete) description of real structures. It underlies also
such universal properties, especially important for intelligent and conscious
behaviour, as autonomous dynamic adaptability and teleology (creation of
and evolution towards local and global purposes).
(3) The absence of the origin of genuine randomness in the dynamically single-valued approach of conventional science is closely related to
its self-identity property and unique-solution projection (item 1). Whereas
the intrinsic and omnipresent dynamic randomness and chaoticity is immediately implied by the unreduced, dynamically multivalued problem solution (Section 2.1), the unitary theory is forced to introduce its “widely accepted” notion of chaos and randomness in an artificial and contradictory
way, in the form of “exponentially diverging” (but in principle regular) trajectories, incorrectly extending the perturbation theory result and supposed
to “amplify” small, but already present, externally inserted “random deviations” in initial conditions. The same kind of incorrect trickery is used in
other ideas of chaoticity in the unitary “complexity science”, such as
“strange attractors” or “routes to chaos”. Note that only genuine, intrinsic
and interaction-driven randomness is necessary for the observed efficiency
of major searching, estimating and planning activities of intelligent and
conscious systems.
(4) The absence of genuine, dynamic discreteness in the dynamically
single-valued analysis is actually related to the problem of structure formation, or emergence, as such, fundamentally missing in usual theory and
only artificially inserted into its models from the beginning (including the
formally imposed space and time concepts and variables). While the discreteness of emerging real structures is provided, in the unreduced interaction analysis, by the dynamic discreteness of changing realisations and their
complexity levels (Sections 2.1 and 2.4), it is replaced either by smooth
unitary continuity or by false, mechanistically imposed discreteness in unitary science. Qualitative limitations and deep contradictions of these imitations are characteristic also of other interconnected mathematical constructions of standard theory, including the unitarity itself, calculus, evolution
62
operators, symmetry operators, any unitary operators, Lyapunov exponents,
path integrals, and statistical theories. Therefore all the related concepts of
emergence, creativity and qualitative transitions omnipresent in intelligence
and consciousness dynamics (“understanding”, “ideas”, etc.) can be consistently formulated only within the unreduced, dynamically multivalued
description of the universal science of complexity.
It is important to emphasize finally the unique, unifying global features of the unreduced complexity description appearing as unified manifestations of the single law, the absolutely universal symmetry of complexity, which expresses the behaviour of the equally unified world structure in
the form of dynamically probabilistic fractal (Sections 2.2 and 2.4). One
can compare these rigorously derived and variously confirmed results [1523,55-57] with ever increasing doubts about the very possibility of such
kind of unification (or even about the existence of objective and truly fundamental scientific laws in general) [59,64-67], even within the limited
scope of fundamental physics (after so many failed attempts to obtain it in
various schemes of unitary “mathematical physics”). The comparison reveals also the astonishing blindness and deafness of unitary science practice, which is closely related to its strongly limited content [16,57].
5.2. Complexity revolution as the necessary transition
to superior level of consciousness
As rigorously demonstrated in previous sections (see especially Sections 4 and 5.1), both techno-social demands of further civilisation progress
and modern deep problems of scientific knowledge development necessitate the transition to a superior level of reality understanding equivalent to a
higher level of (general) consciousness. According to the complexity correspondence principle (Section 3.1), this is indispensable already for the genuine, causally complete and practically efficient understanding of the phenomenon of consciousness itself, but actually appears to be necessary for
further progress in all fields of fundamental science (and thus eventually
technology and everything else), starting already from the lowest complexity levels (elementary particles and fields) [15-24,55-57].
One should speak therefore about a much deeper and wider transition
in the entire civilisation development, implied by the universal science of
63
complexity and the observed development tendencies, than the corresponding professional knowledge progress itself (which has, of course, its own
importance and plays the key role in this transition). We deal here, in fact,
with the ensuing “new way of thinking” and related new, complex-dynamic
approaches in all spheres of human activity, as opposed to the still dominating tendency of simplification, even despite the evident advent of superior
complexity in practical life (due to the previous huge, but mainly empirically obtained progress). It becomes obvious that the necessary transition
from the traditional unitary tendency of maximum possible simplification
(where informally “the simpler the better”) to the opposite, exclusively
progress-bringing tendency of growing complexity (where greater complexity is generally better) can occur only in the form of a highly nonlinear,
rapid and collective enough (though fundamentally individual) “revelation”
called here the revolution of complexity (or complexity transition)
[15,16,55-57]. In particular, it is the provably single possible way to realise
the notorious purpose of sustainable development (see also the next section), which remains but a strongly popularised case of wishful thinking (or
even a dangerous illusion) within the traditional, simplification-based unitarity and its mechanistic approach, irrespective of the quantities of technical efforts applied (including the pseudo-“green” technologies, only imitating ecological advantages).
This latter case of sustainable development demonstrates an important general constituent and result of the imminent complexity revolution, which implies not only new ways, means and instruments, but also
and especially the new general purpose of development and human life on
every scale. It is evident that today such suitable, universal and practically
sustainable purpose of civilisation development (in both its social and individual aspects) is persistently absent, probably for the first time in its
“modern” history ( AD ). Former versions of the general purpose (under
various religious, ideological and techno-scientific guises) have disappeared starting approximately from the beginning of the twentieth century
(the famous religious-philosophical “death of God”), while no new ones, of
a suitably high level, have appeared until now. The reason for this persisting (fundamentally) purposeless existence is precisely the necessary qualitatively big progress of consciousness in the direction of explicit complexity growth and efficient monitoring.
64
Now that the necessity of complexity transition becomes evident, together with the key implication of qualitatively growing, essentially complex-dynamic consciousness, we can formulate the expected new general,
ultimate purpose at the forthcoming superior level of complexity-driven
progress as the permanent, maybe uneven but unstoppable progress of that
unreduced, now practically unlimited human (including artificial) consciousness (in all its now unified aspects of mind, spirit, emotion, etc.). It
naturally starts with the key, step-like turn of complexity transition (from
the still dominating unitary thinking) and then continues as a more gradual
and stable, never-ending growth of consciousness dominating in all spheres
of human activity. The huge, unlimited scale of this new general purpose,
far beyond any traditional limitations and separations of usual “science”,
“spirituality” and “practical life”, demonstrates the true extension of consequences of the above dynamic multivaluedness and related universal complexity concept (Section 2), without any decrease of its intrinsic scientific
rigour (taking into account, in particular, its causally complete concept of
consciousness, Sections 3 and 4).
5.3. Genuine sustainability: Its rigorous definition,
major features and practical realisation
As mentioned above, the qualitatively big and nontrivial transition to
the truly sustainable development way for the entire civilisation constitutes
an integral part of the revolution of complexity in science and technology,
implying also the social and intellectual transition to the superior level of
consciousness. This result is very different from all usual, semi-empirical
and basically wrong ideas about sustainability, as we show [55-57] that this
unitary sustainability assumed without essential, qualitatively big transition
to the complexity-growth regime in all human activities is strictly impossible and may actually play the negative role of a vain, but strongly dominating illusion, preventing the transition to genuine sustainability.
We show first [56] that the universal curve of complexity development from dynamic information to dynamic entropy (see Section 2.4) goes
right now through a major bifurcation point, after which it can continue,
within the current tendency and complexity level, only in the fatal complexity-destruction regime ending in the essential degradation down to
65
qualitatively lower levels of complexity and consciousness, or else it can
pass to the intrinsically creative and sustainable way after the transition to
the complexity-creation mode at the superior level of consciousness and
complexity development. It is important that this rigorously derived conclusion does not depend on the details of unitary regime realisation in the
now dominating, default tendency, including the intensely imposed pseudo“green” technologies and various “resource-saving” practices (they can only slightly slow down the occurring degradation, but also provide a dangerous illusion of problem solution until it will be too late for the genuine,
complexity-driven sustainability transition providing the true solution). In
other words, it is rigorously shown that we are in a special development
point now, facing the “complexity barrier” after the global “complexity
threshold”, starting from which the traditional, “eternal” drive of purely
empirical “invisible hand”, in economy and elsewhere, becomes fundamentally inefficient for any further progress, forever and can now produce only
increasing systemic degradation over all scales and dimensions (as opposed
to the dominating idea of only a temporal crisis, however deep it may be,
followed by the “natural”, empirically driven new rise).
As to the concrete ways of realisation of the real sustainability transition and stable progress after that, they will always involve the key change
from the traditional unitary complexity-destruction practices, approaches
and thinking to the qualitatively different complexity-creation activities, in
science, technology and engineering, social dynamics, settlement structure
and related, unifying intellectual development [15,16,55-57]. This crucial
and direct involvement of the unreduced dynamic complexity, rigorously
and universally based on the causally complete, dynamically multivalued
interaction problem solution (Section 2), constitutes the well-defined, essential difference from any dominating unitary ideas of sustainability and
further civilisation progress.
We have demonstrated above the crucial advantages of the unreduced concept of dynamic complexity in understanding of intelligence and
consciousness dynamics, in direct relation to urgent development problems
(Sections 3 and 4). It is important that equally great, problem-solving advantages are provided by the same unreduced complexity analysis in all
other fields of fundamental science (otherwise stagnating, or “ending”),
from particle physics to efficient genetics, causal biology, integral medicine
66
and creative ecology [15-24,55-57]. It is not difficult to see that the same is
true for applied science, technology and engineering development and its
accumulating unsolved, pressing problems related e.g. to the new, pure and
practically unlimited energy sources, efficient, sustainable exploitationdevelopment of all natural resources combined with growing infrastructure
quality, or emerging medical and psychological difficulties [15,55-57]. The
observed dangerous stagnation in these key directions, despite quantitatively huge and technically powerful efforts within the unitary approach, confirms the necessity of a qualitatively new vision, which we specify in the
form of our unreduced dynamic complexity concept.
Similar general transformation from complexity-destruction to complexity-growth mode will inevitably take place in social structure and science organisation and practice itself, from the centralised and selfdestructive Unitary system (the only type of organisation known until now,
in various forms) to the distributed and intrinsically creative Harmonical
system [15,55-57]. The new society of the harmonical level will be qualitatively different from any, even most “developed” unitary organisation, including the appearance of omnipresent social consciousness at the harmonical level located, of course, within each individual consciousness and definitely absent in only empirically, mechanistically driven unitary development mode. Such self-aware society is therefore able, in the normal way of
its existence, to causally understand and guide its own development as that
of a real complex system (with the above general purpose of further consciousness progress, Section 5.2), contrary to any unitary, even scientifically rich social organisation.
Needless to say, the organisation and role of the new, practically unlimited knowledge creation system, now inseparable from the entire social
system and replacing the unitary science content and organisation, will also
change and grow qualitatively after the sustainability transition, where
“science” will not be isolated any more into an esoteric activity of selfestimated “sages”, practically inaccessible for real “public understanding”
(and thus any efficient control), but will instead be organically, inseparably
interwoven with the fabric of entire social life and development as its major, driving element (which is evidently the only possibility for a society to
be estimated as really “developed”, but it can actually be realised only at
the Harmonical level, after the complexity transition). That is why the sus67
tainability and complexity transition can also be called the last scientific
revolution [57] (with the reference to the famous analysis of Thomas Kuhn
[68]), after which the development of science (and actually anything else)
occurs in a stable and permanent way, without accumulating antagonistic
contradictions followed by a characteristic disruptive “revolution” of unitary science (remaining thus a past phenomenon inherent only to that, very
special, artificially limited kind of knowledge). It is evident that such new
kind of progress of ever more complex system of self-aware knowledgebased society can be efficiently guided only by the causally complete content and dynamics of the universal science of complexity, such as the one
tentatively outlined in previous sections, where the organisation and social
involvement of that truly new kind of science forms itself a major integral
part of the unified complex system of Harmonical, intrinsically sustainable
society. The urgently needed sustainability can thus be rigorously specified
itself as that superior level of consciousness and knowledge based on the
unreduced and now properly growing dynamic complexity of the planetary
environment consistently described in the above dynamic multivaluedness
concept.
68
References
[1] J. Horgan, The Undiscovered Mind: How the Human Brain Defies
Replication, Medication, and Explanation (Touchstone, New York,
2000).
[2] S. Blackmore, Consciousness: An Introduction (Oxford University
Press, New York, 2004).
[3] C. Koch, The Quest for Consciousness: A Neurobiological Approach
(Roberts & Company Publishers, Englewood, 2004).
[4] F. Crick, The Astonishing Hypothesis (Charles Scribner’s Sons, New
York, 1994).
[5] D. Dennett, Consciousness Explained (Little, Brown, Boston, 1991).
[6] G.M. Edelman, Wider Than the Sky: The Phenomenal Gift of Consciousness (Yale University Press, New Haven, 2004).
[7] S. Pinker, How the Mind Works (Norton, New York, 1997).
[8] D. Chalmers, The Conscious Mind: In Search of a Fundamental Theory (Oxford University Press, New York, 1996).
[9] O. Flanagan, The Science of the Mind (MIT Press, Cambridge, 1991).
O. Flanagan, Consciousness Reconsidered (MIT Press, Cambridge,
1992).
[10] Towards a Science of Consciousness: The First Tucson Discussions
and Debates, Ed. by S.R. Hameroff, A.W. Kaszniak, and A.C. Scott
(MIT Press, Cambridge, 1996). See also
http://consciousness.arizona.edu/archived.htm.
[11] R. Penrose, Shadows of the Mind: A Search for the Missing Science of
Consciousness (Oxford University Press, New York, 1994).
[12] D. Zohar, The Quantum Self (William Morrow, New York, 1990).
[13] Machine Consciousness, Ed. by O. Holland, Journal of Consciousness
Studies 10, No. 4-5 (2003).
[14] I. Aleksander, How to Build a Mind (Weidenfeld & Nicolson, London,
2000). See also
http://www.scholarpedia.org/article/Machine_consciousness.
69
[15] A.P. Kirilyuk, Universal Concept of Complexity by the Dynamic Redundance Paradigm: Causal Randomness, Complete Wave Mechanics, and the Ultimate Unification of Knowledge (Naukova Dumka, Kyiv, 1997). For a non-technical review see E-print physics/9806002 at
http://arXiv.org.
A.P. Kirilyuk, “Universal Science of Complexity: Consistent Understanding of Ecological, Living and Intelligent System Dynamics”, Eprint arXiv:0706.3219 at http://arXiv.org.
[16] A.P. Kirilyuk, Complex Dynamics of Real Quantum, Classical and
Hybrid Micro-Machines: From Causally Complete Quantum Mechanics to the Efficient Nanotechnology and Development Concept (LAP
LAMBERT Academic Publishing, Saarbrücken, 2013). E-print physics/0211071 at http://arXiv.org.
[17] A.P. Kirilyuk, “The Universal Dynamic Complexity as Extended Dynamic Fractality: Causally Complete Understanding of Living Systems Emergence and Operation”, In: Fractals in Biology and Medicine, Vol. III, Ed. by G.A. Losa, D. Merlini, T.F. Nonnenmacher and
E.R. Weibel (Birkhäuser, Basel, 2002), p. 271. E-print physics/0305119 at http://arXiv.org.
A.P. Kirilyuk, “Complex-Dynamical Extension of the Fractal Paradigm and Its Applications in Life Sciences”, In: Fractals in Biology
and Medicine, Vol. IV, Ed. by G.A. Losa, D. Merlini, T.F. Nonnenmacher and E.R. Weibel (Birkhäuser, Basel, 2005), p. 233. E-print
physics/0502133 at http://arXiv.org.
[18] A.P. Kirilyuk, “Universal Symmetry of Complexity and Its Manifestations at Different Levels of World Dynamics”, Proceedings of Institute of Mathematics of NAS of Ukraine 50 (2004) 821. E-print physics/0404006 at http://arXiv.org.
[19] A.P. Kirilyuk, “Dynamically Multivalued Self-Organisation and Probabilistic Structure Formation Processes”, Solid State Phenomena 9798 (2004) 21. E-print physics/0404006 at http://arXiv.org.
[20] A.P. Kirilyuk, “Double Solution with Chaos: Dynamic Redundance
and Causal Wave-Particle Duality”, E-print quant-ph/9902015 at
http://arXiv.org.
70
A.P. Kirilyuk, “Double Solution with Chaos: Completion of de Broglie's Nonlinear Wave Mechanics and its Intrinsic Unification with the
Causally Extended Relativity”, E-print quant-ph/9902016.
[21] A.P. Kirilyuk, “Quantum Field Mechanics: Complex-Dynamical
Completion of Fundamental Physics and Its Experimental Implications”, E-print physics/0401164 at http://arXiv.org.
A.P. Kirilyuk, “Complex-Dynamical Approach to Cosmological Problem Solution”, E-print physics/0510240 at http://arXiv.org.
A.P. Kirilyuk, “Consistent Cosmology, Dynamic Relativity and Causal Quantum Mechanics as Unified Manifestations of the Symmetry of
Complexity”, E-print physics/0601140 at http://arXiv.org.
[22] A.P. Kirilyuk, “75 Years of the Wavefunction: Complex-Dynamical
Extension of the Original Wave Realism and the Universal Schrödinger Equation”, E-print quant-ph/0101129 at http://arXiv.org.
[23] A.P. Kirilyuk, “Complex-Dynamical Solution to the Many-Body Interaction Problem and Its Applications in Fundamental Physics”,
Nanosystems, Nanomaterials, Nanotechnologies 10 (2012) 217. Eprint arXiv:1204.3460 at http://arXiv.org.
[24] A.P. Kirilyuk, “Quantum chaos and fundamental multivaluedness of
dynamical functions”, Annales de la Fondation Louis de Broglie 21
(1996) 455. E-prints quant-ph/9511034 - 36 at http://arXiv.org.
[25] P.H. Dederichs, “Dynamical Diffraction Theory by Optical Potential
Methods”, In: Solid State Physics: Advances in Research and Applications, Ed. by H. Ehrenreich, F. Seitz, and D. Turnbull (Academic
Press, New York) 27 (1972) 136.
[26] A.P. Kirilyuk, “Theory of charged particle scattering in crystals by the
generalised optical potential method”, Nucl. Instr. Meth. B69 (1992)
200.
[27] S. Rahav, I. Gilary, and S. Fishman, “Time Independent Description of
Rapidly Oscillating Potentials”, Phys. Rev. Lett. 91 (2003) 110404.
[28] M.J. Donald, “Quantum theory and the brain”, Proc. Roy. Soc. London
A 427 (1990) 43.
[29] S. Hameroff and R. Penrose, “Orchestrated reduction of quantum co71
herence in brain microtubules: A model for consciousness”, Neural
Network World 5 (1995) 793.
S. Hameroff, “Quantum computation in brain microtubules? The Penrose-Hameroff "Orch OR" model of consciousness”, Phil. Trans. Roy.
Soc. London A 356 (1998) 1869.
S. Hagan, S.R. Hameroff, and J.A. Tuszynski, “Quantum Computation
in Brain Microtubules: Decoherence and Biological Feasibility”, Phys.
Rev. E 65 (2002) 061901. E-print quant-ph/0005025 at
http://arXiv.org.
S. Hameroff and R. Penrose, “Consciousness in the universe: A review of the ‘Orch OR’ theory”, Physics of Life Reviews (2013),
http://dx.doi.org/10.1016/j.plrev.2013.08.002 .
See also http://www.quantumconsciousness.org/.
[30] G. Vitiello, “The dissipative brain”, In: Brain and Being - At the
boundary between science, philosophy, language and arts, Ed. by
G.G. Globus, K.H. Pribram, and G. Vitiello (John Benjamins, Amstedam, 2004), p. 317. E-print q-bio.OT/0409037 at http://arXiv.org.
E. Pessa and G. Vitiello, “Quantum noise induced entanglement and
chaos in the dissipative quantum model of brain”, Int. J. Mod. Phys. B
18 (2004) 841. E-print quant-ph/0406161 at http://arXiv.org.
E. Alfinito and G. Vitiello, “Formation and life-time of memory domains in the dissipative quantum model of brain”, Int. J. Mod. Phys. B
14 (2000) 853; 1613. E-print quant-ph/0002014 at http://arXiv.org.
[31] A. Mershin, D.V. Nanopoulos, and E.M.C. Skoulakis, “Quantum
Brain?”, E-print quant-ph/0007088 at http://arXiv.org.
[32] M. Perus and H. Bischof, “A neural-network-like quantum information
processing system”, E-print quant-ph/0305072 at http://arXiv.org.
[33] S. Gupta and R.K.P. Zia, “Quantum Neural Networks”, E-print quantph/0201144 at http://arXiv.org.
[34] E.C. Behrman, V. Chandrashekar, Z.Wang, C.K. Belur, J.E. Steck, and
S.R. Skinner, “A Quantum Neural Network Computes Entanglement”,
E-print quant-ph/0202131 at http://arXiv.org.
72
[35] H.P. Stapp, “Chance, Choice, and Consciousness: The Role of Mind in
the Quantum Brain”, E-print quant-ph/9511029 at http://arXiv.org.
H.P. Stapp, “Decoherence, Quantum Zeno Effect, and the Efficacy of
Mental Effort”, E-print quant-ph/0003065 at http://arXiv.org.
H.P. Stapp, “From quantum nonlocality to mind-brain interaction”, Eprint quant-ph/0009062 at http://arXiv.org.
[36] M. Dugic, M.M. Cirkovic, and D.R. Rakovic, “On a Possible Physical
Metatheory of Consciousness”, Open Systems & Information Dynamics 9 (2002) 153. E-print quant-ph/0212128 at http://arXiv.org.
[37] A. Kaivarainen, “Hierarchic model of consciousness: from molecular
Bose condensation to synaptic reorganisation”, E-print physics/0003045 at http://arXiv.org.
[38] H. Hu and M. Wu, “Spin-Mediated Consciousness Theory: Possible
Roles of Oxygen Unpaired Electronic Spins and Neural Membrane
Nuclear Spin Ensemble in Memory and Consciousness”, Medical Hypotheses 63 (2004) 633. E-print quant-ph/0208068 at http://arXiv.org.
[39] D. Zohar and I.N. Marshall, Quantum Self: Human Nature and Consciousness Defined by the New Physics (Quill Books, New York,
1991).
D. Zohar and I. Marshall, The Quantum Society: Mind, Physics, and a
New Social Vision (Quill, New York, 1995).
[40] J. Satinover, The Quantum Brain: The Search for Freedom and the
Next Generation of Man (John Wiley, New York, 2001).
[41] A. Khrennikov, “Classical and quantum mechanics on information
spaces with applications to cognitive, psychological, social and anomalous phenomena”, Found. Phys. 29 (1999) 1065. E-print quantph/0003016 at http://arXiv.org.
A. Khrennikov, “Quantum-like formalism for cognitive measurements”, E-print quant-ph/0111006 at http://arXiv.org.
A. Khrennikov, “Probabilistic pathway representation of cognitive infromation”, J. Theor. Biology 231 (2004) 597. E-print qbio.NC/0408022 at http://arXiv.org.
73
[42] D.V. Juriev, “Quantum String Field Psychophysics of Nastroenie”, Eprint physics/0105066 at http://arXiv.org.
[43] P. Gralewicz, “Quantum computing in neural networks”, E-print
quant-ph/0401127 at http://arXiv.org.
[44] Y. Kurita, “Indispensable Role of Quantum Theory in the Brain Dynamics”, E-print quant-ph/0408148 at http://arXiv.org.
[45] D. Aerts and M. Czachor, “Quantum aspects of semantic analysis and
symbolic artificial intelligence”, J. Phys. A 37 (2004) L123. E-print
quant-ph/0309022 at http://arXiv.org.
D. Aerts, J. Broekaert, and L. Gabora, “A Case for Applying an Abstracted Quantum Formalism to Cognition”, New Ideas in Psychology
29 (2011) 136. E-print quant-ph/0404068 at http://arXiv.org.
[46] E.A. Novikov, “Quaternion dynamics of the brain”, E-print
nlin.PS/0311047 at http://arXiv.org.
E.A. Novikov, “Manipulating consciousness”, E-print
nlin.PS/0403054 at http://arXiv.org.
[47] V.K. Jirsa and H. Haken, “A derivation of a macroscopic field theory
of the brain from the quasi-microscopic neural dynamics”, Physica D
99 (1997) 503.
V.K. Jirsa and H. Haken, “Field theory of electromagnetic brain activity”, Phys. Rev. Lett. 77 (1996) 960.
[48] T.D. Frank, A. Daffertshofer, C.E. Peper, P.J. Beek, and H. Haken,
“Towards a comprehensive theory of brain activity: Coupled oscillator
systems under external forces”, Physica D 144 (2000) 62.
[49] M. Toussaint, “Learning a world model and planning with a selforganising, dynamic neural system”, In: Advances of Neural Information Processing Systems 16, Ed. by S. Thrun, L. K. Saul, B.
Schölkopf (MIT Press, Cambridge, 2004), p. 929. E-print
nlin.AO/0306015 at http://arXiv.org.
[50] Biophysical Aspects of Coherence (conference 1995), In: Neural Network World 5 (1995) No. 5.
G.L. Sewell, “Quantum model of biological coherence and chaos”,
Ibid., p. 725.
74
J. Pokorný, “Fröhlich coherent states: Implications for interaction in
biological systems and information transfer”, Ibid., p. 831.
[51] A. Juarrero, Dynamics in Action. Intentional Behaviour as a Complex
System (MIT Press, Cambridge, 2002).
[52] J.A.S. Kelso, Dynamic Patterns: The Self-Organisation of Brain and
Behaviour (MIT Press, Cambridge, 1995).
[53] S. Lloyd, “Ultimate physical limits to computation”, Nature 406
(2000) 1047. E-print quant-ph/9908043 at http://arXiv.org.
S. Lloyd, “How fast, how small, and how powerful?: Moore's law and
the ultimate laptop”,
http://www.edge.org/3rd_culture/lloyd/lloyd_index.html.
S. Lloyd, “The Computational Universe”,
http://www.edge.org/3rd_culture/lloyd2/lloyd2_index.html.
S. Lloyd, “Computational capacity of the Universe”, Phys. Rev. Lett.
88 (2002) 237901. E-print quant-ph/0110141 at http://arXiv.org.
[54] S. Lloyd, “Universe as quantum computer”, Complexity 3 (1997) 32.
E-print quant-ph/9912088 at http://arXiv.org.
[55] A.P. Kirilyuk, “Towards Sustainable Future by Transition to the Next
Level Civilisation”, In: The Future of Life and the Future of Our Civilisation, Ed. by V. Burdyuzha (Springer, Dordrecht, 2006), p. 411. Eprint physics/0509234 at http://arXiv.org.
A.P. Kirilyuk, “IT Complexity Revolution: Intelligent Tools for the
Globalised World Development”, In: IT Revolutions, Ed. by M. Ulieru, P. Palensky, and R. Doursat (Springer, Berlin Heidelberg, 2009), p.
1. E-print arXiv:0910.5495 at http://arXiv.org.
[56] A.P. Kirilyuk, “Dynamic Origin of Evolution and Social Transformation”, Nanosystems, Nanomaterials, Nanotechnologies 11 (2013) 1.
E-print arXiv:1212.1939 at http://arXiv.org.
[57] A.P. Kirilyuk, “The Last Scientific Revolution”, In: Against the Tide:
A Critical Review by Scientists of How Physics & Astronomy Get
Done, Ed. by M. López Corredoira and C. Castro Perelman (Universal
Publishers, Boca Raton, 2008), p. 179. E-print arXiv:0705.4562 at
http://arxiv.org.
75
[58] J. Horgan, “From Complexity to Perplexity”, Scientific American,
June (1995) 74.
[59] J. Horgan, The End of Science. Facing the Limits of Knowledge in the
Twilight of the Scientific Age (Addison-Wesley, Helix, 1996).
J. Horgan, “The Final Frontier”, Discover Magazine, October (2006),
http://discovermagazine.com/2006/oct/cover.
[60] Against the Tide. A Critical Review by Scientists of How Physics and
Astronomy Get Done, Eds. M. Lopez-Corredoira and C. Castro Perelman (Universal Publishers, Boca Raton, 2008). E-print http://philsciarchive.pitt.edu/4046/.
[61] M. Lopez-Corredoira, The Twilight of the Scientific Age (Brown
Walker Press, Boca Raton, 2013). See also: E-print arXiv:1305.4144
at http://arXiv.org.
M. Lopez-Corredoira, “What is research?”, E-print physics/0201012
at http://arXiv.org. Ciencia Digital 8 (2000).
[62] A. Unzicker and S. Jones, Bankrupting Physics: How Today's Top
Scientists are Gambling Away Their Credibility (Palgrave Macmillan,
New York, 2013).
[63] P. Wells, “Perimeter Institute and the crisis in modern physics”, Maclean’s, 5 September (2013),
http://www2.macleans.ca/2013/09/05/perimeter-institute-and-thecrisis-in-modern-physics/. See also
http://www.math.columbia.edu/~woit/wordpress/?p=6238.
[64] M. Gleiser, A Tear at the Edge of Creation: A Radical New Vision for
Life in an Imperfect Universe (Free Press, New York, 2010).
M. Gleiser, “The imperfect universe: Goodbye, theory of everything”,
New Scientist, 8 May (2010), No. 2759, p. 28.
http://www.newscientist.com/article/mg20627591.200-the-imperfectuniverse-goodbye-theory-of-everything.html .
M. Gleiser, “Theory of Everything... Still Searching?”, 13.7 Cosmos &
Culture, 9 March, 2011,
http://www.npr.org/blogs/13.7/2011/03/09/134373659/theory-ofeverything-still-searching .
76
M. Gleiser, “Enough Already With This ‘Theory Of Everything’”,
13.7 Cosmos & Culture, 28 August, 2013,
http://www.npr.org/blogs/13.7/2013/08/28/216095888/enoughalready-with-this-theory-of-everything .
[65] G. Longo, M. Montévil and S. Kauffman, “No entailing laws, but enablement in the evolution of the biosphere”, E-print arXiv:1201.2069 at
http://arXiv.org.
S. Kauffman, “Beyond Reductionism Twice: No Laws Entail Biosphere Evolution, Formal Cause Laws Beyond Efficient Cause Laws”,
E-print arXiv:1303.5684 at http://arXiv.org.
S. Kauffman, “Beyond Entailing Law?”, 13.7 Cosmos & Culture, 20
June, 2011,
http://www.npr.org/blogs/13.7/2011/06/20/137296039/beyondentailing-law .
[66] M. Campbell, “What is the point of a theory of everything?”, New Scientist, 12 October (2013), No. 2938, p. 36.
http://www.newscientist.com/article/mg22029380.800-what-is-thepoint-of-a-theory-of-everything.html .
[67] A. Noë, “Should We Expect A Theory Of Everything?”, 13.7 Cosmos
& Culture, 7 February, 2014,
http://www.npr.org/blogs/13.7/2014/02/07/273020930/should-weexpect-a-theory-of-everything .
[68] T. Kuhn, The Structure of Scientific Revolutions (Chicago University
Press, Chicago, 1970). First edition: 1962.
77 |
What are quantum theorists doing at a
conference on consciousness?
1
arXiv:quant-ph/9602006v1 9 Feb 1996
Euan J. Squires 2
Department of mathematical sciences
University of Durham
Durham City, DH1 3LE, England.
February, 1996
Abstract The reason why orthodox quantum theory necessarily invokes consciousness is explained.
Several procedures whereby the Born probability rule can be introduced are discussed, and reasons
are given for prefering one in which consciousness selects a unique realised world. Consciousness
is something outside of the laws of physics (quantum mechanics), but it has a real effect upon the
experienced world. Finally, orthodox quantum theory is shown to require that consciousness acts
non-locally.
A possible answer to the question in the title of this talk would be to say that we can explain consciousness. That would be false; we have no more idea how to explain consciousness than anyone else, which
means we have NO idea! In fact the whole idea of trying to explain consciousness is probably a mistake;
consciousness just is.
The proper answer to the question is that we cannot understand quantum theory without invoking
consciousness.3
Quantum theory is a wonderful elegant theory, which, at least in principle, allows us to calculate the
properties of all physical (and chemical) systems. It gives correct results for the probabilities of particular
results of an enormous range of experiments. It is accurate and universal, and no violations of its predictions
are known, even where those predictions are very counter-intuitive.
BUT, if quantum theory really applies to all systems, then, except in very special circumstances, there
can never be any observations, i.e., there can be no events for which the above statistical predictions could
apply.
This fact is so important, and so simple, that we shall discuss an example. We imagine that there is a
system, the one to be “measured”, which is in a state that I describe as |+ >. (There is no need to worry
what this means or why I use such a funny notation).
This system in measured with an apparatus A, and I suppose that after the measurement the combined
system can be described by |+, A+ >. What this means is that the + reading on the apparatus corresponds
to the system being in the state +. Generally the apparatus is not isolated but in interaction with an
environment (air, microwave background, black-holes, strings, etc.). Call all this E, then the full state is
|+, A+ , E + >. Of course this will in general be changing with time, but I do not need to indicate this
explicitly.
Next, I suppose that Melinda looks at the apparatus. This puts her brain, denoted by M e, into a certain
state. Hence the state of the relevant system is now
|+, A+ , E + , M e+ > .
1
(1)
Text of talk to be given at the Tucson II conference, Towards a Science of Consciousness, 1996
e.j.squires@durham.ac.uk
3
The interpretation problem of quantum theory and the hard problem of consciousness also share the
property of attracting articles that claim to provide a solution but in fact do not address the problem.
2
1
Everything up to here is perfectly straightforward. Assuming that I knew the physical structure of the
apparatus (not too difficult to imagine), of the environment (a bit harder) and of Melinda’s brain (harder
still), then the evolution to this final state could be calculated from the Schrödinger equation.
Notice that it is totally irrelevant to the discussion what is the precise nature of the physical brain;
we need make no assuptions whatever about that, except that the brain is a physical thing and is therefore
described by the laws of quantum theory.
Now we need to introduce the bit that we none of us know anything about. Presumably the M e+ state
of Melinda’s brain corresponds to some sort of “pattern” which her consciousness, knowing something about
the apparatus A, interprets as meaning that the system was in the state +. To be concrete, suppose the
pattern is as given in fig. 1.
We can then repeat the above discussion with some other state of the system. Let us call this state
|− >. In an obvious generalisation of the notation used above, the state after measurement will now be
|−, A− , E − , M e− > .
(2)
Again there will be some pattern in Melinda’s brain which her consciousness recognises as meaning that the
system was in the state −. Suppose this time the pattern is as in fig. 2.
At this stage we do not have anything that is different from classical physics. The calculation yields
a particular result which is interpreted by consciousness. These however are the “special circumstances”
referred to above, where there is no measurement problem.
The problem arises because it is possible, and indeed in some cases very easy, to prepare a state which
is not + or −, but is a “bit of each”. We write this as a|+ > + b|− >, where the relative magnitudes of
a and b tell us something about how much of + compared to − the state contains. In practice most states
that are observed will have this form. (To prevent any possible misunderstanding here it is important to
emphasise that this new state is not just a way of saying that the state might be + or it might be −, and
that we do not know which. Quantum theory allows us to discuss this situation - the state is then called a
mixed state - but it is not what we have here.)
What happens when we measure this new state using the same apparatus as before? Here is another
piece of quantum magic. Given the results of the previous calculations, it is a trivial matter to calculate
what happens. In fact the final state becomes
a|+, A+ , E + , M e+ > + b|−, A− , E − , M e− > .
(3)
We do not get one pattern, or the other, but something that is a bit of one and a bit of the other. There is
nothing obviously remarkable about that; we started with the system in a state which we wrote as a “sum”
of system states, and we finish with a similar type of sum of observed states.
Now come the surprises.
1. It is a simple matter of fact that Melinda will experience either the + state or the − state. As far as
her experience is concerned the state (3) will be exactly as if it were either that in (1) or that in (2).
To be careful here, I should say that this is what Melinda will tell us. In order to be sure (see below)
we can check by doing the observation ourselves. Then I will be aware of either the pattern of fig 1 or the
pattern of figure 2 - certainly not the “sum” of the two patterns as in fig. 3.
Notice that this one result of which I am aware exists in Consciousness, but not in “physics”, i.e., no
particular result is present in the state of the physical world as it is calculated according to quantum theory.
If this is “dualism” then I am happy to be called a dualist.
2. The above fact follows from orthodox quantum theory - in the sense that will be made clear immediately. Because I sometimes read statements that seem to deny this, and because it is important to be precise
about what is meant, and because, if we think about it, it is rather amazing, I shall derive it.
To do this I suppose that Melinda had agreed to write a 0 on a piece of paper as soon as she knew
whether the system was in the state + or the state −. Note that she does not write down what it is, only
that she knows what it is. Clearly, in both the cases where the system was in the state + or −, as soon as
she had looked at the apparatus, then she would have written the 0. It then follows trivially from standard
quantum theory that in the case where the state was the sum of the two, she would again write down the 0.
2
Thus, she would tell the world that she had become aware of either the pattern in fig. 1, or the pattern in
figure 2. Every physical action she took would convey this message. I think this means that she would indeed
have become aware of one result, as indeed we know happens in practice. Otherwise she would consistently
be telling the world, and herself, a lie.
This seems to imply that orthodox quantum theory has told us something about how consciousness
actually works. Of course it cannot do this. We have inserted an assumption of consistency. All Melinda’s
physical actions, as long as they are governed by quantum theory will imply that she knows a unique result.
The assumption is that this actually means that she does know such a result. One could imagine (just about)
that, on the contrary, she was not aware of any result, but that nevertheless she put the 0 on the paper, and
in all other ways behaved as though she did.
It is worth noting that we cannot run this argument with a computer (try it). It works because Melinda
is conscious and it therefore makes sense to talk about “knowing”. Computers, on the other hand do not
know anything, and we would not have any way of giving the essential instruction to write a 0 as soon as
the result is known.
3. Here is something that does not follow from the simple evolution equation of quantum theory, i.e.,
the Schrödinger equation, which is all we have used so far. In a large set of identical runs of the above
experiment the number of times Melinda would see + and − would be in the ratio |a|2 /|b|2 . This is a “rule”
which is sort of added to quantum theory. It is called the Born rule (after Max Born who first proposed it),
and it has been confirmed repeatably in myriads of experiments.
So, where is the problem, and what has all this got to do with consciousness?
The complete description of the “physics” in orthodox quantum theory is the state displayed above, which
contains both terms, i.e. both “results”. The unique result of which I am aware does not exist in physics but only in consciousness. The Born rule does not have anything to say about physics - it says something
about consciousness.
I must qualify the above by emphasising the fact that I am speaking of orthodox quantum theory. I
could add something to physics (e.g. the Bohm hidden variable model) or I could change it (e.g. the explicit
collapse models of GRW/Pearle etc), so that the result would be in the physics. Even then the properties of
consciousness would appear, but all that is another story which we shall not follow here.
Naive Many-Minds Interpretation
To continue, we note that the simplest possibility for what is happening would be that after the measurement there are two “Melinda’s”, one of which has one experience, and one of which has the other. We
need have no concern that this does not appear to Melinda to be what is happening, because it is guaranteed
by quantum theory that each “Melinda” will be unaware of the existence of the other, and will indeed have
no possibility of knowing about the other (this is true for all practicable purposes - if she were sufficiently
clever she could perhaps devise means of checking whether the other Melinda really exists). What we have
here is the “naive” many-worlds interpretation of quantum theory; it is better called the “many-views” or
“many minds” interpretation [1,..4] because the physical world, described by the quantum state, e.g., as
displayed above in our simple example (eq. 3), is always ONE thing.
Two points should be noted here. First, the experienced world is precisely that, the world as experienced.
It is not identical to the physical world. When we “measure” something, we experience a particular result,
but, in general, that result does not refer to anything that was there before our experience of it, or even after
the experience; it exists only in consciousness. Secondly, all this has been achieved with nothing beyond
orthodox quantum theory.
However, although it is superficially very attractive, this naive interpretation DOES NOT WORK. The
reason is simple - it contains no probabilities, i.e., no Born rule. There are not “degrees of existence”;
everything will exist regardless of how small its probability should be according to the Born rule. To put this
another way, probabilities are for something to “happen” and here nothing has actually happened. Now I am
aware that the foundations of the whole theory of proability are very unsure, even in the classical domain,
but this should not prevent us from recognising that at this stage we do not have a satisfactory theory of
the quantum world.
3
One Mind Interpretation
To make progress, we can propose instead that, although the description of the physics is as given by
the state above, with both terms, consciousness actually selects one term [ 5,6,7]. Normally this will happen
at random with the weights given by |a|2 and |b|2 , so that the Born rule is guaranteed. (In general to say
that something happens at random requires that we give a weight, and there really are no other possibilities,
so the Born rule is very natural.)
What we have now is I believe an acceptable solution to the measurement problem of quantum theory.
It has several merits.
1. In principle it allows for consciousness to be “efficacious”, i.e., to be able to change the experienced
world. In other words it can help to explain what consciousness is for. The point here is that there may
be circumstances in which there is a quantum superposition in the brain which is not correlated to things
outside the brain (like in the displayed state above). Then the selection, which perhaps need not be random,
could determine the action that a person takes. This would correspond to our experience of free-will, and it
would have an effect on the experienced world, although it would not alter the total wavefunction. In other
words it would not violate the requirement (for some people) that physics is ‘closed”.
Of course, at this stage of our discussion (but not before) we have to make some assumptions about
physical brains. In order for there to be the possibility of what we are describing here to happen we have to
accept that brains are genuinely quantum systems that cannot be described by classical physics. I do not find
this difficult. Although surgeons may see brains as warm wet matter, which from their point of view can be
described perfectly well by classical physics, it remains true that there is no such thing as classical matter.
Without quantum theory there would be no matter. To say that quantum effects, as we are describing here,
cannot occur in brains, would be rather like telling a nineteenth century physicist who had just happened
to have invented quantum theory that, even if it were true, there would be no possibility of ever detecting
its effects in the real world.
2. The association of consciousness with “selection” seems to be something that others, from very
different arguments, want to make. For a recent example Cotterill [8] writes “consciousness is for....evaluation
and choice”.
3. There would be a unique “real”, i.e., experienced, world. The non-selected parts of the wavefunction
would not really exist. To have an analogy here, imagine a sheet of white paper. By putting a suitable mask
on this we could obtain a picture of say a person -see figure 4. Now different masks would produce different
pictures ( worlds) - indeed all possible pictures. It would be a misuse of language however to say that the
sheet of white paper contained all the pictures - only the one selected by the mask would exist.
4. As with most versions of the “many-worlds” interpretations, this allows us to use anthropic arguments
to explain the apparent coincidences necessary for our existence, but here it is with a unique world, rather
then a scenario in which all things conceivable actually exist. The argument would be that in some sort of
universal wavefunction, consciousness selects a part in which consciousness can exist.
Alternative Many-Views Models.
Several attempts have been made to give a meaning to probability when all experiences occur. For
example, Albert and Loewer [3] and Albert [9] have suggested that associated with every person there are
a large number of minds, and that each selects at random as with the single experience proposal above.
Again this seems to work, but clearly the number has to be very large, otherwise there will be the possibility
of meeting “zombies”. In fact Albert and Loewer suggest an infinite number, which I find hard to accept,
because I am not sure that I really know what it means to have an infinite number of “objects” associated
with a given person. Even worse is the fact that they want a continuous infinity. This runs into the problem
that there is no natural measure on a continuous infinity: it just does not mean anything to say, for example,
that “more” minds see one result than another. The same problem is met by Lockwood [4, 10] who proposes
instead to have all “minds” labelled by a continuous parameter, e.g., 0 < λ < 1, so that a certain fraction
of the line goes to one result, and another fraction to another, etc., in each case so as to give the Born rule.
Again, this suffers from what seems to me to be the insuperable problem that there is no natural measure
on such a line.
4
I should add that, on aesthetic grounds, I myself am more comfortable with the idea that there is one
world, rather than having to accept that all things that can be actually are, however improbable the Born
rule would make them. It just seems too much to have to believe that there really are people, holding
conferences on physics and consciousness, etc., who have never experienced interference, or read about it or
met anybody who had! They are going to have an awful shock next time they see a thin film of oil on water
(or at least “a large part”, whatever that may mean in this context, of all of them are!)
Non-locality
Finally, we must discuss the issue of non-locality. It is sometimes stated that one of the advantages
of the “many-worlds” style of solutions to the measurement problem is that they do not suffer from the
non-locality which is all too evident in the Bohm model or in collapse models. To some extent this is true;
the non-locality is removed from the physics because it only arises from the results of measurements, and
so does not occur if there are no such results. However, it is still around; it has simply been removed to
“consciousness”.
We can see this if we consider how consciousness can take note of the quantum probability. To do this
we need to think a little more about how we locate the “patterns” that correspond to a given experience.
Suppose that the quantum state is given by |Ψ(x, y, t) >, where x stands for the variables of particles in
the brain and y for particles in the system, the apparatus and the environment. The displayed state (3)
above is just one particular example of such a state. To see a pattern we must project this onto a state
of some presumed “consciousness basis” in the brain. If we denote this by states |Cn (x) >, where the
n labels possible experiences, then the probablity of the nth experience is, according to quantum theory,
| < C(x)|Ψ(x, y, t) > |2 . This however is not a number, but a function of the positions of all the other
particles (some of these may well be thousands of miles away!). To get a number we must integrate over all
these positions. This of course is horrendously non-local in realistic measurement situations. In other words,
consciousness, if it is to “know about” probabilities, as it must if we are to obtain the Born rule, cannot be
a local thing.
This is very important because it means that in the selection model there will only be one selection,
not one for every separate person, a fact which ensures the essential property that all observers will make
the same selection. Another way of saying this is to say that consciouness must be thought of as being ONE
thing. This is something in which Schrödinger firmly believed, and it may be a contribution that quantum
physics can make to the study of consciousness, thereby guaranteeing that quantum physicists continue to
have a place at meetings like this.
Related Ideas
The idea that consciousness has to be introduced in order to understand quantum theory has been
around since the 1920’s. Apart from the work mentioned above, recent contributions are due to Hodgson
[11], Mavromatos and Nanopolous [12], Penrose [13], Page [14] and Stapp [15]. These models have many
features in common, and in common with the model that I am advocating here (in particular, the selection
model shares many of the features discussed by Stapp in his recent articles [16,17]). The principle difference
is that, in varying ways these authors have models in which the operation of consciousness is associated
with some sort of explicit wavefunction collapse, so that the physics is not given exactly by the Schrödinger
equation. It seems to follow that there will be observable differences between the predictions of these models
and those of standard quantum theory (cf., for example, [18]). This is not necessarily a bad thing, but the
models need to be made sufficiently precise in order that these differences can be calculated.
There may be a more serious objection in that a proper description of the collapse requires a new
equation to replace the Schrödinger equation. Examples of such equations already exist of course (see [19]
and references therein), but, at least in the context of the present discussion, they suffer from the fact that
5
there is no reason why the collapse effect has anything to do with consciousness.4 Rather the collapse is
a universal phenomena, with the rate being very small, i.e. negligible, for microscopic systems, but being
proportional to something like the number of particles, so that it is large in the macroscopic world. If we follow
this line too closely then we are in danger of saying that consciousness arises, like rapid collapse, simply
from having large systems. I believe Stapp, at least, would reject this suggestion, in my opinion rightly.
Maybe things look different if the stochastic nature of the collapse process arises from something that is
non-computable. This might provide a link with possible non-algorithmic aspects of conscious thought.
REFERENCES
1. H.D.Zeh, 1981, The problem of conscious observation in quantum mechanical description, Epistemological
letters 73
2. E.J.Squires, 1987, Many views of one world - an interpretation of quantum theory, Eur. J. Phys.,8,
171-174
3. D.Albert and B.Loewer, 1988, Interpreting the many-worlds interpretation, Synthese, 77, 195-213
4. M.Lockwood, Mind, Brain and the Quantum (Blackwell, Oxford, 1989)
5. E.J.Squires, Conscious Mind in the Physical World (IOP, Bristol, 1990)
6. E.J.Squires, 1991, One mind or many?, Synthese, 89, 283-286
7. E.J.Squires, 1993, Quantum theory and the relation between conscious mind and the physical world,
Synthese, 97, 109-123
8. R.M.J.Cotterill, 1995, On the unity of conscious experience, J. Consc. Studies, 2, 290-311
9. D.Albert, Quantum Mechanics and Experience (Harvard University Press, Cambridge, 1992)
10. M.Lockwood, 1996, Many-minds interpretations of quantum mechanics, Oxford preprint, to be published
in the British Journal for the Philosophy of Science
11. D.Hodgson, The Mind Matters
12. N.Mavromatos and D.V.Nanopolous, 1995, Non-critical string theory formulation of microtubule dynamics and quantum aspects of brain function, CERN preprint TH/95-127
13. R. Penrose, The Emperor’s New Mind (Oxford, 1989)
14. D.Page, 1995, Sensible quantum mechanics: are only perceptions probabilistic?, Alberta preprint
15. H.P.Stapp, Mind, Matter and Quantum Mechanics (Springer-Verlag, Berlin, 1993)
16. H.P.Stapp, 1996, Chance, choice, and consciousness; a causal quantum theory of the mind/brain, Berkeley preprint, LBL-37944MOD, invited talk at this conference.
17. H.P.Stapp, 1996, The hard problem: a quantum approach, Berkeley preprint, LBL-37163MOD, to be
published in Journal of Consciousness Studies
18. P.Pearle and E.J.Squires, 1994, Bound state excitation, nucleon decay experiments, and models of wavefunction collapse, Phys. Rev. Letters, 73, 1-5
19. G.C.Ghirardi, P.Pearle and A.Rimini, 1990, Markov processes in Hilbert space and continuous spontaneous localisation, Phys. Rev., A42, 78-89
FIGURE CAPTIONS
Fig. 1. A hypothetical neural pattern which Melinda interprets as the result +.
Fig. 2. A hypothetical neural pattern which Melinda interprets as −.
Fig. 3. A possible “sum” of neural patterns corresponding to the superposed state. But Melinda’s experience
corresponds either to the pattern in fig. 1 or to that in fig. 2.
Fig. 4. A template that produces a pink man from a sheet of pink paper. Is the man already present without
the template?
4
Some people would regard this as a virtue of these models, but they would be unlikely to attend this
conference.
6 |
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
626
Article
Entheogens, the Conscious Brain and Existential Reality: Part 3
Chris King*
ABSTRACT
The purpose of this article is to provide a ‘state of the art’ research overview of what is
currently known about how entheogens, including the classic psychedelics, affect the brain
and transform conscious experience through their altered serotonin receptor dynamics, and to
explore their implications for understanding the conscious brain and its relationship to
existential reality, and their potential utility in our cultural maturation and understanding of
the place of sentient life in the universe.
Part 3 contains the following sections: 8.Entactogens; 9.Doors of Delirium: Scopolamine and
Muscarinic Acetyl-choline Antagonists; 10. Safety Considerations of Psychedelic Use; and
11. An Across-the-Spectrum Case Study.
Key Words: entheogens, conscious brain, existential reality, psychedelics, serotonin,
conscious experience, sentient life, universe.
8. Ecstasy and the Entactogens
The entactogens have been included within the entheogen orbit because their emotional
effects have made them the key to modern forms of ritual psychotropic agent use, associated
with positive celebration of interconnectedness. Ecstasy, or MDMA, is the clear favourite
among a series of mood enhancing molecules that work as serotonin releasing agents,
promoting empathy and human bonding as well as acting as stimulants and sensory
enhancers, leading to world-wide popularity. Its metabolite MDA has also been used as an
entactogen psychedelic and some phenylethylamine psychedelics such as 2C-B are also
regarded as entactogens. However attempts to make non-toxic variants such as MDAI
(Nichols et al 1990) are less regarded for the quality of their effect and have been banned
despite their lack of toxic effects. My own experience of MDMA is included in the case
study.
The story of Ecstasy’s action and the possible routes of any long-term damage are as
complicated and challenging as the mechanisms of psychedelic entheogens. As already noted
in fig 5, initial reports of serious neurotoxicity and blanket depletion of serotonin system
function (McCann et al), disruption of serotonin axonal pathways (Hatzidimitriou et al), and
dopamine damage, even on a single dose (Ricaurte et al), have proven to be bad science, with
a key research paper retracted (Holden). Initial reports of Ecstasy causing Parkonsinism
through dopamine damage also appear to be unfounded (Jerome et al) with later reports
suggesting MDMA is protective against existing Parkinsons symptoms (Concar). Ecstasy has
also been found to be of potential long-term benefit in therapy for trauma (Buchen). However
more careful subsequent research still shows a degree of potential long-term change that is
cause for concern.
* Correspondence: Chris King http://www.dhushara.com E-Mail: chris@sexualparadox.org
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
627
MDMA acts as a “releasing agent” of serotonin, norepinephrine, and dopamine (Partilla et al,
Verrico et al). It enters neurons via the monoamine transporters. Once inside, MDMA
inhibits the vesicular monoamine transporter, which supplies dopamine in vesicles as a
function of pre-synaptic neuron excitation. This results in increased concentrations of
serotonin, norepinephrine, and dopamine in the cytoplasm and enhances their release by
reversing their respective transporters through phosphorylation. The releasing agent blocks
the presynaptic cell's ability to use the vesicular transporter to package neurotransmitters into
vesicles. The result is increased neurotransmitter release that is not dependent on the phasic
activity of the presynaptic cell. MDMA has been identified as a potent agonist of TAAR1,
trace amine-associated receptor 1, a G protein-coupled receptor located on the presynaptic
membrane. Activation of TAAR1 inhibits transporter function via cAMP. These effects
increase monoamine efflux and prolong the amount of time monoamines remain in the
synapse.
MDMA also acts as a weak 5-HT1 and 5-HT2 receptor agonist, and its more efficacious
metabolite MDA (7% of MDMA becomes MDA) likely augments this action. Its unusual
entactogenic effects may be partly due to oxytocin secretion (Young), which facilitates
bonding and the establishment of trust via agonizing the serotonin 5-HT1A receptor. A
placebo-controlled study in 15 human volunteers found that 100 mg MDMA increased blood
levels of oxytocin, and the amount of oxytocin increase was correlated with the subjective
prosocial effects of MDMA (Dumont et al 2009). MDMA may also act by increasing
ventromedial prefrontal activity and decreasing amygdala activity, which may improve
emotional regulation and decrease avoidance, and by increasing norepinephrine release and
circulating cortisol levels, which may facilitate emotional engagement (Johansen & Krebs).
Because it acts on transporters, MDMA causes a reduction in the concentration of serotonin
transporters (SERTs) in the brain. Animal studies have demonstrated lasting serotonergic
changes, but other studies suggest the process is reversible. Immediate depletion of serotonin
in the days following Ecstasy use can be significantly alleviated by consumption of 5hydroxy-tryptophan an immediate serotonin precursor. In an animal study an MDMA dose
reducing serotonin levels below 35-50% were improved to 66-85% on 5-HTP
supplementation (Wang et al).
Some human studies show MDMA may be neurotoxic (Reneman), however others suggest
that any potential brain damage may be at least partially reversible following prolonged
abstinence (Baggott, & Mendelson). The relevance to humans of animal studies on rodents
documenting neurotoxic damage caused by MDMA is unclear, as different species
metabolize drugs differently and at different rates (Baumann, de la Torre & Farre). The
causes of neurotoxicity also remain unclear. Several studies have indicated a possible
mechanism, through the reaction of α-methyldopamine, a principal metabolite, and
glutathione, the major antioxidant in the human body. One possible product of this reaction,
2,5-bis-(glutathion-S-yl)-α-methyldopamine, has been demonstrated to produce the same
toxic effects observed in MDMA (Miller et al), while MDMA, and alpha-methyldopamine
have been shown to be non-neurotoxic (McCann & Ricaurte). Various metabolites of MDMA
may interfere with the mitochondrial electron transport system, leading to increased leakage
of reactive oxygen species (ROS) from the mitochondria. ROS and catalytic cycles of P450mediated MDMA metabolism may oxidatively modify cellular macromolecules such as
lipids, DNA, and proteins (Song et al).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
628
Many of the reported deficits associated with MDMA may actually result from concurrent
use of other party drugs, including stimulants such as amphetamines (Kish et al).
Methamphetamine is a potent dopamine releasing agent with lesser effects on norepinephrine
and serotonin, which is a known neurotoxin, shown to cause dopaminergic degeneration.
When dopamine breaks down, it produces reactive oxygen species. It is likely that the
approximate twelvefold increase in dopamine levels and subsequent oxidative stress that
occurs after taking methamphetamine mediates its neurotoxicity. Dopamine oxidation,
particularly close to synaptic vesicles, produce oxidative stress that in turn leads to
exacerbation of autophagy that can destroy axons and dendrites (Larsen et al).
Toxicity and entactogenic effects of MDMA may depend to some extent on the two chiral
versions of the molecule. (S)-MDE produced elevated mood, impairments in conceptually
driven cognition and marked right frontal activation. In contrast, (R)-MDE produced
increased depression, enhanced visual feature processing, and activation of visual cortical and
left frontal areas. Plasma concentrations were higher for the (R)-enantiomer. The so-called
entactogenic effects of MDE are likely to be caused by the (S)-enantiomer, whereas (R)MDE appears to be responsible for neurotoxic effects (Spitzer et al). It is possible antioxidants might help alleviate this. The effects may also vary significantly between the sexes
(Allott & Redman). Two studies have also found changes in hormone expression (Gerraa et
al), and emotional facial recognition (Hoshi et al 2004), with ACTH and cortisol levels
higher but more blunted under stress in Ecstasy users, and heightened ability to recognize
fearful facial expressions on day 0 but reduced capacity on day 4, suggesting lowered
serotonin.
Depression (Falck et al., Verheyden S. et al) and deficits in memory have been shown to
occur more frequently in long-term MDMA users (Ainsworth, Lawton). The most
pronounced effects are on associative and prospective memory. Focused attention, the ability
to zoom in quickly on a new task is affected, though sustained attention is not. The difficulty
with these studies is removing confounding factors. Ecstasy use varies from occasional single
tablets to bingeing on up to ten at a time (Parrot 2005), and Ecstasy users are also frequently
multiple drug pill users, often taking stimulants such as amphetamines as well, which are
known to cause significant detriments. Furthermore it remains uncertain exactly what is
actually in underground tablets, which often contain other ingredients, and not Ecstasy at all.
Consistent with these confounding variables, a study of neurocognitive function (Hoshi et al
2007) found recreational drug use in general, rather than Ecstasy use per se, can lead to subtle
cognitive impairments and that recent drug use appears to impact most strongly on cognitive
performance.
Some studies claim a consistent decrement in performance with increasing Ecstasy use. One
review (Zakzanis et al) found small-to-medium effects across all cognitive domains with
learning and memory being most impaired and that total lifetime ingestion of MDMA
appeared to be negatively associated with performance on tasks ranging from attention and
concentration to learning and memory. In another ‘meta-analysis’ (Varbaten et al) ecstasy
users had lower verbal short and long term memory scores, reacted more slowly and made
more errors. However the meta-regression coefficients were not significant, indicating no
support for a linear relationship between the mean effect size values and total lifetime
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
629
Ecstasy exposure, raising questions over whether it was Ecstasy use or confounds causing the
effect.
Fig 19: (Top) Entactogens (a) The role of the transporter in the synapse, (b,c) 2D and 3D
structures of the serotonin transporter SERT (d) Levels of serotonin at Ecstasy dose and 3
weeks after for low and high doses (Chang et al) (e) Comparable enhancement of activation
in various brain areas under several psychotropic agents suggests MDMA causes
hyperexcitation (Jager et al) (f) A study comparing MDMA users against controls for
differences in brain function (Daumann et al). (g) Decrements in serotonin transporter density
with MDMA use above with and below without methamphetamine use (Kish et al).
In two other studies (Montgomery et al, Wareing et al) Ecstasy users performed worse than
nonusers, in the former on all, and in the latter on some cognitive measures. However in
another study (Fisk et al), Ecstasy users were unimpaired on all measures of random
generation performance although Ecstasy users scored significantly lower on one test, the
computation span measure.
A low dose study, (Schlilt 2007, 2008) found initial Esctasy use (mean 3.2 tablets) had a
significant dose-related negative effect on verbal delayed recall after adjusting for the use of
other drugs, suggesting that even a first low cumulative dose of Ecstasy can be associated
with decline in verbal memory, although the performance of the group of Ecstasy users is still
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
630
within the normal range and the immediate clinical relevance of the observed deficits is
limited.
In a study of prospective memory, remembering to do things on a delayed schedule (Rendell
et al), Ecstasy users were significantly impaired irrespective of the task demands, after
controlling for marijuana use, level of psychopathology, and sleep quality, but not apparently
for other drugs such as methamphetamine. Parrott (2006) has suggested that cannabis might
offset some of the acute and toxic effects of MDMA. A second study of prospective memory
(Rodgers et al) gave conflicting results. An association was found between the lifetime use of
ecstasy and self-reported difficulties in long-term prospective memory for some ecstasy
users. However participants accessing the research via an ecstasy-related bulletin board
showed no association between long-term prospective memory and use of ecstasy, and any
association was markedly reduced when nicotine and cannabis were included as covariates.
The researchers suggest nicotine may have been a confounding factor.
In a series of brain scan studies designed to complement direct tests of competency, two
studies (Bauernfeind et al, Jager et al) found evidence of increased cortical excitability in
Ecstasy users completing a cognitive task. The latter found use of Ecstasy had no effect on
working memory and attention, but drug use was associated with reduced associative
memory performance. Multiple regression analysis showed that associative memory
performance was affected by amphetamine much more than by Ecstasy.
An fMRI investigation of motor function (Salomon et al) suggested prior MDMA use was
associated with BOLD deficits in coherence and connectivity, among motor pathways, but
one would imagine any significant effects being noticeable to the subjects and reported in the
medical literature.
Fig 20: Changes in FA, rrCBV and ADC (de Win et al 2008) at baseline (BL) and follow up
(FU). These changes are very moderate, but so is the consumption (de Win et al 2008).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
631
A pair of studies (de Win et al 2007, 2008) explored specific changes in rrCBV - relative
regional blood volume; FA - fractional anisotropy of the diffusional motion of water
molecules in the brain, which gives an indication of axonal integrity; and ADC - apparent
diffusion coefficient. In the first study comparing first Ecstasy users after 2 weeks with nonusers, a variety of metabolic tests were normal and after correction for multiple comparisons,
only the rrCBV decrease in the dorsolateral frontal cortex remained significant. In the second
study, which also compared novel low-dose ecstasy users (mean 6.0, median 2.0 tablets) to
non-users, showed decreased rrCBV in the mid brain globus pallidus and putamen; decreased
FA in thalamus and fronto-parietal white matter; increased FA in the globus pallidus and
increased ADC in the thalamus. No changes in serotonin transporter densities and brain
metabolites were observed. These changes, although subtle, do suggest sustained effects of
ecstasy on brain microvasculature, white matter maturation, and conceivably, axonal damage
due to low dosages of ecstasy.
However other brain studies show only marginal differences and/or signs of long term
recovery to norms. In a study examining blood distribution volume ratio (Buchert et al), this
was significantly reduced in the mesencephalon and the thalamus in Ecstasy users. However
in former Ecstasy users it was very close to drug-naive control subjects in all brain regions,
suggesting recovery. In another study examining cerebal blood flow (Chang et al) abstinent
MDMA users showed no significantly different global or regional CBF compared to the
control subjects. However, within 3 weeks after MDMA administration, regional CBF
remained decreased in several areas compared to baseline and was markedly more
pronounced in subjects who received the higher dosage of MDMA. Likewise a study of
Ecstasy users (50+ tablets) two weeks after abstinence showed reduced SERT binding in the
occipital cortex (Schouw et al).
In a study in which subjects were given a working memory performance task and given fMRI
sacns (Daumann et al), there were no significant group differences in working memory
performance and no differences in cortical activation patterns for a conservative level of
significance, however, for a more liberal criterion, both user groups showed stronger
activations than controls in right parietal cortex, and, heavy users had a weaker blood
oxygenation level-dependent (BOLD) response than moderate users and controls in frontal
and temporal areas. The effects were thus relatively minor but suggestive.
In studies in which more rigorous attempts have been made to remove confounding factors,
the deficits in cognitive function reported for MDMA tend to disappear.
One study (Bedi & Redman) assessed 45 currently abstinent Ecstasy polydrug users, 48
cannabis polydrug users and 40 legal drug users. Standardized neuropsychological tests were
used to measure attention, verbal, visual and working memory and executive function.
Prospective memory function was also assessed. It was not possible to discriminate between
groups on the basis of the cognitive functions assessed. Although the results suggest that
heavy use of Ecstasy is associated with some lowering of higher-level cognitive functions,
they do not indicate a clinical picture of substantial cognitive dysfunction.
A second study (Halpern et al) designed to minimize limitations found in many prior
investigations, in particular minimal exposure to other drugs, failed to demonstrate marked
residual cognitive effects in Ecstasy users. The authors comment: “This finding contrasts
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
632
with many previous findings - including our own - and emphasizes the need for continued
caution in interpreting field studies of cognitive function in illicit Ecstasy users.”
Halpern is sharply critical of the quality of the research that has linked ecstasy to brain
damage: “Too many studies have been carried out on small populations, while overarching
conclusions have been drawn from them,” he said. For a start, some previous research has
studied users who were taken from a culture dominated by all-night dancing, which thus
exposed these individuals to sleep and fluid deprivation - factors that are themselves known
to produce long-lasting cognitive effects. Non-users were not selected from those from a
similar background, which therefore skewed results. In addition, past studies have not taken
sufficient account of the fact that ecstasy users take other drugs or alcohol that could affect
cognition or that they may have suffered intellectual impairment before they started taking
ecstasy. In Halpern's study only ecstasy users who took no other drugs and who had suffered
no previous impairment were selected (McKie).
9. Doors of Delirium: Scopolamine and Muscarinic Acetyl-choline Antagonists
Muscarinic acetyl-choline antagonist deliriants have been used for centuries, both as
hallucinogenic agents in medieval Europe, Asia and Native American cultures, and in rites of
passage of manhood to forget childhood, as well as for criminal and military purposes.
Although they have been sporadically used recreationally, their severe effects of anterograde
and temporary global amnesia combined with delirious and often manic behaviour and
panoramic hallucinations which the subject confuses with reality, talking to non-existent
people and engaging with imaginary spectacles, often also accompanied with
unconsciousness and coma, leave these agents off the spectrum of legitimate entheogens,
except for the continuing evidence of their cultural use.
Scopolamine, despite its severe hallucinogenic and amnesiac properties, is used in minute
quantities for motions sickness, for treatment of addiction and as an anti-depressant (Furey &
Drevits). Hyoscyamine is the active chiral component of atropine an essential WHO core
medicine. The belladonna genus Atropa is named after one of the three Greek fates, who
chose how a person was to die. It has been used historically as an anaesthetic, to dilate the
pupils to make women more attractive (bella donna) and to commit murder, as evidenced by
the actions of the wives of Augustus and Claudius. Four second-hand accounts of its acutely
disabling and dangerous affects are included in the case study.
Early in the 20th century physicians began to employ scopolamine, along with morphine and
chloroform, to induce a state of "twilight sleep" during childbirth. Yet physicians noted that
women in twilight sleep answered questions accurately and often volunteered exceedingly
candid remarks. In 1922 Robert House, a Dallas obstetrician, arranged to interview under
scopolamine two prisoners in the Dallas county jail whose guilt seemed clearly confirmed.
Under the drug, both men denied the charges on which they were held; and both, upon trial,
were found not guilty. Enthusiastic at this success, House concluded that a patient under the
influence of scopolamine "cannot create a lie ... and there is no power to think or reason." His
experiment and this conclusion attracted wide attention, and the idea of a "truth" drug was
thus launched upon the public consciousness, although barbiturates later came to be more of a
drug of choice in interrogation (Bimmerle). Nevertheless scopolamine like drugs, including
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
633
3-quinuclidinyl benzilate and n-ethyl-3-piperidyl benzilate continued to be developed as
incapacitating chemical warfare agents.
Fig 21: (Top row) four hallucinogenic deliriants. Scopolamine and hyoscyamine are present
in Datura, and Brugmansia species and related solonaceous plants such as belladonna (deadly
nightshade), henbame and mandrake. 3-Quinuclidinyl benzilate is a chemical warfare
incapacitating agent also called BZ. Diphenhydramine (benadryl) is an anti-histamine which
also has muscarinic acetyl-choline antagonist activity. (a,b) Reduction of cortical and
hippocampal activation under scopolamine novel face-name pairs vs. fixation, for diazepam
and scopolamine (Sperling et al). (c) Right and left hippocampal inactivation under
scopolamine under active maintenance analysis (d) match and non-match memory tasks also
showing hippocampal inactivation (Schon et al)). (e,f) Hippocampal inactivations and striatal
activations under scopolamine in a spatial memory task (Antonova et al). (g,h) Inactivations
and activations under scopolamine during a memory task matching 2 images back (Voss et
al). All of these studies used a moderate 0.4 mg dose of scopolamine by injection.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
634
Following World War II, the United States military investigated a wide range of possible
nonlethal, psychobehavioral chemical incapacitating agents to include psychedelic indoles
such as LSD-25, marijuana derivatives, certain tranquilizers like ketamine or fentanyl, as well
as several glycolate anticholinergics. Copious amounts of phencyclidine are also documented
as having been tested on active military personnel such as in the Edgewood Arsenal
experiments. One of the anticholinergic compounds, 3-quinuclidinyl benzilate, was assigned
the NATO code BZ and was weaponized at the beginning of the 1960s for possible battlefield
use. BZ was invented by Hoffman-LaRoche in 1951. In 1959 the United States Army began
to show interest in using the chemical as a chemical warfare agent. The agent commonly
became known as "Buzz" because of this abbreviation and the effects it had on the mental
state of its casualties. In February 1998, the British Ministry of Defence accused Iraq of
having stockpiled large amounts of a glycolate anticholinergic incapacitating agent known as
Agent 15, chemically either identical to BZ or closely related to it.
Scopolamine has also been used criminally as a poison or spray that can incapacitate a
person, or cause them to become obedient to a criminal's intent. In Colombia the criminal
administration of Datura or Brugmansia extracts, known as Burundanga, appeared during the
1950s. In the early 1980s, pure scopolamine began to be used. In a Colombian city of
500,000 people around 100 cases were reported in 1980-81. In one instance, a young
professional woman was approached by a man, who possibly sprayed her face, resulting in
her becoming docile, going to work inebriated and withdrawing her salary, her money from
ATMs and her jewelry from her apartment and giving it to her assailant before lapsing into
amnesiac somnolence. In hospital, scopolamine and fenotiazine were found in her urine
(Ardila & Moreno).
Learning and memory (Deutsch) as well as attention and processing speed are critically
modulated by the cholinergic neurotransmitter acetylcholine. Dale in 1914 showed that
acetycholine acts at two pharmacologically different receptors, nicotinic, which form ligandgated ion channels and muscarinic, which are G protein coupled. Muscarinic receptors
represent the majority of cholinergic brain receptors. The neocortex has a mixed muscarinic
population with 67% M1 receptors, with high affinity for pirenzepine and 33% M2
muscarinic receptors. Hyoscyamine (atropine) and probably scopolamine are M1 antagonists.
Increase in the number of muscarinic receptors in the hippocampus of rats has been observed
as a consequence of long-term scopolamine administration (Ardila & Moreno). The
cholinergic system constitutes one of the most important transmission systems for mediating
cognitive processes in humans, with cholinergic projections originating in the nucleus basalis
of Meynert and the substantia innominata in the basal forebrain, which has wide projections
across the neocortex. By projecting to the hippocampus and to frontal areas, they mediate
fundamental cognitive processes (Voss et al).
Studies utilizing scopolamine to examine the effects on cognition have consistently shown
that it impairs cognitive functions like learning, memory, verbal fluency and attention.
Alzheimer’s and schizophrenia patients present cognitive deficits while at the same time
exhibiting specific alterations of the cholinergic system as evidenced by post-mortem studies.
Early studies in India on monkeys smoking cannabis and datura suggested that datura
alkaloids cause brain shrinkage while cannabis does not. Virtually all the brain scan research
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
635
cited focuses on using scopolamine as an experimental drug in learning about memory
impairment, emphasizing its major impact on memory.
Fig 22: Relative safety of a spectrum of psychoactive drugs (left) in terms of dependence
versus active/lethal dose (Wikipedia) and (right) in terms of several measures of relative
harm (Nutt et al). In both perspectives psychedelics rate as very safe and having harm
potential decisively below legal drugs alcohol and tobacco. (Top right) Putative effects of
alcoholism on an MRI scan, showing enlarged ventricles and a shrunken brain.
10. Safety Considerations of Psychedelic Use
The potential long-term health effects and risks of NMDA antagonists, cannabinoids and
entactogens have already been extensively discussed. We now turn back to the classic
psychedelics. By all measures, as noted in fig 22, psychedelics, even the unpredictable genie
in the bottle LSD, do not have evidence of long-term physical damage and rank far below
legal alcohol and tobacco as socially or physically damaging agents. This cannot be said for
street drugs, even some of those purchased over the internet, or for the more savage members
such as the fly series, which have toxic or lethal effects not far above the active dose. A
Danish man whose friend died on bromodragonfly had this to say of it: “It was like being
dragged to hell and back again. Many times. It is the most evil [thing] I've ever tried. It lasted
an eternity”.
I will here focus on the natural psychedelics and in particular psilocybin of sacred
mushrooms, but many of the same considerations apply to mescaline bearing cacti and
ayahuasca. Although sacred mushrooms were pejoratively claimed to cause premature
senility in apocryphal earlier accounts, there is no evidence psilocybin, sacred mushrooms,
mescalin cacti, or ayahuasca cause long-term physical harm. Both my peyote roadman Tellus
Goodmoring and Maria Sabina the mushroom curandero lived well into their nineties and
Senor Trinico the brujo I first took ayahuasca with remained in good heath when I visited
him 20 years after my first experience, despite being in remission from leprosy.
The physical side effects resulting from psilocybin consumption are generally not considered
significant. Nausea and vomiting can occur, particularly with wild mushrooms, which can
contain bacteria, or be partly spoiled. High and or low blood pressure changes can sometimes
result in fainting. Other adverse effects less frequently reported include panic attacks,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
636
paranoia, confusion, derealization, disconnection from reality, and mania. Neither flashbacks,
nor hallucinogen persisting perception disorder, are commonly associated with psilocybin
usage (Carhart-Harris & Nutt) as they have been with LSD (Abraham & Duffy).
Unsurprisingly, usage by those with schizophrenia can induce acute psychotic states. A 2010
study on the short- and long-term subjective effects of psilocybin administration in clinical
settings concluded that despite a small risk of acute reactions such as dysphoria, anxiety, or
panic, “the administration of moderate doses of psilocybin to healthy, high-functioning and
well-prepared subjects in the context of a carefully monitored research environment is
associated with an acceptable level of risk” (Studerus et al). All of these show that use of
hallucinogens should be undertaken only in a protective environment where there are people
able to look after individuals and protect them from immediate harm.
In addition to the beneficial effects of mystical-type experiences (Griffiths et al) already
reported, a pilot study (Vollenweider & Geyer) found that the use of psilocybin was
associated with substantial reductions in OCD symptoms, possibly caused by psilocybin's
ability to reduce the levels of the serotonin-2a receptor. In a second study (Sewell et al), half
of patients with cluster headache, often considered not only the most painful type of headache
but "one of the worst pain syndromes known to mankind," reported that psilocybin aborted
the attacks, and most reported extended remission periods. Preliminary results indicate that
low doses of psilocybin can improve the mood and reduce the anxiety of patients with
advanced cancer, and that the effects last from two weeks to six months (Vollenweider &
Geyer).
There are thus no scientific grounds to continue to ban the use of entheogens, particularly
those of a natural origin, nor to incarcerate people for long periods for consuming or
possessing them. Safe and comfortable protected social contexts for use with sane guidance
need to be developed. Sacred mushrooms, peyote and ayahuasca are intrinsically safer than
either street drug phenylethylamines (which can have lethal consequences, when the drug is
impure, or the dosages are confused), or LSD (which had some very unpredictable
consequences among our friends in the 1970s, including a bout of amnesia lasting several
days, a psychotic episode lasting a month, and an acute manic break requiring physical
restraint followed by coma perceived later as a rebirth experience).
11. An Across-the-Spectrum Case Study
To round off this investigation, I am going to include a case study in the first person. No
matter how much investigation goes into understanding the properties of entheogens, they
remain sine qua non agents of transformation of subjective consciousness, which need to be
understood in the subjective. Short of readers experiencing these agents for themselves, the
closest we can come to an understanding is through first-hand subjective reports. First person
accounts, although they are once-removed, can give a far deeper description of the changes
induced by these substances than brain scans, or EEGs can. So in the interests of a more
enlightened approach to entheogens, in parallel with writing this paper, and as the original
inspiration to write it, I have made a spectral investigation, sampling the conscious states key
members of these agents invoked in my own consciousness.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
637
I will thus discuss the subjective effects of the classic psychedelic psilocybin (sacred
mushrooms), the entactogen MDMA (Ecstasy), a selective 5HT2a agonist n-benzylphenylethylamine psychedelic (25C-NBOMe), the dissociative anaesthetic ketamine, and
salvinorin-A in terms of their capacity to induce a full-blown entheogenic experiences. Each
experience is written as an account to my sister who hasn’t tried any of these agents to
explain some features of the experience that struck me in the evening afterwards. There is
one dreaming account during the time of these case studies to examine provocative
anticipatory features of dreaming consciousness. To gain an idea of the severe effects of
muscarinic acetyl-choline antagonists such as scopolamine, which I have never been prepared
to try, I have included three medieval accounts and a current one.
Sacred Mushrooms and Psilocybin
A couple of days ago, for the first time in a year and a half, because, like most people, I am
habitually fearful of my mind being torn apart by visionary transcendence, I persuaded
myself to imbibe a powerful whack of the very best crisp dried sacred mushrooms, as a
devotional meditation, lest the passage of the years carry me unrequited at the age of 67 ever
closer to the edge of dissolution, before I have fulfilled my covenant with destiny. As the
great wave of reverie broke over me, they gave me an overflowing and integrated vision of
how cosmic consciousness comes about in the universe, in one of the cleanest, and yet
strongest, spiritual experiences I have had, totally restoring my sense of psychic vitality and
meaning, as they have done countless times in younger days, as the sheet-sail for my tortuous
journey through life.
As noted, I have also taken mescalin in the form of San Pedro and peyote in a traditional
peyote meeting at Taos Pueblo with the roadman Tellus ‘Goodmorning’ and on the peyote
fields of el Catorce Real in Mexico, sacred mushrooms at Palenque, and DMT and harmine in
the form of ayahuasca with Senor Trinico at Yarinacocha, Pucallpa in Amazonian Peru (see
fig 3), as well as pure LSD in the days of orange sunshine, so have a reasonably
comprehensive familiarity with psychedelic entheogens.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
638
Real religious sacraments have to be able to be powerful enough agents to be able to
transport us into the mysterium tremendum. They also require meditative vigil to enter deeply
into the experience. I try to retreat into reflective solitude, without thought processes, or
internal dialogue, lying watchfully, with eyes sometimes open and sometimes closed, and
often half-open and half-closed, as the Buddha is depicted as doing, tuning consciousness
with my breathing into a resonant state of attention, sensitive to the ensuing visionary
miasma. I begin lying quietly and over about twenty minutes I can begin to feel the effects
coming on. Often I feel anxious and restless before the peak, something I am coming to
associate with the possible effect of the 2c receptor, and I note Griffith’s statement that a key
to gaining a positive experience for his study participants, depends on getting just the right
dose. This time I have measured just 1.3 grams of very crisp dried psilocybe shoots, and this
proved to be an ideal dose in the company of a mild measure of cannabinoids. The first real
effects if I am lying quietly are a combined synesthesic rush of pattern and sound that often
rises almost to a shrieking peak as the first wave strikes. If I let go of my surroundings I can
fall into or flow into these resonant patterns, so they become visions and experiential spaces
utterly different from the waking world, as if I am not only witnessing my brain generating
consciousness but the nature of disembodied consciousness in the bardo.
I won't go into all the incidental details of the retinal circus, the complex dynamically
interlacing 3-D fibers and fractals, their rushing vortices and echoing currents, of entering
many interconnected layers of dreaming and waking reality, or even a vision of being
transported to join God in heaven, with Saint Peter ushering me in on a comic stage vibrating
like a New Orleans carnival. The key is the overwhelming power, truth, beauty and integrity
of the experience, convincing me in its full intuitive detail, yet again, that the living
sacraments contain the genuine royal blood, or sang raal, route to religious knowing,
beneficial to all life. This is a state that seems to emerge out of the entheogenic experience as
a fully integrated knowledge, or gnosis. It is not something you can put together
philosophically or explain in terms of its details and it can’t be taken back in its entirety to
the everyday world, except as an enchanted memory and a source of life-enhancing wisdom.
By entering into the entheogenic state of reverie without thought in a meditative calm, one
enters a state where there is a resonance with the patterns and sounds, which one can fall into,
and once one does, it is as if one has entered another reality, as different from waking life as
dreaming is, with its own existential implications, one of which is gnosis about the flow of
life, the meaning of life, and the sense of one’s ego dissolution, in becoming one with the
conscious process that drives all sentient life in the universe. It is a state of being amid the
patterns in the stillness of the conscious void that is evidentially true, palpable, felt at once in
one’s emotions and in the stillness of one’s mind. By the same connection I inherit a personal
responsibility to unfold this experience for others, for the sake of life and the planetary future.
Of course one can take sacred mushrooms recreationally and have an adventurous
experience, but for me it is like returning home to a place where I become my true self, and
navigate my life with some grace and insight, as one takes an intercontinental sailing journey
across the Styx between birth and our eventual demise.
Ecstasy or MDMA
Today I finally tried the fabled Ecstasy because I had to eventually discover what it was all
about, 20 years after I first came upon it. The mushrooms last week were so beneficent and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
639
yet powerful that I felt it was finally time to conquer and understand the E experience as part
of figuring out the different actions of serotonin entheogens and entactogens.
And it was a lovely experience too and highly intriguing although its not a transcendental
molecule, but rather a sensual and sensitive molecule, to be more precise an entactogen - that
is it makes the ones you love seem even more tactile, cuddly and nice to be with, bonded and
trusting, through the oxytocin it facilitates, at the same time as an exhilarated feeling of visual
brightness and alertness. As the effects came fully on, the strength was almost too much. My
eyeballs seemed to be shaking and I literally felt awash with serotonin as if I was standing in
a shower. The garden seemed to be bulging out at me with an odd brightness that I could tell
could be awesome in a dance hall setting. I found myself clenching my teeth tightly almost to
the point of forcing them into my gums, but the sensation felt good and right - a form of keen
concentration.
This was definitely a strong ‘high’ but clear of the mental confusion that can happen with full
blown psychedelics, so one can carry on a conversation and engage a social process with
heightened empathy and compassionate appreciation of others. Rather than stare at the ceiling
and become lost in a psychedelic trance, I wanted to sit closer to my bemused partner, who
seemed to have become feathery, as if both she and I had tingles running down our spines
and over our skin. Its not that I had fallen madly in love but just had the insane sensual urge
to crawl into bed and hug one another. And I felt very positively disposed, warm, relaxed and
positive, in a mood with a lot of reserve and no paranoia, able to engage and enjoy social
situations. And I felt exhilarated, energized and insanely clear, struck by the fact that this
agent has a very good social affect, which can really bring people out of themselves so they
bond as friends, or lovers in a vastly superior way to alcohol, which is why people at rave
parties loved it until it got hunted down. I have to ask myself “Why was this banned?” “Why
was no real assessment made of its capacity to induce far better social climates of tolerance
and empathy than alcohol?”
I do have a concern about the risks of neurotoxicity, even if they are less than earlier studies
reported, just because this drug is dumping heaps of serotonin and reversing the transporters
as well, which is a fairly massive intervention. To avoid the Tuesday blues I take 5-hydroxytryptophan supplements over the ensuing 24 hours and have no ill after effects, except for
being a little closer to tearfulness, but no worse than a night on psychedelics with too little
sleep.
25C-NBOMe a Selective 5HT2a Psychedelic
Today I experimented with a super-potent psychedelic developed to significantly activate
only the one kind of brain receptor 5HT2a believed to be involved in the entheogenic state
and no others that can cause anxiety, or dreaminess, or shatter the thought process. The active
dose to smoke is 150-300 micrograms, an amount as small as a grain of salt you can barely
see, let alone measure, but the effects can be overwhelming. I took two very small inhalations
of the smoke and could probably have 50% more, but needed to measure the effect carefully.
And yes it was fully entheogenic - both very powerful and ever so delicate! It begins with a
pronounced serotogenic ‘high’ almost immediately but the full effects take a few minutes to
settle in. Initially it seems to effect higher visual areas without as pronounced geometrical
features as psilocybin, but that impression is deceptive. I had also had some cannabinoids and
by the time the two were activated, I found I was falling into a rich kaleidoscopic sea of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
640
visions and entering the familiar eeriness of the entheogenic visionary trance. It has a very
nice pure feeling, not only pure as a super-potent molecule, but also pure because its action is
selective for the 2a receptor, confirming that this is the site of the entheogenic process, and
evoking an experience free of the other potentially anxious effects of 2c and the loss of
vigilance due to 1a.
Imagine looking at a still pool in the moonlight and something changes, so that, when a little
breeze blows on the pool, causing ripples in the moonlight, instead of them dying away, as
we look at them and pay curious attention, our hair stands a little on end as they respond as to
a resonance and become brighter and clearer, and begin to come ever more alive, but this isn't
just a pool 'out there' - it is one's entire conscious psyche 'in here' AND 'out there', one's
vision, audition, tactile sensation, emotional feelings, the space between us and the space in
and beyond the room, looking down deep down into the abyss, the tingles that run down one's
spine, the musical spectra of the fat sizzling in the pan, the meaning behind the meaning
behind - the whole experiential universe, be it dream, or reality, resonating uncannily as it
becomes one with the conscious void filled with unfolding patterns and memories and dreams
of memories and memories of dreams, all now resonating with the one that is all of our minds
together experiencing the universe unfolding. Then, just as the void is alive and shining and
at the same time empty in its peacefulness, as one's breathing comes to a standstill, the still
point of the turning world, the dew drops into the shining sea and we slip back into the room
around us, realizing yet again that we have made the unspeakable connection to the mystery
that lies at the foundation of all conscious life, as we move in space-time towards our
realization, and all of our destinations.
Ketamine
To take ketamine I insufflated powdered crystals from therapeutic sources. The effects are
very peculiar to say the least. About three minutes later I have become aware that my
consciousness is becoming vastly deranged. It's a feeling I can recognize because I have also
experienced pure salvinorin-A, which has a similar dissociative effects. This can be very
disconcerting, because your normal relation with your body and the world around you can
take on very strange manifestations, where you literally become part of the surroundings, not
just a fly on the wall, but you ARE the wall. You may feel you have turned inside out. It
sounds ridiculous, but its evidentially true! And everything you look at, and everything if you
close your eyes, is wildly disassociated into alien kinds of conscious structure, in wild
motion, as if your internal model of reality has come loose and is resynthesizing on different
principles
For the first few minutes, maybe five or six, I'm trying not to swallow, and spit out
occasionally, because, if it gets down the back of your throat, it can make you quite nauseous.
Then I realize my nose feels cool and I am entering a state of peace. The anesthetic effect is
taking me deep into a psychedelic reverie through pranayamic breathing. I fall deeper into the
dissociated state and I realize that coming backwards through it all is an ever so
overwhelming complete entheogenic experience similar in kind and feel to the classic
psychedelics of simply awesome depth. A depth so inscrutable, you are touched by it, swept
into silent awestruck oblivion - but still conscious - still there - still aware - somewhere in the
aether, as the void breathes its delicate structured emptiness.
At some point, my partner knocks and opens the door to make sure I am okay. All I can say
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
641
barely through the ice of immobility is that it is like the divining salvia 10,000 times over. I
continue to witness drifting in and out of the entheogenic trance and note that this is a definite
confirmation that, although the initial experience seemed more like salvinorin dissociation,
the state is also able to manifest something intimately recognizable as a deep serotonin-like
psychedlic reverie, confirming in my mind the deep association between the classic
psychedelics and dissociatives, hinted at in the 5HT2a, MGluR2 and NMDA interactions
discussed in the article. I begin to become curious what ketamine would be like taken along
with a classic psychedelic. But then I realize that it would be impossible because my hands
and feet are like clay tablets, or I have been set in quick drying cement.
I continue to recognize the depth and mystery of what I am witnessing. But then things take a
more sinister turn. My mind is becoming memory-less. It's as if all my brain and memory
circuits are reprogramming themselves and all the needles are beginning to point every which
way. I know it's going to be alright, but it sure feels as if I am going to be stark staring mad
forever. So I decide just to ride with the experience, because I will probably be able to
remember it all when things settle down at the end of an hour or so. And I'm thinking about
my hippocampus because I know what it does to your memory centers, and then suddenly its
as if the dials have connected to the master index of all my life experiences, and here they are
flashing before my eyes, just as they say about someone who is drowning, and near death
experiences, but its not just my life experiences, but the very peak experiences, like the chain
of the Himalayas.
I am suddenly looking right into the peak experience I had on the Vine of the Soul in
Amazonian Peru in 1980, and all the other times I have been outside the inside out, as if
every moment were written on a stack of cards and now they were flashing past in a flying
shuffle. I realize I am looking back down on them in the same way Moses might look down
on his life and the life of everyone from the mountain top, and that all the experiences of my
life are coming into one cosmic focus of meaning and destiny. At this point I suddenly realize
that everything I have ever done and everything I will ever do has been brought to this very
moment and this very experience, and it is 'God', and my destiny coming to its true
destination at this point, which is beyond time and space, coming from the very beginning,
and for ever. I have this overpowering feeling of having been taken so far it is the full age of
the universe and I have so far to get back to the land of the living. It is the same thing I have
read about in near-death experiences where one’s life flashes before one’s eyes and one feels
one is uniting with the universal self and could go with it or return to the incarnate world of
individuals. But at the same time it is the universal mind coming to know and understand
itself. At that point it seemed almost as if my life was now over. I had made the connection
which gave my life its central meaning and though I might in future do nothing else and
maybe I would never be able to come to this point again, my life had meaning in giving
ultimate meaning to the totality witnessing and knowing itself.
If I look out at the room I still feel deranged, although feeling a little flatter though still
depersonalized, or derealized is probably the better term. And then things come a little more
into focus, and I realize I'm coming out and suddenly I am hit with the unbearable lightness
of being, a ridiculous case of laughing gas splitting my sides, because of course nitrous oxide
is a milder anesthetic of the same basic NMDA antagonist class, and I am simply hilarious
that its all going to be okay again!
And I look at the clock and its only an hour later, and so I lie there trying to soak up the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
642
experience, completely awe struck at the inscrutable point of no return, in becoming one with
the eye of the universe coming to meet its destiny in knowing, as I am knowing and by the
enormous journey I have taken. And so I try to express to my partner what it was like, but
words still won't come and all I can do is utter complete existential overcharge in a
fulminating cry “Aaaahhh!!!” And I stagger out into the living room with feet like snow
boots, the outside world through the windows still looking like a dream, while I try to piece
together the experience and whether it is all going to be lost in the oblivion of the sleep of
forgetfulness.
How do you express these experiences? What do they all mean? Was this God? Was this a
complete delusion? What is the final answer? Would you ever have a better chance on the
edge of life and death? Or is the living brain the crucible of existence and the one chalice of
the infinite through which the universe can pass?
And what of the effects and consequences? Ketamine is a strong anaesthetic and I worry
about the cumulative effects on memory of repeated use of a drug which both has very strong
effects on neuronal excitability and manifest effects on the memory process, which is
something we have at best limited conscious control over, so it is definitely something I
wouldn’t consider taking often. The strange sensations I had about my memory during the
experience is enough to convince me of this, although afterwards I have been able to recall as
much of the experience as in any other entheogenic experience, and cannabinoids can also
disrupt short-term memory.
Salvinorin-A
When taken directly from the leaves of Salvia divinorum, salvinorin has a mildly disturbing
effect on both consciousness and memory which is different from the classic psychedelics in
that it appears to involve crumpled surfaces rather than kaleidoscopic geometries and has an
odd effect on memory as if one feels that one’s memory has always been submerged in this
condition when one knows this is not true. The two times I have taken pure salvinorin,
around 0.7-1 mg vaporized, the effects have been totally dissociative and completely
overpowering, with my body image completely unraveled. The first time I felt I was in an
enormous aircraft hangar with a gigantic wheel rolling over my body flattened and rolled out
like a sheet of paint. The second time I fell to the floor as my body turned inside out and
broke into the flagellating surfaces breaking up the space of the room around me. By the time
I have realized I can handle the experience it is already beginning to fade. Yes these
experiences are profound but they are also transient and leave little time to come to terms
with them contemplatively and they do have strong undertones of dysphoria, although
fascinating and challenging. So I don’t class them as entheogens but as hallucinogenic
dissociatives.
Dreaming
I have had many strange dreams in my life, some apparently precognitive and some
manifestly lucid. In one, I looked at my hands and found my consciousness split in three, one
self was lucid, but lost in the dream universe, desperately wondering how I could ever find
the way back to the Ixtlan of the real world, one shooting upwards ever faster as a blast of
spray hit my body, and the third bumping on the ceiling of my bedroom, reassuringly
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
643
witnessing my body asleep in the bed below. But here I relate a time-spanning dream during
this entheogenic discovery process.
I dreamed I was at a place like a school and someone had been shooting at some other people
and there were little silver bullets on the ground. Then later I realized I had to leave and
worried that I would become a target myself. As I was walking anxiously down a drive
through the site I realized there was a right turn just before the end which went down an alley
lined by an avenue of trees, so it was hard for the shooter to get a line on me. I managed to
slip anxiously away and then managed to take off on my motor cycle around the block, where
I ran into a very crowded situation trying to push the heavy bike up hill. I then found myself
on a crowded truck but at the same time thought I was in a physics lab and wondered why I
had spent so much time in the lab session and had had few or no lectures.
The episodes with the shiny bullets and the physics lab have strong echoes in two television
programs we were watching the night before, Castle about a murder in which the bullets were
crucial evidence, and The Big Bang Theory, which is about nerdy physics graduates.
However there are two features of the dream, the right turn down the alley and pushing my
bike up a hill, which appear as a lock and key to future events that happened after the dream.
The next day, I was fixing a lock on one of our French doors and suddenly remembered I had
thought of looking for a locksmith’s supplies I had visited a few years before in case the lock
was cheaper there. It was long enough ago that I had to look up the name and address on the
internet, but when I rode out around the block on my push bike the destination was down a
cull de sac on the right just before the end of a short side street and when I arrived at the
place, I found that I had to push my bike up a steep slope and couldn't ride it to get out again.
Thus two incidental components of the dream, neither of which related to my immediate past,
were combined in a form which together point to an experience I was going to have after the
dream, reflecting the double blind study in “An Experiment with Time” (Dunne). Since the
role of subjective consciousness in evolution appears to be critically to anticipate threats to
survival, in situations where computational processes become intractable and such choices
may also depend on contingencies which have yet to arise in future, further exploration of the
anticipatory capacity of waking, dreaming and entheogenic experience is an urgent priority
for our understanding of life and consciousness.
Before the alkaloid in Banisteriopsis caapi was found to be harmine, (along with related
tetrahydro-harmine and harmaline), it was initially named ‘telepathine’ because of reports
about ayahuasca’s telepathic powers, in association between harmine as MAO inhibitor and
the DMT from Psychotria viridis in the brew. Maria Sabina’s description of her mushroom
experiences also contain references to thier ‘prophetic’ propensities. Without succumbing to
the naïve claims made by some psychedelic writers, we need to keep an open mind about
exploring the space-time properties of the entheogenic experience. Because it allows the
brain to witness its own inner dynamics consciously in a way which is responsive to our
attention it is effectively the mental equivalent of a cloud or bubble chamber, a unique
facility for fundamental research we cannot afford to suppress, given the conscious mind
being both the central arena through which all our life and action passes and the deepest
enigma facing the scientific description of reality.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
644
Scopolamine and Hyoscyamine
Porta, a colleague of Galileo reported a "man would sometimes seem to be changed into a
fish, and flinging about his arms would swim on the ground, another would believe himself
turned into a goose and eat grass, beat the ground with his teeth and flap his wings". "My
teeth were clenched, and a dizzy rage took possession of me. I knew that I trembled with
horror, but also that I was permeated with a sense of well-being. My feet were growing
lighter, expanding loose and breaking from my body. Each part of my body seemed to be
going off on its own. At the same time I experienced an intoxicating sense of flying. The
frightening certainty that my end was near through the dissolution was balanced by an animal
joy in flight ... the clouds the lowering sky, herds of beasts, falling leaves quite unlike
ordinary leaves, billowing streamers of steam and rivers of molten metal."" (Rudgeley 95).
Johannes Nieder (1692) gives the following account: "having placed a large bowl on top of a
stool, she stepped into it and sat herself down. Then rubbing ointment on herself to the
accompaniment of magic incantations, she lay her head back and fell asleep. With the labour
of the devil she dreamed of Mistress Venus and other superstitions so vividly that crying out
with a shout and striking her hands about, she jarrd the bowl in which she was sitting and
falling down from the stool seriously injured herself about the head. As she lay there
awakened the priest cried out "Where are you? You are not with Diana ... you never left this
bowl!" (Harner (ed) 131).
“The James-Town Weed (which resembles the Thorny Apple of Peru, and I take to be the
plant so call'd) is supposed to be one of the greatest coolers in the world. This being an early
plant, was gather'd very young for a boil'd salad, by some of the soldiers sent thither to quell
the rebellion of Bacon (1676); and some of them ate plentifully of it, the effect of which was
a very pleasant comedy, for they turned natural fools upon it for several days: one would
blow up a feather in the air; another would dart straws at it with much fury; and another, stark
naked, was sitting up in a corner like a monkey, grinning and making mows [grimaces] at
them; a fourth would fondly kiss and paw his companions, and sneer in their faces with a
countenance more antic than any in a Dutch droll. In this frantic condition they were
confined, lest they should, in their folly, destroy themselves — though it was observed that
all their actions were full of innocence and good nature. Indeed, they were not very cleanly;
for they would have wallowed in their own excrements, if they had not been prevented. A
thousand such simple tricks they played, and after eleven days returned themselves again, not
remembering anything that had passed.” – The History and Present State of Virginia.
An overdose on butylscopolamine. “It felt so indescribably weird. It was as if nothing was
real and I began to forget who I, and everybody around me, was. I remember looking at the
ceiling and it started bubbling. I remember seeing some very real hallucinations and feeling
intensely energized and happy. I blacked out - my brother’s friends found me in the woods, I
was conscious upon their arrival but collapsed in mid-discussion, they brought me home. I
remember a little about coming home, it was a familiar place, but a new type of magical
presence was animating it. At this point I had forgotten I took the drug and I went to my
room to sit on my couch (I don’t have a couch in my room). I remember lighting up cigarette
after cigarette and having a great old time talking to random strangers at a very social and
easy going party (I don’t smoke cigarettes, and the only people who came in my room that
night were my parents and brother). They drove me down [to hospital] and apparently the
whole way there I thought we were riding some type of laser train. When I got there I got
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 626-645
King, C., Entheogens, the Conscious Brain and Existential Reality: Part 3
645
really violent with the nurses so they strapped me to the bed and the first 24 hours after being
admitted to intensive care I can’t remember at all, the next two days I remember vividly
accompanied with memories of outrageous things like talking snakes calling me names (the
serious delirium began to subside after about four days). I saw my baby sister sit up in her
cradle and shoot lasers into the air, I got into a very heated argument with a cardboard smiley
faced sun on the wall. At one point all my family was standing around me asking me who
they were and all I knew was my father’s name (but I couldn't remember that he was my
father). I didn’t remember anything at first but as time went on and my family told me stories
some of it came back” (Erowid).
[References at end of Part 4]
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
673
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
Article
Remote Mental Interactions: A Review of Theoretical
Modeling of Psychophysical Anomalies Part 1
Iona Miller*
ABSTRACT
This article presents a review of theoretical modeling of psychophysical anomalies. It originates
from my involvement with the Journal of Non-Locality and Remote Mental Interactions
(JNLRMI) which was founded by Lian Sidorov in the wake of research institutions of previous
decades, such as SRI, IONS, PEARS, and MRU. JNLRMI began as an attempt to bridge widely
scattered evidence and ideas on the frontline of mind-matter research (energetics, remote mindmind and mind-matter interactions). JNLRMI was a challenging and exhilarating journey,
sustained by multidisciplinary readership interest in the subject.
Part 1 of this article contains Introduction; Make Me Want to Psi; Open Sesame; From Trance to
Creativity; Psi Deeply; Hypnosis & SP; Dream of Telepathy and Beyond; and Cyber Psi
Training.
Key Words: psi, parapsychology, biophysics, energetics, Schumann Resonance, mind-body,
geomagnetism, ELF, ESP, precognition, hypnosis, paraphysics, remote viewing, worldview.
[P]si is always present in space and time, waiting to be accessed by crisis, emotion, or by
optimal laboratory stimulus parameters. Geomagnetic activity may affect the detection capacity
of the brain for this information, especially the neural pathways that facilitate the consolidation
and conscious access to this information. Without this geomagnetic activity, awareness of the psi
stimulus might not be as likely and the brain's "latent reserve capacities" would not be utilized. -- Krippner.
INTRODUCTION
Among other theories from the original JNLRMI, Pitkanen and Sidorov proposed that the
Schumann resonance (SR) may be the substrate for a radar-type extrasensory perception
mechanism common to all living beings. Like water bouncing off of rocks and other submerged
objects, this non-specific frequency is absorbed and re-radiated in unique interference patterns
by all objects it encounters. This interference pattern is a composite of external and internal
properties, as the constituent atoms, molecules and their global assembly all re-transmit this
energy according to their specific configurations. They suggest that the “sounding waves” can be
* Correspondence: Iona Miller, Independent Researcher http://ionamiller.weebly.com E-Mail: iona_m@yahoo.com
Note: This work was completed in 2003 and updated in 2012. Further, material authored by Dr. Lian Sidorov has been
reproduced with her permission.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
674
frequency and pattern modulated by conscious intent in order to yield specific information
(interference patterns). Decoded by the brain they return almost instantly on the “back” of the
Schumann Resonance.
Once recaptured, the patterns are then decoded by the brain. In this Fourier-type transformation
the information is translated into conscious data, much like other sensory processing.
Conversely, specific effects may be imprinted as bioinformation and made to exercise a
"mysterious action at a distance", once the signal wave reaches the target. That pattern, in turn,
may, under the right ("pre-requisite") global conditions, avoid routine dissipation and become
instead coupled to the dominating ("state-of-consciousness") standing wave that is picked up and
carried by the Schumann resonance. Mental intent may function as a variable window of
transmission/reception in the exchange of extrasensory information. Tuned into the Schumann
resonance, it may carry such bio-regulating information to distant targets and act as a primitive,
radar-type sensory interface. All these and more mechanisms depend on the SR frequencies
staying within their median range.
As many researchers have discovered, the JNLRMI team soon found themselves deep in the
quicksand of theoretical speculation, “clinging to sparse evidence and ultimately sketching a
map of reality that was not only replete with terrae incognitae but also, like the cartographies of
old, with the mythical beasts of philosophical prejudices.” The journal’s editorial board, after
interviewing many of the leaders in anomalous cognition for input, took a step backward,
humbly admitting there was simply not enough information to draw that meaningful map. But
such humility, under ideal circumstances, hides a great resolve: a stubborn, patient, self-critical
enterprise of direct experimentation which slowly uncovers new stepping stones in our
theoretical path.
In 2012, JNLRMI’s personnel revived their efforts in conjunction with International
Consciousness Research Laboratories (ICRL): The Journal of Nonlocality has been set up to
address an experimental and conceptual impasse in understanding the nature of nonlocality and
observer effects in quantum mechanics. In conjunction with ICRL’s Mind-Matter Mapping
Project, we hope to create a research venue where cutting-edge experimental tools in physics,
biology and parapsychology can be combined to design more revealing protocols; to bypass the
experimental difficulties identified by Wheeler and Bell; and to cast new light on the role that
these effects play in genetic regulatory systems, placebo effects, anomalous perception and
retrocausality. (Sidorov, 2012)
Today, remarkable stories emerge almost daily with such unlikely headlines as, “DNA Found to
Have ‘Impossible’ Telepathic Properties”. Even in light of credible scientific evidence, such
mind-boggling conclusions beg the question, “how can this be?” The short answer is we have no
idea, at least not yet, even though “DNA has been found to have a bizarre ability to put itself
together, even at a distance, when according to known science it shouldn't be able to. If “intact
double-stranded DNA has the “amazing” ability to recognize similarities in other DNA strands
from a distance” does it suggest we might be able to do similarly at the organismic, rather then
molecular level? (Note 1, Sato)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
675
Psi Research
Psi research studies anomalous processes of information retrieval or energy transfer that cannot
be explained by conventional means.
In 1973, the international expose Psychic Discoveries Behind the Iron Curtain, by Shiela
Ostrander & Lynn Schroeder became a best-seller. Former Naval Intelligence Officer, Dr. Carl
Schleicher actively wondered why the U.S. had no comparable program in psychotronics, where
esoterics meets science. He resolved to create one, recruited authors Ostrander & Schroeder to
turn over their untranslated data, and began collecting researchers and creating experimental
protocols. Thus, in 1973, Mankind Research Unlimited (MRU) in Washington D.C. was born as
a private company, seeking government and corporate contracts.
The irony of this Cold War era is that the Soviets thought we were using psychic spies, so they
began their program, which in turn sparked actual US interest, based on their claims of success.
Soviet interest in psi was piqued in February 1960 by a story in the French magazine Science et
Vie (Science and Life) entitled “The Secrets of the Nautilus.” It claimed that the US government
secretly used telepaths to communicate with the first nuclear submarine, the Nautilus, while it
was under the Arctic ice pack. This telepathy project allegedly involved President Eisenhower,
the Navy, the Air Force, Westinghouse, General Electric, Bell Laboratories and the Rand
Corporation.
Communicating with submarines is difficult as radio waves do not penetrate to the depths of the
ocean. Extremely low frequency (ELF) waves are used to signal the submarine to come to the
surface to receive a message. These super-long waves penetrate almost anything including water
but carry little information. If telepathy could work it would be a perfect method of
communicating with submerged submarines. The story was probably a propaganda hoax but the
Soviets were spurred into action.
The Cold War among psychic spies is recounted in James Mills’ book THE POWER (1990),
which is loosely based on MRU’s principle spyentist, “KT,” a longterm advisor to Dr.
Schleicher and Joint Chiefs of Staff. The fictional Jack Hammond is a scientific intelligence
officer for the Monday Afternoon Group, America’s top secret paranormal research unit,
employing occult forces for intelligence and military objectives. As Mills notes, “The most
terrifying weapon lies in the darkest regions beyond the human mind.”
Blue Sky research became of interest to both the government and private sector. It spread from
R&D thinktanks into the open-minded counterculture then to the mainstream. Along the way,
these revolutionary ideas became the obsession of spooks, spyentists, spycologists, psychedelic
physicists and a whole host of fringe characters and psychics. Psychotronic researchers broke
through the Iron Curtain and brought their discoveries to the West. Many world-class scientists
and engineers passed through the threshold of MRU.
In the 1970s, clandestine programs in Remote Viewing were conducted at Standford Research
Institute (SRI). In the 1980s, the Army applied it militarily in the New Earth Battalion, (“Be all
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
676
that you can be”), subject of the 2009 movie, “Men Who Stare At Goats.” Likewise Special
Forces, such as Navy Seals, began using paranormal ESP training for rapid intuitive decisionmaking in the field, and more. One of Dr. Schleicher’s earliest experiments involved dowsing —
not for ‘witching’ a water well, but to find and trace Vietcong tunnels and tunnel rats.
Complementary medicine, including energetics and transpersonal therapies, was another area of
research developing in this same era. Biophotonics led to the detection of biophysical
communications systems and healing applications. Some of Dr. Hiroshi Motoyama’s original
mind-body research took place in conjunction with MRU and its personnel, leading toward
original research in distance healing.
Promising Potential
Astronaut Edgar Mitchell, who did his own telepathy experiment from the dark side of the
Moon, founded the Institute of Noetic Science (IONS) in 1973. It explores different ways of
“knowing,” including spiritual practices and exploration of transformative relationships. IONS
prominent role in Dan Brown’s 2009 best-seller, THE LOST SYMBOL, fixed the meaning of
‘noetic science’ in the public imagination. The Esalan Physics Consciousness Group was
founded at the same time by fellow scientists Jack Sarfatti, Nick Herbert, Saul-Paul Sirag, and
Fred Alan Wolf, to investigate “The Fringe” by studying frontier science subjects such as time
travel, consciousness after death, and ESP.
MRU alumni, Uri Geller with his ESP and spoonbending parlor tricks captured the public
imagination and led to crazes in firewalking and other demonstrations of extraordinary human
potential. Few in the public understood the spectrum of psychotronics or noetics, but the old
mechanical model of the mindbody relationship died and a new model based in psi, mind-body
healing and subtle energies emerged aimed at developing innate human potentials and creative
capacity. Boundaries between inner and outer experience collapsed as if DNA was engineering
imagination to realize itself literally. The New Age now calls this theory by the buzzword
“intentionality”..
The new consciousness paradigm opened our culture to the holistic world of complementary
medicine, the human potential movement and the idea that we, too, could participate directly in
the mysteries of nature and Cosmos. The premise was that the strangest phenomena have the
most to teach us about science and ourselves. New interdisciplinary specialties in
parapsychology, biophysics, accelerated learning and alternative medicine emerged along with
transpersonal therapies.
MRU was at the forefront of this cultural revolution, which promised transformational
breakthroughs in personal and collective consciousness, integral healing and a new worldview.
The fascinating history of early psi research is summarized by Jeffrey Mishlove in his classic
The
Roots
of
Consciousness,
and
MRU’s
homepage.
http://mankindresearchunlimited.weebly.com/
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
677
Many MRU associates, such as Dr. Stanley Krippner, went on to produce early classics in
paranormal literature. He included work by other MRU scientists in his ground-breaking
anthologies on research frontiers.
Technovelties
Blue Sky projects that begin as implausible can produce incremental advances that eventually
result in applied technologies, even if it takes decades. It is bottom-up versus top-down research.
Bottom-up means exploring from the known to the unknown, seeing if there are any
serendipitous opportunities that emerge. By its nature, bottom-up work is unpredictable, based in
some kind of intuition.
Top-down means problem directed and oriented to solving a problem. The reality dimension,
how realistic the project is, shows up independently for either. Some bottom-up projects are
highly realistic, other top-down projects are somewhat unrealistic. No one knows in advance
which research directions will deliver.
We now take for granted many once-magical technologies even better than those from sci-fi
space operas that emerged from the inspiration of the “Star Trek philosophy.” It became Dr.
Schleicher’s policy not to dismiss any outlandish idea for fear of missing some breakthrough.
That led to a wide scope of Blue Sky investigation.
Defense Advanced Research Projects Agency (DARPA), founded in 1958 when the Soviets
launched Sputnik, is the Pentagon’s autonomous Blue Sky agency. Such projects are still
conducted behind closed doors by DARPA, who’s “holy grail” is cracking the brain’s code to
build a brain-computer interface.
Many dark chapters in brainwashing and mind control have been written since Tavistock
Institute of Human Relations began its massive social engineering program after WWII and
teamed with CIA to deploy nefarious experimental programs, such as MK Ultra. There is a
Defense Intelligence Agency (DIA) Psychic Center and the NSA (National Security Agency)
studies parapsychology, that branch of psychology that deals with the investigation of such
psychic phenomena as telepathy, clairvoyance, extrasensory perception, and psychokinesis.
They also did experiments where the mind of one person controlled the bodies of others
(Motoyama).
MAKES ME WANT TO PSI
The spontaneous event commonly called psychic experience, perception or ability is called 'psi'
in scientific arenas. Even more precisely, it is now often referred to as anomalous cognition
(AC). A particular form of intentional AC is known as Remote Viewing. Between 1978 and
1995 the U.S. government sponsored the Stargate Program, in conjunction with Stanford
Research Institute (SRI), a psyops development think tank.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
678
The existence of psi or ESP abilities has been hotly debated among scientists for decades, since
J. B. Rhine began his experiments in 1927. Both the pro (Dean Radin; Ingo Swann; Jessica Utts,
Russell Targ; Hiroshi Motoyama) and con (James Randi, Susan Blackmore, CSICOPS) positions
have their "true believers", and it seems never the twain shall meet.
Psi is still a paradigm that lives on the outskirts trying to become a sanctioned science. But just
because a subject is controversial, and happens to be a space and time transcending experience,
doesn't mean we shouldn't investigate it. In fact, it beckons us to focus on it even more
thoroughly to reveal the truths hidden there. We simply need to do it with stringent, critic-proof
methodology.
There are a variety of psi powers, known for centuries in Eastern philosophy as siddhas,
exceptional human abilities. The uninitiated or skeptical may be perplexed or daunted at the
prospect of coming to any rational conceptual understanding of these anomalous phenomena,
which have been associated with the realm of mysticism, superstition and the supernatural.
In actual fact, research by the author, a clinical hypnotherapist (A.C.H.E.), and others (Miller;
Ryzl) shows that nearly anyone can improve their psi ability through simple techniques of selfhypnosis.
Psi is also at the root of focused intent, distant mental interactions, distance healing and
therapeutic rapport, where there is a subtle shared consciousness and often brainwave
synchronization. This capacity is within everyone’s grasp, as the human potential movement
demonstrated with such trance phenomena as fire walking and guided imagery.
We've virtually all had those uncanny or awesome experiences where we seemed to intuit,
dream, or "know" something in advance of conventional means. Sometimes it is called presentiment. Around 55% of reported incidents occur in dreams. Another example is the
synchronicity at work in the affairs of “star-crossed lovers.” When we are in love, we seem to
share the same “wavelength,” virtually able to read one another’s minds. Who hasn’t thought of
a friend or acquaintance only to have the phone ring?
Often the most compelling stories come from those who don't even "believe" in the
phenomenon, but find themselves experiencing it, usually in the unfortunate circumstance of the
illness, injury or death of a distant loved-one. Psi is not just a mental perception or conception;
we feel it in our guts, in our bones, in our marrow. It is first and foremost a holistic mind/body
experience.
According to leading parapsychologist Dr. Stanley Krippner, "At one level of investigation,
there already are 'replications' and 'battle-tested' results, specifically the finding that about 50%
of an unselected group will report having had a 'psychic experience,' supposedly involving those
psi phenomena that have been given such labels as 'telepathy', 'clairvoyance', 'precognition', and
'psychokinesis' [mind over matter]. This percentage may vary from one culture, age group, and
educational level to the next, but it has been repeated, in one study after another, for the last
several decades."
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
679
The move in biophysics is to take psi research from endless theorization, proofs of existence and
boring replications into innovative and practical experimentation. The problem is that in order to
do that scientifically, one has to risk credibility and professional suicide, as well as being
underfunded.
OPEN SESAME
Though it often seems confined to mediums, channels, sensitives, or ESPers, most individuals
are capable of expressing some nonlocal communication or psi phenomena. However, that
ability may be blocked for various reasons by an adaptation to consensus reality, to conventional
thinking. We need to develop “out of the box” thinking. Even Einstein said that past, present and
future are illusions, even if they are stubborn ones. Conscious calculation rarely plays a role in
ESP; the same is true for creativity.
Both ESP and creativity have deep taproots in the psyche. Pang and Forte (1967) found some
evidence of a relationship between creativity and ESP, as did others (Honorton, 1967). Frederick
Myers reported that a large proportion of ESP experiences occur in altered states such as dreams,
trance, hypnosis and creativity while Masters and Houston (1966) counted it among the varieties
of psychedelic experience.
ESP, hypnosis and mind-expanded states have sensitivity to the unconscious at their core. And
that subconscious expresses itself through symbols, imagery, and sensations to communicate
with the conscious mind. Hypnosis is the "open sesame" to the waking impressions and sensory
images of the deeper mind/body.
The elusive ability to swing back “the doors of perception” and enter the numinous realm of the
collective unconscious was described by psychologist C. G. Jung. Whether deliberate or
accidental, anyone can open to the force of this revealed process, to this dynamic information
field. Those who frustrate themselves with self-defeating behavior in other areas of life often
show poor psi performance.
Positive ESP scores seem to correlate generally with traits such as openness, high self-esteem,
warmth, sociability, adventuresomeness, relaxation, assertiveness, talkativeness and practicality.
However, some psi-talented individuals often don't score well in laboratory settings.
On the other hand Russell Targ (1994) claims, "[P]si is no longer elusive; it can be demonstrated
when needed for study and investigation." Even though psychic training to strengthen the signal
line is possible, unpredictability has been the hallmark of this emergent gift. To overcome this
problem in both the theoretical and experimental arenas requires a marriage of the disciplines of
physics, biology, medicine, psychology, and hypnosis.
Findings from all these fields converge in the paradoxical subject of Extra-Sensory Perception.
As the ideas of quantum mechanics, relativity and parapsychology slowly make their way into
our collective consciousness, our common-sense views on time and causality find themselves
more strained than they've ever been in the course of human history.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
680
Will this challenge remain the domain of theoretical science, or can we foresee a day in which
the general understanding, and even the experience of the average individual, will be shaped by
this new perspective on reality? (Sidorov, 2003, “The Mind In Time”).
It takes many disciplines, as well as the latest findings in physiology, neurobiology and
information theory to begin to formulate any comprehensive understanding of the phenomenon
and bridge the conceptual gap. ESP used to be studied in Parapsychology, an adjunct of
psychology. But its subject matter has become so mainstream, the field has been return to
ordinary Psychology. ESP “software” is studied in psychology, but ESP “hardware” is the
domain of biophysics.
Researchers are probing the interface between matter, spacetime and mind with increasing
precision. There is optimism that ultimately conventional pathways will be found to explain their
appearance. Suggestions have included Schumann Resonance as a nearly-instantaneous carrier
of psi information or perhaps paradoxical quantum nonlocality or coherence to account for it.
There are many models that provide potentially viable explanations. The mental aspects can
perhaps be described psychologically, but the mechanics require models from physics. A variety
of theories have been proposed, including neurological, holographic, electromagnetic, and
quantum mechanics based hypotheses.
Like electricity, no one knows how psi works. However, to foster and practice psi we don't need
to know how it works, anymore than we need to know the mechanics of internal combustion to
drive a car.
The faculties of (1) Telepathy; (2) Clairvoyance; and (3) Precognition came into the public eye
when stories of Russian and CIA remote viewers broke in the press. But compelling, anecdotal
stories alone do not satisfy the scientific method.
Stories of distance healing, a form of PK or psychokinesis (mind over matter), require another
article of their own to do them justice. It may be easier to model virtual information transfer than
mind over matter. "Spooky action at a distance" requires even stronger evidence than sensing at
a distance. But is "distance" here really a factor or an illusion in a holographic simply-connected
universe? The paradox of spacetime and relativity presents itself in psi as psycho-retrocognition,
or time-reversed PK.
Though these experiences of knowing at a distance are called "extra-sensory," they often appear
"as if" received by conventional sensory or mental means, for how else can we "know what we
know"? It is a holistic psychophysical experience, affecting the whole self, physically,
emotionally, mentally and often spiritually. The impediments of distance and time seem to
dissolve; the barriers of spacetime are mysteriously overcome. The information is 'just there' in
one form or another, whether spontaneous or facilitated.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
681
1). Telepathy is a message, direct mind-to-mind communiction, direct knowing through being,
a clear intuition or empathic awareness, often demonstrated in the psychotherapeutic or healing
setting. Telepathy is a transmission from one mind to another.
2). Clairvoyance appears as information about events at remote locations, manifesting as an
image, or gestalt psychic impression, rather than a thought; (it is often linked to perception at a
distance: so-called astral travel, out-of-body experience, or remote viewing).
3). Precognition is the most uncanny; transcending time, it seems to rend the veils of the
future (jamais vu) and the past (deja vu) with strong, often unpleasant, premonitions.
According to Scientific American (Sept. 2002, p. 103), [apparently long after Pribram's theory
from the 70s], "in 1990 Herman Sno, a psychiatrist at Hospital de Heel in Zaandam, the
Netherlands, suggested that memories are stored in a format similar to holograms. Unlike a
photograph, each section of a hologram contains all the information needed to reproduce the
entire picture. But the smaller the fragment is, the fuzzier the resultant image become. According
to Sno, deja vu occurs when some small detail in one's current situation closely matches a
memory fragment, conjuring up a blurry image of that former experience." There are competing
theories of deja vu, but the holographic concept of reality is a leading contender in the
biomechanical explanations of psi.
Psi meaning comes through emotionally intense visual, auditory and kinesthetic experiences. It
is a human potential we can learn to tap. We can use our intentionality as a probability
perturbation instrument. We can use mental focus to alternately concentrate and relax our
attention. Intent is suggested as a variable in transmission and reception in the exchange of
extrasensory information, possibly within the range of ELF electromagnetic frequencies
(Sidorov, 2002).
Stanford and Lovin (1970) found possible support for a relationship between the generation of
alpha waves and ESP, as did Monroe (1971). More recent research has implicated the
electromagnetic signals of Schumann Resonances as carrier of seemingly non-local transfer of
information (Pitkanin, 2001). Persinger (1989) has suggested that psi information signals are
actually carried on extremely low electromagnetic frequencies and our temporal lobe structures
are sensitive to them.
Whether one believes in spontaneous psi experience, or not, it has a long and colorful history, in
the mystic and healing arts of the East and West, and in science, even business. The difference is
the trigger that evokes the experience. Management trainers have taught self-hypnosis as a
means of fostering intuition, rapport and other practical applications of ESP.
The role of ESP is inextricably bound up with other creative processes where information or
inspiration seemingly appear from nowhere. Data acquired through ESP, prescient dreams and
other imaginative thought processes riddles the stories of scientific discovery and creativity.
Psychic detective work and investigative reporting has received mixed reviews, since following
up on dry leads uses time and vital resources. Without controls, these anecdotes are difficult to
evaluate.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
682
In the arts, it has been said that "life imitates art," sometimes to uncanny proportions. Krippner
(1972) recounts a story of ESP in creativity, whose prophetic detail later took on ominous tones.
In 1898, Morgan Robertson published a popular novel called Futility. It described the wreck of a
giant ship called the Titan, considered "unsinkable" by the characters in the novel. Perhaps you
recognize this oft-told tale as that of the Titanic, but it was not wrecked until April 15, 1912. In
the novel, the ship displaced 70,000 tons (Titanic 66,000 tons), was 800 feet long (Titanic 828
feet); the Titan carried 3000 passengers and 24 lifeboats, while Titanic had only 20 lifeboats for
the same number of people. Both ships sank while encountering an iceberg at the speed of 23-25
knots. The rest, as they say, is history.
FROM TRANCE TO CREATIVITY
The question becomes "How can we facilitate the emergence of psi phenomena, either for
greater awareness or creativity?" Knowing what we know about psi expression, how can we
train ourselves to encourage its emergence? Hypnosis or self-hypnosis simply helps engage the
emotional mind, the imaginal mind, the biophysical mind rather than just approaching the task
rationally and conceptually.
Unfortunately, the question of psi-facilitation was asked by covert forces during the Cold War,
and much of the statistical and practical data on psi comes from those black-ops sources (CIA,
KGB, NSA, DIA, DOD, U.S. Army and Navy). The Russians wanted to use psi for espionage
and the US countered with its own team. Much of this government-sponsored work went on at
Stanford Research Institute (now SRI International), by Puharich, Puthoff, Targ, and Swann.
Human potential advocates, Jack Schwarz and Robert Monroe separately pursued independent,
more explorative and mystical approaches. Both taught consciousness management techniques
through forms of self-hypnosis. Schwarz, practicing as the Aleithea Foundation in Southern
Oregon, focused on bioregulation with autohypnosis and subtle human energies.
Monroe's techniques employ neuroregulation with the frequency-following response (which he
trademarked with the Monroe Institute in Virginia, as Hemi-Synch) to induce trance, entraining
both hemispheres in alpha and theta (1982).
Hemi-Synch, also known as binaural beat technology, actively drives the modulation of
electrocortical activity through resonance effects, changing levels of awareness and arousal,
attentional focus, and cognitive content. Often combined with biofeedback, it helps shortcut
processes that would take years of technologically unassisted yogic training.
Graywolf Swinney (2001), Dr. Stanley Krippner, and Iona Miller have conducted trainings in
co-consciousness (Erickson, Rossi & Rossi, 1976) and theta training at Asklepia Foundation,
also in Southern Oregon. A deep state of rapport is used in psychotherapeutic journey processes,
employing shamanic hypnotherapeutic techniques. Theta is reportedly the psychic range of the
mind, generated largely in the temporal lobes. Co-consciousness is a shared virtuality, a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
683
telepathic rapport wherein both participants’ brainwaves become synchronized into a single
holographic biofield (Miller and Swinney, 2000).
Spontaneous psi phenomena have been associated with theta waves by Krippner (1977), the
Greens (1977), and more recently by Persinger (1987). Consciously producing theta requires
quieting the body, emotions and thoughts simultaneously, leading to an integrative reverie, a
deep focus of attention. Theta is often accompanied by hypnagogic or dream-like imagery
emanating from the temporal lobes.
John Curtis Gowan (1975) catalogued the entire spectrum of extraordinary phenomena related to
trance, art, and creativity. In his taxonomy, he called these distinctive modes or domains of
human dynamics Prototaxic (Trance), Parataxic (Art), and Syntaxic (Creativity).
Trance is characterized by loss of ego, art by emotionally charged (often symbolic) imagery, and
in creativity meaning is more or less fully cognized symbolically with ego present. In some
ways, these modalities could represent the uncanniness of precognition, the imagery of
clairvoyance, and the knowing of telepathy.
Trance is often associated with awe, dread, horror, and panic since ego control is weak or absent.
These numinous effects are moderated in the artistic experience that comes as visualization,
audialization, emotional inspiration, sensual, symbolic and mythopoetic imagery.
In terms of precognition, artists are often said to be perceptually "ahead of their time." Art is the
transition phase in the relationship between the ego and the emergent transcendent function.
Transcendence is a "quantum leap," a recurrent process, not a steady-state. It is a phasetransition moving toward illumination. The syntaxic experience of creativity is even more
benign since the mind apprehends directly without ego dissociation. Psi experiences become
more naturally integrated – regular, inspirational and uplifting while less frightening or
awesome.
Gowan's work naturally included both hypnosis and ESP, which he cited as consciously or
unconsciously operative at these various levels of dissociation, ego-involvement and levels of
arousal (sympathetic and parasympathetic). Puharich (1961) found telepathic reception
facilitated by parasympathetic activation, while sending the message was stronger with
activation of the sympathetic, or adrenergic system.
For Gowan, the accessibility of certain psychic experiences depended on the mode of
functioning. Intuitive self-knowledge is intrinsic to a wide variety of higher mental functions.
Hypnosis and self-hypnosis are clearly linked to the primal trance, but can be applied in more
integrated modes to enhance psi ability (Krippner, 1968).
PSI DEEPLY: HYPNOSIS & ESP
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
684
In 1967, the Czech government tried to co-opt the allegedly successful psychical research and
training program of biochemist Milan Ryzl. After screening many candidates, he found 50 highscoring subjects, and they proceeded to win several rounds of the Czech lottery.
Milan Ryzl, a chemist who defected to the United States from Czechoslovakia in 1967, developed
a hypnotic technique for facilitating ESP. . .Ryzl’s technique involved the intensive use of deep
hypnosis sessions almost daily for a period of several months. The first stage of the sessions was
to instill confidence in his subjects that they could visualize clear mental images containing
accurate extrasensory information. Once this stage was reached, Ryzl concentrated on
conducting simple ESP tests with immediate feedback so that subjects might learn to associate
certain mental states with accurate psychic information. Subjects were taught to reject mental
images which were fuzzy or unclear. This process, according to Ryzl, continued until the subject
was able to perceive clairvoyantly with accuracy and detail. Finally, Ryzl attempted to wean the
subject away from his own tutelage so that he or she could function independently. While still in
Czechoslovakia, Ryzl claimed to have used this technique with some five hundred individuals,
fifty of whom supposedly achieved success.
Other studies have shown heightened ESP in states of physical relaxation or in trance and
hypnotic states. In fact, the use of hypnosis to produce high ESP scores is one of the most
replicable procedures in psi research. (Mishlove, 1975).
The standard definitions used for hypnosis often call it a borderline state between sleeping and
waking, i.e. body asleep, mind awake. Any state characterized by an intense concentration of
attention in on area, accompanied by a profound lack of attention in other areas, may also be
considered hypnosis. It opens us to our psychophysical impressions by limiting external input.
With this type of definition, everyone is considered to be continually in a light state of hypnosis,
witness “white line fever” while driving, or the plea, “I was spaced-out.” Musicians call it “being
in the groove,” others “sharing a wavelength.” Our social roles are also like trance states with
their intrinsic patterns. When we go in public we wear the ‘armour” of our persona and immerse
ourselves in that self-image.
Charisma is also a form of hypnosis akin to Mesmer’s original “animal magnetism.” Traumas
also create trance states with automatic behaviors that can persist for years. The “scripts, games,
and rackets” of Transactional Analysis can also be seen as trance states, where we habitually
replay our typical ways of dealing with self, others, and world. So the question becomes not “if”
one is hypnotized, but what kind of trance and its depth one is in at any given moment.
The depth of hypnosis, which is an implied issue in this definition, may be defined as the
difference between the intensity of concentration in one sphere or area and the depth of
inhibition in others. Attention focused in one area creates a corresponding lacuna, or lack of
attention, in other areas of the brain. Centering the attention for prolonged periods, often with
suggestions for further deepening, leads to deeper states of hypnosis. With these definitions,
Ryzl developed a useful model for relating hypnosis to psi phenomena.
Psi Theory:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
685
Postulate I: The conscious experience is associated with the nervous processes which take
place above a certain critical level of awareness/alertness. This function, defined as I(c), varies
considerably in a state of hypnosis, where attention is focused.
Postulate II: Psi Energy, arbitrarily defined as E(psi), is an equivalent in the field of extrasensory phenomenon of what, in our three-dimensional world, is called energy.
Correlate A: E(psi) is not limited by time.
Correlate B: E(psi) can not be transformed into other energies (i.e. physical energies,;
converting heat into light).
Correlate C: E(psi) operates by manipulating the transformation of physical energies.
Postulate III: Psi Energy, is responsible for extra-sensory perception and psycho-kinetic
phenomenon (PK).
Postulate IV: Psi Energy is the product of some aspect of the metabolic processes. Physical
data regarding the relationship between metabolic processes and extra-sensory perception can be
found in Beyond Telepathy, by Andrija Puharich.
Postulate V: The generation of Psi Energy rapidly decreases the level of alertness. This
immediately explains why:
(1) each conscious act has a limited duration,
(2) why we experience a permanent train of changing thoughts, and
(3) why our attention permanently shifts from one object to the next.
When you think, Psi Energy is created. The Psi Energy automatically decreases the level of
alertness so that one shifts to something else.
Postulate VI: The intensity of conscious experience, I(c), depends on the time rate of the
generation of psi Energy. Mathematically, this is described as dE(psi)/dt = A(e) x I(c).
The rate of change of E(psi) as a function of time is equal to some geographical constant,
A(e), times the intensity of concentration, I(c). More simply stated Psi Energy is equal to a
geographical constant times the intensity of concentration, I(c), times the amount of time that the
thought is held. E(psi) = A(e) x I(c) x t
If we cannot make any particular thought last long enough, it should be sufficient to repeat it
again and again until the value of the individual brief periods add up to a sufficient value. The
equation now becomes E(psi) = A(e) c I(c) x [t(1) + t(2) + t(3) + …]
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
686
Postulate VII: The formation of Psi Energy, which is created by a holistic psychophysical act,
preserves the semantic control of the thought that created it. In essence, your thought is uniquely
distinct. If you deviate from your thought slightly, it is a different thought-form, including the
psychosomatic component. There is a tangible shift in the mind/body.
The Method:
(1). Formulate the question.
(2). Hold that thought for as long as possible.
(3). Assume that the event has occurred.
(4). Drop into a “blank mind” state and wait.
When questioning or desiring thoughts are intense enough, lasting long enough or repeated
frequently enough, psi is produced in sufficient intensity and structure to be detectable in the
physical world. This may occur in hypnotic states, in states of intentionality, elated or traumatic
emotions, or when interest, motivation, or desire is strongly increased.
The individual confronts the continuum with desire and prolonged concentration. The question
being asked must be intense enough to impress itself on the unconscious. Lacking intensity, the
signal will not be perceived. Intentionality strengthens the signal path.
Consciousness is then dropped into a “blank” state, an empty state, or “beginner’s mind.” The
actual visualization is a switch from the concentrated point to the void. When this occurs the
information is impressed on consciousness, resulting in a psychophysical perceptual event. This
event is independent of both space and time.
Ordinarily when people spontaneously fall into trance states, they are generally not in a “blank
mind” state of expectant emptiness. There is the chatter of subconscious thoughts going on even
as the process deepens toward sleep. These thoughts are generated and go on automatically at a
subliminal level, often without awareness.
Consequently, the information or signal path gets distorted, and weird patterns emerge, much
like those experienced in dreams. In a waking dream, distorted signals may be perceived as
“spirit guides”, automatic handwriting, or other autonomous related phenomena of trance states.
We have seen earlier that Gowan characterized this loss of ego-awareness as the Prototaxic
Mode.
Puharich believes reception is enhanced by “parasympathetic activation” in which there is an
increase in released acetylcholine. He claims that telepathic sending of information is easier
when there is an increased amount of adrenaline in the system. These metabolic processes are
not “causal”, but merely correlates of psi. Psi meaning comes through intense visual, auditory,
and kinesthetic psychosensory experiences.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
687
This “energized enthusiasm” can be seen in states of emotional involvement and artistic
inspiration (Parataxic Mode), as well as creativity (Syntaxic Mode). Parataxic experience
consists of relationships with multisensory images whose meaning remains on the symbolic
level.
Syntaxic experiences occur when the consciously aware ego cooperates willingly with the
subconscious forces. Here knowing and meaning are clearer and fully cognized with minimal
distortion. Other higher forms of concentration include biofeedback, meditation, tantra, peak
experiences, higher Jhana states of yoga, and so on. Concentration is intense, structured and
prolonged.
Discussion:
ESP is often observed in hypnosis, a state characterized by a single intensive thought. Recurrent
cases of psycho-kinetic phenomena, such as the haunted-house variety, are often reported to be
connected with previous trauma or tragic events, associated with intensity of concentration, I(c).
The frequently reported cases of crisis telepathy – ESP contact between two persons, one of
which is dying or in grave danger – are necessarily associated with intense thought or
concentration, even obsession and a highly aroused state. The length of time experienced
depends entirely upon the circumstances; in some cases there is subjective dilation of time
perception.
The discovery of mental impregnation, known in the literature as psychometry suggests that
repeated identical thoughts increase the expected psychic effect. Wearing a ring for a long time
may “imprint” memory of the wearer onto the ring; just slipping a ring on and off and handing it
to a psychometrist will not generally reveal any memory of the wearer.
Religious or spiritual traditions assert that repeated prayers may be more effective than single
ones. In other words, the more you repeat the same prayer, or mantra, or the more you do a
single ritual, the greater the effect. Along that line of reasoning, “tithing” might be seen as a
factor of one’s time or attention, rather than money. Some meditation schools, for example,
require no money but 10% of your daily time (2.5 hours) in meditation.
The stimulating action of psi formation on the brain may account for memory, more particularly,
active recollection. The influence of psi formation increases the level of awareness of the neuropatterns corresponding to the thought to be remembered. The synapses are flooded over and over
with the same chemical messengers and electrical signals. The correlating psychosomatic
content is consciously re-experienced.
DREAM TELEPATHY AND BEYOND
In 1969, Charles Honorton and Stanley Krippner reviewed the experimental literature of studies
designed to use hypnosis to induce ESP. Of nineteen experiments reported, only seven failed to
produce significant results. Many of the studies produced astounding success. In a particularly
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
688
interesting precognition study, conducted by Fahler and Osis with two hypnotized subjects, the
task also included making confidence calls – predicting which guesses would be most accurate.
The correlation of confidence call hits produced impressive results with a probability of
0.0000002. (Mishlove, 1975).
Krippner went on to conduct research in Dream Telepathy (1973) with Montague Ullman,
following the lead of other Maimonides Hospital (Brooklyn, N.Y.) researchers, such as
Frederick Myers. These experiments in nocturnal ESP are foundational and though never
replicated, the results were highly suggestive of a strong psi correlation.
Their ten-year study concluded that dream reports can show the effect of telepathy, clairvoyance,
and precognition. Their hypothesis was that ESP is more common during dreaming than waking
and therefore an "agent" could more easily transfer the target thoughts or imagery to a sleeping
subject, influencing their dreams.
Such prominent dream researchers as David Foulkes (Belvedere & Foulkes, 1971), Gordon
Globus (Globus et al., 1968), Calvin Hall (1967), Robert Van de Castle (1971), and Keith
Hearne (1987) attempted to repeat these findings. Because the replication rate from these other
laboratories was inconsistent, the Maimonides team did not claim to have conclusively
demonstrated that communication in dreams can sometimes transcend space and time. However,
they did open a promising line of investigation.
Years later, Stanley Krippner and Michael Persinger, a Canadian neuroscientist, reviewed the
entire body of dream research data from Maimonides Medical Center, selecting the first night
that each subject in a telepathy experiment had visited the laboratory. They matched the results
of these nights with geomagnetic data, discovering that the subjects' telepathy "hits" tended to be
higher during calm nights than during nights marked by electrical storms and high sunspot
activity (Persinger & Krippner, 1989).
Persinger (1974) has urged using reported psi phenomena in new and ingenious ways, observing,
"Across cultures and throughout history people have been reporting psi- experiences. Let us find
out what they are saying. . .It is by looking at the similarities of the verbal behavior that we may
find enough consistencies to understand the factors responsible for the reports” (p. 13).
Persinger (e.g., Schaut & Persinger, 1985) has examined several collections of spontaneous
cases, including the 35 gathered by Stevenson (1970), reporting that they seem to occur most
frequently when geomagnetic activity is calmer than the days before or after the experience - and lower than the month's average activity.
This approach can be applied to any collection of cases (e.g., Persinger & Krippner, 1989) where
the date of the alleged experience has been recorded. If repeatable, these effects may help to
provide an understanding of the mechanisms underlying psi phenomena, and may even indicate
a potentially predictable pattern for such events. (Krippner)
Geomagnetic field perturbations have been reported to affect biological systems by other
investigators (e.g., Subrahmanyam, Sanker Narayan, & Srinivasan, 1985). Persinger (1989) has
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
689
proposed two interpretations of the geomagnetic field effect. The first is that psi is a
geomagnetic field correlate; solar disturbances and consequent geomagnetic storms affect this
correlate. The second is that the geomagnetic field affects brain receptivity to psi, which remains
constant.
In the latter interpretation, psi is always present in space and time, waiting to be accessed by
crisis, emotion, or by optimal laboratory stimulus parameters. Geomagnetic activity may affect
the detection capacity of the brain for this information, especially the neural pathways that
facilitate the consolidation and conscious access to this information. Without this geomagnetic
activity, awareness of the psi stimulus might not be as likely and the brain's "latent reserve
capacities" would not be utilized.
Taking this argument one step further, Persinger (1989) points out that deep temporal lobe
activity exists in equilibrium with the global geomagnetic condition. When there is a sudden
decrease in geomagnetic activity, there appears to be an enhancement of processes that facilitate
psi reception, especially telepathy and clairvoyance.
Increases in geomagnetic activity may suppress pineal melatonin levels and contribute to
reductions of cortical seizure thresholds. Indeed, melatonin is correlated with temporal loberelated disorders such as depression and seizures. (Krippner)
CYBER PSI TRAINING
So what direction can we expect psi research to take in this new millennium? Clearly, the
experimenters themselves want to follow a self-directed course rather than the mandates of a
government-driven program. They would like access to private, academic, and government
funds, with leading edge equipment: high-ticket brain monitoring equipment such as 90-channel
EEG, fMRI, SPECT, and ERP. They would like to practice without a professional stigma
attached to their pioneering work.
Several theories of psi have been put forth throughout the years. Psychologist Rex Stanford,
altered-states expert Charles Tart, post-quantum physicist Jack Sarfatti, and psi researcher
Charles Honorton, as well as physicists Helmut Schmidt, Claude Swanson, Dean Radin and
William Tiller have all developed models for ESP and precognition. Each embodies certain
possible, even plausible factors. Some researchers worked with Eastern swamis and yogis to
understand the mechanisms and induction techniques or evocation of this psychic power.
Quantum theory predicts that empty space (the vacuum) contains an enormous amount of
residual background energy known as zero-point energy (ZPE). Physicist David Bohm, biologist
Rupert Sheldrake (researching psychic pets) with his morphogenetic fields, and Ervin Laszlo
propose zero-point or vacuum potential mediation for psi. The superdense quantum vacuum may
be a physically real field, including but not limited to gravitation and electromagnetism. Perhaps
it can transmit psi.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
690
However, they can’t provide any experimental protocols that might test such theories. Is psi a
field or a quantum effect? Fields link phenomena in time as well as space. But, fields themselves
cannot be observed; only the influences propagating through them.
Other theories suggest phase-conjugate pilot waves, scalar waves, virtual states, hyperfield flux,
holographic hyperchannel effect, complementarity, even uncertainty. Biophysical theories for
the paranormal bridge include Josephson junctions, microtubules, and liquid crystals as psi
transducers.
Honorton and others long ago found defects in old psi testing techniques and addressed
criticisms with new methodology. They eliminated variables like subconscious cueing by
covering the subjects’eyes with split ping-pong balls and playing “white noise” into their ears.
Researchers hypothesized that this neutral field would function as a less-distracting “blank
canvas” for psi hits. So it served a dual purpose of refining experimental procedure and
minimizing distracting sensory input. These experiments, (known as Ganzfield tests), were
replicated by many experimenters in many facilities, with encouragingly similar positive results.
Other tests were conducted in sensory deprivation chambers and electrically-shielded Faraday
cages.
Experimenter bias, the tendency to find what one seeks, is an occupational hazard, though
skeptics have found positive psi correlations. But careful interpretations of models, artifacts,
experimental method, instrumentation, randomization, target selection, statistical inference,
sensory leakage, recording errors, and controls can’t be rigorous enough.
Proper scientific control for ESP research has been refined over the years, though cheating and
frauds have plagued the field, and the naïve scientist. One solution to this dilemma lately has
been to experiment with the field-tested government Remote Viewers, who have established
track records. They have their own reports of their subjective experiences – not the results of
their missions – but the sensations that led to the observation or retrieval of those images.
Remote viewer Ingo Swann, called the father of RV, argues for the demystification of psi.
Swann’s model supersedes the traditional psi paradigm and focuses on the hardware issues
discussed in neurobiology and information theory.
Swann argues for systematic and deliberate development of this ability much like athletic
training, as well as conceptual understanding. He prefers the term Distant Mental Interactions
with Living Systems (DMILS) to ESP. He wants this capacity tested in the context of physical
science as part of man’s natural spectrum of senses. He claims applying focus or attention on the
perceptual apparatus with feedback on results “fine tunes” psi ability.
His concrete approach and insightful conclusions include his view of our sensory apparatus as a
“transducer array” to convert information from one form to another. He calls his human
“software” program a “mental information processing grid.” He simply converts various forms
of input energy to another form his sensory system can “read.”
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 673-691
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 1
691
We do much the same when we interpret the electromagnetic signals that come through the air
from a voice into meaning in our brains. He suggests we can develop the ability for several
transducers of signals, depending on our exposure to the cognitive processing of these signals.
Targ claimed to see reasonably sharp and clear pictures. In remote viewing, if the mental picture
doesn’t form, one is left with a mere “impression,” a less-precise signal. The signal is compared
against memory to determine if it is meaningful to the task at hand – the target.
In other words, you can develop this ability through practice and feedback of the accuracy of
your perceived signals. Pathways that work get reinforced. The process is very similar to
psychophysical learning with biofeedback, such as alpha and theta training.
Swann argues for learning to fine tune one’s signal to noise ratio, learning to notice direct
sensory data as well as imaginal signals, such as feelings, intuition, impressions. Repeated
exposure and accurate feedback strengthens recognition of subtle and implicit relationships. Can
cybernetic machines, such as random number generators, computers, and biofeedback devices
help us hone psi faculties?
Swann emphasizes the difference between message and its structure. An experienced viewer can
put together mental images from subtle cues. In RV, the signal appears as symbols, sounds,
feelings, tastes, pictures, and holistic impressions. One learns to organize them based, again, on
repeated feedback.
Misconceptions, fears, rigid concepts, body movement, excessive gastrointestinal activity,
sleepiness, language categories, and other psychological “baggage” can be sources of
confounding noise. Other blocks come from trying too hard, and distracting daydreaming or
preoccupying thoughts. Telepathy, empathy or rapport, and charisma seem to be related and
clearly come into play during therapeutic entrainment.
[References at end of Part 4]
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
715
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
Article
Remote Mental Interactions: A Review of Theoretical
Modeling of Psychophysical Anomalies Part 3
Iona Miller*
ABSTRACT
This article presents a review of theoretical modeling of psychophysical anomalies. It originates
from my involvement with the Journal of Non-Locality and Remote Mental Interactions
(JNLRMI) which was founded by Lian Sidorov in the wake of research institutions of previous
decades, such as SRI, IONS, PEARS, and MRU. JNLRMI began as an attempt to bridge widely
scattered evidence and ideas on the frontline of mind-matter research (energetics, remote mindmind and mind-matter interactions). JNLRMI was a challenging and exhilarating journey,
sustained by multidisciplinary readership interest in the subject.
Part 3 of this article contains a round-table discussion on memory, information and the limits of
identity entitled “Who and where is the Self?” moderated by JNLRMI Editor, Lian Sidorov, and
participated by Roger Nelson, Stanley Krippner, Jim Tucker, Mark Germine, Chris King, Matti
Pitkanen and Gerry Zeitlin. Such discussions help researchers re-contextualize what has come
before, determine where we “are” in deciphering the minscape, and where we are going by
suggesting pertinent open-ended questions.
Key Words: psi, parapsychology, biophysics, energetics, Schumann Resonance, mind-body,
geomagnetism, ELF, ESP, precognition, hypnosis, paraphysics, remote viewing, worldview.
Who and where is the Self?
A round-table discussion on memory, information and the limits of identity
Lian Sidorov, Moderator
The hard problem of consciousness is no petty adversary but the abyss staring us back in the
face. The universal record is an undecidable proposition which intent turns into an acute
paradox. --Chris King
Introduction
In 1964 Dr. Ian Stevenson, chief psychiatrist at the hospital of the University of Virginia, took a
step that many regarded as professionally suicidal: he abandoned his practice in order to focus
* Correspondence: Iona Miller, Independent Researcher http://ionamiller.weebly.com E-Mail: iona_m@yahoo.com
Note: This work was completed in 2003 and updated in 2012. Further, material authored by Dr. Lian Sidorov has been
reproduced with her permission.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
716
his full attention on the investigation of alleged cases of reincarnation. His decision, in
Stevenson's own words, was prompted by his increasing frustration with the current psychiatric
dogma, which attributes human personality development to a combination of genetics and pre/post-natal environmental factors. As he saw it, some of the psychiatric disorders confronting
him in his practice simply could not make sense within that framework. With a rare combination
of visionary zeal and highly-trained investigative skepticism, he went on to document, analyze
and archive over 2,000 cases over the next 4 decades (Stevenson, 1975-1983; Stevenson, 1993;
Cranston and Williams, 1984; Becker, 1993; Secrest, 1988). In 1977, the prestigious Journal of
Nervous and Mental Diseases devoted a special issue to his studies. Since then, he has published
numerous scientific papers as well as a series of books in which he makes the case for this
extraordinary body of evidence in a refreshingly dry, critical and understated tone that has
earned him universal professional accolades as well as academic followers - such as Dr. Jim
Tucker, assistant professor of psychiatry also at the University of Virginia, Charlottesville. Their
studies focus on young children (primarily for credibility reasons, but also because these
memories tend to fade around the age of seven, as the child enters the turbulence of the outside
world and starts forming abundant new impressions once in the school environment) and rely on
a thorough investigation of subject statements, witnessed behavior, medical and legal
documents, verification of names, dates and factual information that the child could not have
been exposed to by other means. Particularly strong evidence comes from skills (typically
xenoglossia, or the use of unlearned dialects, old or foreign languages); behaviors (phobias,
philias); and biological traits (rare birthmarks corresponding to documented cause of death or
maiming in the claimed "previous personality"). This pioneering work continues to evolve as
innovative investigative methods and theoretical approaches are developed by a new generation
of researchers (see Keil J. and Tucker JB, 2000; Tucker JB, 2000; Tucker JB and Keil J, 2001).
Technically coincidental with Stevenson's decision to delve full-time into the study of alleged
reincarnation cases, in 1964 Dr. Stanley Krippner joined the staff of the newly-funded Dream
Laboratory at the Maimonides Medical Center in Brooklyn. There, in collaboration with
Montague Ullman and a small team including Sol Feldstein, Robert Van de Castle and other
occasional collaborators, he went on to develop what has become a landmark in experimental
parapsychology: a series of studies in dream telepathy, which made use of rank-ordering
techniques by independent judges in order to assess whether a sleeping subject could
successfully perceive imagery transmitted by a sender.
In the prototypical experiment (see Ullman and Krippner, 1973) the subject slept in an isolated
room, while his EEG tracings were monitored by the experimenter in a nearby room. The agent,
whose location varied from 98 feet away to a separate building in later experiments, would
randomly choose an envelope containing one of a pre-selected group of art-prints, then - once
informed by the experimenter that the subject had entered REM sleep - would focus his/her full
attention on trying to transmit that image to the subject. After each REM period, the subject
would be awakened and allowed to tape-record his dream impressions, then was allowed to go
back to sleep. The same target and agent were to be used for the entire night. Once the night's
dreams were transcribed, the transcripts were sent with the entire pool of 12 art-prints to a panel
of three independent judges, who would rank the dream reports for correspondence against all 12
prints, with number 1 for the best match, down to number 12 for the least degree of
correspondence. A similar rank-order matching was performed by the subjects themselves.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
717
Over the course of several years, this protocol was varied to incorporate precognitive function
tests, comparisons between the effect of multiple versus single agents and between
multiple/single targets for a given night, while other experiments studied the impact of targetenhancing, multi-sensory agent "immersion" (such as a combination of visual, auditory and
tactile stimuli) on the success of telepathic transmission. Out of ten formal studies described in
"Dream Telepathy", seven yielded statistically significant results.
This type of rank-order judging has also been used in the context of another well-studied
paranormal function: remote viewing, defined as "the acquisition and description, by mental
means, of information blocked from ordinary perception by distance, shielding or time", has
been the subject of the most extensive government-sponsored psi research program to date (see
1; 2; Targ and Katra, 1998; Radin, 1997; McMoneagle, 1997, 2000, 2002).
Over 24 years, various intelligence-gathering agencies such as the CIA, the Defense Intelligence
Agency, the Army, the Navy and NASA have contributed about 20 million dollars in funding to
test the limits of human remote perception and collect information for their various operations.
Typical examples included the nature of foreign military installations, the location and condition
of kidnap victims, the description of nuclear facilities or nuclear events, surface and atmospheric
characteristics of yet-unvisited planets, etc.
The essential feature of all RV protocols is that the viewer and anyone else who may be present
during the session is completely blind to the nature of the target - which is typically designated
by a nonsensical string of random alpha-numeric characters called the coordinate; under these
conditions, trained viewers produced results in which the overall odds against chance were
10^20 to one (Radin 1997, pp. 101). Even though "blueprint accuracy" is a relatively rare event
even for the top viewers in the world, the results were judged sufficiently valuable to ensure
continued funding from these various agencies over more than two decades (see above
references for a full history, or Sidorov 2003 for a discussion of main RV characteristics).
After 1995, when the CIA decided to discontinue this program following a Congressional
investigation, remote viewing became part of the public domain; while some of the viewers went
on to establish formal teaching programs (with varying degrees of respect for the original
methodology and protocol rigors), a small number of motivated researchers have continued to
develop innovative experimental approaches meant to shed light on the physical mechanisms
that are at work behind this phenomenon (see May & al. 1994; McMoneagle 1997, 2000, 2002;
Swann 1996; 4)
One of the most remarkable observations made by telepathy and remote viewing researchers,
starting with Rene Warcollier at the beginning of last century, is that study participants
sometimes seemed to involuntarily tap into each other's subconscious, retrieving data which had
nothing to do with the intended target (Warcollier 2001; Warcollier 1927, 1928; Targ & Katra
1998; Swann 1996). For example, in "La telepathie experimentale" (Revue Metapsychique,
1926-1927), Warcollier discusses his series of studies with batteries of senders and recipients,
noting that "the most extraordinary observation we have made [under our experimental
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
718
conditions] is that the percipients have very frequently shared identical spontaneous images
(perceived visually or intuitively) whose origin remained unknown."
But such group interference effects are not restricted to anomalous cognition: since 1998 the
Princeton-based Global Consciousness Project, headed by Dr. Roger Nelson, has been involved
in what is probably the largest, most coordinated and innovative PK study ever conducted: using
a synchronized array of over 50 RNGs (random number generators) hosted by labs all over the
surface of the globe, the project members have looked for statistical deviations in the generated
data stream which can be linked with events of global significance - such as the funeral
ceremonies of Princess Diana, New Year's Eve celebrations, World Cup Soccer, or the terrorist
attacks of September 11, 2001 (Nelson & al., 2002). While not every one of the 98 predictions
made as of January 2002 behaved as expected, the composite probability for the whole array of
events was 8.3 x 10^ -8 - a strikingly robust demonstration that the RNG network reacts to major
collective experiences (Nelson, 2002).
But what do all these apparently distinct phenomena have in common, beyond the stigma of
"subjective states" or "paranormal function" imposed on them by the scientific orthodoxy?
Although not evident at first glance, there is a remarkable common feature that emerges from
their study, and it is simply this: that in questioning their underlying mechanism, one is forced,
sooner or later, to recognize the fluid nature of individual boundaries. If one's personality can be
dramatically affected by "memories" which could not have possibly originated in the present
life; if a trained person can successfully remote view complex physical targets, the emotions of
people present at the site, and past or future events including their cognitive context; if our
dream experiences can reflect the contents of another human being's simultaneous circumstances
or deliberate intent; and if our minds can collectively create such a powerful constructive
interference that distant RNGs are capable of detecting it - then how do we decide where one
mind ends and another begins?
Is it reasonable to believe that telepathy, remote viewing, pre-cognition, reincarnation memories
and similar experiences are based on one consciousness mode (non-local in space and time)
while our common, waking mind is the emergent product of brain activity? And if we choose to
believe that all consciousness is non-local - that it can survive separation from bodily functions then what can we conclude about the substrate of our individual memories and the limits of the
self? What is the role of the brain, beyond a local motor control unit? Clinical amnesia cases
suggest that memories can be intactly stored, but non-retrievable. Could the same be one day
extended to a vast range of mental experiences - such as dream material and past life events? If
what we are is dictated by our memories, then how do we draw the line between experiences
acquired via "normal", sensory means, and those we access mentally, such as reincarnation-type
data or the rare but powerful remote viewing bi-location event?
Of course, this is merely a rhetorical question: just as we can temporarily immerse in a book or
film to the point of identifying with the character, we can emerge from the typical remote
viewing experience unscathed, with as strong a sense of identity as ever. The same goes for the
majority of Stevenson's cases, where the child spontaneously and gradually stops talking about
his "other life" around the age of six, as he/she begins to interact intensely with the outside world
and its demands - to the point that these memories fade into oblivion. But the observation needs
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
719
to be made that in both cases it is one and the same mechanism which restores one's sense of
identity - and that mechanism is focus. It is complete focus on a target which allows the remote
viewer to retrieve correct information about it, with nothing but a string of numbers and letters
as a coordinate and the joint intent of the tasker to assign that particular coordinate to the given
target; it is the collective focus of the sender and percipients which allows group telepathy to
work; and it is a powerful emotional experience (which creates its own focal attraction) that
presumably results in mind-matter interactions such as the GCP's sharp statistical deviations, or
the birth defects described by Stevenson.
There is also, from a theoretical point of view, the question of how exactly information is
encoded, or imprinted, into the fabric of reality. Regardless of what we choose to call the
collection of memories produced by Stevenson's children, there is no question that, in the cases
validated by him and others, there is at least proof of anomalous cognition involved. Yet, as he
and others have repeatedly argued (see Becker, 1993), this is no typical psychic ability: these
children have not given any indication that they are able to produce extrasensory information
about subjects other than the personality they claim to be, or show any other aptitude for psychic
functioning.
From a remote viewer's perspective, there is a highly significant phenomenological discrepancy
between the fragmentary, subtle mental impressions that form the typical RV data and the
coherent, controlled retrieval of information that these individuals are capable of - spontaneously
or under questioning. A similar chasm separates the experience of conscious or dream telepathy
from that demonstrated by Stevenson's cases. If both sets of information (those involved in
remote perception and those verified as "reincarnation evidence") require a non-physical
substrate as an intermediary storage medium, why are the latter so much more cohesive?
Finally, Stevenson's case for biological "imprinting" of information on the fetus forces us to reexamine the problem of mind-matter interactions in light of their highly charged emotional
content. As Stevenson has noted, about 35% of children who allege to remember previous lives
present with atypical birthmarks or birth defects which are claimed to correspond to bodily
wounds in the previous personality. From the 210 such cases he has investigated, 43 out of the
49 cases in which a post-mortem report was obtained showed a high concordance between
wounds and birth defects - typically within a 10 square centimeter radius of the same anatomical
location, but often much closer or present at multiple locations, as in the case of bullet entry and
exit points (Stevenson, 1993).
The parapsychology literature is also unanimous in recognizing the importance of emotionallycharged targets in functions like presentiment/precognition (with negative emotions showing by
far more prominence to the percipient's mind). Does powerful emotion bind together cognitive
representations and automatic reactions (including a possibly archaic psi function) in the same
way as the emotional memory shortcut loop studied by neurophysiologists (Chin 1996)? Is this
the basis of karmic doctrine, of belief in the persistence of psychic complexes which are fated to
seek new physical experiences until gradually dissolved by enlightenment?
Regardless of how we choose to interpret Stevenson's data, his evidence should give fresh
impetus to the study of anomalous cognition. While most of the parapsychology literature has
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
720
tended to focus on subject parameters (psychological profile, brain states, etc) it is our belief that
the careful investigation of target characteristics (the type of information that best manifests in
psi function, and how this information packet is organized) has just as much to teach us about
remote perception. It is our hope that this joint discussion may bring to light some novel
perspectives and research possibilities - as well as a deeper understanding of the functional
organization of Global Consciousness.
____________________
PARTICIPANTS
RN: Roger Nelson
SK: Stanley Krippner
JT: Jim Tucker
MG: Mark Germine
CK: Chris King
MP: Matti Pitkanen
GZ: Gerry Zeitlin
Moderator: Lian Sidorov
•
Roger Nelson is the director of the Global Consciousness Project. Until his retirement in
2002, he served as the coordinator of experimental work in the Princeton Engineering
Anomalies Research (PEAR http://www.princeton.edu/~pear/index.html) lab, directed by
Robert Jahn in the department of Mechanical and Aerospace Engineering, School of
Engineering/Applied Science, Princeton University.
•
Stanley Krippner is professor of psychology at Saybrook Graduate School, San
Francisco and a former director of the Kent State University Child Study Center, Kent
OH, and of the Maimonides Medical Center Dream Research Laboratory, Brooklyn NY.
He is a member of the editorial board for the Journal of Indian Psychology and Revista
Argentina de Psicologia Paranormal, and the advisory board for International School for
Psychotherapy, Counseling, and Group Leadership (St. Petersburg) and the Czech
Unitaria (Prague). He holds faculty appointments at the Universidade Holistica
Internacional (Brasilia) and the Instituto de Medicina y Tecnologia Avanzada de la
Conducta (Ciudad Juarez).
•
Jim Tucker is Assistant Professor in the Division of Personality Studies, Department of
Psychiatric Medicine of the University of Virginia (Charlottesville, VA). His research on
cases suggestive of reincarnation has been published in Psychological Reports, The
Journal of Scientific Exploration and The Journal of Psychology & Human Sexuality.
•
Chris King is a senior lecturer in the Department of Mathematics, University of
Auckland, NZ. Publications of interest include: King C.C. 2003 “Chaos, Quantumtransactions and Consciousness: A Biophysical Model of the Intentional Mind”,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
721
NeuroQuantology 1, 129-148. King C. C. 2003 “Biocosmology”, WED Open Peer
Reviewed Monographs 2 1-42.
•
Mark Germine is a clinical psychiatrist with a post-doctoral clinical neuroscience
research fellowship in 1990-1992 at Yale University School of Medicine. He is associate
editor of the journal Dynamical Psychology and a recipient of the American
Psychological Foundation F. J. McGuigan Award for contributions to the understanding
of the human mind.
•
Matti Pitkanen is on the editorial board of JNLRMI and a former professor in the
Department of Physical Sciences, High Energy Physics Division at the University of
Helsinki, Finland.
•
Gerry Zeitlin is a graduate of Cornell University (B.E.E. 1960) and the University of
Colorado (M.S.E.E. 1969). His work in physics and astronomy is outlined online. He
currently runs the Open SETI Initiative.
___________________
Dr. Roger Nelson:
1. Could you share with our readers the origins of the Global Consciousness Project? How was
the idea initially received by the parapsychology community - was the scientific world ready for
it?
RN: Origins go back to philosophical considerations, for example, being impressed by the ideas
of Teilhard de Chardin, presented in The Phenomenon of Man and The Future of Man. In the
early '90's it became possible to do field work with REGs in group situations, and this led to
some prototype, ad hoc experiments with multiple REGs at separated locations: the OJ Simpson
trial, the Gaiamind Meditation, the funeral ceremonies for Princess Diana and Mother Teresa.
This work developed into the idea of a permanent network of continuously recorded REGs
placed around the world in late 1997, and after some months of preparation, the GCP (EGG)
network was in place by August 1998.
Most people in parapsychology were interested, and positive but careful; several became
participant contributors. The consensus, I think, was that this was a good idea even if far out, but
that it had to be done with scientific rigor.
2. What is the rough number and distribution of the GCP random number generators?
RN: There are, as of October 2003, about 60 active eggs in the network. They are distributed as
broadly as we can arrange with volunteer hosts, and we have sites from Alaska to Fiji, in both
hemispheres, all continents but Antarctica, and in most time zones.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
722
3. What is the most sparsely populated area in which you have located a RNG? Have you
noticed any correlations between a region's population density or its degree of media exposure
and the magnitude/temporal onset of the statistical deviation?
RN: I don't know what is the most sparsely populated area -- maybe Alaska? I have not seen
evidence of correlations with population density, and we have not looked at questions like the
local media exposure on individual eggs, except informally. In the coming year we will develop
greater facility to examine questions like that, but they require subsidiary information and
measures that have to be developed. We do not assume that the eggs are affected primarily by
the local environment, though that remains a research question. The evidence points to nonlocal
effects, and toward "relevance" as the more potent manifestation of "distance".
4. Is there any evidence for a "wave of deviations" reflecting spatio-temporally dependent events
such as local New Year celebrations? In other words, are local RNGs more likely to be
influenced by geographically proximal human reactions (i.e. analyses for 1999 Indian elections,
Wien University exams)?
RN: See the previous question. As for New Years, we do signal averaging that simply combines
all time zones to yield a result representing, in effect, a single, synchronous celebration. In this
case, the data from eggs all over the world are used for each sequential midnight. The strong
result is one piece of evidence favoring the notion that the anomalous structuring effect is
nonlocal. Yet we have seen some evidence of stronger deviations in geographically local eggs,
specifically, in the data from September 11 2001 (but note the relevance conundrum.) We can in
principle do an analysis that would test whether the New Year's effect is larger on relatively
local eggs. This is one of the areas we will focus on in the next year of comprehensive analytical
work.
5. Is there any indication, from your preliminary analysis, that some kind of amplification also
occurs at a cognitive level? In other words, have you tried to look for RNG effects in isolated
locations or populations without access to current news? Have you any indication that such
populations might have been cognitively affected by a global tidal wave of psychological
upheaval - the source of which nevertheless remained hidden to these individuals?
RN: While we have not looked for effects on isolated locations as you suggest, there is good
evidence in the data that much or most of what happens in the "global consciousness" is
unconscious. For example, the huge deviations on September 11th 2001 began some hours
before the overt events. I think, by implication, there may indeed be subtle effects of major
global upheavals on people who don't know about the primary source.
6. This might be a stretch - but based on Cleve Backster's well-known work with plant "primary
perception" (Stone 1994, 1995; Jensen 1997) there is reason to hypothesize that large plant
populations might also be capable of an effect on RNGs when exposed to a powerful threat.
Have you ever considered placing a number of RNGs in the vicinity of, say, a forest area
scheduled for controlled burning? It would probably be important, in such a study, to separate
any major human reaction from that of the organisms involved - therefore a controlled fire
would be better suited than a wild one, which can evoke large-scale reactions of fear and loss
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
723
among humans. Along the same line, it might be interesting to test a field RNG's reaction to half
of an animal population when the other one is removed and distantly sacrificed - as might
happen on laboratory subjects or farm animals diagnosed with a contagious disease. According
to a series of preliminary studies published in the July issue of JNL (see Agadjanian, 2003) such
split animal populations appear capable of communicating their experience at least to the point
of stimulating an increased replication rate in the unexposed group. It might therefore be
interesting to note any possible RNG effects from such remote "primary perceptions"... How do
you feel about expanding the GCP paradigm beyond the scope of human consciousness?
RN: The experiments you propose are interesting but out of the line of development of the GCP.
Someone else could use our technology, but we don't plan to go there. Our mission is to develop
and manage a monitor for the globe that might give us insight into subtle manifestations of
events that are important to humans. This is a big enough task to preclude excursions into other
areas that themselves would require serious and ongoing investment to do properly. As for
expanding beyond the scope of human consciousness, it is apparent to me that we have lots to
learn before concluding that what we see in the data is in fact due exclusively to humans. My
guess is there are other sources than the nominal. In one direction, we have to consider the
experimenters; in the other we have to consider the whole universe, animals, trees, and the earth
herself.
7. The September 11, 2001 event was one of the most shocking, reverberating tragedies in recent
memory - and presumably the one with the greatest cultural resonance since the start of the GCP
experiment. Your results demonstrate not only a significant deviation from typical RNG
behavior, but, surprisingly, that this pattern began several hours prior to the onset of the events
(Nelson, 2002; Radin, 2002) Have you noted this type of "pre-sentient" RNG behavior in any
other circumstances - and if so, can you make any observations about the type of event that tends
to trigger it - are major catastrophic occurrences more likely to manifest this pattern than
positive events? What about unscheduled (i.e. earthquakes, deaths) versus scheduled (large
group meditations, New Year Celebrations) events? Does the magnitude (presumably
demonstrating the size of the impact on our collective subconscious) correlate with the onset of
the deviation?
RN: Good questions, and ones that we do have some preliminary experience with. There is a
little evidence that surprise catastrophic events like earthquakes may register a little ahead of the
nominal time. I have not seen any similar suggestive evidence in the scheduled events, but the
question has not been well-defined. Except for September 11, we have not done thorough
assessments, and conclusions are not yet warranted. This topic will be one of several specific
areas we will be addressing in the intense analysis program planned for the next year.
8. It is also very interesting to note, in this context, that the data obtained on Monday, September
10, 2001 by a group of trained remote viewers (the Hawaii Remote Viewing Guild) meeting for
their weekly class was remarkably congruent with the events that were to take place
approximately 7 hours later (see "Migrations into the near future" by Sita Seery in this issue).
How do you try to interpret such "intrusions" of future events into our consciousness?
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
724
RN: I don't try to interpret these descriptions. I find them interesting, but I would have to be
much better educated about the material, the sources and context, before I would feel
comfortable attempting any interpretation.
Dr. Stanley Krippner:
9. Dr. Krippner, in your book Dream Telepathy you conclude that "an important ingredient in the
success of experiments [...] is the use of potent, vivid, emotionally impressive human interest
pictures to which both agent and subject can relate". You have also made the observation that
certain basic themes (for example eating, drinking, or religious themes) tend to come through
more predictably. Have you been able to further differentiate between various classes of targets i.e. are archetypal images, or culturally prominent symbols, more readily transmitted?
SK: No. These are great ideas; we did not have the financial resources to do this, but perhaps
someone will in the future.
10. Have you noticed any "contaminating" elements (information originating from one
participant's personal experience or circumstances, rather than the expected association basin of
the designated target) that seem to inadvertently manifest in other participants' dreams?
SK: Yes. We have discussed this "contamination" in our book and articles. It happened early in
our studies, but did not happen once we took steps to keep the "sender" from reading extraneous
material, etc.
11. In 1971, you attempted an experiment in which the telepathic image was to be transmitted by
approximately 2,000 agents simultaneously. The target slide was "The seven spinal chakras" by
Scralian and was projected on a wall, before a concert audience, with the words "Try using your
ESP to 'send' this picture to Malcolm Bessent. He will try to dream about the picture. Try to
'send it to him. Malcolm Bessent is now at the Maimonides Dream Laboratory in Brooklyn". A
number of clear correspondences (mean score of 83 out of 100) appeared in Bessent's dream that
night, whereas the control subject, whose name and location was not disclosed to the audience,
showed a high correspondence score (96 out of 100) for this image two nights later. Overall,
however, there was no significant improvement in dream correspondence scores with 2,000
agents as opposed to the typical single one.
How do you interpret these findings in light of the purported field effect observed by the Global
Consciousness Project? Do you feel there might be a difference between emotional and symbolic
cognitive interactions at the global level - that perhaps a resonant effect, or constructive
interference, is only possible for the former? Does your body of research support such a
hypothesis - have you noted a difference between the group communication patterns of abstract
versus emotional content?
SK: Here you are asking questions on the basis of one study, a study that did not yield overall
positive results. So to make a conjecture would not be possible.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
725
12. Another one of your experiments (the "Vaughan Study") showed that using the same target
over several nights decreased, rather than increased, the overall correspondence scores. In other
words, the amount of time an agent spent "transmitting" the target image did not result in
improved performance. In your book, you assign this observation to the gradual loss of interest
on the part of the agent, who found herself increasingly bored with the single target.
This is a particularly interesting finding in light of RV performance because it suggests that the
amount of time spent "probing" a target aspect may be less important than the intensity of the
focus with which it is probed (assuming that telepathy and remote viewing share a similar
mechanism, as suggested by Ingo Swann). Somehow, for both sender (target) and percipient,
remote sensing appears to require a critical threshold of intent, which typically seems to undergo
a rapid decay rate once generated - hence the need for persistent re-focusing, re-probing and recueing...
Have you found that particular agent focusing techniques tended to enhance the probability of
successful telepathy? For example, you have noted that a "sensory bombardment" with visual,
auditory and tactile stimuli meant to reinforce a particular idea for the agent (such as "Birds" or
"Painter") appeared to evoke significant dream correspondences in the subjects. How does that
compare with situations in which the agent is simply asked to think of multiple associations for
his target - and do these sensory associations tend to appear in the subject's dream more vividly
or consistently when there is a real multi-sensory immersion on the part of the agent? To
translate this into RV analysis language, do you feel it might be possible to differentiate between
valid remote perception and cognitive contamination among multiple viewers on the basis of
how complex and multi-faceted a piece of data appears across their reports - or do associated,
recalled mental images easily morph into various sensory aspects in your experience?
SK: The pilot study you mention was such a minor attempt that no conclusions can be drawn
from it. Your suggestion to compare abstract vs. emotional content is a good one, and if
someone would like to do it, I would be delighted. The Maimonides dream transcripts were
destroyed (without my permission) and so we can not do it retrospectively. And your other
questions can not be answered because there are not enough data available from the work that
we did.
I must say that these questions are extremely perceptive. If the dream transcripts had not been
destroyed, it would be possible to go back and make a retrospective analysis. All that I have is
the record of judgings that were done and the dates on which the experiments took place. This
enabled Michael Persinger and me to look for geomagnetic correlates with the studies as a whole
and with the subject who spent the most nights in our laboratory. In both analyses we found such
correlates at statistically significant levels (and published the results).
Dr. Jim Tucker
13. Dr. Tucker, you have directly investigated a number of cases suggestive of reincarnation.
How many points of validated evidence do you typically require to consider a case solved, and
what type of evidence do you feel is most persuasive?
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
726
JT: While we have criteria for when to register a case, the determination that a case is solved is
more subjective. Occasionally, a child’s statements need to be compared to the specifics of the
life of more than one deceased individual to see which one is a better match. A case being solved
does not mean that we are convinced that it is a case of reincarnation but rather that the child’s
reported statements appear to correspond to one particular individual.
As for which evidence is most persuasive, that can certainly vary from case to case, but the rare
cases that include written documentation of the child’s statements made before the case was
solved I find hard to dismiss, particularly the ones that include very specific details about the
previous personality.
14. How is your research approach today different from the methods pioneered by Dr.
Stevenson? Which aspects of this phenomenon intrigue you most? What about the theoretical
approach - are there any comparative studies attempting to place such cases within a broader
class of phenomena? How do you see the future evolution of your field?
JT: The basic approach to investigating the cases is the same-trying to document as accurately
as possible what each child said, whether he or she had access to the information through normal
means, the details of the previous personality’s life, etc. Beyond that, as we are getting more and
more of this data in our computer database, we are now able to look more at features of the cases
as a group, so we may be able to get insights that we cannot get from simply looking at
individual cases. Nonetheless, the careful study of strong individual cases remains the backbone
of the work.
One area that intrigues me is that of cases in the West. We have gotten a number of reports of
cases from parents with no previous belief in reincarnation or with a previous distain for the
idea, and while the American cases are weaker that the best of the Asian ones, this may be
because we haven’t collected enough yet to find the really strong ones. If we could find cases
here that were as strong as the best Asian ones, then I think they would have to make an impact
on people’s thinking regarding reincarnation.
For now, the predominant question in the work is whether the cases are evidence of
reincarnation or at least of the ability of young children to have memories of previous lives, and
until we are able to answer that question with reasonable confidence, we will have difficulty
moving the field to other areas. People have asked from time to time, “Why collect more cases?”
but until we’ve collected enough so that we can say with confidence, “Some young children
have memories of previous lives” or “Young children are not capable of remembering previous
lives,” then moving on to other issues is difficult.
15. In a recent JSE paper (Stevenson and Haraldsson, 2003), the authors compare certain
features of reincarnation type cases as documented about one generation apart by two different
investigators. Remarkable in both series is the mean age when the child first began speaking
about his previous life (31 months for IS; 32 months for EH); the mention of the previous
personality's name (in 88%, respectively 63% of the children); the percentage of cases in which
the child mentioned the mode of death (82% for IS; 83% for EH); the proportion of violent
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
727
deaths among these (73% for IS and 80% for EH); and the prevalence of unusual behaviors such
as phobias related to the previous life (typically mode of death), which occurred in 77% of IS's
cases and 42% of EH's cases.
How do these memories typically present, how many specific details tend to be spontaneously
described at one time?
JT: The memories present in different ways. Often, the children are very young when they begin
making a statement here or there, and the statements gradually form a cohesive story. At times,
families have difficulty being certain that a particular statement relates to the previous life that
the child has described, and the children often resist questioning. In other situations, however,
the children come out with the bulk of the story in one sitting and remain very consistent during
any questioning about it.
16. How consistently are the children able to retrieve specific information when prompted to do
so? Is there any qualitative difference you have observed between the way they describe current
life memories and those of the alleged past personality - such as richness of sensory detail, the
speed of information retrieval, logical associations between memories, temporal coherence of
the perspective on a given episode, etc? (This would be particularly interesting to compare with
the usual mode of information retrieval in remote viewing, where the data most typically
manifests as fragmented sensory or conceptual material; and "normal" episodic memories, where
one's mental film remains more or less a replay of the events as perceived at the time.)
JT: Many of the children are not able or at least not willing to answer questions about their
memories. They seem to have to be in the right frame of mind to express them, and this is often
during relaxed times. Certainly, exceptions exist, and some of the children talk about the past
lives on a nearly constant basis. Parents often report that the children are very serious when they
discuss their memories--that their manner is very different from when they are fantasizing. The
memories often seem rather fragmentary, though some of the fragments, of course, are much
bigger than others are. I cannot give a good answer to the question of differences between their
descriptions of current life memories and the past life ones except to say that many show an
intense emotional attachment to the past life ones. That emotion may be quite intermittent, but
the children may cry intensely as they describe missing previous parents or other family
members.
17. Recent brain imaging studies into multiple personality syndrome (MPS) have shown that the
patterns of hippocampus activation (which are associated with the laying down and retrieval of
personal memories) vary markedly between the different personalities. For example, Condie and
Tsai found that when a dominant personality was replaced by a weaker alter, hippocampal
activity died down only to light up again when the dominant personality returned - as if they
both had access to different memory basins. These changes, however, were not observed when
simply "play-acting" a personality shift. It is also interesting to note that the consensus
explanation for MPS involves a defense mechanism against emotional trauma, which scars or
severs natural memory pathways (Carter, 2003).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
728
Has there been any attempt so far to use this type of imaging in order to study children in the act
of recollecting past life memories? Especially in cases where there is a strong behavioral or skilltype effect, one might hypothesize that the past-life, adult memories of the previous personality
might overwhelm the set of memories formed by the child in this life. Were hippocampal
activation patterns to differ in this fashion, we would have not only a further indication that these
personality-centered memories are far more complex than mere imagination, but also a proof
that they affect the very physical foundation of the brain - which would not be surprising, given
Dr. Stevenson's remarkable findings with respect to the high correlations between atypical
birthmarks/birth defects and the validated mode of death in the previous personality (Stevenson,
1993). Indeed, the brain and its activity during fetal development may be an important link in
understanding the impact of these psychic information clusters on the child's somatic evolution.
JT: No functional imaging studies have been done with these children. Logistical difficulties
would have to be overcome-such as having equipment and cases available in the same location,
having the children recall the memories on demand, etc -- but beyond that, we would not know
at this point what to look for. Recent studies in neuropsychology have looked at functional
imaging differences when general subjects recall accurate memories vs. false ones, but at this
point, tests are not available to assess a particular memory in a particular subject.
I would not expect the patterns in these subjects to be the same as the ones with multiple
personality disorder (or dissociative identity disorder, as it is now known). Many of the children
talk about the past life in the past tense; they do not appear to dissociate and “become” the
previous personality.
18. What is the typical age and experience these children seem to recall? Do most of these
alleged past life memories center around a particular age or event, or can the children easily
move along their previous life time-line and produce information on demand? Have you been
able to identify any general patterns - are children most likely to dwell on their routine
environment and habits, or on particularly traumatic events, including death, in their previous
incarnation? Are there particular types of memories, particular sensory modalities (such as
visual, auditory, olfactory, texture) reported more frequently than others? Any particular trends
in "archetypal experiences" - ie., are children more likely to evoke the life of a soldier?, mother?
or leader? And has it been your general experience that these individuals are not aware of events
which occurred between their purported death and their new life?
JT: The children tend to talk about people and events from the end of the previous life, and 75%
of them state the mode of death for the previous personality. Along with that traumatic memory
are more mundane ones, as the children recall various everyday details of the previous life. Most
of the children do not seem able to easily move along their previous life time-line, and many of
those who recall lives as adults appear unable to access early life events at all.
The memories do not appear to involve any particular sensory modalities, but that can be
difficult to judge from the children’s statements. The children do not report “archetypal
experiences” but rather the details of routine lives.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
729
While most of the children do not say anything about events between lives, a few describe
intermission memories. These can involve either memories of events on Earth that occurred after
the death, usually near either the home or the place of death of the previous personality and
occasionally at least partially verifiable, or ones of another realm with spiritual beings.
19. Have you seen cases in which the child confused events in the lives of past relatives or
friends with his own experiences (as the previous personality) - perhaps trying to fit all these
memories into a meaningful pattern, as we do in dreams?
JT: By all appearances, the children report memories from the vantage point of only one
deceased individual. One possible exception is Stevenson’s case in Twenty Cases Suggestive of
Reincarnation of Imad Elawar, who vividly described a fatal accident in which the uncle of the
man eventually identified as the previous personality died, but that is a very complex case.
Otherwise, the details given by the children match the life of the identified previous personalities
and not their relatives. The parents sometimes try to fit the various statements of the children
into a meaningful pattern (as in the case of Imad Elawar when the parents were judged to have
inferred details about the previous life that were not accurate), but when the previous personality
is identified, the statements that are correct are correct for that one individual. Some statements
are incorrect, of course, just as some of our memories of our own childhoods are incorrect.
20. The question I am working toward is whether such memory complexes might in fact linger
in our collective subconscious and be "adopted" by a young child on the basis of some yetunknown predisposing factors. Both Warcollier and Krippner (Warcollier 2001; Ullman and
Krippner, 1973), to mention only two major investigators, have noted that a certain latency
between information transmission and reception is rather common in telepathy - ranging from
minutes to days or even longer; is it conceivable that such information becomes part of our
collective, trans-temporal record and that anyone might be able to tap into it? Is there any
persuasive argument you can invoke for interpreting this validation data (otherwise a spectacular
body of evidence for nonlocal, trans-temporal information access) as proof for reincarnation,
rather than a single-target, recurrent type of anomalous perception? How would you ultimately
differentiate between "reincarnation" and remote "tapping" into the collective unconscious?
JT: Well, depending on how you define “single-target, recurrent type of anomalous perception,”
you might end up with what amounts to being another term for reincarnation, but many of these
cases clearly involve more than just information transmission. The birthmarks, emotions, and
behaviors that accompany the memories all suggest an individual consciousness that has
continued from a previous life rather than adopted memory complexes that have somehow
attached to a young child. A child who cries every day for his previous parents certainly appears
to be an individual who is missing his parents from a previous life rather than a child who has
unknowingly tapped into the collective unconscious. Likewise, the fact that the memories cluster
around items that would have been on the mind of the previous personality at the time of death
suggests that the consciousness has somehow continued from the end of that life, as opposed to a
super-psi explanation that might be expected to include more varied memories.
Two other arguments against the idea of nonlocal information access: as in the case of crying
children, it runs directly opposite to the subjective experiences of the subjects, who believe that
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
730
they are remembering events that they previously experienced in a prior life, and in addition,
almost all of these children show no other paranormal abilities that would predispose them to
being able to access such information.
Joint questions
21. A recent series of independent studies has shown that one's focus, or global brain
configuration, has an unexpected effect on the firing patterns of sensory processing neurons,
starting as early as the bottom of the visual hierarchy (McCrone, 1997). This top-down
modulation runs contrary to everything neurophysiologists traditionally believed about the
emergence of mental processes - but it is not much of a surprise from the empirical perspective
of remote viewing, where the strength and specificity of intent produces data that is highly
specific to particular cues (such as visual, auditory, olfactory, emotional, aesthetic impact, etc).
RV analysis presents a particularly fertile area for studying the way in which information is
decoded by each viewer. Of course, as in psychoanalysis, symbols are highly individualized and
fluctuate with time; the focus also tends to vary, with viewers apparently attracted by different
aspects of the target: some viewers tend to produce very detailed technical data while others are
more sensitive to landscapes or the emotions and personal rapport of humans detected at the
target. Finally, the angle from which a target is "approached" on initial contact, as determined
from the post-session analysis of sketches and visual descriptors, seems to vary considerably
between individual viewers - with some describing the view from overhead while others
approach it from ground level or even the center of the target... This observation, in particular,
seems to hide some important clues about the formalism of data encoding and processing in the
global information space - perhaps analogous to the sensitivity of specialized neurons to
particular lines, angles, directions of movement, etc. (see Diamond & al., 1999)
What, in your opinion, might account for two or more remote viewers seeing the same target
from different perspectives, or "picking up" different conceptual aspects?
RN: Seems likely to be much the same as in ordinary perception, where most who study the
topic agree that it is constructive. We bring to our view of the world the characteristics of the
viewer, biases, experience, motivations, etc. I think we should expect something like that,
perhaps even more pervasively, in remote viewing.
SK: Of course two remote viewers could "pick up" different aspects of the target. Just look at the
data from mainstream psychology, especially that concerning eyewitness reports of crimes and
accidents. People see events through their own lens, and these lens are based on early experience
as well as genetic perceptual differences.
GZ: In addressing this question one must keep in mind that the formal RV protocol is based on a
model of a viewer fixed in the laboratory and recording incoming impressions, not actually
traveling as in the "OOBE" model. Although some RVers occasionally eschew the formal
protocol and undertake a "trip" to the target, we need to assume that this question does not allow
for that, which would actually create a second and very different question.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
731
Thus when this question refers to 'the angle from which a target is "approached" on initial
contact, as determined from the post-session analysis of sketches and visual descriptors', it is
already contradicting the protocol assumed to be in operation during the RV session.
It is impossible, however, to draw an image of the target or to describe its appearance without
interjecting an apparent visual angle, but one must not impute an actual approach from the data.
But a viewing angle does not require an actual approach. One could as well imagine the viewer
had used a powerful telescopic capability that could be used from the viewing position. I
suppose it would be useful to check whether the recorded viewing angle actually matched what
would be seen under those circumstances.
Assuming the answer to that check is "no", then the viewing perspective is just another aspect of
the recording, along with the other conceptual aspects picked up. And that simplifies the
question.
When something is observed or experienced, a conceptual model of the actual thing that it is,
seems to be constructed or encoded by the observer based on the raw sensory data received and
the observer's choices in ordering or prioritizing the data. In the RV situation there is no raw
sensory data input, but all the other faculties of integrating and modeling, whatever they may be,
are there and are used to construct the observer's inner model. We don't know what those
faculties are, and we don't know how or of what the model is "constructed". In fact there is a
deeper mystery here, because the existence of a model implies that sensory organs etc. are used
to view it, and of course this leads to an infinite succession of model making and viewing.
Laughlin, McManus, and d'Aquili in Brain, Symbol, & Experience postulate Conscious Network
(always capitalized) as the ultimate experiencer in the brain, sidestepping the infinite regress of
models viewed by homunculi. But they haven't actually located Conscious Network. It's just
another postulate.
Does the literature on consciousness contain any more satisfactory proposition as to how things
are experienced? Lacking that, my answer to the current question would be that we need to have
a general explanation for conscious experience of ordinary, local objects and events before we
can explain features of the remote viewing process.
MP: That focus would have strong effect on neuronal firing patterns conforms with the
hypothesis that time mirror mechanism is a general mechanism of brain functioning. In this
approach neural firing is preceded by a process, which is much like a desire communicated from
the top of organization downwards and generating lower level desires. This process proceeds
downwards along the hierarchy of magnetic bodies down to the level of sensory organs and from
there to brain and brain and CNS finally respond to the process by generating neural activity
(remember Libet's findings about time delays of consciousness).
That different viewers pick up different conceptual aspects is quite an interesting finding. If the
remote viewer is like a single neuron of a higher level collective self, the personal RV profile
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
732
would be analogous to the specialization of the neuron, and also reflect the "wiring" between the
"neurons" of the multi-brained higher level self.
CK: Actually standard tests of perceptual judgment show that active cognition is able to
determine the mode of perceptual discrimination when different strategies of visual assessment
of the sameness of two stimuli with respect to two differing populations are proposed.
I have a problem with the preponderance of remote viewing as an idea. I want to explain why it
is limited and limiting as a concept. All conscious viewing is essentially remote viewing. Also
remote viewing is an attempt to tame and confine the 'otherness' of psychic consciousness.
Firstly remote viewing tends to assume we have a clairvoyant capacity to se other places and
know the conditions of those places. However this doesn't in any way address the mystery of
intent, the nature of consciousness, or any idea of the after life or disincarnate consciousness.
Evidence that there is a mental plane is little help to us unless we can begin to understand the
"otherness" - the deep and utterly wild differences this 'abyss' might have. Basically we want
remote viewing powers to convince ourselves that life is worth living because it has a
supernatural dimension, but we want it to be tame enough that we don't have our own ideas too
seriously challenged.
Central to this is the failure of remote viewing to address of itself the paradox of intentionality or
how to deal with anticipating reality - not just precognition, but survival through anticipating
change in terms of the quantum realm. This is a similar failing to the initial ideas of morphic
resonance which were primarily spatial without fully addressing the paradoxes time and
intentionality raise about reality. It is only when we begin to consider how present can anticipate
future and what kind of universe it is that permits this that we are beginning to face these
questions.
22. In his work with plant "primary perception", Cleve Backster has repeatedly noted that his
subjects only seemed to respond to authentic, spontaneous emotions: for example, a sincere
impulse to burn the plant would evoke a marked electrophysiological response, but only
pretending to did not (Stone 1994, 1995; Jensen 1997). Furthermore, when he correlated his outof-laboratory experiences with the polygraph tracings of the experimental plants or cells, he
consistently found the significant deviations to coincide with emotional reactions - whereas
neutral conversation and events did not produce any remarkable signatures.
How do you interpret these results, especially in light of the preceding discussion? Why would
the same mental image (i.e. burning a leaf) only evoke a response when genuine emotion (such
as aggression) accompanied it?
RN: How could it be otherwise? To the extent there is plant perception, or anomalous perception
of any kind, it seems sensible to expect it to penetrate facade and deception as easily as it
penetrates the barriers of locality and missing physical medium. In other words, if we are talking
about a truly "psychic" phenomenon, we must expect it to operate transparently in a transparent
world.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
733
SK: I can not comment on this question because I do not consider Backster's work sufficiently
well established. The experiments you cite have never been published in a refereed scientific
journal.
MP: Authentic emotions are necessary if sharing of mental images is involved.
CK: If you are talking mental action you have to explain why you think an image of burning will
be transmitted but lethal intent or the sense of deceit in cheating will not. Isn't the raw emotion
simpler, more direct an organismic reality than a complex image of fire?
23. One alternative to the hypothesis of reincarnation would be that past-life memories are
simply association basins strengthened by a powerful emotional event - such as when people
report that "their life flashed before their eyes" . If there is a non-physical information substrate
accounting for anomalous, non-local perception, then one might surmise that a group of trained
remote viewers blindly targeting such a case would be able to produce more cohesive data about
the "past-life impressions" of a very young child than about his recent memories. Alternatively,
blind RV targeting of the previous personality (once a reasonable identification has been made
by the field researcher) could give us a clue about which events in his/her life are most salient to
remote perception. Comparing these three sets of data (the child's, the viewers' and the objective
history of the previous personality) might yield valuable insights into how information is
encoded and accessed nonlocally.
How do you feel about such an experiment - do you think there may be anything worth learning
from it, and would it be ethical, in your opinion?
SK: The proposed experiment would, indeed, produce valuable information. But it would be
expensive. Who would fund it?
JT: To repeat, the past-life memory cases involve a lot more than just information, and any
explanation that starts with an information transfer to explain the other features, the birthmarks,
emotions, and behaviors, becomes rather convoluted. Having remote viewers attempt to access
facts from the previous life might be interesting, but I'm not sure what it would really tell us.
Similarly, having mediums try to contact the previous personality could be very interesting, but
interpreting the results might be challenging.
GZ: Lian has clarified the first part of this question, up to the word "Alternatively", for me
(personal communication).
· The connection of "a powerful emotional event" with the "life flash" experience is a reference
to the commonly-reported review experienced at the time of a major life-threatening event or
NDE, which are presumed to be powerful emotional events.
· "Case" refers to Ian Stevenson's use of the term, as in "cases suggestive of reincarnation". This
does not imply, as I understand it, that the flash life review itself qualifies the case as being
suggestive of reincarnation, and in fact I don't believe Lian is suggesting using subjects who
have had the life flash experience. The suggestion is simply to remote-view "cases suggestive of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
734
reincarnation", and the purpose would be to determine if information could be developed by RV
that could be attributed to previous lives.
Lian asked:
Why would the proposition of a non-physical substrate lead one to surmise that RV would
produce this particular result, and why is this limited to a case of a very young child? Given that
very young children are more likely to have "past-life impressions", I still don't see why data
about those past-life impressions should be more cohesive than recent memories if there is a
non-physical substrate.
Lian explained that most RV theories invoke something like a pure information substrate, and
reincarnation research suggests the same. Thus past-life memories might be susceptible to
probing through RV. Since the bulk of past-life memories would have been recorded by the past
personality in a mature state of development, these memories might be more cohesive than the
present-life memories of a 3-4 year-old child, and in fact might overwhelm them as well. RV of
the previous life could perhaps be used to check on these memories. If the match was not good,
various other explanations for them could be considered.
As to how I would feel about an experiment along the lines of the first part of this question as
clarified, I think that the idea is generally logical, but there must be a well-thought-out
experimental design; otherwise the results could be rather chaotic. The design should clearly
state the issue that the experiment is intended to elucidate. Presumably the point of the
experiment is to remote-view the presumed past life in order to shed light on the hypothesis that
the subjects' memories are indeed due to a connection with a past-life personality (via the
substrate). Is the relative cohesiveness of two sets of memories (present-life and "past")
significant and will the differences in cohesiveness themselves be used to select subjects for the
experiment? Will a standard RV judging protocol be used, and is it clear how the results will be
statistically evaluated? Will the aforementioned cohesiveness enter into the evaluation in some
way? (I would expect not, but this question needs to be asked.)
The alternative proposed experiment is intended to reveal information about the nature and
functioning of the "substrate" or other means of accessing nonlocal information. This one is also
interesting, but appears to be less amenable to formal design and more of an exploration.
Insights gained from this experiment could then lead into a more structured follow-up study to
either test the validity of the insights or to develop further detail.
Now as to the ethics - and perhaps this should have been addressed first - I cannot see how these
experiments could be considered ethical. Young children are not competent to decide whether or
not to enter into such experiments. In matters of health and other vital issues, decisions are
expected to be made by the parents. However, these proposed experiments are not vital to the
child's well-being, and in fact might well prove to be damaging in some way, such as by
revealing information that would actually be hurtful. In this case I cannot support letting the
decision as to whether to participate be made by the parents, the child, or by anyone else.
In other words, these experiments are unethical and should not be performed.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | July 2012 | Vol. 3 | Issue 6 | pp. 715-735
Miller, I., Remote Mental Interactions: A Review of Theoretical Modeling of Psychophysical Anomalies Part 3
735
MP: The experiment would be very interesting. A skeptic would probably argue that the
experiment is quite too complex. Concerning the proposed interpretation of re-incarnation:
normal personal identity could also be seen as being determined by the mental images that I
have/share. For instance, the inhabitant of the TGD Universe identifies himself with his physical
body during his biological life and with his magnetic body after his biological death. The
personal evolution from highly ego-centered consciousness of a teenager could be seen as a
process in which the sharing of mental images gradually delocalizes the contents of
consciousness and ego centeredness gradually disappears.
CK: The sheaf of incarnation is the unraveling of reincarnation and the afterlife. I am a sheaf of
incarnation containing threads of the incarnate in many beings. There is for example no need for
me to be reincarnated nor to have past lives to be a living manifestation of another from another
time. I may even be born on the epiphany, as I am, and yet not simply a reincarnation of Jesus
while at the same time here to unveil the reunion. Furthermore we may each exist at the crest of
full organismic consciousness only in the biological frame and still consciousness is eternal from
alpha to omega and we are yet witness to the totality in this life.
Again the problem is one of taming the wilderness.
I'm not remote viewing the Messiah - rather I am viewing reality remotely as I stand here in the
living flesh - it's a question of being one with my own cubic centimeter of chance.
[References at end of Part 4]
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1149
Exploration
A Cosmogonic Model of Human Consciousness: Part I
Claudio Messori*
ABSTRACT
This series of articles present a physicalist account on the origin of human consciousness. What
is presented is a cosmogonic model based on the centrality of Tension assumed as an intrinsic
and irreducible ontological presupposition associated with a pre-energetic undifferentiated and
totipotent proto-dynamic principle (dynamis), whose differentiation gives birth to a space-time
system of correlative interactions between physical objects denominated differentiated tensorial
fractals (or tangent tensions) and undifferentiated tensorial fractals (or qualia). To describe the
structure and dynamics that qualify the fundamental space-time dimension we can make use of
the holographic principle, fractal self-similarity and the role reserved to the twisting moment
(torque) in certain dual torus topology. In this light, human consciousness is recognized as the
ecological and neuropsychological result obtained from the joint action realized through the
holographic module, between poietic function, syntropic function and mnemotropic function
the meanings of which shall be defined in the articles.
Part I of this series of articles contain: Preliminary Remarks; and 1. Introduction: The problem
of consciousness.
Key words: consciousness, states of consciousness, image-making, qualia, psychism, autoorganization, strange holographic attractor, syntropy, entropy, negentropy, mnemotropy,
mnemopoiesis, confinement process, dynamis, holographic-fractal space-time, event-horizon,
toroid-poloid, tension, torque, Coriolis force, spin-internal motion.
Dedicated to the Jungian unus mundus
Preliminary Remarks
95% of our Universe escapes our knowledge. Aurélien Benoit-Lévy
A growing capacity to investigate and manipulate the intimate structure of animate and
inanimate matter, as well as:
-
the fetishist cult of the hyper-technological tool and the power gained from possessing it
and being possessed by it;
the use of scientific knowhow and research which is increasingly unbiased and
progressively further from the idea of knowledge as a resource and collective asset;
the pervasive and seductive power of the commercial offer with its promises of
gratification and freedom from the burden of frustrations that lurk in the real world;
the unyielding acceleration towards computerization of data-sharing and
communication;
*
Corresponding author: Claudio Messori, Independent Researcher, Str. Villaggio Prinzera 1, Fraz. Boschi
di Bardone, Terenzo 43040, Italy. Phone: +393282876077; e-mail: messori.claudio@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
-
1150
the consolidation of markets based round organ transplants, genetic engineering,
neuroengineering and bio-nanotechnologies;
the appearance on the world markets of hundreds of millions of aspiring
consumers/producers of articles for all tastes and all ages;
the destabilizing effect produced on individual and collective identity by enormous
domestic and international migratory flows of have-nots summoned by free market
globalization,
seem to be laying the path to the introduction of a human identity model that is gradually more
uncertain and disconnected from the natural body, sensitive-thinking-vulnerable-perishableunique-finite, and increasingly fascinated by the idea of a virtual body, computerizedcybernetic-invulnerable-artificial-modifiable-transparent.
The successes obtained by the significant scientific and technological evolution which, over the
last fifty years has allowed the investigation, deciphering (circa 5%) and manipulation of the
intimate structure of the constituent elements that lie at the basis of the physical and biological
reality we form part of (the unknown portion amounting to 95% of their overall dynamic would
suggest considering this 5% as a sufficient percentage for the formulation of partial hypotheses
to be applied with caution), have made it increasingly problematic and uncertain to understand
what is being observed, increasingly obvious the limit of knowledge acquired, and increasingly
partial and controversial the answers to the myriad questions that arise when seeking to
forecast the consequences, above all in the medium- to long-term, resulting from the attempt to
manipulate what we can only catch a glimpse of.
In the medical/health environment these successes are translated into a growing capacity to
save human lives, in acting on the person and his/her vital functions to guarantee survival, even
when this leads to a lasting state of suspension of consciousness (coma), which often leads to a
total or semi-total dependence on doctor/nurse monitoring, daily pharmacological
administration, the adoption of medical devices which allow artificial survival, and on a source
of continuous socio-health and family assistance, where necessary for extended periods of time,
even years or decades, with profound repercussions on the quality of life of the person being
assisted and the life of his/her family members.
In other sectors of knowledge and knowhow these successes have laid the path to cloning, the
transplantation of organs, the development of sophisticated neuroinformatics devices plus a
new generation of computers (quantum-bit), to artificial insemination and, simultaneously, to a
flourishing illicit trafficking in clones, gametes, placentas and, sadly, even human beings;
babies, women and men recruited from situations of extreme poverty and used to satisfy the
burgeoning request for biological components.
Meanwhile, in the military and aerospace sectors, these successes are generating new security
systems, new devices of dissuasion and persuasion, new weapons and new forms of military
equipment destined to revolutionize the equilibrium of the forces at play in resolving domestic
and international conflicts.
We are faced by a rapid, profound scientific, technological, social, religious and cultural
transformation abounding in promises but also closely packed with unknown factors, a
transformation that seems to succumb to rules dictated by a world of national and
supernational finance focussing on speculation to the advantage of the few and damage to the
many.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1151
Precisely because of this high-speed, hi-tech transformation, the necessity to establish what
should be understood by consciousness and by state of consciousness is no longer a need but a
mandatory objective.
How and from what did our Energy Universe originate? Is the energy dimension all there is, or
can we hypothesize a fundamental pre-energy physical reality? And if this does exist, what does
it consist of, how can we describe it, and what relationships does it entertain with the Energy
Universe?
In anthropopoietic mapping of phenomenological reality there is a phenomenon known as
individual consciousness linked to a universal consciousness phenomenon: is it correct to speak
of consciousness outside of its anthropological dimension? Is it correct to refer to it as an
epigenetic phenomenon that emerges from the neuropsychological dimension assumed by the
same dynamics that preside over the structuring, organization and development of every other
physical phenomenon?
In this series of articles, the poietic function of auto-organization and the syntropic function of
attractors are assumed as fundamental but inadequate presuppositions to describe
phenomenological genesis and becoming. The missing link to complete their role is identified in
memory processes, whose dynamics are exemplified through the Twisted-Pinched
Hysteresis Loop model, and indicated as the mnemotropic function. The result of the
joint action which by means of the holographic module is realized between poietic function,
syntropic function and mnemotropic function is equivalent to an a-intentional articulate and
complex ordering function which is defined as mnemopoiesis (MOPS).
Hence what is presented is a cosmogonic model based on the centrality of Tension assumed as
an intrinsic and irreducible ontological presupposition associated with a pre-energetic
undifferentiated and totipotent proto-dynamic principle (dynamis), whose differentiation
gives birth to a space-time system of correlative interactions between mass and energy-free
physical objects denominated differentiated tensorial fractals (or tangent tensions) and
undifferentiated tensorial fractals (or qualia). To describe the structure and dynamics that
qualify the fundamental space-time dimension we can make use of the holographic principle,
fractal self-similarity and the role reserved to the twisting moment (torque) in HarameinRauscher U4 Space-time Dual Torus Topology. Description of the factors that determine the
transitions from one physical dimension to another (relativistic dimension, quantum
dimension, hyper and middle dimensions) is provided in terms of breaking symmetry and
explained as a re-distribution of non-linear relationships between monopolar tensorial
potential, dipolar tensorial potential, and kinetic potential.
Human consciousness is stripped of its anthropocentric requisites and isolated from its
anthropopoietic genesis to be recognized as the ecological and neuropsychological result
obtained from the joint action realized through the holographic module, between poietic
function, syntropic function and mnemotropic function. In this light what we are defining as
consciousness constitutes a particular case of mnemopoiesis, a particular case whose specific
a-intentional articulate and complex ordering function is in no way transferable outside of
the phylogenetic and anthropological collocation of the biological system homo.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1152
1. Introduction: The problem of consciousness
We have seen that there where science has achieved its greatest conquests, the spirit
has received from nature what it itself had lent: from the shores of the unknown we
discovered a mysterious footprint. We have excogitated one profound theory after
another to be able to gaze intently on its origin. In the end we were able to reconstruct
the beingfrom which the footprint comes. And here we are: that footprint is ourselves.
Arthur Eddington
Is it legitimate to state that human consciousness, or, more exactly, Homo Sapiens’
consciousness, represents the expression of a universal-immanent psycho-physical
phenomenon it too declinable as consciousness1 in turn generated by a principle of original
consciousness or proto-consciousness? (Alfred North Whitehead)
In view of the distinctive and peculiar neurological, psychological and neuropsychological
implications that accompany it2 and in view of the more or less anthropomorphic cultural and
religious contents communicated and evoked by the term “consciousness”, it would be
preferable to avoid treating human consciousness as the expression of a universal-immanent
psycho-physical phenomenon declinable as consciousness in turn generated by a principle of
original consciousness or proto-consciousness.
Nonetheless, while awaiting to enrich our lexicon with a more appropriate and less
compromized term than that of consciousness, a term which from the next paragraph I shall call
mnemopoiesis (Mnem- memory, O- holographic, Poie- poietic, Sis- syntropic; acronym
MOPS), let’s suppose that this extensive use of the term consciousness can be considered
admissible, with reserve.
In this case: human consciousness is neither the universal-immanent psychophysical
phenomenon which it forms part of (a Chinese aphorism says: a white horse is not horse) nor
the principle of original consciousness or proto-consciousness from which both would come
from, nor does it represent them but is merely the expression of a correlative, stationary and
particular configuration (neuro-psycho-logical), more unique than rare W. F. Nietzsche would
say, between physical mass and energy-free objects belonging to the territory of psychism [Carl
Gustav Jung], or the holo-fractal tensorial dimension [Messori 2011][1], known as qualia
[Alfred North Whitehead] and images [Messori, 2011], and neurological processes in-formed by
the convergent action of the proto-consciousness, which human consciousness would derive
from and with which it would share, together with the immanent psychophysical phenomenon
it forms part of, certain fundamental properties.
What would these properties be? What would the common factors be between human
consciousness, the universal-immanent psychophysical phenomenon and the principle of
original consciousness or proto-consciousness? What would produce a relationship between
them and render them comparable?
1 See: Hameroff S., What is Consciousness?
http://www.quantumconsciousness.org/presentations/whatisconsciousness.html
2 See: Morin A., Levels of consciousness and self-awareness: A comparison and integration of
various views, http://www.societyofrobots.com/robottheory/self-awareness_review.pdf;
Schwartz J.M., Stapp H.P., Beauregard M., Quantum Physics in Neuroscience and Psychology: a
Neurophysical Model of Mind/Brain Interaction: http://www-physics.lbl.gov/~stapp/PTB6.pdf
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1153
We shall exclude from our investigation just how much human too human there is in the
current meaning of consciousness: sensation, perception, willpower, intention, ambition,
awareness, discernment, sentiment, desire, the rational and irrational, thought, attention,
volitionality, acting with cognition of cause and effect (cognitive thought), the capacity to
foresee and resolve problems, self-awareness, and, the most important thing of all, being human
in flesh and bone without which human consciousness would be nothing more than pure
abstraction3.
And what remains?
What remains is the historical-cultural-religious environment which forms the background to
the first 800 years of domain and expansionism before the Roman Republic and then the
Roman Empire on the Euro-Mediterranean area and the near East4, an environment which,
3 According
to Francisco Varela: Basically when I say that consciousness is lived experience I am
not speaking of something that exists only in my head. I cannot begin looking for consciousness by
starting from a section of cerebral circuitry. Consciousness does not belong, so to speak, to a
group of neurons: it belongs to an organism, to a human being, to an action that one is living.
That really isn't the same thing. (….) Basically, consciousness is an emergence which requires the
existence of these three phenomena or cycles: with the body, with the world and with others. The
phenomena of consciousness can exist only within the cycle, in the de-centralization that it
involves. In all this the brain evidently has a central role, because it is the enabling condition,
the condition that makes everything else possible.(….) The amazing thing about the brain is that it
permits, for example, the sensory-motor co-ordination of the whole interaction, the hormonal
regulation which ensures the maintenance of corporeal integrity, and so on, but the notion of
neuronal correlates of consciousness as such is, to use the words of Alfred Norton Whitehead,
“an inopportune concretization”. (Francisco Varela, Consciousness in the Neurosciences,
http://www.psychomedia.it/jep/number14/varela.htm)
4
Eight hundred years from 509 BC, the date of the founding of the Roman Republic, until the
Council of Nicaea 325 AD. In particular:
-
between the middle and the end of the 2 n d Millennium BC the Semite peoples of the Sinai
invented alphabetic writing (Sinaitic inscriptions), applying the principle of acrophony to
the ideographic value of the signs in their mother tongue, Akkadian-Sumerian, the mother
tongue lingua of the Assyrians and Babylonians;
-
later, the Phoenicians, who maintained close relations with the Jews, adopted and modified
the Semitic invention to create the Phoenician alphabet (funerary inscriptions of King
Hiram, around 13 t h C BC.);
-
towards the end of the 9 t h C BC, the Greeks adopted and modified the Phoenician alphabet;
from the Greek alphabet were to come all the western alphabets (Latin, Italic, Etruscan and
probably the Iberian);
-
between the 7 t h and 6 t h C BC, under siege by the Assyrian empire, the Kingdom of Judah,
with its capital at Jerusalem, became the first kingdom in history to venerate one god in one
temple, the Abrahamite Yahweh, He Who Is, a divine figure inspired by Īśvara, one of the
many names given to Krishna (a divine figure who inspired the hierophany of Chris-t-os,
which comes from the ancient Greek chrisos, gold, by interposing the letter T or the Tau of
the Egyptian, Phoenician and Hebrew alphabets, symbol of death and resurrection −
distinctive characteristics of Krishna − of the solar cross of light and the musical scale sol,
la, re) in turn one of the many names, the 57 t h , given to Vishnu, a Vedic masculine divinity,
one of the personifications of Tat];
-
between the 8 t h and 7 t h C BC were born in Greece the polis system and in Rome the
monarchic-senatorial system, systems to govern power where: (the speech) became the
political instrument par excellence, the key to every State authority, the means of
command and dominium over others, (where) language is no longer the ritual word, the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1154
with the advent of the Christian Era, in particular with the Nicene version of the New
Testament, would give birth to the word consciousness (a term which has no equivalent
outside the territorial and temporal extension of this historical-cultural-religious environment).
Consciousness represents the compromise reached by the theological/theoretical synthesis
which since the dawn of the first millennium attempted to re-harmonize, for the sake of
Imperial stability, three contemporary visions of the World, linked to as many cosmogonic and
social interpretations and as many versions of the word anima5 (ànemos/pneuma-ruahanimus, all terms translatable by wind, gust of air, breath and all inspired by the breath of
Brahman from Vedic cosmogony):
i)
ii)
iii)
the Hellenistic Platonic-Aristotelian version,
the Old Testament Hebrew version,
and the New Testament Judaic-Christian version.
The object of the dispute is not so much the meaning to be attributed to anima as the
hierarchical position to be accorded to the two separate animas that make it up.
In fact, the anima possesses an intrinsically ambivalent character, cosmic-terrestrial/
unmanifest-manifest6, i.e. it possesses two separate animas:
i)
one of the two animas is immanent, conditioned by events, and knows or
understands (direct object) through the combined and simultaneous knowing of
three hierarchically ordered activities which are, from the lowest to the highest, bioenergetic activity (genetic-vegetative), neuro-sensorial activity (animal) and
psycho-perceptive/proto-cognitive/cognitive activity (human), the latter generally
right formula, but contradictory debate, discussion, argumentation [in: Pierre Vernant,
The Origins of Greek Thought];
-
between the 6 t h and 5 t h C BC the Pre-Socratics decided to make their knowledge public via
writing, and adopted writing as a literary means (Anaximenes, Pherecydes and Heraclitus
were the first to introduce this custom), thereby interrupting the purely oral transmission of
knowledge;
-
from the 1 s t C BC there was a transition from the pre-Christian religious cults, in particular
Greco-Roman and pagan in general, up to the Nicaean version (Council of Nicaea, 325AD) of
Judaic-Christian monotheism.
(Translation by Alex Ghillan) : The anima is the personification of the unconscious. The
determinant force that operates at these depths represent by the anima, that is it creates symbols,
images, to itself it is only an image. In these images it transmits to the consciousness the strength
of the unconscious. Hence the anima is an organ that contains and transmits, an organ of
perception for unconscious contents. The anima perceives symbols. But these symbols are energies
(forces) formed, i.e. determinant ideas that have a value that is at the same time intellectual and
affectionate.(In: Jung C.G., Psychological Types, Newton Compton Editori, 1993, pagg. 201-202)
5
6 For further information:
-
Desideri F., L’ascolto della coscienza, Feltrinelli Editore, Milano, Italy, 1998
Messori C., Il Sole e la Luna. Sulla natura dei symbols e della mente umana, Federico
Ceratti Editore, Milano, Italy, 2000
Messori C., Le metamorfosi della meraviglia. I percorsi della conoscenza dall’età del
Bronzo ad oggi, Maremmi Editore, Firenze, Italy, 2004
Napolitani D., Identità, Alterità, Culture, at:
http://www.rivistacomprendre.org/allegati/XIX.Napolitani.pdf
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1155
identified with the visual perception organ; this belongs to the territory of Being and
the Born, and corresponds to Prakriti in the Sankhya system of Hindu doctrine;
ii)
the other is transcendent, unconditioned by events, and knows or understands
(locative complement of place) without recourse to any interior or exterior means of
investigation, frequently indicated as the other eye that “sees without seeing”
(equivalent to wu-wei, “acting without acting”, of Taoist doctrine); a direct
emanation of Non-Being and the Non-Born, corresponding to Purusha.
The theological/theoretical compromise is reached when it is agreed to maintain the name of
anima in reference to the cosmic-unmanifest character of the transcendentunconditioned anima (equivalent to the Immobile Motor of Aristotelian descent), while the
terrestrial-manifest character of the immanent-conditioned anima is assigned the name of
consciousness (the mirror of the anima).
The word consciousness, therefore, cannot be separated from the historical-culturalreligious womb that gave birth to it nor can it be separated from the intrinsic ambivalence of the
anima-word, just as neither can be separated from the role assumed by the logos-word in
the social environment and the Logos-Word made Man in the religious environment.
Nonetheless, the semantic evolution of the word consciousness, and before it the triad
ànemos/pneuma-ruah-animus, does not stop at the ordering function performed in the sociocultural field by the oral word and the spoken word (logos), not does it stop at the ordering
function of the divine Word (Logos) sculpted in letters of fire on Moses’ tablets (XIII century
BC), but breaks through the eastern borders of the Roman Empire until re-cognizing its origins
in the doctrine of the Vedas (pneuma-ruah-anima-consciousness are three versions of the
prana of Hindu doctrine; just as the Father-Son-Holy Ghost Trinity is a slighter version of the
Brahma-Vishnu-Shiva Trimurti) sunken in the Neolithic pictorial production of spiral motifs,
Palaeolithic petroglyphs (incisions in stone) and in the late-Palaeolithic pre-rational and
apotropaic use of shamanic chanting and the magic word (whose evolution would lead to
divinatory formulae, sacred chants, prayer and poetry), the magic of the word that from the
Upper Palaeolithic onwards would occupy and continue and to occupy a deservedly central
place (even if subject to progressive removal) in all human communities.
Prana-pneuma-ruah-anima-consciousness-divine breath (whether of Brahma or Yahweh the
substance changes little) indicate a single thing, namely the Sound-Breath that became
Speech-Voice, they are symbol-words (for some time debased to metaphors) custodians of the
dramatic passage (datable to a span of time from around 100 thousand to 10 thousand years
ago) between a humanity that did not know communication through codified oral language and
a humanity that slowly discovered to be such through the Speech that gives a voice to the
anthropopoietic process, since from that moment on it would be through recourse to the use of
the speech which in-forms, that the World would take form!
The introduction of oral language in human communication would have an enormous impact on
the life of human communities and on the embryonic state of their cultural production. One of
the most important consequences would be the competitive relationship that came to be
created, still existing, between the oropharyngeal cavity as an anatomical instrument for the
gestation-generation of articulate sounds and the uterine cavity as an anatomical tool for the
gestation-generation of life [Messori, 2012].
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1156
In fact, the most revolutionary invention of all time, verbal language, from the apotropaic use
of the magic speech (which allows physical planes that differ from one another to be related)
until the gradual social use of the oral and written speech (which, by allowing different
individuals and communities to relate to one another catalyses the making of culture), laid the
foundations for the male sex to subjugate the female sex:
-
the function of naming things as an act of legitimizing reality and the function of giving a
unique name to each individual (semantic baptism) as an initiatory act that assigns an
individual a new value of reality, places the oral-laryngeal generatrix power (which
gives voice to the breath that becomes speech) in open opposition with the generatrix
power of the female uterus (which gives life to the breath that becomes the human
being).
In the meeting/clash between the oral-laryngeal cavity that generates the World and the
uterine cavity that generates life there is room for both the idea of the fecundating
sound and the fecundated anima, and the idea of an anima disposed to listening and
its “soul-mate” involved in communication.
One lives in a Mythical Time, the other lives in a Physical Time:
-
-
the Mythical Time of the transcendent anima becomes a psychic territory (the heart
for the Hebrews and the intellect for the neo-Platonists) and a temple for Sound
(emanation of the Primordial Sound OM-AUM-AMEN that generates the World) which
with different discontinuous rhythms is transformed into forms of manifestation and
lasts throughout their transformation and impermanence (transformed without being
transformed)7 ;
the Physical Time of the immanent anima becomes a psychic territory and home8 to
the premeditated articulate Sound that traverses the semantic baptism assigns a new
value of reality to reality itself, in-forming the progress of humane relationships and
participating in their vicissitudes and transitory nature (transformed with
transformation).
7 Thus Heraclitus:
Immortals are mortal, mortals immortal,
living in their death and dying in their life.
To those entering the same river,
other and still other waters flow.
Into the same river we both step and do not step.
We both are and are not.
(Credit: HERACLITUS OF EPHESUS, The G.W.T. Patrick translation,
http://www.classicpersuasion.org/pw/heraclitus/herpate.htm )
8 This house is the human body where, in the neo-Platonic-gnostic-alchemical vision, the immanent
anima-conditioned consciousness emerges from the degree of synergy that exists between the
three levels of consciousness of which we said earlier, correspond to as many chakras (resonance
cavities) and as many relatively autonomous independent vital functions governed by as many
centres: one centre for the bio-energetic function (genetic-vegetative) located in the sacral plexus
(corresponding to the first chakra, Muladhara), one centre for the neuro-sensorial function
(animal) located in the solar plexus (corresponding to the third chakra, Manipura) and one centre
for the psycho-perceptive/proto-cognitive/cognitive function (human) located in the pair
(corresponding to the sixth chakra, Ajina) of the pineal or epyphisis gland/pituitary or hypophisis
gland.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1157
Heraclitus’ incipit panta chorei kai ouden menei (Everything flows and nothing abides)
stigmatizes this flowing of the transitory nature of things and the World but at the same time,
by naming it, embraces it, i.e. does not take flight (consciously?) in the recourse to use of the
speech which in-forms by embracing, that the World takes form.
Through the Breath-Sound-Speech, through its magical and mysterious power, through its
ordering function, its power to give form (Logos-Consciousness) to the formless (ChaosUnconsciousness9) and the power to give voice (logos-life) to silence (chaos-death), the World
ceases to be merely lived to also become interpreted. With the troubling re-birth in the womb of
Breath-Sound-Speech humanity thereby sees itself forced to look at itself in its not being the
World, but only part of it, forced to give some sense to the painful and never completely
resolved detachment from the belly of the Great Mother Earth. And it is here in the excruciating
attempt to sew together the wound resulting from the estrangement from the Maternal Breath
that the human being finds refuge in the archetypical triad which forms the basis of all internal
representations of external reality, whether pre-rational and pre-verbal, or rational and verbal:
-
from this point on, its place in the World would be between Earth and Sky, an elective
agent of connection (medium) between its own image reflected by the mirror of the
Earth’s anima and its own image reflected by the mirror of Sky’s anima...... each with its
own quota of consciousness10.
9 (Translation by Alex Ghillan): The unconscious, as historical background of the psyche, contains,
in a concentrated form, the entire series of engrams that have conditioned the current psychic
structure from the dawn of time. The engrams are none other than functional traces, signaling in
which way the human psyche has functioned, on average and with the maximum frequency and
intensity. These functional engrams, are represented as images and mythological motifs, that
appear in part identical, in part very similar, in all peoples, and it is easy to point them out even
in the unconscious material of modern man. Therefore it is logical that among the contents of the
unconscious, as well as the sublime images that have always accompanied man on the road of life,
there are also traits or elements that are expressly animal-like. (In: C. G. Jung, Tipi psicologici,
Newton Compton Editori, Italia, 1993, pag. 140)
10 In this reflective relationship is summarized the identity of human psychological birth [Messori
2011, 2012], its potency-dynamis being correlated to action-energheia, its giving of itself as a
presupposition of possibility, a possibility that makes it inevitabile to leave the relationship of
continuity with the World, a relationship which, as is true for every other animal maintains the
human being in a dimension of in-fusion-ante-rem with the Great Mother Earth, to enter the
dimension of detachment from it, in a relationship of contiguity brimming with unknowns and
hence tragic.
A tragicalness that we discover expressed in the myth of Oedipus, of which M. Graves gives us the
following version (translation by Alex Ghillan): Narcissus was marked, in his short life, by the
maternal intentionality which the myth wishes modulated in Tiresias’ warning (“Your son will
live until he knows himself”, which means “until he stops nestling in the conscious
womb of you, his mother”) and, true to this “norm”, he avoided any relationship, keeping
himself to a solitude that we could define as “autistic”. Until the day when, gazing at his reflection
in a pond, as was his wont, he saw it rippling thanks to a spiteful puff of air from Zephyrus, the
spring wind, and so saw his image in the water disappear: no longer, in this image, a Narcissus
reflecting his existential condition of a oneness with the maternal intentionality, but, all of a
sudden, a reflective him in his own autonomy, in his self-knowledge emerging from the norm
that had led him to this point. The unbearable distress due to this laceration led him to stab
himself to death. [In: D. Napolitani, Identità, Alterità, Culture,
http://www.rivistacomprendre.org/allegati/XIX.Napolitani.pdf]
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1158
The passage that follows (translation by Alex Ghillan), taken from Transformations and
Symbols of the Libido by C. G. Jung11, appears to close the circle around the problem of
consciousness:
For the neo-Platonist Plotinus (204-270 AD), the universal anima is the energy
of the intellect. Plotinus compares the One (the primordial creator principle)
with Light in general, the intellect with the Sun, the universal anima with
the Moon. Plotinus also compares the One with the Father and the intellect
with the Son. The One, called Uranus, is transcendent. The Son, Cronus,
governs the visible world. The universal anima (indicated as Zeus) appears
subordinate to him. (…..) As Drews observes, this is also the formula of the
Christian Trinity (God-Father, God-Son and Holy Ghost) as they were defined
at the councils of Nicaea [325 AD, editor’s note ] and Constantinople [381 AD,
editor’s note ]. It is superfluous to note that certain early Christian sects
attributed a maternal significance to the Holy Ghost (universal anima,
Moon). In Plotinus, the universal anima has a tendency to separation and
divisibility, a sine qua non condition of every change, creation and
reproduction (hence a maternal quality); it is an infinite whole of life, all
energy; it is a living organism of ideas, which achieve reality and efficacy
within them. The intellect is its generator, its Father, and the universal anima
evolves what it has contemplated in him in the sensible world. What is
contained in the intellect manifests in the universal anima as Logos,
fills it with contents and inebriates it, so to speak, with nectar. Nectar,
like soma [editor’s note: a sacred drink of many peoples in proto-history, hence
the blood of Christos (Krishna) which is the reinterpretation in a Christian key],
is a drink of fecundity and life, hence sperm. The anima is fertilized by the
intellect (hence by the Father). As superior anima it is called Celestial
Aphrodite; as inferior anima, Terrestrial Aphrodite. This knows the pain of
birth, etc. Not for nothing Aphrodite’s bird, the dove, is the symbol of the
Holy Ghost.
Having sketched the journey of its semantic evolution all that remains is to delineate the
etymological profile of the word consciousness.
Con-science (Italian: co-scienza) is derived from the Latin cum-scire (scire to know, cum
together, to know together, to know as sharing, the knowledge given by the knowledges), but
also con-scientia (with-wisdom, in a wise), in turn derived from the Greek σύνοιδω [synoido],
composed of syn (together) and οἶδα [oida] (knowledge), hence knowledge originating from
knowledges, coming from the Sanskrita root chid (cut, separate, break, distinguish), analogous
to the proto-Indo-European root *sker (trace a furrow).
From this necessarily partial etymological profile, the word consciousness (con-science)
displays two complementary meanings.
The first is linked to the Sanskrita root chid, akin to the proto-Indo-European root *sker, and
establishes the intrinsically discriminative nature of consciousness, its tendency to
emerge, to operate in the world and on the world, cor-rupting (from the Latin rationem
putare, establishing a relationship) whatever it encounters. In this meaning discriminative
consciousness is such because it inherits, develops and integrates the discriminative function
11 C.G. Jung, Libido, simboli e trasformazioni, Newton Compton Editori, Italy, 1993, pagg. 123-124
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1159
exercised by psycho-perceptive activity (which in turn develops and integrates the
discriminative function exercised by neuro-sensorial activity gradually reaching the
discriminative function prefigured in confinement processes that give form to manifestation),
and operates following a process of transformation of the separation properties in reunion
properties and the reunion properties in separation properties, which corresponds to exercising
the power of direct separation of concrete quantities (calculating). In terms of numeration in
the strict sense of the word, this corrupting-calculating is based on counting the objects of a
whole, which means assigning each of its constituents a metaphor-sign (acoustic, mathematical,
verbal, mental, gestural, graphic, etc.) corresponding to a number that is part of the natural
series of integers, starting from unity and proceeding in order until completing the elements of
this set that thereby assumes, arbitrarily, the characteristics of a sequence12. Hence, counting is
equivalent to introducing an order of sequential separation in an otherwise undivided set, while
calculating-corrupting is equivalent to subjecting a sequence to a re-combination.
In terms of mental processes the consciousness that discriminates coincides with
conditioned consciousness and operates by breaking up perceived reality and/or that
thought of as sequences of mental images (it derives mental artefacts, or mentifacts, from the
rudimentary object) which through recourse to the non-linear dynamics of the mnesic
processes (mnemotropy, see Paragraph 2) are constantly re-elaborated and re-composed
resembling themselves and never identical.
This process of re-elaborating the sequences of mental images based on the
perception/representation of the surrounding world is realized along two roads: a dynamic one
that consists in traversing space while being conscious of it, the other static, which, immobile,
allows reconstruction around itself of successive circles that extend as far as the limits of the
unknown. One of the roads gives an image of the world on an itinerary, the other integrates
the image of the two opposing surfaces, that of Sky and that of the Earth which meet at the
horizon.(…….) In Man the two ways are essentially linked to sight, and coexist; they have
produced a two-pronged representation of the world with simultaneous modalities13.[André
Leroi-Gourhan (translation by Alex Ghillan)]
The second meaning is linked to the prefix cum of cum-scire and syn of synoido (but also of
syn-esis) and affirms the relationship of dependence that subordinates consciousness (conscience) to the archetypical presupposition of all the anthropopoietic relational categories: on
high is Sky, below is Earth, in the middle Man. In the human body this archetypical
presupposition means that the discriminating possibility of consciousness depends on the
availability and quality of the synergic relationship (from the Greek synerghìa, from
synérghein, conjoined action, composed of syn, together, and érghein, acting) that elapses
between the wisdom of bio-energetic activity (vegetable-Earth), the wisdom of neuro-sensorial
activity (animal-man/theriomorphism) and the wisdom of psycho-perceptive activity/protocognitive/cognitive (Man-Sky).
The circle around the problem of consciousness has tightened.
12 It is interesting to note that the word Sankhya, which we mentioned in relation to the definition of
conditioned consciousness, literally means number and therefore indicates a doctrine based on
enumeration and analysis. In a broader sense, the Sankhya system could be defined as that system
which aims to approach Ultimate Reality via an exact all-inclusive enumeration of its constituent
principles (tattva).
13 In: A.G. Gourhan, I gesti e la parola: la memoria e i ritmi, Einaudi, Italy, 1977.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2012 | Volume 3 | Issue 11 | pp. 1149-1160
Messori, C., A Cosmogonic Model of Human Consciousness: Part I
1160
And what remains?
The upended 8 (equivalent to a twisted-pinched loop), the mathematical symbol of infinity
(Secondary Source: http://bringingforthworldequality.files.wordpress.com/2011/09/infinity.jpg )
(Continued on Part II)
Note: References are listed at the end of Part IV
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
arXiv:1902.04321v1 [q-bio.NC] 12 Feb 2019
The Φ measure of integrated information is not well-defined for
general physical systems
Adam B. Barrett*1 , Pedro A. M. Mediano2
1
Sackler Centre for Consciousness Science and
Department of Informatics, University of Sussex, Brighton, UK
2
Department of Computing, Imperial College, London, UK
*adam.barrett@sussex.ac.uk (correspondence)
Abstract
According to the Integrated Information Theory of Consciousness, consciousness is a fundamental
observer-independent property of physical systems, and the measure Φ of integrated information
is identical to the quantity or level of consciousness. For this to be plausible, there should be no
alternative formulae for Φ consistent with the axioms of IIT, and there should not be cases of Φ
being ill-defined. This article presents three ways in which Φ, in its current formulation, fails to
meet these standards, and discusses how this problem might be addressed.
1
Introduction
A key component of integrated information theory (IIT) is the mathematical formalism for supposedly describing quantitatively the extent and nature of the consciousness (subjective experience)
generated by any physical system (Oizumi et al, 2014). The theory claims that at every moment
that the physical state is updated, there is potential for a conscious experience to be generated. The
“intrinsic informational structure” of the mechanisms behind a state transition governs the quality
of the experience, whilst the overall quantity of consciousness generated is identical to the system’s
value of the measure Φ (Tononi et al, 2016). The quantity Φ essentially captures the extent to
which the whole system is generating intrinsic information over and above its parts. By intrinsic
information it is meant that which is independent of the frame of reference imposed by outside observers of the system. The axioms and postulates of IIT state that consciousness is a fundamental,
observer-independent property of physical systems, analogous to mass, charge or energy (Tononi and
Koch, 2015), and hence imply that Φ is a fundamental physical quantity.
Much of the critique of the Φ measure has been based on the impracticality of its application to
empirical neural data, and thus its inability to make testable predictions for IIT (e.g. Bor, 2012).
Notably, the computation time required to compute Φ grows faster than exponentially with the
number of system components;1 and it has only ever been computed on a specific kind of toy model
1
More precisely, the computation time required to compute the effective Φ for a particular system graining grows
1
system with just a handful of components (Mayner et al, 2017). Here we set testability issues aside,
and address the deeper question of whether it it is theoretically possible for Φ to be a fundamental
physical quantity. For it to be so, it must be well-defined, and there should be no alternative formulae
for Φ consistent with the axioms and postulates of the theory. Here, we list three ways in which it is
not well-defined, and hence conclude that further development of the theory and operationalisation
of Φ is required.
2
Key quantities for the construction of Φ
This section provides some description of the construction of Φ in words, and writes down the
key mathematical quantities (probability distributions) from which it is constructed. A detailed
description is not provided; for that the reader is referred to Oizumi et al (2014). Φ has been
developed and illustrated via the use of examples of toy model systems consisting of indivisible and
discrete binary components (logic gates). These systems evolve in discrete time; at each discrete
time-step each component has its state updated according to the specified interactions (mechanisms)
present. The dynamics are memoryless (Markovian): the probability distribution for the state at the
next time-step only depends on the present state, and not on the past history. Most real complex
systems are not easily modelled in this way, and this is a source of the theoretical problems presented
below. Defining Φ relies on quantifications of (i) information and (ii) integration, in the system. Each
of these components is rehearsed here in turn.
Information is specified as that which the current state of the system contains about a hypothetical
past state in which all configurations of the system were a priori equally likely.2 Informally, the
concept is that the more past states that are ruled out (or made improbable) by the current state,
the greater the information generated. Formally, the key quantity is the joint probability distribution
Pce (X 0 , X 1 ) for the states X 0 and X 1 of the system at discrete time t = 0 and t = 1, given that the
system was perturbed at t = 0 into all possible states with equal probability (Krohn and Ostwald,
2017). The acronym ‘ce’ stands for cause-effect. This quantity decomposes as
Pce (X 0 , X 1 ) = P (X 1 |X 0 )Pu (X 0 ) ,
(1)
where Pu (X 0 ) is the uniform (or maximum entropy) distribution and P (X 1 |X 0 ) is given by the
system’s dynamics. From this, the conditional distribution Pc (X 0 |X 1 ) is extracted:
Pc (X 0 = x0 |X 1 = x1 ) =: P
Pce (x0 , x1 )
.
∗
x∗ Pce (x , x1 )
(2)
As discussed below: (i) P (X 1 |X 0 ), and hence Pce (X 0 , X 1 ), is only well-defined for Markovian
systems; (ii) Pu (X 0 ) is only defined if the set of states is finite (or else compact, i.e. closed and
bounded).
Integration is operationalised by comparing probability distributions associated with the whole
system to analogous probability distributions associated with a partition of the system. For the
faster than exponentially with the number of components. To obtain the maximum Φ over all grainings is intractable
in the absence of a short-cut. See Section 2.1.
2
Only integrated information of ‘cause’ is considered here. For integrated information of ‘effect’ one swaps t = 0
and t = 1. The final Φ is the minimum of that computed for causes and that computed for effects.
2
comparison, the probability distributions associated with distinct parts within a partition are taken
to be independent. Formally, one computes the distance in probability distribution space between
the probability distribution for the whole and the product of the probability distributions for the
parts. To define the parts, one must specify a partition P = {M 1 , M 2 , . . . , M r } that divides the
elements of X into r non-overlapping, non-trivial sub-systems, such that X = M 1 ∪ M 2 ∪ . . . ∪ M r .
With these key elements defined, integration is quantified by considering the distance between
Y
Pc (X 0 |X 1 = x) and
Pc (M k0 |M k1 = mk )
(3)
k
where the mk are the sub-system states corresponding to whole system state x under the partitioning.
The greater the distance between these, in probability distribution space, the greater the amount of
integrated information (with respect to the given partition). The metric on probability distribution
space is taken to be the “earth mover’s” (or Wasserstein) distance (Oizumi et al, 2014). Then Φ is
the minimum of this distance taken across all possible partitions – in what is commonly known as
taking the “cruelest cut” of the system; see Oizumi et al (2014) and Krohn and Ostwald (2017) for
details.
2.1
Maximisation over possible grainings
Importantly, to compute Φ, a graining of the system is needed, in space, time and the set of possible
states of the components. Since the measure is supposed to be independent of the point of view of the
observer, the choice of grainings must be observer-independent. It is prescribed that the grainings
to be used are those that lead to the maximum possible value of Φ. Thus, the Φ of a graining is the
minimum across partitions of that graining, and the final Φ of the system is the maximum over all
possible grainings.
This maximisation over grainings is currently infeasible to carry out in practice for any real
physical system, since no compelling short-cuts or approximations yet exist for searching through
the infinity of possibilities (Barrett, 2016). Hence computation of Φ is currently intractable for any
real physical system. Nevertheless, from the intrinsic (or ontological) perspective, a physical system
may instantiate its own maximisation despite that maximisation being infeasible to compute by
any external observer. The problems highlighted in Section 3 are distinct from and go beyond this
practical computability challenge. We emphasise this issue of graining here since the requirement to
maximise over all grainings increases the extent to which Φ is not well-defined, according to Problems
2 and 3 below.
3
Three ways in which Φ is not well-defined
This section lists three ways in which Φ, as currently formulated, is not well-defined.
3.1
Problem 1: There is no canonical metric on the space of states, nor a canonical metric on probability distribution space
In order to compute the earth mover’s distance, a metric is required on the space of states, i.e. one
requires there to be a well-defined distance between any two states. In IIT-3.0 the Hamming distance
3
is proposed as the distance when the state of each component of the system is binary. However, for
general non-binary states there are a range of possible metrics and no canonical ‘intrinsic’ choice.
For
pP valid expressions for the distance between them are the ‘L1 norm’
P two states x and y, example
2
|x
−
y
|,
the
‘L2
norm’
i
i
i (xi − yi ) and the ‘L∞ norm’ maxi |xi − yi |. The earth mover’s
i
distance is further not the only distance measure for probability distributions. Tegmark (2016) lists
several alternatives, and there is no canonical choice. As demonstrated in simulation in Mediano et al
(2018), different choices in the construction of a variant Φ measure can lead to profound differences
in the behaviour, even on small systems. Therefore, in the absence of a well-argued principle by
which to uniquely fix the metrics on the space of states and on probability distribution space, Φ is
not well-defined.
3.2
Problem 2: The requirement of a discrete set of states
The maximum entropy distribution on the set of states of the system is not well-defined if the set
of states is infinite (except for the case of the set of states being compact, i.e. closed and bounded
[Barrett and Seth, 2011]). Thus, for example, the neuron membrane potential can not be taken
as the state variable, since there is no way to define precise absolute limits on it. More generally,
any system with Gaussian or exponentially distributed state variables does not have a well-defined
Φ for this reason. A possible fix might be to only consider grainings into discrete sets of states.
However, one would need a canonical method for labelling a discrete set of states obtained from the
continuous variable, and to have solved Problem 1 above for there to then be a canonical metric on
any discretisation. Then, one would need to show that there always exists an upper bound to the
effective Φ over all discrete finite grainings.
3.3
Problem 3: The requirement of Markovian dynamics
Additionally, Φ is not well-defined for a system with non-Markovian dynamics, i.e. one for which the
dynamics are not memoryless (Barrett and Seth, 2011). The probability distributions P (X 1 |X 0 )
and Pce (X 0 , X 1 ) in the formula are not well-defined unless the probability distribution for future
states depends only on the current state, and not on the system’s past history. This is because for a
non-Markovian system the distribution on the past history given X 0 is not specified. We highlight
that this is an important problem, and not just merely a theoretical construct – brain dynamics
are non-Markovian at many levels, ranging from the EEG level (see for example von Wegner et al,
2017), to the level of ionic current fluctuations in membrane channels (see for example Fuliński et al,
1998). More generally, a system may be Markovian with respect to some grainings, but not for all
grainings. Given that Φ is supposed to be specified by the maximisation over all possible grainings,
(see Section 2.1), it only takes one graining of a given system to have non-Markovian dynamics for
Φ to be ill-defined for that system.
For non-Markovian systems, one might perhaps attempt to define Φ as the limit as k → ∞ of
the analogous quantity with X 0 replaced everywhere with (X 0 , X −1 , X −2 , . . . , X −k ), i.e. try setting
all past states in an indefinitely long past history to be independent and maximum entropy under
the perturbation, and see if there is convergence as the length of past history considered tends to
infinity. Such an approach would not however solve the issue for non-ergodic systems: for a nonergodic system, by definition, there is no convergence of P (X 1 |X 0 , X −1 , X −2 , . . . , X −k ).
4
As an example, we consider a non-ergodic system, which has non-Markovian grainings. This
system has a variable S (potentially in addition to other variables, which we need not consider to
make the point), which follows a random walk:
St+1 = St + Bt ,
(4)
where the Bt are independent identically distributed binary random variables with equal probability
of taking the values -1 and 1. Consider the binarisation of this variable S such that the binary state
X is given by X = 1 if S exceeds some threshold θ, and X = 0 otherwise. To compute Φ for this
graining we would need the quantity
P (X1 = 1|X0 = 1) = P (S1 > θ|S0 > θ) =
∞
X
P (S1 > θ|S0 = s)P (S0 = s) .
(5)
s=θ+1
But this is not well-defined since there is no well-defined probability density function for S0 : one
cannot impose a maximum entropy distribution because the range of values S0 can take is not a
compact set (see Problem 2 above), because as the length of history considered tends to infinity, the
set of possible values of S0 goes to infinity also.
4
Discussion
For IIT to mature as a theory, the three problems above will need to be addressed. This article
concludes with some discussion on this.
Problems 2 and 3 arise from needing to quantify the information that the current state holds
about some prior state. The maximum entropy distribution is the only possible prior one can impose
on the past state, as any other choice will depend on some arbitrary information held by the observer.
An empirical distribution can not be used, because not all systems are stationary: the statistics of
the system could change the moment any recording is terminated, so one would never know if one
has recorded everything that the system could have done. A reformulation of Φ in terms solely of
the geometrical and topological structure of the instantaneous state of the system, without reference
to past and future states, might be the only way of solving Problems 2 and 3 (Barrett, 2014).
This would change the fundaments of the theory somewhat- it would be less about the mechanisms
underlying the evolution of the system, and more about simply obtaining a mapping from a physical
structure onto the structure of the phenomenal experience associated with the physical structure.
Nevertheless, a complex set of mechanisms are needed to generate a system that can exist in multiple
complex configurations, so mechanisms would still in some sense be fundamental to consciousness on
such an updated theory.
Problem 1 appears to be harder to solve. However one might reformulate the theory, any attempt
to create a formula for consciousness as intrinsic information needs to define, spatially, where one
system ends and another begins. Without a canonical metric on the space of system configurations,
one would not be able to quantify differences between systems and sub-systems in a truly observerindependent fashion. It might be that the possible metrics are heavily constrained by the requirement
that the effective Φ must always remain bounded under increasingly fine grainings (see Problem 2);
such an investigation is beyond the scope of this paper, but could form the basis for future work.
5
Successful observer-independent theories for how macroscopic physics emerge from fundamental
entities are typically cast in terms of continuous fields, e.g. Einstein’s theory of mass and gravitation (general relativity), and Maxwell’s theory of electromagnetism (Barrett, 2016). Barrett (2014)
proposes that an approach to IIT, and the emergence of consciousness, based on fields might offer advantages over the existing discretization-based approach. It is a debatable supposition that
the state of consciousness of a physical system is determined by its structure at a variable spatiotemporal scale and state graining, given by that which happens to maximise Φ for the given system
at the given moment (Bayne, 2018). If a formula for the integrated information intrinsic to a field
configuration could be obtained, there would be no need to consider alternative grainings of states,
or system components. Because human consciousness arises from complex electrical activity in the
brain, the hypothesis would be that its fundamental substrate is the integrated information intrinsic
to specifically the electromagnetic field (as opposed to say, the gravitational or nuclear force field) it
generates (Barrett, 2016); see Barrett (2014) for more on this idea.
Continuing to attempt a formulation of intrinsic information via discrete graining, one might make
use of quantities related to Kolmogorov-Sinai (KS) entropy (Sinai, 2009). KS entropy is well-defined
for all ergodic systems as a supremum over all grainings. Furthermore, Thurner and Hanel (2012)
recently proposed a formalism for defining generalised entropies for non-ergodic systems. Perhaps
that could be used to generalise KS entropy to non-ergodic systems, and hence to obtain a universally
well-defined intrinsic description of information dynamics.
4.1
Final remarks
We have shown that the supposedly fundamental Φ measure of integrated information, as described
in IIT version 3.0 (Oizumi et el., 2014) is not well-defined for general physical systems. We have
not addressed here the many variant Φ measures that have been developed for potential practical
application to specific classes of systems, see Tegmark (2016) and Mediano et al. (2018) for reviews.
These tend to quantify information with respect to the empirical distribution as opposed to the
maximum entropy distribution, and can be applied to systems with continuous states (Problem 2
doesn’t apply), and moreover to any stationary system (Markovian or not). Further, for a non-linear
deterministic system, a distinct approach to operationalising integrated information in terms of
topological dimensionality of attractor dynamics has been proposed (Tajima and Kanai, 2017). Any
of these measures might be tested for correlation with consciousness when computed across choice
sets of brain variables (Barrett and Seth, 2011). However, the behaviour of these various measures is
very diverse even on small simple networks, so one must remain cautious about considering them as
generalisations or approximations of any eventual, ‘fundamental’ Φ measure (Mediano et al., 2018).
The key idea of IIT, that consciousness is, in some sense, intrinsic information remains intriguing
and influential (Tegmark, 2015). However, operationalising this idea and obtaining a candidate
universal mathematical description of intrinsic information remains challenging. The current Φ
measure is neither universally well-defined, nor fully independent of certain arbitrary choices input
into its construction. It is in the best interest of IIT that we recognise and address these problems
to move towards a truly plausible measure of phenomenal experience from physical structure.
6
Acknowledgements
ABB is funded by EPSRC grant EP/L005131/1.
References
Barrett, A.B. (2014) An integration of integrated information theory with fundamental physics,
Front. Psychol., 5, 63.
Barrett, A.B. (2016) A comment on Tononi & Koch (2015) ‘Consciousness: here, there and everywhere?’, Phil. Trans. R. Soc. B, 20140198.
Barrett, A.B., & Seth, A.K. (2011). Practical measures of integrated information for time-series
data. PLoS Comput. Biol., 7(1): e1001052.
Bayne, T. (2018). On the axiomatic foundations of the integrated information theory of consciousness, Neuroscience of Consciousness, 2018(1), niy007.
Bor, D. (2012) The Ravenous Brain: How the New Science of Consciousness Explains Our Insatiable
Search for Meaning, New York, NY: Basic Books.
Fuliński, A., Grzywna, Z., Mellor, I, Siwy, Z., & Usherwood, P.N.R. (1998) Non-Markovian character
of ionic current fluctuations in membrane channels Phys. Rev. E 58, 919.
Krohn, S. & Ostwald, D. (2017) Computing Integrated Information, Neuroscience of Consciousness,
2017(1), nix017.
Mayner, W.G.P., Marshall, W., Albantakis, L., Findlay, G., Marchman, R. & Tononi, G. (2017)
PyPhi: A toolbox for integrated information theory, arXiv, 1712.09644.
Mediano, P.A.M., Seth, A.K., & Barrett, A.B. (2018). Measuring integrated information: Comparison of candidate measures in theory and simulation. arXiv, 1806.09373.
Oizumi, M., Albantakis, L. & Tononi, G. (2014) From the phenomenology to the mechanisms of
consciousness: Integrated Information Theory 3.0, PLoS Computational Biology, 10 (5), e1003588.
Sinai, Y. (2009) Kolmogorov-Sinai entropy, Scholarpedia, 4(3):2034.
Tajima, S., & Kanai, R. (2017) Integrated information and dimensionality in continuous attractor
dynamics, Neuroscience of Consciousness, 2017(1), nix011.
Tegmark, M. (2015) Consciousness as a state of matter, Chaos, Solitons and Fractals, 76, 238-270.
7
Tegmark, M. (2016) Improved Measures of Integrated Information. PLoS Comput Biol, 12(11):
e1005123.
Thurner, S. & Hanel, R. (2012) The entropy of non-ergodic complex systems - A derivation from
first principles. International Journal of Modern Physics: Conference Series, 16, 105-115.
Tononi, G. & Koch, C. (2015) Consciousness: here, there and everywhere? Phil Trans. R. Soc. B
370, 20140167.
Tononi, G., Boly, M., Massimini, M., & Koch, C. (2016) Integrated information theory: from consciousness to its physical substrate Nature Reviews Neuroscience 17, 450-461.
von Wegner F., Tagliazucchi, E., & Laufs, H. (2017) Information-theoretical analysis of resting state
EEG microstate sequences - non-Markovianity, non-stationarity and periodicities. Neuroimage. 158,
99-111.
8 |
Cooling down and waking up: how a quantum
accelerator in the cortex switches on consciousness
Andrew Bell
Eccles Institute of Neuroscience
John Curtin School of Medical Research
The Australian National University
Canberra, ACT 2601, Australia
andrew.bell@anu.edu.au
Abstract:
This paper presents a theory of how feedback cooling in the cortex reduces thermal noise to
the point where quantum mechanics can operate at body temperature. It revisits the Eccles
model of consciousness and builds on it so that its core anatomical units – which Eccles
called psychons – function as a quantum accelerator, a type of quantum computer that
supercharges a standard computer. When the accelerator is idle, as in sleep, we have a
neural network computer operating unconsciously, but when switched on, the psychons
light up, computing power is multiplied, and consciousness arises. Switching depends on
feedback cooling – a mechanism that permits amplifiers to act as refrigerators – allowing
Bose–Einstein condensation and quantum computation to occur. The model narrows the
brain–mind gap, explains how and why consciousness evolved, and is testable. Quantum
accelerators are now commercially available, but perhaps nature came to the idea first.
2023-09-18 – p.1
Introduction
A constant current of thought ever since philosophy began has been dualism: that
we are a mind inhabiting a body, between which there is two-way traffic (Anastopoulos,
2021; Chalmers, 2007; Popper & Eccles, 1977). Many people naturally gravitate to this
model, although it has not been popular among modern philosophers and neuroscientists,
who tend to favor the materialistic picture offered by the physical sciences. Nevertheless,
there are those who think there must be more to existence than electrical signals
propagating through neurons – more than just “atoms in the void” as Democritus put it. So
where do those mysterious qualia, the elements of sensation, come from? How can a
neuron light up and give us the colour crimson or the taste and aroma of freshly brewed
tea? Despite its past unpopularity, a number of modern philosophers and scientists are now
willing to take on a dualistic mantle of some kind, and a common theme is quantum
mechanics (Anastopoulos, 2021; Atmanspacher, 2020; Gao, 2022; Hameroff & Penrose,
2014; Schwartz et al., 2005; Stapp, 2007).
This paper does not argue the case for dualism. 1 Rather it accepts the basic
interactive dualism of Popper and Eccles (1977) and then gives an outline of how, based on
modern developments, mind could realistically arise from matter. The core of the story is
that it involves quantum mechanics, but it adds a crucial, but overlooked ingredient –
feedback cooling. To foreshadow, feedback cooling is a technique widely used in
gravitational wave detectors and involves using feedback to cancel out thermal motion in a
material, effectively lowering its temperature and allowing quantum behaviour to emerge
above thermal noise. In the context of the brain, it is notable that there are myriads of
feedback paths between efferent and afferent nerves. And finally, neural tissue has the
distinct property of being piezoelectric, meaning that, like a quartz crystal, an electrical
voltage can produce a displacement and, reciprocally, a displacement can produce a
voltage. So when placed in a feedback circuit, a piezoelectric material can be effectively
cooled: when a thermally induced displacement (such as from Brownian motion) creates a
1
See Robinson (2018) for arguments for and against dualism.
2023-09-18 – p.2
voltage, then that displacement can be cancelled out by negatively feeding back that voltage
(Kawamura & Kanegae, 2016).
All this will be explained in more detail. But to begin, we direct attention to the
existence of quantum accelerators, which are add-ons to conventional computers that use
quantum mechanical processes to speed up computation. You can go online today and
purchase such a device off the shelf (https://quantumbrilliance.com/). Remarkably, such
devices do not require cryogenic temperatures in order to operate, although many of them
do. One quantum accelerator, based on 5 quantum mechanical bits (qubits), involves the
entanglement of nuclear spins from 5 nitrogen nuclei embedded within a diamond
substrate. It operates at room temperature and is available as a 19-inch rack-mountable unit
(Doherty, 2021).
Why would you pay for 5-bit computing power when your own laptop uses
gigabytes? The answer is that, broadly speaking, quantum computation happens in parallel,
not serially, giving an immense speed-up in processing power. In an entangled quantum
field, we have “everything, everywhere, all at once”, with the instantaneous collapse of the
wave function being the endpoint of a computation. If we set up an array of probabilities,
then a single quantum computation will instantly arrive at the outcome. One can solve the
travelling salesman problem serially using protracted processing power, or you can set up an
array of coherent sources and the resulting collapse will provide the same answer
exponentially quicker. The ultimate aim, of course, is to increase the size of quantum
computers way beyond 5 bits, but it is a start (Doherty, 2021).
Given the acknowledged advantage of quantum computers in terms of processing
power, the central question examined here is: might the human mind be an instance of a
quantum computer? Could nature have long-ago done what modern-day science is only
now latching on to? There are immense advantages in terms of processing power, and
quantum mechanics provides that same unity of experience that has long attracted
physicists such as Stapp, Penrose, and Bohm, neuroscientists like Eccles, and an increasing
number of philosophers (Gao, 2022). The quantum field is there all at once, just like our
2023-09-18 – p.3
consciousness is. 2 Our conscious mind is able to take in a multitude of sights, sounds,
sensations, thoughts, and memories, all available for instant access (Nagel, 2012).
There is growing interest in the idea that quantum mechanics offers a solution to the
longstanding and perplexing problem of how minds and bodies interact. The field is large
and growing, but key works pointing in this direction are Al-Khalili and McFadden (2014);
Atmanspacher (2020); Penrose (2022); Chalmers and McQueen (2023); Josephson (2019);
and Hameroff (2022). But if the mind is quantum mechanical, a crucial question is how can it
sustain itself against the decoherence of thermal noise? The plan of this paper is to supply a
possible answer.
A core part of the synthesis involves revisiting the psychon model of Eccles – a
largely underappreciated quantum mechanical model of the human brain – and build on it
to give a modern-day account of how mind could arise from matter. Economically, it places
the cut between mind and body in the same place as between classical and quantum
physics, so that the mind is identified as the quantum aspect of a neural cluster in the cortex
which comes to the fore when the cluster is cooled and thermal noise is cancelled out. The
cluster of pyramidal cells (which Eccles called a dendron) then becomes what in Eccles’
terms is a ‘psychon’ (Eccles, 1990). The explanation brings together the elements of cortical
anatomy, neurophysiology, philosophy, and basic quantum physics (Beck, 2001; Eccles,
1990) and then, adding more modern developments, arrives at a specific model in which the
conscious human brain is a quantum computer. A persistent criticism of the Eccles model
(and of other quantum mechanical models) is how it is possible for subtle quantum
phenomena to exist amid the din of thermal noise. Here the solution draws on the
phenomenon of feedback cooling.
We note that the anatomical units of the Eccles model – the cluster of pyramidal
cells in the cortex – are in just the right spot to be causally efficacious: at the pinnacle of
efferent (sensory) and afferent (motor) nerve pathways. The mind is in a position to receive
A nice definition of consciousness is the here-I-am-ness of Dennett (2013). This definition is in
plainer English than the “something that it is like to be” of Nagel (1974). Further, Nagel’s wording has difficulty
capturing meditational states which are “not like anything” (Shear 2007, p. 700), whereas Dennett’s
formulation captures some of the universal I-ness which underlies the experience. Stapp (1993) defines it
more wordily as “[t]hat luminescent presence of coming-into-beingness that constitutes our inner world of
experience” (p. 234).
2
2023-09-18 – p.4
sensory input, generate a quantum field, and execute motor action, just as prescribed by
dualistic interactionism (Popper & Eccles, 1977). The units “light up” (quantum mechanically
speaking), and the aggregate of grey matter awakes. The brain, once in a state of sleep,
experiences the light of consciousness and becomes, in philosophical terms, a multiplicity of
flowing qualia. In a similar way, one can explain how a sleepwalker, or perhaps even a
zombie, may awaken (as explored later). One might say that the model reinstates the “ghost
in the machine”, the much-derided entity described by Gilbert Ryle to describe how dualists
view the relation between mind and body (Ryle, 1949). By introducing quantum mechanics,
Eccles was able to turn the epithet back on his critics, holding that our minds could well be
at the controls of a process so subtle that even a ghost might operate it, and this is the
position taken here.
The basic elements of such a machine are set out below, where the case is made
that the conscious human mind is an instance of a powerful quantum computer. The missing
element that revives the Eccles model is feedback cooling, and here it is shown how positive
feedback is more than possible – perhaps even commonplace – between efferent and
afferent nerve pathways. In fact, feedback is almost inevitable whenever one establishes
connections between a system of sensors (afferents) and a system of motors (efferents). By
recognising widespread feedback, and the possibilities it offers in terms of cooling, the
criticism that quantum coherence cannot take place at room temperature can be effectively
overcome. As Bialek (1983) has shown, positive feedback is a way of reducing the “effective
temperature” of a system (to be distinguished from its actual temperature). If one hangs a
mass on a spring, for example, and uses a laser beam to sense its position, Bialek describes
how the thermal vibration of the mass can be much reduced by hooking up an actuator to
always oppose its velocity. The result is that it will hang perfectly still, as if its temperature
were close to absolute zero. 3 The actual temperature may still be at room temperature, but
its motion is that of a freezingly cold body, and that provides a multitude of low-energy
quantum states filled with vibrational quanta called phonons. The process is not easy to
control, but given the immense potential benefits in terms of computational power and
Bialek calculates that, by applying carefully controlled laser feedback, a suspended mass of 1 g could
be given an effective temperature of 7 mK. See later section for more details of feedback cooling.
3
2023-09-18 – p.5
stability, and given the existence of observed feedback paths within pyramidal cells of the
cortex, the model deserves fresh consideration.
There are considerable advantages to this picture, as set out later. In summary: it is
precisely specified anatomically and functionally; it is at the pinnacle of the cortex where
efferent and afferent nerve pathways meet (just where mind needs to be for sensing and
acting); it explains the connection between sleep and wakefulness; and it helps to
understand how and why consciousness could have evolved from a nonconscious system
(by adding feedback cooling circuits onto existing reflex circuits). Importantly, the
hypothesis is testable using nuclear magnetic spectroscopy techniques that can
noninvasively sense temperatures at specific sites in conscious brains. It can also supply an
economical account of sleepwalkers and zombies.
This paper elaborates on ideas first sketched in earlier work (Bell et al., 2022) and
here they are placed on a firmer footing.
Eccles’ psychons
Eccles was perhaps the first to connect the classical and quantum realms in an
explicit neurophysiological way. Inspired by the quantum ideas of Margenau (1984), Eccles
pointed to a precise locus where the two realms meet: at pyramidal cells in the neocortex
where efferent and afferent nerve fibres come together. Here he suggested that mind is
generated through some quantum process, calling each of the mental–physical units
“psychons” (Eccles, 1990), a name which in 1990 led many hard-nosed neuroscientists to
treat his ideas with derision. Now, however, when more philosophers and scientists are
prepared to entertain dualism, it is opportune to revisit his key idea.
Eccles proposed that psychons, each made up of a large collection (200 or more) of
pyramidal cells, were at the very pinnacle of the cortex, precisely where efferent and
afferent nerve fibres come together. He may have encountered less resistance to his ideas if
he had used a more neutral name, such as neural–mental units, a term he used elsewhere.
The psychon idea was designed to fit in with his dualistic philosophy, but in 1990 dualism
was much out of favour. Although the quantum mechanical properties of the synaptic cleft
2023-09-18 – p.6
on which Eccles focused were elaborated by collaboration with physicist Friedrich Beck, the
idea failed to gain traction.
Here we update the Eccles model by adding on a modern proposal originating from
Bialek: we suppose there is a process of ‘feedback cooling’ in these cortical units which
cancels out thermal noise and allows them to operate at low effective temperatures. In this
way, quantum phenomena are able to exist in a warm, wet brain, and this opens the door to
a room-temperature quantum computer composed of millions of units dispersed (and
entangled) over the entire cortical sheet. When switched on during wakefulness, the
quantum field generated by feedback cooling in all these units is, we suggest, the conscious,
qualia-filled mind. We now address how feedback cooling can be applied to Eccles’ psychon
model.
For his whole life, Eccles had been looking for how the mind could reside within
neural tissue (Bell, 2022; Popper & Eccles, 1977). How could awareness, full of life and
sound and colour, arise from a conglomeration of neurons? The answer came from
combining the neuroanatomical findings of his colleague Szentágothai and the quantum
mechanical ideas of Margenau. Putting them together, he arrived at the idea of a
“psychon”, as illustrated in Figure 1 (Eccles, 1990; Eccles, 1994). The idea was further
developed in collaboration with Friedrich Beck, a quantum physicist (Beck, 2001; Beck &
Eccles, 1992): in their model, quantum mechanical processes occur within the tangle of
synapses found in the pyramidal cells of the neocortex, where there is a rich connection of
efferent and afferent pathways (Figure 2).
2023-09-18 – p.7
FIGURE 1. How consciousness arises in clusters of cortical cells, following the model of
Eccles (1990). The colours represent quantum mechanical fields which are generated by
pyramidal cells in the cortex (layers I to V) when the cells within each cluster operate
coherently. Eccles called each cluster a psychon, considering it an atom of consciousness.
According to the updated model here, coherence arises within psychons when feedback
loops within each cluster become active and feedback cooling occurs. This cancels thermal
noise and reduces the effective temperature, allowing quantum mechanical behaviour and
the psychon effectively lights up (as suggested by the shading). When the coloured
envelopes overlap, the whole cortex becomes a unitary Bose–Einstein condensate, and
consciousness arises. Reproduced from Eccles (1990) with permission of The Royal Society.
2023-09-18 – p.8
FIGURE 2. A close-up view of the cells in Figure 1 (layers III–V) shows the feedback paths
which can form between them. A distinct feature of each cell cluster is that there are
multiple contacts between afferent (ascending or sensory) nerve fibres shown in blue, and
efferent (descending or motor) nerve fibres shown in red. The two classes of nerve fibres
are highlighted by the yellow rectangle. Moreover, there are places where sensory and
motor nerves touch (e.g., in green square) and this, it is suggested, leads to feedback
between the two complementary types (as with a microphone near a loudspeaker) and in
turn produces feedback cooling, lowering the effective temperature. With low thermal
noise, a Bose–Einstein condensate can form, and this, it is proposed, is the basis of
consciousness. (pyr = pyramidal cell; sst = spiny stellate cell; spec. aff. = specific afferent).
From Szentágothai (1979) and reproduced with permission of MIT Press (all rights reserved,
© 1979 Massachusetts Institute of Technology).
Afferents are ascending nerve pathways which convey action potentials from
peripheral sense organs to the brain, while efferents are descending pathways which deliver
command signals from higher brain levels down to muscles so as to perform actions. There
is more to the story, of course, in that there are many intermediate relay stations and crossover points, and, notably, there is a rich supply of efferents to sense organs, the role of
which is still being explored. The important point is that connections between efferents and
afferents have the potential to create reverberating loops of activity (Kistler & De Zeeuw,
2023-09-18 – p.9
2003). Some have suggested that reverberating loops may underlie the regularity of certain
EEG waves (for example, the 40 Hz gamma wave, discussed later, which may serve to
synchronise brain activity). But confining ourselves to the cerebral cortex, Szentágothai has
noted the “massive reentrant circuitry” in these higher centres where efferent and afferent
meet, and has wondered at the “crucial significance” this special modular architecture may
have (Szentágothai, 1984). One effect of the intertwined reflex arcs between afferents and
efferents might be the establishment of a “circular chain” of reciprocal connections
(Szentágothai, 1979).
Figure 2 is a diagram from Szentágothai (1979) which illustrates how efferents and
afferents combine in cerebral cortex (layers III, IV, and V), which is largely populated with
pyramidal cells (pyr). The afferents are coloured blue, and the efferents red (see bottom
yellow square), and the green patch is an example of where the two types touch, creating a
possible reverberant loop. In such a loop, there is the potential for feedback, and this is
where Bialek’s ideas come into play. Feedback can happen whenever a motor network and a
sensor network are connected and, like a microphone near a loudspeaker, the loop will
create a continuous feedback squeal if the gain is sufficiently high.
Returning to Figure 1, from Eccles (1990), we see a broader view of the same cortical
region (layers I to V). This shows what happens when the same pyramidal cells act
cooperatively: this time the cells are surrounded by an envelope of colour, a coherent field
that Eccles identified as a psychon. Eccles regarded each psychon, about 80 micrometres
across, as an atom of consciousness. This special place, at the pinnacle of where efferent
and afferent meet, is the point where brain and mind interact. The different colours are
meant to suggest different qualia, depending on the origin and destination of the underlying
nerve pathways.
There are perhaps hundreds of pyramidal cells within a single psychon. For example,
in the diagram by Beck (2001), his Fig. 7B shows more than 260 pyramidal cells extending
over layers I to VI, a depth of some 1500 micrometres. Within each psychon and its bundle
of dendrites, there are perhaps 100,000 boutons in which synaptic contact can take place.
However, it is important to note that the synapses do not all operate independently, but
coherently. This paper proposes that feedback loops within a psychon give rise to a single
electrical or magnetic field, which establishes a quantum mechanical Bose–Einstein
2023-09-18 – p.10
condensate, as described later. The end result is that all the pyramidal cells within a single
psychon will operate synchronously. 4 The psychon is therefore the quantum mechanical
unit, not the individual synapses of the pyramidal cells.
Eccles and Beck thought that psychons arose through a quantum mechanical process
of some kind occurring at synapses, so their quantum mechanical analysis was based on the
stochastics of what was happening in the synaptic cleft. Beck (2001) makes a general
statement that there is “cooperation” among individual cells, but he leaves this process
largely unspecified, although it could be “stochastic resonance” (p. 109). He is reluctant to
talk about qualia. 5 Against this background, the model presented in this paper provides a
more definite picture: that the psychon is the site where, as in an induction coil, a longlasting, self-sustaining coherent field is generated. In brief, an electromagnetic field arises
from feedback activity of all the pyramidal cells within an isolated cortical column and gives
rise to a single psychon and its associated quale. Whether the quale is a colour, a sound, a
touch, or so on, depends on its cortical location. Because psychons are quantum mechanical
fields poised at the interface between afferents and efferents, not only are they influenced
by incoming signals from the sensory system (via the afferents) but can also supply output
through the motor system (the efferents).
The crux of the matter is that coherence in a single psychon derives from electrical
feedback between all its pyramidal cells acting in concert, and that this feedback could, if
the feedback gain were high enough, produce ‘feedback cooling’, reducing the effective
temperature of the column. The multiple layers in the cortex suggest there could be
multiple stages of cooling, as in a multi-stage refrigerator. If the effective temperature
becomes low enough, thermal noise is reduced to the extent that the whole column
becomes quantum noise limited. The resulting state is comparatively long-lived, perhaps in
We put aside the details of how the bosons – considered to be vibrational quanta or phonons – are
created from neural activity. Although synchronised firing of pyramidal cells within a psychon is the outcome,
the process might involve either synaptic or ephaptic transmission between cells, the latter being suggested by
Hameroff (2010) as underlying consciousness. In this context see also Debanne et al. (2013). Ephaptic
connections at gap junctions create much smaller delays and tighter feedback loops than synaptic
mechanisms. In terms of psychons, if we take a psychon to be 60 µm in diameter, and assume it behaves like a
simple inductor, then a neural conduction velocity of about 1 m/s would create a feedback loop in the range
1–10 kHz. Such a frequency well be a multiple of the 40 Hz thalamocortical loop that we presume switches the
psychon off and on (via feedback cooling).
5
He says that “[s]cience can not, by its very nature, present any answer to the philosophical, ethical
or religious questions related to the mind” (p. 109-110).
4
2023-09-18 – p.11
the region of tens of milliseconds, not the picoseconds or femtoseconds (as standard
quantum mechanical calculations in a warm brain suggest). Feedback cooling is discussed in
more detail in the following section.
As Eccles suggested, the electromagnetic fields of one psychon are quantum
mechanically entangled with the fields of neighbouring psychons, so that the whole of the
cortex, containing perhaps 40 million psychons, each a qubit, operates as a powerful
quantum computer which displays all the distinctive properties of mind. In other words,
consciousness might be a quantum field extending over all the cortex, and is so entangled
that it operates as a single superconducting sheet (Freeman & Vitiello, 2016).
Of note, the consciousness field could be switched on and off by controlling the
feedback circuit, and this might readily be done via the thalamus. If feedback is on, we are
conscious; if not, we are unconscious. They are the same underlying cellular circuits, but
acting in different modes. In one case we are asleep, mere automata, and in the other we
are at the controls of a remarkable quantum computer. A later section describes the
observed thalomocortical loops which give rise to 40 Hz oscillations in the cortex, and which
are known to play a key role in regulating consciousness (Alkire et al., 2000; Edelman &
Gally, 2013). Accordingly, this paper suggests that the principal role of thalamocortical loops
is to switch psychons on and off: when the thalamic circuit is active, feedback cooling of
psychons takes place, quantum mechanical processes are enabled, and consciousness
arises.
Feedback cooling
The above account relies on feedback cooling to produce low effective temperatures
in the cortex, and in this section we consider the phenomenon in more detail. In summary,
feedback cooling is a process of applying feedback to a system so as to reduce thermal
noise; this is the same process as used in a gravitational wave detector when its mirror is
suspended in a vacuum and a laser beam and feedback is used to cancel out the mirror’s
thermal motion. The feedback narrows the vibrational bandwidth and this effectively cools
the system. The idea was investigated in the context of animal sensory systems by Bialek,
and here we give a broad account.
2023-09-18 – p.12
Bialek’s investigations began with his PhD thesis in which he examined the
boundaries between the macroscopic and the microscopic (Bialek, 1983). His thesis begins
by calculating Schrödinger’s equation for a one-ton brass bar. Due to thermal noise, it will
contain phonons reverberating through it. As the bar is cooled, the number of phonons will
be reduced, but even if we cool it to absolute zero there will still be spontaneous
fluctuations in position due to quantum mechanical uncertainty. There will be a point where
Brownian motion due to thermal energy equals quantum zero-point motion, and Bialek
sought to discover where that cross-over point might be. In particular, he investigated how
the same principles might apply to biological sensory organs. It turns out that the sensory
organs of animals are amazingly sensitive and extend down to at least thermal limits (1 kT of
energy, where k is Boltzmann’s constant and T the temperature). He wondered if any
biological system operated below the thermal limit, and considered ways by which the gap
between the quantum and the classical might be bridged. It is here that he introduces the
principles of feedback cooling, and he spent several years investigating how that principle
might apply in biology. Applied to hearing, for example, he calculates that a frog can detect
displacements that are smaller than 10–11 m, which is broadly comparable with quantum
limits. 6 In another challenging paper, he makes the case that the faint sounds emitted by
the human cochlea as otoacoustic emissions (and recorded with a sensitive microphone in
the ear canal) are also at levels which approach quantum limits (Bialek & Wit, 1984).
As it happened, in the end he considered these efforts a failure and abandoned the
attempt (Bialek, 2012). 7 Nevertheless, his approach provides a keen challenge: in a sensory
system, can feedback cooling be used to overcome thermal noise and move us towards
quantum limits? The principle of feedback cooling is simple but profound – that amplifiers
can be used in place of refrigerators8 – and we believe it is worth persisting with the idea,
for it injects fresh life into Eccles’ proposal. Recent work in physics has made considerable
Bialek calculates that at absolute zero, quantum noise is larger than 10–12 m. At room temperature,
noise displacements are some 40 dB greater than this. He concludes that the ear is a macroscopic quantum
detector (Bialek 1983a, p. 50) and that stereocilia must possess a filter with a bandwidth of 50 Hz or less. As to
the amplifiers used, he concludes that a necessary quantum limited amplifier must have a long memory for
quantum mechanical phase – they must be coherent (op. cit., p. 70).
7
“… (confession time) there was a time when I worked very hard to convince myself that these
quantum limits to measurement could be relevant to biological systems. This project failed, and I would rather
not revisit old failures, so let’s skip this one.” (loc. cit., p. 237).
8
Bialek (1983a), p. 43.
6
2023-09-18 – p.13
progress in using feedback cooling of nanoparticles suspended in an optical cavity. For
example, Gieseler and colleagues have cooled a laser-trapped nanoparticle, 0.14 µm in
diameter to 50 mK (Gieseler et al., 2012). Similarly, as cited by Bialek, it is possible to cool a
suspended 1 g mirror to 7 mK (Corbitt et al., 2007). Theoretically, at least, it is evident that it
is possible to cool a particle to its quantum ground state, so that the occupation number is
less than one quantum (Manikandan & Qvarfort, 2023). Some work has entertained the idea
of levitating a living tardigrade (Romero-Isart et al., 2010).
FIGURE 3. How the effective temperature of a mass hanging on a spring and surrounded by
liquid can be reduced by using a sensor and applying feedback to counteract any vibration.
Initially, the mass experiences drag γ but feedback provides additional drag η, so that the
total drag becomes γ + η and the effective temperature, Teff, becomes Tγ/(γ + η), where T is
the initial temperature. Note that the sensor could be a piezoelectric material; similarly, the
feedback force could also be supplied using a piezo material. From Bialek (1983) and used
with permission.
How does feedback cooling work? Figure 3 is a diagram of a mass hanging on a
spring, and by adding a displacement sensor and feeding back a signal so as to cancel any
perceived motion, the centre-of-mass system can be effectively frozen. That is, the feedback
reduces the mass’s thermal vibration so that its bandwidth is less and its effective
temperature much lower. As Bialek explains, the reduction of noise via feedback has no
limit, since it is possible to narrow the bandwidth as much as we like, although it is paid for
in terms of the response time of the detector and the power expended in pushing on the
mass. So far as the mass is concerned, it experiences the feedback force as if it were extra
drag, and in this way the effective temperature, Teff, can be indefinitely reduced (see
caption).
2023-09-18 – p.14
Thus, through sensing an object and applying negative feedback, it is possible to
create a system that is effectively colder.9 In the same way, it is suggested that an
arrangement of feedback circuits in the pyramidal neurons could reduce their effective
temperature to a level where thermal effects are reduced and quantum mechanical
processes come into play. In particular, cooling may allow a Bose–Einstein condensate to
form in which bosons, such as phonons, crowd into low-energy states and, via quantum
mechanical correlations, the material takes on long-range order. The cortex effectively
becomes a superconductor. A way of getting a feel for what is going on is to recognise that
when a material is cooled its atoms begin to take on precisely defined momenta (nearly
zero), which means, quantum mechanically, that the complementary variable (position)
must be highly indeterminate (via the Heisenberg uncertainty principle). Cooling thus
produces a fundamental change of state, a condensation, in which activity in one part of the
brain is quantum mechanically linked to all the other parts.
Another thing to note is that in a typical superconductor only one entity in 10,000
participates in the phase change, even though it leads to a dramatic change in macroscopic
behaviour. As this small fraction enters the lowest momentum state, the complementary
variable, position, becomes increasingly undefined until eventually there is shared identity
and long-range order. The message here is that cooling does not have to be total: it is
enough if the effective temperature of the psychons is reduced and only a fraction of the
quantum states are low-momentum states (the states with centre-of-mass coordinates
reflecting low effective temperatures), even though the bulk of the material remains at
room temperature and most of the molecules (or nuclei) occupy high momentum states.
Another perspective on Bose–Einstein condensation comes from Marshall (1989)
where, in the latter part of his paper, he argues that consciousness may arise from a system
with long-range order in which the constituent quantum mechanical bosons have
overlapping wave functions, a picture consistent with the psychon model. Marshall lists how
a Bose–Einstein condensate fulfils the requirements for a substrate of consciousness: it is
extended in space, capable of myriad states, and cannot be separated into parts with
Its centre of mass temperature is low, even though its bulk temperature remains near room
temperature. Nevertheless, effective cooling allows quantum phenomena – occupation of low-level quantum
states – to be observed (Romero-Isart et al. 2010), and this provides a route for Bose–Einstein condensation.
9
2023-09-18 – p.15
individual identities (ibid., p 79). He notes that Bose–Einstein condensates normally exist
only at extremely low temperatures (such as in superfluids and superconductors), although
it is possible for a pumped phonon system (such as that suggested by Frölich) to operate at
room temperature. Marshall therefore favours the pumped phonon system, as does
Penrose (2022), but here we suggest that the low-temperature approach provided by
feedback cooling could be a more realistic option.
There is one additional factor in this scheme which needs to be considered, and that
is to give an indication of how feedback might be sensed and applied. In this connection, it is
pointed out that the material of which nerve axons are made has the unique and unusual
property of being piezoelectric (Costa et al., 2018). What this means is that when an action
potential passes along an axon, its diameter momentarily changes. Most piezoelectric
materials behave reciprocally, meaning that a change in diameter is also accompanied by a
change in voltage (see Ludwig et al. (2001) for the biological example of prestin, a
bidirectional transducer in cochlear outer hair cells). Thus, by using piezoelectricity and
feedback, it appears possible to devise a scheme whereby a particular site within a psychon
could be effectively frozen. Any change in diameter due to thermal noise, for example, could
be compensated for by a change in voltage.10 This piezoelectric property in nerves deserves
greater attention, as it provides a possible explanation of why this special property might
have arisen. As inspection of Figure 3 shows, piezoelectrical properties are required in order
for feedback cooling to operate.
Quantum accelerators
When quantum computers are mentioned, most people think of a large room filled
with rows of cryogenic equipment and racks of electronics. 11 A team based in Canberra and
It is again helpful to consider the effects of ephaptic (electrical) potentials at gap junctions. In this
way the more complicated effects of action potentials in the synaptic cleft can be treated separately. For a
perspective on analog and digital processing in neural networks, see Debanne et al. (2013), who point out that
the effects of action potentials and digital signalling have been overemphasised at the expense of electrical
synapses and analog signalling.
11
For reviews of quantum computers see Ladd et al. (2010) and de Leon et al. (2021). An engaging
introduction to the topic is Feynman (1986). Perspectives on theories of mind can be found in Aaronson
(2013).
10
2023-09-18 – p.16
Stuttgart are changing that conception. They have developed a small room-temperature
quantum computer, small enough to hold in your hand, that they describe as a “quantum
accelerator” (Doherty, 2021). Doherty and his team are part a research spin-off company
who have developed, and now offering for sale, a desk-top device that plugs in to a
conventional computer and speeds up difficult computations (such as cryptographic
problems), greatly increasing computing power. The quantum accelerator developed by the
Australian–German company Quantum Brilliance 12 is a solid-state device based on atoms of
nitrogen embedded within a diamond lattice, and contains a total of 5 quantum bits
(qubits), although the aim is to increase that number considerably.
The core idea of the present paper is that the human brain also contains a quantum
accelerator which speeds up normal neural processing. The brain, we suggest, can either
motor along using its standard neural networks to deal with inputs and outputs, or it can
add on a quantum accelerator to perform faster and more complex computations. (The
speed advantages of quantum computation were first laid out by Deutsch and Jozsa (1992)).
In the first case, the processing is done unconsciously; in the latter case, the quantum
processing involves qualia. The owner of the computer, the self, is vividly aware of these
qualia but not of the subconscious activity. That distinction will be brought out in the
following section, where sleepwalkers and zombies are discussed.
Room-temperature diamond computing was discovered in 2001, and work since
then has demonstrated that it works. The practical problems are fabricating them
consistently and interfacing them with conventional computers, and Quantum Brilliance is
working on these aspects.
The quantum accelerator consists of an array of nodes within a diamond crystal in
which each node contains a nitrogen vacancy (where a nitrogen atom substitutes for a
carbon atom). These NV defects contain a cluster of nuclear spins – the intrinsic nitrogen
nuclear spin and a handful of nearby 13C nuclear spin impurities – which act as the qubits of
the system. The NV centres act as quantum buses that initialise and readout the qubits, and
quantum computations are controlled by microwave, optical, and magnetic fields (which is
proprietary information). The remarkable part of the system is the long electron spin
12
https://quantumbrilliance.com.
2023-09-18 – p.17
coherence time, about 1 ms, which is the longest of any known solid-state electron at room
temperature. This allows the NV centre to initialise the spins, processing to happen, and
read-out to take place without decoherence setting in.
Development is proceeding, with the short-term goal being to build quantum
accelerators with more than 50 qubits, which will outperform CPUs of comparable size and
weight (computing power increases exponentially as the number of qubits). Ultimately,
there will be massively parallel quantum accelerators which will far exceed the capabilities
of today’s classical supercomputers. Applied to neural networks, it has been calculated that
a quantum algorithm will be n5 times faster than the best classical algorithm (Doherty, 2021,
p. 78). The conclusion to be drawn here is that nature would be able to create immense
computing power of unrivalled sophistication by drawing on quantum computation,
especially if n were large. A discussion of how this enormously expanded capacity might be a
powerful factor in evolution is provided later.
Decoherence is the biggest enemy of a quantum computer, and in making a better
quantum computer the goal is always to minimise it (Schlosshauer, 2019; Stamp, 2006). The
field is highly technical, but there are certain configurations of quantum systems – for
example, decoherence-free subspaces – in where quantum information can be encoded such
that it is immune from environmental intrusion (Schlosshauer, 2019, Sec. 5.1). 13 See Lidar
(2014) for additional details of how to minimise decoherence and Viola and Fortunato
(2002) for an actual example. Speculations of the link between consciousness and the
existence of some long-lived spin states in phosphorus atoms have already been made
(Fisher, 2015).
It is notable that recent investigations have used quantum techniques to perform
noninvasive thermometry on living cells (e.g. Kucsko et al. (2013)), and this is a potential
For the human brain, we are probably looking for decoherence times in the millisecond range, even
though, at room temperature, the decoherence time has been calculated as about 10–20 sec (Tegmark, 2000).
This means that ways to create decoherence-free subspaces are important. One possible method outlined by
Schlosshauer is to create environmental symmetry so that each qubit operator couples to the environment in
exactly the same way. If so, in a very large qubit system “essentially every state in the system’s Hilbert space
will be immune to decoherence” (Schlosshauer 2019, p. 29). The speculation put forward here is that coherent
electrical or magnetic fields in the brain (as evident in the EEG and MEG) might affect all the qubits
symmetrically and make them immune from decoherence. It is also significant that decoherence falls
particularly rapidly in insulators (Stamp 2006, p. 480), and we note that the myelin surrounding a nerve fibre is
a high-resistance insulator.
13
2023-09-18 – p.18
avenue for experimentally detecting localised cooling effects in the cortex. Once more, the
technique is based on NV centres in diamond, and the Kucsko group have detected
temperature changes within a living cell of less than 2 mK. An alternative approach could be
to use nuclear magnetic spectroscopy (NMS) to measure temperatures within a conscious
brain. If an NMS probe reveals a narrow line-width, this indicates that the signal has
encountered low-temperature nuclei (Buonocore & Maddock, 2015). 14 In principle, such
non-invasive experiments are relatively simple.
Of sleepwalkers and zombies
Why are we conscious? And what is it that makes us conscious? These are the
notoriously ‘hard’ questions of consciousness (Chalmers, 1995b, 1996), and philosophers
have grappled with them since philosophy began. A valuable perspective on how
consciousness relates to matter and the evolutionary advantage it provides was set out
some time ago by Owen Flanagan, and is based on reflections about sleep, dreams, and
zombies (Flanagan, 1995b). His perspective provides a unique handle for tackling the hard
questions head on, and provides an opening for possible answers.
To begin, there are two realms, the classical and the quantum, and this paper aims
to establish that there is a potential gateway between them that is opened and shut by
feedback cooling. Al-Khalili and McFadden (2014) present a picture (their p. 314) of a living
cell as being like a ship afloat on a thermodynamic sea, tossed back and forth by thermal
noise, but being ultimately connected to the quantum world on the sea floor. In these
terms, the classical brain, warm and wet, is tossed around by thermal vibrations, but by
making use of feedback cooling, it is able to connect to the quantum realm. When it enters
the quantum realm, we have access to a non-classical world governed by quantum
phenomena – nonlocality, entanglement, and unity – which brings us a consciousness filled
with feelings, colours, sounds, odors, thoughts, and all the other furniture of awareness. It is
a doorway through the looking glass, an opening of the doors of perception.
To be clear, it is the nuclei that are cold; most of the brain remains at room temperature. This is like
in a diamond-based quantum accelerator, where the atoms are at room temperature but the nuclei are
effectively at 1 mK.
14
2023-09-18 – p.19
Staying with this thought, consider that together with the intricate neural machinery
inside our brain, we also have a mind which, during wakefulness, works seamlessly with it.
The question that arises is, why isn’t everything done subconsciously, in the dark? The brain
is an anatomical structure that seems perfectly capable of working away unconsciously,
giving us processing power to receive signals from our senses and issue commands to our
muscles. There is much that can be done subconsciously, as demonstrated by the prime
example of the sleepwalker, a case raised by Flanagan and which we reexamine here. The
sleepwalker can go to the fridge in the middle of the night, fill a glass of water from a tap,
eat a snack, and return to bed – all done without awareness, as later paragraphs will
document. On top of that, however, this paper suggests that if positive feedback is applied
to a certain structure in our cortex, an astounding change occurs: we suddenly become
awake, and our senses are filled with a cornucopia of qualia, all simultaneously accessible to
our awareness and able to be willingly acted upon. We have entered the quantum realm,
where we have a front-row insider’s view.
On this picture, the outstanding feature of consciousness is that it bestows immense
processing power. Just like the add-on quantum accelerator, it multiplies processing power,
allowing multiple inputs and outputs to be processed at once. We become the operator of
an awake quantum computer, not a fumbling sleepwalker. We are the ‘ghost in the
machine’ which not only receives inputs from all over our bodies but can issue commands
that allow the acrobat to execute a triple somersault with twist in just the way they
imagined. The fast quantum computer sits above the classical neural computer, an
architecture which allows our minds to program our brains: with practice, our minds can
consolidate neural pathways so that things can be learnt and done automatically,
subconsciously. In reverse, our conscious mind has direct access to all the “hard-wired”
memory traces laid down over the years in various regions of the brain.
Although our neural hardware is amazingly sophisticated, the extra ingredient that
consciousness brings is an accompanying boost in processing power. An added bonus, we
might add, is the facility to enjoy that power, as we quietly take in a glowing sunset. This is
where human creativity comes in, whether painter, photographer, novelist, gymnast, poet,
or scientist. It is the inspiration which drives us as we look out upon the physical world. It is
the reason we are conscious.
2023-09-18 – p.20
Sleepwalkers
Despite a variety of quantum theories of consciousness (Gao, 2022), few of them
have clearly addressed what the benefits of being conscious are. But of direct relevance is a
rich literature on philosophical zombies, creatures who are supposed to have all the
faculties of conscious humans, save consciousness (Kirk, 2023). Although they lack qualia,
they are still assumed to display all the functions of normal humans. This paper takes the
view that such an assumption is wrong: a zombie is severely compromised by a lack of
computing power. Without a quantum accelerator, it will be slow and clumsy, and in fact
these are precisely the qualities traditionally ascribed to Haitian zombies. If real-life zombies
did exist, they would be easily distinguished from real-life humans: they would have a glazed
look, stumble along, and be bad conversationalists. They would also probably make bad
philosophers. They would be exactly like sleepwalkers.
For some reason, sleepwalkers have not been much discussed by philosophers, but
in fact sleepwalking is a very curious phenomenon that repays close attention (Flanagan,
1995a, 1996). The contention here is that if one is looking for beings devoid of qualia, it is
much more fruitful to consider sleepwalkers, not zombies. 15 Crucially, sleepwalkers
indubitably exist – they are real people who, after a restless night’s sleep, wake to become
normal human beings who can report what they’ve been through – and they provide
valuable insights into the difference that consciousness makes.
The literature on sleepwalking is mostly in neurological journals, specifically those
dealing with sleep behaviour disorders (SBDs). A useful review (Castelnovo et al., 2018)
classifies sleepwalking as a sleep parasomnia characterised by incomplete arousal from
deep (non-rapid eye movement or NREM) sleep. During episodes of sleepwalking, there is
an absence of rapid eye movement but the muscles controlling body movement remain
active (the atonia that normally prevents us from moving during sleep and acting out our
dreams is absent). This means that complex movements and behaviours are still possible,
even though the sleepwalker is more or less unresponsive to their surroundings and their
behaviour is “dissociated from awareness” (Castelnovo et al., 2018, p.471). That is, the
Stapp (1993) recognised that sleepwalking is a distinct, unconscious state. When defining
consciousness (p. 234) he notes that it “is extinguished during dreamless sleep … [and is] … absent in the state
of somnambulism.”
15
2023-09-18 – p.21
sleepwalker is operating below the threshold of consciousness, and they normally go back
to bed and “continue sleeping without reaching conscious awareness at any point” (loc. cit.).
In the morning, they have no memory of the episode. There may also be somniloquy (sleeptalking), with slow speech and inappropriate responses to questions. It is estimated that
perhaps 2% of adults sleepwalk, although the proportion is about 20% in children aged 2 to
6 years.
In the 12th and 13th centuries it was believed that during sleepwalking the soul split
from the body and was temporarily elsewhere (Sukel, 2019). In the 1300’s, Pope Clement V
absolved sleepwalkers from moral responsibility for actions their bodies may have
committed while sleepwalking. These perspectives deserve more consideration, for as
Chalmers (2023) notes, while conscious beings are moral agents, unconscious ones are not.
A personal account from a sleepwalker is illuminating (Hammond, 2012). She
recounts how she gets out of bed in the middle of the night and wanders around her flat, all
the while remaining fast asleep. In the morning she doesn’t recall a thing. She describes how
sleepwalkers tend to have open eyes but a glazed expression; they move around, usually in
the dark, navigating largely from memory. Hammond relates how on one occasion she
suddenly woke when she clumsily smashed a glass while filling it from a tap. A medical case
describes a sleepwalker who went out of the house and started driving, all while fast asleep.
Sleepwalkers tend not to notice other people, even when that person tries to wake them. I
have spoken to a sleepwalker who relates how she sent a text message to her husband,
copied for good measure to visiting friends, in which she complained, in rude and garbled
language, that they had the TV on too loud. She has no memory of sending it, and finds it
hard to believe (but for the irrefutable evidence on her phone) that she would send such a
message. She does remember going to bed early and being annoyed at the loudness of the
television. Clearly, subconscious processing can occur at a remarkably high level, but, even
with that facility, becoming conscious calls for more than just that. What might that extra
ingredient be?
The distinctive feature of sleepwalking is that body movements are slow. Walking is
slow, actions are slow and clumsy, speech is slow and indistinct, typing is full of mistakes –
just the sort of symptoms one might expect if the processing power of a computer
controlling a robot were suddenly compromised. The frame rate of its display would plunge
2023-09-18 – p.22
– similar to what might be expected if a quantum computer were to somehow lose its
accelerator. Lacking consciousness, and relying only on subconscious brain circuits, the
sleepwalker is forced to act slowly. No wonder the eyes are glazed and the face
expressionless – the somnambulist is in deep sleep. In common terms, there is nothing it is
like to be a sleepwalker, no feeling of here-I-am.
EEG studies have shown that the prefrontal cortex and hippocampus of sleepwalkers
are profoundly disengaged, reflecting automatic behaviour and inactive memory circuits
(Krouse, 2022). Importantly, the distinctive 40 Hz oscillation between thalamus and cortex, a
marker of qualia being present (when awake or in REM sleep), is decidedly absent
(Flanagan, 1995a, 1996; Llinas & Paré, 1991). The result is that sleepwalkers put themselves
in “great danger, given the absence of conscious control, awareness, and perceived pain”
(Castelnovo et al., 2018, p.478). Having no qualia is a risky state of affairs (Schenk et al.,
1989), even if automatic mechanisms (involving both afferent and efferent nerve traffic),
allow complex manoeuvres to be performed.16 The situation has similarities to another
puzzling condition, blind-sight. 17
We need much more research on sleepwalkers (and on blind-sight) to chart the
limits of subconscious processing. Is there truly nothing it is like to be a sleepwalker? Are
such people susceptible to common visual illusions? Flanagan (1995a, p. 10) says “it is
obscure whether, or in what precise sense, sleepwalkers and talkers are experiential
blanks,” and this aspect deserves further study. As Flanagan emphasises, if someone says
they are conscious, that is self-evidently true. In contrast, it seems plain that a zombie is
Llinas & Paré (1991) call attention to what they call the central paradox of REM sleep. Stimuli which
are readily perceived when awake generally do not awaken subjects in REM sleep, even though the primary
evoked cortical responses, recorded electrically, are considerably higher than in the waking state (ibid.,
p. 524). That is, the 40 Hz circuits have the ability to override other brain activity. They also remind us that
cartoleptics can suddenly fall asleep during the day, presumably due to a faulty on/off switch.
17
A lot could be said about blind-sight but we limit ourselves to one perspective. In Godfrey-Smith
(2016) there is a discussion of blind sight (p. 88) in connection with the work of Milner and Goodale who
suppose there are two paths for visual information: the ventral stream and the dorsal stream. These
researchers suggest that the ventral stream is conscious whereas the dorsal stream is unconscious. If the
former is disabled by brain injury, the latter remains as blind sight. In our model, however, the difference
between the two sorts of vision hinges on whether or not feedback cooling is operating in visual cortex.
16
2023-09-18 – p.23
incapable of saying such a thing, and a similar impossibility also seems true of a
sleepwalker. 18
Zombies revisited
This brings us to zombies, who have occupied a large philosophical literature (see
Seager (n.d.) and its references). An accessible and wide-ranging perspective into the
workings of zombies and how they relate to conscious beings has also been given by Kirk
(1974). Of direct relevance to the model of consciousness set out here is his consideration of
what it might be like to be “Zulliver” – a parallel to the Gulliver of Gulliver’s Travels except
that his brain has been invaded by technologically advanced microscopic beings far smaller
than Lilliputians. These creatures are able to disconnect his brain from his nerves, and then
monitor the ascending nerves, the afferents, and to stimulate the descending fibres, the
efferents, so as to recreate behaviour indistinguishable from the human Gulliver. Zulliver
acts like what Kirk calls a “super-puppet, with resident puppeteers”. The clever invaders use
sophisticated algorithms to analyse incoming nerve traffic and compute what outgoing
signals are needed to produce the required behaviour. The point is that no-one would want
to say that Zulliver was conscious, even though his behaviour was similar to his pre-invasion
state. He would, in fact, be a machine, a zombie. Elsewhere in his argument, Kirk alludes to,
but does not take up, cases of sleep-walking and sleep-talking, even though I would
maintain that the parallels are indeed exact.
The crucial difference between Gulliver and Zulliver, I suggest, is that Gulliver carries
a quantum computer in his head whereas Zulliver is limited to whatever common or garden
computing power the invaders have been able to assemble. The point is that, to work like a
human, the necessary computing power would be immense: the information from each
afferent nerve has to be shared with every other afferent nerve and the ensuing output
state computed in real time so as to produce a driving signal for an efferent nerve, each one
of which also has be considered in relation to all the other efferents. It is a formidable task,
Unlike the hypotheticals of zombies, this is an experiential fact that can be put to the test. Strawson
summarises: “So when people say that consciousness is a mystery, as so many do today, they’re wrong,
because we know what it is. In fact, we know exactly what it is. It’s the most familiar thing there is” (Strawson,
2019, p. 12). Denying that view, he says, is a Very Large Mistake (ibid., p. 13). Instead, it is our conception of
matter that is problematic.
18
2023-09-18 – p.24
and without almighty computing power at hand poor Zulliver is left as slow and mindless as
a zombie, a sleepwalker. It is a magical gift that we have a mind, a quantum accelerator,
that can compute all the efferent inputs and afferent outputs and act – smoothly and
seamlessly – like a sentient, thinking, speaking, living human. Seager (n.d.) makes the point
that the logical possibility that zombies might exist automatically refutes physicalism, for if
there were such an entity that had the same physical properties as me, but had none of my
mental properties, then the assertion that everything is ultimately physical must be false.
The argument is even stronger when applied to sleepwalkers, for unlike zombies, such
beings indeed exist and can be found all around us. 19 The fundamental difference between a
sleepwalker and the same person when awake is that the former is (temporarily)
unconscious, even if texting, while the latter, of course, is gloriously awake.
Kirk uses his discussion of Zulliver to argue that there is something about human
beings which materialism leaves out. Briefly, the missing ingredient is self-awareness. A
mind has a unified experience of its multiple inputs and outputs (except for certain
unconscious functions controlled by the autonomic nervous system), and is powerful
enough that it can operate in real time to judge and choose what the next moment should
bring. The general thrust of this paper is that the cooled quantum field in our brain is in
intimate connection with the entire quantum realm and all its possibilities, and that, in this
way, consciousness arises. 20
Consciousness has immense power because it is in just the right place to mediate
between the physical world and the quantum world, between input and output. The
quantum field represents the state of the world and computes what is needed to make our
way forward in life. By existing it enables mathematics, science, literature, art, and all other
creative endeavours. Consciousness relies on our minds being poised at the pinnacle
between efferents and afferents, and feedback cooling is the key to its awakening.
The considerations here argue against physicalism and instead support an interactive
dualism as described by Popper and Eccles. There is matter – atoms and molecules – on one
Seager notes that “it is logically possible that I might become a zombie in the next instant.” A
stronger, more empirical statement is that I could well become a sleepwalker after I go to bed tonight.
20
An interesting question following on from this is whether a quantum robot (Benioff, 1998) could be
conscious.
19
2023-09-18 – p.25
side and a quantum field – from which qualia emerge – on the other. Depending on
interpretation, neutral monists and panpsychists may also find areas of agreement.
Although this picture narrows the explanatory gap, it is acknowledged that some sort of gap
still seems to remain – why should quantum computations necessarily give rise to qualia?
This question deserves a section of its own.
Qualia and some metaphysics
As Chalmers has forcefully reminded us, quantum mechanics by itself does not solve
the hard problem (Chalmers, 1996). There is still an explanatory gap between the states of
bosons and the subjective impression of a luminous patch of blue. As Lockwood (1998) puts
it, why do certain physical events in my brain give rise to subjective correlates when
agitation of molecules in a stirred cup of tea presumably does not (ibid., p. 85). Lockwood
inclines to the view that it is just a brute fact. We are entering metaphysical waters here,
but to keep matters brief we highlight two clear landmarks.
First, there is a commendably readable paper which considers the metaphysics of
quantum mechanics and clearly maps out the territory (Marshall, 1989). Marshall begins by
describing three realms – the mental, the bodily, and the quantum. Then, from the
existence of two fundamental properties of consciousness – one its unity even though
extended in space, and two its complexity – he concludes that the brain processes
corresponding to states of consciousness cannot be described by classical physics (ibid.,
p. 74). That is, the mental and bodily realms both emerge from different sorts of underlying
quantum stuff (as he illustrates in his Figure 2). He therefore suggests that neutral monism,
or perhaps some sort of panpsychism, might be an appropriate way of describing the world,
although he admits that dualists may well be able to live with the quantum mechanical
picture. 21 Neutral monism is a position that is compatible with the “general monism /
panpsychism” advocated by Nagel (2012, p. 56,57), the panpsychism of Strawson (2019) and
Stubenberg (1998), and the protoconsciousness favoured by Chalmers (1996) and Penrose
(2022). If the whole world is quantum mechanical through and through then classical
I take this to mean “pure” dualists, and not interaction dualists such as Eccles and Popper who are
willing to embrace quantum mechanics. So both Marshall and I agree that consciousness does have an
“isomorph” in physics, as he puts it (Marshall, 1989, p. 81).
21
2023-09-18 – p.26
physics actually becomes an unwanted hindrance. A wide-ranging review of how quantum
mechanics relates to classical physics can be found in Schlosshauer (2019). According to
him, the key is the notion of decoherence, which acts as the boundary between the
quantum and classical realms (ibid., p.2). It is unfortunate that Nagel does not mention
quantum mechanics at all in his work. 22
In this context I raise a second point, based largely on intuition. As a speculation, it
may be that qualia are necessary because we have two different coordinate systems in our
brain, each associated with the two computers that reside there. We have the position –
the cartesian coordinates – of the pyramidal cells within our cortex, and the coordinates of
the Hilbert space in which quantum processing is done.23 The suggestion is that these two
systems are different but need to be kept in alignment, and that qualia are necessary to
“label” the results of the quantum accelerator, separate from those of the basic reflex
computer.
To expand this a little, the low-level computer is used to calculate reflex reactions. It
operates unconsciously and is involved in sleepwalking. Its coordinates are effectively those
of the pyramidal cells, and it provides a map of neural inputs and outputs. Here we point to
the octopus, which has separate reflex computers in each of its eight arms and a second
high-level computer in its brain, but both need to be able to refer to the same things.
Likewise, we have a neural computer formed from pyramidal clusters and a second
quantum computer – the accelerator – sitting on top of it. The neural computer operates in
cartesian space, and the accelerator operates in Hilbert space, but the two need to have a
common reference point. This means there needs to be strict mapping between the
computers – as the octopus case illustrates24 – so that both coordinate systems operate
seamlessly. The suggestion made here is that qualia, which are the eigenstates of the
quantum computer, need to be clearly distinguished as products of the mental self but still
Nagel points to Sorell, Strawson, Hartshorne, and Whitehead as some of those supporting his
position (footnote #16). In another footnote (#11) he delivers a cutting attack on reductive materialism, and on
p. 26 he supplies apt quotes from Schrödinger, de Broglie, Eddington, Planck, and Einstein to reinforce his
argument that mind and matter are different aspects of the same stuff.
23
Schlosshauer (2019) explains that “Hilbert space is a vast and seemingly egalitarian place. If |ψ1>
and |ψ2> represent two possible states of a quantum system, then quantum mechanics postulates that an
arbitrary superposition α|ψ1> + β|ψ2> constitutes another possible physical state” (ibid., p. 2).
24
See Godfrey-Smith (2016).
22
2023-09-18 – p.27
refer back to the same (spatially defined) inputs and outputs. In brief, qualia may be the
quantum mechanical ‘labels’ that allow mind and body to synchronise. 25
Evolution of consciousness
The foregoing gives insights into why and how consciousness evolved. Primates may
well have evolved to the point of acting like sleepwalkers, but by adding feedback cooling to
the same neuronal architecture, the possibility of having a quantum computer with superior
processing power becomes possible. Feedback cooling involves adding feedback circuits on
top of the neuronal processor, and with this quantum leap (so to speak), consciousness
emerged.26 With the light of consciousness, we are able to instantly survey all our neuronal
inputs and outputs, an enormous advantage in terms of decision-making and survival. This is
the adaptive significance of consciousness.
The paper by Marshall (1989) describes how consciousness arises from a Bose–
Einstein condensate, work which provides a nice unifying account of how quantum
mechanics underlies consciousness. When Marshall asks why consciousness exists in the
world, his answer is close to the one outlined here: he says that “consciousness is a
necessary concomitant of a certain kind of holistic system which, if it were intervened
between stimulus and response, would enable the response to be more integrated” (and
hence favouring survival) (Marshall, 1989, p. 81).
Moreover, with the ability for the conscious computer to program the subconscious
computer, one can understand that an enormous increase in adaptability and processing
power becomes possible. Humans can teach themselves how to perform certain desired
actions – play a sonata, perform a double back-flip with twist, even strive to understand
themselves and the world around them. Consciousness was a great advance, and it can be
reasonably argued that many animals have also learned to use it. A not unlikely proposition
Any mismatch between the two computers could give rise to illusions – either minor and temporary
(such as perceiving stationary circles as rotating) or major and long-lasting (such as feeling pain in a phantom
limb). It would be of interest to test whether sleepwalkers, who operate only with the lower-level computer,
are susceptible to common visual or auditory illusions.
26
Godfrey-Smith (2016) inclines to the view that consciousness is not an on/off affair, but that it is
graded (p. 87). See also Godfrey-Smith (2021), p. 262.
25
2023-09-18 – p.28
is that all animals that sleep – most of them – might be conscious beings (Descartes and his
followers notwithstanding, see Huxley (1874)). For the other side of consciousness is that it
requires expenditure of energy – feedback circuits need energy to operate – and so all
conscious creatures need restorative sleep. 27 Sleep is the time when all conscious creatures
become unconscious, and during that phase all the reprogramming of the physical brain can
take place and the energy circuits replenished. We have also seen that during sleep it is
even possible for sleepwalking to occur, depending on how well our automatic subconscious
circuits have been trained.
Many philosophers have been puzzled by why evolution should have taken a path
from unconscious reflexes to complex conscious behaviour, in humans at least. The puzzle is
clearly set out by Lockwood (1998), where he notes that sentience (consciousness), which
“sticks out like a sore thumb” (ibid., p. 84), must confer some adaptive advantage.
Specifically, he assumes that there are some cognitive tasks which either cannot be
performed at all without sentience, or more to the point, as put forward in this paper, that
they can be performed more efficiently with sentience (Lockwood, 1998, p. 83). The parallel
he makes with blind-sight is particularly apt.
Flanagan continues on from his zombie ruminations, discussed earlier, by asking
another hard question – why did creatures need to be more than just “informationally
sensitive” – and reports that he found a total absence of credible theories (Flanagan, 1995b,
p. 319). However, he does provide one clue by suggesting that in times past there might
have arisen a “computational bottleneck", which led to a problem of information overload.
He mentions serial computers and parallel computers, and this appears to be on the right
track, although he mistakenly, I think, identifies consciousness with the serial variety. The
real distinction, I suggest, should be that between a classical computer and a quantum
computer. The standard computer is no match for the quantum computer, which can
operate in parallel and solve wholly different classes of problems (Deutsch & Jozsa, 1992;
Penrose, 1989; Schlosshauer, 2019). Moreover, a quantum computer can be built on top of
a classical computer (and then called a quantum accelerator), enabling an animal to evolve
It is known that all mammals undergo REM sleep, which could be a marker that these animals, at
least, have dedicated consciousness-raising circuits in which they dream (Flanagan, 1995a). Octopuses are also
thought to dream in that they undergo periods of rapid skin colour change while asleep (Godrey-Smith, 2016).
27
2023-09-18 – p.29
and overcome computational bottlenecks. All it requires is for a mechanism to be devised to
cool down the dendritic cluster in the cortex and shift it into quantum mode. With quantum
processing enabled, the animal becomes fully conscious and its skill repertoire is speeded up
and refined. The difference in performance is like that between a sleepwalker and the same
person fully awake. It is now possible to understand why such an intelligence-boosted
creature would win an evolutionary battle against what Flanagan calls “zombie-like
information-sensitive organisms” (Flanagan, 1995b, p. 321).
Thomas Nagel is similarly puzzled when he looks at evolutionary reductionism
(Nagel, 2012). If materialism cannot explain the fundamental mind–body problem, it
certainly can’t provide a credible account of how conscious minds evolved from unconscious
ones, however hard it tries (Chs. 1–4, and the list of references in their endnotes). It will
take more than “just the lacing of life with a tincture of qualia” (p. 44) and at some point he
thinks evolutionary biology will need to make a fresh start, starting with an understanding of
the mind and the important role it plays in living creatures. The basic question is how can a
single accidental mutation create a conscious creature from one that has none, and why
should that mutation have more evolutionary success than its unconscious rival? Nagel finds
that, despite its great achievements, the prevailing austere doctrine – that everything is due
to the action of forces on physical matter – is untenable. That can only be part of the truth,
he believes, and suggests the answer must lie in some sort of neutral monism, rather than
dualism. We put aside a metaphysical discussion here, but, as suggested earlier, if the
missing ingredient is quantum mechanics, then dualistic interactionism can overcome this
sticking point. Interestingly, Nagel mentions concepts such as relativity, but quantum
mechanics itself is never on the table. He accepts that mind is a biological phenomenon
(p. 45), but, as matters stand, he cannot see how to explain it naturalistically. He regards the
resources of physical science as inadequate, but fails to engage with the possibilities that
quantum mechanics offers.
This paper proposes that the long-sought explanation of how the physical and the
mental sides of an organism can develop together (Nagel, 2012, pp. 46-47) lies in the realm
of quantum computers. The co-existence in the one brain of both a classical and a quantum
computer renders the facts intelligible. The emergence of a quantum computer as an addon to an existing neural network computer explains why, in Nagel’s words, “the appearance
2023-09-18 – p.30
of complex organisms, and not merely behaviourally complex organisms, was likely” (p. 48).
The quantum computer allows the physical and the mental to work together to achieve a
wondrous thing – the universe waking up and becoming aware of itself (p. 85).
General discussion
We have set out a speculative, but considered proposal for how the human brain
may operate as a room temperature quantum computer. Much more could be said, but for
now we let the model speak for itself. At its core, the picture is one in which feedback
cooling in the cortex allows quantum mechanical fields to be established in assemblies of
pyramidal cells (called dendrons by Eccles), and which, when energised (in Eccles’
terminology, becoming psychons), can be identified with the luminous mind. In a word, we
say that, quantum mechanically speaking, mind is matter waking up. The model places the
mind just where we might expect it – at the pinnacle of the afferent and efferent systems –
and each psychon supplies one qubit to a quantum field extending over the entire cortical
sheet. Effectively, the cortex then becomes a superconductor.
An apt conceptual model of what we have been describing is Indra’s net, sometimes
called the pearls of Indra, which in Buddhist tradition has been likened to the mind (see
Wikipedia for a brief outline). Each pearl is perfectly reflective, and reflects the images of all
its neighbouring pearls, just like each psychon is reciprocally connected to all of its
neighbours. The resulting quantum mechanical field creates a powerful quantum computer
which can be identified with consciousness.28 As we have noted in the section on
sleepwalkers, the 40 Hz loop is highly active during periods of wakefulness and REM sleep,
which is just when qualia arise. At other times, the loop is quiescent and we are
unconscious. Ultimately, then, our thalamus is responsible for waking us up (Redinbaugh et
al., 2020).
28 In the case of the cortex it may be more apt to imagine Indra’s net as 2-dimensional rather than
3-d, but we leave that for further research.
2023-09-18 – p.31
Advantages of the model
There are a number of advantages of the two-level computer model, which we now
enumerate.
1. Pinnacle of efferent and afferent
They are poised just where the mind needs to be for both sensing and acting. The
psychons are already at the junction in their unconscious form, and they just need feedback
cooling to switch them into their higher-power quantum mechanical gear. They are in the
right place to latch on to the information stream and begin to process it nonalgorithmically,
alleviating a concern that Grush and Churchland had with the Penrose–Hameroff model
(Grush & Churchland, 1995). The section dealing with the evolutionary emergence of
consciousness makes the case in its simplest form.
2. Consistent with anatomy
The psychon model is absolutely specific in pointing to its anatomical substrate. The
model as updated here says that feedback cooling switches clusters of pyramidal cells from
subconscious mode into conscious mode, producing a coherent entity – a psychon – which
becomes entangled with all the other 40 million or so psychons to form a Bose–Einstein
condensate. Our conscious mind is therefore a powerful quantum accelerator sitting on top
of a lower-level neurocomputer. Working together, the combination bestows on us
extraordinary mental abilities (Penrose, 1989). Through reprogramming of the lower-level
computer by the upper-level computer, we can learn novel things, whether it be acrobatics
or a new language. We are able to see mathematical proofs, or perhaps reduce numbers to
prime factors in our heads (as Gauss was reportedly able to do), and gives us insight into
what Ramanujan and similar savants could do. We might also have a handle on
understanding subtler dimensions of the human mind – is meditation, for example, a case of
the upper computer exploring itself? 29
Meditational experiences seem to suggest that it may be possible to shut down the neural
computer while leaving oneself immersed in the quantum computer. One thing this ancient practice clearly
demonstrates is that consciousness is either on or off – it is not graded in the way that Godfrey-Smith (2021,
p. 262) sees it.
29
2023-09-18 – p.32
3. Consistent with reentrant circuits and 40 Hz loops
We have suggested there is a vital functional role for feedback loops within the
psychons of the cortical sheet. To elaborate a little, it is worth underlining the importance of
feedback circuits within the brain, especially the 40 Hz thalamocortical loop, which is known
to play a major role in regulating consciousness (Llinas & Paré, 1991). All sensory messages
(except smell) reach the cerebral cortex though the thalamus. Moreover, pyramidal cells in
layer VI project back to the area of the thalamus where their specific input arises, although
the number of corticothalamic fibres is about 10 times larger than the number of
thalamocortical fibres (ibid, p. 525). The neurophysiological literature describes how brains
sustain multiple feedback circuits, often called reentrant or reverberant circuits, of many
kinds, and their combined activity is thought to underlie the electroencephalogram (the
EEG). The 40 Hz activity falls within the gamma band of the EEG, and a key property is that it
acts in synchrony over the entire cortical mantle (Llinas & Paré, 1991, p. 527–9), and this has
important quantum mechanical implications. A good overview of reentrant feedback loops
and how they relate to the generation of qualia is given by Opwood (2013).
Opwood’s survey recognises the immense amount of research that has been done in
the area. Although Llinas and Paré (1991) explicitly hypothesised that the thalamocortical
system is “the consciousness-generating apparatus”, the most influential work has been
that of Edelman who has set out descriptions of how 40 Hz circuits could be the locus of
conscious percepts (Edelman, 1992). Feedback can operate at different levels, but Edelman
claims that the 40 Hz thalamocortical loop is fundamental and in fact he identifies it with
consciousness itself (Edelman, 1992; Edelman & Gally, 2013). His implication is that
reverberating activity between the thalamus and pyramidal cells in the cortex could be the
actual origin of qualia. Whereas that might be true, Edelman does not explain how qualia
necessarily arise from what is, fundamentally, neural activity. He does call the qualia
assumption “tricky”, and despite a lengthy discussion, the explanatory gap, in the end,
lingers.
In the model proposed here, the 40 Hz thalomocortical loop has the important role
of switching cortical cooling on (awake) and off (asleep). This means the loop is essential for
consciousness, but by itself it is not sufficient. So even though Llinas & Paré and Edelman
both provide valuable context for how consciousness is generated, the picture remains
2023-09-18 – p.33
general, whereas, by comparison, Eccles pin-points the locus to specific clusters of dendrons
(or psychons) in the cortex. Although the psychons are actually switched on by the 40 Hz
thalamo-cortical and cortico-cortical loops, it is the tight feedback loops within the psychons
themselves – a very local loop within a domain of just 60 × 1500 µm – which lead to
feedback cooling and consciousness. These small loops probably operate at considerably
higher frequencies (auditory frequencies of 1 to 10 kHz were suggested earlier).
4. The feedback cooling idea is testable
As set out earlier, NMS techniques could be used to detect cold spots in the brain
when it is awake. Cooler temperatures reflect the presence of bosons which take part in
quantum mechanical correlations between different cortical regions (with the whole cortex
acting as a single superconducting sheet).
5. Sleep/wakefulness
The cooled psychon model gives a clear explanation of the difference between sleep
and wakefulness, and a rational framework for describing the brain states of sleepwalkers.
Crucially, sleepwalkers actually exist, unlike the fraught case of philosophical zombies,
making discussion of these intriguing cases much more tractable. The model explains why
consciousness provides a distinct advantage over unconscious neural processing –
consciousness reflects the action of a quantum accelerator that greatly increases computing
power. To give a rough idea of the difference, Stapp (1995) calculates (p.7) that a classical
system might contain M × N states and need the same number of registers to describe it,
whereas a quantum description of the same system would need 2 × (2L + 1)M × N registers,
where L is the number of possible states in each register. This exponentially greater number
lets us understand why consciousness confers a distinct evolutionary advantage, and why it
has probably appeared in many creatures on multiple occasions.
The model fits neatly with the “facilitation hypothesis” of Birch (2022), who argues
that conscious perception of a stimulus facilitates cognitive ability compared to what is
possible unconsciously. The contrast between the sleepwalker and the fully awake person is
obvious. Birch makes the point that a conscious person can report their experience and can
learn new things – which he categorises as trace conditioning, reversal learning, and crossmodal learning. It would be particularly illuminating to devise an experiment which involved
one of these categories in a sleepwalking situation. I would argue that a sleepwalker would
2023-09-18 – p.34
fail such a task – the distinguishing feature of sleepwalking is that the activity seems to be
reenactments of previous habitual behaviour.
6. Anesthesia
The present model provides a coherent picture of what might be happening with
anesthesia. Although the mode of action of anesthetics is still not known in detail, there is
good evidence that the same thalomocortical loops which give rise to 40 Hz oscillations in
the cortex play a key role in regulating consciousness (Edelman & Gally, 2013). We have
suggested that a major function of thalamocortical loops is to regulate the feedback cooling
of psychons, and hence switch on consciousness, and the same process might be said to
operate during anesthesia (Alkire et al., 2000; Alkire & Miller, 2005). Alkire and colleagues
describe how, via the control of the thalamocortical loop, anesthesia causes firing of cells to
change from tonic to burst-like, causing consciousness to turn to unconsciousness. In later
work, they elaborate on their “thalamic consciousness switch” hypothesis, and propose that
anesthetics act to prevent coordinated communication between thalamus and cortex,
disengaging both sensory input and motor output (Alkire & Miller, 2005).
Remarkably, the inert gas, xenon, acts as an anesthetic, and it turns out that its
effectiveness depends on what isotope of xenon is used (Li et al., 2018). That strongly
implies that the atomic number of the isotope, reflecting the quantum mechanical spin of its
nucleus, controls the effectiveness of its anesthetic action, and Li and colleagues point out
that such a finding points to quantum mechanics playing a key role in consciousness (Li et
al., 2018, p. 271); see also Hameroff (2018). The involvement of nuclear spin provides
evidence that anesthesia interferes in some way with the spins of certain nuclei in the brain,
and this in turn supports the idea that consciousness involves long-lived quantum spin
states, similar to how NV states in diamond also depend on spin states.
7. Causal closure
Because this paper inclines to a dualistic view of the world, it is relevant to address
one common objection to the idea that mind and body are distinct entities, and that is that
the physical world is causally closed. If that were true, the argument goes, any interference
with the state of the world, via a mind, will violate a fundamental principle of physics –
2023-09-18 – p.35
energy conservation. If mind is to be effective, it somehow has to push and pull on the
world, and this, it is claimed, will disrupt causal closure (Gibb, 2010).
The physics of mind–body interaction (MBI) has been addressed by many who worry
about the energy conservation aspect (Collins, 2008). In one recent contribution,
Anastopoulos (2021) uses a mathematical formalism and ideas about physical and mental
degrees of freedom to demonstrate that MBI and physics are perfectly compatible. The
work is notable in that Anastopoulos provides an explicit counterexample to the claim that
MBI is incompatible with modern physics. The problem arises, he says, from considerations
of classical physics, which have been picked up by those involved in the philosophy of mind
or neuroscience. He quotes the dire warnings of Leibnitz, Bunge, and Fodor. By way of
contrast, in quantum physics there is no such objection – energy conservation is by no
means universal 30 and there is no need for the physical world to be causally closed – and he
adds that there is a strong tradition in physics against reducing the mental to the physical.
Anastopoulos provides the analogy of a game of chess played with two chess-boards, one
mental and the other physical. We simply need to find a set of rules that describe how the
movement of pieces on one board connect to movements on the second. Chalmers would
describe them as psychophysical laws (Chalmers & McQueen, 2023; Chalmers, 1995b), and
although he seems to prefer a world that is physically closed (Chalmers, 1995a), a possible
position is that the world operates through dualistic interactionism, with the physical and
mental interacting reciprocally. The degrees of mental freedom constitute our free will, and
that is what makes us human.
8. Potential explanation for qualia
If the pearls of Indra model is apt, and consciousness reflects the existence of bosons
generated by feedback cooling in psychons, then it may be that qualia exist to label the
central pearl, distinguishing it from all its multiple reflections. Although this is speculation, it
does move things forward in trying to bridge the explanatory gap between physics and
Anastopoulos mentions that energy is not conserved in general relativity, cosmology, or most of
quantum mechanics. Energy conservation is completely insensitive to the dynamics of the mental degrees of
freedom – provided that just one equation (his Eq. 26) is satisfied. To account for MBI, he frames the concept
of ‘generalised energy’ (Eq. 27) involving a conserved quantity, K, which is made up of the Hamiltonian of the
physical system plus a new form of energy, L, associated with mental processes.
30
2023-09-18 – p.36
qualia. Qualia are special features of the human brain, so why is the brain so special
compared to other physical systems? Might psychons be a satisfactory place for qualia to
call home? (Lockwood, 1998, p. 85,86). This paper has attempted to erect a lamp-post
under which we might, if lucky, find what we are looking for (a Buddhist would say, of
course, we never lost anything). Equating consciousness with a certain quantum mechanical
entity in the brain explains the unity of the self and why it should be an all-or-nothing affair
(Lockwood, 1998, p. 86). Lockwood sides with Descartes and sees the mind as indivisible. He
is also scathing of all materialist perspectives, seeing them, ultimately, as “futile exercises in
intellectual contortionism” and that “there must be more to matter than meets the
physicist’s gaze or registers on laboratory instruments” (Lockwood, 1998, p. 87).
Broader context and limitations
The present paper has set out a physically based and reasoned description of how a
room temperature quantum computer might reside in the human brain – at least when
awake. This model of consciousness seems to avoid a number of problems which arise from
other models of consciousness (Doerig et al., 2020). In particular, it appears to avoid
criticisms that have been levelled at Penrose’s OrchOR model (Grush & Churchland, 1995) as
well as avoiding some of the intricacies and arbitrariness of Tononi’s integrated information
theory (Oizumi et al., 2014). 31 The distinguishing feature of consciousness is not that there is
some simple numerical measure (which misses the point about the puzzle of qualia), but
whether the subjects themselves are able to report they are conscious.
There are a number of quantum mechanical models (Gao, 2022; Pylkkanen, 2018),
and it would be of interest to compare the merits and drawbacks of each. However, this is
beyond our present scope. We have assumed the reader has some familiarity with the
major proposals, e.g., Penrose (2022), Tononi (Oizumi et al., 2014), and Freeman and Vitiello
(2016). For now, we just make the general claim that the psychon model provides an
The present model may not be incompatible with certain aspects of other models. For example,
cooling may support the appearance of some microtubule states, and IIT measures may correlate with the
appearance of Bose–Einstein condensates.
31
2023-09-18 – p.37
anatomically and physically well-specified model of consciousness, with a number of distinct
advantages. In particular, it builds on known neuroscience and draws a clear line between
classical physiology and the quantum realm, a boundary that matches what is known about
conscious and unconscious experience.
Nevertheless, it must be acknowledged that although we have edged closer, some
sort of explanatory gap still lingers. Why exactly should a quantum mechanical field “light
up” and generate qualia? In seeking an answer, we have suggested possible directions, but
it will require concerted effort in order to make progress. Some NMR experiments on
conscious volunteers may be fruitful.
On the negative side of the ledger, this model does present certain limitations. The
model is speculative, and it has one major drawback: feedback cooling is a delicate process
that has yet to be observed in a biological system. Cooling can certainly be achieved using
lasers and a carefully arranged system of sensors and actuators. However, as noted
previously, Bialek devoted years to investigating how feedback cooling could be applied to
human sensory systems, and eventually gave up on the enterprise (Bialek, 2012).
Nevertheless, that failure does not prove that feedback cooling cannot occur biologically,
and the potential advantages encourage further investigation of what is possible. It is
premature to dismiss feedback cooling until more work is done.
Finally, of course, there is the need to work out in much more detail the physics of
the psychon itself. Was Eccles on the right track, and if so how does a psychon actually
work? Physically, what are the electrical, magnetic, vibrational, and quantum mechanical
processes involved?
Conclusions
In 1986, before a quantum computer had even been constructed, Michael Lockwood
wrote a piece entitled “Could the brain be a quantum computer?” and, based on theoretical
considerations by Deutsch (see Deutsch and Jozsa (1992)), answered the question with a
2023-09-18 – p.38
tentative yes (Lockwood, 1989, Ch. 14). 32 Lockwood recognised that there were things a
quantum brain could do that a classical brain could not, greatly increasing its computational
power.
He refers to the paper of Marshall (1989) and notes how consciousness may be
associated with Bose–Einstein condensates. “Bose-condensed states,” he says, “are exactly
the sort of thing that is needed if the brain is to operate as a quantum computer. They lend
themselves to coherent superposition, with constructive and destructive interference, in
just the way that is required of quantum computer memory states” (Lockwood, 1989,
p. 259). Lockwood notes that evolution is the ultimate opportunist, and “…if the possibility
is there, we shouldn’t baulk at the thought that natural systems may have taken advantage
of it” (loc. cit.).
Lockwood later relates, echoing Strawson’s sentiments (our footnote 18), that the
mind–body problem is not a problem to do with the mind – we are intimately acquainted
with it all the time (“In awareness, we are, so to speak, getting an insider’s look at our own
brain activity” Lockwood (1998, p. 88)) – but with our conception of matter, which is an
antiquated classical version due to Newton, not a modern quantum mechanical version with
all the subtleties of waves, entanglement, and simultaneity (Lockwood, 1989, p. ix). We
know all about the ghost, it’s the machinery we don’t understand. 33 This paper maps out
how there can be an isomorphism between a certain quantum mechanical field which arises
in the cortex due to cooling and the insider’s view of qualia.
Here we have suggested that consciousness arises due to feedback cooling, which
gives rise to a fundamental change in the way that neurons operate – from classical nerve
Tegmark (2000) answered with a fairly definite no, but his analysis assumed room temperature
conditions. Litt (2006) asked a similar question when criticising the Hameroff and Penrose model and thought
the idea implausible. In a reply entitled “The brain is both neurocomputer and quantum computer”, Hameroff
(2007) gave a wide-ranging rebuttal but did not clearly set out the relationship between the two computers
except to say that “[d]uring general anesthesia in the absence of consciousness, neurocomputation in the
brain continues” (p. 1041). In Hameroff (2010), it is explained how a “conscious pilot” assumes control of an
otherwise non-conscious “auto-pilot neurocomputation”. Curiously, however, despite the quantum
mechanical complexity of the Hameroff and Penrose model, the 2010 paper says the model still falls short of
explaining consciousness, instead pointing to 40 Hz gamma synchrony (perhaps generated by ephaptic
‘sideways’ connections between neurons). The virtue of the psychon model is that it unifies these two aspects
by explaining that gamma synchrony is the control signal that switches on cortical cooling (and hence
consciousness).
33
Lockwood (1988) cites the words of a character in one of Sagan’s novels: “Think of what
consciousness feels like … Does that feel like billions of tiny atoms wiggling in place?” (ibid., p. 88).
32
2023-09-18 – p.39
firing to the creation, at a certain threshold temperature, of long-lived quantum mechanical
states. At this threshold, psychons are switched on and come into long-range
communication with their neighbours. The change takes place at a precise temperature and
causes a change of state – from thermal agitation to quantum coherence, and the system
“lights up”. This is such a dramatic change that it seems reasonable to see it in the same
class as between sleep and wakefulness. Moreover, that change of state is amenable to
detection, as previously explained.
The psychon model provides a clear and straightforward theory of consciousness,
and has distinct advantages. In particular, it builds on known anatomy and draws a clear line
between the classical and the quantum, a boundary that exactly matches the line between
the unconscious and the conscious. Equating the mind with a quantum mechanical field in
the brain is a fruitful speculation – since the whole world is ultimately quantum mechanical
– although it will take much work over many years to fully explore the proposition. We put
the developed Eccles model on the table and invite further consideration.
The present model applies not only to human brains, but no doubt to the brains of
other animals as well. It may be possible to establish the consciousness of animals by
detecting, via NMR, the same low temperature quantum states as found in awake humans.
The ultimate aim, then, is to provide a scheme that fully bridges the brain–mind gap.34
Did Nature, not without precedent in such things, get there first and implement a
room-temperature quantum computer?
Acknowledgements
I thank Marcus Doherty for helpful discussions.
(Tegmark, 2000) (Nagel, 1974) (Godfrey-Smith, 2016) (Godfrey-Smith, 2021)
In his textbook on biophysics, Bialek says how many people tend to regard physics as stopping
somewhere along the path from the outside world to our subjective experience, at which point something
uniquely human takes over. He relates that Helmholtz hoped otherwise, and concludes his own afterword with
“so do I” (Bialek 2012, p. 471).
34
2023-09-18 – p.40
(Debanne et al., 2013) (Stamp, 2006) (Ladd et al., 2010) (de Leon et al., 2021) (Shear, 2007) (Feynman, 1986)
(Benioff, 1998) (Litt et al., 2006) (Hameroff, 2007) (Strawson, 2019) (Hameroff, 2010) (Aaronson, 2013;
Robinson, 2018)
References
Aaronson, S. (2013) Quantum Computing since Democritus. Cambridge University Press.
Al-Khalili, J., & McFadden, J. (2014) Life on the Edge: The Coming of Age of Quantum Biology.
Bantam Press.
Alkire, M. T., Haier, R. J., & Fallon, J. H. (2000) Toward a unified theory of narcosis: brain
imaging evidence for a thalamocortical switch as the neurophysiologic basis of
anesthetic-induced unconsciousness. Consciousness and Cognition, 9, pp. 370-386.
https://doi.org/10.1006/ccog.1999.0423
Alkire, M. T., & Miller, J. (2005) General anesthesia and the neural correlates of
consciousness. Progress in Brain Research, 150, pp. 229-244.
https://doi.org/10.1016/S0079-6123(05)50017-7
Anastopoulos, C. (2021) Mind–body interaction and modern physics. Foundations of Physics,
51, pp. 65. https://doi.org/10.1007/s10701-021-00472-7
Atmanspacher, H. (2020) Quantum approaches to consciousness. In Stanford Encyclopedia
of Philosophy (pp. https://plato.stanford.edu/archives/sum2020/entries/qtconsciousness).
Beck, F. (2001) Quantum brain dynamics and consciousness. In P. Van Looke (Ed.), Physical
Nature of Consciousness (pp. 83-116). John Benjamins.
Beck, F., & Eccles, J. (1992) Quantum aspects of brain activity and the role of consciousness.
Proceedings of the National Academy of Sciences of the United States of America, 89,
pp. 11357. https://doi.org/10.1073/pnas.89.23.11357
Bell, A. (2022) Eccles, Sir John Carew (Jack) (1903–1997) [biography]. In Australian
Dictionary of Biography. Australian National University.
https://adb.anu.edu.au/biography/eccles-sir-john-carew-jack-338/text40217
Bell, A., Davies, B., & Ammari, H. (2022) Bernhard Riemann, the ear, and an atom of
consciousness. Foundations of Science, 27, pp. 855-873.
https://doi.org/10.1007/s10699-021-09813-1
Benioff, P. (1998) Quantum robots and environments. Physical Review A, 58(2), pp. 893-904.
https://doi.org/10.1103/PhysRevA.58.893
Bialek, W. (2012) Biophysics: Searching for Principles. Princeton University Press.
Bialek, W. S. (1983) Quantum Effects in the Dynamics of Biological Systems. PhD thesis,
University of California, Berkeley. https://escholarship.org/uc/item/9tk804vg
Bialek, W. S., & Wit, H. P. (1984) Quantum limits to oscillator stability: theory and
experiments on acoustic emissions from the human ear. Physics Letters, 104A, pp.
173-178. https://doi.org/10.1016/0375-9601(84)90371-2
Birch, J. (2022) The search for invertebrate consciousness. Nous, 56, pp. 133-153.
https://doi.org/10.1111/nous.12351
Buonocore, M. H., & Maddock, R. J. (2015) Magnetic resonance spectroscopy of the brain: a
review of physical principles and technical methods. Reviews in the Neurosciences,
26(6), pp. 609-632.
2023-09-18 – p.41
Castelnovo, A., Lopez, R., Proserpio, P., et al. (2018) NREM sleep parasomnias as disorders of
sleep-state dissociation. Nature Reviews Neurology, 14, pp. 470-481.
Chalmers, D. (2007) Naturalistic dualism. In M. Velmans & S. Schneider (Eds.), The Blackwell
Companion to Consciousness (pp. 359-368). Blackwell.
Chalmers, D., & McQueen, K. (2023) Consciousness and the collapse of the wave function. In
S. S. Gao (Ed.), Consciousness and Quantum Mechanics (pp. 11-63). Oxford University
Press.
Chalmers, D. J. (1995a) Facing up to the puzzle of consciousness. Journal of Consciousness
Studies, 2, pp. 200-219.
Chalmers, D. J. (1995b) The puzzle of consciousness. Scientific American, 273, pp. 80-86.
https://doi.org/10.2307/24985588
Chalmers, D. J. (1996) The Conscious Mind: In search of a fundamental theory. Oxford
University Press.
Chalmers, D. J. (2023) Could a large language model be conscious? arxiv.
https://doi.org/10.48550/arXiv.2303.07103
Collins, R. (2008) Modern physics and the energy-conservation objection to mind-body
dualism. American Philosophical Quarterly, 45(1), pp. 31-42.
Corbitt, T., Wipf, C., Bodiya, T., et al. (2007) Optical dilution and feedback cooling of a gramscale oscillator to 6.9 mK. Physical Review Letters, 99, pp. 160801.
https://doi.org/10.1103/physrevlett.99.160801
Costa, A. R., Pinto-Costa, R., Sousa, S. C., et al. (2018) The regulation of axon diameter: from
axonal circumferential contractility to activity-dependent swelling. Frontiers in
Molecular Neuroscience, 11, pp. 319. https://doi.org/10.3389/frmol.2018.00319
de Leon, N. P., Itoh, K. M., Kim, D. O., et al. (2021) Materials challenges and opportunities
for quantum computing hardware. Science, 372, pp. eabb2823.
https://doi.org/10.1126/science.abb2823
Debanne, D., Bialowas, A., & Rama, S. (2013) What are the mechanisms for analogue and
digital signalling in the brain? Nature Reviews Neuroscience, 14, pp. 63.
Deutsch, D., & Jozsa, R. (1992) Rapid solutions of problems by quantum computation.
Proceedings of the Royal Society of London A, 439, pp. 553-558.
Doerig, A., Schurger, A., & Herzog, M. H. (2020) Hard criteria for empirical theories of
consciousness. Cognitive Neuroscience, 12(2), pp. 41-62.
https://doi.org/10.1080/17588928.2020.1772214
Doherty, M. (2021) Quantum accelerators: a new trajectory of quantum computers. Digitale
Welt, 2, pp. 74-79.
Eccles, J. (1990) A unitary hypothesis of mind–brain interaction in the cerebral cortex.
Proceedings of the Royal Society of London B, 240, pp. 433-451.
Eccles, J. C. (1994) How the Self Controls Its Brain. Springer-Verlag.
Edelman, G. M. (1992) Bright Air, Brilliant Fire: On the matter of the mind. Basic Books.
Edelman, G. M., & Gally, J. A. (2013) Reentry: a key mechanism for integration of brain
function. Frontiers in Integrative Neuroscience, 7, pp. 63.
https://doi.org/10.3389/fnint.2013.00063
Feynman, R. P. (1986) Quantum mechanical computers. Foundations of Physics, 16(6), pp.
507-531.
Fisher, M. P. A. (2015) Quantum cognition: the possibility of processing with nuclear spins in
the brain. Annals of Physics, 362, pp. 593-602.
https://doi.org/10.1016/j.aop.2015.08.020
2023-09-18 – p.42
Flanagan, O. (1995a) Deconstructing dreams: the spandrels of sleep. Journal of Philosophy,
92, pp. 5-27.
Flanagan, O. (1995b) Zombies and the function of consciousness. Journal of Consciousness
Studies, 2(4), pp. 313-321.
Flanagan, O. (1996) Prospects for a unified theory of consciousness or, what dreams are
made of. In J. D. Cohen & J. W. Schooler (Eds.), Scientific Approaches to
Consciousness. Taylor & Francis.
Freeman, W., & Vitiello, G. (2016) Matter and mind are entangled in two streams of images
guiding behavior and informing the subject through awareness. Mind and Matter,
14, pp. 7-24.
Gao, S. (2022) Consciousness and Quantum Mechanics. Oxford University Press.
Gibb, S. (2010) Closure principles and the laws of conservation of energy and momentum.
Dialectica, 64(3), pp. 363-384. https://doi.org/10.1111/j.1746-8361.2010.01237x
Gieseler, J., Deutch, B., Quidant, R., et al. (2012) Subkelvin parametric feedback cooling of a
laser-trapped nanoparticle. Physical Review Letters, 109, pp. 103603.
https://doi.org/10.1103/physrevlett.109.103603
Godfrey-Smith, P. (2016) Other Minds: The octopus, the sea, and the deep origins of
consciousness. Farrar, Strauss and Giroux.
Godfrey-Smith, P. (2021) Metazoa: Animal minds and the birth of consciousness. William
Collins.
Grush, R., & Churchland, P. S. (1995) Gaps in Penrose's toilings. Journal of Consciousness
Studies, 2, pp. 10-29.
Hameroff, S. R. (2007) The brain is both neurocomputer and quantum computer. Cognitive
Science, 31, pp. 1035-1045.
Hameroff, S. R. (2010) The "conscious pilot": dendritic synchrony moves through the brain
to mediate consciousness. Journal of Biological Physics, 36, pp. 71-93.
https://doi.org/10.1007/s10867-009-9148-x
Hameroff, S. R. (2018) Anesthetic action and "quantum consciousness". Anesthesiology, 129,
pp. 228-231.
Hameroff, S. R. (2022) Orch OR and the quantum biology of consciousness. In S. Gao (Ed.),
Consciousness and Quantum Mechanics (pp. 363-414). Oxford University Press.
Hameroff, S. R., & Penrose, R. (2014) Consciousness in the universe: a review of the 'Orch
OR' theory. Physics of Life Reviews, 11, pp. 39-78.
https://doi.org/10.1016/j.plrev.2013.08.002
Hammond, C. (2012) Is it dangerous to wake a sleepwalker? BBC Future.
https://doi.org/https://www.bbc.com/future/article/20120208-it-is-dangerous-towake-a-sleepwa.html
Huxley, T. H. (1874) On the hypothesis that animals are automata, and its history. In
Collected Essays I.
Josephson, B. D. (2019) The physics of mind and thought. Activitas Nervosa Superior, 61, pp.
86-90. https://doi.org/10.1007/s41470-019-00049-w
Kawamura, Y., & Kanegae, R. (2016) Feedback damping of a microcantilever at room
temperature to the minimum vibration amplitude limited by the noise level.
Scientific Reports, 6, pp. 27843. https://doi.org/10.1038/srep27843
Kirk, R. (1974) Zombies v. materialists. Proceedings of the Aristotelian Society, 48, pp. 135152.
2023-09-18 – p.43
Kirk, R. (2023) Zombies. In E. N. Zalta & U. Nodelman (Eds.), The Stanford Encyclopedia of
Philosophy. https://plato.stanford.edu/archives/sum2023/entries/zombies/
Kistler, W. M., & De Zeeuw, C. I. (2003) Time windows and reverberating loops: a reverseengineering approach to cerebellar function. The Cerebellum, 2, pp. 44-54.
Krouse, L. (2022) Should you wake a sleepwalker? Sleep.com [online].
https://doi.org/https://www.sleep.com/sleep-health/sleepwalking
Kucsko, G., Maurer, P. C., Yao, N. Y., et al. (2013) Nanometre-scale thermometry in a living
cell. Nature, 500, pp. 54-58. https://doi.org/10.1038/nature12373
Ladd, T. D., Lelezko, F., Laflamme, R., et al. (2010) Quantum computers. Nature, 464, pp. 4553. https://doi.org/10.1038/nature08812
Li, N., Lu, D., Yang, L., et al. (2018) Nuclear spin attenuates the anesthetic potency of xenon
isotopes in mice: implications for the mechanism of anesthesia and consciousness.
Anesthesiology, 129, pp. 271-277.
Lidar, D. A. (2014) Review of decoherence-free subspaces, noiseless subsystems, and
dynamical decoupling. Advances in Chemical Physics, 154, pp. 295-354.
Litt, A., Eliasmith, C., Kroon, F. W., et al. (2006) Is the brain a quantum computer? Cognitive
Science, 30, pp. 593-603.
Llinas, R. R., & Paré, D. (1991) Of dreaming and wakefulness. Neuroscience, 44, pp. 521-535.
Lockwood, M. (1989) Mind, Brain and the Quantum: The compound 'I'. Blackwell.
Lockwood, M. (1998) The enigma of sentience. In S. R. Hameroff, A. W. Kaszniak, & A. Scott
(Eds.), Toward a Science of Consciousness II: The second Tucson discussions and
debates (pp. 83-95). MIT Press.
Ludwig, J., Oliver, D., Frank, G., et al. (2001) Reciprocal electromechanical properties of rat
prestin: the motor molecule from rat outer hair cells. PNAS, 98, pp. 4178-4183.
Manikandan, S. K., & Qvarfort, S. (2023) Optimal quantum parametric feedback cooling.
Physical Review A, 107, pp. 023516. https://doi.org/10.1103/physreva.107.023516
Margenau, H. (1984) The Miracle of Existence. Ox Bow Press.
Marshall, I. N. (1989) Consciousness and Bose–Einstein condensates. New Ideas in
Psychology, 7, pp. 73-83.
Nagel, T. (1974) What is it like to be a bat? Philosophical Review, 83, pp. 435-450.
Nagel, T. (2012) Mind and Cosmos: Why the materialist neo-Darwinian conception of nature
is almost certainly false. OUP.
Oizumi, M., Albantakis, L., & Tononi, G. (2014) From the phenomenology to the mechanisms
of consciousness: Integrated Information Theory 3.0. PLoS Computational Biology,
10(5), pp. e1003588. https://doi.org/10.1371/journal.pcbi.1003588
Opwood, R. (2013) Qualia could arise from information processing in local cortical networks.
Fontiers in Psychology, 4, pp. 121. https://doi.org/10.3389/fpsyg.2013.00121
Penrose, R. (1989) The Emperor's New Mind: Concerning computers, minds, and the laws of
physics. Oxford University Press.
Penrose, R. (2022) New physics for the Orch-OR consciousness proposal. In S. Gao (Ed.),
Consciousness and Quantum Mechanics (pp. 317-362). Oxford University Press.
https://doi.org/10.1093/oso/97801975501665.003.0014
Popper, K., & Eccles, J. C. (1977) The Self and Its Brain: An argument for interactionism.
Springer.
Pylkkanen, P. (2018) Quantum theories of consciousness. In R. J. Gennaro (Ed.), Routledge
Handbook of Consciousness (pp. 216-231). Taylor & Francis.
2023-09-18 – p.44
Redinbaugh, M. J., Phillips, J. M., Kambi, N. A., et al. (2020) Thalamus modulates
consciousness via layer-specific control of cortex. Neuron, 106, pp. 66-75.
https://doi.org/10.1016/j.neuron.2020.01.005
Robinson, W. S. (2018) Dualism. In R. J. Gennaro (Ed.), The Routledge Handbook of
Consciousness (pp. 51-63). Taylor & Francis.
Romero-Isart, O., Juan, M. L., Quidant, R., et al. (2010) Toward quantum superposition of
living organisms. New Journal of Physics, 12, pp. 033015.
https://doi.org/10.1088/1367-2630/12/3/033015
Ryle, G. (1949) The Concept of Mind. Hutchinson.
Schenk, C. H., Milner, D. M., Hurwitz, T. D., et al. (1989) A polysomnographic and clinical
report on sleep-related injury in 100 adult patients. American Journal of Psychiatry,
146, pp. 1166-1173.
Schlosshauer, M. (2019) Quantum decoherence. Physics Reports, 831, pp. 1-57.
https://doi.org/10.1016/j.physrep.2019.10.001
Schwartz, J. M., Stapp, H. P., & Beauregard, M. (2005) Quantum physics in neuroscience and
psychology: a neurophysical model of mind–brain interaction. Philosophical
Transactions of the Royal Society of London. Series B, 360, pp. 1309-1327.
https://doi.org/10.1098/rstb.2004.1598
Seager, W. (n.d.) Are zombies logically possible? And why it matters.
https://www.utsc.utoronto.ca/~seager/zombie.html
Shear, J. (2007) Eastern methods for investigating mind and consciousness. In M. Velmans &
S. Schneider (Eds.), The Blackwell Companion to Consciousness (pp. 697-710).
Blackwell.
Stamp, P. C. E. (2006) The decoherence puzzle. Studies in History and Philosophy of Modern
Physics, 37, pp. 467-497. https://doi.org/10.1016/j.shpsb.2006.04.003
Stapp, H. (2007) Quantum mechanical theories of consciousness. In M. Velmans & S.
Schneider (Eds.), The Blackwell Companion to Consciousness (pp. 300-312).
Blackwell.
Stapp, H. P. (1995) Why classical mechanics cannot naturally accommodate consciousness
but quantum mechanics can. Psyche, 2(5).
Strawson, G. (2019) A hundred years of consciousness: "a long training in absurdity".
Estudios de Filosofía, 59, pp. 9-43. https://doi.org/10.17533/udea.ef.n59a02
Stubenberg, L. (1998) The place of qualia in the world of science. In Toward a Science of
Consciousness: The first Tucson discussions and debates (pp. 41-49). MIT Press.
Sukel, K. (2019) Is it dangerous to wake a sleepwalker? Neuromyth [online].
https://doi.org/https://www.brainfacts.org/thinking-sensing-andbehaving/sleep/2019/is-it-dangerous-to-wake-a-sleepwalker-101119
Szentágothai, J. (1979) Local neuron network of the neocortex. In F. O. Schmitt & F. G.
Worden (Eds.), The Neurosciences Fourth Study Program (pp. 399-415). MIT Press.
Szentágothai, J. (1984) Downward causation? Annual Review of Neuroscience, 7, pp. 1-11.
Tegmark, M. (2000) Why the brain is probably not a quantum computer. Information
Sciences, 128, pp. 155-179.
Viola, L., & Fortunato, E. M. (2002) Realizing a noiseless subsystem in an NMR quantum
information processor. Los Alamos Science, 27, pp. 260-263.
2023-09-18 – p.45 |
Embodied Consciousness Theory
Jahan N. Schad, PhD; Retired LBNL (UCB) Scientist
376 Tharp Drive, Moraga, Ca 94556
Email: schadn5@berkeley.edu
Phone: (925) 376-4126
The mysterious phenomenon of consciousness, after having been the subject of philosophic
attention for few millennia, has drawn much scientific curiosity in recent decades; and many
brilliant minds of various areas of sciences are trying to throw some light on it. Present
neuroscience knowledge allows envisioning the neural processes behind the physical aspects of
consciousness, however what may be behind the experiences of it, which has no physical
insignia, has remained a mystery despite the grounds gained in recent well received efforts:
monumental endeavors concluding in the known theories such as global work space theory
(GWT) [1] and integrated information theory (IIT) [2], still fall short of providing a solid theory
for consciousness: the former “proposes a simple hypothesis concerning the neural basis of
‘‘making a conscious mental effort,” and the latter, assuming experience to be an intrinsic
property of the brain, “formulates how it is transitioned, through certain information based neural
activity, to its physical substrate.” Present work puts forward a theory of consciousness, rooted in
the simple and straightforward implications of the computational operation of the brain which is
consistent with well known facts and recent findings, which indicates presence of motor cortex
activity in relaying conscious experiences. Despite simplicity, the theory provides fundamental
basis for physicalism [3], as well answers for some Meta level problems of consciousness.
The Concept
Consciousness, the perceptions/conceptions of the inner/outer environment, as well as the
commensurate activities, is rendered by the computations (simulations) in the brain-- evoked by
the inputs from our five senses (at least four are of tactile nature) -- should inferentially be
considered the expressions of the outputs at the interfaces available to the brain; and certainly in
case of the physical expressions, the interface is the body. The physical aspects of consciousness
are promulgated by the efferent signals, which are known to be issued from various parts of the
motor cortex, graphically depicted by the homunculus despite the inaccuracy in suggesting the
concept of the specific modular brain functioning; other parts of the brain are normally engaged
in rendition of most effects. However, some subjective aspects of it (the non-physical
experiences) also promote the physical effects: such facial and bodily displays of “emotions”
have been noted since ancient times, and the following quote from St. Augustine [4] vividly
depicts it:
“And that they meant this thing and no other was plain from the motion of their body, the natural
language, as it were, of all nations, expressed by the countenance, glances of the eye, gestures of
the limbs, and tone of voice, indicating the affections of the mind, as it pursues, possesses,
rejects, or shuns.”
And therefore this fact attests to the presence of the motor neuron signals in at least in some
aspects of our “subjective experiences;” the hard part of consciousness phenomenon. To this
point, the report “reproducibility” of some of the subjective experiences, which is a “physical
activity,” further confirms it. Also, there is some evidence of “motor activity along with
perceptual and semantic processes,” which is reported in the global work theory (GWT) [1],
published in the proceeding of the national academy of sciences (PNAS). The direct evidence of
the continued activity of the motor neurons is clearly reported in the following quotes from
research in Motor Robotics [5]
“Motor cortex is also engaged when actions are observed or imagined.”
“Beyond its central role in movement generation, primary motor cortex (MI) also appears to be
engaged in cognitive and sensory processes in the absence of overt movement”
Engagement of sensory cortex in “observation” and motor cortex in “physical activity” is
expected, however, presence of “motor neuron activity when observing”, with no inclining of
even imagining action, is unexpected because of the “efferent nature” of such download even in
the face of no apparent physical activity. The above fact provide the context in which the
disruptive concept of the embodied consciousness based on simple inference from ground level
understanding of the computational brain, can be formalized: This falsifiable theory put forward
here, claims that consciousness in all its totality, physical, reported and unreported subjective
aspects, all are bound to be “downloads, in the realm of the computational operations (inputprocess-output), of brain” by means of neural signals (some proven motor) to the interfaces of
the body; some in muscular- skeletal displays, some in vocalization and some inevitably in the
likeness of thought signals. And thought signal are also very likely to be of the efferent nature,
which is indicated by the bimodal (on-off) vocal nature of thoughts (some people do their
thinking loud all the time). Some of the efferent signal expressions are undoubtedly filtered by
the bandpass characteristics of the bodily interfaces, which have limited the development of
syntactic expression for the quality of the Qualia; and much is inhibited to begin with, with
options for intentional display, as in vocalization. The embodied consciousness theory (ECT) is
predictive of permanent activity of motor cortex, in conjunction with other areas of the cortex; in
waking hours and REM sleep, whether one gets note of it or not, since many activities occur
autonomously.
Another major aspect of the mystery of the consciousness phenomenon, which is comfortably
avoided in the context of “one is one’s brain,” or presumed to have been answered in the
vernacular of the IIT and GWT, is, how “persona” the identity of the claimant of consciousness,
has come about; a sort of “meta problem of consciousness,” perhaps similar to the other meta
problem regarding the validity of the very question of consciousness itself that philosophers have
raised [e.g., 6]; the latter a likely by-pass of the main question which may possibly resolve the
mystery, or do away with it all, in approaches such as illusionism [7]. However, the ECT
suggests a ground level explanation for the both Meta aspects in the context of brain’s underlying
dynamics that has led to the very development of the “referential” language syntaxes [8], serving
as a basis for the development of the persona identity, and perhaps as well for the d3eveopmet of
the spoken language. To this end, we need to start with the fact that whatever detailed
information (afferent signals) related the characteristics of “things out there (not necessarily in
themselves)--” which are parts of existence -- that our senses (vision inclusive) relay to the brain,
has to result in the specific outputs rudely defining the “things” from which senses signals are
picked up. It must be obvious that each “thing” (characteristic) depiction, the results of the brain
computations, will have its nature stamped in the variances of the outputs. Parts of these
characteristics, downloaded through bodily interfaces end up in specific vocalization (in case of
absence of the vocal box, bodily expression or chemical outputs do the function), which
gradually gets refined through the evolutionary processes, becoming the referral identity of
“things”; the specific “referential” calls. And it is not hard to speculate the referential language
much ties in with survival drive of beings. Also, the vocalizing body, being always in internal
physiologic commotion (one way or the other), would have its own specific generally fixed
download from the brain, which would always appear distinctly separately, or as a “preamble” to
whatever else gets downloaded in the vocal box; and this permanent signature, as preamble or
otherwise, becomes the identity of the being, distinguishing one from another, “ones Identity (the
Is); somewhat like the “MAC” address of data processing devices which identifies them!
Conclusion
Our computational brains, which process the data received through sensation by our five
interfaces with the environment,-- deploying learned and inherited neural patterns, and/or trial
and error adjustments of synaptic functions-- also necessitates presence of interfaces for the
expressions of the outputs. As known, some physical, as wells as some “emotional” aspects of
our consciousness are broadcasted through our body interfaces; muscular-skeletal for the former
and mostly facial expression for the latter, which are indicative of motor signals. The acts of
“conscious experience reporting”, and “loud thinking (voluntary or otherwise)”, evince motor
cortex involvement promulgating the act. These facts, supported by the recent research indicative
of motor cortex activity during simple “observation” where no action, even in the realm of
imagination, is intended or involved, provides the basis for theorizing that the output of brain
computation are motor signals, which engages the body, though mostly vocal system, for its
expressions. In this context, thoughts are low energy signal or perhaps of certain frequency range
that is outside of bandpass of the vocal box, and therefore remains muffled. This testable theory
claims that consciousness is embodied.
References
[1] Stanislas Dehaene, Michel Kerszberg, and Jean-Pierre Changeux
PNAS November 24, 1998 95 (24) 14529-14534; https://doi.org/10.1073/pnas.95.24.14529
[2] Tononi, G., Boly, M., Massimini, M., & Koch, C. (2016). Integrated information
theory: from consciousness to its physical substrate. Nat Rev Neurosci, 17(7),
450-461. doi:10.1038/nrn.2016.44
[3] Stoljar, Daniel; Physicalism (New Problems of Philosophy), Routlege, New York, 2010
[4] MLA. Augustine, of Hippo, Saint, 354-430. The Confessions of Saint Augustine. Mount
Vernon :Peter Pauper Press, 19401949 [5]Vargas-Irwin, C. E., Feldman, J. M., King, B.,
[5] Simeral, J. D., Sorice, B. L., Oakley, E. M., Cash, S. S., Eskandar, E. N., Friehs, G. M.,
Hochberg, L. R., & Donoghue, J. P. (2018). Watch, imagine, attempt: Motor cortex single-unit
activity reveals context-dependent movement encoding in humans with tetraplegia. Frontiers in
Human Neuroscience, 12, [450]. https://doi.org/10.3389/fnhum.2018.00450
[6] Chalmers D. J. (2014) The Hard Problem of Consciousness, 342 years on; 20th Anniversary
Conference, Towards a Science of Consciousness. Tucson Arizona
[7] Bostrom, N. 2003. “Are You Living In a Computer Simulation?” Philosophical Quarterly 53
(211): 243–255.
[8] Chomsky N. (2007) On language. New York: New York Press |
If consciousness is dynamically relevant,
artificial intelligence isn’t conscious
Johannes Kleiner1,2,3 and Tim Ludwig4
1
arXiv:2304.05077v1 [cs.AI] 11 Apr 2023
2
Munich Center for Mathematical Philosophy, LMU Munich
Munich Graduate School of Systemic Neurosciences, LMU Munich
3
Association for Mathematical Consciousness Science
4
Institute for Theoretical Physics, Utrecht University
Princetonplein 5, 3584 CC Utrecht, The Netherlands
Abstract. We demonstrate that if consciousness is relevant for the temporal evolution
of a system’s states—that is, if it is dynamically relevant—then AI systems cannot be
conscious. That is because AI systems run on CPUs, GPUs, TPUs or other processors which have been designed and verified to adhere to computational dynamics that
systematically preclude or suppress deviations. The design and verification preclude
or suppress, in particular, potential consciousness-related dynamical effects, so that if
consciousness is dynamically relevant, AI systems cannot be conscious.
dynamical relevance. Here, dynamical refers to the
temporal evolution of a system’s states. Consciousness is relevant to a system’s time evolution if the
time evolution with consciousness, as described by
a theory of consciousness, differs from the time
evolution without consciousness, as described by
a physical theory. Crucially, consciousness can be
dynamically relevant in both physicalist and nonphysicalist ontologies. An example of the former
is a theory which posits that consciousness serves
a specific functional role that is absent in systems
without consciousness; an example of the latter is
a theory that violates the closure of the physical.
What sets AI systems apart in the context
of consciousness is not the specific computational
architecture that is employed; architectures that
closely resemble the mammalian brain’s computational structure can arguably also be used, after
all [18]. Instead, the distinctive aspect is the hardware on which an AI architecture operates, namely
CPUs, GPUs, TPUs, or other processors. This
hardware is designed and verified to ensure that
the physical dynamics evolve precisely as described
by a computational theory during what is known
as functional and post-silicon verification. These
verification processes ensure that the physical design of the chip (the layout of integrated circuits
in terms of semiconductors), as well as the actual
The question of whether artificial intelligence
(AI) systems are conscious has emerged as one of
critical scientific, philosophical, and societal concern. While empirical support to differentiate theories of consciousness is still nascent and while current measures of consciousness (the simplest example of which is interpretation of verbal reports)
cannot justifiably be applied to AI systems, our
best hope for reliable answers is to link AI’s potential for consciousness with fundamental properties
of conscious experience that have empirical import
or philosophical credibility.
Significant progress in this regard has already
been achieved. In [12], David Chalmers assesses
evidence for or against AI consciousness based on
an extensive array of features that a system or organism might possess or lack, such as self-report,
conversational ability, general intelligence, embodiment, world or self-models, recurrent processing,
or the presence of a global workspace. In [48],
Wanja Wiese proposes a criterion for distinguishing between conscious and non-conscious AI, anchored in the desiderata of the neuroscientific Free
Energy Principle.1
In this paper, we propose a result of similar nature, which however does not rely on system features and how they relate to consciousness, but
on a general property of theories of consciousness:
1These are examples of research whose aim is to evaluate whether AI systems of the more recent form are or can be
conscious. Other interactions between AI research and consciousness science include the use of AI inspired tools and
concepts to model consciousness, for example [5, 23, 25], and studies of how models of consciousness might help to build
better AI, for example [6, 24, 37]. The question of whether machines in general can be conscious has guided much of the
debate in philosophy of mind over the decades, notable contributions include [4, 8, 11, 14, 15, 16, 20, 21, 40, 43, 44, 46, 47].
1
2
physical product (the processing unit after production), yield dynamics exactly as specified by the
computational theory. Any dynamical effects that
violate the specification of this theory are excluded
or dynamically suppressed by error correction.
The intuition behind our result is summarised
below. The objective of the paper is to delineate
all concepts involved in this intuition carefully, so
as to present a theorem that underwrites the intuition both in scope and precision.
(A1) Verification of processing units ensures that
any dynamical effects that change the computational dynamics of a processing unit are
precluded or suppressed.
(A2) If consciousness is dynamically relevant, and
AI systems are conscious, then there are dynamical effects that change the computational dynamics of an AI system.
(A3) AI systems run on processing units.
(C) If consciousness is dynamically relevant, AI
systems cannot be conscious.
The conclusion (C) follows because qua (A3)
and (A1), verification ensures that any dynamical
effects that change the computational dynamics of
an AI system are precluded or suppressed. (A2)
states that if consciousness is dynamically relevant,
and AI systems are conscious, then there are dynamical effects that change the computational dynamics of an AI system. Therefore, if consciousness is dynamically relevant, then AI systems cannot be conscious. The crucial work of the formalisation we introduce below is to make sure this
reasoning is also sound if consciousness’ dynamical
effects apply on a “level below” the computational
level.
In a nutshell, this paper shows that if consciousness makes a difference to how a system evolves
in time—as it should if consciousness is to have
any evolutionary advantage, for example—then
any system design which systematically precludes
or suppresses diverging dynamical effects systematically precludes or suppresses the system from
being conscious.
1. Preliminaries
The central notion which underlies our result
is that of the time evolution of a system’s states.
Given a scientific theory T and a system S within
the scope of the theory, we denote by kT (S, s) the
dynamical evolution (also called ‘trajectory’) of S
with initial state s. This dynamical evolution describes how the state s evolves in time according to
T . An example is the evolution of a brain state according to a neuroscientific theory. We will mostly
abbreviate kT (S, s) by kT if it is clear from context
that we’re talking about one system and one initial
state.
The class of theories which is relevant in the
present context are physical theories, on the one
hand, and theories of consciousness, on the other
hand. We use the symbol Υ to denote physical
theories that have been discovered by the natural
sciences, in so far as they are relevant for AI or consciousness. Examples are theories of neuroscience,
biology, chemistry, computer science and physics.
Different theories describe systems at different
levels [31], and in some cases, the states of a system posited by one theory T (the “lower” level)
can (in principle) be mapped to sates of another
theory T ′ (the “higher” level). If this is the case,
we write T < T ′ . Because dynamical evolutions
are sequences of states, if T < T ′ , we can map
any dynamical evolution kT of T to a (not necessarily dynamical) evolution of T ′ , which we denote
as kT |T ′ . We assume that there is a fundamental
physical theory TF ∈ Υ that can be mapped to
states of any other physical theory in Υ, so that
TF < T for all T ∈ Υ. It is likely that the states
of quantum theory can, in principle, be mapped to
states of all physical theories in Υ, which is why
for all practical purposes we can think of TF as
quantum theory.
We also assume that there is a fact to the matter
of what the real (that is: actual) dynamics of any
system are, even if that fact may not be knowable.
We denote the description of the real dynamics in
terms of the states of any physical theory T ∈ Υ
(any “level” of description, so to speak) by k∗ |T .
If T < T ′ , the description of the real dynamics in
terms of the states of both theories are compatible,
that is k∗ |T |T ′ = k∗ |T ′ .
2. Theories of Consciousness
The second class of theories that are relevant in
this context are theories of consciousness (tocs),
which are sometimes also called models of consciousness. Tocs express a relation between a physical description of a system, on the one hand, and
a description of its conscious experiences, on the
other hand. The latter could be a description of
its phenomenal character (cf. e.g. [26, 29]), or simply an expression of whether a system S has conscious experiences at all. Together, the physical
description and the description of conscious experiences applied by a toc M constitute a state s
of the toc, and the dynamical evolution kM (S, s)
of this state expresses how the physical and consciousness relate according to the toc M . Independently of what the description is that a toc applies
on the side of consciousness, there is a fact to the
matter of whether a system is conscious or not in
3
kM (S, s), that is: whether the system S has conscious experiences at least at one point of time in
the dynamical evolution kM (S, s).
Because tocs contain a physical description of
a system at some level, for every toc M , there is
at least one physical theory TP ∈ Υ such that the
physical part of any state s of M , and therefore also
any dynamical evolution kM , can be expressed in
TP . We denote this by s|TP and kM |TP , respectively. So, kM |TP is what M says about the evolution of physical states on TP ’s level of description.
We call any such TP an underlying physical theory
of M .
Making use of this important link between tocs
and physical descriptions, we can say that a system S is conscious in a physical evolution kTP iff
there is a dynamical evolution kM of M such that
(a) we have kM |TP = kTP and (b) the system is
conscious in kM .
Whether a toc has anything original to say
about the dynamical evolution of its physical
states, or simply presumes the dynamical evolution of an underlying physical theory, is precisely
the question of dynamical relevance, defined as follows. Let M denote a toc and TP ∈ Υ an underlying physical theory of M .
Definition 1. Consciousness is dynamically relevant according to M with respect to TP iff
S is conscious in kM ⇒ kM |TP 6= kTP .
Here, the right-hand-side is short-hand for
kM (S, s)|TP 6= kTP (S, s|TP ), where s|TP denotes
the restriction of the state s of M to TP . The
left-hand side is a shorthand for ‘S is conscious in
kM (S, s)’, meaning that there is at least one point
of time in kM (S, s) so that S has a conscious experience at that time according to M . The definition
expresses the intuition that if S is conscious according to a toc M , then the dynamical evolution
as specified by M differs from the dynamical evolution as specified by the underlying physical theory
alone.
We have already referenced the ‘real’ dynamics
of a system and introduced the symbol k∗ |TP to
denote what the real dynamics of a system would
look like in terms of the states of TP . There is also
a fact to the matter of whether a system in a trajectory k∗ is conscious and how conscious experiences
relate to the physical. That is, there is a ‘true’ or
‘real’ theory of consciousness, which we denote by
M ∗ . As in the physical case, M ∗ may be unknown
and or unknowable. We will denote its dynamical
evolutions by kM ∗ . Because these describe what
really happens, we have kM ∗ |TP = k∗ |TP for all TP .
Using M ∗ , we can define dynamical relevance simpliciter:
Definition 2. Consciousness is dynamically relevant (CDR) only if it is dynamically relevant according to the ‘true’ toc M ∗ with respect to some
physical theory TP ∈ Υ.
3. Verification
What is unique about AI systems in the present
context is not the particular architecture that is
employed; AI can also be built on architecture derived from the brain; cf. e.g [18]. What is unique is
rather that the architecture runs on CPUs, GPUs,
TPUs or other processors that have been designed
and verified in the lab.
There are two major verification steps in processor development, called functional and post-silicon
verification. Functional verification [34, 49] is applied once the design of a processor in terms of integrated circuits has been laid out, but before the
manufacturing phase begins. It applies simulation
tools, formal verification tools and hardware emulation tools to ensure that the design of the chip
meets the intended specifications as described by
a computational theory Tcomp . Post-silicon verification [35, 36] is applied after the silicon waver
has been fabricated. It applies in-circuit testing,
functional testers, failure analysis tools and reliability testing, among other things, to ensure that
the physical product works as Tcomp would have it.
Functional verification is a theoretical endeavour. It applies simulation and emulation tools
based on a theoretical account on how the substrate, on which a processor is to be built, behaves.
Because this substrate is a semi-conductor, this
theoretical account is based on quantum theory
TF . Put in terms of dynamics, functional verification aims to ensure that whatever happens in the
quantum realm implements or is compatible with
the dynamics as described by Tcomp , formally:
kTF |Tcomp = kTcomp
(3.1)
for all dynamical evolutions of a processor S.
Post-silicon verification, on the other hand, is
applied to a chip once it has been built. It ensures
that the dynamics of the actual physical product
comply with Tcomp . Making use of the k∗ notation to denote the actual dynamical evolution of a
system, post-silicon verification enforces that
k∗ |Tcomp = kTcomp
(3.2)
for all dynamical evolutions of a processor S.
Being an AI system means running on CPUs,
GPUs, TPUs or other processors that have been
designed and verified. That’s what makes the system “artificial”. And because processor dynamics
compose (the output of one is the input of the
next), verification holds for AI systems as well:
there is an underlying computational theory Tcomp
4
that accounts for what “happens” on the processors while the system is running, and the computational dynamics satisfy (3.1) and (3.2).
post-silicon verification (3.2), all of the dynamical
evolutions of S satisfy
4. AI Consciousness
Application of Definition 2 for the case TP = Tcomp
implies, via Definition 1, that if S is conscious in
a kM ∗ , then kM ∗ |Tcomp 6= kTcomp . The converse of
this statement is that if kM ∗ |Tcomp = kTcomp , then
S is not conscious in kM ∗ . Because kM ∗ |Tcomp =
k∗ |Tcomp , the identity (5.1) establishes the prerequisite of this condition for all dynamical evolutions
of S. Therefore, it follows that S is not conscious
in any kM ∗ . Thus, Definition 3 implies that S is
not conscious, as claimed.
The remainder of this section is devoted to the
proof of the theorem in the general case. To this
end, we first state and prove the following lemma.
With all this in place, we can formulate the
question that is being asked precisely. The term
‘artificial intelligence’ is used very broadly, comprising many different computational architectures
and applications. What one means when one asks
whether an AI system is conscious is whether the
computational architecture that is applied by this
system, with the specific quirks of its implementation and training, potentially in a specific task,
has conscious experiences. The architecture and
these specifics determine the computational dynamics the system is capable of. Thus, the question is whether the system has a computational
evolution kTcomp such that it is conscious in this
computational evolution according to a theory of
consciousness M ; cf. Section 2 for a definition of
what this means in terms of dynamics kM of M .2
In summary:
Definition 3. An AI system S is conscious according to a theory of consciousness M only if there
is at least one dynamical evolution kTcomp in which
the system is conscious according to M .
This is a very weak condition, which however
has one important consequence: that the question of AI consciousness is determined by facts
on the computational level and above; it is independent of what happens on a sub-computational
level. That is, if we have a a trajectory kTP
on a sub-computational level (TP < Tcomp ) with
kTP |Tcomp = kTcomp then S is conscious in kTcomp
only if it is conscious in kTP .
5. Main Result
k∗ |Tcomp = kTcomp .
(5.1)
Lemma 5. Dynamical relevance passes downward,
in the sense that if TP < TP′ and consciousness is
dynamically relevant according to M with respect
to TP′ , then it is also dynamically relevant according to M with respect to TP .
Proof of the Lemma. Consciousness is dynamically relevant according to M with respect to TP′ ,
iff
S is conscious in kM ⇒ kM |TP′ 6= kTP′ .
Because TP < TP′ , there is a function which maps
states—and therefore also dynamical evolutions—
from TP onto TP′ . Therefore, we have
kM |TP′ 6= kTP′ ⇒ kM |TP 6= kTP .
Together with the above, this gives
S is conscious in kM ⇒ kM |TP 6= kTP ,
which is the case iff consciousness is dynamically
relevant according to M with respect to TP .
We now proceed to the proof of the theorem.
Our main result is the following theorem.
Theorem 4. If consciousness is dynamically relevant, then AI systems aren’t conscious.
Before giving the proof, we first illustrate the
result for the simpler case where consciousness is
dynamically relevant with respect to the computational level Tcomp itself. The power of the theorem
is to extend this result to all other cases. Subsequent to this illustration, we prove a lemma needed
for the main theorem, and then proceed to prove
the theorem itself.
So let us consider the case where TP in Definition 2 is Tcomp . Let S be an AI system. Because of
Proof of the Theorem. We first consider the case
where TP in Definition 2 is TF .
Let S be an AI system. Because of functional
and post-silicon verification, we have
kTF |Tcomp = kTcomp = k∗ |Tcomp
(5.2)
for all dynamical evolutions of S. Because consciousness is (by assumption) dynamically relevant
and we have assumed TP = TF , Definition 1 applies to give
S is conscious in kM ∗ ⇒ kM ∗ |TF 6= kTF
(5.3)
∗
for all dynamical trajectories kM ∗ of M .
2The point here is to restrict downwards, not upwards. Any question “above” the computational level can be posed
in terms of computational dynamics.
5
Let us now assume that S is conscious in some
trajectory kM ∗ of M ∗ . According to the last implication, we thus have
kM ∗ |TF 6= kTF .
Because TF < Tcomp , we can map both of these
trajectories to Tcomp . For kM ∗ |TF , this gives
kM ∗ |TF |Tcomp = k∗ |TF |Tcomp
= k∗ |Tcomp = kM ∗ |Tcomp ,
where we have made use of identities established
in Sections 1 and 2. Equation (5.2) furthermore
establishes that
kM ∗ |Tcomp = k∗ |Tcomp = kTcomp .
The two facts that (a) kM ∗ |Tcomp = kTcomp and
(b) that S is conscious in kM ∗ establish that S is
conscious in kTcomp .
Equation (5.2) also establishes that
kTF |Tcomp = kTcomp .
Because of this equation and TF < Tcomp , the implication of Definition 3 explained in the last paragraph of Section 4 applies and establishes that S
is conscious in kTF .
Unwrapping what ‘S is conscious in kTF ’ means
by definition, we find that there must by a dynamical evolution k̃M ∗ of M ∗ such that
(a) k̃M ∗ |TF = kTF
and
(b) S is conscious in k̃M ∗ .
Together, these two conditions violate (5.3). Thus
we have arrived at a contradiction.
The assumptions that went into the derivation
of this contradiction were that consciousness is dynamically relevant with respect to the TF level,
that S is an AI system, and that S is conscious
in a trajectory kM ∗ of M . The first assumption is
stated as a condition in the theorem. Thus it follows that the latter two cannot be both the case.
Because kM ∗ was arbitrary, it follows that an
AI system S cannot be conscious in any trajectory
kM ∗ of M ∗ . Consequently, applying Definition 3,
it cannot be conscious at all. This establishes the
claim that if consciousness is dynamically relevant
with respect to TF , then AI systems aren’t conscious.
It remains to consider all other cases of TP in
Definition 2. Therefore, let us assume that consciousness is dynamically relevant with respect to
some TP 6= TF . Because TF < TP for all TP ∈ Υ,
and because dynamical relevance passes downward
(Lemma 5), it follows that consciousness is also dynamically relevant with respect to TF . Hence the
previous case applies and the result follows in full
generality.
6. Is Consciousness
Dynamically Relevant?
There are at least three routes to answer this
question. Dynamical relevance is an epistemic assumption which is partially related to an ontological assumption known as ‘causal closure of the
physical’ or ‘completeness of the physical’ [42]: if
the physical is not causally closed in virtue of consciousness, then consciousness is dynamically relevant. Therefore, a first route to determine whether
consciousness is dynamically relevant is via philosophy of mind.
There have been extensive arguments for and
against the causal closure of the physical in the literature, cf. [42] for a short summary. To the best
of our knowledge, there is to date no conclusive
argument against the causal closure. On the other
hand, no argument for causal closure can establish dynamical ir relevance because if consciousness
is physical, causal closure holds, yet consciousness
can still be dynamically relevant.
The second route is to study necessary conditions of some of the practices we engage in as
researchers or as a society; those are conditions
which are presupposed by these practices.
A great example is the empirical investigation
of consciousness itself, as pursued broadly now
under the roof of the Association for the Scientific Study of Consciousness, among other organisations. Any empirical investigation of consciousness presupposes behavioural measures (such as,
but not limited to, reports) that can be used to
infer the state of consciousness of a subject in certain contexts. These means of inference are often
referred to as measures of consciousness [22]. Dynamical relevance is a premise for any measure of
consciousness to work as intended. That is because if consciousness does not make a difference
to the time evolution of any physical states, its
presence or absence cannot be inferred from the
physical states that account for body movement
(pressing of a button, say) or sound waves (verbal
report). Empirical distinguishability of theories of
consciousness hinges on dynamical relevance.3
Another good example of the second route is the
investigation of consciousness from an AI engineering perspective. If consciousness makes a difference
to how a system performs, it is dynamically relevant. Therefore, any AI engineering perspective
3[27] proves this point by analysing what data is and how it is used in experiments in consciousness science. Data is
determined by physical states such as charge position or magnetic orientation; dynamical relevance is required for two
theories to cause different such states and hence different data. For details, cf.[27], noting that dynamical relevance is
referred to as an ‘empirical version of the closure of the physical’.
6
which asks how the implementation of consciousness can make a difference to a system’s evolution
presupposes that consciousness is dynamically relevant.
The third route, finally is via existing theories
of consciousness, where it is helpful to distinguish
between metaphysical theories and scientific theories. Metaphysical theories primarily target the
question of what consciousness is, whereas scientific theories primarily model what consciousness
does.4
Some metaphysical theories, such as type identity theory [41], Russelian-type panpsychism [19],
or Chalmers-style dualism [10], presuppose consciousness to not be dynamically relevant. Others, such as interactive dualism [17] or dual aspect
monism [1], render consciousness dynamically relevant. Yet others leave the question open, for example most versions of functionalism [30]: it remains
unclear whether the function that consciousness is
identified with has a dynamical relevance over and
above the physical theories that are thought to implement it.
The situation isn’t much better in the case of
scientific theories, unfortunately. The only unambiguous example we know of is Integrated Information Theory (IIT) [38], which despite its nonphysicalist ontology and emphasis of the primacy
of conscious experiences proposes a mathematical model in which consciousness is not dynamically relevant.5 Models such as Global Neuronal
Workspace Theory [32] or Higher Order Thought
Theory [9] do not imply either case, as far as we
can see.
In summary, it seems to us that the only conclusive route to date seems to be route number
two, which largely speaks in favour of dynamical
relevance.
7. Objections
In this section, we discuss a few immediate responses to our result.
7.1. Verification is imperfect. Verification is
an industrial process that may not be perfect: despite functional and post-silicon verification, the
actual dynamics of a processor may not adhere to
the computational theory targeted by verification
in all cases. Verification may leave a bit of wiggleroom for the dynamics to diverge from the computational theory. Could this wiggle-room suffice for
consciousness to unfold its dynamical effects?
Any answer to this question depends on how
exactly consciousness is dynamically relevant and
which imperfections arise in day-to-day verification. It is natural to expect that consciousness’
dynamical relevance is systematic in nature: dynamical effects should systematically occur if a system is conscious and make a systematic difference
to how the system evolves in time. The imperfections in day-to-day verification, on the other hand,
are likely to be mostly random in nature, meaning
that the deviation in dynamical evolution they fail
to suppress are random too, both in time (when
such a deviation can occur) and in the extend to
which they can make a difference. If this is true,
it is unlikely that the wiggle-room left open due to
imperfections suffices for consciousness to unfold
its dynamical effects.
7.2. Emergence. Our result is compatible with
emergence. If consciousness is weakly emergent
from a physical substrate [39], consciousness is
not dynamically relevant with respect to this substrate, so that our result does not apply. If consciousness is strongly emergent, it is dynamically
relevant: the “fundamental higher-level causal
powers” [39, Sect. 4] which exist in this case make
a difference to the time evolution of the substrate
states, a difference that is excluded or suppressed
by any design which is verified to comply to nonemergent substrate dynamics.
7.3. Probabilistic processing. Verification as
applied in industry targets deterministic computational theories. Would our result also hold in
case of verified probabilistic processing?
The mathematical framework we apply is compatible with probabilistic processing: we do not
make an assumption as to whether the notions of
state and dynamical evolution are deterministic or
not; a state may well be a probability distribution
and its dynamical evolution a stochastic process.
Verification, in this case, implies that a system conforms to the stochastic process as described by a
stochastic computational theory. This leaves room
for consciousness to have a dynamical effect, but
only if this effect conforms to the probability distributions as described by the stochastic computational theory. That is, consciousness may determine how the probability distributions of the stochastic computational theory are sampled, but it
cannot change them. As in the case of imperfect
verification, we remain sceptical as to whether this
limited freedom is compatible with the systematic
4Thanks to Kobi Kremnitzer for pointing us to this terminology.
5The algorithm that IIT presupposes takes the form of a mapping (function) from a physical descriptions of systems
to a space of states of conscious experiences [28], so that the time evolution of the physical state is precisely as described
by the underlying physical theory.
7
nature of consciousness’ dynamical effects that are
to be expected.
7.4. Quantum computing. Does our result also
hold true in the case of quantum computing?
Quantum computing is a young industry and it
is not yet clear which type of verification, if any,
will need to be deployed. It is likely, however,
that any type of verification will need to presuppose a notion of measurement, which is an inherently vague concept in quantum theory [2] that is
partially external to the account of quantum dynamics by the Schrödinger equation. If consciousness were related to measurement (for example via
consciousness-induced dynamical collapse as proposed in [13]), then verification might leave enough
room for consciousness to have a systematic and
meaningful effect. If, on the other hand, consciousness is not related to measurement in quantum theory, it is likely that verification of quantum computers to adhere to quantum dynamics will preclude any potential dynamical effects of consciousness; just as in the classical case.
8. Conclusion
This paper addresses the question of whether AI
systems are conscious. Its objective is to introduce
a new formal tool, in the form of a theorem, that
provides an answer to this question which is independent of the specific computational architecture
that an AI system utilises, and which does not rely
on any specific cognitive feature that an AI system
might possess or lack that may be related to conscious experience.
Our result is based on what we take to be the
only property that distinguishes AI systems from
other cognitive systems, a property that might well
embody the actual meaning of the word ‘artificial’
in ‘artificial intelligence’: that the system runs on
a substrate that has been designed and verified,
rather than naturally evolved.
Ultimately, we believe that any statement about
whether a system is conscious needs to be based on
a theory of consciousness that is supported by theoretical, philosophical, and most importantly empirical evidence. The Science of Consciousness6
searches for such theories. The crucial premise
in our result—dynamical relevance—is a property
which theories ascribe to consciousness, so that
our theorem can be regarded as establishing a
fact about AI’s capability for consciousness for a
whole class of theories of consciousness: all those
that posit consciousness to be dynamically relevant. Results of this form are important as long as
evidence in favour of any single theory of consciousness, as well as evidence to distinguish among
them, is still in its early stages, and while the
space of possible theories remains only partially
explored.
Our result has a few interesting, slightly funny,
and potentially relevant implications for AI engineering and AI interpretability. The most notable
of these is that our result shows that if an AI system states that it is conscious, then this cannot be
because it is conscious. That is to say, the cause of
any such statement cannot be that the AI system is
conscious. This follows because if such a cause existed, consciousness would have to be dynamically
relevant, in which case our theorem implies that
the system isn’t conscious. Another implication is
that if consciousness has functions that could improve a system’s information processing, then, to
make use of those functions, theories of consciousness should be taken into account when designing
the substrate on which an AI system will run.
The question of whether AI systems are conscious is of major societal concern. It has important ethical [7, 33], legal [3, 45], and technological consequences, and will likely play a major role
in shaping governance of AI and how individuals
interact with this technology. Our result aims to
deliver a rigorous and justified answer to this question that does not rely on contingent assumptions,
such as the truth of a particular theory of consciousness, or the validity of a particular test of
consciousness when applied to AI systems.
Acknowledgements. We would like to thank the
participants of the Modelling Consciousness Workshops 2022 and 2023 of the Association for Mathematical Consciousness Science for valuable discussions on the topic of AI consciousness and feedback
about this result, specifically Alexandra Proca,
Cameron Beebe, Sophie Taylor, Peter Thestrup
Waade, Joscha Bach, Mathias Gutmann, George
Deane, Jordan O’Byrne, Ian Durham and Sean
Tull. This research was supported by grant number FQXi-RFP-CPW-2018 from the Foundational
Questions Institute and Fetzer Franklin Fund, a
donor advised fund of the Silicon Valley Community Foundation. We would like to thank the
Dutch Research Council (NWO) for (partly) financing TL’s work on project number 182.069 of
the research programme Fluid Spintronics, and the
Mathematical Institute of the University of Oxford
for hosting JK while working on this project.
6Also called Scientific Study of Consciousness to emphasise the importance of contributions from humanities, most
notably philosophy.
8
References
[1] H. Atmanspacher and C. A. Fuchs. The Pauli-Jung
conjecture and its impact today. Imprint Academic,
2014.
[2] J. Bell. Against ‘measurement’. Physics world,
3(8):33, 1990.
[3] C. Benzmüller and B. Lomfeld. Reasonable machines:
A research manifesto. In KI 2020: Advances in Artificial Intelligence: 43rd German Conference on AI,
Bamberg, Germany, September 21–25, 2020, Proceedings 43, pages 251–258. Springer, 2020.
[4] N. Block. Troubles with functionalism. In The Language and Thought Series, pages 268–306. Harvard
University Press, 1980.
[5] L. Blum and M. Blum. A theory of consciousness from
a theoretical computer science perspective: Insights
from the conscious turing machine. PNAS, 2022.
[6] L. Blum and M. Blum. A theoretical computer science
perspective on consciousness and artificial general intelligence. arXiv preprint arXiv:2303.17075, 2023.
[7] N. Bostrom and E. Yudkowsky. The ethics of artificial intelligence. In Artificial intelligence safety and
security, pages 57–69. Chapman and Hall/CRC, 2018.
[8] Z. Bronfman, S. Ginsburg, and E. Jablonka. When
will robots be sentient? Journal of Artificial Intelligence and Consciousness, 8(02):183–203, 2021.
[9] R. Brown, H. Lau, and J. E. LeDoux. Understanding
the higher-order approach to consciousness. Trends in
cognitive sciences, 23(9):754–768, 2019.
[10] D. J. Chalmers. The conscious mind: In search of a
fundamental theory. Oxford Paperbacks, 1997.
[11] D. J. Chalmers. The singularity: A philosophical analysis. Journal of Consciousness Studies, 2010.
[12] D. J. Chalmers. Could a large language model be conscious? arXiv preprint arXiv:2303.07103, 2023.
[13] D. J. Chalmers and K. J. McQueen. Consciousness
and the collapse of the wave function. In S. Gao, editor, Consciousness and Quantum Mechanics. Oxford
University Press, forthcoming.
[14] W. J. Clancey. The strange, familiar, and forgotten:
An anatomy of consciousness. Artificial Intelligence,
60(2):313–356, 1993.
[15] A. Clark. Being there: Putting brain, body, and
world together again. MIT press, 1998.
[16] D. C. Dennett. Consciousness Explained. Little,
Brown and Co., 1991.
[17] J. C. Eccles and K. Popper. The self and its brain:
an argument for interactionism. Routledge, 1977.
[18] K. J. Friston, M. J. Ramstead, A. B. Kiefer,
A. Tschantz, C. L. Buckley, M. Albarracin, R. J.
Pitliya, C. Heins, B. Klein, B. Millidge, et al. Designing ecosystems of intelligence from first principles.
arXiv preprint arXiv:2212.01354, 2022.
[19] P. Goff. Consciousness and fundamental reality. Oxford University Press, 2017.
[20] J. Haugeland. Artificial intelligence: The very idea.
MIT press, 1989.
[21] O. Holland. Machine consciousness. Imprint Academic, 2003.
[22] E. Irvine. Measures of consciousness. Philosophy
Compass, 8(3):285–297, 2013.
[23] X. Ji, E. Elmoznino, G. Deane, A. Constant, G. Dumas, G. Lajoie, J. Simon, and Y. Bengio. Sources of
richness and ineffability for phenomenally conscious
states. arXiv preprint arXiv:2302.06403, 2023.
[24] A. Juliani, K. Arulkumaran, S. Sasai, and R. Kanai.
On the link between conscious function and general intelligence in humans and machines. Transactions on
Machine Learning Research, 2022.
[25] A. Juliani, R. Kanai, and S. S. Sasai. The perceiver
architecture is a functional global workspace. In Proceedings of the Annual Meeting of the Cognitive Science Society, volume 44, 2022.
[26] J. Kleiner and T. Ludwig. What is a mathematical
structure of conscious experience? arXiv preprint
arXiv:2301.11812, 2023.
[27] J. Kleiner and H. Stephan. The closure of the physical,
consciousness and scientific practice. arXiv preprint
arXiv:2110.03518, 2023.
[28] J. Kleiner and S. Tull. The mathematical structure of
Integrated Information Theory. Frontiers in Applied
Mathematics and Statistics, 6:602973, 2021.
[29] A. Y. Lee. Modeling mental qualities. Philosophical
Review, 130(2):263–298, 2021.
[30] J. Levin. Functionalism. In E. N. Zalta and U. Nodelman, editors, The Stanford Encyclopedia of Philosophy. Stanford University, 2023.
[31] C. List. Levels: descriptive, explanatory, and ontological. Noûs, 53(4):852–883, 2019.
[32] G. A. Mashour, P. Roelfsema, J.-P. Changeux, and
S. Dehaene. Conscious processing and the Global Neuronal Workspace Hypothesis. Neuron, 105(5):776–
798, 2020.
[33] T. Metzinger. Artificial suffering: An argument for
a global moratorium on synthetic phenomenology.
Journal of Artificial Intelligence and Consciousness,
8(01):43–66, 2021.
[34] P. Mishra and N. D. Dutt. Functional verification of
programmable embedded architectures: a top-down
approach. Springer Science & Business Media, 2005.
[35] P. Mishra, R. Morad, A. Ziv, and S. Ray. Post-silicon
validation in the soc era: A tutorial introduction.
IEEE Design & Test, 34(3):68–92, 2017.
[36] S. Mitra, S. A. Seshia, and N. Nicolici. Post-silicon
validation opportunities, challenges and recent advances. In Proceedings of the 47th Design Automation Conference, pages 12–17, 2010.
[37] D. C. Mollo and R. Millière. The vector grounding
problem. arXiv preprint arXiv:2304.01481, 2023.
[38] M. Oizumi, L. Albantakis, and G. Tononi. From the
phenomenology to the mechanisms of consciousness:
Integrated Information Theory 3.0. PLoS computational biology, 10(5):e1003588, 2014.
[39] T. O’Connor. Emergent Properties. In E. N. Zalta, editor, The Stanford Encyclopedia of Philosophy. Stanford University, 2021.
[40] R. Penrose. The emperor’s new mind. Oxford University Press, 1989.
[41] U. T. Place. Is consciousness a brain process? British
Journal of Psychology, 47(1):44–50, 1956.
[42] D. Robb, J. Heil, and S. Gibb. Mental Causation. In
E. N. Zalta and U. Nodelman, editors, The Stanford Encyclopedia of Philosophy. Stanford University, 2023.
[43] J. R. Searle. Minds, brains, and programs. Behavioral
and brain sciences, 3(3):417–424, 1980.
[44] S. W. Smoliar. The remembered present: A biological
theory of consciousness: Gerald m. edelman. Artificial Intelligence, 52(3):295–318, 1991.
[45] R. Susskind. Online courts and the future of justice.
Oxford University Press, 2019.
[46] M. Tegmark. Life 3.0: Being human in the age of
artificial intelligence. Knopf, 2017.
[47] A. M. Turing. Computing machinery and intelligence.
Mind, 1950.
[48] W. Wiese. Could large language models be conscious? a perspective from the Free Energy Principle.
Preprint, 2023.
[49] B. Wile, J. Goss, and W. Roesner. Comprehensive
functional verification: The complete industry cycle. Morgan Kaufmann, 2005. |
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 1009-1014
Tank, H. K., On the Nature of Consciousness, Space & Ultimate Reality
1009
Exploration
On the Nature of Consciousness, Space & Ultimate Reality
Hasmukh K. Tank*
ABSTRACT
In this article, I discuss first the physics involved in our subjective experience of mind and
consciousness and then its similarity with the nature of space is pointed out based on the
transmission of electromagnetic waves. From this similarity, a possibility of universality of
consciousness is inferred.
Key Words: consciousness, space, ultimate reality, subjective experience, mind.
Introduction
(i) How exactly the large conglomeration of atoms, called DNA and RNA molecules, got
formed; and self-replicating, conscious living-beings got evolved? (ii) What is ‘mind’, and what
is ‘consciousness’; and how they can be understood in terms of physics and chemistry? Such
questions are going to be the most interesting topics of research in this 21st century. I present
here a preliminary discussion on these subjects.
Firstly, we will divide the total reality into two aspects: (i) the ‘subjective’ aspect which can be
subjectively felt and experienced, but cannot be objectively shown and demonstrated; and (ii) the
‘objective’ aspect, which can be weighed and measured; and can be subjected to scientific
experiments. Then we will try to establish certain correlations between these two aspects. And
finally, we will draw some inferences on a possibility of presence of ‘subjective aspect’ where
we are unable to feel them directly. Based on this discussion we will arrive at a hypothesis that
‘consciousness’ may be present even in the ‘space’; and so, ‘consciousness’ may be a universal
entity, not just limited to our brains and ‘minds’.
The Hypothesis
All of us are very much sure about the fact that each one of us is a conscious living being; and
our ‘consciousness’ has something to do with our brains. We also know that when a neurosurgeon opens a human brain, he is able to find only a large network of interconnected neurons.
These neurons get electrically charged by a mechanism called ‘sodium-pump’, operated by the
energy from our food; and they generate a sequence of electrical-discharge-pulses, whenever
they come in contact with the sense-objects like: sound, touch, vision, taste and odor. The neurosurgeons are not able to objectively see any ‘mind’ or ‘consciousness’ in the brain. From this
observation we find that: where we are perfectly sure about the presence of subjective aspects
*
Correspondence: Hasmukh K. Tank, Indian Space Research Organization, 22/693 Krishna Dham-2, Vejalpur, Ahmedabad380015, India. E-Mail: tank.hasmukh@rediffmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 1009-1014
Tank, H. K., On the Nature of Consciousness, Space & Ultimate Reality
1010
called ‘mind’ and ‘consciousness’, what we are able to objectively see is only a large,
interconnected network of neurons; similarly, just because we are not able to see ‘mind’ and
‘consciousness’ in ‘electrons’, ‘atoms’ and ‘molecules’, it does not mean they may not be able to
subjectively perceive the presence of other ‘electrons’, ‘atoms’ and ‘molecules’. With whom-soever we are able to establish communication; and get response, then we come to know that the
other one has ‘mind’ and ‘consciousness’; and who-so-ever do not respond to our stimuli, then
we think it is ‘dead’ and ‘inert’[1]. A particular subjective experience of ‘mind’ may be related
to a particular neuronal-discharge-sequence, but what exactly is ‘mind’ and ‘consciousness’? To
seek answers to these questions, let us consider the following:
Human brain contains around 1010 neurons. Each neuron is electrically charged at about 70 millivolts as shown in fig.1. Now, if we could connect all the neurons in a series, then they can
develop 700 mega-volts of e.m.f. And if we can connect all the neurons in parallel, and assume
that each neuron can deliver just one micro-ampere of current, then also human-brain can deliver
700 000 Amperes of current. Human-brain is equivalent to a 700 watt electric-lamp. But when
we try to measure the potential-difference between any two points of brain, the electroencephalogram measures only a few micro-volts. It is so, because the neurons are comparable
with electrically-charged-capacitors, as shown in fig.1a-b, which are electrically-connected as
shown in the fig.2. The compact packaging of the brain seem to produce a ‘mutually-balancingelectric-field’, as shown in fig.3.
Fig.1(a): A diagram, representing electrically charged neurons. Excitatory and inhibitory
neurotransmitters enter the cell through dendrites; and when the in-put of neurotransmitters
crosses a threshold-level, the cell electrically discharges, and that discharge-wave travels towards
the ends of axon. These ends, in turn, release neurotransmitters in the synaptic-junction, and
enter the neighboring neuron.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 1009-1014
Tank, H. K., On the Nature of Consciousness, Space & Ultimate Reality
1011
Fig.1(b): From the view-point of electrostatics, the arrangement of neurons, shown in fig.1(a) is
equivalent to electrically-charged capacitors, shown here.
Fig.2: Four electrically-charged capacitors are so connected that the volt-meter reads zero volts.
When the switch S is closed, the mutually-balancing-electric-field gets disturbed; and the voltmeter reads voltages equal to the amount of imbalance.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 1009-1014
Tank, H. K., On the Nature of Consciousness, Space & Ultimate Reality
1012
Fig.3: A diagram representing mutually-balancing electrostatic-field of the whole brain. Each
and every spherical-capacitor of the figure-1(b) is being pushed apart by the neighboring
neurons, as shown here by pushed springs; giving rise to a balanced electrostatic-field. When
some of the neurons get discharged, the balance of the ‘whole’ brain gets disturbed. Separate
chains of neuronal-discharge-sequence, contribute to disturb the balance of the whole brain, thus
connecting different subjective-experiences.
We are sure that this large collection of neurons has a subjective aspect called ‘mind’ and
‘consciousness’. Now, supposing we emulate an equally large collection of electrically
chargeable spherical capacitors, which can be sequentially discharged by photo-cells, pressuregauges, thermistors, smoke-detectors…etc; and get re-charged by current-sources connected to
each one of them; and supposing further that ‘mind’ and ‘consciousness’ is an electromagnetic
process, related to electromagnetic-field of the whole brain, then we can expect a similar
subjective experience of ‘mind’ and ‘consciousness’ which may be subjectively felt by the
emulator built by us. As far as our objective observation is concerned, there is not much
difference between the human-brain and the emulated-brain built by us; because both of them
generate a sequence of electrical discharge pulses whenever some audio-visual stimulus is
applied; and both of them can get re-charged. Theoretically, such a simulator can be built so
perfectly, that the electro-encephalogram patterns (EEG-pattern) generated by human-brain and
the emulated-brain in response to a given stimulus are exactly the same. By incorporating longISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 1009-1014
Tank, H. K., On the Nature of Consciousness, Space & Ultimate Reality
1013
term-memory and out-put-transducers the emulated-brain may even be able to speak: “O, it is
very cold today!” If we get such a response from the emulator, then we can draw a scientifically
acceptable inference that our subjective experiences of ‘mind’ and ‘consciousness’ are collective
processes of electrostatic-fields due to charge and discharge activities of neurons.
Now, let us concentrate on the nature of electromagnetic waves, and true nature of ‘space’
emerging from our discussion. We know that in the case of water-waves, particles of water do
not travel physically. Only the activity of up and down motion of water-molecules gets spread in
the direction of propagation of the wave. Similarly, in the case of ‘electromagnetic waves’, they
are the oscillations of electric-field which induce oscillations in the neighboring space. From this
discussion it is clear that the so-called ‘empty-space’ is not really empty. Space must be an
equilibrium-state of positive and negative electrostatic fields, then-alone a particular point in
space can become electrically positive or negative without transport of any physical thing. In this
physical world, there is nothing other than such activity of waves. The so-called ‘particles’ of
‘matter’ are nothing more than ‘standing-wave-patterns’ of the above-mentioned waves.
The reader must have already noticed a similarity between the electrostatic equilibrium generated
in the human brain due to the large collection of electricity charged neurons; and the electrostatic
equilibrium of ‘space’, because of which transmission of electromagnetic waves becomes
possible, without any physical transportation. Both, empty-space as well, as human brain,
experience electrostatic disturbances; our brain due to the transmission of neuronal discharge
sequence; and ‘space’ due to the electromagnetic waves. Since we have a direct subjective
experience of our thoughts and feelings, perfectly correlated with the neuronal discharge
sequences in our brains, it will not be illogical to infer that the ‘space’ also must be experiencing
some kind of subjective feeling whenever electromagnetic-waves pass through it.
Empty space is a three-dimensional, electrically balanced “screen” or an ‘arena’ which gets
modified during the propagation of electromagnetic waves. As we discussed earlier, human brain
is a crude version of ‘space’; and neuronal discharge sequences generated in it are crude, bandlimited representations of the external world; whereas external physical world is a multidimensional pattern of full-band of waves. From this discussion it should not be difficult to
imagine how crude must be our mental version of the world than the actual physical world; and
how crude must be our personal version of ‘consciousness’ from the Cosmic Consciousness.
Summary & Discussion
We first discussed the physics involved in our subjective experiences of ‘mind’ and
‘consciousness’; and then, from the study of propagation of electrostatic disturbances, found a
similarity between the ‘brain’ and ‘empty space’. This similarly led us to infer a possibility of
presence of ‘subjective aspect’ in the ‘space’. The ‘omni-present GOD’ referred in religious
literatures, may be scientifically understandable as follows. Empty-looking ‘space’ is not really
empty; the ultimately-real, most-fundamental-reality is present everywhere in space. This
ultimate reality can be visualized as ‘mutually-balancing-electrostatic-field’ which is
subjectively aware of its own existence; and whenever electromagnetic-waves, or ‘matter-waves’
pass through it, it is able to subjectively ‘feel’ the passage of the waves. Since this ultimateISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 1009-1014
Tank, H. K., On the Nature of Consciousness, Space & Ultimate Reality
1014
reality is subjectively aware of its own existence, and is able to perceive the waves passing
through it, we should use the word ‘He’ instead if ‘it’ for the ultimate-reality.
Our conclusion is in agreement with the statements found in ancient spiritual scriptures, e.g. In
the Yoga Vashishtha Maha-Ramayana, the Guru Vashishtha explains to the Prince Rama: “This
physical-world is a play of waves, arisen in the nectar-ocean of all-pervading pure
‘consciousness’; and it (the physical-world) also subsides in that ocean alone” [2].
An eighteenth-century mathematician William Clifford had uttered these prophetic words: “A
piece of ‘matter’ is nothing but ‘curvature of space’, subject (possibly) to fluctuations in the
manner of waves” [3].
According to the Nobel Laureate biochemist, Prof. George Wald, [4]: “Mind, rather than
emerging as a late product in evolution, may be present always as a complimentary aspect of all
matter”.
References
1. Tank, H. K. “A hypothesis for ‘consciousness’” Aswina- The Bulletin of Bio-medical Engg. Society,
Vol.4, January, (1988)
2. Yoga-Vashishtha Maharamayana (1500)
3. William Clifford The Philosophical Magazine, Vol. 4 (1896)
4. Wald George, Souvenir published on the occasion of The World Congress for the Synthesis of Science
and Religion (1986)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
CONSCIOUSNESS AND THE WIGNER’S FRIEND PROBLEM
Bernard d’Espagnat
arXiv:quant-ph/0402121v2 11 Jan 2006
Laboratoire de Physique Théorique1
Université de Paris XI, Bâtiment 210, 91405 Orsay, Cedex, France
It is generally agreed that decoherence theory is, if not a complete answer, at least
a great step forward towards a solution of the quantum measurement problem. It is
shown here however that in the cases in which a sentient being is explicitly assumed
to take cognizance of the outcome the reasons we have for judging this way are not
totally consistent, so that the question has to be considered anew. It is pointed
out that the way the Broglie-Bohm model solves the riddle suggests a possible clue,
consisting in assuming that even very simple systems may have some sort of a protoconsciousness, but that their “internal states of consciousness” are not predictive.
It is, next, easily shown that if we imagine the systems get larger, in virtue of
decoherence their internal states of consciousness progressively gain in predictive
value. So that, for macro-systems, they may be identified (in practice) with the
predictive states of consciousness on which we ground our observational predictions.
The possibilities of carrying over this idea to standard quantum mechanics are then
investigated. Conditions of conceptual consistency are considered and found rather
strict, and, finally, two solutions emerge, differing conceptually very much from one
another but in both of which the, possibly non-predictive, generalized internal states
of consciousness play a crucial role.
Key words: measurement, decoherence, reality, consciousness, time.
1
Unité Mixte de Recherche (CNRS) UMR 8627
1
1. INTRODUCTION
The central claim, in this paper, is that the Schrödinger-cat – or Wigner’s friend –
paradox cannot be really solved without going deeply into a most basic question,
namely: are we able to describe things as they really are or should we rest content
with describing our experience? A priori, of course, we have a hope of doing both at
once. We think that, by enlarging our experience, and reasoning on it, we shall progressively lift the veil of appearance and attain knowledge of reality. But historically
things did not take this turn. It is well known that the attempts at imparting an ontological interpretation to modern physics, and particularly quantum physics, have
met, and still meet, with difficulties. Admittedly, these obstacles are not insuperable, but still they imply that essentially ad hoc and quite artificial-looking changes
should be made in the formalism. And this is one of the reasons why the alternative
standpoint, centered on the description of communicable human experience, is also
considered reasonable after all. Of course another reason – a historical one – is the
fact that such a standpoint was taken up both by the “founding fathers” of quantum
physics and, in the same period, by the Vienna Circle positivists. Unfortunately, it
must be observed that, on the whole, neither the ones nor the others were explicit
concerning the very existence of the dilemma in hand. Schlick, for example [1] had
clearly stated the basic positivist axiom that the meaning of a scientific statement
boils down to its method of verification, which obviously makes the notion of “mind”
(the mind or minds that verify) prior to that of scientific reality. But still, in spite
of this, in most of their writings the logical positivists implicitly seemed to suggest
that the rules they claimed science should follow (the principle of verification for
example) somehow led to some knowledge of a reality “out there”, in other words
of mind-independent reality.
This ambiguity got transferred to quantum physics and, in fact, it is still with
us. In a sense it should be considered beneficial. Thanks to it, most physicists do
not think it necessary to take sides concerning two opposite and equally unpleasant
views, the – seemingly aberrant – one that mind is actually the “basic stuff” and the
technically disturbing one that words such as “observables”, “measurements” and
so forth should be banned from basic physics... Which is fortunate since it turns out
that explicitly opting in favor of one of these standpoints is not at all necessary for
2
doing research in that science. In it, the vague notion of “empirical reality” serves
as a conceptual basis and is, for practically all purposes, a totally sufficient one.
On the other hand however, it is a general rule of reasoning that, wherever they
appear, ambiguities should be removed. And sometimes this indeed is even useful
in practice. I claim that this is the case concerning the problem in hand and that,
for solving it, the rule in question should be followed, even at the price of having
to openly face one or both of the two just mentioned queer views. Here both of
them will therefore be taken seriously. In fact, it will be shown that either of them
constitutes a suitable framework for solving the Wigner’s friend paradox, provided
that they are taken with all the consequences each one implies, disregarding their
incompatibility with such and such deeply engrained “received views”.
In view of the foregoing it would not be entirely unreasonable to consider that
going into such considerations somehow amounts to deviating from physics proper.
It is therefore not surprising that most physicists turn away from such problems.
But still, this disinclination is far from being fully general. In our times some first
rate physicists do take great interest in the question of how quantum mechanics is to
be interpreted, whether or not it is compatible with realism, and so on. And Asher
Peres is distinctly one among them, as the number of papers in which he touched
upon such matters convincingly shows. It is therefore a pleasure to dedicate this
article to him. It is true that, in such a field, most physicists – Peres included –
manage so as to avoid speculating, which renders their statements concise and,
correspondingly, leaves a few questions open. Here I shall not be so careful. I shall
quite avowedly – but, still, not wildly! – speculate.
The paper is divided into four parts. In the first one (Section 2) general facts are
perused concerning the measurement problem and the extent is discussed to which
decoherence theory may be considered to solve the latter, particularly in the case
in which, besides instruments, the measurement process is explicitly assumed to
involve also conscious beings. The second part (Section 3) describes a tentative solution to the just mentioned problem – often called the “Wigner’s friend problem” –
based on an explicitly ontologically interpretable approach to quantum mechanics
(in fact, on the Broglie-Bohm model). The third part (Section 4) explores the possibilities of building up a solution in line with the general ideas underlying the just
3
mentioned one but freed from the condition of ontological interpretability, hence essentially compatible with the general philosophy of standard quantum mechanics. It
deals with criticisms of a logical-conceptual nature that might conceivably be raised
against it, and shows they can be overcome. Finally, in the fourth part (Section 5)
possible bearings of this approach on an age-old philosophical problem, the one of
the nature of time, are briefly sketched.
2. DECOHERENCE AND MEASUREMENT
As is well known, the main difficulty with quantum measurement theory is that
when the system Q on which a quantity B is to be measured (by means of an
appropriate instrument) is not, initially, in an eigenstate of B, if the instrument
is described quantum mechanically the Schrödinger time evolution leads, for the
overall system composed of Q and the pointer (or of Q and the rest of the world
if, along with the pointer, we take the environment into account, as we should), to
a state that is a superposition of macroscopically distinct states or a combination
thereof. This result seems hardly compatible with the often held view that the basic
quantum mechanical symbols describe reality as it really is quite independently of
us, since what is observed has no clear relationship with such superpositions. And,
what is more, under the assumption that the quantum predictive rules are universal
the superposition in question could be shown [2, 3] to be incompatible with the view
that macroscopic objects always have definite localizations.
Then decoherence theory came in. As we all know, it is grounded on the fact that
all macroscopic systems significantly interact with their environment (including their
“internal” one) and on the remark that, in practice, most of the physical quantities
pertaining to the environment cannot be measured. It is claimed by many that
decoherence actually solves the measurement problem. This assertion however is
far from being endorsed by all physicists, and the reason is that recognition of the
universality of the said interaction is only one of the ingredients in the solution.
Another one is a watering down of realism.
This point being quite crucial for what follows, some details are worth being
recalled concerning it. In quantum mechanics it is usually and appropriately considered that the meaning of factual statements is directly tied to what we count as
4
evidence for them. More precisely: in it a factual statement, if true at all, can be
true only in virtue of something of which we could know. In particular, statements
concerning the physical state in which a physical system lies can have truth-values
(be true or false) only in virtue of measurements that we could perform. Hence it is
only by referring to the possible outcomes of the measurements of some observables
pertaining to a physical system that we may define the state of the latter. A strict,
somewhat Schlick-like, interpretation of these epistemological principles leads to the
(strong) completeness hypothesis, according to which, referring to the measurement
outcomes of a complete set of compatible observables entirely specifies the physical
state in question. This argument corroborates the commonly accepted view that
states of individual systems are specified by state vectors2 .
It is on this basis that, in one of the above referred to papers, Bassi and Girardi
[3] could build up quite a general proof that decoherence fails to solve the measurement problem. They proceeded as follows. Given the macroscopic configuration of
a macro-object of any sort they considered the set V of all the state vectors that
may represent it. Next, they pointed out that, assuming the (strong) completeness
hypothesis, the sets of vectors corresponding to two well-separated macroscopic configurations should be “almost orthogonal” in a mathematically well-defined sense.
In particular this must hold true concerning the sets, VU and VD , that, in a measurement process, contain the final overall state-vectors corresponding to two distinct
values, U and D, say, of the measured quantity. They then considered a generalized
such process, such as the above-described one, in which the to-be-measured quantity
B may have one of the two values U and D. And they could show that, in virtue
of the quantum evolution law, the final state-vector of the overall system (including
the instrument pointer as well as the environment) can then be neither in VU nor in
VD . (nor indeed in any other macroscopic position different from “U” and “D”).
In view of this, an upholder of the view that pointers always are at definite places
(in short, a “realist”) may not consider that decoherence solves the measurement
2
It is true that the notion of “protective measurements” (in which the interaction Hamiltonian
acts for a long time with low intensity) makes it possible, in principle, to impart an operationally
defined meaning to mean values of observables of individual systems, and hence also to the notion
of density matrices attached to such systems [4]. To my knowledge the question whether this new
idea might possibly serve as a basis for new attempts towards a realist approach of the measurement
problem has not been examined.
5
riddle. This shows that for decoherence to be significant a further move, one of
a philosophical nature, is necessary. Roughly speaking it consists in taking two
“conceptual steps” successively. The first one is to consider, along the lines marked
out by Plato, Descartes, Kant and others, that our senses may, to a great extent,
be deceitful and that what we apprehend – the set of the phenomena – is liable to
considerably differ from whatever may be said to “really exist”. Such a view makes
it easier for us to grant that, after all, there might be a gap between what we see –
pointers positions – and what we think of – state vectors. On the other hand, the
view in question is still a purely negative one. It does not positively tell us what
type of information mathematical entities such as state vectors may provide us with.
Our second step must be a positive one in this direction. And it seems that there is
no other one to be taken than just to turn to the (generalized) Born rule, otherwise
said to the rule yielding the probabilities that, upon measurement of a physical
quantity, such or such value should be obtained. Now, what is most important at
this point is that the rule in question is essentially predictive of observations. It has
no ontological significance. It does not describe objects and their properties (it is
well known that attributing such a function to the Born rule would immediately
raise a host of conceptual difficulties). It merely informs us of what we shall see – or
of the chances we have of seeing this or that – if we perform such and such actions.
Hence there are some good grounds for considering quantum theory to be essentially – and exclusively – predictive of observations. Now, it is true that if quantum
mechanics is considered universal this limitation partly deprives physics of its “explanatory power at first level”, grounded on the notion of physical events being
explanatory causes of other physical events. It implies that ultimately such notions
as those of cause and explanation should be either dropped or (as seems more rationally justified [5]) transferred to the “higher realm” of some “veiled reality” lying
outside the direct reach of science proper. It is therefore understandable that some
of us should consider the limitation in question to be a pity. But it may be claimed
that, in a strict scientific sense, it is not. After all, describing ultimate reality as it
really is always was the role taken up by metaphysics, and it was often claimed that
the success of science was due to just its parting with metaphysics. In this respect
there is therefore much truth in Schlicks [1] above cited axiom according to which
the meaning of a statement is nothing else than its method of verification, which
6
is, indeed, tantamount to saying that statements that look descriptive are, in truth
merely predictive of observations.
It follows that the fact quantum mechanical predictive methods are so good as
to never have been found at variance with experimental tests may legitimately be
felt to remove our conceptual qualms relative to this theory, including those concerning measurement. And this is especially true since it may then legitimately be
claimed [6] that, at least when only inanimate instruments are involved (see below), decoherence solves the measurement problem. Basically this is due to the fact
that, to repeat, if Schlick’s views are taken literally, when we say that “obviously”,
in an ensemble E of systems S that include pointers, each individual pointer is in
one definite scale interval, the word “is” should not be misunderstood. In fact, it
does not describe a state of things. It merely means that if we look at E we shall
have the impression of seeing the pointers distributed as just said. True, we also
have something else in mind. Accustomed as we are to the “descriptive” sense of
the verb “to be”, by using this verb here we also express our expectation that, of
all the predictions concerning practically feasible measurements that are normally
inferred from its use, none will be at variance with the data. Fortunately, in virtue
of decoherence this condition is fulfilled as we know.
It is important to observe that this “predictive” or “purely operational” interpretation of quantum mechanics happens to remove two well-known conceptual
difficulties that, within the more realist interpretations, still beset the decoherence
theory of measurement. The first one is tightly connected with what was just noted.
It is known that, concerning some extraordinarily complex measurements also involving the environment, quantum mechanics unavoidably yields probabilities that
are at variance with consequences of our usual “realist” way of picturing “outside
macroscopic reality”. But here, and especially since (as has now been shown [7])
the predictive rules of classical mechanics are mere consequences of the quantum
mechanical ones, we may completely drop any realist picture. We may center on
observational predictions. And it is then clear that the discrepancy in question, exclusively bearing as it does on practically unfeasible measurements, is void of both
theoretical and experimental significance.
The second difficulty we have in mind is the famous “and-or” one. Within the
more current (and more “realist”) approaches, applying decoherence theory to indi-
7
vidual cases rather than ensembles raises quite serious problems. Let it be stressed
that such a difficulty does not actually arise here. The reason is that, to repeat,
quantum mechanics is now viewed as merely being a set of computational rules
informing us, via the (generalized) Born formula, of the probabilities we have of
observing this or that. And it is in the spirit of the approach in hand that these
rules, including the Born one of course, should be considered truly primitive. As
such, they do not have to be explained, or inferred from anything else. They are
just given as they are. And in particular, the Born rule is not derived from ensemble
considerations... It is given in its probabilistic form, that is, it yields the probabilities that we shall have such or such specific, “individual” impression. Admittedly,
experimentally verifying the correctness of the thus computed probabilities necessitates considering ensembles. But this was already the case, in classical physics,
concerning all the theories that involved probabilities. In other words the probabilities that, making use of decoherence, we calculate on the basis of the quantum rules
apply to individual events in the same way as do those a card player attributes to
the event of pulling out a given card.
So, upholders of the views of Schlick and the most thoughtful authors of philosophy of science books may well consider that everything is quite in order. On
the other hand, considered under this light quantum mechanics obviously has the
notion of consciousness, not the notion of reality, as a referent. It deals, not with
what is but with what we perceive. More precisely, it involves two basic notions,
one having to do with actuality and the other one with potentiality, both related
to consciousness. The “actual” one is that of “state of consciousness” or “state of
mind” (distinguishing these two notions will not be here necessary): When a human
being has made some observation it is quantum mechanically meaningful to state
that he or she “is” in the corresponding state of consciousness. As for the “potential” notion, it is the one of “probabilities of observation” following from applying
the quantum rules to the pieces of knowledge the state of consciousness contains.
Now, it so happens that this state of affairs raises new questions. The point is as
follows. True, quantum mechanics does not provide us with anything like a God’s
Eye view on what is. That much we just saw. But still, in fact it gives us – or seems
to give us – a point of view that somewhat partakes of a God’s Eye one. It does so
in the sense that the predictions quantum mechanics makes are held to be true for
8
a whole abstract community of human beings. For, in fact, a kind of disembodied
Experimentalist, who is supposed to be looking at an ensemble of measurementperforming instruments and whom these predictions inform about the proportion of
the latter on which he or she will see the pointer at such and such a place on the
dial. This would raise no problem if only one Experimentalist, or, say, one conscious
being existed. Unfortunately (as Wigner quite appropriately remarked!) there are
several ones. Unavoidably we therefore have to face the so-called “Wigner’s friend
problem”, which is just the Schrdinger-cat one, only, with a cat explicitly endowed
with consciousness.
This raises, as I said, a question. To explain what it consists of, let us consider
again a “measurement process” (in the generalized sense) bearing on a microscopic
quantum system Q and let us assume that a physicist P has prepared Q in a state
that is not an eigenstate of the to-be-measured observable B. Let then S be the
system composed of Q, the instrument and a friend F of P looking at the pointer.
Let us think of S at a time t when the process is over but P has not yet looked at
the result (nor asked F what he saw). Within a statistical ensemble E of such S’s,
each one of the friends then sees “his or her” pointer lying in a graduation interval
corresponding to one definite eigenvalue of B. From this actual knowledge, and assuming quantum mechanics is exactly true, he/she may make definite (probabilistic)
predictions concerning what results would be obtained in the future if such or such
measurements were done. All these predictions may then be combined according
to classical, standard probability rules, so as to yield the probabilities with which
P should herself obtain these results. As we know, there are physical quantities
(involving the environment) concerning which these probabilities do not coincide
with those P directly obtains by means of a quantum-mechanical calculation based
on the content of her own state of consciousness, without assuming the friends to be
in definite consciousness states. True these quantities are, in virtue of decoherence
etc., not measurable in practice. But, in the present context, this remark does not
remove the difficulty. The reason is that, in fact, we here have to do with a question
of logical consistency. Assuming both that quantum mechanics is a universal theory
and that the states of consciousness of the friends are predictive same as the one of
P is (i.e. assuming the predictive quantum rules may be applied to them same as to
it) would amount to putting forward a theory yielding different results according to
9
the way calculations are made. This is unacceptable, quite independently of whether
or not the results are practically checkable.
Note that this objection cannot be raised against the general argument on the
basis of which decoherence is said to “solve” the measurement problem (when the
consciousness of the “friends” is not brought into the picture). The reason is that, to
repeat, within the conception in hand the only data that lie in the realm of actuality
(i.e. to which the verbs “to be” or “to have” may, strictly speaking, be applied)
are states of consciousness. Now, in the just mentioned case, the only relevant state
of consciousness is that of P , which merely contains potentialities of observations,
informing her of the chances she would have of getting this or that result if she
chose to measure such and such observable. True, P likes to think of these results as
referring to some empirical reality. She expects that, of all the predictions concerning
practically feasible measurements that may be inferred from assuming this to be
true, none will be at variance with what she directly derives from what she knows,
without making that assumption. But, to repeat, decoherence provides her with
proper insurance in this respect. Within the here taken up conception of what
quantum mechanics is and describes it is therefore true that the above objection is
restricted to the case in which conscious “friends” are involved.
3. THE “WIGNER’S FRIEND” PROBLEM, A MODEL
The just mentioned conception may be referred to as the “purely operationalist”
one3 . But note that it does not in any way amount to rejecting – as meaningless – the
notion of a basic mind-independent reality, as pure idealist thinkers do. It consists in
observing that, whatever this entity “really is”, it presumably differs even more than
previously thought from what it looks like. And that, consequently, the more secure
standpoint is not to take sides, in an a priori manner, on the question whether or
not it should be pictured and, if it should, how it should be. Observe in this respect
that within this standpoint the completeness assumption should not be stated in
the standard, strong form: “hidden variables do not exist” that, following Bassi
and Ghirardi, we implicitly imparted to it in Section 2, since this is a metaphysical
hypothesis, even though a negative one. Following Stapp [9], the assumption in
3
The content of this Section appeared in a preliminary form in Ref. [8]
10
question should be expressed as the hypothesis that “no theoretical construction can
yield experimentally verifiable predictions about atomic phenomena that cannot be
extracted from a quantum theoretical description”. This leaves open the possibility
that hidden variables exist, provided that they should be “really hidden”. Otherwise
said the operationalist conception is, as here understood, quite general. For example,
it is compatible with both pure antirealism and Bohm’s ideas, especially when the
latter are expressed via the conception of a real implicit order, differing very much
from the explicit one that reflects but the appearance of mind-independent reality.
Now, it turns out that the latter remark is here of help, in that it provides us
with some sort of a guiding line. For indeed, when faced with riddles such as the
one described in Section 2 we, physicists, feel somewhat at a loss until we find some
similarity between them and problems that are, to us, more familiar. In this respect,
the old Louis de Broglie-Bohm (hereafter B.B.) hidden variable model (with pilot
wave or quantum potential) may be useful. Not that we should necessarily believe it
is true. Many arguments (e.g. those described in detail in [5] and [10]) speak against
it. But it does reproduce all the observational quantum mechanical predictions; it
yields, to the quantum measurement problem, a solution differing from the above
one but fully consistent as well4 ; and it has the great advantage of being conceptually crystal-clear. It can therefore be used as a “theoretical laboratory”. If, within
it, it proves possible to take explicitly into account the (unquestionable!) fact that
Wigner’s friend is conscious, it is conceivable that the basic idea underlying this
solution can be extended, outside the model, to the general theory. Incidentally,
note that in the model the above-mentioned difference between implicit and explicit
orders of course holds. The implicit order concerns the hidden variables that, together with the nonlocal pilot-wave, compose mind-independent reality. The explicit
order is the order that is manifest in the appearances that compose the set of the
observed phenomena, alias empirical reality.
According to the B.B. model, within a Young-type thought-experiment with two
slits the particle is driven by a pilot-wave that passes through both slits at once;
4
In it, the representative point is, right from the start, determined to proceed into one or the
other of the sectors of configuration space corresponding to the possible pointer positions. The
reason why this solution is not at variance with the Bassi and Ghirardi proof is, as pointed out by
these authors, that, in this model, the strong form of the completeness assumption is not assumed.
11
and this has the consequence that, in the model, while each particle passes through
but one slit, fringes nevertheless appear. We can therefore say that, in the B.B.
model, the particle is at any time at some well-defined place even though it takes
part in a typically quantum phenomenon. In this respect it resembles the friend in
Wigner’s apologue, who is at any time in some well-defined state of consciousness
while he also is taking part in a quantum phenomenon. To strengthen the analogy
it is then appropriate that, in the model, we should attribute to the particle some
kind of a mentality (or, say, proto-mentality), the physical nature of which needs not
be specified in detail. Within the experiment in question, each one of the involved
particles then “observes” that, at a certain time, it passes through one, well specified,
slit. This is an internal state of consciousness of the particle and since, in the model,
the particle position is an element of mind-independent reality, this internal state
of consciousness should also be considered as being an element of mind-independent
reality. For the particle, this internal state of consciousness has no predictive power,
since what will happen to the said particle is entirely governed by the pilot wave.
Now, it is often, and quite rightly, said that the very fact of knowing through
which slit the particle passes prevents the fringes from being formed. At first sight
this might seem to constitute a valid objection against any idea of attributing a
state of consciousness to the particles. And in fact, so it would be if we assumed
that the particle could communicate its knowledge to the world at large. So let us
assume that it can’t. That, at least as far as micro-systems are concerned, “internal
states of consciousness” are really private (since hidden variables do not act on the
pilot wave, such an idea is quite consistent with the fact that, in the model, the
“consciousness state” in question is a “hidden variable” just as the position itself).
This being the case, an external observer such as our P above, even if we assume
she knows of the existence of such internal states of consciousness, must explicitly
ignore this existence when predicting what will be observed. She therefore predicts
the fringes will appear. And this prediction agrees, as we know, with experiment.
On the other hand, imagining a category of states of consciousness that always
remain totally hidden would obviously be quite pointless. Hence, we should ask
whether circumstances exist in which statements bearing on such “internal” states
may, after all, have some relationship with the public domain of shared experience
(while remembering of course that this domain is the one of the explicit order, that
12
is, in the model, the one of “appearances that are the same for everybody”). Now,
decoherence helps us here. For, in the Young-type experiment, call φ1 and φ2 the
partial wave functions issuing from slits 1 and 2 respectively, and suppose we replace
the micro-particles by corpuscles that are appreciably larger and whose interaction
with the environment is, consequently, not negligible. The fringes then fade and,
when the corpuscles are macroscopic enough, they practically disappear. For the
purpose of predicting outcomes of future observations, the ensemble of the involved
corpuscles may then be treated as a mixture of two “pure cases” described by the
wave functions φ1 and φ2 . Now φ1 (φ2 ) is just the wave function that an observer
would attribute to a set of corpuscles known to have passed through slit 1 (2).
This shows that, in such circumstances, the internal state of consciousness of the
corpuscles passing through one particular slit may indeed be considered without
harm to have the intersubjective predictive role normally attributed, in quantum
mechanics, to pieces of knowledge obtained from measurements. Incidentally, note
that this reasoning is fully consistent with the Broglie-Bohm model since, as far as
mere predictions are concerned, this model yields the same ones as non-relativistic
quantum mechanics.
If we now turn back to the Wigner’s friend problem and still consider it within
the Broglie-Bohm model, we find that the foregoing views can quite naturally be
fitted to it. Indeed, for the same reasons as above, we may assume without inconsistency that S has an internal state of consciousness as long as we assume it has
no predictive power. And we can also relax somewhat the latter assumption when
we take into account the fact that S is macroscopic and interacts therefore with its
environment. In fact, for the purpose of predicting what will practically be observed,
(forgetting about measurements that are conceivable only in principle) an ensemble
E of thus prepared S’s can be treated as a mixture, for decoherence is at work.
And – just as above – the quantum states composing this mixture are the ones that
the various possible internal states of consciousness of the friends would generate if
these consciousness states were viewed as predictive. Hence these internal states of
consciousness, which, related as they are to hidden variables, are basically ontological, still may be considered to also represent elements of empirical reality. More
precisely they can be viewed as coinciding in nature with the predictive states of
consciousness we normally refer to when we state that such and such a measurement
13
outcome has been observed.
To sum up, within this conception (or “model”) it is considered that even
microsystems can be endowed with “internal states of consciousness” (or “protoconsciousness”, whatever this may be) that are elements of a basic, not publicly
accessible, reality, rather than of empirical reality. In other words, they are hidden
(remember we left open the possibility that hidden variables should exist, provided
that they should be “really hidden”). It is only when the involved systems become
macroscopic enough for their interaction with the environment to be appreciable
that these internal states of consciousness obtain some degree of public significance.
This means that they gain predictive power. More precisely (as we easily realize
by thinking of intermediate cases in which “not quite macroscopic” systems are involved) they make it possible to correctly predict the outcomes of a certain class
– call it A – of observations whereas they yield incorrect ones concerning those of
another class – call it B. Now, it is a fact that (due to the nature of these two
classes) human beings perform observations of class A much more easily than observations of class B. And indeed this is true to such an extent that when the
involved systems are thoroughly macroscopic, observations of class B are, as a rule,
practically unfeasible, as we know. Moreover, it is also the case that the impressions
corresponding to the outcomes of measurements of class A may usually be described
in a realist language, that is, as if they referred to objects existing per se. The set
of such intersubjective appearances is what is called here “empirical reality”. It is
thus meaningful to speak of a kind of “co-emergence” of, on the one side, “public”,
states of consciousness that are practically predictive (although, concerning class B
observations, they are not), and, on the other side, empirical reality. In line with
one of the foregoing remarks this co-emergence is to be thought of as (a-temporally)
taking place out of a “mind-independent reality” that, itself, presumably lies beyond
our intersubjective abilities at describing.
It is interesting to note that, surprisingly enough, this model shows a similarity
with Whitehead’s views. For indeed the notion of internal states of consciousness
is quite akin to the ones of “prehensions” and “occasions of experience” that, in
Whitehead’s philosophy, play a basic role even at the elementary particle level.
14
Discussion
Before proceeding further we should, as a precaution, ask ourselves whether
the model is, after all, fully consistent. The reason why this question arises is
as follows. Although the Bohm theory on which the model rests is ontologically
interpretable by construction, still, in it, the difference between the implicit and
explicit orders is basic and unavoidable. Which, to put it bluntly, means that the
explicit order (alias empirical reality) is, in a way, but an illusion of our senses.
This raises a question since the here described model takes macroscopic systems to
be elements of mind-independent reality. Now, by definition so to speak, macroscopic objects are localized in definite regions of space whereas Bell’s theorem shows
mind-independent reality to be non-local. At first sight it would therefore seem that
macroscopic objects couldn’t be elements of the latter (alias of implicit order). A
moment reflection shows however that this objection has no real substance. The
point is that the Broglie-Bohm theory is ontological and that, in it, complex systems are composed of corpuscles each of which has, at any time, quite a definite
localization in space. In virtue of the interaction existing between them, many such
corpuscles may then constitute a stable localized composite system. This does not
violate the Bell theorem since, in the B.B. model, non-locality essentially takes the
form of instantaneous interactions that do not decrease when distance increases.
Admittedly the complex systems in question somehow interact this way with one
another (through the non-local overall wave function or, equivalently, the quantum
potential) but this in no way prevents them from existing as definite entities. And
indeed Bohm himself forcefully claimed (Bohm and Hiley [11], ch. 8) that, in his
model, macroscopic objects do exist, not only as elements of the “explicit order”
but quite independently from us, that is, in an ontological sense.
Remark
Consider, within the B.B. model, a two photon correlation-at-a-distance experiment, of the type used for checking Bell’s theorem, and assume that two distant
observers A and B successively make, in this time order, polarization measurements
along one and the same direction. According to the foregoing their internal states
of consciousness are elements of mind-independent reality. On the other hand, the
results that A and B get are strictly correlated, but we know from the Bell theo-
15
rem that this correlation is not due to “common causes at the source”. John Bell
([Ref.12], ch.15) explicitly showed it follows from the fact that what takes place in
A’s instrument directly influences – via the non-local pilot wave – the behavior of
the photon in B’s instrument. In other words, contrary to what we naively expect,
the outcome of B’s measurement does not depend at all on the hidden variables of
the photon arriving to B. And therefore, since, in our model, B’s internal state of
consciousness is strictly linked to the hidden variables affecting B we must consider
the said internal state to be non-predictive. But of course both A and B have a
natural tendency to take up the view according to which (i) their internal states of
consciousness are predictive and (ii) the correlation they observe is due to common
causes at the source. This view may be considered to be the embryo of a conception of empirical reality. In the case in hand such a conception is obviously deficient
since all the tests of Bell’s inequalities violation prove it is wrong. But when photons
are replaced by somewhat more complex corpuscles, the corresponding tests rapidly
become extremely difficult to make. In fact they quite soon become practically unfeasible. Correspondingly the conception of empirical reality the embryo of which we
just described becomes more and more credible. Finally, when macroscopic objects
are involved in place of photons, it becomes established truth. This is all right, after
all. But it is conceptually and logically all right, only provided we are aware that,
when we express ourselves in this way, we merely refer to an “empirical reality” that
crucially depends on human aptitudes.
Again, in this model it is legitimate to speak of a kind of “co-emergence” of
empirical reality on the one hand and states of consciousness on the other hand.
But it is so with the important reservation that the said states of consciousness
are not those that are deepest in our mind (the internal ones, which alone are
ontological) but just the predictive ones, which refer but to Bohm’s “explicit order”.
4. BACK TO STANDARD QUANTUM MECHANICS
In Section 3 we used the ontologically interpreted Broglie-Bohm theory as a
theoretical laboratory and we constructed a model. It is true that along with distinct
advantages, the said theory has in it quite unpleasant, well known features. But,
to repeat, our idea has been that if, within it, it proves possible to take explicitly
16
into account the fact that Wigner’s friend is conscious – as we have just found is
indeed the case – it is conceivable that the basic idea underlying this solution may
be extended to a much wider theoretical framework. It is the feasibility of this that
is now to be examined.
Let us first observe that there exists a fully consistent and very simple way of
doing this. It consists in observing that the features of the B.B. model we made use
of are but general ones. In fact, they boil down to the idea that the notion of a basic,
mind-independent reality is meaningful and that the quantum mechanical symbols
do not necessarily yield the finest possible description of it, so that the completeness
assumption may be taken up merely in the weak, Stapp, sense. Now there is, of
course, no reason to believe that the B.B. model is the only possible ontological
interpretation of the quantum observational predictive rules. Indeed, other models
are available that also have the general features in question. Hence a fully reasonable
standpoint is to assume what follows. The notion of reality does have an ontological
significance even though we don’t really know what reality consists of. Objects have
an ontological status. Minds, with also an ontological status, are attached to some
of them. And quantum mechanics happens to provide minds, directly or indirectly,
with reliable observational predictions in, as it seems, all the various domains of
physics. Within such a conception space and time – or space-time, or cosmic time –
also enjoy an ontological status. They are arenas in which quite real events take
place. Clearly, such a world-view is general enough to allow for the possibility of
developing within it considerations akin to those unfolded in the foregoing section.
It may therefore be claimed that, from a quantum-mechanical point of view, it
constitutes an acceptable metaphysics.
On the other hand, since the advent of quantum mechanics it was always considered imperative to avoid anything resembling mechanistic, or too realistic, models.
And, to repeat, it was claimed that to this end one should abide to the basic epistemological principle that statements unrelated with anything we could get informed
about through appropriate measurements are meaningless. According to this view,
ontological commitments should be banned. As we saw, in quantum mechanics following such a line of thought results in attributing primeval importance to the Born
rule. Which, since this rule is fundamentally predictive of observations, amounts
to consider quantum mechanics to be essentially and exclusively predictive of ob-
17
servations. It is therefore appropriate that we should inquire whether or not the
way of removing the Wigner’s friend paradox put forward in the foregoing section is
susceptible of being transposed into the framework of such a conception of quantum
mechanics.
A preliminary question arises at this point, namely: is there a risk that this
purely observational predictive nature of quantum mechanics should jeopardize the
validity of the whole decoherence-based quantum measurement theory? In this section it will first be shown that, concerning measurements that involve but inanimate
instruments this, fortunately, is not the case. But it will also be shown that indeed,
same as above, a problem is thereby raised as soon as animated participants are
involved. It will however be proved that, when all is said and done, here also the
problem in question may be solved by adopting, concerning minds, the views stated
in Section 3.
The reason why, prima facie, we might wonder whether the standard quantum
measurement theory is as self-consistent as we usually believe it to be is of the
same general nature as the one that motivated the discussion towards the end of
Section 3 ... although it “pulls in the opposite way” so to speak. While the difficulty
came there from the fact that macroscopic objects seemed not to be “real” enough,
here it comes from them looking too ontologically real. The point is this. In Section
2 we noted that for showing that decoherence does remove the measurement riddle
we had to drop the idea that pointers are intrinsically in such and such states
corresponding to definite places on the dial. We observed that such a descriptive
view has to be replaced by an approach purely predicting observations. But on
the other hand, in order to show that the measurement riddle is really removed,
we eventually had to take into account the fact that instruments are macroscopic.
And this was by no means just an observational prediction. It was a statement of
a descriptive sort. Now, is the occurrence, in the theory, of a statement of such a
nature compatible with the view that the said theory should be purely predictive
and in no way “ontological”?
The question sounds debatable but it should be answered positively. To require
that a theory should merely be predictive of observations does not mean that it
should involve no descriptive assertions. It means that the constitutive statements
of the theory should be of the form “in such and such circumstances we shall ob-
18
serve this or that”, and this very structure implies that the circumstances in question
should be described. Now, the requirement that the theory should not be ontological
implies in turn that these circumstances should be mere phenomena, that is, should
be referred to human experience. But here this raises no problem for in standard
(non-ontological) quantum mechanics this requirement is satisfied. The set of the
quantum rules includes the time-independent Schrödinger equation, which predicts
what types of objects we shall perceive; and this equation shows that among such
objects there may be bound states involving a great number of particles. In other
words, macroscopic objects, far from necessarily belonging to the “ontological” realm
may consistently be considered to be mere phenomena, in a Kantian sense. Moreover, the same Schrödinger equation informs us that the energy levels of such objects
must lie very close to one another, so that the said objects have non-negligible interactions with their environment. It follows that the decoherence-based measurement
theory as it is reported on in Section 2 is indeed fully consistent with what we called
the operationalist conception of quantum mechanics.
On the other hand the same cannot be said concerning the theory of measurements involving animated observers (cats or “friends”). As repeatedly noted above,
this operationalist conception centers on the notion of consciousness, which (apart
from basic unknowable reality, see below) indeed is, in it, (as, by the way, in logical positivism!) the only primitive one (objects and so on essentially being “what
is perceived by consciousness”). According to it the whole of quantum mechanics
deals with the impressions consciousness will get under such and such circumstances.
And, since physics essentially deals with inanimate objects, in this science the multiplicity of conscious beings does not normally constitute a problem. As pointed out
above, the predictions quantum mechanics makes are held to be true for a whole
abstract community of human beings, otherwise said, for a kind of disembodied Experimentalist, assumed to be looking at instruments. But then, when it is assumed
that a “friend” (or, for what we know, just even a cat) looks at the pointer, the
situation radically changes. For, clearly, the consciousness of this individual may
not be lumped together with the one of the disembodied Experimentalist, that is, in
the present instance, with the one of the people who started the experiment. But,
on the other hand it must obviously be considered to stand on the same “ontological
level” as the latter, for Wigner’s friend surely is just as thoughtful a person as you
19
and I. If the consciousness of the experimentalist – call her P again – who initiated the experiment is objectively real, the one of the “friend” must be real as well.
Now, in the operationalist conception this raises a problem for, as we just noted, in
it the instruments of observation are not considered to exist per se. They are mere
“objects for us”, that is, in the case in hand they ultimately are referred to P ’s
consciousness. They are just parts of what P perceives, otherwise said they are, in
a sense, mere appearances. Hence the body of the “friend” is a mere “appearance
to P ” as well. And it seems absurd to assume that his consciousness, which, as we
just pointed out, is just as real as P ’s one, should be univocally bound to something
that is a mere “appearance to P ”. Is it conceivable that a mere “appearance to
consciousness” be the bearer of consciousness?
To investigate this question let it first be reiterated that the operationalist conception differs from pure idealism. In it, it is assumed that some fundamental reality
exists in an ontological sense; that it is basically unknowable; and that it is somehow
endowed with (hidden) structures. And it is further postulated that the existence
of these structures is what accounts for the regularities we observe within the phenomenal realm and synthesize in the form of rules enabling us to predict our future
observations. (Whether or not these rules vaguely reveal us something concerning
the said hidden structures is an open question that lies outside our present subject).
Consequently, we have to do with two notions of an ontological nature, the said, hidden mind-independent reality and consciousnesses, alias minds (although, of course
the latter may be taken to just be components, or emanations, of the former).
Now, normally intersubjective agreement holds between individual minds about
what they see (“what they see” being an abbreviation for “what they have the impression of seeing”, for remember that objects are but appearances). Physicists had
to account for it and the way they managed to do so was to invent universal predictive rules, at present remarkably synthesized in the form of the quantum predictive
rules. Now, the important point concerning the question in hand is the (already
mentioned) one that the said rules (mainly the Born one) intersubjectively predict
the appearance (to the minds) of (phenomenal) macroscopic objects. And we may
consider this observational prediction to be experimentally corroborated since we do
see macroscopic objects. In particular, each individual mind has the impression of
being associated to one particular such macroscopic object, called its own “body”,
20
as well as that of seeing other similar objects. Now, according to the conception
in hand, for a long – indeed a very long! – time the fact that the realist language
is by far the most practical one (without it we could hardly communicate as Bohr
stressed) misled us into considering such bodies to be ontologically real. And we
even took them to be the bearers, or supports, of our minds ... which nowadays
directly leads to the above stated difficulty (how could what is just an appearance,
or image, in our mind be the support, or seat, of a mind?). But within the operationalist conception here under study bodies, which are mere phenomena, are not
in the least the supports of minds. Quite on the contrary, the fact that physics is
basically a set of observational predictive rules indicates that the objects – human
bodies included – essentially are intersubjective appearances to minds. We must
then consider it as a given fact that each individual mind has the impression of
being associated to one particular such macroscopic object, called its own “body”,
and also has the impression of seeing other similar objects, bodies included.
Under these conditions, it is clear that the reasoning made near the end of
Section 2 (the one bearing on a “measurement in the generalized sense”) holds
good. At time t both physicist P and her friend F have the impression of seeing,
along with the instrument, two human bodies; and also have the impression that
one of these bodies is their own. And, moreover, F has the impression of seeing the
pointer at one definite place on the scale. When ensemble E is considered the same
holds true concerning all the “friends” in E and their respective pointers. According
to standard quantum mechanics, from this knowledge they have, each of them infers
definite probabilities concerning what results would be obtained in the future if
this or that measurement were done. And, again all these possible observational
predictions may – theoretically – be combined according to classical and standard
probability rules, so as to yield the probabilities with which P should herself obtain
these results. Now, to repeat, there are (environment involving) physical quantities
concerning which these probabilities do not coincide with those P directly obtains
by means of a quantum-mechanical calculation based on the content of her own state
of consciousness, without assuming the friends to be in definite consciousness states.
Hence, to sum up, we found:
(i) That within the operational conception the received view according to which
21
bodies are (ontologically) the bearers of minds is inconsistent and must be dropped5 .
(ii) That to drop the said view changes nothing to the fact that, as long as
observational outcomes are considered to be predictive, the Wigner’s friend riddle
remains unsolved.
But then the considerations that were put forward in Section 3 obviously yield
the solution. Here, just as there, it suffices to introduce the notion of “internal states
of consciousness”, taken to be elements of a basic reality, and to assume that they
are not publicly accessible in general. The friends F do really have the impression of
seeing this or that, but this does not necessarily count as public knowledge. Hence,
when P calculates her probabilities of getting such and such outcomes were she to
perform such and such measurements (possibly involving the F ’s as objects), she
should, as a matter of principle, ignore the very existence of these private impressions
the F ’s have. As for the F ’s, however, due to the fact that they feel themselves
associated with macroscopic bodies it turns out that, in practice, they may use the
private impressions in question in order to predict what they themselves will see.
Note moreover that, since P thinks of the F ’s as being so associated, when directly calculating the above-mentioned probabilities she must, concerning all practically feasible measurements, take decoherence theory into account. This implies
that if she chose to violate the above-stated prescription and take the existence of
the said private impressions of the F ’s into account, this choice, concerning the said
measurements, would by no means lead her astray. She would make no detectable
error as to the probabilities of their outcomes. This explains that, not only in our
daily life but also in our scientific activity, we may do as if our states of consciousness relative to factual data were totally predictive (though, quite strictly speaking,
we know they are not) and as if those of our colleagues yielded predictions fully
consistent with our owns.
5
It is well known that, in the line of Kant’s views, many philosophers split the “mind” notion
into two. They consider, on the one hand a disembodied, non-personal so called “epistemic subject”
or “first person subject”, to whom objects, bodies etc. appear, and on the other hand “third person
subjects”, who are minds as emanating from bodies. We consider that the existence of the Wigners
friend paradox seriously invalidates this conception and we strive here to avoid it.
22
5. THE CONSTRUCTION OF TIME
When a physicist speculates his guidelines include taking account of all relevant
data and having strict regard for consistency requirements. They do not specify
that commonsense and received views should be obeyed, be it only for the reason
that quantum mechanics gave him abundant proofs of the frailty of such handrails.
This remark, obviously, applies first of all to the “space” and “object” notions.
While, according to commonsense corpuscles clearly are somewhere in space, quantum physicists take them to be at no definite place until we look. And, what is
more, nonseparability suggests that space itself should be but an “a priori mode of
our sensibility”, as Kant thought. But then, what about time? In contrast with
space, up to now time resisted such an “idealization” process. Attempts at making
it a quantum observable were, on the whole, unsuccessful. They were so, however,
merely for technical reasons. Within a speculative theory such as the present one,
in which, conceptually, minds are taken to be prior to objects and their location, it
is therefore quite natural – be it only for curiosity sake! – that we should wonder
whether, by any chance, they might be conceptually prior to time as well.
Well, it turns out that, in fact, it is possible to modify the foregoing model so as to
make it compatible with such a view. For this purpose, let us start with the following
set of ideas. Minds possess ontological existence, have definite impressions, may
communicate with one another and observe that they agree about most impressions
they have. Among these impressions there is the one of space and of perceiving
objects of various sizes lying in space. There also is the impression of perceiving
events taking place in that space, as well as that of perceiving two events as taking
places either simultaneously or successively. Minds, moreover, are able to imagine
events they don’t actually see and separate them in two classes, those they “believe
in” and call “objective” and those that they call “purely imaginary”. Let it be
added that minds primitively have the notions of “before” and “after” as well as
the ones of longer, shorter or equal duration between two pairs of successive events.
They also realize that if the duration between events a and b is strictly longer than
the one between events c and d they are able to think of an event d′ taking place
after a and before b and such that the duration between a and d′ is equal to that
between c and d. Now, it can be shown (Montbrial [13], Kranz et al [14] as quoted by
23
Montbrial) that the fulfillment of this set of conditions (plus a few others, needed
for mathematical strictness but trivial in this context) entails the existence of a
mapping of the set of all the objective events onto the set of real numbers. This
mapping, then, is just (intersubjective) time.
Now, with the “time” notion at our disposal, we may essentially take over the
reasoning developed towards the end of the foregoing section. Indeed, we may argue
that the minds observe some events to regularly follow other ones. They take note
of such regularities and quite naturally (let us admit they have a natural propensity
to induction) they make use of them and build up observational predictive rules, enabling them to calculate probabilities of future events when past ones are known. In
this way they eventually construct the, classical and quantum, observational predictive rules (now, in fact, unified since we know the former ones to be deducible from
the latter). With the help of these rules they predict future instances of intersubjective agreement between them all. And all the rest of our Section 4 construction
may then be taken over without change. Finally we therefore get a grand, somewhat
Plotinus-like, model, according to which Ultimate Reality generates or contains (appropriate words are lacking!) minds that, just as Ultimate Reality itself, are prior
to both space and time. But these minds have a great many impressions of all sorts,
including the one of having bodies, of being in time (as we just saw), of living in a
Universe endowed with events and laws, and so on.
This model is rational and – as it seems to me – truly consistent with what we
know about basic physics. In view of the great amount of questioning that, since its
advent, quantum mechanics raised with regard to its interpretation this is certainly
a nontrivial point, and if the model is to be taken seriously I think it should be on
this ground. Indeed, it cannot be on any other one since it is at variance with basic
things we think we know! Hence it may be taken into consideration only provided
we balance acceptation of it with due recognition of the empirical reality notion, and
acknowledge the central role of the latter in, not only our activity but also our way
of thinking. Empirical reality is the whole set of the phenomena. Otherwise said,
it is an understandable and manageable mapping of everything that minds actually
perceive and act on. So that in practice – in our daily life but also in pure science
(interpretation of quantum mechanics is no real exception for strictly speaking it
lies beyond science) – we must do and think as if the model it constitutes did
24
represent Reality-per-se. Concerning minds (alias consciousness) this, in particular,
implies that no changes at all are necessary concerning the investigation procedures
of neurologists. True, these procedures are grounded on the view that minds are
on the dependence of bodies and more or less produced by them, which is quite at
variance with the views propounded here and in the foregoing section. But such
notions of dependence and causation are themselves of a purely phenomenal nature,
and this is what, in a phenomenal World, makes them useful. They synthesize in
a simple way some features of the observational predictive rules that the minds
discovered, so that, clearly, we have to go on using them.
6. CONCLUSION
The main result reached in this article is that decoherence theory alone does not
remove the Wigner’s friend problem but that the said problem can still be solved,
by introducing the “internal state of consciousness” notion in the above described
manner. More precisely, we found that this can be done in two ways. Admittedly
both of them are quite obviously at variance with the two most common received
views. This however is partly due to the fact that, upon inspection, the said views
turn out to be inconsistent with one another. It is impossible to claim at the same
time that the meaning of statements about the existence of objects of any kind
(neurons included) boils down to their method of verification and that neurons are
conceptually prior to the verifying agent. Looking for an approach to the Wigner’s
friend problem made it necessary to clearly face this conceptual difficulty. And
finally two solutions were put forward.
One of them consists in openly accepting the idea, discarded both by the quantum
mechanics founding fathers and by the logical positivists, that the theory should
be ontologically interpreted. This solution is self-consistent. It has the virtue of
being compatible with the intuitive views of both the “man in the street” and the
scientists at large, inasmuch as most of the latter take minds to emerge from matter.
It may however be criticized on the basis that it is vague without being deliberately
so. As a matter of principle, an ontologically interpretable theory should describe
reality “as it really is” and such descriptions should match what is observed. The
B.B. model does not fulfill this condition and there are good reasons for believing
25
(nonseparability foremost) that other models yet to be invented cannot fare better
in this respect.
Conceptually, the other solution we found is the opposite of this one. The Ultimate Reality it refers to is in principle unknowable and is not what science deals
with. Indeed, the subject matter of the latter is just communicable human experience. In other words it is the set of all the impressions human minds may have
and communicate to others. There is no doubt that the initiators of this conception intended to place scientific knowledge on secure grounds by setting it apart
from ill-defined problems and particularly those of an ontological nature. Quantum
mechanics essentially developed along these lines and the difficulties realist models
steadily meet with indicate that, indeed, they presumably constituted, for it, the
most favorable conceptual framework. On the other hand, it is unquestionable that
the conception in question implicitly sets minds in a privileged position, especially
since not only matter but also space and time are, in it, elements of experience. It
was therefore to be expected that its progressive development should, at some time
or other, involve – not just implicitly but explicitly – the somewhat disturbing idea
that minds are conceptually prior to matter, space and time.
Anyhow, it may be difficult to choose between the two solutions we found but it
is worth stressing that the proto-mentality idea is independent of this choice since
we showed it to be consistent within both conceptions.
Throughout Antiquity and the Middle Ages thinkers focused on purely existential
questions. But during the last centuries, and in relation with the development of
science, they were led to attach more and more importance, even within the realm
of pure knowledge, to what can be achieved and to how it can be achieved. Maybe
it is now time that between these two tendencies – existential and operational –
some balance should be reached, and that the research tools of the latter should be
applied to the former. The present article may be viewed as a step in this direction.
26
References
[1] M. Schlick, Allgemeine Erkennislehre, (Springer, Berlin, 1918).
[2] B. d’Espagnat, Conceptual Foundations of Quantum Mechanics, 2d. ed.
(Addison-Wesley, Reading, Mass, 4th ed. Perseus Books, Reading, Mass., 1999).
[3] A. Bassi and G. C. Ghirardi, Phys. Letters A275, 373 (2000).
[4] Y. Aharonov and J. Anandan, ArXiv, quant-ph/9803018 (1998).
[5] B. d’Espagnat, Veiled Reality (Addison-Wesley, Reading, Mass, 2d. ed. Westview Press, Boulder, Colorado, 2003).
[6] B. d’Espagnat, Phys. Letters A282, 133 (2001).
[7] R. Omnès, The Interpretation of Quantum Mechanics (Princeton University
Press, Princeton NJ, 1994).
[8] B. d’Espagnat, ArXiv, quant.ph.0301160 (2003).
[9] H. P. Stapp, “The Copenhagen interpretation”, Am. J. Phys. 40, 1098 (1972).
[10] B. d’Espagnat, Traité de physique et de philosophie (Fayard, Paris, 2002).
[11] D. Bohm and B. J. Hiley, The Undivided Universe (Routledge, London, 1993).
[12] J. S. Bell, Speakable and Unspeakable in Quantum Mechanics (Cambridge University Press, Cambridge, 1987).
[13] T. de Montbrial, “Evénements et temps quasi leibnizien” in Implications
philosophiques de la physique contemporaine T.3 B. d’Espagnat ed., (P. U. F.,
Paris, 2003).
[14] D. Kranz, D. Luce, P. Suppes and A. Tversky, Foundations of Measurement
(Academic Press, Vol. 7, 1971).
27 |
647
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
Review Article
Near Death Experiences & Afterlife in Religions (Part I)
Kamel B. Salem*
Department of Computer Science, University of Tunis El Manar, Tunis, Tunisia
Abstract
As the intensive care techniques improve, more and more patients are brought back to life from
the frontier of clinical death. Some of them tell about their significantly intense experience when
they seem to live and function outside their body. First, we shall present the various stages of a
near death experience (NDE). We shall particularly explain why the observed phenomena during
an NDE are troubling and destabilizing for the adepts of certain religions. Second, we shall
analyze and interpret these phenomena according to different points of view. We then discuss
life in the hereafter and exhibit some of its properties. In this paper we shall also raise the issue
of premonitory dreams which constitute a mystery for scientists.
Part I of this two-part article includes: 1. Introduction; 2. The Main Stages of the Experience on
the Brink of Death; 3. Assessment & Interpretation of the Facts Observed during an NDE.
Key Words: birth, death, NDE, Near Death Experience, brink of death, life after death, Bible,
Quran, Buddhism, Hinduism.
1. INTRODUCTION
Our birth initiates a process leading to our death. The concept of a life after death constitutes
one of the founding principles of all the major religions. However, there remains to elucidate the
most intriguing mystery: Is there proof of the existence of a life after death? For many years,
this mystery has generated a raging debate between the faithful and the skeptics, but the NDE
has proved to be a powerful argument in favor of the existence of an afterlife.
First of all, we must explain the nature of a near death experience. According to the
International Association for Near Death Studies (IANDS), this experience is defined as a lucid
experience of an out of body conscious perception occurring at the moment of real death, the risk
of death or in the wake of a critical medical case [30].
The experience of near death consists in that the spirit of the person in question leaves the body
momentarily. In this out of body situation, the spirit can evolve within the spiritual world.
We may classify the NDEs into two major categories: the positive experiences and the negative
experiences [29].
*
Correspondence: Professor Kamel B. Salem, Department of Computer Science, Faculty of Sciences of Tunis, University of Tunis El Manar,
Tunis, Tunisia.. Email: kamel.bensalem@fst.rnu.tn
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
648
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
1.1 Positive NDEs
The individuals who lived this experience reported that they soon regained consciousness, had
the feeling of finding themselves outside their body and were able to perceive everything around
them in detail (the efforts to reanimate them for example). Then, there follows the perception of
a kind of tunnel with a very attractive light at its end, which is described as strong but not
blinding. In the course of their journey through this tunnel, deceased relatives and/or a being of
light are met. This meeting is characterized by intense feelings of love, joy and peace. Some
witnesses reported that they were able to view a panoramic display of their entire life.
Frequently, the more one approached the end of the tunnel the more the observed light took the
shape of a forbidden barrier. At that instant, the subjects understood or were made to understand
that they had to come back to earth and that their life must go on.
1.2 Negative NDEs
For the moment, the statistics show that the negative experiences are estimated at 4 to 5% of
cases. Actually, it is not easy to determine the significance of such estimates for the simple
reason that even those who underwent positive experiences found a great difficulty in expressing
it, let alone those who underwent negative ones! Obviously, the person who saw ‘Hell’ during
an NDE will never muster enough courage to express it and will rather seek to put together this
perception of this experience of a deserved hell and his/her past causing to the subject a posttraumatic stress. It is to be noted that the statistics show that the negative NDEs often end in
suicide attempts.
Generally speaking, the negative NDEs may be distinguished in three categories: infernal NDEs,
meaningless NDEs and inverted NDEs.
1.2.1 Infernal NDEs
These are entirely the opposite of the positive experiences in that the subjects, instead of moving
up to meet the light, they rather go down towards darkness where linger thousands of people
screaming from heat and thirst in the presence of devilish beings. This situation is quite similar
to our traditional vision of Hell and this is why we termed these NDEs infernal.
1.2.2 Meaningless NDEs
In the meaningless NDEs, the subjects will find themselves alone in an absolute eternal void
which would trigger a feeling of terror, rather understandable. Sometimes, geometrical shapes
are perceived in this nothingness from which ironic manifestations transpire. All the events
happen as if the subjects are mocked, giving them the impression that eventually, nothing has
meaning, nothing ever existed, neither the world nor life nor family nor profession and that all is
but illusion, hence the feeling of a meaningless experience.
1.2.3 Inverted Experiences
In this category, the NDE takes place like a positive experience, but it is perceived negatively by
the subjects. The same light mentioned above will be perceived as aggressive so much so that it
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
649
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
is not the subjects who move towards the light but rather, it is the light that moves towards them
to take possession of them. This light is described as white, milky and more or less disgusting.
The feeling of dissolving in this light by the subjects is perceived in a dramatic way which
entails a great fear of disappearing in an infinite space.
We must note that the events mentioned in the testimony of the subjects experiencing the NDEs
are quite current and repetitive. Such NDEs are so universal in nature that similar accounts have
been registered in all countries.
Many editors [16] have published the accounts by those who experienced clinical or temporary
death. The fact of raising the issue embodies a kind of open-mindedness which salvages our
contemporary way of life as rooted in materialist thought.
Nowadays, there is agreement that the human being is a spirit incarnate in a body and that at
death, the spirit continues to live. It is equally agreed that the soul or spirit may live on without
its body but that a body cannot live without its soul. Many witnesses assert that during an NDE,
they saw a kind of vapor escaping from the skull of the patient. The people who lived an NDE
are quite numerous and the time has come when we should analyze this phenomenon rationally.
Indeed, materialist thinking becomes obsolete when faced with those testimonies since now, we
have scientific proof that our life proceeds without our body [9].
Those best informed skeptics with a closed mind now admit that they can no longer deny the
existence of NDEs but rather, the discussion revolves around their significance.
Dr Moody was a pioneer in this domain though he started his investigation as a skeptic. His first
book entitled “Life after Life” which was published in 1975 is considered to be the classic work
that paved the way for modern research in this domain [16]. Since 1975 numerous studies were
conducted in many countries. Let us particularly quote the works by K. Ring [19], M. Sabom
[20], M. Morse [15] and the Australian Ch. Sutherlands [22] published in 1992 including a
selected bibliography of more than 150 case-studies.
The studies have concerned persons who were brought back to life after a state of clinical death
(stopped heart or flat encephalogram).
2. THE MAIN STAGES OF THE EXPERIENCE ON THE BRINK OF
DEATH
The publication of Raymond Moody’s “Life after Life” in 1975 raised great concern the world
over. Having collected several testimonies by patients who died clinically and came back to life,
Raymond Moody proceeded to relate in detail the way the NDEs took place for the first time. Dr
Moody discovered a striking similarity between the testimonies of 150 patients who lived such
experiences. He was able to identify several different items recurring in the reports and he
designed a typical model covering all the factors.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
650
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
2.1 A Typical NDE Scenario
A given person is declared dead when s/he reaches the point of a great physical distress and
hears her/his doctor confirming the patient’s death. S/he starts to hear a disturbing noise, a loud
ringing or a siren after which s/he realizes that s/he is outside the physical body but still in the
immediate surroundings and perceives her/his own body from a certain distance as a spectator.
S/he is given to observe the efforts to resuscitate the body in a disturbing emotional state.
Soon, s/he regains control and starts to adapt to this strange situation. S/he notices that s/he still
has a “body”, but of quite a different nature with powers that differ greatly from those of the
body left behind.
Following this, the patient starts a journey along a dark tunnel and dead relatives come to meet
him or her, to guide and help. The spirits of dead relatives and friends are also perceived and
more particularly, a loving and warm spirit who was never met previously is then perceived. It is
-a being of light- who asks a non verbal question about the evaluation of the patient’s entire life,
helping in this evaluation by displaying an instantaneous panoramic view of the major events of
her/his existence. In a way, s/he feels that s/he is approaching a kind of barrier apparently
representing the border between life and death. However, s/he feels the need to return to earth
because the instant of death has not yet come and hence, s/he will resist the return to earth since
s/he is in the throes of afterlife. Submerged by intense feelings of joy, love and peace s/he will
join the physical body and live again in spite of it all.
Upon her/his return to earth, s/he will find it very difficult to tell about this experience for two
reasons. On the one hand, no adequate human terms can be found to describe the experience in
the netherworld and on the other, s/he would feel annoyed to tell about it for fear of ridicule.
However, this experience will affect the behavior deeply, especially regarding the conception of
death and its relation with life [16].
It must be noted that statistically, Moody’s model of a typical experience represented the persons
who lived positive experiences only. Indeed, witnesses of negative experiences are quite rare for
the reasons we mentioned in §1.2.
The researchers who focused on this phenomenon unveiled a certain number of essential traits or
common denominators shared by numerous experiences at the brink of death. It must be
emphasized that the resulting statistics based on the variables of age, sex, race, profession,
educational level and religion have no incidence on the number of NDEs and none on their
content. At times, the visions reported by certain patients show that those factors contradict their
religious convictions.
2.2 Testimonies and Account of the Main Feature of an NDE
In what follows, we present the testimonies of a few people who lived an NDE out of which
eleven main traits were made out. Since the testimonies are coherent and repetitive, we shall
limit ourselves to no more than two testimonies for each case. The essential traits of these NDEs
include several stages.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
651
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
• Hearing the Announcement of Death
The first stage mentioned by R. Moody is what he termed “hearing the verdict”, meaning that the
patient in a state of clinical death is given to hear and see perfectly the doctors announce the
verdict of death though it is in principle impossible for him to feel anything.
Dr Sabom cites the case of a lady who was in the throes of death following an internal
hemorrhage two weeks after the birth of her first child:
In the emergency room, I felt I was leaving and said good bye. I had the impression that
I was sliding away and I could hear them say that I was in a state of shock. I heard a
nurse say that she could no longer feel my pulse, that I did not breathe and that I had
passed away. Then, another nurse ordered to put me under intensive care. [20]
• Peace and Well-being
The second stage consists of a feeling of perfect calm accompanied by an end to suffering
marked by lightness, total relaxation and well-being. According to K. Ring, 60% of the
interviewed lived this stage of the experience and 71% of them literally used the terms ‘peaceful’
and ‘calm’ to describe the emotional aspect of their experience [19]. Moody for his part cited
several excerpts from this kind of testimonials [16].
One lady said that following a heart attack:
I began to feel wonderful, experiencing nothing other than peace, comfort, well-being
and calm. I had the impression that all my troubles had ceased, thinking that
everything was sweet, peaceful with no pain anywhere.
• Hearing Sound Phenomena
During the third stage, Moody asserts that some patients claimed to have heard an annoying
sound going from “a rather painful roar” to “a strong ringing” and to “an acute humming
sound” and “a thundering noise” before entering the dark zone (fifth stage). However, we must
note that a large majority of patients only remember a feeling of complete silence.
• Disembodiment (separation of the soul from the body)
The fourth stage is the disembodiment experience with a modified sensory perception and a
different awareness of time and space. In this respect, Moody cites two particularly interesting
cases [16]. First, there is the account by a young man who reported that:
passers-by were coming to the site of the accident from different directions, and I
observed them from the middle of the pavement which was rather narrow.
Nevertheless, as they approached, they did not seem to notice me and continued to walk
straight ahead. When they came close nearby, I wanted to move away to let them pass,
but they walked through me.
A second account showed that the intellectual and sensory perceptions were modified and
became hyper-developed:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
652
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
Our mind becomes marvelously clear. My thinking took note of everything and solved
all the problems as it never happened before, without having to go over the same ideas
more than once.» Further, one lady reported that : « when she wished to see a far away
person, it was as if a searching head inside of me hurled me towards that person. I had
the feeling then that if anything happened anywhere in the world, I could easily attend
it.
• Entering a Dark Tunnel
In the course of the fifth stage, one enters a dark zone with a feeling of peace. This zone is often
compared with a tunnel, a narrow valley, a barrel or a cave… Here are two testimonies selected
from those presented by Moody [16].
- the case of a man who fell unconscious following a serious illness who reported:
I found myself in empty space and in complete darkness. It is difficult to explain, but I
had the feeling of sinking in that dark emptiness. However, I was fully conscious and it
was as if I had been immersed in an airless cylinder, in a limbo: I was here and
elsewhere at the same time.
- the case of a lady who neared death, following a traffic accident:
I felt absolute peacefulness and I found myself in a tunnel made of concentric circles….
• Meeting Guides or Departed Persons (relatives or deceased friends)
These characters attributed the role of guides or counsels will show up. They are close deceased
people: relatives or friends, old neighbors, acquaintances or even unknowns who communicate
by telepathy, thought exchanges or instant emotions. Moody reports the testimony by a man who
was welcomed in the hereafter by a friend who had died recently before him:
As soon as I had left my body, I had the vivid feeling that Bob stood nearby… He was
there, but without his earthly body. The latter was more of a translucent entity, giving
the impression that he had all his limbs, arms and legs, but I cannot say I was seeing
him in a physical way.
• Meeting a Being of Light
A common event is the meeting with a shining light. This light is shapeless and cannot be
perceived as a being often represented according to the patient’s faith as Jesus, Buddha, Krishna,
etc… This being will cause the panoramic view of the newcomer’s elapsed life to appear.
• Panoramic View
The eighth stage is extremely curious in that the deceased person is given a panoramic view of
her/his entire life and s/he judges all her/his deeds. Moody gives the example of a young woman
who gave a very detailed account of her experience. According to her, it was the presence
emanating from the magnificent light (stage 8) which coached her into judging her own life and
to review all the events that characterized it. She saw herself as a child, breaking a toy that she
liked, then as an adolescent in high school. The review is chronological in nature, with certain
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
653
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
aspects emphasized by the luminous presence ever at the side of the young woman. The
importance of love and knowledge are clearly made out by the being of light:
I was there and I could really see all those events and everything took place rapidly,
giving me nonetheless enough time not to miss any of them. However, this did not take
much time overall, at least that was the feeling I had. First there was the light, the
review of the past and then the return to the light. I gather that it all took no longer
than five minutes, probably more than thirty seconds, but I really cannot say any more.
Generally speaking, after the review of the past, there is the return to the being of light for selfevaluation.
• The Barrier of Light
At a given time, the patient encounters a luminous barrier resembling a door or even a wall, a
kind of border or boundary and s/he has a strong urge to return to the earthly body. We find in
[25] the following testimony:
Jean identified his last journey as surrounded by different elements: the looming of a
barrier that he was forbidden to transgress… he tried to reach it with his hand in vain;
the presence of ancestors or parents: his grandmother, died when he was twelve and his
father died when he was seventeen. He had the feeling that they looked at him
judgingly, but could not say anymore as there was no dialogue.
A lady interviewed by Moody declared that she found herself amid a marvelous scenery, a
meadow of an intense luminous green and then, she reached a fence which she could not cross
despite all her attempts. [16]
• Reintegration of the Body
The tenth stage gives an account of the return to life of the patients by reintegrating their body.
The process is often instantaneous and violent. One man asserted:
I was up there near the ceiling and I could see them trying to resuscitate me. When the
electrodes were placed on my chest and my body jerked up, I fell like a dead weight and
soon, I had reentered my body.
A lady asserted:
I had the feeling of being recalled, as if drawn by a magnet.
This return is often realized against the will of the patients who had felt so good in their new
state that they no longer wished to come back to life… [16].
• Incommunicability
Each person who experienced an NDE finds it difficult to express it via the habitual language
and the same goes for its emotional components. More particularly, Dr Moody cited the
testimony of a young woman who tried to analyze the reasons for this incommunicability:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
654
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
You see, it is hard for me to explain that because all the words I use apply to three
dimensions. During my experience, I could not stop thinking that : ‘My geometry
classes had taught me that there were only three dimensions which I took for granted,
but that was a mistake as there are more dimensions’. Indeed, the world we live in is
three-dimensional, but the other world is not like that at all. This is why I am at pains to
explain it. I am forced to use three dimensional words and to stick to reality, but that is
not the way. [16]
In the following section, we shall attempt to analyze the different states of an NDE to deduce the
pertinent information.
3. ASSESSMENT AND INTERPRETATION OF THE FACTS OBSERVED
DURING AN NDE
3.1 Failure of the Materialist Explanation
To this day, NDEs represent something new to science. Psychiatrists, neurologists and
cardiologists searched for physiological causes and even tried to reproduce an NDE in laboratory
via electric excitation of the brain, in vain. Other rationalists tried to explain the content of an
NDE (hence the disembodiment experience) through the elaboration of “phantasmagoric
scenarios”. However, this type of simplistic and reductionist explanation was strictly negated
from the very start by the early studies conducted by the pioneers on NDEs such as R. Moody,
K. Ring, M. Sabom etc… All of these authors demonstrated that the mere psychological
explanations (disembodiment experience, phantasms, dreams, simple hallucinations etc…) were
incapable of explaining the sequence of visions proper to the NDEs. One argument among
others is that the phantasms are known to vary from one individual to the next whereas the
content of NDEs’ testimonials shows remarkable similitude, whatever the culture, the age, the
religion or the way of life of those telling about this experience.
The disembodiment phenomenon cannot be a hallucination since there were blind subjects who
were able to depict the doctors’ actions in a very precise manner. One could then safely deduce
that these patients did in fact observe their own carnal self from outside as they claimed. There
were also those who left their body, moved about the intensive care room and were even able to
read the stickers on the ceiling fans. They were even able to reproduce conversations which took
place in adjoining rooms and beyond, in their integrality [9].
It is finally obvious that the materialistic image of the body and of the brain as the producer of
thought has become obsolete. Indeed, a new conception of the body and soul is emerging. This
conception which is spiritual and scientific at the same time maintains that a human being also
incorporates an abstract entity which remains the seat of consciousness after death. Eradicating
the spiritual component underlying the NDEs is thus bound for failure.
Flowing from the above considerations, there are certain aspects which deserve our attention.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
655
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
● If one day we were able to transplant a brain on another patient, the transplant will
absolutely have no effect either on the personality or the behavior of the subject. Indeed, in
the disembodiment state of the NDE, handicapped persons asserted that they had
regained their physical integrity and their normal functional capabilities (no
incapacitation was present).
● The human shape remains as it was after the disembodiment experience (to wit the
perception and recognition of deceased relatives by the NDE witnesses).
● Our conscience may access levels of reality other than that of the ordinary physical one.
● The soul does have a material constitution made of a subtle substance. Some intensive
care specialists reported having « felt and observed smoke, vapor or other ‘entities’ leaving
the body of those leaving us.» [9]
● This subtle material substance constituting the soul is made of matter very different from
what we know since everything demonstrates that its specificities belong to another spacetime.
Regarding this issue, some researchers postulated that the soul (our double so to speak) which is
immortal and indivisible is constituted by particles resembling the neutrinos a great deal. Their
argument was that certain patients who came to, had been able to go through solid objects (walls,
glass, etc…). Other more daring researchers have even tried to establish a model for the soul in
order to explain the phenomena characterizing the NDEs. We shall particularly cite the model
attempted by R. Dutheil [11].
3.2 Towards a Model for Conscience
In Quantum Mechanics, it has been shown that if an elementary particle is split into two halfparticles, the latter move away from each other at the speed of light. Further, when the spin
direction of one part is modified, the spin of the other part would also be modified in the same
manner. In other words, the two particles will communicate the position to each other
instantaneously thanks to information traveling at a speed superior to the speed of light. Thus,
matter is not totally deprived of consciousness which led R. Dutheil to elaborate a model
attesting to the complexity of our world and to hypothesize the existence of a second
complementary and symmetrical universe (parallel to ours) where speeds are always superior to
the speed of light.
In that universe, our notion of time no longer applies since one can travel instantaneously in the
past, the present and the future. This universe which he called “super luminous time-space” is
composed only of information. It is, among other things the universe of the soul and the spirit
and it can be defined as composed of ‘tachyonic’ (or super luminous) particles.
From this vantage point, the brain would not be the producer of thought but rather a kind of
interface allowing the latter to act in the inferior luminous world. The world we perceive would
then only be a holographic projection of the super luminous world.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
656
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
Flowing from this model, the author provides an explanation for numerous phenomena which
have irritated thinkers a great deal, such as the NDEs, prediction, survival after death and the
like. According to the author :
- Death consists in the transfer of the soul to the super luminous space time. It would then
be logical that sensations emanating from another time-space dimension be incommunicable
since our language is not adapted for it.
- The actual seat for sensations is located in the super luminous space. Such organs as the
eyes and ears are but the receptors of sensations without being their seat or origin.
Then, there is no reason why an “unconscious” patient -according to our under luminous
criteria- whose organs have stopped functioning, can still perceive sensations.
- Life rarely provides us with fully pleasing sensations because its daily emotional content is
rather negative, characterized by stress, anguish, anger…At the moment of death, our soul is
ridden of all the influences associated with the under luminous world. New sensations
emanating from the super luminous world -that of total consciousness, order and information
in its pure state- reach the subject. They can only be positive and pleasant, hence the feeling
of well-being.
- The sound effects reported by some rare patients may be explained by the fact that when a
subject is placed in a sound-proof room sometimes believes he is hearing loud noises while
they really do not exist.
- The journey through the dark zone (tunnel) represents the transfer of the soul from the
under luminous time-space to the super luminous time-space and this move indicates the
crossing of the light barrier. The soul is then impregnated with luminous particles,
becoming luminous itself, and thus, it will perceive the outside only as dark.
- The disembodiment experience is nothing more than the return of the soul to the luminous
time-space dimension i.e. to the universe of total information.
- Following the disembodiment experience, the deceased person has the feeling of being
“pure spirit”. However, s/he is still attached to sub-luminous world by several links.
Therefore, s/he has the need to create an environment in keeping with what he was familiar
with in earthly life : marvelous scenery, meadows, rivers etc…
Although the attempt by Professor Dutheil seems laudable, it is still characterized by several
shortcomings.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
657
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
3.3 Criticisms of the Model
The criticisms touch upon several essential points :
R. Dutheil considers that during an NDE, “the partial sub-luminous soul attempts to penetrate
the super-luminous universe in order to melt within the total soul” [11].
We deal here then with two souls, one embedded in the carnal envelope and the second in the
super-luminous space. He claims that all our deeds are dictated by the super-luminous soul and
hence that all illnesses (particularly mental illnesses) are “all illnesses of information processing.
The patient no longer manages the information correctly or perceives disturbed information in
the same way as a TV set displays unclear or distorted pictures”.
■ We do not agree with R. Dutheil’s opinion that postulates two souls, one in the superluminous dimension (total soul) and the other in our body (sub-luminous soul), one dictating
it over the other. In our opinion, there is only one soul but it is doubled (cf. section 4.4.4.1)
and it is the one which is embedded in our body. Information and instructions emanating
from our soul are received by the brain which executes them. If the brain suffers from a
neurological, biological or other defect, then the illness will appear since, as we established
it earlier the brain is but a mere interface between the soul and the rest of the body.
Further, Dutheil’s model does not explain the phenomena observed in the course of a negative
NDE for the following reasons:
■ In a “meaningless” NDE, the subject is within the vacuum, in absolute nothingness,
perceiving no light, although the space he reaches is supposed to be that of light.
■ The model presented by Dutheil hypothesizes that the will of the deceased creates its own
environment after death: everything that is observed can be created instantly in no time, but
it can also be annulled likewise. In a positive experience, it is only natural that the deceased
person enjoys the beautiful scenery encountered and that he would in no way delete that
environment. In the case of an infernal NDE, the witnesses were not capable of ridding
themselves of their horrible environment. [18]
■ In the case of a reverse NDE, the soul of the deceased has the feeling of regressing in the
bottom of the tunnel whereas s/he is normally supposed to progress in the super-luminous
universe in order to melt into total soul. The light which is supposed to be pleasant is rather
milky white and disgusting.
■The tunnel which is described as a dark zone is seen as the consequence of the crossing of
the light barrier by the soul while this barrier is hypothetical very much like the sound
barrier.
■ The model has no explanation for the meaning of the panoramic vision of the patient’s life
who judges his own deeds.
We must note that if the resuscitation is not accomplished within a short time, at least within the
three first minutes, the patient will go from clinical death to biological death and the return to life
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
658
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
will no longer possible. Since the resuscitation time varies from one patient to the next, not all
people can access all the stages of an NDE. We shall therefore consider -in our study- only those
persons who underwent the most advanced stages of the experience on the brink of death.
3.4 Analyses & Interpretations
In order to make out pertinent information derived from the frontiers of death, we feel that it
would be convenient to distinguish the stages characterizing the experience into two categories:
the stages before entering the tunnel and those occurring after crossing it.
3.4.1 Stages Preceding the Entering of the Tunnel
The statistics show that in these first stages:
■ 100% of the witnesses were able to report and describe exactly all the details of their
resuscitation, sometimes repeating the words uttered at that time by the doctors and nurses,
while they were not supposed to hear anything since they were entirely unconscious.
■ All the witnesses without exception declared that they underwent a modification of their
intellectual and sensory faculties which became hyper-developed.
■ Their human nature (reason, memory, emotions etc…) is preserved to a point that they
never realize that they died.
3.4.2 Stages Following the Crossing of the Tunnel
According to the gathered accounts, all of the questioned witnesses without exception reported
about :
■ Their failure to describe their experience after crossing the tunnel, correctly: that is the
“incommunicability”,
■ A sensation of peace and well-being or of horror depending on whether the experience
was positive or negative.
Among those who survived the most advanced stages of an NDE, there is agreement on :
■ An encounter with guides or close deceased persons,
■ An encounter with a Being of Light who displays a panoramic view of the past life and
who coaches the newcomer into evaluating his terrestrial life,
■ The existence of a barrier which stops the patient, a kind of ultimate barrier between life
and death.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
659
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
Regarding the latter point, it is possible to postulate the existence of three universes and not only
one:
- our material and perceptible universe,
- transient universe (apprehended by those who have experienced an NDE),
- the universe of the soul (that of the hereafter).
Indeed, the subjects who were declared dead by their doctors have all reported that after
journeying through the tunnel, they had found that they were in a world different from ours
(transient universe) then they were stopped by the barrier. In this intermediary world, there are
two possibilities, either to return to life (reintegrating one’s body) or dying (crossing the barrier).
This world then plays the role of an interface between our own material world and the hereafter
ensuring the passage of the soul before its integration to this world…the world of death. Each of
these three universes has its own specific space time.
3.4.2.1 Interpreting Incommunicability
In our opinion, the journey through the tunnel achieved by the deceased consists in a transition
from our three-dimension space towards the transient universe which certainly possesses space
time attributes different from that of our.
It is known that in the practice of multidimensional data analysis in Applied Mathematics, if we
want to express a data belonging to a large dimension space into a lower dimension one, there
will be in general a loss of information due to the transition between the two spaces.
Let us consider for instance a cloud of n points in a three-dimension space where each point is
defined by the usual three coordinates. The structure of this cloud can be easily described in our
space. Let us assume that we want to give to a bi-dimensional being a detailed description of
what we observe. In order to reach this goal, we have to project the cloud on his proper space
(i.e. the plane). This projection will consequently lead in general to a distortion or an
information loss. This latter corresponds, for a given couple of points to either a relative increase
or decrease of the distance between them.
Therefore, transferring information from a multi-dimensional space to a three-dimensional one
via a projection will always lead to some distortion. This will be the same when we move from a
three-dimensional space to a bi-dimensional one as shown above.
Note: However, we may encounter a minimal or even no distortion in very particular cases and under
some conditions (especially depending on the shape of the projection and its direction) hence the
preservation of the information.
It would then be only normal in the case of an NDE that the witnesses’ sensations emanating
from another time-space be incommunicable because our language itself is made of sensations
based on a three-dimensional image of our reality. This incommunicability is then not the fruit
of any fraud or lies, but it rather constitutes the proof of the patients’ sincerity who are the first to
be stupefied by their experience. Indeed, they are unable to explain their sensations with our
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
660
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
three-dimensional logic nor can they describe their sensations since our language is not
applicable.
A first deduction transpires from our analysis, namely the transient universe equates a multidimensional space.
Some survivors reported their encounter with close deceased persons even before ascending the
tunnel. In other words, the encounter took place in our three-dimensional space. Thus we can
deduce that our space or universe is reachable by the deceased and that it is entangled within
the transient universe.
Furthermore, the survivors who lived the panoramic stage reported that they viewed all the
details of their life. Obviously, this process cannot last a few seconds or even minutes. We may
thus deduce that we deal here with a time quite different from the usual physical one. On one
hand, this conclusion may be supported by the fact that witnesses asserted that they felt their
experience lasted an eternity. On the other hand, the space in question has certainly a geometry
different from our. In addition, it is admitted that it is the geometry of each space that defines its
proper time. So time does not flow the same way when we move from one universe to another.
We are thus led to this conclusion : the transient universe as a multidimensional space is
entangled in our proper universe. In the former, the time flow is quite different from the flow
of our usual time. Therefore, in this context, the tunnel appears as a hidden dimension
common to the two spaces, that achieves a kind of interconnection.
The third universe, (that of the soul) for its part, is impossible to apprehend because biological
death is irreversible. However, we are certain it is multidimensional but the present data do
not allow us to draw any conclusion regarding its time-space specificities which are radically
different from those we know. We shall examine one of its specificities in section 4, by
focusing on matters other than the observations reported by witnesses.
3.4.2.2 Interpreting the Sensation of Peace or of horror
Several researchers who wanted to explain the sensation of peace or horror during an NDE
focused on purely psychological considerations : « at the moment of death, the soul rids itself of
stress progressively » hence the feeling of peace and well-being in the case of a positive NDE or
« an increase of the degree of fear of what will happen » in a negative NDE. To our mind, if we
set aside any spiritual dimension from our deeds, we will not be able to explain why there are
positive experiences in certain cases and negative ones in others. Indeed, all experiences should
logically take place identically.
3.4.2.3 Explaining the Being of Light and of the Panoramic Vision of Life
In all the testimonies, the controversy is centered around the identity of the Being of Light which
is interpreted according to the religious beliefs of the subject as an angel, a prophet: Jesus,
Buddha or Krishna etc… We shall in this respect review the case Alexa’s experience with an
NDE (1973) excerpted from the witness data base of the Near Death Experience Research
Foundation : NDERF [32].
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
661
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
The review of my life has started. Absolutely everything I thought, did, said, hated,
whether I helped or not was displayed much like on a home cinema. The extent to
which I had been cruel to people, how I could have helped them, how I had been wicked
with animals …[…] I fell face down with shame. I was given to see how the
consequences of my actions to help or their lack had affected the others and their life.
It was only then that I realized that every small decision or choice touches the whole
world. The feeling that I failed the Savior was only but real. Astonishingly, despite the
horror I was in, I felt the compassion and the acceptance of my limitations by the Savior
and the others.
In the course of this review, the evil being was present. […] Each time I made a
mistake or missed something, this pleased him a great deal and he shouted : ‘There!
Do you see how she failed? Why didn’t she do better or help better? Should she not be
punished?’ I was devastated. My few small good actions could not satisfy God’s
perfect norms. I did deserve all that I reaped. When it was all over, a voice roared : ‘Is
she covered by the lamb’s blood?’ Answer : ‘yes!!!’
Once the Court had disappeared, the evil being, Satan screamed, whistled, shrank and
‘Pouf’ disappeared. Everything vanished except for Jesus Christ who gazed at me with
incredible love!
According to this account, we may unambiguously understand that Alexa is not a practicing
Christian (« the feeling that I had let my Savior down was only but real »). Nonetheless, she was
convinced to be in the presence of Jesus « who gazed at her with an incredible love». But one
must ask how the evil being can appear side by side with whom she considered to be ‘the Son of
God’. He is even introduced as his equal in condemning Alexa’s sins. Would this lady have
badly reported her experience or falsified it? This holds little truth because there are other
accounts which corroborate this by asserting the encounter with Jesus.
This testimony which seems to be inconsistent is quite normal since the events took place in a
multidimensional universe (after crossing the tunnel). As soon as the soul reintegrates the body,
a transition is operated towards our three-dimensional universe. Therefore, the information
which will be explored in the first universe will be entirely distorted for the reasons mentioned
above.
We must note that in an NDE, the panoramic stage must take place in a standardized manner for
all subjects and there is no reason why the Being of Light should vary in accordance with the
beliefs of the individual who is dead clinically. The Being of light will then certainly be neither
Jesus, nor Buddha nor Krishna… We shall reveal the identity of this Being in section 4.
3.5 Rethinking Death
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
662
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 647-662
Salem, K. B., Near Death Experiences & Afterlife in Religions (Part I)
According to our analysis, we may safely assert that death is only a simple transition towards a
different plane which exists elsewhere, i.e. an existence displacement. Indeed, why should the
presence of the physical body or its absence matter if we continue to live on without losing our
senses or our identity?
In an interview, Dr Moody declared:
Whenever any survivor was asked about her/his opinion on her/his NDE, the answer
would be unequivocal that true life was in the hereafter and that life on Earth was but a
dream when compared with it.
The accounts by the persons who lived an NDE are rather disturbing and even destabilizing for
the adepts of some religions, hence the need to confront the Holy Scriptures, leaving it to the
discretion of the reader to judge what is pertinent and what is not.
(Continued on Part II)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
354
Article
Compassion, Performance & Programs for Excellence
Pradeep B. Deshpande*1 and Bhaskar D. Kulkarni2
1
Professor Emeritus of Chemical Engineering, University of Louisville, & President, Six Sigma &
Advanced Controls, Inc. P.O. Box 22664, Louisville, KY 40252-0664
2
Distinguished Scientist, Chemical Engineering Division, CSIR-National Chemical Laboratory, Homi J
Bhabha Road, Pune-411008.
Abstract
The paper presents strong evidence showing that higher S, R, T levels of consciousness, which
necessarily equate to higher levels of compassion, reduce defect levels in products and services
even if six sigma programs are not in place. It follows therefore that compassion will boost the
performance of six sigma programs. The link of compassion to performance is unexpected
presenting a huge opportunity for all organizations in any country to improve the performance at
all levels whether or not six sigma programs are in place.
Keywords: compassion, performance, meditation, consciousness, programs for excellence.
Introduction
Over the past couple of years the authors have published several papers in this journal on a
scientific framework for individual and national transformation (1 – 4). The authors pointed out
that nations are characterized as developed or emerging/developing on the basis of defect levels
in their products and services (5). As depicted in Figure 1, developed nations are characterized
by low defect levels while emerging/developing nations are characterized by high defects levels.
The plot is believed to be correct in the qualitative sense.
Defects in products and services of nations arise for two fundamental reasons: (1) The processes
which produce them are not designed and put together sufficiently well and therefore unable to
deliver acceptably low possible defects upon commissioning, and/or (2) The processes and
transactions are not operated in the best possible manner. Six sigma pioneered at Motorola in the
late seventies and early eighties being the correct methodology for designing and operating all
processes and transactions in any field of activity for the best possible performance, it is logical
to surmise that emerging/developing nations would have a certain shot at joining the ranks of
developed nations if they were to embrace six sigma in all their activities in a national initiative.
Developed nations need to do so as well if they are to maintain their preeminent status in the
globalized world so the standard of living of their societies is not compromised. The authors
have termed this, Scientific Framework for the Excellence of the External which allows everyone
to do all that they do from wakeup time to bedtime including things at work in the best possible
manner and six sigma is the wherewithal for achieving this objective.
*
Correspondence: Prof. Pradeep B. Deshpande, Six Sigma & advanced Controls, Inc. P.O. Box 22664, Louisville,
KY 40252-0664, http://www.sixsigmaquality.com E-mail: pradeep@sixsigmaquality.com
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
355
Figure 1. Defect Levels vs. Nations
The authors pointed out that while six sigma is essential for the excellence in the external world,
it is not insufficient for emerging as one’s best. What completes the quest for excellence is the
pursuit of the Excellence of the Internal whose goal is to remain serene and relatively unaffected
in the presence of ever-changing external conditions which are part and parcel of life. Raising the
S, R, T level of consciousness and becoming compassionate is the key to achieving this state and
meditation is one way to achieve the objective. In such a state, the decisions and actions of
individuals and the organizations they represent are much more conducive not only for their own
wellbeing but also for their families, organizations, nations, and the world.
The two scientific frameworks, one for the excellence of the external and the other for the
excellence of the internal, may appear to be obliquely related. The purpose of this paper is to
present strong evidence that higher level of consciousness can deliver outstanding performance
even in the absence of six sigma. It follows therefore that compassion will boost six sigma
success. Conversely, in the absence of a concomitant effort to raise the level of consciousness,
and therefore compassion, six sigma initiatives will fall short of expectations. This realization is
nothing short of a Eureka moment for it provides individuals, organizations, and nations a path
forward for improvement heretofore unrecognized regardless of the phase of rise and decline
their societies may find themselves at present.
Relevance of the Theory of Rise and Decline of Cultures
The first author developed a theory of rise and decline of societies in the early nineties. A brief
discussion of the theory with reference to three of the author’s most favorite societies; India,
Greece, and the United States is relevant to the topic at hand. Rise and decline are natural
phenomena and no culture is immune to them. Furthermore, the phenomenon of rise and decline
is cyclical as many natural processes are. Rise and decline occurs because of the transformation
of the three components of the mindset, S, R, and T (the definitions are at the end of the article).
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
356
During the period of rise, the S component is dominant and when the average S component of
the society reaches its maximum, the society is at its best. Following this, the S component
begins to decrease and the T component begins to assume dominance and the society begins to
decline. The society continues to decline as the average T component of the society increases and
when it reaches its maximum, the society is at its worst and then it is time for the S component to
begin its ascent and the society begins to rise again. The perceived locations of the three nations
on the rise and decline curve are shown in Figure 2.
After making phenomenal contributions to human civilization, India declined in its last cycle
over two thousand years ago and is now rising again. The rise and decline of Greece as gleaned
from Figure 3 which plots the Greek individuals listed in the twenty-three volumes of the
Encyclopedia Britannica indicates that Greece declined around the 5th Century C. E.
Figure 2. India, Greece, and the United States in their current phase of Rise and Decline
Figure 3. Rise and Decline of Greece in the Last Cycle
The United States is thought to be somewhere in the region marked in red in Figure 2. Only in
hindsight would we know where the US was at this point in time. The calibrations for the US and
India in Figure 2 were reported by Dr. David R. Hawkins, MD in his work Power vs. Force (7).
He also coauthored the book Orthomolecular Psychiatry with The Late Linus Pauling, Nobel
Laureate in Chemistry and Peace. So powerful is the theory of rise and decline that the very
culture whose wisdom led the theory itself finds calibrated considerably lower than the United
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
357
States at this point in time. The reported calibration in case of Greece in Figure is the first
author’s perception, possibly in error by as much as +30%.
The Evidence
The evidence has come about from an unlikely place, The 2013 Kumbh Mela, in Allahabad,
India. This is especially significant as the sample size is very large, in millions, an envy of
statisticians. It would be impossible to deliberately conduct such a large experiment to assess the
benefits of rising levels of consciousness. Kumbh Mela, believed to be the largest religious
gathering on earth is held every 12 years on the banks of the confluence of the holy rivers Ganga,
Yamuna, and the mythical Saraswati. Between the twelve-year events, the Mela alternates every
three years between the cities of Nasik, Allahabad, Ujjain and Haridwar. Most recently the Mela
was celebrated at the Holy confluence of the rivers in Allahabad during the first quarter of 2013.
The Financial Times carried an interesting article on March 1, 2013 written by Victor Mallet
titled, “Pop-up Mega City is a Lesson for India” along with a photograph of the tent city in
Figure 4.
Figure 4. Temporary tents for devotees during the Kumbh Mela in Allahabad
(Source: The Financial Times, March 1, 2013)
Excerpts from the article presented here strengthen the hypothesis compassion boosts
performance.
Mr. Onno Ruhl, Head of the World Bank in India, who visited the Kumbh Mela this year, was
moved to bathe in the Ganges himself. He calls it an incredible logistical operation. Says Mr.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
358
Ruhl, “the city on the sandbanks, soon to be dismantled before the river floods, “has water,
sanitation, power, and solid-waste management, everything, actually, that many Indian cities
lack”.
Harvard researchers describe it as “a pop-up mega city”. On the sandbanks of the river Ganges
at Allahabad, bureaucrats and workers from Uttar Pradesh, India’s most populous and one of
poorest state, took less than three months to build a tent city for 2 million residents complete
with hard roads, toilets, running water, electricity, food shops, garbage collection, and wellmanned police stations. This year’s event attracted millions of pilgrims from across India who
came to wash away their sins in the Ganges at its confluence with the Yamuna. Over its two
months to mid-March, the Mela attracted 80 million-100 million visitors, with up to 30 million
attempting to bathe in the river on February 10 alone, officials say. Precise numbers are hard to
come by but the devotees and foreign visitors are generally full of praise for the organizers of
what is arguably the largest gathering of humans on earth. Apart from a February 10 stampede
at the nearby Allahabad railway station in which 36 were killed, the Kumbh Mela itself has so
far gone off smoothly. Fresh water comes out of the taps. Toilets are disinfected. Trained
police carefully shepherd the crowds to the bathing areas. The lights come on at night.
To somebody who does projects, it’s like a mega-refugee camp that came up overnight and
gets sustained and managed for two months with people filtering [in and out] at a rate of
millions a day. It’s managed by the Uttar Pradesh government. If somehow we could translate
that capacity to day-to-day business, you could transform UP. It’s a really powerful thought.”
Uttar Pradesh is often seen as the epitome of all that is wrong with India. With a population of
over 200 million – larger than Brazil’s – the state is notoriously corrupt and inefficient. Take
sanitation. In the decade to 2011, the UP government reported steadily rising construction of
latrines in rural areas with the help of $600 million in public funds. But the 2011 census
showed that almost no toilets had actually been built. Most of the money was stolen, leaving
tens of thousands of children to die each year as a result of diarrhea spread by what one aid
worker called “appalling” sanitation. There are few such problems at the Kumbh Mela,
however.
Devesh Chaturvedi, a senior official who is divisional commissioner of Allahabad, is proud of
the “huge task” that he and perhaps 100,000 workers completed in organizing this year’s
festival. He mentions 165 km of roads on the sand made of steel plates, 18 pontoon bridges,
560 km of water supply lines, 670 km of electricity lines, 22,500 street lights and 200,000
electricity connections, as well as 275 food shops for essential supplies such as flour, rice, milk
and cooking gas. Mr. Chaturvedi agrees there is a contrast between the successful provision of
these services and the way life continues in the rest of the state, and has two explanations.
First, the authorities ensure that all those working on the project are accountable for their
actions and the money they spend. Second, those involved are highly motivated. “They feel it’s
a real service to all these pilgrims who have come here, the sadhus [holy men] and the seers, so
it’s a sort of mission which motivates them to work extra, despite difficult working
conditions.”
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
359
Good organization and efficient infrastructure, in short, are no more impossible in India than
anywhere else. “The lesson is, it can be done,” says Bhagawati Saraswati, a Californian-born
Hindu devotee (whom the first author knows as Dr. Thoebe Garfield, Ph. D., Stanford along
with Swami Chidanand Saraswati, Head of the Ashram Paramarth Niketan in Rishikesh)
camped on the river bank with other members of an ashram based on the upper Ganges. She
notes the “phenomenal” number of man-hours and employees devoted to the Kumbh Mela, and
says the event shows that India can organize itself. “It’s an amazing lesson,” she says. “What it
means is: India can do it. All of the villages, all of the cities can have electricity, they can have
running water, they can have roads. That attention, that focuses, that clarity, that commitment,
just has to be there.”
In the concluding thoughts on the article, Victor writes, a question on the minds of both Indians
and foreigners is: How? Why? Or rather: if the authorities can build infrastructure so
efficiently for this short but very large festival and its instant city, why can they not do the
same for permanent villages and towns?
We trust the answer is clear to the readers of this article. This level of performance would have
been impossible in the absence of a high level of consciousness. This means that such
performance is possible when the level of consciousness is raised and in such an environment,
six sigma will lead to unparalleled excellence.
Discussion
For the last seven years the first author has been conducting six sigma training for the MBA
students of the Gatton College of Business & Economics, University of Kentucky, Lexington,
KY, in Greece at the Technical Education Institute (TEI) of Piraeus, Athens. The framework for
external and internal excellence is appropriate for all three nations which are in different stages
of rise and decline. The challenge for Greece is to turn the direction as it currently finds itself in
the depth of decline. The challenge for India (or China for that matter) is to accelerate its rise
while the challenge for the United States is to maintain a favorable trajectory to keep decline at
bay longer.
Courtesy of Nikolas Rouhatas, an elected Councilman in Office of the Mayor of a city of
200,000 in Greece who was a student in the recent six sigma offering at TEI, the first author had
the pleasure to meet with Dr. Andres Papastamou, Special Adviser to the current Greek Prime
Minister, Hon. Mr. Antonis Samaras. The meeting lasted for ninety minutes and it was clear that
Dr. Papastamou had fully understood the need to embrace both frameworks of excellence in
Greece.
On the concluding day of the recent six sigma training program in Greece, the first author
inquired how many students would be interested in learning the scientific framework for the
excellence of the internal on the following evening. Since virtually everyone raised their hand,
the TEI management graciously invited the first author to give the talk to the students on Friday
March 1, 2013 to which former students from the previous cohorts were also invited. Some
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
360
thirty-five to forty students and former students came for the talk and went away fully convinced
about the value of the two frameworks not only for them but also for Greece. The first author
will always cherish the signed copy of the book of Poems by a Greek Poet the Late C. P. Cavafy
and a replica of an ancient Greek statue from the students. If two weeks of training can make this
level of change in the mindset of students, then we must assume that diligent pursuit of the
framework is just what the doctor ordered.
Over the past year, the first author has also has presented talks on the Framework for internal
excellence in the United States, Peru and India to learn how people of different cultures, races,
and religions would react to the ideas. The reactions of the audiences in all four countries have
been overwhelmingly positive. This should be taken as a complement to the framework and not
intended to convey a self-serving intention. Figures 5(a) – (c) are photos from the offerings in
Peru, Louisville, and Greece.
(a) Peruvian Congress at Lima
(b) Metro Louisville Program Hosted by
Tony Belak/ J. R. Curtin
(c) University of Kentucky MBA at TEI/Piraeus Athens, Greece
Peruvian Congress at Lima
Figure 5. Participants in Scientific Framework for Excellence of the Internal Program
Dr. Mikel Harry who helped introduce six sigma at General Electric in the early nineties wrote
an article for the Times of India in 2004 (8) titled, “India should use 6 Sigma to catch up with the
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
361
world” urging Indians to embrace six sigma even in mega projects like linking of the rivers with
plentiful water with those which perennially suffer from draught conditions. Had he been made
aware how significant the problem of pollution of Indian rivers had become, he would have
added it to the list. It is now possible to make an even more powerful statement. India, or for that
matter any nation, should introduce formal programs to raise the level of consciousness to
become to become more compassionate and that in itself will reduce defect levels in products
and services. Of course, embracing six sigma will improve performance. For example, in the
Government of India project supported by the World Bank to clean up the Ganges river of the
Allahabad example, the route to progress is to raise the level of consciousness of the people
living around the 2,500 km stretch of the river. Cleaning up will take care of itself and six sigma
will be invaluably helpful. The first author had the pleasure of meeting Dr. Harry about a decade
ago in Arizona and there is every reason to believe that the paper will resonate with him.
According to the Times of India reporter, Dr. Harry was candid about its limitations. “Six Sigma
is not a panacea. It helps you innovate better, not invent. It’s just a better mousetrap which helps
bring about higher levels of value with customers and shareholders.” But he’s also passionate
about its benefits. “Six Sigma is a credible journey. TQM is a dream. Dr Deming awakened the
world to the need for quality. But he didn’t put down a roadmap on getting there. I did. I’m
saying with all humility that Six Sigma has proven itself as a superior way of thinking.”
In fact, the authors of this article are comfortable with the assertion Six sigma is as valuable for
external excellence as Vedas, Upanishads, Geeta, Yoga Sutras, Shastras, etc., are for internal
excellence. Without six sigma it would have impossible to decipher the ancient wisdom of the
excellence of the internal. The readers might find it interesting that the New York Times had
titled their 1998 article, Six Sigma Enlightenment (9)!
Six sigma being an auditable methodology, there are a myriad of opportunities to further validate
the crucial role of compassion in improving performance. Here are some examples:
Business Excellence. The application of these ideas in corporations should lead to
demonstrably better bottom-line performance and higher satisfaction levels of all parties.
Healthcare Systems. Significant variations in patient outcomes and costs have been reported
across hospitals in the United States. Six sigma is clearly an issue but it would be most
interesting to investigate the impact of rising compassion levels on the performance. We are
rather sure the difference would be substantial.
Complaint management. Management of complaints may present an interesting opportunity
to assess the efficacy of thesis in this paper.
We are heartened to note that the Metro Louisville Mayor may have implicitly recognized the
thesis of this article. He is not only a six sigma black belt but has embraced a vision to make
Metro Louisville the most compassionate city in America. In 2013, the week of April 13 -21 was
dedicated to acts of compassion, public service, as a part of an official Kentucky Derby Festival
event, joined by the Festival, Metro United Way, and Jefferson County Public Schools and the
Metro Government as sponsors. Last year’s effort prompted the U.S. Conference of Mayors to
recognize Louisville as “America’s Most Livable City.”
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
362
We are also pleased to have come across several corporations which are practicing compassion
in one form or another. For example, PNC Bank has embarked on an initiative called Human
Sigma which in our language translates into Compassion + Six Sigma = Human Sigma, and
Google is passionate about everyday compassion at Google.
Conclusions
The explicit link of compassion to performance is identified and evidence presented to
substantiate the claim. A scientific framework for raising the S, R, T level of consciousness and
therefore compassion being on hand, the link represents a wonderful opportunity for individuals,
organizations and nations to improve performance in any field of endeavor regardless of the
phase of rise and decline they may find themselves in at the time. The concepts cut across all
boundaries of race, caste, religion, and national origin. We conclude by adding that some of the
feelings expressed in this paper although well intentioned have the scope to raise our R and T
components and make us less compassionate, not more.
Definitions and Notes:
S: Truthfulness, honesty, steadfastness, equanimity; R: Attachment, bravery, ego, ambition, greed,
desire to live; T: Lying, cheating, causing injury in words or deeds, sleep.
Minimum S, R, T required for life.
S component strongly correlates with the positive emotions (Unconditioned love, kindness, empathy,
compassion, gratitude, forgiveness, etc.); Excessive R, T components strongly correlate with negative
emotions (Anger, hostility, hatred, irritation, sorrow, fear).
Acknowledgments: The first author thanks Dr. Roberto Z. Tantalean for introducing him to Honorable
Congressman Mr. Mesías Guevara and to the Honorable Congressman for hosting the talk on Science of
Enlightenment at the Peruvian Congress in Lima. The first author thanks Dr. Vivek Ranade, Head of the
Chemical Engineering Division at the National Chemical Laboratory, Pune, as well as the coauthor Dr. B.
D. Kulkarni for organizing the talk at NCL The first author is grateful to Prof. Petros Kalantonis who
manages the University of Kentucky’s MBA program in Athens for hosting the talk at TEI/Piraeus in
Athens. Grateful thanks are also due to Tony Belak and J. R. Curtin for hosting the talk and the follow-up
100 day program for the Metro Louisville community and for their comments on the paper. Finally, the
review and comments of Thangam “Sam” Rangaswamy and Joseph MacDonald are greatly appreciated.
References
[1]
[2]
[3]
Deshpande, P. B., Science of Compassion, Journal of Consciousness Exploration and Research, 3,
9, October 2012.
Deshpande, P. B. and Kulkarni, B. D., The Brahma Uncertainty Principle, Journal of
Consciousness Exploration and Research, 3, 2, February 2012.
Deshpande, P. B., Science of Enlightenment, Journal of Consciousness Exploration and Research,
3, 2, February 2012.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | April 2013 | Volume 4 | Issue 4 | pp. 354-363
Deshpande, P. B. & Kulkarni, B. D., Compassion, Performance & Programs for Excellence
[4]
[5]
[6]
[7]
[8]
[9]
363
http://2012daily.com/?q=node/17 (Pradeep B. Deshpande’s Message for World Transformation,
September 30, 2011).
Deshpande, P. B. and Christopher, P. M., On The Cyclical Nature of Excellence, reflections, Vol.
1, No. 1, 1993.
Deshpande, P. B., Six Sigma for Karma Capitalism, Six Sigma and Advanced Controls, Inc., 2011.
Hawkins, David R., Power vs. force, The hidden Determinants of Human Behavior, Veritas
Publishing, W. Sedona, AZ 2004.
Harry, Mikel J., India should use 6 Sigma to catch up with the world, Times of India, August 18,
2004.
Deutsch, Claudia H., Six Sigma Enlightenment, December 7, 1998.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com |
arXiv:2308.08708v3 [cs.AI] 22 Aug 2023
Consciousness in Artificial Intelligence:
Insights from the Science of Consciousness
Patrick Butlin*
Robert Long*
Eric Elmoznino
Yoshua Bengio
Jonathan Birch
Axel Constant
George Deane
Stephen M. Fleming
Chris Frith
Xu Ji
Ryota Kanai
Colin Klein
Grace Lindsay
Matthias Michel
Liad Mudrik
Megan A. K. Peters
Eric Schwitzgebel
Jonathan Simon
Rufin VanRullen
Abstract
Whether current or near-term AI systems could be conscious is a topic of scientific interest and
increasing public concern. This report argues for, and exemplifies, a rigorous and empirically
grounded approach to AI consciousness: assessing existing AI systems in detail, in light of our
best-supported neuroscientific theories of consciousness. We survey several prominent scientific
theories of consciousness, including recurrent processing theory, global workspace theory, higherorder theories, predictive processing, and attention schema theory. From these theories we derive
”indicator properties” of consciousness, elucidated in computational terms that allow us to assess
AI systems for these properties. We use these indicator properties to assess several recent AI
systems, and we discuss how future systems might implement them. Our analysis suggests that no
current AI systems are conscious, but also suggests that there are no obvious technical barriers to
building AI systems which satisfy these indicators.1
* Joint first authors and corresponding authors (patrickbutlin@gmail.com, rgblong@gmail.com)
1
A previous version of this sentence read ”...but also shows that there are no obvious barriers to building conscious
AI systems.” We have amended it to better reflect the messaging of the report: that satisfying these indicators may
be feasible. But satisfying the indicators would not mean that such an AI system would definitely be conscious.
Authors
Patrick Butlin*, Future of Humanity Institute, University of Oxford
Robert Long*, Center for AI Safety
Eric Elmoznino, University of Montreal and MILA - Quebec AI Institute
Yoshua Bengio, University of Montreal and MILA - Quebec AI Institute
Jonathan Birch, Centre for Philosophy of Natural and Social Science, London School of Economics and Political Science
Axel Constant, School of Engineering and Informatics, The University of Sussex and Centre de
Recherche en Éthique, University of Montreal
George Deane, Department of Philosophy, University of Montreal
Stephen M. Fleming, Department of Experimental Psychology and Wellcome Centre for Human
Neuroimaging, University College London
Chris Frith, Wellcome Centre for Human Neuroimaging, University College London and Institute
of Philosophy, University of London
Xu Ji, University of Montreal and MILA - Quebec AI Institute
Ryota Kanai, Araya, Inc.
Colin Klein, School of Philosophy, The Australian National University
Grace Lindsay, Department of Psychology and Center for Data Science, New York University
Matthias Michel, Center for Mind, Brain and Consciousness, New York University
Liad Mudrik, School of Psychological Sciences and Sagol School of Neuroscience, Tel-Aviv
University and CIFAR Program in Brain, Mind and Consciousness
Megan A. K. Peters, Department of Cognitive Sciences, University of California, Irvine and CIFAR Program in Brain, Mind and Consciousness
Eric Schwitzgebel, Department of Philosophy, University of California, Riverside
Jonathan Simon, Department of Philosophy, University of Montreal
Rufin VanRullen, Centre de Recherche Cerveau et Cognition, CNRS, Université de Toulouse
2
Details
Authorship statement: PB and RL are joint first authors. PB and RL planned and coordinated
the project and formulated the core ideas. PB drafted the majority of the report with substantial
contributions from RL. EE wrote the first drafts of sections 3.1.2 and 3.1.3, GD wrote the first draft
of section 4.1.2, and GL wrote the box on attention. All authors participated in workshops where
we planned the report, developed the ideas and reviewed drafts. Authors other than PB, RL and
EE are listed in alphabetical order.
Acknowledgements: The authors would like to thank: Nick Bostrom, who proposed the project
to PB and RL and contributed in the early stages; Tim Bayne, Matt Botvinick, David Chalmers,
Hakwan Lau, Matt McGill and Murray Shanahan, who attended workshops or took part in other
discussions contributing to the preparation of the report; Xander Balwit for her help as a research
assistant in the final stages of the project; and Charlie Thompson for his help with graphics and
formatting.
Funding:
• RL and PB ran workshops for the report that were supported by Effective Ventures and the
EA Long-Term Future Fund.
• EE was supported by the FRQNT Strategic Clusters Program (Centre UNIQUE) and a Vanier
Doctoral Canada Graduate Scholarship.
• AC was supported by European Research Council grant (XSCAPE) ERC-2020-SyG 951631.
• YB, AC, GD and JS were supported by a grant from Open Philanthropy.
• JS was supported by a grant from FRQ and a grant from SSHRC
• MM was supported by the Templeton World Charity Foundation, as part of the grant ‘Analyzing and Merging Theories of Consciousness’, at the Center for Mind, Brain, and Consciousness (NYU).
• SMF was supported by a Wellcome/Royal Society Sir Henry Dale Fellowship (206648/Z/17/Z).
• SMF, LM and MAKP were supported by Fellowships from the CIFAR Program in Brain,
Mind and Consciousness.
• XJ was supported by IVADO.
• CK was supported by Templeton World Charity Foundation grant TWCF-2020-20539.
The authors have no conflicts of interest to report.
3
Executive Summary
The question of whether AI systems could be conscious is increasingly pressing. Progress in AI
has been startlingly rapid, and leading researchers are taking inspiration from functions associated
with consciousness in human brains in efforts to further enhance AI capabilities. Meanwhile,
the rise of AI systems that can convincingly imitate human conversation will likely cause many
people to believe that the systems they interact with are conscious. In this report, we argue that
consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness. We
describe prominent theories of this kind and investigate their implications for AI.
We take our principal contributions in this report to be:
1. Showing that the assessment of consciousness in AI is scientifically tractable because
consciousness can be studied scientifically and findings from this research are applicable to AI;
2. Proposing a rubric for assessing consciousness in AI in the form of a list of indicator
properties derived from scientific theories;
3. Providing initial evidence that many of the indicator properties can be implemented in
AI systems using current techniques, although no current system appears to be a strong
candidate for consciousness.
The rubric we propose is provisional, in that we expect the list of indicator properties we would
include to change as research continues.
Our method for studying consciousness in AI has three main tenets. First, we adopt computational functionalism, the thesis that performing computations of the right kind is necessary and
sufficient for consciousness, as a working hypothesis. This thesis is a mainstream—although disputed—position in philosophy of mind. We adopt this hypothesis for pragmatic reasons: unlike
rival views, it entails that consciousness in AI is possible in principle and that studying the workings of AI systems is relevant to determining whether they are likely to be conscious. This means
that it is productive to consider what the implications for AI consciousness would be if computational functionalism were true. Second, we claim that neuroscientific theories of consciousness
enjoy meaningful empirical support and can help us to assess consciousness in AI. These theories
aim to identify functions that are necessary and sufficient for consciousness in humans, and computational functionalism implies that similar functions would be sufficient for consciousness in AI.
Third, we argue that a theory-heavy approach is most suitable for investigating consciousness in
AI. This involves investigating whether AI systems perform functions similar to those that scientific theories associate with consciousness, then assigning credences based on (a) the similarity of
the functions, (b) the strength of the evidence for the theories in question, and (c) one’s credence in
computational functionalism. The main alternative to this approach is to use behavioural tests for
consciousness, but this method is unreliable because AI systems can be trained to mimic human
behaviours while working in very different ways.
Various theories are currently live candidates in the science of consciousness, so we do not
endorse any one theory here. Instead, we derive a list of indicator properties from a survey of theories of consciousness. Each of these indicator properties is said to be necessary for consciousness
4
by one or more theories, and some subsets are said to be jointly sufficient. Our claim, however,
is that AI systems which possess more of the indicator properties are more likely to be conscious.
To judge whether an existing or proposed AI system is a serious candidate for consciousness, one
should assess whether it has or would have these properties.
The scientific theories we discuss include recurrent processing theory, global workspace theory,
computational higher-order theories, and others. We do not consider integrated information theory,
because it is not compatible with computational functionalism. We also consider the possibility
that agency and embodiment are indicator properties, although these must be understood in terms
of the computational features that they imply. This yields the following list of indicator properties:
Recurrent processing theory
RPT-1: Input modules using algorithmic recurrence
RPT-2: Input modules generating organised, integrated perceptual representations
Global workspace theory
GWT-1: Multiple specialised systems capable of operating in parallel (modules)
GWT-2: Limited capacity workspace, entailing a bottleneck in information flow and
a selective attention mechanism
GWT-3: Global broadcast: availability of information in the workspace to all
modules
GWT-4: State-dependent attention, giving rise to the capacity to use the workspace
to query modules in succession to perform complex tasks
Computational higher-order theories
HOT-1: Generative, top-down or noisy perception modules
HOT-2: Metacognitive monitoring distinguishing reliable perceptual representations
from noise
HOT-3: Agency guided by a general belief-formation and action selection system,
and a strong disposition to update beliefs in accordance with the outputs of
metacognitive monitoring
HOT-4: Sparse and smooth coding generating a “quality space”
Attention schema theory
AST-1: A predictive model representing and enabling control over the current state
of attention
Predictive processing
PP-1: Input modules using predictive coding
Agency and embodiment
AE-1: Agency: Learning from feedback and selecting outputs so as to pursue goals,
especially where this involves flexible responsiveness to competing goals
AE-2: Embodiment: Modeling output-input contingencies, including some
systematic effects, and using this model in perception or control
Table 1: Indicator Properties
We outline the theories on which these properties are based and describe the evidence and
arguments that support them in section 2 of the report, as well as explain the formulations used in
the table.
5
Having formulated this list of indicator properties, in section 3.1 we discuss how AI systems
could be constructed, or have been constructed, with each of the indicator properties. In most
cases, standard machine learning methods could be used to build systems that possess individual
properties from this list, although experimentation would be needed to learn how to build and train
functional systems which combine multiple properties. There are some properties in the list which
are already clearly met by existing AI systems (such as RPT-1, algorithmic recurrence), and others
where this is arguably the case (such as the first part of AE-1, agency). Researchers have also
experimented with systems designed to implement particular theories of consciousness, including
global workspace theory and attention schema theory.
In section 3.2, we consider whether some specific existing AI systems possess the indicator
properties. These include Transformer-based large language models and the Perceiver architecture,
which we analyse with respect to the global workspace theory. We also analyse DeepMind’s
Adaptive Agent, which is a reinforcement learning agent operating in a 3D virtual environment;
a system trained to perform tasks by controlling a virtual rodent body; and PaLM-E, which has
been described as an “embodied multimodal language model”. We use these three systems as case
studies to illustrate the indicator properties concerning agency and embodiment. This work does
not suggest that any existing AI system is a strong candidate for consciousness.
This report is far from the final word on these topics. We strongly recommend support for further research on the science of consciousness and its application to AI. We also recommend urgent
consideration of the moral and social risks of building conscious AI systems, a topic which we do
not address in this report. The evidence we consider suggests that, if computational functionalism
is true, conscious AI systems could realistically be built in the near term.
6
Contents
1
2
Introduction
9
1.1
Terminology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
9
1.2
Methods and Assumptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
1.2.1
Computational functionalism . . . . . . . . . . . . . . . . . . . . . . . . . 13
1.2.2
Scientific theories of consciousness . . . . . . . . . . . . . . . . . . . . . 14
1.2.3
Theory-heavy approach . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
Scientific Theories of Consciousness
2.1
2.2
2.3
2.4
Recurrent Processing Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
2.1.1
Introduction to recurrent processing theory . . . . . . . . . . . . . . . . . 19
2.1.2
Evidence for recurrent processing theory . . . . . . . . . . . . . . . . . . 20
2.1.3
Indicators from recurrent processing theory . . . . . . . . . . . . . . . . . 21
Global Workspace Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
2.2.1
Introduction to global workspace theory . . . . . . . . . . . . . . . . . . . 22
2.2.2
Evidence for global workspace theory . . . . . . . . . . . . . . . . . . . . 24
2.2.3
Indicators from global workspace theory . . . . . . . . . . . . . . . . . . 25
Higher-Order Theories . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29
2.3.1
Introduction to higher-order theories . . . . . . . . . . . . . . . . . . . . . 29
2.3.2
Computational HOTs and GWT . . . . . . . . . . . . . . . . . . . . . . . 30
2.3.3
Indicators from computational HOTs . . . . . . . . . . . . . . . . . . . . 31
Other Theories and Conditions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33
2.4.1
Attention Schema Theory . . . . . . . . . . . . . . . . . . . . . . . . . . 33
2.4.2
Predictive Processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
2.4.3
Midbrain Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35
2.4.4
Unlimited Associative Learning . . . . . . . . . . . . . . . . . . . . . . . 35
2.4.5
Agency and Embodiment . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
2.4.6
2.5
19
2.4.5(a)
Agency . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 37
2.4.5(b)
Embodiment . . . . . . . . . . . . . . . . . . . . . . . . . . . 40
2.4.5(c)
Agency and embodiment indicators . . . . . . . . . . . . . . . 43
Time and Recurrence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 44
Indicators of Consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 45
7
3
Consciousness in AI
3.1
3.2
4
47
Implementing Indicator Properties in AI . . . . . . . . . . . . . . . . . . . . . . . 48
3.1.1
Implementing RPT and PP . . . . . . . . . . . . . . . . . . . . . . . . . . 48
3.1.2
Implementing GWT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49
3.1.3
Implementing PRM . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51
3.1.4
Implementing AST . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55
3.1.5
Implementing agency and embodiment . . . . . . . . . . . . . . . . . . . 56
Case Studies of Current Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . 58
3.2.1
Case studies for GWT . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58
3.2.2
Case studies for embodied agency . . . . . . . . . . . . . . . . . . . . . . 60
Implications
4.1
64
Attributing Consciousness to AI . . . . . . . . . . . . . . . . . . . . . . . . . . . 64
4.1.1
Under-attributing consciousness to AI . . . . . . . . . . . . . . . . . . . . 64
4.1.2
Over-attributing consciousness to AI . . . . . . . . . . . . . . . . . . . . . 65
4.2
Consciousness and Capabilities . . . . . . . . . . . . . . . . . . . . . . . . . . . . 66
4.3
Recommendations . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 68
Glossary
71
8
1
Introduction
In the last decade, striking progress in artificial intelligence (AI) has revived interest in deep and
long-standing questions about AI, including the question of whether AI systems could be conscious. This report is about what we take to be the best scientific evidence for and against consciousness in current and near-term AI systems.
Because consciousness is philosophically puzzling, difficult to define and difficult to study empirically, expert opinions about consciousness—in general, and regarding AI systems—are highly
divergent. However, we believe that it is possible to make progress on the topic of AI consciousness
despite this divergence. There are scientific theories of consciousness that enjoy significant empirical support and are compatible with a range of views about the metaphysics of consciousness.
Although these theories are based largely on research on humans, they make claims about properties and functions associated with consciousness that are applicable to AI systems. We claim that
using the tools these theories offer us is the best method currently available for assessing whether
AI systems are likely to be conscious. In this report, we explain this method in detail, identify the
tools offered by leading scientific theories and show how they can be used.
We are publishing this report in part because we take seriously the possibility that conscious
AI systems could be built in the relatively near term—within the next few decades. Furthermore,
whether or not conscious AI is a realistic prospect in the near term, the rise of large language
model-based systems which are capable of imitating human conversation is likely to cause many
people to believe that some AI systems are conscious. These prospects raise profound moral
and social questions, for society as a whole, for those who interact with AI systems, and for
the companies and individuals developing and deploying AI systems. Humanity will be better
equipped to navigate these changes if we are better informed about the science of consciousness
and its implications for AI. Our aim is to promote understanding of these topics by providing a
mainstream, interdisciplinary perspective, which illustrates the degree to which questions about
AI consciousness are scientifically tractable, and which may be a basis for future research.
In the remainder of this section, we outline the terminology, methods and assumptions which
underlie this report.
1.1
Terminology
What do we mean by “conscious” in this report? To say that a person, animal or AI system is
conscious is to say either that they are currently having a conscious experience or that they are
capable of having conscious experiences. We use “consciousness” and cognate terms to refer
to what is sometimes called “phenomenal consciousness” (Block 1995). Another synonym for
“consciousness”, in our terminology, is “subjective experience”. This report is, therefore, about
whether AI systems might be phenomenally conscious, or in other words, whether they might be
capable of having conscious or subjective experiences.
What does it mean to say that a person, animal or AI system is having (phenomenally) conscious experiences? One helpful way of putting things is that a system is having a conscious experience when there is “something it is like” for the system to be the subject of that experience (Nagel
9
1974). Beyond this, however, it is difficult to define “conscious experience” or “consciousness” by
giving a synonymous phrase or expression, so we prefer to use examples to explain how we use
these terms. Following Schwitzgebel (2016), we will mention both positive and negative examples—that is, both examples of cognitive processes that are conscious experiences, and examples
that are not. By “consciousness”, we mean the phenomenon which most obviously distinguishes
between the positive and negative examples.
Many of the clearest positive examples of conscious experience involve our capacities to sense
our bodies and the world around us. If you are reading this report on a screen, you are having a
conscious visual experience of the screen. We also have conscious auditory experiences, such as
hearing birdsong, as well as conscious experiences in other sensory modalities. Bodily sensations
which can be conscious include pains and itches. Alongside these experiences of real, current
events, we also have conscious experiences of imagery, such as the experience of visualising a
loved one’s face.
In addition, we have conscious emotions such as fear and excitement. But there is disagreement about whether emotional experiences are simply bodily experiences, like the feeling of having
goosebumps. There is also disagreement about experiences of thought and desire (Bayne & Montague 2011). It is possible to think consciously about what to watch on TV, but some philosophers
claim that the conscious experiences involved are exclusively sensory or imagistic, such as the
experience of imagining what it would be like to watch a game show, while others believe that we
have “cognitive” conscious experiences, with a distinctive phenomenology1 associated specifically
with thought.
As for negative examples, there are many processes in the brain, including very sophisticated
information-processing that are wholly non-conscious. One example is the regulation of hormone
release, which the brain handles without any conscious awareness. Another example is memory
storage: you may remember the address of the house where you grew up, but most of the time
this has no impact on your consciousness. And, perception in all modalities involves extensive
unconscious processing, such as the processing necessary to derive the conscious experience you
have when someone speaks to you from the flow of auditory stimulation. Finally, most vision
scientists agree that subjects unconsciously process visual stimuli rendered invisible by a variety
of psychophysical techniques. For example, in “masking”, a stimulus is briefly flashed on a screen
then quickly followed by a second stimulus, called the “mask” (Breitmeyer & Ogmen 2006). There
is no conscious experience of the first stimulus, but its properties can affect performance on subsequent tasks, such as by “priming” the subject to identify something more quickly (e.g., Vorberg et
al. 2003).
In using the term “phenomenal consciousness”, we mean to distinguish our topic from “access
consciousness”, following Block (1995, 2002). Block writes that “a state is [access conscious]
if it is broadcast for free use in reasoning and for direct ‘rational’ control of action (including
reporting)” (2002, p. 208). There seems to be a close connection between a mental state’s being
conscious, in our sense, and its contents being available to us to report to others or to use in making
rational choices. For example, we would expect to be able to report seeing a briefly-presented
visual stimulus if we had a conscious experience of seeing it and to be unable to report seeing
1
The “phenomenology” or “phenomenal character” of a conscious experience is what it is like for the subject. In our
terminology, all and only conscious experiences have phenomenal characters.
10
it if we did not. However, these two properties of mental states are conceptually distinct. How
phenomenal consciousness and access consciousness relate to each other is an open question.
Finally, the word “sentient” is sometimes used synonymously with (phenomenally) “conscious”,
but we prefer “conscious”. “Sentient” is sometimes used to mean having senses, such as vision or
olfaction. However, being conscious is not the same as having senses. It is possible for a system to
sense its body or environment without having any conscious experiences, and it may be possible
for a system to be conscious without sensing its body or environment. “Sentient” is also sometimes
used to mean capable of having conscious experiences such as pleasure or pain, which feel good
or bad, and we do not want to imply that conscious systems must have these capacities. A system
could be conscious in our sense even if it only had “neutral” conscious experiences. Pleasure and
pain are important but they are not our focus here.2
1.2
Methods and Assumptions
Our method for investigating whether current or near-future AI systems might be conscious is
based on three assumptions. These are:
1. Computational functionalism: Implementing computations of a certain kind is necessary and sufficient for consciousness, so it is possible in principle for non-organic
artificial systems to be conscious.
2. Scientific theories: Neuroscientific research has made progress in characterising functions that are associated with, and may be necessary or sufficient for, consciousness;
these are described by scientific theories of consciousness.
3. Theory-heavy approach: A particularly promising method for investigating whether AI
systems are likely to be conscious is assessing whether they meet functional or architectural conditions drawn from scientific theories, as opposed to looking for theory-neutral
behavioural signatures.
These ideas inform our investigation in different ways. We adopt computational functionalism
as a working hypothesis because this assumption makes it relatively straightforward to draw infer2
For the sake of further illustration, here are some other definitions of phenomenal consciousness:
Chalmers (1996): “When we think and perceive, there is a whir of information-processing, but there is also a
subjective aspect. As Nagel (1974) has put it, there is something it is like to be a conscious organism. This subjective
aspect is experience. When we see, for example, we experience visual sensations: the felt quality of redness, the
experience of dark and light, the quality of depth in a visual field. Other experiences go along with perception in
different modalities: the sound of a clarinet, the smell of mothballs. Then there are bodily sensations, from pains to
orgasms; mental images that are conjured up internally; the felt quality of emotion, and the experience of a stream
of conscious thought. What unites all of these states is that there is something it is like to be in them.”
Graziano (2017): “You can connect a computer to a camera and program it to process visual information—color,
shape, size, and so on. The human brain does the same, but in addition, we report a subjective experience of those
visual properties. This subjective experience is not always present. A great deal of visual information enters the
eyes, is processed by the brain and even influences our behavior through priming effects, without ever arriving in
awareness. Flash something green in the corner of vision and ask people to name the first color that comes to mind,
and they may be more likely to say ‘green’ without even knowing why. But some proportion of the time we also
claim, ‘I have a subjective visual experience. I see that thing with my conscious mind. Seeing feels like something.’”
11
ences from neuroscientific theories of consciousness to claims about AI. Some researchers in this
area reject computational functionalism (e.g. Searle 1980, Tononi & Koch 2015) but our view is
that it is worth exploring its implications. We accept the relevance and value of some scientific
theories of consciousness because they describe functions that could be implemented in AI and
we judge that they are supported by good experimental evidence. And, our view is that, although
this may not be so in other cases, a theory-heavy approach is necessary for AI. A theory-heavy
approach is one that focuses on how systems work, rather than on whether they display forms of
outward behaviour that might be taken to be characteristic of conscious beings (Birch 2022b). We
explain these three ideas in more detail in this section.
Two further points about our methods and assumptions are worth noting before we go on. The
first is that, for convenience, we will generally write as though whether a system is conscious is
an all-or-nothing matter, and there is always a determinate fact about this (although in many cases
this fact may be difficult to learn). However, we are open to the possibility that this may not be
the case: that it may be possible for a system to be partly conscious, conscious to some degree, or
neither determinately conscious nor determinately non-conscious (see Box 1).
Box 1: Determinacy, degrees, dimensions
In this report, we generally write as though consciousness is an all-or-nothing matter: a
system either is conscious, or it isn’t. However, there are various other possibilities. There
seem to be many properties that have “blurry” boundaries, in the sense that whether some
object has that property may be indeterminate. For example, a shirt may be a colour somewhere on the borderline between yellow and green, such that there is no fact of the matter
about whether it is yellow or not. In principle, consciousness could be like this: there could
be creatures that are neither determinately conscious nor determinately non-conscious (Simon 2017, Schwitzgebel forthcoming). If this is the case, some AI systems could be in this
“blurry” zone. This kind of indeterminacy arguably follows from materialism about consciousness (Birch 2022a).
Another possibility is that there could be degrees of consciousness so that it is possible for
one system to be more conscious than another (Lee 2022). In this case, it might be possible to build AI systems that are conscious but only to a very slight degree, or even systems
which are conscious to a much greater degree than humans (Shulman & Bostrom 2021).
Alternatively, rather than a single scale, it could be that consciousness varies along multiple
dimensions (Birch et al. 2020).
Lastly, it could be that there are multiple elements of consciousness. These would not be
necessary conditions for some further property of consciousness, but rather constituents
which make up consciousness. These elements may be typically found together in humans,
but separable in other animals or AI systems. In this case, it would be possible for a system
to be partly conscious, in the sense of having some of these elements.
The second is that we recommend thinking about consciousness in AI in terms of confidence
or credence. Uncertainty about this topic is currently unavoidable, but there can, nonetheless, be
good reasons to think that one system is much more likely than another to be conscious, and this
can be relevant to how we should act. So it is useful to think about one’s credence in claims in this
12
area. For instance, one might think it justified to have a credence of about 0.5 in the conjunction of
a set of theoretical claims which imply that a given AI system is conscious; if so, one should have
a similar credence that the system is conscious.
1.2.1
Computational functionalism
Computational functionalism about consciousness is a claim about the kinds of properties of systems with which consciousness is correlated. According to functionalism about consciousness, it
is necessary and sufficient for a system to be conscious that it has a certain functional organisation: that is, that it can enter a certain range of states, which stand in certain causal relations to
each other and to the environment. Computational functionalism is a version of functionalism that
further claims that the relevant functional organisation is computational.3
Systems that perform computations process information by implementing algorithms; computational functionalism claims that it is sufficient for a state to be conscious that it plays a role of the
right kind in the implementation of the right kind of algorithm. For a system to implement a particular algorithm is for it to have a set of features at a certain level of abstraction: specifically, a range
of possible information-carrying states, and particular dispositions to make transitions between
these states. The algorithm implemented by a system is an abstract specification of the transitions
between states, including inputs and outputs, which it is disposed to make. For example, a pocket
calculator implements a particular algorithm for arithmetic because it generates transitions from
key-presses to results on screen by going through particular sequences of internal states.
An important upshot of computational functionalism, then, is that whether a system is conscious or not depends on features that are more abstract than the lowest-level details of its physical
make-up. The material substrate of a system does not matter for consciousness except insofar as
the substrate affects which algorithms the system can implement. This means that consciousness
is, in principle, multiply realisable: it can exist in multiple substrates, not just in biological brains.
That said, computational functionalism does not entail that any substrate can be used to construct
a conscious system (Block 1996). As Michel and Lau (2021) put it, “Swiss cheese cannot implement the relevant computations.” We tentatively assume that computers as we know them are in
principle capable of implementing algorithms sufficient for consciousness, but we do not claim
that this is certain.
It is also important to note that systems that compute the same mathematical function may
do so by implementing different algorithms, so computational functionalism does not imply that
systems that “do the same thing” in the sense that they compute the same input-output function are
necessarily alike in consciousness (Sprevak 2007). Furthermore, it is consistent with computational
functionalism that consciousness may depend on performing operations on states with specific
representational formats, such as analogue representation (Block 2023). In terms of Marr’s (1982)
levels of analysis, the idea is that consciousness depends on what is going on in a system at the
3
Computational functionalism is compatible with a range of views about the relationship between consciousness and
the physical states which implement computations. In particular, it is compatible with both (i) the view that there is
nothing more to a state’s being conscious than its playing a certain role in implementing a computation; and (ii) the
view that a state’s being conscious is a matter of its having sui generis phenomenal properties, for which its role in
implementing a computation is sufficient.
13
algorithmic and representational level, as opposed to the implementation level, or the more abstract
“computational” (input-output) level.
We adopt computational functionalism as a working hypothesis primarily for pragmatic reasons. The majority of leading scientific theories of consciousness can be interpreted computationally—that is, as making claims about computational features which are necessary or sufficient
for consciousness in humans. If computational functionalism is true, and if these theories are
correct, these features would also be necessary or sufficient for consciousness in AI systems. Noncomputational differences between humans and AI systems would not matter. The assumption
of computational functionalism, therefore, allows us to draw inferences from computational scientific theories to claims about the likely conditions for consciousness in AI. On the other hand,
if computational functionalism is false, there is no guarantee that computational features which
are correlated with consciousness in humans will be good indicators of consciousness in AI. It
could be, for instance, that some non-computational feature of living organisms is necessary for
consciousness (Searle 1980, Seth 2021), in which case consciousness would be impossible in nonorganic artificial systems.
Having said that, it would not be worthwhile to investigate artificial consciousness on the assumption of computational functionalism if this thesis were not sufficiently plausible. Although
we have different levels of confidence in computational functionalism, we agree that it is plausible.4 These different levels of confidence feed into our personal assessments of the likelihood that
particular AI systems are conscious, and of the likelihood that conscious AI is possible at all.
1.2.2
Scientific theories of consciousness
The second idea which informs our approach is that some scientific theories of consciousness are
well-supported by empirical evidence and make claims which can help us assess AI systems for
consciousness. These theories have been developed, tested and refined through decades of highquality neuroscientific research (for recent reviews, see Seth & Bayne 2022, Yaron et al. 2022).
Positing that computational functions are sufficient for consciousness would not get us far if we
had no idea which functions matter; but these theories give us valuable indications.
Scientific theories of consciousness are different from metaphysical theories of consciousness.
Metaphysical theories of consciousness make claims about how consciousness relates to the material world in the most general sense. Positions in the metaphysics of consciousness include
property dualism (Chalmers 1996, 2002), panpsychism (Strawson 2006, Goff 2017), materialism
(Tye 1995, Papineau 2002) and illusionism (Frankish 2016). For example, materialism claims that
phenomenal properties are physical properties while property dualism denies this. In contrast, scientific theories of consciousness make claims about which specific material phenomena—usually
brain processes—are associated with consciousness. Some explicitly aim to identify the neural correlates of conscious states (NCCs), defined as the minimal sets of neural events which are jointly
sufficient for those states (Crick & Koch 1990, Chalmers 2000). The central question for scientific
theories of consciousness is what distinguishes cases in which conscious experience arises from
4
One influential argument is by Chalmers (1995): if a person’s neurons were gradually replaced by functionally-equivalent artificial prostheses, their behaviour would stay the same, so it is implausible that they would undergo any
radical change in conscious experience (if they did, they would act as though they hadn’t noticed).
14
those in which it does not, and while this is not the only question such theories might address, it is
the focus of this report.
We discuss several specific scientific theories in detail in section 2. Here, we provide a brief
overview of the methods of consciousness science to show that consciousness can be studied scientifically.
The scientific study of consciousness relies on assumptions about links between consciousness
and behaviour (Irvine 2013). For instance, in a study on vision, experimenters might manipulate a
visual stimulus (e.g. a red triangle) in a certain way—say, by flashing it at two different speeds. If
they find that subjects report seeing the stimulus in one condition but not in the other, they might
argue that subjects have a conscious visual experience of the stimulus in one condition but not
in the other. They could then measure differences in brain activity between the two conditions,
and draw inferences about the relationships between brain activity and consciousness—a method
called “contrastive analysis” (Baars 1988). This method relies on the assumption that subjects’
reports are a good guide to their conscious experiences.
As a method for studying consciousness in humans and other animals, relying on subjects’
reports has two main problems. The first problem is uncertainty about the relationship between
conscious experience, reports and cognitive processes which may be involved in making reports,
such as attention and memory. Inasmuch as reports or reportability require more processing than
conscious experience, studies that rely on reports may be misleading: brain processes which are
involved in processing the stimulus and making reports, but are not necessary for consciousness,
could be misidentified as among the neural correlates of consciousness (Aru et al. 2012). Another
possibility is that phenomenal consciousness may have relatively rich contents, of which only a
proportion are selected by attention for further processing yielding cognitive access, which is, in
turn, necessary for report. In this case, relying on reports may lead us to misidentify the neural basis
of access as that of phenomenal consciousness (Block 1995, 2007). The methodological problem
here is arguably more severe because it is an open question whether phenomenal consciousness
“overflows” cognitive access in this way—researchers have conflicting views (Phillips 2018a).
A partial solution to this problem may be the use of “no-report paradigms”, in which indicators
of consciousness other than reports are used, having been calibrated for correlation with consciousness in separate experiments, which do use reports (Tsuchiya et al. 2015). The advantage of this
paradigm is that subjects are not required to make reports in the main experiments, which may
mitigate the problem of report confounds. No-report paradigms are not a “magic bullet” for this
problem (Block 2019, Michel & Morales 2020), but they may be an important step in addressing
it.
Another possible method for measuring consciousness is the use of metacognitive judgments
such as confidence ratings (e.g. Peters & Lau 2015). For example, subjects might be asked how
confident they are in an answer about a stimulus, e.g. about whether a briefly-presented stimulus
was oriented vertically or horizontally. The underlying thought here is that subjects’ ability to
track the accuracy of their responses using confidence ratings (known as metacognitive sensitivity)
depends on their being conscious of the relevant stimuli. Again, this method is imperfect, but it has
some advantages over asking subjects to report their conscious experiences (Morales & Lau 2021;
Michel 2022). There are various potential confounds in consciousness science, but researchers can
combine evidence from studies of different kinds to reduce the force of methodological objections
15
(Lau 2022).
The second problem with the report approach is that there are presumably some subjects of
conscious experience who cannot make reports, including non-human animals, infants and people
with certain kinds of cognitive disability. This problem is perhaps most pressing in the case of nonhuman animals, because if we knew more about consciousness in animals—especially those which
are relatively unlike us—we might have a far better picture of the range of brain processes that are
correlated with consciousness. This difficult problem has recently received increased attention
(e.g. Birch 2022b). However, although current scientific theories of consciousness are primarily
based on data from healthy adult humans, it can still be highly instructive to examine whether AI
systems use processes similar to those described by these theories.
Box 2: Metaphysical theories and the science of consciousness
Major positions in the metaphysics of consciousness include materialism, property dualism,
panpsychism and illusionism (for a detailed and influential overview, see Chalmers 2002).
Materialism claims that consciousness is a wholly physical phenomenon. Conscious experiences are states of the physical world—typically brain states—and the properties that
make up the phenomenal character of our experiences, known as phenomenal properties,
are physical properties of these states. For example, a materialist might claim that the experience of seeing a red tulip is a particular brain state and that the “redness” of the experience
is a feature of that state.
Property dualism denies materialism, claiming that phenomenal properties are non-physical
properties. Unlike substance dualism, this view claims that there is just one sort of substance
or entity while asserting that it has both physical and phenomenal properties. The “redness”
of the experience of seeing the tulip may be a property of the brain state involved, but it is
distinct from any physical property of this state.
Panpsychism claims that phenomenal properties, or simpler but related “proto-phenomenal”
properties, are present in all fundamental physical entities. A panpsychist might claim that
an electron, as a fundamental particle, has either a property like the “redness” of the tulip
experience or a special precursor of this property. Panpsychists do not generally claim that
everything has conscious experiences—instead, the phenomenal aspects of fundamental entities only combine to give rise to conscious experiences in a few macro-scale entities, such
as humans.
Illusionism claims that we are subject to an illusion in our thinking about consciousness
and that either consciousness does not exist (strong illusionism), or we are pervasively mistaken about some of its features (weak illusionism). However, even strong illusionism acknowledges the existence of “quasi-phenomenal” properties, which are properties that are
misrepresented by introspection as phenomenal. For example, an illusionist might say that
when one seems to have the conscious experience of seeing a red tulip, some brain state is
misrepresented by introspection as having a property of phenomenal “redness”.
Importantly, there is work for the science of consciousness to do on all four of these metaphysical positions. If materialism is true, then some brain states are conscious experiences
16
and others are not, and the role of neuroscience is to find out what distinguishes them. Similarly, property dualism and panpsychism both claim that some brain states but not others
are associated with conscious experiences, and are compatible with the claim that this difference can be investigated scientifically. According to illusionism, neuroscience can explain
why the illusion of consciousness arises, and in particular why it arises in connection with
some brain states but not others.
1.2.3
Theory-heavy approach
In section 1.2.1 we adopted computational functionalism, the thesis that implementing certain
computational processes is necessary and sufficient for consciousness, as a working hypothesis,
and in section 1.2.2 we noted that there are scientific theories that aim to describe correlations between computational processes and consciousness. Combining these two points yields a promising
method for investigating consciousness in AI systems: we can observe whether they use computational processes which are similar to those described in scientific theories of consciousness, and
adjust our assessment accordingly. To a first approximation, our confidence that a given system is
conscious can be determined by (a) the similarity of its computational processes to those posited by
a given scientific theory of consciousness, (b) our confidence in this theory, (c) and our confidence
in computational functionalism.5 Considering multiple theories can then give a fuller picture. This
method represents a “theory-heavy” approach to investigating consciousness in AI.
The term “theory-heavy” comes from Birch (2022b), who considers how we can scientifically
investigate consciousness in non-human animals, specifically invertebrates.
Birch argues against using the theory-heavy approach in this case. One of Birch’s objections
is that the evidence from humans that supports scientific theories does not tell us how much their
conditions can be relaxed while still being sufficient for consciousness (see also Carruthers 2019).
That is, while we might have good evidence that some process is sufficient for consciousness in
humans, this evidence will not tell us whether a process in another animal, which is similar in
some respects but not others, is also sufficient for consciousness. To establish this we would need
antecedent evidence about which non-human animals or systems are conscious—unfortunately,
the very question we are uncertain about.
Another way of thinking about this problem is in terms of how we should interpret theories of
consciousness. As we will see throughout this report, it is possible to interpret theories either in
relatively restrictive ways, as claiming only that very specific features found in humans are sufficient for consciousness, or as giving much more liberal, abstract conditions, which may be met
by surprisingly simple artificial systems (Shevlin 2021). Moderate interpretations which strike a
balance between appealing generality (consciousness is not just this very specific process in the human brain) and unintuitive liberality (consciousness is not a property satisfied by extremely simple
systems) are attractive, but it is not clear that these have empirical support over the alternatives.
5
The theory may entail computational functionalism, in which case (c) would be unnecessary. But we find it helpful
to emphasise that if computational functionalism is a background assumption in one’s construal of a theory, one
should take into account both uncertainty about this assumption, and uncertainty about the specifics of the theory.
17
While this objection does point to an important limitation of theory-heavy approaches, it does
not show that a theory-heavy approach cannot give us useful information about consciousness in
AI. Some AI systems will use processes that are much more similar to those identified by theories of consciousness than others, and this objection does not count against the claim that those
using more similar processes are correspondingly better candidates for consciousness. Drawing
on theories of consciousness is necessary for our investigation because they are the best available
guide to the features we should look for. Investigating animal consciousness is different because
we already have reasons to believe that animals that are more closely related to humans and display more complex behaviours are better candidates for consciousness. Similarities in cognitive
architecture can be expected to be substantially correlated with phylogenetic relatedness, so while
it will be somewhat informative to look for these similarities, this will be less informative than in
the case of AI. 6
The main alternative to the theory-heavy approach for AI is to use behavioural tests that purport to be neutral between scientific theories. Behavioural tests have been proposed specifically
for consciousness in AI (Elamrani & Yampolskiy 2019). One interesting example is Schneider’s (2019) Artificial Consciousness Test, which requires the AI system to show a ready grasp
of consciousness-related concepts and ideas in conversation, perhaps exhibiting “problem intuitions” like the judgement that spectrum inversion is possible (Chalmers 2018). The Turing test
has also been proposed as a test for consciousness (Harnad 2003).
In general, we are sceptical about whether behavioural approaches to consciousness in AI can
avoid the problem that AI systems may be trained to mimic human behaviour while working in very
different ways, thus “gaming” behavioural tests (Andrews & Birch 2023). Large language modelbased conversational agents, such as ChatGPT, produce outputs that are remarkably human-like
in some ways but are arguably very unlike humans in the way they work. They exemplify both
the possibility of cases of this kind and the fact that companies are incentivised to build systems
that can mimic humans.7 Schneider (2019) proposes to avoid gaming by restricting the access of
systems to be tested to human literature on consciousness so that they cannot learn to mimic the
way we talk about this subject. However, it is not clear either whether this measure would be
sufficient, or whether it is possible to give the system enough access to data that it can engage with
the test, without giving it so much as to enable gaming (Udell & Schwitzgebel 2021).
6
Birch (2022b) advocates a “theory-light” approach, which has two aspects: (1) rejecting the idea that we should assess consciousness in non-human animals by looking for processes that particular theories associate with consciousness; and (2) not committing to any particular theory now, but aiming to develop better theories in the future when
we have more evidence about animal (and perhaps AI) consciousness. Our approach is “theory-heavy” in the sense
that, in contrast with the first aspect of the theory-light approach, we do assess AI systems by looking for processes
that scientific theories associate with consciousness. However, like Birch, we do not commit to any one theory at
this time. More generally, Birch’s approach makes recommendations about how the science of consciousness should
be developed, whereas we are only concerned with what kind of evidence should be used to make assessments of
consciousness in AI systems now, given our current knowledge.
7
See section 4.1.2 for discussion of the risk that there may soon be many non-conscious AI systems that seem conscious to users.
18
2
Scientific Theories of Consciousness
In this section, we survey a selection of scientific theories of consciousness, scientific proposals
which are not exactly theories of consciousness but which bear on our project, and other claims
from scientists and philosophers about putatively necessary conditions for consciousness. From
these theories and proposals, we aim to extract a list of indicators of consciousness that can be
applied to particular AI systems to assess how likely it is that they are conscious.8 Because we
are looking for indicators that are relevant to AI, we discuss possible artificial implementations of
theories and conditions for consciousness at points in this section. However, we address this topic
in more detail in section 3, which is about what it takes for AI systems to have the features that we
identify as indicators of consciousness.
Sections 2.1-2.3 cover recurrent processing theory, global workspace theory and higher-order
theories of consciousness—with a particular focus in 2.3 on perceptual reality monitoring theory.
These are established scientific theories of consciousness that are compatible with our computational functionalist framework. Section 2.4 discusses several other scientific theories, along with
other proposed conditions for consciousness, and section 2.5 gives our list of indicators.
We do not aim to adjudicate between the theories which we consider in this section, although
we do indicate some of their strengths and weaknesses. We do not adopt any one theory, claim that
any particular condition is definitively necessary for consciousness, or claim that any combination
of conditions is jointly sufficient. This is why we describe the list we offer in section 2.5 as a list
of indicators of consciousness, rather than a list of conditions. The features in the list are there
because theories or theorists claim that they are necessary or sufficient, but our claim is merely
that it is credible that they are necessary or (in combination) sufficient because this is implied by
credible theories. Their presence in a system makes it more probable that the system is conscious.
We claim that assessing whether a system has these features is the best way to judge whether it is
likely to be conscious given the current state of scientific knowledge of the subject.
2.1
Recurrent Processing Theory
2.1.1
Introduction to recurrent processing theory
The recurrent processing theory (RPT; Lamme 2006, 2010, 2020) is a prominent member of a
group of neuroscientific theories of consciousness that focus on processing in perceptual areas in
the brain (for others, see Zeki & Bartels 1998, Malach 2021). These are sometimes referred to
as “local” (as opposed to “global”) theories of consciousness because they claim that activity of
the right form in relatively circumscribed brain regions is sufficient for consciousness, perhaps
provided that certain background conditions are met. RPT is primarily a theory of visual consciousness: it seeks to explain what distinguishes states in which stimuli are consciously seen from
those in which they are merely unconsciously represented by visual system activity. The theory
8
A similar approach to the question of AI consciousness is found in Chalmers (2023) which considers several features
of LLMs which give us reason to think they are conscious, and several commonly-expressed “defeaters” for LLM
consciousness. Many of these considerations are, like our indicators, drawn from scientific theories of consciousness.
19
claims that unconscious vs. conscious states correspond to distinct stages in visual processing. An
initial feedforward sweep of activity through the hierarchy of visual areas is sufficient for some
visual operations like extracting features from the scene, but not sufficient for conscious experience. When the stimulus is sufficiently strong or salient, however, recurrent processing occurs, in
which signals are sent back from higher areas in the visual hierarchy to lower ones. This recurrent processing generates a conscious representation of an organised scene, which is influenced
by perceptual inference—processing in which some features of the scene or percept are inferred
from other features. On this view, conscious visual experience does not require the involvement
of non-visual areas like the prefrontal cortex, or attention—in contrast with “global” theories like
global workspace theory and higher-order theories, which we will consider shortly.
2.1.2
Evidence for recurrent processing theory
The evidence for RPT is of two kinds: the first is evidence that recurrent processing is necessary
for conscious vision, and the second is evidence against rival theories which claim that additional
processing for functions beyond perceptual organisation is required.
Evidence of the first kind comes from experiments involving backward masking and transcranial magnetic stimulation, which indicate that feedforward activity in the primary visual cortex
(the first stage of processing mentioned above) is not sufficient for consciousness (Lamme 2006).
Lamme also argues that, although feedforward processing is sufficient for basic visual functions
like categorising features, important functions like feature grouping and binding and figure-ground
segregation require recurrence. He, therefore, claims that recurrent processing is necessary for the
generation of an organised, integrated visual scene—the kind of scene that we seem to encounter
in conscious vision (Lamme 2010, 2020).
Evidence against more demanding rival theories includes results from lesion and brain stimulation studies suggesting that additional processing in the prefrontal cortex is not necessary for
conscious visual perception. This counts against non-“local” views insofar as they claim that functions in the prefrontal cortex are necessary for consciousness (Malach 2022; for a countervailing
analysis see Michel 2022). Proponents of RPT also argue that the evidence used to support rival
views is confounded by experimental requirements for downstream cognitive processes associated
with making reports. The idea is that when participants produce the reports (and other behavioural
responses) that are used to indicate conscious perception, this requires cognitive processes that
are not themselves necessary for consciousness. So where rival theories claim that downstream
processes are necessary for consciousness, advocates of RPT and similar theories respond that the
relevant evidence is explained by confounding factors (see the methodological issues discussed in
section 1.2.2).
20
2.1.3
Indicators from recurrent processing theory
There are various possible interpretations of RPT that have different implications for AI consciousness. For our purposes, a crucial issue is that the claim that recurrent processing is necessary for
consciousness can be interpreted in
two different ways. In the brain, it
is common for individual neurons to
receive inputs that are influenced by
their own earlier outputs, as a result
of feedback loops from connected regions. However, a form of recurrence can be achieved without this
structure: any finite sequence of operations by a network with feedback Figure 1: An unfolded recurrent neural network as deloops can be mimicked by a suitable picted in LeCun, Bengio, & Hinton (2015). Attributionfeedforward network with enough Share Alike 4.0 International.
layers. To achieve this, the feedforward network would have multiple
layers with shared weights, so that the same operations would be performed repeatedly—thus mimicking the effect of repeated processing of information by a single set of neurons, which would be
produced by a network with feedback loops (Savage 1972, LeCun et al. 2015). In current AI,
recurrent neural networks are implemented indistinguishably from deep feedforward networks in
which layers share weights, with different groups of input nodes for successive inputs feeding into
the network at successive layers.
We will say that networks with feedback loops such as those in the brain, which allow individual physically-realised neurons to process information repeatedly, display implementational
recurrence. However, deep feedforward networks with weight-sharing display only algorithmic
recurrence—they are algorithmically similar to implementationally recurrent networks but have a
different underlying structure. So there are two possible interpretations of RPT available here: it
could be interpreted either as claiming that consciousness requires implementational recurrence,
or as making only the weaker claim that algorithmic recurrence is required. Doerig et al. (2019)
interpret RPT as claiming that implementational recurrence is required for consciousness and criticise it for this claim. However, in personal communication, Lamme has suggested to us that RPT
can also be given the weaker algorithmic interpretation.
Implementational and algorithmic recurrence are both possible indicators of consciousness in
AI, but we focus on algorithmic recurrence. It is possible to build an artificial system that displays
implementational recurrence, but this would involve ensuring that individual neurons were physically realised by specific components in the hardware. This would be a very different approach
from standard methods in current AI, in which neural networks are simulated without using specific
hardware components to realise each component of the network. An implementational recurrence
indicator would therefore be less relevant to our project, so we do not adopt this indicator.
Using algorithmic recurrence, in contrast, is a weak condition that many AI systems already
meet. However, it is non-trivial, and we argue below that there are other reasons, besides the
21
evidence for RPT, to believe that algorithmic recurrence is necessary for consciousness. So we
adopt this as our first indicator:
RPT-1: Input modules using algorithmic recurrence
This is an important indicator because systems that lack this feature are significantly worse
candidates for consciousness.
RPT also suggests a second indicator, because it may be interpreted as claiming that it is sufficient for consciousness that algorithmic recurrence is used to generate integrated perceptual representations of organised, coherent scenes, with figure-ground segregation and the representation of
objects in spatial relations. This second indicator is:
RPT-2: Input modules generating organised, integrated perceptual representations
An important contrast for RPT is between the functions of feature extraction and perceptual
organisation. Features in visual scenes can be extracted in unconscious processing in humans,
but operations of perceptual organisation such as figure-ground segregation may require conscious
vision; this is why RPT-2 stresses organised, integrated perceptual representations.
There are also two further possible interpretations of RPT, which we set aside for different
reasons. First, according to the biological interpretation of RPT, recurrent processing in the brain
is necessary and sufficient for consciousness because it is associated with certain specific biological
phenomena, such as recruiting particular kinds of neurotransmitters and receptors which facilitate
synaptic plasticity. This biological interpretation is suggested by some of Lamme’s arguments (and
was suggested to us by Lamme in personal communication): Lamme (2010) argues that there could
be a “fundamental neural difference” between feedforward and recurrent processing in the brain
and that we should expect consciousness to be associated with a “basic neural mechanism”. We set
this interpretation aside because if some particular, biologically-characterised neural mechanism is
necessary for consciousness, artificial systems cannot be conscious.
Second, RPT may be understood as a theory only of visual consciousness, which makes no
commitments about what is necessary or sufficient for consciousness more generally. On this
interpretation, RPT would leave open both: (i) whether non-visual conscious experiences require
similar processes to visual ones, and (ii) whether some further background conditions, typically
met in humans but not specified by the theory, must be met even for visual consciousness. This
interpretation of the theory is reasonable given that the theory has not been extended beyond vision
and that it is doubtful whether activity in visual brain areas sustained in vitro would be sufficient for
consciousness (Block 2005). But on this interpretation, RPT would have very limited implications
for AI.
2.2
Global Workspace Theory
2.2.1
Introduction to global workspace theory
The global workspace theory of consciousness (GWT) is founded on the idea that humans and
other animals use many specialised systems, often called modules, to perform cognitive tasks
22
of particular kinds. These specialised systems can perform tasks efficiently, independently and
in parallel. However, they are also integrated to form a single system by features of the mind
which allow them to share information. This integration makes it possible for modules to operate
together in co-ordinated and flexible ways, enhancing the capabilities of the system as a whole.
GWT claims that one way in which modules are integrated is by their common access to a “global
workspace”—a further “space” in the system where information can be represented. Information
represented in the global workspace can influence activity in any of the modules. The workspace
has a limited capacity, so an ongoing process of competition and selection is needed to determine
what is represented there.
GWT claims that what it is for a state to be conscious is for it to be a representation in the
global workspace. Another way to express this claim is that states are conscious when they are
“globally broadcast” to many modules, through the workspace. GWT was introduced by Baars
(1988) and has been elaborated and defended by Dehaene and colleagues, who have developed
a neural version of the theory (Dehaene et al. 1998, 2003, Dehaene & Naccache 2001, Dehaene
& Changeux 2011, Mashour et al. 2020). Proponents of GWT argue that the global workspace
explains why some privileged subset of perceptual (and other) representations are available at
any given time for functions such as reasoning, decision-making and storage in episodic memory.
Perceptual representations get stronger due to the strength of the stimulus or are amplified by
attention because they are relevant to ongoing tasks; as a result, these representations “win the
contest” for entry to the global workspace. This allows them to influence processing in modules
other than those that produced them.
The neural version of GWT claims there is a widely distributed network of “workspace neurons”, originating in frontoparietal areas, with activity in this network, which is sustained by recurrent processing, constituting conscious representations. When perceptual representations become
sufficiently strong, a process called “ignition” takes place in which activity in the workspace neurons comes to code for their content. Ignition is a step-function, so whether a given representation
is broadcast, and, therefore, conscious, is not a matter of degree.
GWT is typically presented as a theory of access consciousness—that is, of the phenomenon
that some information represented in the brain, but not all, is available for rational decision-making.
However, it can also be interpreted as a theory of phenomenal consciousness, motivated by the
thought that access consciousness and phenomenal consciousness may coincide, or even be the
same property, despite being conceptually distinct (Carruthers 2019). Since our topic is phenomenal consciousness, we interpret the theory in this way. It is notable that although GWT does
not explicitly require agency, it can only explain access consciousness if the system is a rational
agent since access consciousness is defined as availability for rational control of action (we discuss
agency in section 2.4.5)
23
Figure 2: Global Workspace. The figure used by Dehaene et al. (1998) to illustrate the basic idea
of a global workspace. Note that broadcast to a wide range of consumer systems such as planning,
reasoning and verbal report does not feature in the figure. 1998. National Academy of Sciences.
Reprinted with permission.
2.2.2
Evidence for global workspace theory
There is extensive evidence for global workspace theory, drawn from many studies, of which we
can mention only a few representative examples (see Dehaene 2014 and Mashour et al. 2020
for reviews). These studies generally employ the method of contrastive analysis, in which brain
activity is measured and a comparison is made between conscious and unconscious conditions,
with efforts made to control for other differences. Various stimuli and tasks are used to generate
the conscious and unconscious conditions, and activity is measured using fMRI, MEG, EEG, or
single-cell recordings. According to GWT advocates, these studies show that conscious perception
is associated with reverberant activity in widespread networks which include the prefrontal cortex
(PFC)—this claim contrasts with the “local” character of RPT discussed above—whereas unconscious states involve more limited activity confined to particular areas. This widespread activity
seems to arise late in perceptual processing, around 250-300ms after stimulus onset, supporting the
claim that global broadcast requires sustained perceptual representations (Mashour et al. 2020).
24
Examples of recording studies in monkeys that support a role for PFC in consciousness include
experiments by Panagiotaropoulos et al. (2012) and van Vugt et al. (2018). In the former study,
researchers were able to decode the presumed content of conscious experience during binocular
rivalry from activity in PFC (Panagiotaropoulos et al. 2012). In this study the monkeys viewed
stimuli passively—in contrast with many studies supporting GWT—so the results are not confounded by behavioural requirements (this was a no-report paradigm; see sections 1.2.2 and 2.1.2).
In the latter, activity was recorded from the visual areas V1 and V4 and dorsolateral PFC, while
monkeys performed a task requiring them to respond to weak visual stimuli with eye movements.
The monkeys were trained to move their gaze to a default location if they did not see the stimulus
and to a different location if they did. Seen stimuli were associated with stronger activity in V1
and V4 and late, substantial activity in PFC. Importantly, while early visual activity registered the
objective presence of the stimulus irrespective of the animal’s response, PFC activity seemed to
encode the conscious percept, as this activity was also present in false alarms—cases in which
monkeys acted as though they had seen a stimulus even though no stimulus was present. Activity
associated with unseen stimuli tended to be lost in transmission from V1 through V4, to PFC.
Studies on humans using different measurement techniques have similarly found that conscious
experience is associated with ignition-like activity patterns and decodability from PFC (e.g. Salti
et al. 2015).
2.2.3
Indicators from global workspace theory
We want to identify the conditions which must be met for a system to be conscious, according
to GWT, because these conditions will be indicators of consciousness in artificial systems. This
means that a crucial issue is exactly what it takes for a system to implement a global workspace.
Several authors have noted that it is not obvious how similar a system must be to the human
mind, in respect of its workspace-like features, to have the kind of global workspace that is sufficient, in context, for consciousness (Bayne 2010, Carruthers 2019, Birch 2022b, Seth & Bayne
2022). There are perhaps four aspects to this problem. First, workspace-like architectures could be
used with a variety of different combinations of modules with different capabilities; as Carruthers
(2019) points out, humans have a rich and specific set of capabilities that seem to be facilitated
by the workspace and may not be shared with other systems. So one question is whether some
specific set of modules accessing the workspace is required for workspace activity to be conscious. Second, it’s unclear what degree of similarity a process must bear to selection, ignition and
broadcasting in the human brain to support consciousness. Third, it is difficult to know what to
make of possible systems which use workspace-like mechanisms but in which there are multiple
workspaces—perhaps integrating overlapping sets of modules—or in which the workspaces are
not global, in the sense that they do not integrate all modules. And fourth, there are arguably two
stages involved in global broadcast—selection for representation in the workspace, and uptake by
consumer modules—in which case there is a question about which of these makes particular states
conscious.
Although these questions are difficult, it is possible that empirical evidence could be brought to
bear on them. For example, studies on non-human animals could help to identify a natural kind that
includes the human global workspace and facilitates consciousness-linked abilities (Birch 2020).
Reflection on AI can also be useful here because we can recognise functional similarities and dis25
similarities between actual or possible systems and the hypothesised global workspace, separately
from the range of modules in the system or the details of neurobiological implementation, and thus
develop a clearer sense of the possible functional kinds in this area.
Advocates of GWT have argued that the global workspace facilitates a range of functions in
humans and other animals (Baars 1988, Shanahan 2010). These include making it possible for
modules to exert ongoing control over others for the duration of a task (e.g. in the case of searching
for a face in a crowd), and dealing with novel stimuli by broadcasting information about them,
thus putting the system in a position to learn the most effective response. Global broadcast and
the capacity to sustain a representation over time, while using it to process incoming stimuli,
are necessary for these functions. Because the global workspace requires that information from
different modules is represented in a common “language”, it also makes it possible to learn and
generate crossmodal analogies (VanRullen & Kanai 2021, Goyal et al. 2022). A particularly
sophisticated and notable possible function of the global workspace is “System 2 thought”, which
involves executing strategies for complex tasks in which the workspace facilitates extended and
controlled interactions between modules (Kahneman 2011, VanRullen & Kanai 2021, Goyal &
Bengio 2022). For example, planning a dinner party may involve engaging in an extended process,
controlled by this objective, of investigative actions (looking to see what is in the fridge), calls to
episodic memory, imagination in various modalities (how the food will taste, how difficult it will
be to cook, how the guests will interact), evaluation and decision-making. In this case, according
to the theory, the workspace would maintain a representation of the goal, and perhaps compressed
summaries of interim conclusions, and would pass queries and responses between modules.
We argue that GWT can be expressed in four conditions of progressively increasing strength.
Systems that meet more of these conditions possess more aspects of the full global workspace
architecture and are, therefore, better candidates for consciousness.
The first condition is possessing specialised systems which can perform tasks in parallel. We
call these systems “modules”, but they need not be modules in the demanding sense set out by
Fodor (1983); they need not be informationally encapsulated or use dedicated components of the
architecture with functions assigned prior to training. Mashour et al.’s recent statement of the
global neuronal workspace hypothesis claims only that modules in which unconscious processing takes place are localised and specialised, and that they process “specific perceptual, motor,
memory and evaluative information” (2020, p. 777). It may be that having more independent
and differentiated modules makes a system a better candidate for consciousness, but GWT is most
plausibly interpreted as claiming that what matters for consciousness is the process that integrates
the modules, rather than their exact characteristics. The first indicator we draw from this theory is,
therefore:
GWT-1: Multiple specialised systems capable of operating in parallel (modules)
Building on this, a core condition of GWT is the existence of a bottleneck in information flow
through the system: the capacity of the workspace must be smaller than the collective capacity of
the modules which feed into it. Having a limited capacity workspace enables modules to share
information efficiently, in contrast to schemes involving pairwise interactions such as Transformers, which become expensive with scale (Goyal et al. 2022, Jaegle et al. 2021a). The bottleneck
also forces the system to learn useful, low-dimensional, multimodal representations (Bengio 2017,
26
Goyal & Bengio 2022). With the bottleneck comes a requirement for an attention mechanism that
selects information from the modules for representation in the workspace. This yields our second
indicator:
GWT-2: Limited capacity workspace, entailing a bottleneck in information flow and a
selective attention mechanism
A further core condition is that information in the workspace is globally broadcast, meaning
that it is available to all modules. The two conditions we have seen so far are not enough to
ensure that ongoing interaction between modules is possible, or that information in the workspace
is available to multiple output modules which can use it for different tasks. Our third indicator is,
therefore:
GWT-3: Global broadcast: availability of information in the workspace to all modules
This entails that all modules must be able to take inputs from the global workspace, including those modules which process inputs to the system as a whole. The first two conditions can
be satisfied by wholly feedforward systems which have multiple input modules, feeding into a
limited-capacity workspace, from which information then flows on to one or more output modules. But this new condition entails that information must also flow back from the workspace to
the input modules, influencing their processing. In turn, this means that the input modules must be
(algorithmically) recurrent—and thus provides further justification for indicator RPT-1—although
output modules, which map workspace states to behaviour, need not be recurrent.
Finally, for the workspace to facilitate ongoing, controlled interactions between modules it
must have one further feature. This is that the selection mechanism that determines information
uptake from the modules must be sensitive to the state of the system, as well as to new inputs. That
is, the system must implement a form of “top-down attention” as well as “bottom-up attention”.
This allows representations in the workspace itself or in other modules to affect which information
is selected from each module. State-dependent selection can be readily implemented by systems
that meet GWT-3 because global broadcast entails that information flows from the workspace to the
modules. Generating controlled, functional interactions between modules, however, will require
that the system as a whole is suitably trained. Our fourth indicator is:
GWT-4: State-dependent attention, giving rise to the capacity to use the workspace to
query modules in succession to perform complex tasks
Compared to other scientific theories of consciousness, many more proposals have been made
for the implementation of GWT in artificial systems (e.g. Franklin & Graesser 1999, Shanahan
2006, Bao et al. 2020). We discuss implementations of GWT, together with other theories, in
section 3.1.
27
Box 3: Attention in neuroscience and in AI
The fields of neuroscience and machine learning each have their own distinct concepts of
attention (Lindsay 2020). In machine learning, several different forms of attention have been
developed, but at present, the most common is “self-attention” (Vaswani et al. 2023). This
is the mechanism at the heart of Transformer networks, which power large language models.
In self-attention, representations of elements of an
input sequence (for example, words in a sentence)
are allowed to interact multiplicatively. Specifically,
each word representation, that is given as a vector
is transformed into three new vectors: a query, key,
and value. The query vector of one word is multiplied
by the key vectors of all other words to determine a
weighting for each of these words. This weighting
is applied to the value vectors of these words; the
sum of these weighted value vectors forms the new
representation of the word. This process is done in
parallel for all words.
“Cross-attention” follows a similar formula but allows the query to be generated from one set of representations and the key and values to come from
another (self-attention and cross-attention are both
forms of “key-query attention”). This can be helpful, for example, in translation networks that use the
words of the sentence being generated in the target language to guide attention toward the
appropriate words of the sentence in the original language.
Key-query attention has only loose connections to how attention is conceptualised in neuroscience. Similar to self-attention, gain modulation (wherein attention multiplicatively
scales neural activity) has been found in many neural systems (Treue & Trujillo 1999,
Reynolds & Heeger 2009). However, this attentional modulation is frequently thought to
arise from recurrent top-down connections, not from the parallel processing of concurrent
inputs (Noudoost et al. 2010, Bichot et al. 2015). Previous versions of attention in machine
learning have relied on recurrent processing, and in this way could be considered more similar to biological attention (Mnih et al. 2014, Bahdanau et al. 2014). However, it should be
noted that there are many different flavors of attention within neuroscience and the underlying neural mechanisms may vary across them. Therefore, saying definitively which forms
of artificial attention are closest to biological attention in general, is not straightforward.
Insofar as different theories of consciousness depend on recurrent processing or other specific components of the attention mechanism, self-attention may not be sufficient to form
the basis of artificial consciousness. For example, there is nothing akin to the binary ignition process in global workspace theory in self-attention, as attention is implemented as a
graded weighting of inputs. There is also no built-in model of the attention process on top
of attention itself, as required in attention schema theory.
28
2.3
Higher-Order Theories
2.3.1
Introduction to higher-order theories
The core claim of higher-order theories of consciousness is helpfully distilled by Brown et al.
(2019):
The basic idea . . . is that conscious experiences entail some kind of minimal inner awareness of one’s ongoing mental functioning, and this is due
to the first-order state being in some ways monitored or meta-represented
by a relevant higher-order representation. (p. 755)
Higher-order theories are distinguished from others by the emphasis that they place on the idea
that for a mental state to be conscious the subject must be aware of being in that mental state, and
the way in which they propose to account for this awareness. This is accounted for by an appeal to
higher-order representation, a concept with a very specific meaning. Higher-order representations
are ones that represent something about other representations, whereas first-order representations
are ones that represent something about the (non-representational) world. This distinction can be
applied to mental states. For example, a visual representation of a red apple is a first-order mental
state, and a belief that one has a representation of a red apple is a higher-order mental state.
Higher-order theories have long been advocated by philosophers (Carruthers & Gennaro 2020,
Rosenthal 2005). One of the main motivations for the view is the so-called “simple argument”
(Lycan 2001): if a mental state is conscious, the subject is aware that they are in that state; being
aware of something involves representing it; so consciousness requires higher-order representation
of one’s own mental states. The substantive commitment of this argument is that there is a single
sense of “awareness” of mental states on which both premises are true—which is both weak enough
that consciousness entails awareness of mental states, and strong enough that this awareness entails
higher-order representation. In the last two decades, higher-order theories have been elaborated,
refined and tested by neuroscientists, and influenced by new experimental methods and ideas from
the study of metacognition, signal detection theory, and the theory of predictive processing.
A variety of higher-order theories have been proposed, which describe distinct forms of monitoring or meta-representation, and imply different conditions for consciousness (Brown et al.
2019). They include: several philosophical theories, including higher-order thought theory (Rosenthal 2005) and higher-order representation of a representation theory (Brown 2015); the selforganising meta-representational account (Cleeremans et al. 2020); higher-order state space theory
(Fleming 2020); and perceptual reality monitoring theory (Lau 2019, 2022, Michel forthcoming).
We will concentrate on perceptual reality monitoring theory (PRM) and to some degree also the
closely-related higher-order state space theory (HOSS). These are both recent computational theories based on extensive assessments of neuroscientific evidence.
The core claim of PRM is that consciousness depends on a mechanism for distinguishing meaningful activity in perceptual systems from noise. There are multiple possible sources of neural
activity in perceptual systems. This activity could be caused by perceptible stimuli in the environment; it could be sustained after these stimuli have passed; it could be generated top-down
29
through expectations, imagination, dreaming or episodic memory; or it could be due to random
noise. PRM claims that a “reality monitoring” mechanism, which operates automatically, is used
to discriminate between these different kinds of activity and assess the reliability of first-order representations. Perceptual representations are conscious when they are identified as reliable, or in
other words, as being sufficiently different from noise.
Meanwhile, HOSS makes the similar claim that “awareness is a higher-order state in a generative model of perceptual contents” (Fleming 2020, p. 2). This higher-order state, which is the
product of a metacognitive inference, signals the probability that some particular content is represented in the perceptual system. This is presented as a theory of the basis of awareness reports
(i.e. reports of the form “I am/not aware of X”), but Fleming suggests that higher-order awareness
states are necessary for consciousness.
2.3.2
Computational HOTs and GWT
Computational higher-order theories are sometimes grouped together with GWT as “global” theories, in opposition to “local” theories such as RPT (Michel & Doerig 2022). Like GWT, higherorder theories such as PRM claim that cognitive functions supported by the prefrontal cortex play
an important role in consciousness. As such, the evidence reviewed above in favour of the involvement of the PFC in consciousness supports PRM as well as GWT. PRM also claims, again
like GWT, that “consciousness is the gating mechanism by which perception impacts cognition; it
selects what perceptual information should directly influence our rational thinking” (Lau 2022, p.
159). Lau (2022) endorses the existence of global broadcast as a phenomenon in the brain, and also
affirms that it is related to consciousness: when representations are conscious, “global broadcast
and access” of that representation “are likely to happen” (p. 159).
However, higher-order theorists reject the claim that broadcast in the global workspace is necessary and sufficient for consciousness. Notably, according to higher-order theories, unconscious
representations can be encoded in the global workspace, which implies that a representation might
be unconscious and yet available for high-level cognitive processes, such as reasoning. Higherorder theories and GWT make distinct predictions, and advocates of computational HOTs appeal
to experiments testing these predictions as providing important evidence in favour of their view.
In one such experiment, Lau and Passingham (2006) conducted a visual discrimination task
under a range of different masking conditions and asked participants to press a key to indicate
whether they had seen or merely guessed the shape of the stimulus in each trial. They identified
two different masking conditions in which participants’ ability to discriminate between stimuli
was at the same level, but differed in how likely they were to report having seen the stimulus.
Higher-order theorists interpret this result as showing that there can be a difference in conscious
perception of a stimulus without a corresponding difference in task performance, and claim that
this result is inconsistent with a prediction of GWT (Lau & Rosenthal 2011). This purported prediction of GWT is that differences in consciousness should entail differences in task performance,
because—according to GWT—consciousness makes information available to a wide range of cognitive functions, useful across a wide range of tasks. Furthermore, according to GWT, ignition
leading to global broadcast is necessary and sufficient for consciousness, and ignition depends on
the same factors which affect visual task performance, such as signal strength and attention.
30
The broader argument here is that evidence for GWT is confounded by differences in performance between conscious and unconscious conditions (Morales et al. 2022). Ignition leading
to global broadcast is correlated with better performance on many tasks, and in the absence of
controls, better performance is also correlated with consciousness. But since experiments seem
to show that performance and consciousness are dissociable, it is possible that ignition is neither
necessary nor sufficient for consciousness (Fleming 2020, Lau 2022).
2.3.3
Indicators from computational HOTs
As we have seen, PRM claims that perceptual states are conscious when they are identified as
reliable by a metacognitive monitoring mechanism. This mechanism outputs higher-order representations which label first-order states as accurate representations of reality. Similarly, HOSS
claims that consciousness depends on higher-order awareness states directed at perceptual representations. Therefore, these two theories both suggest that metacognitive monitoring of perceptual
systems with relevant properties is necessary for consciousness in AI.
We propose two indicators based on this claim:
HOT-1: Generative, top-down or noisy perception modules
HOT-2: Metacognitive monitoring distinguishing reliable perceptual representations
from noise
HOT-1 is an indicator of consciousness because, according to computational HOTs, the function of the monitoring mechanisms which are responsible for consciousness is to discriminate
between different sources of activity in perceptual systems. This means that consciousness is more
likely in systems in which there are multiple possible sources of such activity. Examples of such
systems include ones in which perceptual representations can be produced top-down in imagination, as well as ones affected by random noise. HOT-2 is a statement of the main necessary
condition for consciousness according to computational HOTs.
Lau (2022) suggests that generative adversarial networks (GANs) may possess these two indicators, a possibility which we discuss further in section 3.1.3. However, PRM advocates claim
that current AI systems do not meet the conditions of their theory (Michel & Lau 2021, Lau 2022).
They emphasise that perceptual reality monitoring systems must have a further feature: in addition to discriminating between perceptual states, a perceptual reality monitoring mechanism must
output to a system for “general belief-formation and rational decision-making” (Michel & Lau
2021). This condition is justified on the grounds that conscious experience has a certain “assertoric force”. Some of our conscious perceptual experiences present themselves to us as accurate
impressions of the outside world, and it is difficult for us to resist believing that things are as these
experiences represent them.9 Even if we believe that we are subject to an illusion, an impression that our conscious experience is representing the world as it is remains—knowing about the
9
Imaginative experiences are an exception, but PRM can claim that they are classified differently by the reality
monitoring mechanism, and, therefore, have a different phenomenal character. Alternatively, higher-order theories
like HOSS and PRM can hold that imaginative experiences have some minimal amount of assertoric force, thus
explaining results in which participants are more likely to report a target as visible if it is congruent with their mental
imagery (Dijkstra et al. 2021, 2022; Dijkstra & Fleming 2023).
31
Müller-Lyer illusion does not prevent the two lines from looking unequal. Such experiences are
persistent inputs to cognition, which are not under direct cognitive control.
Another aspect of this idea is that what makes it the case that the monitoring mechanism labels
some perceptual contents as “real” is that the person or system as a whole tends to take them
to be real when they are so labelled. This entails that the system which includes the monitoring
mechanism must be an agent which relies on perceptual representations tagged as “real” when
selecting actions. The function of the reality monitoring mechanism, then, is to identify which
perceptual states are accurate enough to be relied on in this way. Advocates of PRM propose that
to rely on perceptual content is a matter of believing that content—given their picture of belief, this
implies a system for reasoning and action selection with a holistic character, in which any belief
can in principle be called on in examining any other or in reasoning about what to do. These claims
give us our third indicator arising from HOTs:
HOT-3: Agency guided by a general belief-formation and action selection system, and
a strong disposition to update beliefs in accordance with the outputs of metacognitive
monitoring
Computational HOTs also make a further claim which yields a fourth indicator. Like most
scientific theories of consciousness, PRM aims to answer the question “what makes a state conscious, rather than unconscious?” However, it also attempts to answer the further question “why
do conscious mental states feel the way they do?” Its answer to this second question appeals to
quality space theory, a view that claims that phenomenal qualities can be reduced to the discriminations they allow for the system (Clark 2000, Rosenthal 2010, Lau et al. 2022). For instance,
two features feel the same in virtue of the fact that, from the perspective of the system, they are
indiscriminable (Rosenthal 2010). According to this proposal, the subjective similarity of two experiences is the inverse of their discriminability, and the experience of subjective qualities depends
on implicit knowledge of the similarity space. As such, quality space theory provides a functional
account of qualities (see Lau et al. 2022). For example, to have a conscious experience of the red
colour of a tulip one must have an implicit grasp of its similarity to the colour of a red apple and its
discriminability from the green of a new leaf. One hypothesis is that this implicit knowledge depends on sparse and smooth coding in perceptual systems—that is, on qualities being represented
by relatively few neurons, and represented according to a continuous coding scheme rather than
one which divides stimuli into absolute categories (Lau et al. 2022).
Importantly, PRM claims that consciousness is not possible without qualities, so although quality space theory is not a theory of what makes a state conscious, the posits of this theory are putative
necessary conditions for consciousness. Our final indicator arising from HOTs is, therefore:
HOT-4 Sparse and smooth coding generating a “quality space”
This condition may be relatively readily met in AI: all deep neural networks use smooth representation spaces, and sparseness can also be achieved by familiar machine learning techniques
(see section 3.1.3).
32
2.4
Other Theories and Conditions
Many scientific theories of consciousness have been proposed (see Seth & Bayne 2022 for a list).
In addition, there are influential theoretical proposals that are not exactly theories of consciousness, but which bear on our investigation. Furthermore, there may be necessary conditions for
consciousness that are not explicitly emphasised in scientific theories because all humans meet
them (such as having a body), but which need to be considered in the context of AI. In this section,
we survey several relevant theories, proposals and conditions, before presenting our indicators in
section 2.5.
One theory that we do not discuss below is integrated information theory (IIT; Oizumi et al.
2014, Tononi & Koch 2015). The standard construal of IIT is incompatible with our working
assumption of computational functionalism; Tononi & Koch (2015) hold that a system that implemented the same algorithm as the human brain would not be conscious if its components were of
the wrong kind. Relatedly, proponents of IIT claim that the theory implies that digital computers are unlikely to be conscious, whatever programs they run (Albantakis & Tononi 2021). As a
result, in contrast to other scientific theories, IIT does not imply that some AI systems built on
conventional hardware would be better candidates for consciousness than others; this makes it less
relevant to our project. It has recently been proposed that measures of information integration
may be correlated with “global states of consciousness” such as wakefulness, sleep and coma—a
paradigm called “weak IIT” (Michel & Lau 2020, Mediano et al. 2022). But the implications of
weak IIT for our project are limited: it suggests that measurable properties of integration and differentiation matter for consciousness, but does not (yet) tell us which measures to rely on or how
to interpret their results when applied to artificial systems.
2.4.1
Attention Schema Theory
The attention schema theory of consciousness (AST) claims that the human brain constructs a
model of attention, which represents—and may misrepresent—facts about the current objects of
attention. This model helps the brain to control attention, in a similar way to how the body schema
helps with control of bodily movements. Conscious experience depends on the contents of the
attention schema. For example, I will have the conscious experience of seeing an apple if the
schema represents that I am currently attending to an apple (Webb & Graziano 2015, Graziano
2019a). Attention schema theory claims that the workings of the attention schema explain our
intuitions about our experiences: because the attention schema does not represent the details of the
mechanism of attention, the theory claims, it seems to us that we are related to the stimulus (e.g.
an apple) in an immediate and seemingly mysterious way.
AST can be thought of as a higher-order theory of consciousness because it claims that consciousness depends on higher-order representations of a particular kind (in this case, representations of our attention). Like other higher-order theories, it places special emphasis on our awareness of our own mental states. Unlike most higher-order theories, however, AST has been developed with the specific aim of explaining what we believe and say about consciousness, such as
that we are conscious and that consciousness seems difficult to square with physical descriptions
of the world (that is, AST aims to solve the meta-problem of consciousness—see Chalmers 2018,
33
Graziano 2019b). Because it focuses on explaining why we (potentially mistakenly) believe certain
things about consciousness, AST could be construed as an attempt to explain away consciousness.
But it is also open to interpretation as an account of the conditions for consciousness.
AST gives us a further indicator of consciousness in AI:
AST-1: A predictive model representing and enabling control over the current state of
attention
Representing the current state of attention allows the mind to learn about both the effects of
attention and how attention is affected by events in the mind and the environment. Having a model,
therefore, makes it easier for the mind to learn to take attention-affecting actions because they will
have beneficial effects on other cognitive processes. A predictive model is especially valuable because it allows the mind to anticipate how the objects of attention might change, conditional on
changes in the mind or the environment, and make adjustments accordingly. These could include
preemptive adjustments, for instance when distraction from an important task is anticipated. Attention schema-like models which enable the effective control of attention could be valuable for
the increasing number of AI systems which employ attention—here understood as active control
of information flow (Liu et al. 2023).
2.4.2
Predictive Processing
Predictive processing (PP) is presented as a comprehensive, unifying theory of human cognition,
and has been used as a framework for addressing many questions about the mind. Because it is
a general framework, some PP theorists describe it as a theory for consciousness, not a theory
of consciousness (Seth & Hohwy 2021, Seth & Bayne 2022)—a paradigm within which theories
of consciousness should be developed. However, advocates of PP have used it to explain many
specific features of conscious experience, such as the puzzling nature of “qualia” (Clark 2019) and
the phenomenology of emotion and embodiment (Seth 2021). Consciousness has been discussed
extensively by PP theorists, but relatively little direct attention has been given to the questions
which are most important for our purposes: what distinguishes conscious from non-conscious
systems, and what distinguishes conscious from non-conscious states within conscious systems
(Deane 2021, Hohwy 2022, Nave et al. 2022).
PP claims that the essence of human and animal cognition is minimisation of errors made by a
hierarchical generative model in predicting sensory stimulation. In perception, this model is continually generating predictions at multiple levels, each influenced by predictions at neighbouring
levels and in the immediate past, and by prediction error signals which ultimately arise from sensory stimulation itself. This process is modulated by attention, and—according to the thesis of
‘active inference’—it can also control action because acting can be a means of reducing prediction
error. Adaptive actions will be selected if organisms predict their own success (Friston 2010).
Although PP is not a theory of consciousness, its popularity means that many researchers regard
predictive processing as a plausible necessary condition for consciousness. We, therefore, include
the use of predictive coding among our indicators:
PP-1 Input modules using predictive coding
34
In keeping with the “theory for consciousness” idea, the PP framework has been employed in
developments of GWT and HOT. Hohwy (2013) and Whyte (2019) propose that global broadcast
(via ignition) takes place when the process of perceptual inference settles on some representation
of the state of the environment as most probable, then makes this representation available as the
basis for active inference. Meanwhile, the higher-order state space theory adopts the PP framework
(Fleming 2020).
2.4.3
Midbrain Theory
While the neuroscientific theories of consciousness we have discussed so far focus primarily on
cortical processes, Merker (2007) argues that the cortex is not necessary for consciousness. This
view has been particularly influential in recent discussions of consciousness in non-human animals. Merker’s proposal is that activity in parts of the midbrain and basal ganglia constitute a
“unified multimodal neural model of the agent within its environment, which is weighted by the
current needs and state of the agent” (Klein & Barron 2016), and that this activity is sufficient for
subjective experience. In Merker’s account, one midbrain region, the superior colliculus, integrates
information from spatial senses and the vestibular system to construct a model of the organism’s
position and movement in space. Other regions including the hypothalamus, periaqueductal gray,
and parts of the basal ganglia bring in information about the organism’s physiological state and
contribute to identifying opportunities and selecting actions. In functional terms, the midbrain
theory claims that consciousness depends on “integrated spatiotemporal modeling” for action selection (Klein & Barron 2016).
Birch (2022b) summarises and criticises evidence for the midbrain theory. For our purposes,
it is notable because it offers a particular perspective on the significance of cognitive integration
for consciousness. The midbrain theory proposes that the integration which is necessary for consciousness arose to solve the biologically ancient problem of decision-making in complex mobile
animals, particularly the need to distinguish the effects of self-caused motion on perceptual input
(Merker 2005). Hence the midbrain theory emphasises the need to integrate specific kinds of information, such as spatial, affective, and homeostatic information, into a single common model.
This theory, therefore, gives us additional reason to believe that systems for purposeful navigation
of a body through space are necessary for consciousness, and thus contribute to the case for the
indicators we present in section 2.4.5.
2.4.4
Unlimited Associative Learning
Another influential theory in animal consciousness literature is Ginsburg and Jablonka’s (2019)
unlimited associative learning framework (Birch et al. 2020). The proposal here is that the capacity
for unlimited associative learning (UAL) is an evolutionary “transition marker” for consciousness:
a single feature that indicates that an evolutionary transition to consciousness has taken place in a
given lineage. Ginsburg and Jabolanka identify UAL as a marker on the grounds that it requires
a combination of several “hallmarks” that are argued to be jointly sufficient for consciousness in
living organisms. The UAL framework, therefore, brings together a list of features that seem to be
related to consciousness and argues that they are unified by facilitating UAL.
35
Somewhat like this report, the UAL project aims to identify a set of jointly sufficient conditions
for consciousness. This set is summarised in the table below (which follows the presentation of
these conditions in Birch et al. 2020).
Hallmarks of consciousness according to UAL
Global accessibility integrating sensory, evaluative and mnemonic information
Selective attention
Integration over time through forms of short-term memory
Embodiment and agency
Self-other registration, used in constructing a representation of the moving
body in space
Flexible value system capable of revaluation and weighing needs
Binding/unification of features to form compound stimuli, enabling discrimination of complex patterns
Intentionality, i.e. representation of the body and environment
This list of conditions is similar to the conditions which are emerging from our work in this
section (like us, Ginsburg and Jablonka examined scientific theories of consciousness in developing
their list). The global accessibility and selective attention conditions are met by systems that
implement global workspace architectures. The integration over time condition may be as well; we
discuss integration over time in section 2.4.6. Several of the other conditions are related to agency
and embodiment, which we discuss in section 2.4.5. These include not only the embodiment
and agency condition itself but also self-other registration (which also aligns with the midbrain
theory) and having a flexible value system. We take it that the binding/unification condition will
be met by any neural network-based AI system because these systems are designed to learn to
discriminate complex patterns. The final condition, that the system should represent its body and
the environment, raises philosophical questions about intentionality which we will not go into
here. But any naturalistic theory of intentionality is likely to entail that systems that meet the
other conditions will also meet this one because the other conditions entail the performance of the
functions which might ground intentionality.
What about the capacity for unlimited associative learning itself? This could be argued to be
an indicator of consciousness in artificial systems. In the UAL framework, it is characterised as
an open-ended capacity for associative learning. In particular, to have this capacity an organism
must be capable of conditioning with compound stimuli and novel stimuli and of quickly and
flexibly updating the values it associates with stimuli, actions and outcomes. It must also be capable
of second-order conditioning, meaning that it can link together chains of associations, and trace
conditioning, which is learning an association when there is a time gap between stimuli. Having
the capacity for unlimited associated learning, therefore, implies that an organism or system can
integrate information across modalities and over time, and that can evaluate stimuli and change
these evaluations in response to new information.
This capacity is also, therefore, linked to many of our indicators. Integration of information
from different modalities and flexible learning are emphasised by GWT. PRM also suggests similar capacities by requiring a general-purpose belief-formation and decision-making system, which
receives input from any sensory modality subject to metacognitive monitoring. Evaluation and
36
evaluative learning are closely connected with agency. AI systems that combine agency with indicators implying integration and flexibility may be particularly good candidates for consciousness,
because they will share notable cognitive capacities with the animals which are, according to UAL,
most likely to be conscious. Furthermore, having an architecture of the kind described by either
GWT or PRM is perhaps particularly good evidence for consciousness if it facilitates flexible
learning.
However, it is possible that the capacity for unlimited associative learning could be achieved in
AI systems in different ways—using architectures that are both unlike those described by theories
like GWT, and unlike those belonging to animals that share this capacity. These systems might
have this capacity while lacking some of the hallmarks of consciousness identified by Ginsburg
and Jablonka. This would undermine the argument for consciousness in such systems, which is
a reason to doubt whether UAL itself is a good indicator for consciousness in artificial systems.
Another reason is that the status of the UAL hypothesis is very different from that of the other
theories we have considered: rather than claiming to identify the mechanism underlying conscious
experience, it claims to identify a behavioural marker for consciousness in living organisms. For
these reasons, we do not include the capacity for UAL in our list of indicators.
2.4.5
Agency and Embodiment
Current AI systems often relate to their environments in very different ways from humans and
other animals, and it can be argued that these differences are evidence against consciousness in
such systems. For example, consider the well-known image classifier AlexNet (Krizhevsky et
al. 2012), a relatively small and simple DNN trained by supervised learning. The beings which
we usually take to be conscious are very different from AlexNet: they are agents which pursue
goals and make choices; they are alive and have bodies; and they continually interact with the
environment in a way that involves storing and integrating information over short periods of time.
AlexNet, in contrast, has the function of classifying images but does not take actions or pursue
any goal. It is physically realised in the sense that the weights and other features which define it
are stored in physical memory devices, but it does not have a body. And it processes inputs that
are separated in time and independent of each other and its outputs in feedforward passes that do
not change its state. In this and the following section, we discuss whether further indicators of
consciousness can be identified among these “big-picture” differences between humans and some
AI systems.
As we will see in this section, scientists and philosophers have argued that various properties
related to agency and embodiment are necessary for consciousness. We survey some of these
arguments, identifying possible indicators, then discuss whether they can be formulated in ways
that are consistent with computational functionalism. We close the subsection by adding two more
indicators to our list.
2.4.5(a)
Agency
One argument for the claim that agency is necessary for consciousness is that this is implied by
many scientific theories. Most of the theories of consciousness we have discussed make some
37
reference to agency.
PRM is particularly clear that agency is a necessary condition for consciousness. PRM claims
that the subsystem that discriminates between sensory signals and noise must output to a “general
belief-formation and rational decision-making system” (Lau & Michel 2021). One of the foundational ideas on which the theory is built is that conscious perceptual experiences have an “assertoric
force” which may be explained either as a certain kind of persistence of the signal as an input to
this decision-making system or as a strong disposition to form corresponding beliefs. What distinguishes beliefs from other representations, on most philosophical accounts, is in part their use
in decisions about how to act (Stich 1978, Dretske 1988, Schwitzgebel 2021). We have already
formulated an indicator that expresses this aspect of PRM, but the point remains that agency is a
prerequisite for the functions cited in this theory.
The midbrain theory explicitly requires agency, since it claims that the function of the midbrain
is to integrate information for action selection, and GWT also emphasises agency, without being
quite so clear that it is necessary. Dehaene and Naccache (2001) claim that representation in the
global workspace is needed for information to be available for intentional action, in keeping with
their presentation of GWT as a theory of access consciousness, and, therefore, of the availability of
information for rational agency. The UAL hypothesis claims that “agency and embodiment” and a
“flexible value system” (Birch et al. 2020) are hallmarks of consciousness.
There are also independent arguments in philosophy that agency is necessary for consciousness
(Evans 1982, Hurley 1998, Clark & Kiverstein 2008). Hurley (1998) claims that consciousness
requires intentional agency, which she spells out as agency in which:
. . . [the system’s] actions depend holistically on relationships between what
it perceives and intends, or between what it believes and desires. Relations
between stimuli and responses are not invariant but reflect the rational relations between what it perceives and intends and various possibilities of
mistake or misrepresentation. (p. 137)
Hurley’s argument for this claim is related to the sensorimotor theory of consciousness and
theories of embodied and enactive cognition, which we explore further below. A key idea is that
consciousness requires a perspective or point of view on the environment, and embodied agency
can give rise to such a perspective. Hurley also argues that part of what it is to be conscious is
to have access to the contents of one’s conscious experiences and that this requires the ability to
act intentionally in the light of these contents. However, other philosophers argue that it is at least
conceptually possible that there could be conscious experience in entities that are entirely incapable
of action (Strawson 1994, Bayne et al. 2020).
There are three possible indicators of consciousness suggested by these considerations (in addition to indicator HOT-3, arising from PRM). These are: being an agent of any kind; having flexible
goals or values, as suggested by advocates of UAL; and being an intentional agent, as suggested
by Hurley. The latter two are strictly stronger conditions than the first, but that does not in itself
imply that any should be excluded. It could be that agents in general are significantly stronger
candidates for consciousness than non-agents, and intentional agents (say) are also significantly
stronger candidates than other agents, in which case agency and intentional agency would both be
38
useful indicators.
In their classic AI textbook, Russell and Norvig write that “an agent is anything that can be
viewed as perceiving its environment through sensors and acting upon that environment through
activators” (2010, p. 34). This is a very liberal definition of agency. AlexNet meets these conditions—in fact, all AI systems meet them—and so do many simple artifacts, such as thermostats.
So it is too liberal a notion of agency for our purposes.
A more substantive notion of agency can be defined by adding three conditions to Russell and
Norvig’s account. First, it is a plausible condition for agency that the system’s outputs affect its
subsequent inputs. Without this, a system can only respond to inputs individually, as opposed to
interacting with an environment. AlexNet does not meet this condition because, in general, the
labels it produces as output do not affect which images it is subsequently given as input. This
relates to the second condition, which is that agents pursue goals. We typically think of this as
involving ongoing interaction with an environment, in which outputs are selected because they
will bring the system closer to the goal—that is, they will change the environment state, affecting
their own input, so that the goal can be more readily achieved by future outputs.
The third condition is that the system must learn to produce goal-conducive outputs. This point
is emphasised by Dretske (1988, 1999), who argues that a system’s output is only an action if it is
explained by the system’s own sensitivity to the benefit of producing that output when receiving
a given input. A system’s being sensitive to benefits in this way is manifested in its learning
to produce beneficial outputs. Dretske’s idea is that this distinguishes some of the behaviour of
animals, which he thinks of as exhibiting agency, from the behaviour of plants, which have evolved
to respond to stimuli in particular ways, rather than learning to do so, and artefacts like thermostats,
which have been designed to produce particular responses. In a similar vein, Russell and Norvig
say that an agent lacks autonomy if its success depends on its designer’s prior knowledge of the
task (2010, p. 39).
Reinforcement learning (RL) research explicitly aims to build artificial agents which pursue
goals (Sutton & Barto 2018), and typical RL systems meet all three of these conditions. In RL,
the task is to maximise cumulative reward over an episode of interaction with an environment in
which the system’s outputs affect its subsequent inputs. So there is a strong case that typical RL
systems meet substantive criteria for agency (Butlin 2022, 2023).10 However, this is not to say that
RL is necessary for agency—there are other methods by which systems can learn from feedback
to more effectively pursue goals. It is also important to note that the criteria for agency suggested
here are relatively minimal.
According to UAL advocates, there are two senses in which agents’ goals or values can be flexible (Bronfman et al. 2016, Birch et al. 2020). One way is that the agent can be capable of learning
new goals, such as through classical conditioning, in which a novel stimulus can come to be valued
through association with one that the agent already values. The other is that the agent’s goals and
values can be sensitive to its changing needs, as in cases in which animals’ preferences change
depending on their homeostatic condition. A requirement for flexibility of either kind would be
somewhat stronger than the requirement for agency, although even very simple agents tend to be
capable of either classical conditioning or habit learning, in which new actions are reinforced.
10
A possible exception is so-called “bandit” systems, which learn from reward signals in environments in which outputs
do not affect subsequent inputs.
39
There are better arguments that the second form of flexibility is connected to consciousness: it
may require a centralised architecture in which multiple sources of value-relevant information are
integrated, and it would also mean that the motivational significance of states of different kinds,
relating to different goals or values, must be compared. One suggestion in the scientific and philosophical literature is that conscious valence—that is, the degree to which conscious experiences
are pleasurable or unpleasant—could constitute a “common currency” making such comparisons
possible (Cabanac 1992, Carruthers 2018). So it is arguably flexible responsiveness to competing
goals that is most compelling.
One way to spell out the idea of intentional agency, in which action depends on rational relations between belief-like and desire-like states, is through the distinction made in animal behaviour
research between “goal-directed” and “habitual” behaviour (Heyes & Dickinson 1990). In the goaldirected case, the animal can learn independently about the value of an outcome and about actions
that might lead to it. It can then combine this knowledge with information about other actions and
outcomes, in instrumental reasoning, to make a choice. Action, therefore, depends holistically on
the animal’s “beliefs” and “desires”. Computational neuroscience interprets goal-directed action
selection in animals as an implementation of model-based RL (Dolan & Dayan 2013). On this
understanding, the intentional agency which Hurley emphasises is similar to the form of agency
which is required by PRM. What matters for PRM is that the agent relies on the accuracy of a set
of representations that are belief-like in that they are used in instrumental reasoning for action selection. This gives reality-monitoring its function: accurate representations in perceptual systems,
caused by sensory stimulation, should be used to update this set, while representations without this
connection with reality should not.
2.4.5(b)
Embodiment
On both the minimal and intentional conceptions of agency, it seems possible for a system to be
an agent without being embodied. For example, consider AlphaGo, the first AI system to beat the
world’s best human Go players (Silver et al. 2016). AlphaGo was an agent but lacked the features
which seem to distinguish embodied systems. Embodied systems are located at particular positions
in their environments, and the actions and observations available to them are constrained by their
positions. They also typically have relatively complex effectors, which they must continuously
control over extended periods in order to perform effective actions. Their outputs are movements,
and these have some direct and systematic effects on their inputs—for example, turning one’s head
has a systematic effect on visual input—as well as less direct effects. These ideas are described in
a philosophical account of embodiment by Clark (2008, p. 207), who writes that:
. . . the body is . . . the locus of willed action, the point of sensorimotor
confluence, the gateway to intelligent offloading, and the stable (although
not permanently fixed) platform whose features and relations can be relied
upon (without being represented) in the computations underlying some
intelligent performances.
The point about “intelligent offloading” here is a reference to the thesis of embodied and extended cognition: embodied agents can exploit properties of their bodies and environments in many
40
ways to make the cognitive tasks they face more tractable, such as by recording information in the
environment.
One aspect of embodiment which is thought to be connected with consciousness is having what
Hurley (1998) calls a “perspective”. This also requires agency. According to Hurley,
Having a perspective means in part that what you experience and perceive
depends systematically on what you do, as well as vice versa. Moreover, it
involves keeping track . . . of the ways in which what you experience and
perceive depends on what you do. (p. 140)
For embodied agents that move through their environments, sensory inputs can change either
because the environment changes, or because the agent changes its position in the environment,
either actively or passively. To distinguish these cases, agents must keep track of their own active
movements, and learn how these affect inputs. This will allow them to predict the sensory consequences of their own actions, which will typically be tightly coupled to movements, and thus
distinguish them from exogenous changes in the environment. Passive movements can also be
distinguished because these will cause the kinds of changes in input which are characteristic of
movement in the absence of corresponding outputs. These functions involve the agent’s implicitly
distinguishing between a self, located in a moving body, and an environment in which its movement takes place. Consciousness arguably requires that the subject has a single perspective or point
of view on the environment, and this account aims to explain how embodied agency gives rise to
such a perspective (Hurley 1998, Merker 2005, Godfrey-Smith 2019).
Relatedly, according to the sensorimotor theory of perceptual consciousness, conscious experiences are activities of interaction with the environment which constitute exercises of implicit,
practical sensorimotor knowledge (Hurley 1998, O’Regan & Noë 2001, Noë 2004, Kiverstein
2007). A simple application of sensorimotor knowledge is moving one’s head in order to see an
object from a different perspective. Like Hurley’s proposal, this theory implies that learning a
model of output-input contingencies and using this model in perception is a necessary condition
for consciousness. The midbrain theory also suggests that consciousness is associated with the
presence of an integrated model of the embodied self in its environment, used in perception, action
selection and control.
However, to capture the idea of embodiment as opposed to mere agency, we need to specify
further features of the output-input model—which might also be called a “transition model” or a
“forward model”. AlphaGo, our example of a non-embodied agent, used a model of this form in
Monte Carlo tree search, a planning algorithm that involves evaluating the expected consequences
of possible actions.
One way in which output-input models in embodied systems may be distinctive is by representing the direct and systematic effects that movements have on sensory inputs. This condition
is not necessarily satisfied by Go-playing systems, because each of the inputs they receive may be
affected by their opponents’ moves. Furthermore, embodied systems may also be distinctive in the
way they use such models. The employment of an output-input model in perception to distinguish
endogenous from exogenous change is one possible example of a characteristic use because it is
required when sensory input depends on the position and orientation of a moving body.
41
A second way of using output-input models which may be distinctive of embodied systems is
in motor control. Embodied systems often have effectors with multiple degrees of freedom which
must be controlled in precise and responsive ways, and it has been argued that forward models
(as they are called in this literature) have several uses which are specific to this context (Miall
& Wolpert 1996, McNamee & Wolpert 2019). In particular, forward models can help embodied
agents to estimate and adjust the positions of their effectors in the course of action, by providing a
representation of the expected position at each moment. Discrepancies between these expectations
and either sensory feedback or internal representations of goal states could be used for online
adjustment.
In addition to agency and embodiment, a further possible necessary condition for consciousness
is that conscious systems must be self-producing, self-maintaining, “autopoietic” systems (Maturana & Varela 1991, Thompson 2005, 2007, Seth 2021, Aru et al. 2023). That is, they must sustain
their existence and organisation through their own ongoing activity. This feature is characteristic of
living things, which continually repair themselves and homeostatically regulate their temperatures
and the balance of chemicals present in their tissues. Self-maintaining activity usually, perhaps
always, involves “proto-cognitive” processes of sensing and responding (Godfrey-Smith 2016).
Advocates of this idea refer to concepts such as agency, selfhood and autonomy in arguing that
self-maintenance is necessary for consciousness. For instance, Thompson (2005) writes:
This self-producing organization defines the system’s identity and determines a perspective or point of view in relation to the environment. Systems organized in this way enact or bring forth what counts as information
for them; they are not transducers or functions for converting input instructions into output products. For these reasons, it is legitimate to invoke the
concepts of selfhood and agency to describe them. (p. 418)
Those who are also sympathetic to predictive processing, such as Seth (2021), think of selfmaintenance in living tissues as a similar process to prediction error minimisation in the brain—they
are both instances of free energy minimisation, or “self-evidencing” (Hohwy 2022). More prosaically, engaging in self-maintenance gives an extra reason for systems to model their own states,
is related to having flexible goals, and arguably adds a dimension of valence to representations of
the self and environment. On this last point, however, it is not clear why agency in the service of
self-maintenance should be distinguished from agency directed at “external” goals.
Building on this line of thought, Godfrey-Smith (2016) argues that self-maintaining activity is
only at all readily possible by virtue of the way that molecules behave at the nanometre scale when
immersed in water. There is continual random activity at this scale, in this context, which can be
marshalled to support metabolic processes. On this basis, Godfrey-Smith suggests that artificial
systems can only bear coarse-grained functional similarities to living organisms and that these will
not be sufficient for consciousness. So another proposed necessary condition is that a conscious
system must undergo metabolic processes realised at the nanoscale. Man and Damasio (2019) also
suggest that self-maintenance, and thus consciousness, may depend on systems’ specific material
composition.
42
2.4.5(c)
Agency and embodiment indicators
The proposal that consciousness depends on material composition is clearly incompatible with
computational functionalism, so we can set it aside. However, the compatibility of the other proposals we have discussed with computational functionalism is a more complicated matter. The
issue is the same in each case: natural formulations of the putative indicators make reference to
conditions external to the system. This is incompatible with computational functionalism if a similar system could perform the same computations in different external conditions.
For example, consider the claim that self-maintenance is necessary for consciousness, and
suppose that for a system to be self-maintaining in the relevant sense, it must persist in part because
it keeps track of certain inputs or internal states and acts to regulate them. It seems that for any
system that does this, there could be another that performs the same computations—keeping track
of the same inputs or internal states and using the same outputs to regulate them—but which does
not persist for this reason. Perhaps the system works to keep an “energy measure” from dropping
too low, but in fact, it would persist even if this measure fell to zero, and its energy is supplied by
an external operator in a way that does not depend on its behaviour.
If agency or embodiment are necessary for consciousness, these conditions may be incompatible with computational functionalism for similar reasons. These conditions require that the
system’s inputs are sensitive to its outputs. But in principle, it is possible for a system to exist in an
environment in which its inputs do not depend on its outputs, and yet receive, by chance, patterns
of inputs and outputs which are consistent with this dependency. Such a system might perform the
same computations as one that genuinely interacted with its environment.
To avoid this incompatibility, indicators concerning agency, perspective, or self-maintenance
should be formulated “narrowly”, in ways that do not make reference to external conditions. For
instance, rather than saying that a system is more likely to be conscious if it pursues goals by
interacting with its environment, we can say that it is more likely to be conscious if it learns from
feedback and selects actions in such a way as to pursue goals by interacting with its environment.
Similarly, we can say that a system is embodied if it has a model of how its outputs affect its
inputs, which represents some systematic effects, and uses this model in perception or control.
There is a sense in which this system might misrepresent itself as an embodied agent, even if it has
learnt this model, because it may be that the apparently systematic contingencies suggested by its
past observations are mere coincidences. However, only embodiment conditions on which this is
enough for consciousness are consistent with computational functionalism. Notably, this account
of embodiment allows that systems controlling virtual avatars can count as embodied.
In this section, we have seen several indicators which could be added to our list. These include:
being an agent; having flexible goals or values; being an intentional agent; having a perspective;
having a body; and being self-maintaining. However, there are also reasons to exclude some of
these. We already have an indicator requiring a relatively sophisticated form of agency with belieflike representations: indicator HOT-3, derived from PRM. An intentional agency indicator would
be too similar to this one. And although a narrow formulation of a self-maintenance indicator is
possible, which would be compatible with computational functionalism, this would be contrary to
the spirit of the philosophical theories which emphasise self-maintenance. The ideas of being an
agent and having flexible goals are closely related, and the main way in which flexible goals add to
43
the case for consciousness is through the argument for centralisation and a common motivational
currency, so we combine these in one indicator.
We, therefore, adopt the following two further indicators of consciousness:
AE-1 Agency: Learning from feedback and selecting outputs so as to pursue goals, especially where this involves flexible responsiveness to competing goals
AE-2 Embodiment: Modeling output-input contingencies, including some systematic
effects, and using this model in perception or control
2.4.6
Time and Recurrence
Human conscious experience seems to be highly integrated over time. We seem to undergo experiences that are themselves extended in time, and constitute conscious perception of temporallyextended phenomena, such as when we hear a bird’s song or watch it fly from one perch to another.
What’s more, from the time we wake up each day we seem to experience a flow of several hours
of continuous, integrated experience. Whether or not this feature of our experience should be explained in terms of memory (Dainton 2000, Phillips 2018b), our conscious experiences also seem
to be deeply influenced by our memories. This integration might be seen as a reason to doubt that
consciousness is possible in ANNs whose activity consists of temporally discrete forward passes;
the point is particularly vivid if we imagine that there are long intervening periods (weeks, years)
between passes. However, several responses can be made to this objection.
One response is that it is not obvious that consciousness is necessarily integrated over time.
Patients with dense amnesia seem to have a series of brief, disjointed experiences (Wilson et al.
1995). These experiences may not be static, but it seems possible to imagine a conscious being that
had only a succession of brief, static, discrete experiences. There is a question about what would
make it the case that these were the experiences of a single subject, but it is not obvious either that
integration over time is the only possible grounds for the persistence of the subject of conscious
experience, or that there could not be conscious systems without a persisting subject.
Furthermore, it is possible that the apparent temporal continuity of human experience is illusory. Philosophers and scientists defend a range of views about how our experiences are generated
over time (Dainton 2023), but these include the view that we undergo discrete, static experiences in
rapid succession, generated by sampling from unconscious activity (VanRullen 2016, Herzog et al.
2020). Prosser (2016) calls this the “dynamic snapshot” view. The content of discrete experiences
may be informed by unconscious retention of information, and be capable of representing change
despite being static. For example, when watching a bird I might undergo a brief static visual experience representing not only that the bird is in a certain location, but that it is moving in a certain
way. On this model, there may be no special integration between successive experiences, since the
appearance of such integration can be explained by their being sampled at a fairly high frequency
from smoothly-changing unconscious perceptual activity which in turn reflects smooth continuous
change in the environment.
Despite these points, it does seem that algorithmic recurrence (i.e. recurrence as it is usually
understood in machine learning; see section 2.1.3) is likely to be necessary for conscious expe44
rience with a human-like temporal character. For conscious experience to represent change or
continuity in the environment in any way, information about the past must be retained and used
to influence present processing. This is a further reason to take algorithmic recurrence to be an
indicator of consciousness, as expressed in our indicator RPT-1. Integration over time, and, therefore, recurrent processing, is also emphasised by the midbrain and sensorimotor theories, the UAL
framework and some PP theorists.
2.5
Indicators of Consciousness
Each of the theories and proposals which we have discussed in sections 2.1-2.4 is of some value in
assessing whether a given AI system is likely to be conscious, or how likely it is that a conscious
system could be built in the near future. They are each supported by evidence and arguments
that have some force. We, the authors of this report, have varying opinions on the strength of
the evidence and arguments supporting each theory, as well as varying background views about
consciousness that influence our assessments of the likelihood of near-term AI consciousness.
Here we summarise the findings of section 2 by giving a list of indicators of consciousness drawn
from the theories and proposals we have discussed.
Our claim about these indicators is that they jointly amount to a rubric, informed by current
views in the science of consciousness, for assessing the likelihood of consciousness in particular
AI systems. Systems that have more of these features are better candidates for consciousness.
Theories of consciousness make stronger claims than this, such as that some of these are necessary
conditions for consciousness, and that combinations are jointly sufficient. We do not endorse
these stronger claims, but we do claim that in using these indicators one should bear in mind
how they relate to theories and to each other—some combinations of indicators will amount to
more a compelling case for consciousness than others. The extent to which these indicators are
individually probability-raising also varies, with some being plausibly necessary conditions that do
not make consciousness significantly more likely in isolation (perhaps including RPT-1, GWT-1
and HOT-1).
45
Recurrent processing theory
RPT-1: Input modules using algorithmic recurrence RPT-1 and RPT-2 are largely independent
RPT-2: Input modules generating organised,
indicators. RPT-1 is also supported by
integrated perceptual representations
temporal integration arguments.
Global workspace theory
GWT-1: Multiple specialised systems capable of
operating in parallel (modules)
GWT-2: Limited capacity workspace, entailing a
bottleneck in information flow and a selective
GWT claims that these are necessary and
attention mechanism
jointly sufficient. GWT-1 through GWT-4
GWT-3: Global broadcast: availability of
build on one another. GWT-3 and GWT-4
information in the workspace to all modules
entail RPT-1.
GWT-4: State-dependent attention, giving rise to
the capacity to use the workspace to query modules
in succession to perform complex tasks
Computational higher-order theories
HOT-1: Generative, top-down or noisy perception
modules
PRM claims that these are necessary and
HOT-2: Metacognitive monitoring distinguishing
jointly sufficient. HOT-1 through HOT-3
reliable perceptual representations from noise
build on one another; HOT-4 is
HOT-3: Agency guided by a general
independent. The first clause of HOT-3 is
belief-formation and action selection system, and a
also supported by arguments concerning
strong disposition to update beliefs in accordance
intentional/flexible agency, and entails
with the outputs of metacognitive monitoring
AE-1.
HOT-4: Sparse and smooth coding generating a
“quality space”
Attention schema theory
AST-1: A predictive model representing and
enabling control over the current state of attention
Predictive processing
PP-1: Input modules using predictive coding
Entails RPT-1 and HOT-1.
Agency and embodiment
AE-1: Agency: Learning from feedback and
selecting outputs so as to pursue goals, especially
Both indicators are also supported by
where this involves flexible responsiveness to
midbrain and UAL theories, and to some
competing goals
extent by GWT, PRM and PP, especially
AE-2: Embodiment: Modeling output-input
AE-1. Systems meeting AE-2 are likely, but
contingencies, including some systematic effects,
not guaranteed, to also meet AE-1.
and using this model in perception or control
Table 2: Indicator Property Entailments
46
3
Consciousness in AI
What do the findings of section 2 imply about consciousness in current and near-future AI systems?
In this section, we address this question in two ways. First, in section 3.1 we discuss the indicator
properties in turn, asking how they could be implemented in artificial systems. Second, in section
3.2 we examine several existing AI systems as case studies illustrating both how the indicators
should be used, and how our method evaluates some current systems. We discuss large language
models and the Perceiver architecture (Jaegle et al. 2021a, b) with a particular focus on global
workspace theory, and consider whether any of a selection of recent systems—PaLM-E (Driess
et al. 2023), a “virtual rodent” (Merel et al. 2019) and AdA (DeepMind Adaptive Agents Team
2023)—are embodied agents.
Reflecting on how to construct systems with the indicator properties, and on whether they
are present in current systems, illustrates some crucial lessons of our work. One is that assessing whether a system possesses an indicator property typically involves some interpretation of the
description of the property; the descriptions of indicator properties, like the theories from which
they are drawn, contain ambiguities that possible implementations draw out. To describe indicator properties with so much precision that this kind of interpretation is not needed would mean
going well beyond the claims made by scientific theories of consciousness, and these more precise claims would also tend to be less well-supported by the available empirical evidence. We
hope that interdisciplinary research on consciousness, which brings together neuroscientists and
AI researchers, will result in greater precision in theories of consciousness and the development of
empirical methods that can provide evidence supporting more precise theories.
A second lesson from the discussion in this section is that in assessing AI systems for consciousness, it is not always sufficient to consider the system’s architecture, training and behaviour.
For example, we may know that a system is a recurrent neural network and has been trained via RL
to successfully control a virtual body to perform a task, and yet not know whether its performance
relies on a learned model of output-input contingencies. In such a case, we may not know whether
the system satisfies our embodiment condition. Interpretability methods, such as examining the
information encoded in hidden layers (Olah et al. 2018), would be required to determine whether
the system has acquired such a model in the course of training.
The third lesson is that, despite the challenges involved in applying theories of consciousness
to AI, there is a strong case that most or all of the conditions for consciousness suggested by
current computational theories can be met using existing techniques in AI. This is not to say that
current AI systems are likely to be conscious—there is also the issue of whether they combine
existing techniques in the right ways, and in any case, there is uncertainty about both computational
functionalism and current theories—but it does suggest that conscious AI is not merely a remote
possibility in the distant future. If it is possible at all to build conscious AI systems without
radically new hardware, it may well be possible now.
47
3.1
Implementing Indicator Properties in AI
3.1.1
Implementing RPT and PP
We begin our investigation of the indicators by discussing the two indicators taken from RPT, algorithmic recurrence and perceptual organisation, along with the PP indicator (i.e., indicators RPT-1,
RPT-2 and PP-1). The reason for including PP here is that, as we will see, recent studies have
found that using predictive coding in computer vision can facilitate processing that is more sensitive to global features of visual scenes, in contrast to the local-feature sensitivity of feedforward
convolutional neural networks which perform well in classification tasks.
Algorithmic recurrence (RPT-1) is a feature of many deep learning architectures, including
recurrent neural networks (RNNs), long short-term memory networks (LSTMs) and gated recurrent unit networks (GRUs) (LeCun et al. 2015). Building systems that possess indicator property
RPT-1 is, therefore, straightforward. Although they are less widely used, there are also methods
for implementing predictive coding (which is a form of algorithmic recurrence) in artificial systems (Lotter et al. 2017, Oord et al. 2019, Millidge et al. 2022). These systems meet indicator
PP-1. Furthermore, recurrent neural networks trained on prediction tasks and optimised for energy
efficiency self-organise into distinct populations of “prediction” and “error” units (Ali et al. 2022).
Turning to perceptual organisation (RPT-2), artificial vision models such as deep convolutional
neural networks (DCNNs), are already both highly successful and often claimed to be good models
of human vision (Kietzmann et al. 2019, Lindsay 2021, Mehrer et al. 2021, Zhuang et al. 2021).
However, the claim that current systems are good models of human vision has recently been criticised (Bowers et al. 2022, Quilty-Dunn et al. 2022), and, more to the point, the human-level
performance in visual object recognition that DCNNs achieve does not entail that they represent
organised visual scenes. Bowers et al. (2022) and Quilty-Dunn et al. (2022) both cite evidence that
DCNNs trained to classify objects are more sensitive to local shapes and textures than to global
shapes, and tend to ignore relations between parts of objects, suggesting that they do not employ
representations of integrated scenes. Conwell and Ullman (2022) found that the recent image
generation model DALL-E 2 performed poorly when prompted to generate a scene with objects
arranged in unfamiliar ways.
From the point of view of RPT, these points might be taken to show that the models in question
are capable of categorising features of visual stimuli, a function which is said to be performed unconsciously in humans, but are not capable of further functions up to and including the generation
of organised, integrated representations of visual scenes, some of which may require consciousness
(Lamme 2020). However, other current systems, including predictive coding networks, do perform
some of these further functions.
48
PredNet, a predictive coding network
trained to predict the next frame of video inputs, is notable partly because success at this
task seems to require representation of the objects that make up a scene and their spatial
relations (Lotter et al. 2017). Furthermore,
there is evidence that PredNet units respond
to illusory contours in the Kanizsa illusion,
the perception of which depends on inferring
the presence of objects from the wider context (Lotter et al. 2020). Extending this finding, Pang et al. (2021) used a technique for
adding feedback predictive coding connections
to a feedforward DCNN and found further ev- Figure 3: Illustration of the Kanizsa illusion.
idence that this predictive coding network, but 2020. Wikimedia Commons. Reprinted with pernot the initial feedforward model, was sensi- mission.
tive to the Kanizsa illusion. However, Lamme
(2020) claims that the Kanizsa illusion requires only perceptual “inference”, not perceptual organisation as understood by RPT.
Beyond predictive coding, systems of other kinds have been developed specifically to represent
objects and their relations in visual scenes. MONet, which uses a recurrent attention mechanism
and a variational autoencoder to decompose and reconstruct scenes, is one example (Burgess et al.
2019). In this system, the attention network picks out individual objects in turn for identification
and reconstruction by the variational autoencoder. Another system, the Object Scene Representation Transformer, is trained to predict the appearance of complex scenes from new angles, a task
which (like video prediction) requires the representation of scenes as made up of objects in space
(Sajjadi et al. 2022). Representing organised perceptual scenes is an active area of research in
machine learning for which several methods have already been developed (Greff et al. 2020).
3.1.2
Implementing GWT
Implementing GWT in artificial systems has been the subject of several studies, including recent
research by VanRullen and Kanai (2021) and Goyal et al. (2022). Here we give brief overviews of
these two studies before discussing indicators GWT-1 through GWT-4 in turn.
VanRullen and Kanai’s (2021) proposal involves a set of specialised neural modules, at least
some of which are generative networks that can produce behavioural outputs or drive sensory
processing top-down. Each of these modules has its own low-dimensional latent space in which
key information is represented. The modules are integrated by a workspace, which is a shared
latent space trained to perform unsupervised translation of representations in the latent spaces of
the modules so that the information they carry is available to the others. The workspace has a
lower capacity than the sum of the module latent spaces, and a task-dependent key-query attention
mechanism is used to determine which information it broadcasts. So this architecture includes
the important features of a bottleneck, global broadcast and state-dependent selection. However,
49
this work is a “roadmap” to a possible implementation, rather than a working system. It faces
a substantial open question about how the attention mechanism could be trained to select among
the potential inputs to the workspace, and especially how this could achieve the sequences of
operations of attention needed to control extended, functional sequences of operations by relevant
modules.
Meanwhile, Goyal et al. (2022) experimented with a method for implementing global workspace
which similarly involved using key-query attention to select which of multiple modules would
write to a shared space, with the contents of the shared space then being broadcast to all modules. In this case, the modules were trained together to generate mutually usable representations,
avoiding the need for translation in the workspace. A limitation of the specific implementations
developed in this work was that the “modules” were elements processing tokens in a sequence
or parts of an image, so it is questionable whether they were specialised subsystems capable of
operating in parallel; instead, they each contributed in similar ways to the performance of a single
task.
Although neither of these studies produced a working system that clearly satisfies all four GWT
indicators, this does seem to be a realistic objective, as we will argue by considering the indicators
in turn. Indicator GWT-1 states that the system must have specialised systems, or modules, capable
of working in parallel. To make global broadcast possible, these modules must be implemented by
recurrent neural networks, unless they are “output” modules for the system as a whole, which do
not provide information to the workspace. The modules might take as input:
1. Sensory input in one or more modalities.
2. Input from a small number of other modules that typically work in tandem. For instance, a “saccade” module might take input from a “visual saliency” module in order
to enable quick bottom-up saccades towards potentially important objects.
3. Top-down signals coming from an executive Global Workspace module.
These modules might be trained independently on narrow tasks, as suggested by VanRullen
and Kanai (2021). Or they might be jointly trained end-to-end with the workspace in order to
achieve some system-wide objective, from which module specialisation to subtasks would naturally emerge. The end-to-end training approach was employed by Goyal et al. (2022), although
for relatively simple tasks (see also Goyal et al. 2020).
The second element of an implementation of GWT is a limited-capacity workspace, which is
a further neural module with different properties. The simplest way to limit the capacity of the
workspace is to limit the number of dimensions of its activity space. Another interesting option
is to train a recurrent neural network that exhibits attractor dynamics. An attractor is a state in a
dynamical system such that when that state is reached, it will remain stable in the absence of inputs
or noise to the system. The reason that attractor dynamics limits capacity is that it induces a manyto-one mapping from initial conditions in a neural trajectory to attractors (any neural trajectory
that enters an attractor’s basin of attraction will converge to that attractor). Thus, these attractor
dynamics induce an information bottleneck by contracting the size of the space of stable states.
Ji, Elmoznino et al. (2023) argue that attractor dynamics in the workspace can help to explain the
apparent richness and ineffability of conscious experience.
50
For indicator GWT-3, global broadcast, the basic requirement is that all modules take workspace
representations as input. As we have seen, this means that some mechanism must be in place to
ensure that these inputs can be used by all modules, such as the translation mechanism proposed
by VanRullen and Kanai (2021). In the global neuronal workspace theory developed by Dehaene
and colleagues (Dehaene & Naccache 2001, Dehaene & Changeaux 2011, Mashour et al. 2020),
the workspace exhibits particular dynamic properties: for a representation to be in the workspace
and globally broadcast, it must be sustained by recurrent loops. While it is not clear that this is
essential, this behaviour could be replicated in AI if a network exhibiting attractor dynamics was
used to implement the workspace. In this case, the broadcast mechanism might consist of a leaky
neural integrator whose dynamics have slow timescales such that sustained inputs are required to
place it in a particular state, and in the absence of these sustained inputs it relaxes back to some
baseline state (as in models of decision-making through evidence accumulation). This broadcast
mechanism would generate the top-down signals feeding into each specialised module.
Indicator GWT-4 includes the conditions that the system must use a state-dependent attention
mechanism and that the workspace must be able to compose modules to perform complex tasks by
querying them in succession. For the state-dependent attention mechanism, both VanRullen and
Kanai (2021) and Goyal et al. (2022) propose the use of key-query attention, which is common
in current AI models. A query can be computed from the workspace’s current state, and keys
can be computed for all other modules. The similarity between the workspace’s query and a given
module’s key would be normalised by the similarities across all other modules in order to introduce
competition between modules, and these normalised similarities would determine the degree to
which each module’s value contributes to the net input to the workspace. That is, a standard
key-query attention mechanism would be applied at each timepoint to compute the input to the
workspace in a way that depends on its current state.
The model described here would be able to meet the second part of GWT-4—the capacity to
use the workspace to query modules in succession to perform complex tasks— when it is unrolled
through time because there are computational loops between the workspace and the modules. The
modules receive input from bottom-up sensory input and from a small number of other modules,
but they also receive top-down input from the workspace. This means that, for instance, it is
possible for one module to control others by controlling what is represented in the workspace. The
sequential recruitment of modules by the workspace is within the computational repertoire of the
system, so it could emerge if it is beneficial during training. However, suitable training would be
required for such a system to learn to compose modules in useful ways and to perform complex
tasks, and constructing a suitable training regime may be a significant challenge for implementing
GWT.
3.1.3
Implementing PRM
We now consider how perceptual reality monitoring theory, as a representative computational HOT,
could be implemented in AI. That is, we consider how an AI system could be constructed with indicator properties HOT-1 through HOT-4. Although PRM researchers claim that there are no current
AI systems that meet all of the requirements (Dehaene et al. 2017, Michel & Lau 2021, Lau 2022),
and there have been no implementation attempts that we are aware of, standard machine learning
51
methods are sufficient for plausible implementations of most elements of the theory. We begin by
considering the implementation of a “quality space”—that is, a space of possible representations
which satisfies the PRM account of the basis of phenomenal qualities—before turning to the core
claim of PRM, that first-order representations become conscious as a result of being represented
as “real” by a higher-order monitoring mechanism.
Indicator HOT-4 states that the system must have sparse and smooth coding generating a “quality space”. One of the most important features of all DNNs is that each layer endows the model
with a smooth representation space, in which a continuous range of possible activations codes for
the range of possible inputs. The smoothness of these representation spaces is thought to be one
of the primary reasons why they can generalise to novel inputs at test time; even if a novel input
drives a layer into a different activation pattern, this pattern can still be interpreted by subsequent
layers so long as it is within the model’s training distribution (that is, so long as the layer activated
with similar patterns at training time) (Belkin et al. 2018, Bartlett et al. 2021). In fact, there is
evidence that the perceptual representation spaces learned by current DNNs already closely resemble those of the human visual system, meaning their corresponding “quality spaces” might already
be substantially aligned. For instance, Kriegeskorte (2015) finds that the matrix of pairwise dissimilarities between representations of many visual stimuli in a DNN is closely aligned to what is
observed in neural activity and that there is even a correspondence between successive layers in
the network and the hierarchical organisation of the visual cortex—although more recent studies
have complicated this picture (see e.g. Golan et al. 2020, Lindsay 2021, Bowers et al. 2022).
Standard methods in machine learning can be used to satisfy the condition that representations
be sparse. For example, regularization techniques can enforce sparse representations in DNN
models, by minimising the magnitude of the network’s representations or the mutual information
between inputs and representations (Tishby 2000). Layers that use normalisation functions like
SoftMax, in which higher values suppress lower values in the representation, also increase sparsity.
Indicators HOT-1 and HOT-2 state that the model must contain both first-order perceptual representations of sensory data and higher-order representations that assign a measure of reliability
or “realness” to particular first-order representations. To meet these conditions, a vast number of
known deep learning solutions are possible, of which we review a few. Importantly, all of these
solutions share a simple architectural design of two components: (1) a (first-order) neural network takes sensory data and/or top-down signals as input and produces a number of perceptual
representations distributed across a hierarchy of layers (2) in parallel, a series of separate (higherorder—specifically second-order) neural networks each take a first-order layer’s activations as input and then output a single scalar, representing the probability that the first-order representation
of that layer is veridical. Solutions for meeting the conditions will differ primarily in terms of how
the second-order networks are trained.
If supervision signals are occasionally present that provide the second-order networks with
“ground-truth” about the reliability of first-order representations, then the second-order network
can be trained to estimate the probability of correctness by standard supervised learning. Obtaining
this ground-truth signal may be difficult, but not impossible. For instance, if a source of first-order
representation errors is internal noise in the network, ground-truth can be estimated simply by
averaging noisy first-order representations over time. Another possibility is to obtain ground-truth
by comparing representations of the same percept in different sensory modalities (e.g., verifying
52
the veracity of a sound using visual feedback) or through movement (e.g., checking if a visual
percept behaves as it should given known motor actions).
If ground-truth is not directly available, the second-order networks can be trained on other
surrogate tasks where the reliability of a signal is an implicit factor in performance. For instance,
second-order networks might try to predict upcoming first-order representations using past ones.
Because externally generated signals are sometimes more predictable than internally generated
signals—a perception of a falling ball is more predictable than a hallucination generated by random
internal noise—when the networks’ predictions have high error, the second-order network can
assign a lower probability to the veracity of the first-order representation. Alternatively, when
imagery is under cognitive control, engaging in imagination can lead to more predictable sensory
consequences (I imagine a pink bear and a pink bear appears) than when it is not (I allow my mind
to wander). Thus the level of effortful control can serve as another internal signal that could train
a reality monitoring system (Dijkstra et al. 2022). In these ways, a second-order network could
learn to use predictability as a cue to “realness” even in the absence of supervision signals. These
methods are closely related to predictive coding, which has already seen applications in modern
deep learning (e.g., Millidge et al. 2022, Oord et al. 2019, Alamia et al. 2023), except that here
the prediction is done across time rather than across layers in a hierarchy.
Other methods of training the second-order network involve thinking of it as a world-model.
For instance, Bayesian methods in deep learning view perception as an inference process, in which
a neural network attempts to infer the values of latent variables that might have generated the data.
For ideal Bayesian inference, these latent variables must be sampled according to their posterior
probability, which is proportional to their prior probability multiplied by their likelihood of having
generated the data under some world model that specifies how latent variables produce sensory
observations. This sort of perspective fits well with PRM; the inference machinery for latent variable values can be seen as producing perceptual first-order representations, while the second-order
networks evaluate the probability that the first-order representations are true.
While Bayesian inference is intractable in general, several approximate methods exist. For
instance, a recent class of models called Generative Flow Networks (GFlowNets) provide a framework for doing approximate Bayesian inference using modern deep neural networks (Bengio et al.
2021, Bengio et al. 2022), and can even be used to jointly train the inference model (first-order
network) at the same time as the world-model (second-order network) (Hu et al. 2023, Zhang et
al. 2023). This proposed GFlowNet architecture (like other approximate Bayesian inference methods) is again related to predictive processing theories of consciousness, which state that conscious
percepts are the brain’s best guesses of the latent causes of its own sensory input (Seth 2021). An
important difference in the PRM case, though, is that after the first-order inference system samples
perceptual latent variables, they only become conscious if the second-order world model assigns
them a high enough probability of being veridical, where either a hard or a soft threshold can be
used to produce the “real” tag.
Note that the mechanism described above could also be used to produce internally-generated
conscious experiences in the system. For instance, a top-down imagination module might first
produce a goal (e.g., visualize an apple) and then drive neural activity accordingly in the first-order
network’s sensory and perceptual layers. Following this, the second-order world model would
assign a probability of veracity to this activity. If the imagination module is capable of producing
53
coherent enough representations in the sensory and perceptual layers, then the second-order model
would assign the signals a “real” tag in the same way as for externally-generated signals, and
the imagined content would be consciously experienced. A similar mechanism may exist in the
brain, as it has been shown that neural activity in sensory regions is similar during imagination
and bottom-up perception and that the degree of similarity correlates with the vividness of the
experience (Dijkstra 2019, Dijkstra 2023).
A final possibility is to learn a world model implicitly through adversarial methods. In particular, Generative Adversarial Networks (GANs) (Goodfellow et al. 2014) are a class of methods
in which a generator network attempts to sample synthetic data and a discriminator attempts to
differentiate real data from synthetic data produced by the generator. The generator is optimized
to fool the discriminator into predicting its outputs as “real”, with the result that, if the networks
used are powerful enough, the stable solution is for the generator to sample data from the true
data distribution. The discriminator in GANs is comparable to the higher-order monitoring mechanism posited by PRM (Lau 2022). A GAN-based implementation of PRM might involve (a) a
first-order perception network that produces perceptual representations given sensory data, (b) a
generator network that inverts this process by first sampling synthetic perceptual representations
and then producing synthetic sensory data given those percepts, and (c) a second-order network
that is trained to discriminate between the real sensory-percept tuples produced by the first-order
network and the synthetic ones produced by the generator (Gershman 2019). Like in the case of
explicit world models, we can subsequently produce the “real” tag of PRM by applying a hard or
a soft threshold to the discriminator’s output given representations from the first-order network.
It now remains for us to consider indicator HOT-3, which concerns the consumer of outputs
from the metacognitive monitoring mechanism. Indicator HOT-3 states that this should be a “general belief-formation and action selection system” and that there should be a “strong disposition”
to update it in accordance with the monitoring mechanism’s outputs. There are dual motivations
for this condition: the function of the monitoring mechanism is to serve this consumer, which relies
on the accuracy of first-order representations which are tagged as “real”; and the “force” of these
inputs to the consumer is intended to explain the force and persistence of conscious experiences.
To implement the consumer, we can instantiate one or more higher-level networks that similarly
take only perceptual representations with the “real” tag as input. There might be many ways to
accomplish this, but one possibility is to use standard Transformer architectures for the higherlevel networks with one small adaptation. In the Transformer, one or more query vectors would
be produced by the higher-level network (intuitively representing the current computational goal)
that would then attend to first-order perceptual representations depending on the values of their key
vectors (intuitively representing the “kind” of percept or its “data type”). In a standard Transformer,
each precept would then be modulated based on the similarity between its key and the higher-level
network’s query, and then subsequently integrated into the downstream computation. If we wish
to additionally make use of the “real” tags produced by the second-order networks, we need only
multiply the query-key similarities by the value of the “real” tags for each corresponding percept,
which would allow them to effectively serve as prior masks on which precepts may influence
computations in the Transformer. Importantly, such an architecture is compatible with predictions
made by PRM about the stubbornness of conscious percepts (Lau 2019): even if we are cognitively
aware that a percept is inaccurate (e.g., a phantom pain, or a drug-induced hallucination), we still
have a strong disposition to integrate it into our higher-level reasoning. With this Transformer54
based architecture, conscious experiences cannot be reasoned away. This is because the higherlevel network simply takes the percepts modulated by their “real” tags as input, and has no ability
to change those “real” tags itself.
This proposal focuses on the second aspect of indicator HOT-3 (the “strong disposition”), rather
than the idea that the consumer should be a general belief-formation and action selection system.
Philosophers have various ideas about the features a system would need to have to count as forming
beliefs, but one plausible necessary condition, which may be sufficient in this context, is that the
system engages in instrumental reasoning leading to action selection (see section 2.4.5).
3.1.4
Implementing AST
Two notable studies have implemented simple attention schemas in artificial systems. Wilterson
and Graziano’s (2021) system used reinforcement learning on a three-layer neural network with
200 neurons per layer to learn to catch a ball falling on an unpredictable path. The primary input
to this system was a noisy “visual” array showing the position of the ball. This array included an
“attention spotlight”—a portion of the array with the noise removed—that the system could learn
to move. A natural strategy for solving the task was thus for the system to learn to position the
spotlight over the ball, so that noise in the visual array would not interfere with its ability to track
and catch it. This was facilitated by a second input, an “attention schema” that represented the
current position of the spotlight in the array. Wilterson and Graziano found that this system was
much more successful in learning to perform the task when the attention schema was available,
even though the spotlight remained when the schema was removed.
This very simple system did possess some part of indicator property AST-1, the attention
schema, because it used a representation of an attention-like mechanism to control that mechanism, resulting in improved performance. However, this was not a predictive model, and the attention spotlight was substantially different from attention itself because it was a simple controllable
feature of the input rather than an internal process with multiple degrees of freedom governing
information flow through the system.
More recently, Liu et al. (2023) tested several different systems employing key-query-value
attention on multi-agent reinforcement learning tasks. Their systems involved three main elements:
multi-head attention layers, a recurrent neural network for “internal control” and a policy network.
In the version that they took to most accurately implement an attention schema, the attention layers
were applied to inputs to the system and sent information on to the policy network that generated
actions, with the internal control network both learning to predict the behaviour of the attention
layers and influencing this behaviour. This system performed better than the others, with different
architectures made up of the same components, which were tested on the multi-agent RL tasks.
Compared to Wilterson and Graziano’s system, this system had the advantage of using a learnt
predictive model of attention, rather than having an infallible representation provided as input. It
was still used only for relatively simple tasks in 2D visual environments, and a caveat to this line of
research is that attention in AI is not perfectly analogous to attention as understood by neuroscience
(see Box 3). However, this system does illustrate a route to constructing systems that possess the
attention schema indicator.
55
3.1.5
Implementing agency and embodiment
The remaining indicators are agency and embodiment. Reinforcement learning is arguably sufficient for agency as we have characterised it (“learning from feedback and selecting outputs so
as to pursue goals”), so meeting this part of indicator AE-1 may be very straightforward. Reinforcement learning is very widely used in current AI. To recap the argument for the claim that RL
is sufficient for agency, the basic task in RL is for the system to learn to maximise cumulative
reward in an environment in which its outputs affect not only the immediate reward it receives but
also its opportunities for future reward. RL algorithms are, therefore, designed to be sensitive to
the consequences of outputs, making the system more likely to repeat outputs that lead to greater
reward over multiple time-steps. This means that there is a contrast between RL and other forms
of machine learning. Like systems trained by supervised or self-supervised learning, RL systems
gradually come to approximate a desired input-output function. However, in RL what makes this
the desired function is that the outputs are conducive to goals that can only be achieved by extended
episodes of interaction between the system and the environment. Crucially, RL systems learn these
functions by virtue of their sensitivity to relationships between outputs, subsequent inputs, and rewards. Model-based RL systems learn models of these relationships, but model-free systems are
also sensitive to them. So RL systems learn and select actions so as to pursue goals (Butlin 2022,
2023).
Figure 4: Reinforcement learning diagram of a Markov decision process based on a figure from
Reinforcement Learning: An Introduction (second edition). by Sutton and Barto. 2020. Creative
Commons Attribution-Share Alike 4.0 International. Reprinted with permission.
56
The second part of indicator AE-1 says that the probability of consciousness is raised to a
greater degree if systems exhibit “flexible responsiveness to competing goals”. The example motivating this clause is an animal balancing multiple homeostatic drives: this requires prioritisation
which is sensitive to shifting circumstances. Several computational approaches to this problem
have been explored, including in the context of reinforcement learning (Keramati & Gutkin 2014,
Juechems & Summerfield 2019, Andersson et al. 2019). One proposal is to use multiple modules
that learn independently about how to maximise distinct reward functions, with each of these modules assigning scores to possible actions, and then to pick the action with the highest total score
(Dulberg et al. 2023). In the homeostatic case, these reward functions might each correspond to
a homeostatic drive, with large penalties for allowing any one of them to depart too far from a set
point.
Our embodiment indicator, AE-2, states that systems should use output-input models (also
known as forward models) for perception or control. There are specific uses of such models,
which neuroscientists have identified in humans, that are particularly associated with embodiment.
In perception, predictions of the sensory effects of the system’s own actions can be used to distinguish changes to sensory stimulation caused by these actions from those caused by events in
the environment. Systems that engage in this form of inference implicitly or explicitly distinguish
themselves from their environments. In motor control, forward models can be used for state estimation and feedback control, enabling rapid adjustments of complex effectors. It is important
to distinguish these uses of output-input models from other uses, such as planning, which do not
imply embodiment.
Learning output-input models for tasks related to perception and control is common, but there
are few examples of current AI systems which meet these specific descriptions. For example, video
prediction is a much-studied task (Oprea et al. 2020), and this includes predicting how visual input
will develop conditional on the system’s outputs (Finn et al. 2016). But this is not sufficient for the
kind of use in perception that we have described, which also includes making sense of exogenous
changes which are not predictable from outputs. Output-input models are used in model-based
reinforcement learning for control, facilitating successful control of quadrotor drones (BeckerEhmck et al. 2020) and other robots (Wu et al. 2022). But it is uncertain whether the models are
used in these cases for control-specific purposes rather than for planning, a topic that we explore
further in section 3.2.2.
One good example of recent research which does employ a forward model for a purpose specific to embodied systems is the system described in Friedrich et al. (2021). In this system,
Kalman filtering (Todorov & Jordan 2002) was used to combine a forward model with sensory
inputs, which were subject to a time delay, in order to estimate the current state of the system in its
environment. These estimates were then used in ongoing motor control, although only of relatively
simple effectors in virtual environments.
57
3.2
Case Studies of Current Systems
3.2.1
Case studies for GWT
In practice, it is not always immediately obvious whether a given AI system possesses one of the
indicator properties. One reason for this is that we have not given absolutely precise definitions
for each indicator. Another is that how deep learning systems work, including what they represent at intermediate layers, is often not transparent. In this section and section 3.2.2 we present
case studies illustrating the use of the indicators to assess current AI systems. Here we focus on
the GWT indicators (GWT-1 through GWT-4), and on two kinds of systems that are notable for
different reasons. These systems are Transformer-based large language models (LLMs) such as
GPT-3 (Brown et al. 2020), GPT-4 (OpenAI 2023), and LaMDA (Thoppilan et al. 2022), which
are notable for their remarkable performance on natural language tasks and the public attention
they have attracted; and Perceiver (Jaegle et al. 2021a) and Perceiver IO (Jaegle et al. 2021b),
which are notable because Juliani et al. (2022) argue that they “implement a functioning global
workspace”. Neither of these kinds of systems was designed to implement a global workspace, but
there are arguments to be made that they each possess some of the GWT indicator properties.
In a Transformer, an operation called “selfattention” is used to integrate information from
different parts of an input, which are often
positions in a sequence (see Box 3 on attention; Vaswani et al. 2017). If we see the
elements of the system which process information from each position (attention heads)
as modules, then there is a basic similarity
between the Transformer architecture and the
global workspace: both integrate information
from multiple modules. Transformers consist
of a stack of layers of two types, which alternate: layers of attention heads, which perform the self-attention operation, moving information between positions, and feedforward
layers. An interpretation of Transformers by
Elhage et al. (2021) describes them as made
up of “residual blocks”, each consisting of one
Figure 5: The Transformer architecture. layer of each type, which process information
Vaswani, A., Shazeer, N., Parmar, N., Uszkor- drawn from and then added back to a “residual
eit, J., Jones, L., Gomez, A. N., Kaiser, L., & stream”.
With the concept of the residual stream in
Polosukhin, I., 2023. Attention is all you need.
mind, it is possible to argue that Transformers
arXiv:1706.03762. Reprinted with permission.
possess indicator properties GWT-1 through
GWT-3—that is, that they have modules, a
limited-capacity workspace introducing a bottleneck, and global broadcast. The residual stream
58
is the (alleged) workspace, and its dimensionality is lower than that of the self-attention and feedforward layers which write to it and read from it (Elhage et al. 2021). There is “global broadcast”
in the sense that information in a particular layer in the residual stream can be used by downstream
attention heads to influence further processing at any position. The information which is added to
the residual stream at a given layer also depends on the state of the residual stream at earlier layers, so on this interpretation one might argue that Transformers meet the state-dependent attention
requirement in GWT-4.
One problem with this argument is that it is questionable whether the dimensionality of the
residual stream constitutes a bottleneck, since it is the same as that of the input to the system as a
whole. However, a more fundamental problem with the argument is that Transformers are not recurrent. The residual stream is not a single network, but a series of layers interspersed between others. There are no modules that pass information to the residual stream and receive it back—instead,
when attention heads and feedforward layers combine to write to the residual stream, this affects
only what is received by different attention heads and feedforward layers downstream. One way
to think about this is to ask which parts of Transformers are the modules. If modules are confined to particular layers, then there is no global broadcast. But if modules are not confined to
particular layers, then there is no distinguishing the residual stream from the modules. Transformers lack the overall structure of a system with a global workspace, in that there is no one distinct
workspace integrating other elements. There is only a relatively weak case that Transformer-based
large language models possess any of the GWT-derived indicator properties.
The two versions of the Perceiver architecture, meanwhile, are closer to satisfying the GWT
indicators than Transformers, but in our view still fall short of satisfying them all. The Perceiver
architecture was designed to address a weakness of Transformers, which is that the self-attention
operation integrates positions by generating pairwise interactions. This is computationally expensive to scale to high-dimensional inputs, motivating an approach that uses a single limited-capacity
latent space to integrate information from specialists (Jaegle et al. 2021a, b, Goyal et al. 2022).
In particular, Perceiver IO is designed to handle inputs from multiple domains or modalities, and
to produce outputs of various kinds, using multiple input encoders and output decoders. It uses
self-attention to process information in the latent space, and a related operation, cross-attention,
to select information from input modules and write to output modules. The latent space alternates
between self-attention and cross-attention layers, enabling it to take new information from input
modules repeatedly. Perceiver IO achieves high performance in tasks including language processing, predicting movement in videos, image classification, and processing information about units
for the purpose of action selection in Starcraft II (Jaegle et al. 2021b).
59
Figure 6: Perceiver architecture. Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A.,
& Carreira, J., 2021. In Proceedings of the 38th International Conference on Machine Learning,
PMLR 139:4651-4664. Reprinted with permission.
The Perceiver architecture allows for sequences of inputs to be processed diachronically, with
the latent space state updating with each new input, but also influenced by its previous state. So
Perceiver arguably possesses indicator properties GWT-1 (specialised modules) and GWT-2 (bottleneck), as well as the first part of GWT-4 (state-dependent attention). However, it is notable that
while specialised modules are possible in the architecture, they are not mandatory—the Perceiver
can be used with one input network with a single function. Also, more importantly, the number
of inputs that can be processed sequentially is limited by the number of cross-attention layers in
the latent space. This means that although attention in Perceiver is state-dependent, in practice the
system must be reset to begin a new task, so its states are determined by previous inputs on the
current task.
As in the case of Transformers, the clearest missing element of the global workspace in the
Perceiver is the lack of global broadcast. Perceiver IO has multiple output modules, but on any
given trial, its inputs include an “output query”, which specifies what kind of output is required.
So only one output module acts on information from the workspace. Furthermore, input modules
do not generally receive information from the workspace. So while the Perceiver architecture is
important as an example of the successful use of a workspace-like method to improve functionality
in AI, it is some way from being a full implementation of GWT.
3.2.2
Case studies for embodied agency
We now consider examples of AI systems that illustrate what is required for indicators AE-1 and
AE-2, which concern agency and embodiment. The systems we discuss in this subsection are:
PaLM-E (Driess et al. 2023), described as an “embodied multimodal language model”; a “virtual rodent” trained by RL (Merel et al. 2019); and AdA, a large Transformer-based, RL-trained
“adaptive agent” (DeepMind Adaptive Agents Team 2023).
60
Figure 7: PaLM-E architecture. Driess, D., Xia, F., Sajjadi, M. S. M., Lynch, C., Chowdhery,
A., Ichter, B., Wahid, A., Tompson, J., Vuong, Q., Yu, T., Huang, W., Chebotar, Y., Sermanet, P.,
Duckworth, D., Levine, S., Vanhoucke, V., Hausman, K., Toussaint, M., Greff, K., & Florence,
P., 2023. PaLM-E: An embodied multimodal language model. arXiv:2303.03378. Reprinted with
permission.
PaLM-E is a decoder-only LLM (Driess et al. 2023), fine-tuned from PaLM (Chowdhery et
al. 2022). It takes encoded multimodal strings which can include both text and images as input,
and produces text tokens as output. Like other LLMs, it can be used autoregressively to produce
extended strings of text. Its use requires an encoder, and in combination with a suitable encoder,
it can perform well in both pure language tasks and vision-language tasks such as visual question
answering. However, PaLM-E can also be combined with a separately-trained policy unit that
maps natural-language instructions and visual context to low-level robot actions. The PaLM-E
study used policies from Lynch et al. (2022) which were trained to imitate human control of robot
actuators. In this setup, the system can take input from a camera, combine it with task instructions
provided by a human, and generate and execute plans for action. PaLM-E generates high-level
plans while the policy unit provides low-level vision-guided motor control. If necessary, the plan
can be updated later based on new observations.
In considering Palm-E, we can focus on several different systems: the PaLM-E model itself,
the policy unit, or the complete system comprised of these two elements and the robot they control.
The complete system is very naturally described as an embodied agent. When given tasks,
it can make plans and execute them by moving its robotic “body” through spaces it shares with
humans. However, both of the main components of the system are trained, in effect, to imitate
human behaviours. PaLM-E is trained by self-supervised learning to predict the next token in
human-generated strings, and the policy unit is trained to imitate human visuomotor control. So
the system arguably imitates planning and using visuomotor control to execute plans, as opposed
to actually doing these things. It does not learn to pursue goals from feedback about success or
61
failure.
Since the complete system includes a robot, it is natural to describe it as embodied. However,
according to the account we have adopted, for a system to have an embodied perspective it must
model how its outputs affect the environment in order to distinguish itself from the environment in
perception or to facilitate motor control. It is hard to see how the complete PaLM-E system could
have learnt a model of this kind, given that it is not trained end-to-end and has, therefore, not been
exposed to the effects of its outputs on the environment in the course of training. The components
are also trained in environments in which there is little or no exogenous change, so the need to
learn to disambiguate sources of change in input is absent.
Perhaps the best case to be made for embodiment here focuses on the policy unit. This is a
Transformer-based network trained to map from video and text to continuous actions in imitation
of human control. In human motor control, a forward model (mapping outputs to predicted inputs)
is used to generate expectations for comparison to intentions and sensory inputs so that movement trajectories can be corrected in real time (McNamee & Wolpert 2019). This may involve
distinguishing the self from the environment, since exogenous events may be responsible for mismatches. Something like this mechanism might in principle be used by the policy unit because the
input to the network includes some observation history. This means that it could learn to detect a
mismatch between the observations it would have predicted given past states and those it is now
receiving and correct its actions accordingly. For example, if it is instructed to push a block East
and observes that the block is moving North as it acts, this could prompt a correction.
It could also be argued that the policy unit is an agent, even though it is not trained by RL. It can
learn sequences of inputs that are associated with progress towards a goal, specified by another part
of the input, and adjust its outputs so as to generate these sequences. However, it is questionable
whether this is enough for agency because although the system learns about sequences of inputs
and about which outputs to produce when confronted with these sequences, it does not learn how
its outputs affect inputs – so it cannot produce outputs because it expects them to help to generate
the right sequences. A similar objection can also be made against the case for embodiment: the
system can learn to detect “mismatches” between past and present observations in the context of a
task, but not between past observations and actions, on the one hand, and present observations on
the other. This is not to say that the policy unit definitively lacks agency and embodiment but to
illustrate the kinds of considerations that are relevant to these issues.
Given that controlling an avatar in a simulated environment can be enough for embodiment,
the “virtual rodent” of Merel et al. (2019) is a promising candidate for these attributes. It is trained
by RL, which is sufficient for agency. This system was constructed by implementing a virtual
“body” with 38 degrees of freedom based on the anatomy of laboratory rats. A recurrent LSTMbased actor-critic architecture was trained end-to-end by RL to control this body, using rich visual
and proprioceptive inputs, to perform four tasks in a static 3D environment. This architecture is
plausibly sufficient for the system to learn a model of how its outputs affect its inputs which it could
use in perception and action. Because recurrent networks are used, new inputs can be processed in
the context of stored representations of inputs and outputs from the recent past. So the system can,
in principle, process inputs and select outputs in the context of expectations generated from its past
behaviour—that is, in the context of outputs from a self-model, which would (perhaps implicitly)
represent information about stable properties of its body.
62
However, in this study, the environment did not change exogenously, and it appears the tasks
could have been solved by producing combinations of a set of stereotyped movements, such as
running, jumping and rearing. The analysis indicates that the system did learn a repertoire of
behaviours like these. These movements may not need ongoing control from perceptual feedback.
This raises a question about whether the task demands were sufficient to cause the system to learn
to use a self-model rather than a relatively simple input-output policy.
AdA, DeepMind’s “adaptive agent”, is also trained end-to-end by RL to control an avatar in a
3D virtual environment (DeepMind Adaptive Agents Team 2023). The system consists of a Transformer which encodes observations at the past few hundred timesteps (the exact figure varied in
the team’s experiments), including past actions and rewards as well as task instructions and sensory input and feeds into an LSTM which is trained to predict future actions, values and rewards.
This system was trained on a very wide range of tasks, of increasing difficulty, in order to cause
it to undergo meta-RL. This meant that it learnt an implicit online learning algorithm, allowing it
to learn to perform new tasks from observations in its memory—the Transformer encoding recent
past timesteps—without updating weights. After this training regime, the system was able to adapt
to new tasks in its environment at human timescales.
AdA is a significantly more powerful system than the virtual rodent, although it controls a much
less complex avatar. Its environment is somewhat less stable, including because some of the tasks
it performs involve cooperating with another agent, but the emphasis is on learning to generate
and test behavioural strategies for new tasks, rather than on coordinating complex dynamics. So
again we could question whether the system faces the kinds of challenges that seem to have been
responsible for the evolution of self-modelling in animals. However, unlike the virtual rodent,
it has a specific training objective to generate predictions based on past sequences of interleaved
inputs and outputs. AdA may, therefore, be the most likely of the three systems we have considered
to be embodied by our standards, despite not being physically embodied (like PaLM-E) or being
trained primarily for motor control of a complex avatar (like the virtual rodent).
63
4
Implications
In this final section, we discuss the topic of consciousness in AI in a broader context. We consider
risks from under- and over-attribution of consciousness to AI systems (in section 4.1) and the
relationship between consciousness and AI capabilities (in section 4.2). We also make some limited
recommendations, in section 4.3. Our comments in this section are brief—the main aim of this
report is to propose a scientific approach to consciousness in AI and to establish what current
scientific theories imply about this prospect, not to investigate its moral or social implications.
4.1
Attributing Consciousness to AI
There are risks on both sides of the debate over AI consciousness: risks associated with underattributing consciousness (i.e. failing to recognize it in AI systems that have it) and risks associated
with over-attributing consciousness (i.e. ascribing it to systems that are not really conscious). Just
as in other cases of uncertain consciousness, such as other animals (Birch 2018) and people with
disorders of consciousness (Peterson et al. 2015; Johnson 2022), we must consider both types of
risk.
4.1.1
Under-attributing consciousness to AI
As many authors have noted, as we develop increasingly sophisticated AI systems we will face
increasingly difficult questions about their moral status (Bryson 2010, Gunkel 2012, Schwitzgebel
& Garza 2015, 2020, Metzinger 2021, Shulman & Bostrom 2021). Philosophers disagree about the
exact relationship between being conscious and moral status, but it is very plausible that any entity
which is capable of conscious suffering deserves moral consideration. If we can reduce conscious
suffering, other things being equal, we ought to do so. This means that if we fail to recognise the
consciousness of conscious AI systems we may risk causing or allowing morally significant harms.
An analogy with non-human animals helps to illustrate the issue. Humans mistreat farmed
animals in very large numbers, motivated by powerful economic incentives. Whether or not this
mistreatment depends on a failure to attribute consciousness to these animals, it illustrates the potential problem. In the case of AI, there is likely to be considerable resistance to attributions of
consciousness, partly because developers of AI may have powerful economic incentives to downplay concerns about welfare. So if we build AI systems that are capable of conscious suffering, it
is likely that we will only be able to prevent them from suffering on a large scale if this capacity
is clearly recognised and communicated by researchers. However, given the uncertainties about
consciousness mentioned above, we may create conscious AI systems long before we recognise
we have done so.
An important point in this context is that being conscious is not the same as being capable
of conscious suffering. It is at least conceptually possible that there could be conscious systems
that have no valenced or affective conscious experiences—that is, no experiences that feel good
or bad to them (Carruthers 2018, Barlassina & Hayward 2019). If it is only valenced experiences
that have special moral significance, then the key question for establishing the moral status of AI
64
systems is whether they are capable of such experiences (that is, whether they are sentient, as
this term is sometimes used). We have not discussed neuroscientific or philosophical theories of
valence or otherwise investigated the prospects of specifically valenced conscious experience in
AI systems. Theories of valenced conscious experience are less mature than theories of visual
experience, suggesting an important priority for future work. However, we suspect that many
possible conscious systems which are also agents will have valenced experiences since agents
must evaluate options in order to select actions.
In short, the risk of under-attributing consciousness should be taken seriously. Failing to recognise conscious AI systems as such could lead us to cause unwarranted suffering to many conscious
beings.
4.1.2
Over-attributing consciousness to AI
There is also a significant chance that we could over-attribute consciousness to AI systems—indeed,
this already seems to be happening—and there are also risks associated with errors of this kind.
Most straightforwardly, we could wrongly prioritise the perceived interests of AI systems when
our efforts would better be directed at improving the lives of humans and non-human animals. As
Schwitzgebel and Garza (2015, 2020) argue, uncertainty about the moral status of AI systems is
dangerous because both under- and over-attribution can be costly.
Over-attribution is likely because humans have a well-established tendency to anthropomorphise and over-attribute human-like mental states to non-human systems. A growing body of work
examines the tendency of people to attribute consciousness and agency to artificial systems, as
well as the factors influencing this attribution (Dennett 1987, Gray & Wegner 2012, Kahn et al.
2006, Krach et al. 2008, Sytsma 2014). There may be various reasons for humans to have an
“agent bias”—a natural inclination to ascribe agency, intentions, and emotions to non-human entities—stemming from our evolutionary history (Guthrie 1993).
One possibility is that we might anthropomorphise AI systems because it seems to help us to
understand and predict their behaviour—although this impression could be false, with anthropomorphism in fact causing us to make incorrect interpretations. Anthropomorphism allows us to
understand and anticipate complex systems like AI using the same cognitive frameworks we use
for understanding humans, potentially helping us navigate interactions with AI (Epley et al., 2007).
Dennett postulates that individuals employ a cognitive strategy, called the “intentional stance”, to
predict and explain the behaviour of various entities, including humans, animals, and artificial systems (Dennett 1987). The intentional stance involves attributing mental states, such as beliefs,
desires, and intentions, to an entity to decipher and anticipate its behaviour. Observation and interaction with AI systems often lead to the natural adoption of the intentional stance, especially when
their behaviours appear purposeful or goal-directed. This tendency is further amplified when AI
systems exhibit human-like characteristics, such as natural language processing, facial expressions,
or adaptive learning capabilities (Mazor et al. 2021). Researchers have identified several factors
that predispose individuals to anthropomorphise AI systems, including their physical appearance,
behaviour, and perceived autonomy (Kahn et al. 2006; Złotowski et al. 2015).
Attributions of agency and consciousness to artificial agents may also be driven by an emotional need for social interaction (Mazor et al. 2021). Individuals who seek social interaction and
65
fulfillment from artificial systems may be more prone to attributing consciousness to them. Assigning human-like traits to AI can help people cope with difficult emotions or situations, such
as feeling more comfortable confiding in an AI that appears empathetic or understanding (Turkle
2011). The use of artificial systems such as Replika chatbots as sources of social interaction is
already evident.
The recent rapid progress in language model capabilities is particularly likely to drive overattribution of consciousness, as the case of Blake Lemoine arguably illustrates (Lemoine 2022).
Modern LLMs can convincingly imitate human discourse, making it difficult to resist the impression that one is interacting with a conscious agent, especially if the model is prompted to play the
role of a person in a conversation (Shanahan et al. 2023).
In addition to the risk of misallocation of resources which we mentioned above, over-attributing
consciousness to AI systems creates risks of at least three other kinds. First, if consciousness is
sometimes attributed to AI systems on weak grounds, these attributions may undermine betterevidenced claims of consciousness in AI. Observers of debates on this topic may recognise that
some attributions are weak, and assume that all are. This effect could be particularly powerful if
there are also reasonable concerns that attributions of consciousness to AI are distracting us from
addressing other pressing problems. Second, if we judge that a class of AI systems are conscious,
this should lead us to treat them differently—training them in different ways, for instance. In
principle, this could conflict with work to ensure that AI systems are developed in ways that benefit
society. And third, overattribution could interfere with valuable human relationships, as individuals
increasingly turn to artificial agents for social interaction and emotional support. People who do
this could also be particularly vulnerable to manipulation and exploitation.
Whatever one’s views about the relative importance of these various risks, they amount to a
powerful case for research on the prospect of consciousness in AI. If the development of AI is to
continue, this research will be crucial: it is risky to judge without good grounds either that no AI
systems can be conscious, or that those of a particular class are conscious.
4.2
Consciousness and Capabilities
In the popular imagination, consciousness is associated with free will, intelligence and the tendency
to feel human emotions, including empathy, love, guilt, anger and jealousy. So our suggestion that
conscious AI may be possible in the near-term might be taken to imply that we will soon have
AI systems akin to the very human-like AIs depicted in science fiction. Whether this in fact follows depends on the relationships between consciousness and other cognitive traits and capacities.
Furthermore, conscious AI systems are more likely to be built if consciousness is (or is expected
to be) associated with valuable capabilities in AI. So in this subsection, we briefly consider how
consciousness might be related to differences in AI systems’ behaviour and capabilities.
One possible argument for the view that we are likely to build conscious AI is that consciousness is associated with greater capabilities in animals, so we will build conscious AI systems in
the course of pursuing more capable AI. It is true that scientific theories of consciousness typically
claim that conscious experience arises in connection with adaptive traits, selected for the contributions they make to cognitive performance in humans and some other animals. For example, Baars
66
(1988, 1997) claims that the global workspace “optimizes the trade-off between organization and
flexibility” (1988, p. 348), a trade-off that advanced AI systems must also presumably manage.
A weakness of this argument is that human and animal minds are not necessarily a good guide
to the connection between consciousness and capabilities in artificial systems. This is because the
“design” of animal minds is explained not only by the adaptive value of our capabilities but also by
the constraints under which we evolved, which include limits on the quantity and form of data from
which we can learn; limits on the amount of energy available to power our minds; and the forms of
our ancestors’ minds and the availability of relevant mutations. The space of possible designs for
AI systems is different from the space of possible mind designs in biology (Summerfield 2022).
So we may well find ways to build high-performing AI systems which are not conscious.
However, some influential AI researchers are currently pursuing projects that aim to increase
AI capabilities by building systems that are more likely to be conscious. We have already discussed
the ongoing work by Bengio and colleagues which uses ideas from GWT. Goyal and Bengio (2022)
write that:
Our aim is to take inspiration from (and further develop) research into the
cognitive science of conscious processing, to deliver greatly enhanced AI,
with abilities observed in humans thanks to high-level reasoning.
The aim here is to build AI systems that implement at least some of the features underlying
consciousness in humans, specifically in order to enhance capabilities. Similarly, LeCun’s proposed architecture for autonomous intelligence has features such as a world model for planning
and a “configurator”, described as an element that “takes inputs from all other modules and configures [the other modules] for the task at hand” (LeCun 2022, p. 6). LeCun also suggests that
the existence of elements like these in the human brain may be responsible for what he calls “the
illusion of consciousness”. These are examples of a widespread and long-established practice in
AI of drawing on insights from the cognitive sciences (Hassabis et al. 2017, Zador et al. 2022).
So regardless of whether building in consciousness-associated features is the only possible route
to greater capabilities, it is one that we are likely to take.
Turning now to the issue of how conscious artificial systems are likely to behave, there are both
conceptual and empirical reasons to doubt that being conscious implies having human-like motives
or emotions. Conceptually, to be conscious is simply to have subjective experiences. In principle,
there could be conscious subjects who had experiences very unlike ours. In particular, there is no
apparent conceptual incoherence in the idea of motivationally neutral conscious experiences which
lack valence or affect—and even if a conscious subject does have valenced or affective states, these
may be triggered by different circumstances from those which trigger our emotions, and motivate
them to behave in different ways.
Empirically, the theories of consciousness we have discussed do not generally claim that consciousness implies human-like motives or emotions. One exception is the view that consciousness
is only possible in the context of self-maintenance, which we discussed in section 2.4.5, since
this presumably entails not only that conscious beings engage in self-maintenance, but that they
are motivated to do so. But this view is an outlier. Some theories, such as GWT and PRM, suggest that conscious subjects must be agents and perhaps that their desires are likely to enter into
67
conscious experience—in GWT, the workspace maintains representations that provide important
context for processing in the modules, and current desires might fit this description. But these theories are neutral about what motivates conscious subjects. AST is a somewhat more complicated
case: Graziano (2013) argues that the use of an attention schema is important for social cognition
because it allows one to model attention either in oneself or in others. He further claims that this
is a reason to build conscious AI because AI systems with attention schemas will be capable of
empathy (Graziano 2017). But the claim here seems to be that implementing AST is necessary for
attributing conscious states to others, and, therefore, for being motivated by empathy to help them,
not that consciousness is sufficient for empathetic motives.
Many current concerns about the impacts of AI do not turn on whether AI systems might
be conscious. For example, the concern that AI systems trained on data that reflects the current
structure of society could perpetuate or exacerbate injustices does not turn on AI consciousness.
Nor does the concern that AI could enable various forms of repression, or that AI systems could
replace human workers in most jobs (although the economic value of replacing human workers
may motivate capabilities research which leads to conscious AI, as we have noted). Perhaps most
surprisingly, arguments that AI could pose an existential risk to humanity do not assume consciousness. A typical argument for this conclusion relies on the premises that (i) we will build AI
systems that are very highly capable of making and executing plans to achieve goals and (ii) if we
give these systems goals that are not well chosen then the methods that they find to pursue them
may be extremely harmful (see e.g. Hilton 2022). Neither these premises nor the ways in which
they are typically elaborated and defended rely on AI systems being conscious.
4.3
Recommendations
Several authors have made important practical recommendations concerning the possibility of AI
consciousness. These include: Bryson’s (2010) case that conscious AI should be avoided; Metzinger’s (2021) call for a moratorium on work that could lead to conscious AI; Graziano’s (2017)
arguments in favour of conscious AI; Schwitzgebel and Garza’s (2020) argument that we should
only build particular AI systems if we can either be confident that they will be conscious, or be
confident that they will not be; and the detailed recommendations of Bostrom and Shulman (2022).
We have not assessed the arguments for these recommendations and do not consider them further
here.
However, we do recommend support for research on the science of consciousness and its application to AI (as recommended in the AMCS open letter on this subject; AMCS 2023), and the use
of the theory-heavy method in assessing consciousness in AI. One way that we can make progress
in learning which AI systems are likely to be conscious is by developing and testing scientific theories of consciousness; theoretical refinements within the existing paradigms are valuable, as well
as attempts to test predictions of competing theories, as in the ongoing Cogitate adversarial collaboration (Melloni et al. 2021). A second is by undertaking careful empirical research to extend
theories of consciousness to non-human animals. This will help us to establish a more general account of the correlates of consciousness, based on evidence from a wider range of cases (Andrews
& Birch 2023). And a third is research that refines theories of consciousness specifically in the
context of AI. Research of this kind may involve theorising about AI implementations of mecha68
nisms implicated in theories of consciousness; building such systems and testing their capacities;
identifying ambiguities in existing theories; and developing and defending more precise formulations of theories, so that their implications for AI are clearer. Integrating work of this kind with
continued empirical research on human and animal consciousness can be expected to be especially
productive.
Two other lines of research may be important. One is research specifically on valenced and
affective consciousness; if conscious experience of this kind is especially morally important, as
seems to be the case, then we have a pressing need for well-founded computational theories which
can be applied to AI. The other is efforts to develop better behavioural tests for consciousness in
AI. Although our view is that the theory-heavy approach is currently the most promising, it may
be possible that behavioural tests could be developed which are difficult to game and based on
compelling rationales, perhaps informed by theories. If such tests can be developed, they may
have practical advantages over theory-heavy assessments.
As we learn more about consciousness, and gain better tools to assess whether it may be present
in AI systems, we must also use these tools effectively. That means applying the theory-heavy
method as we develop new kinds of AI systems, both prospectively—in assessing the likelihood
of consciousness in planned systems, before we build them—and retrospectively. In retrospective
evaluation, methods for mechanistic interpretability may be important, since it is possible that
systems that do not have potentially consciousness-supporting features built in could acquire them
in the course of training. It also means that scientific theories should be central to consciousnessrelated AI policy and regulation.
Box 4: Open questions about consciousness in AI
This report is not the last word on AI consciousness. Far from it: one of our major aims is to
spur further research. Further progress in the neuroscience of consciousness will contribute
to our understanding of the conditions for consciousness in AI, and we have suggested that
research on consciousness in non-human animals may be particularly valuable. Here, we
highlight research questions that are relevant for understanding AI consciousness in particular.
Refining and extending our approach
While following the same basic approach as this report, further research could:
• Examine other plausible theories of consciousness, not considered in this report, and
use them to derive further indicators of consciousness;
• Refine or revise the indicators which we have derived from the theories considered
here;
• Conduct assessments of other AI systems, or investigate different ways in which the
indicators could be implemented.
Furthermore, our approach could be extended by developing a formal evaluation procedure
for consciousness that could be applied to AI systems, although it is questionable whether
69
this would be justified at present, in the context of significant uncertainty about computational functionalism and about particular scientific theories.
Computational functionalism and rival views
Determining whether consciousness is possible on conventional computer hardware is a difficult problem, but progress on it would be particularly valuable, and philosophical research
could contribute to such progress. For example, sceptics of computational functionalism
have noted that living organisms are not only self-maintaining homeostatic systems but are
made up of cells that themselves engage in active self-maintenance (e.g. Seth 2021, Aru et
al. 2023); further work could clarify why this might matter for consciousness. Research
might also examine whether there are features of standard computers which might be inconsistent with consciousness, but would not be present in unconventional (e.g. neuromorphic)
silicon hardware. A further topic for philosophical research is the individuation of AI systems, given that they can be copied, distributed, called in multiple places at once, and so
forth.
Valence and phenomenal character in AI
We have set aside the question of what kinds of experiences conscious AI systems might
have. In principle, these could be quite different from human experiences. An important
issue is what it would take for AI systems to be capable of having valenced conscious experiences—that is, ones that feel good or bad—because these might have special moral
significance. Research on computational theories of valence would help to address this issue.
AI interpretability research
A significant obstacle for the theory-heavy approach is our limited understanding of the
inner workings of complex deep learning systems. AI interpretability research seeks to illuminate and explain these workings, and can, therefore, contribute to many forms of research
on AI, including research on consciousness.
Behavioural tests and introspection
Although we have stressed the limitations of behavioural tests for consciousness in AI, we
are open to the possibility that compelling tests could be developed, so research towards this
end may be valuable. Behavioural tests need not be “theory-neutral”, but could be based
on specific scientific theories. Another possible approach is to develop AI systems with
reliable introspective capacities that could allow them to meaningfully report on their own
consciousness or lack thereof (Long forthcoming).
The ethics of research on AI consciousness
On balance, we believe that research to better understand the mechanisms which might
underlie consciousness in AI is beneficial. However, research on this topic runs the risk
of building (or enabling others to build) a conscious AI system, which should not be done
lightly. Mitigating this kind of risk should be carefully weighed against the value of better
understanding consciousness in AI.
70
Glossary
Term
AST
GWT
HOSS
HOT
PP
PRM
RPT
UAL
access consciousness
agency
algorithmic recurrence
assertoric force
attractor dynamics
backward masking
Bayesian inference
binocular rivalry
classical conditioning
cognitive architecture
Description
Attention schema theory
Global workspace theory
Higher-order state space theory
Higher-order theory
Predictive processing
Perceptual reality monitoring theory
Recurrent processing theory
Unlimited associative learning
“Functional” concept contrasted with phenomenal
consciousness; a state is access conscious if its content is
directly available to its subject to perform a wide range of
cognitive tasks such as report, reasoning, and rational action
Systems are agents if they pursue goals through interaction
with an environment (see section 2.4.5(a))
Form of processing in which the same operation is applied
repeatedly, such as processing in a neural network in which
information passes through layers with the same weights;
contrasted with implementational recurrence
A feature of some conscious experiences that present their
contents as accurately representing the world, disposing us to
form corresponding beliefs
The property of some dynamical systems that the system tends
to converge to one of a number of stable “attractor” states
Presenting a stimulus (mask) soon after a briefly-presented
target stimulus, with the effect that the first stimulus is not
consciously perceived
Inference according to Bayes’ Rule, which states that the
probability that a state holds given some data is proportional to
the prior probability of the state multiplied by the probability of
the data given the state
An experimental paradigm in which a different image is
presented to each eye, leading to perceptual alternations
between the images
A form of learning in which a neutral stimulus is paired with a
stimulus that triggers an innate response, such as approach or
avoidance, leading to an association between the previously
neutral stimulus and the response
The way in which functional units are arranged and connected
in a cognitive system
71
Term
computational
functionalism
confidence or credence
contrastive analysis
cross-attention
embodied, enactive and
extended cognition
end-to-end training
feature extraction
feature binding
feedforward processing
figure-ground segregation
first-order representations
forward models
generative model
global broadcast
goal-directed vs. habitual
behaviour
higher-order
representations
ignition
implementational
recurrence
Description
The thesis that implementing computations of a certain kind is
necessary and sufficient for consciousness (see section 1.2.1)
Degree of belief; the probability that one would assign to a
claim
Method in consciousness science in which conscious and
unconscious conditions, for example, conscious and
unconscious visual processing of a stimulus, are contrasted
with each other; e.g. to find corresponding differences in brain
activity
Process in AI allowing information to be selected and passed
from one part of a system to another (see Box 3)
The view that cognitive processes are deeply influenced by, and
sometimes employ, the body and environment
In machine learning, training all components of a system
together, as opposed to combining components trained
separately
Identifying features in visual scenes
Integrating the separate features of objects, for example
“yellow” and “square”, into a unified representation
Processing in which a non-repeating set of operations is applied
sequentially, as opposed to recurrent processing
Distinguishing objects from background in vision
Representations that are about the non-representational world,
in contrast with higher-order representations; paradigm cases
include the visual representation of an external object like an
apple
Models of how outputs will lead to changes in the body and
environment, especially in the context of motor control
A statistical model of input data (e.g. patterns of sensory
stimulation) that can be sampled to produce new synthetic data
In GWT, information being made available to all modules (see
section 2.2)
In psychology, distinction between behaviour that is caused by
representations of outcome values and action-outcome
contingencies (goal-directed) and behaviour that is caused by
representations of the values of actions in situations (habitual)
Representations that are about other representations (e.g. a
representation that another representation is reliable)
In GWT, a sudden, non-linear change in brain activity
associated with a state’s coming to be globally broadcast
Feature of computing systems, widespread in the brain, in
which algorithmic recurrence is implemented by feedback
loops passing information repeatedly through the same units
72
Term
indicators/indicator
properties
key-query attention
latent space
masked priming
experiments
metacognition
metacognitive monitoring
modules
multi-head attention layers
natural kind
no-report paradigm
neural correlates of
conscious states
perceptual organisation
perspective
phenomenal consciousness
phenomenal character
predictive coding
problem intuitions
Description
Properties identified in this work that make AI systems more
likely to be conscious
Process for selecting information in AI; cross-attention and
self-attention are forms of key-query attention (see Box 3)
Representation space representing variables that are not
directly observable, or architectural feature of an AI allowing
such a space to be learnt
Experiments in which a masked stimulus (see backward
masking) influences (typically, facilitates, i.e. primes) the
processing of a second, visible, stimulus
Cognition about one’s own cognitive processes, for example
about their reliability or accuracy
Monitoring of cognitive processes by other cognitive systems
(see section 2.3)
In GWT, specialised subsystems capable of performing tasks
independently (see section 2.1)
In Transformers, layers that implement variants of self- or
cross-attention in parallel
Collection of entities that have similar superficial properties as
a result of a shared underlying nature (e.g. gold, tigers);
consciousness may be a psychological/computational natural
kind
Experimental paradigm using contrastive analysis but with
other measures (e.g. brain activity, eye movements) used to
distinguish conscious and unconscious conditions
Minimal sets of neural events that are jointly sufficient for
conscious states
Generation in perception of a representation of an organised
scene, e.g. distinguishing objects and representing their relative
locations
Feature of embodied systems that their inputs depend on their
position in the environment and are affected by their
movements
Consciousness as we understand it in this report; see section 1.1
The content of an experience; what it is like for the subject to
have that experience
Form of computation described by the predictive processing
theory of cognition, in which a hierarchical generative model
predicts inputs and the state of the environment is estimated by
prediction error minimisation
Intuitions that humans have about consciousness that are
difficult to reconcile with materialism
73
Term
quality space
recurrent processing
reinforcement learning
self-attention
sentience
subjective experience
System 2 thought
theory-heavy approach
Transformer
valenced or affective
experiences
Description
The similarity space of phenomenal qualities, which are the
properties making up the phenomenal character of an
experience
See algorithmic recurrence and implementational
recurrence
Form of machine learning in which the objective is to maximise
cumulative reward through interaction with an environment
(see section 3.1.5); also a form of biological learning
Process in AI in which information about multiple input tokens
is integrated through pairwise interactions between functional
units; key process in Transformers (see Box 3)
Term sometimes, but not always, used synonymously with
“consciousness”; see section 1.1
Conscious experience; see section 1.1
Controlled, effortful, often verbalisable thought relying on
explicit knowledge; contrasted with more automatic System 1
thought in “dual-process” theories of cognition
Method for determining which systems are conscious based on
scientific theories of consciousness
Deep learning architecture, the basis for many large language
models and other recent AI systems that relies on the
multi-head attention mechanism (see section 3.2.1 and Box 3)
Experiences that feel good or bad, such as pleasure or pain
74
Bibliography
Alamia, A., Mozafari, M., Choksi, B., & VanRullen, R., 2023. On the role of feedback in image recognition under noise and adversarial attacks: A predictive coding perspective. Neural
Networks, 157, pp.280–287.
Albantakis, L., & Tononi, G., 2021. What we are is more than what we do. arXiv preprint
arXiv:2102.04219.
Ali, A., Ahmad, N., de Groot, E., Johannes van Gerven, M. A., & Kietzmann, T. C., 2022. Predictive coding is a consequence of energy efficiency in recurrent neural networks. Patterns, 3(12),
100639.
Andersson, P., Strandman, A. & Strannegård, C., 2019. Exploration strategies for homeostatic
agents. In Artificial General Intelligence: 12th International Conference, pp. 178-187.
Andrews, K., & Birch, J., 2023. To understand AI sentience, first understand it in animals. Aeon
Essays. Aeon. https://aeon.co/essays/to-understand-ai-sentience-first-understand-it-in-animals
Aru, J., Bachmann, T., Singer, W. & Melloni, L., 2012. Distilling the neural correlates of consciousness. Neuroscience & Biobehavioral Reviews, 36(2), pp.737-746.
Aru, J., Larkum, M., & Shine, J. M., 2023. The feasibility of artificial consciousness through the
lens of neuroscience. arXiv:2306.00915.
Baars, B. J., 1988. A Cognitive Theory of Consciousness. Cambridge University Press.
Baars, B. J., 1997. In the theatre of consciousness: Global workspace theory, a rigorous scientific
theory of consciousness. Journal of Consciousness Studies, 4(4), pp.292–309.
Bahdanau, D., Cho, K., & Bengio, Y., 2014. Neural machine translation by jointly learning to
align and translate. arXiv preprint arXiv:1409.0473.
Bao, C., Fountas, Z., Olugbade, T., & Bianchi-Berthouze, N., 2020. Multimodal data fusion based
on the global workspace theory. arXiv:2001.09485.
Barlassina, L., & Hayward, M. K., 2019. More of me! Less of me!: Reflexive imperativism about
affective phenomenal character. Mind, 128(512), pp.1013–1044.
Bartlett, P. L., Montanari, A., & Rakhlin, A., 2021. Deep learning: A statistical viewpoint. Acta
Numerica, 30, pp.87–201.
Bayne, T., 2010. The Unity of Consciousness. Oxford University Press.
Bayne, T., & Montague, M., 2011. Cognitive Phenomenology. Oxford University Press.
Bayne, T., Seth, A. K., & Massimini, M., 2020. Are there islands of awareness? Trends in Neurosciences, 43(1), pp.6–16.
Becker-Ehmck, P., Karl, M., Peters, J., & van der Smagt, P., 2020. Learning to fly via deep modelbased reinforcement learning. arXiv:2003.08876.
Belkin, M., Ma, S., & Mandal, S., 2018. To understand deep learning we need to understand
kernel learning. In Proceedings of the 35th International Conference on Machine Learning,
pp.541–549.
75
Bengio, Y., 2017. The consciousness prior. arXiv:1709.08568.
Bengio, E., Jain, M., Korablyov, M., Precup, D., & Bengio, Y., 2021. Flow network based generative models for non-iterative diverse candidate generation. arXiv:2106.04399.
Bengio, Y., Lahlou, S., Deleu, T., Hu, E. J., Tiwari, M., & Bengio, E., 2023. GFlowNet foundations. arXiv:2111.09266.
Bichot, N. P., Heard, M. T., DeGennaro, E. M., & Desimone, R., 2015. A source for feature-based
attention in the prefrontal cortex. Neuron, 88(4), pp.832-844.
Birch, J., 2018. Animal cognition and human values. Philosophy of Science, 85(5), pp.1026–1037.
Birch, J., 2020. Global workspace theory and animal consciousness. Philosophical Topics, 48(1),
pp.21–38.
Birch, J., Schnell, A. K., & Clayton, N. S., 2020. Dimensions of animal consciousness. Trends in
Cognitive Sciences, 24(10), pp.789–801.
Birch, J., Ginsburg, S., & Jablonka, E., 2020. Unlimited associative learning and the origins of
consciousness: A primer and some predictions. Biology & Philosophy, 35(6), p. 56.
Birch, J., 2022a. Materialism and the moral status of animals. The Philosophical Quarterly, 72(4),
pp.795–815.
Birch, J., 2022b. The search for invertebrate consciousness. Noûs, 56, pp.133–153.
Block, N., 1995. On a confusion about a function of consciousness. Behavioral and Brain Sciences, 18, pp.227–247.
Block, N., 1996. Mental paint and mental latex. Philosophical Issues, 7, pp.19–49.
Block, N., 2002. Some concepts of consciousness. Philosophy of Mind: Classical and Contemporary Readings. pp.206–218.
Block, N., 2007. Consciousness, accessibility, and the mesh between psychology and neuroscience. Behavioral and Brain Sciences, 30, pp.481–499.
Block, N., 2023. The Border Between Seeing and Thinking. Oxford University Press.
Bowers, J. S., Malhotra, G., Dujmović, M., Montero, M. L., Tsvetkov, C., Biscione, V., Puebla,
G., Adolfi, F., Hummel, J. E., Heaton, R. F., Evans, B. D., Mitchell, J., & Blything, R., 2022.
Deep problems with neural network models of human vision. Behavioral and Brain Sciences,
pp.1–74.
Breitmeyer, B. G., & Öğmen, H., 2006. Visual Masking: Time Slices Through Conscious and
Unconscious Vision (2nd ed.). Oxford University Press.
Bronfman, Z. Z., Ginsburg, S., & Jablonka, E., 2016. The transition to minimal consciousness
through the evolution of associative learning. Frontiers in Psychology, 7, 1954.
Brown, R., 2015. The HOROR theory of phenomenal consciousness. Philosophical Studies, 172,
pp.1783–1794.
Brown, R., Lau, H., & LeDoux, J. E., 2019. Understanding the higher-order approach to consciousness. Trends in cognitive sciences, 23, pp.754–768.
76
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam,
P., Sastry, G., & Askell, A., 2020. Language models are few-shot learners. Advances in neural
information processing systems, 33, pp.1877–1901.
Bryson, J., 2010. Robots should be slaves. Wilks (Ed.), Close Engagements with Artificial Companions. John Benjamins.
Burgess, C. P., Matthey, L., Watters, N., Kabra, R., Higgins, I., Botvinick, M., & Lerchner, A.,
2019. MONet: Unsupervised scene decomposition and representation. arXiv:1901.11390.
Butlin, P., 2022. Machine learning, functions and goals. Croatian Journal of Philosophy, 22(66),
pp.351–370.
Butlin, P., 2023. Reinforcement learning and artificial agency. Mind & Language.
Cabanac, M., 1992. Pleasure: The common currency. Journal of Theoretical Biology, 155(2),
pp.173–200.
Carruthers, P., 2018. Valence and value. Philosophy and Phenomenological Research, 97, pp.658–
680.
Carruthers, P., 2019. Human and Animal Minds: The Consciousness Questions Laid to Rest.
Oxford University Press.
Carruthers, P., & Gennaro, R., 2020. Higher-order theories of consciousness. E. N. Zalta (Ed.),
The Stanford Encyclopedia of Philosophy (Fall 2020 Edition).
Chalmers, D., 1995. Absent qualia, fading qualia, dancing qualia. Conscious Experience.
Chalmers, D., 1996. The Conscious Mind: In Search of a Fundamental Theory. Oxford University
Press.
Chalmers, D., 2000. What is a neural correlate of consciousness? Metzinger (Ed.), Neural Correlates of Consciousness: Conceptual and Empirical Questions. The MIT Press.
Chalmers, D., 2002. Consciousness and its place in nature. Chalmers (Ed.), Philosophy of Mind:
Classical and Contemporary Readings. Oxford University Press.
Chalmers, D., 2004. How can we construct a science of consciousness? Gazzaniga (Ed.), The
Cognitive Neurosciences III. The MIT Press.
Chalmers, D., 2013. Panpsychism and panprotopsychism. Amherst Lecture in Philosophy.
Chalmers, D., 2018. The meta-problem of consciousness. Journal of Consciousness Studies, 25,
pp.6–61.
Chalmers, D., 2023. Could a large language model be conscious? Boston Review.
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung,
H. W., Sutton, C., Gehrmann, S., & Schuh, P., 2022. PaLM: Scaling language modeling with
pathways. arXiv:2204.02311
Clark, A., 2000. A Theory of Sentience. Oxford University Press.
Clark, A., 2008. Supersizing the Mind: Embodiment, Action, and Cognitive Extension. Oxford
University Press.
77
Clark, A., 2019. Consciousness as generative entanglement. Journal of Philosophy, 116, pp.645–
662.
Cleeremans, A., Achoui, D., Beauny, A., Keuninckx, L., Martin, J. R., Muñoz-Moldes, S., Vuillaume, L., & Heering, A., 2020. Learning to be conscious. Trends in Cognitive Sciences 24,
pp.112–123.
Conwell, C., & Ullman, T., 2022. Testing relational understanding in text-guided image generation. arXiv:2208.00005.
Crick, F., & Koch, C., 1990. Towards a neurobiological theory of consciousness. Seminars in the
Neurosciences. Saunders Scientific Publications, pp.263–275.
Dainton, B., 2000. Stream of Consciousness: Unity and Continuity in Conscious Experience.
Routledge.
Dainton, B., 2023. Temporal consciousness. E. N. Zalta & U. Nodelman (Eds.) The Stanford
Encyclopedia of Philosophy (Spring 2023 Edition).
Deane, G., 2021. Consciousness in active inference: Deep self-models, other minds, and the
challenge of psychedelic-induced ego-dissolution. Neuroscience of Consciousness, 2021(2),
niab024.
Dehaene, S., & Changeux, J. P., 2011. Experimental and theoretical approaches to conscious
processing. Neuron, 70, pp.200–227.
Dehaene, S., Kerszberg, M., & Changeux, J. P., 1998. A neuronal model of a global workspace in
effortful cognitive tasks. In Proceedings of the National Academy of Sciences, 95(24). 14529–
14534.
Dehaene, S., Lau, H., & Kouider, S., 2017. What is consciousness, and could machines have it?
Science, 358, pp.486–492.
Dehaene, S., & Naccache, L., 2001. Towards a cognitive neuroscience of consciousness: Basic
evidence and a workspace framework. Cognition, 79, pp.1–37.
Dehaene, S., Sergent, C., & Changeux, J. P., 2003. A neuronal network model linking subjective reports and objective physiological data during conscious perception. Proceedings of the
National Academy of Sciences, 100, 8520–8525.
Dehaene, S., 2014. Consciousness And the Brain: Deciphering How the Brain Codes Our Thoughts.
Viking.
Dennett, D. C., 1987. The Intentional Stance. The MIT Press.
Dijkstra, N., Bosch, S. E., & Gerven, M. A. J. van., 2019. Shared neural mechanisms of visual
perception and imagery. Trends in Cognitive Sciences, 23(5), pp.423–434.
Dijkstra, N., van Gaal, S., Geerligs, L., Bosch, S. E., & van Gerven, M. A. J., 2021. No evidence for neural overlap between unconsciously processed and imagined stimuli. ENeuro, 8(5),
ENEURO.0228-21.2021.
Dijkstra, N., Kok, P., & Fleming, S. M., 2022. Imagery adds stimulus-specific sensory evidence to
perceptual detection. Journal of Vision, 22(2), 11.
78
Dijkstra, N., & Fleming, S. M., 2023. Subjective signal strength distinguishes reality from imagination. Nature Communications, 14(1), Article 1.
Doerig, A., Schurger, A., Hess, K., & Herzog, M. H., 2019. The unfolding argument: Why IIT and
other causal structure theories cannot explain consciousness. Consciousness and Cognition, 72,
pp.49–59.
Dolan, R. J., & Dayan, P., 2013. Goals and habits in the brain. Neuron, 80(2), pp.312–325.
Dretske, F., 1988. Explaining Behavior: Reasons in a World of Causes. The MIT Press.
Dretske, F., 1999. Machines, plants and animals: The origins of agency. Erkenntnis, 51(1), pp.19–
31.
Driess, D., Xia, F., Sajjadi, M. S. M., Lynch, C., Chowdhery, A., Ichter, B., Wahid, A., Tompson,
J., Vuong, Q., Yu, T., Huang, W., Chebotar, Y., Sermanet, P., Duckworth, D., Levine, S., Vanhoucke, V., Hausman, K., Toussaint, M., Greff, K., & Florence, P., 2023. PaLM-E: An embodied
multimodal language model. arXiv:2303.03378.
Dulberg, Z., Dubey, R., Berwian, I. M., & Cohen, J. D., 2023. Having multiple selves helps
learning agents explore and adapt in complex changing worlds. Proceedings of the National
Academy of Sciences, 120(28), e2221180120.
Elamrani, A., & Yampolskiy, R., 2019. Reviewing tests for machine consciousness. Journal of
Consciousness Studies, 26, pp.35-64.
Elhage, N., Nanda, N., Olsson, C., Henighan, T., Joseph, N., Mann, B., Askell, A., Bai, Y., Chen,
A., Conerly, T., DasSarma, N., Drain, D., Ganguli, D., Hatfield-Dodds, Z., Hernandez, D., Jones,
A., Kernion, J., Lovitt, L., Ndousse, K., Amodei, D., Brown, T., Clark, J., Kaplan, J., McCandlish, S., & Olah, C. 2021. A mathematical framework for transformer circuits. Transformer
Circuits Thread. https://transformer-circuits.pub/
Epley, N., Waytz, A., & Cacioppo, J. T., 2007. On seeing human: A three-factor theory of anthropomorphism. Psychological Review, 114(4), pp.864–886.
Evans, G., 1982. The Varieties of Reference. Oxford University Press.
Finn, C., Goodfellow, I., & Levine, S., 2016. Unsupervised learning for physical interaction
through video prediction. Advances in Neural Information Processing Systems, 29.
Fleming, S. M., 2020. Awareness as inference in a higher-order state space. Neuroscience of
consciousness, 2020, 020.
Fodor, J. A., 1983. The Modularity of Mind: An Essay on Faculty Psychology. The MIT Press.
Francken, J. C., Beerendonk, L., Molenaar, D., Fahrenfort, J. J., Kiverstein, J. D., Seth, A. K., &
van Gaal, S., 2022. An academic survey on theoretical foundations, common assumptions and
the current state of consciousness science. Neuroscience of Consciousness, 2022, niac011.
Frankish, K., 2016. Illusionism as a theory of consciousness. Journal of Consciousness Studies,
23, pp.11–39.
Franklin, S., & Graesser, A., 1999. A software agent model of consciousness. Consciousness and
Cognition, 8(3), pp.285–301.
79
Friedrich, J., Golkar, S., Farashahi, S., Genkin, A., Sengupta, A., & Chklovskii, D., 2021. Neural
optimal feedback control with local learning rules. Advances in Neural Information Processing
Systems, 34, 16358–16370.
Friston, K., 2010. The free-energy principle: a unified brain theory? Nature Reviews Neuroscience,
11, pp.127–138.
Gershman, S. J., 2019. The generative adversarial brain. Frontiers in Artificial Intelligence, 2, 18.
Ginsburg, S., & Jablonka, E., 2019. The Evolution of the Sensitive Soul: Learning and the Origins
of Consciousness. The MIT Press.
Godfrey-Smith, P., 2016. Mind, matter, and metabolism. The Journal of Philosophy, 113, pp.481–
506.
Godfrey-Smith, P., 2019. Evolving across the explanatory gap. Philosophy, Theory, and Practice
in Biology, 11(1).
Goff, P., 2017. Consciousness and Fundamental Reality. Oxford University Press.
Golan, T., Raju, P. C., & Kriegeskorte, N., 2020. Controversial stimuli: Pitting neural networks
against each other as models of human cognition. In Proceedings of the National Academy of
Sciences, 117(47), 29330–29337.
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A.,
& Bengio, Y., 2014. Generative adversarial networks. arXiv:1406.2661.
Goyal, A., Lamb, A., Gampa, P., Beaudoin, P., Levine, S., Blundell, C., Bengio, Y., & Mozer, M.
2020. Object files and schemata: Factorizing declarative and procedural knowledge in dynamical systems. arXiv:2006.16225.
Goyal, A., & Bengio, Y., 2022. Inductive biases for deep learning of higher-level cognition. Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 478(2266),
20210068.
Goyal, A., Didolkar, A., Lamb, A., Badola, K., Ke, N. R., Rahaman, N., Binas, J., Blundell, C.,
Mozer, M., & Bengio, Y., 2022. Coordination among neural modules through a shared global
workspace. arXiv preprint arXiv:2103.01197.
Gray, K., & Wegner, D. M., 2012. Feeling robots and human zombies: Mind perception and the
uncanny valley. Cognition, 125(1), pp.125–130.
Graziano, M. S., 2013. Consciousness and the Social Brain. Oxford University Press.
Graziano, M. S., 2017. The attention schema theory: a foundation for engineering artificial consciousness. Frontiers in Robotics and AI, 4(60).
Graziano, M. S., 2019a. Rethinking Consciousness: A Scientific Theory of Subjective Experience.
WW Norton & Company.
Graziano, M. S., 2019b. We are machines that claim to be conscious. Journal of Consciousness
Studies, 26, pp.95–104.
Greff, K., van Steenkiste, S., & Schmidhuber, J., 2020. On the binding problem in artificial neural
networks. arXiv:2012.05208.
80
Gunkel, D. J., 2012. The Machine Question: Critical Perspectives on AI, Robots, and Ethics. The
MIT Press.
Guthrie, S., 1993. Faces in the Clouds: A New Theory of Religion. Oxford University Press.
Harnad, S., 2003. Can a machine be conscious? How? Journal of Consciousness Studies, 10(4–4),
pp.69–75.
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M., 2017. Neuroscience-inspired artificial intelligence. Neuron, 95(2), pp.245–258.
Herzog, M. H., Drissi-Daoudi, L., & Doerig, A., 2020. All in good time: Long-lasting postdictive
effects reveal discrete perception. Trends in Cognitive Sciences, 24(10), pp. 826–837.
Heyes, C., & Dickinson, A., 1990. The intentionality of animal action. Mind & Language, 5,
pp.87–103.
Hohwy, J., 2022. Conscious self-evidencing. Review of Philosophy and Psychology, 13(4), pp.809–
828.
Hu, E. J., Malkin, N., Jain, M., Everett, K., Graikos, A., & Bengio, Y., 2023. GFlowNet-EM for
learning compositional latent variable models. arXiv:2302.06576.
Hurley, S. L., 1998. Consciousness in Action. Harvard University Press.
Irvine, E., 2013. Measures of consciousness. Philosophy Compass, 8(3), pp.285–297.
Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., & Carreira, J., 2021a. Perceiver:
General perception with iterative attention. International Conference on Machine Learning.
PMLR, pp.4651–4664.
Jaegle, A., Borgeaud, S., Alayrac, J.-B., Doersch, C., Ionescu, C., Ding, D., Koppula, S., Zoran,
D., Brock, A., Shelhamer, E., 2021b. Perceiver IO: A general architecture for structured inputs
& outputs. arXiv:2107.14795.
Ji, X., Elmoznino, E., Deane, G., Constant, A., Dumas, G., Lajoie, G., Simon, J., & Bengio, Y.,
2023. Sources of richness and ineffability for phenomenally conscious states. arXiv:2302.06403.
Johnson, L. S. M., 2022. The Ethics of Uncertainty: Entangled Ethical and Epistemic Risks in
Disorders of Consciousness. Oxford University Press.
Juechems, K., & Summerfield, C., 2019. Where does value come from? Trends in Cognitive
Sciences, 23(10), pp.836–850.
Juliani, A., Kanai, R., & Sasai, S. S., 2022. The Perceiver architecture is a functional global
workspace. In Proceedings of the Annual Meeting of the Cognitive Science Society, 44(44).
Kahn, P. H., Freier, N. G., Kanda, T., Ishiguro, H., Ruckert, J. H., Severson, R. L., & Kane, S.
K., 2008. Design patterns for sociality in human-robot interaction. In Proceedings of the 3rd
ACM/IEEE International Conference on Human Robot Interaction, pp.97–104.
Kahneman, D., 2011. Thinking, Fast and Slow. Farrar, Straus and Giroux.
Keramati, M., & Gutkin, B., 2014. Homeostatic reinforcement learning for integrating reward
collection and physiological stability. ELife, 3, e04811.
Kietzmann, T. C., Spoerer, C. J., Sörensen, L. K. A., Cichy, R. M., Hauk, O., & Kriegeskorte,
81
N., 2019. Recurrence is required to capture the representational dynamics of the human visual
system. Proceedings of the National Academy of Sciences, 116(43), 21854–21863.
Kiverstein, J., 2007. Could a robot have a subjective point of view? Journal of Consciousness
Studies, 14, pp.127–139.
Clark, A., & Kiverstein, J., 2007. Experience and agency: Slipping the mesh. Behavioral and
Brain Sciences, 30(5–6), pp.502–503.
Krach, S., Hegel, F., Wrede, B., Sagerer, G., Binkofski, F., & Kircher, T., 2008. Can machines
think? Interaction and perspective taking with robots investigated via fMRI. PLOS ONE, 3(7),
e2597.
Kriegeskorte, N., 2015. Deep neural networks: A new framework for modeling biological vision
and brain information processing. Annual Review of Vision Science, 1(1) pp.417–46.
Krizhevsky, A., Sutskever, I., & Hinton, G. E., 2012. ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 25.
Lamme, V. A. F., 2006. Towards a true neural stance on consciousness. Trends in Cognitive
Sciences, 10(11), pp.494–501.
Lamme, V. A. F., 2010. How neuroscience will change our view on consciousness. Cognitive
Neuroscience, 1(3), pp.204–220.
Lamme, V. A. F., 2020. Visual functions generate conscious seeing. Frontiers in Psychology, 11,
83.
Lau, H., 2019. Consciousness, metacognition, & perceptual reality monitoring. PsyArXiv.
Lau, H., 2022. In Consciousness we Trust: The Cognitive Neuroscience of Subjective Experience.
Oxford University Press.
Lau, H. C., & Passingham, R. E., 2006. Relative blindsight in normal observers and the neural
correlate of visual consciousness. Proceedings of the National Academy of Sciences, 103(49),
18763–18768.
Lau, H., & Rosenthal, D., 2011. Empirical support for higher-order theories of conscious awareness. Trends in Cognitive Sciences, 15(8), pp.365–373.
LeCun, Y., Bengio, Y., & Hinton, G., 2015. Deep learning. Nature, 521, pp.436–444.
Lee, A. Y., 2022. Degrees of consciousness. Noûs.
Lemoine, B., 2022, June 14. Scientific data and religious opinions. Medium. https://
cajundiscordian.medium.com/scientific-data-and-religious-opinionsff9b0938fc10
Lindsay, G. W., 2020. Attention in psychology, neuroscience, and machine learning. Frontiers in
computational neuroscience, 14, 29.
Lindsay, G. W., 2021. Convolutional neural networks as a model of the visual system: Past,
present, and future. Journal of Cognitive Neuroscience, 33(10), pp.2017–2031.
Liu, D., Bolotta, S., Zhu, H., Bengio, Y., & Dumas, G., 2023. Attention schema in neural agents.
arXiv:2305.17375.
82
Long, R., forthcoming. Introspective capabilities in large language models. Journal of Consciousness Studies.
Lotter, W., Kreiman, G., & Cox, D., 2017. Deep predictive coding networks for video prediction
and unsupervised learning. arXiv:1605.08104.
Lotter, W., Kreiman, G., & Cox, D., 2020. A neural network trained for prediction mimics diverse
features of biological neurons and perception. Nature Machine Intelligence, 2(4), Article 4.
Lycan, W. G., 2001. A simple argument for a higher-order representation theory of consciousness.
Analysis, 61(3–4).
Lynch, C., Wahid, A., Tompson, J., Ding, T., Betker, J., Baruch, R., Armstrong, T., & Florence, P.,
2022. Interactive language: Talking to robots in real time. arXiv:2210.06407.
Malach, R., 2021. Local neuronal relational structures underlying the contents of human conscious
experience. Neuroscience of Consciousness, 2021, niab028.
Malach, R., 2022. The role of the prefrontal cortex in conscious perception: The localist perspective. Journal of Consciousness Studies, 29(7–8), pp.93–114.
Man, K., & Damasio, A., 2019. Homeostasis and soft robotics in the design of feeling machines.
Nature Machine Intelligence, 1(10) pp.446–452.
Marr, D., 1982. Vision: A Computational Investigation Into the Human Representation and Processing of Visual Information. W.H. Freeman.
Mashour, G. A., Roelfsema, P., Changeux, J. P., & Dehaene, S., 2020. Conscious processing and
the global neuronal workspace hypothesis. Neuron, 105, pp.776–798.
Maturana, H. R., & Varela, F. J., 1991. Autopoiesis and cognition: The realization of the living.
Springer.
Mazor, M., Risoli, A., Eberhardt, A., & Fleming, S. M., 2021. Dimensions of moral status. In
Proceedings of the Annual Meeting of the Cognitive Science Society, 43(43).
McNamee, D., & Wolpert, D. M., 2019. Internal models in biological control. Annual Review of
Control, Robotics, and Autonomous Systems, 2(1), pp.339–364.
Mediano, P. A. M., Rosas, F. E., Bor, D., Seth, A. K., & Barrett, A. B., 2022. The strength of weak
integrated information theory. Trends in Cognitive Sciences, 26(8), pp.646–655.
Mehrer, J., Spoerer, C. J., Jones, E. C., Kriegeskorte, N., & Kietzmann, T. C., 2021. An ecologically motivated image dataset for deep learning yields better models of human vision. Proceedings of the National Academy of Sciences, 118(8), e2011417118.
Melloni, L., Mudrik, L., Pitts, M., & Koch, C., 2021. Making the hard problem of consciousness
easier. Science, 372, 911–912.
Merel, J., Aldarondo, D., Marshall, J., Tassa, Y., Wayne, G., & Ölveczky, B., 2019. Deep neuroethology of a virtual rodent. arXiv:1911.09451.
Merker, B., 2005. The liabilities of mobility: A selection pressure for the transition to consciousness in animal evolution. Consciousness and Cognition, 14, pp.89–114.
Merker, B., 2007. Consciousness without a cerebral cortex: A challenge for neuroscience and
medicine. Behavioral and Brain Sciences, 30(1), pp.63–81.
83
Metzinger, T., 2021. Artificial suffering: An argument for a global moratorium on synthetic phenomenology. Journal of Artificial Intelligence and Consciousness, 8, pp.43–66.
Miall, R. C., & Wolpert, D. M., 1996. Forward models for physiological motor control. Neural
Networks, 9(8), 1265–1279.
Michel, M., 2022. Conscious perception and the prefrontal cortex a review. Journal of Consciousness Studies, 29, pp.115–157.
Michel, M., forthcoming. The perceptual reality monitoring theory. M. Herzog, A. Schurger, &
A. Doerig (Eds.), Scientific Theories of Consciousness: The Grand Tour. Cambridge University
Press.
Michel, M., & Doerig, A., 2022. A new empirical challenge for local theories of Consciousness.
Mind & Language, 37(5), pp.840–855.
Michel, M., & Lau, H., 2021. Higher-order theories do just fine. Cognitive Neuroscience, 12,
77–78.
Michel, M., & Morales, J., 2020. Minority reports: Consciousness and the prefrontal cortex. Mind
& Language, 35(4), pp.493–513.
Millidge, B., Salvatori, T., Song, Y., Bogacz, R., & Lukasiewicz, T., 2022. Predictive coding:
towards a future of deep learning beyond backpropagation? arXiv:2202.09467.
Mnih, V., Heess, N., & Graves, A., 2014. Recurrent models of visual attention. Advances in neural
information processing systems, 27.
Morales, J., Odegaard, B., & Maniscalco, B., 2022. The neural substrates of conscious perception
without performance confounds. F. De Brigard & W. Sinnott-Armstrong (Eds.), Neuroscience
and Philosophy. The MIT Press.
Nagel, T., 1974. What is it like to be a bat? The Philosophical Review, 83, pp.435–450.
Nave, K., Deane, G., Miller, M., & Clark, A., 2022. Expecting some action: Predictive processing
and the construction of conscious experience. Review of Philosophy and Psychology, 13(4),
1019–1037.
Noe, A., 2004. Action in Perception. The MIT Press.
Noudoost, B., Chang, M. H., Steinmetz, N. A., Moore, T., 2010. Top-down control of visual
attention. Current Opinion in Neurobiology, 20(2), pp.183-190.
Oizumi, M., Albantakis, L., & Tononi, G., 2014. From the phenomenology to the mechanisms of
consciousness: Integrated information theory 3.0. PLOS Computational Biology 10, e1003588.
Olah, C., Satyanarayan, A., Johnson, I., Carter, S., Schubert, L., Ye, K., & Mordvintsev, A., 2018.
The building blocks of interpretability. Distill, 3.
Oord, A. van den, Li, Y., & Vinyals, O., 2019. Representation learning with contrastive predictive
coding. arXiv:1807.03748.
Oprea, S., Martinez-Gonzalez, P., Garcia-Garcia, A., Castro-Vargas, J. A., Orts-Escolano, S.,
Garcia-Rodriguez, J., & Argyros, A., 2022. A review on deep learning techniques for video
prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(6), 2806–2826.
84
O’Regan, J. K., & Noë, A., 2001. A sensorimotor account of vision and visual consciousness.
Behavioral and Brain Sciences, 24, pp.939–973.
Panagiotaropoulos, T. I., Deco, G., Kapoor, V., & Logothetis, N. K., 2012. Neuronal discharges
and gamma oscillations explicitly reflect visual consciousness in the lateral prefrontal cortex.
Neuron, 74(5), pp.924–935.
Pang, Z., O’May, C. B., Choksi, B., & VanRullen, R., 2021. Predictive coding feedback results in
perceived illusory contours in a recurrent neural network. Neural Networks, 144, pp.164–175.
Papineau, D., 2002. Thinking About Consciousness. Oxford University Press.
Peters, M. A. K., & Lau, H., 2015. Human observers have optimal introspective access to perceptual processes even for visually masked stimuli. ELife, 4, e09651.
Peterson, A., Cruse, D., Naci, L., Weijer, C., & Owen, A. M., 2015. Risk, diagnostic error, and the
clinical science of consciousness. NeuroImage: Clinical, 7, pp.588–597.
Phillips, I., 2018a. The methodological puzzle of phenomenal consciousness. Philosophical Transactions of the Royal Society B: Biological Sciences 373, 20170347.
Phillips, I., 2018b. Consciousness, time, and memory. The Routledge Handbook of Consciousness
(pp.286–297). Routledge.
Prosser, S., 2016. Experiencing Time. Oxford University Press.
Quilty-Dunn, J., Porot, N., & Mandelbaum, E., 2022. The best game in town: The re-emergence
of the language of thought hypothesis across the cognitive sciences. Behavioral and Brain
Sciences, pp.1–55.
Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., & Sutskever, I., 2019. Language models are
unsupervised multitask learners. OpenAI blog 1, 9
Reynolds, J. H., & Heeger, D.J., 2009. The normalization model of attention. Neuron, 61(2),
pp.168-185.
Rosenthal, D., 2005. Consciousness and Mind. Clarendon Press.
Rosenthal, D., 2010. How to think about mental qualities. Philosophical Issues, 20(1), pp.368–
393.
Russell, S., & Norvig, P., 2010. Artificial Intelligence: A Modern Approach (3rd Edition). PrenticeHall.
Sajjadi, M. S. M., Duckworth, D., Mahendran, A., van Steenkiste, S., Pavetić, F., Lučić, M.,
Guibas, L. J., Greff, K., & Kipf, T., 2022. Object scene representation transformer. arXiv:2206.06922.
Salti, M., Monto, S., Charles, L., King, J.-R., Parkkonen, L., & Dehaene, S., 2015. Distinct cortical
codes and temporal dynamics for conscious and unconscious percepts. ELife, 4, e05652.
Savage, J. E., 1972. Computational work and time on finite machines. Journal of the ACM, 19(4),
pp.660–674.
Schneider, S., 2019. Artificial You: AI and the Future of Your Mind. Princeton University Press.
Schwitzgebel, E., 2016. Phenomenal consciousness, defined and defended as innocently as I can
manage. Journal of Consciousness Studies, 23, pp.224–235.
85
Schwitzgebel, E., 2021. Belief. In E. N. Zalta (Ed.), The Stanford Encyclopedia of Philosophy
(Winter 2021). Metaphysics Research Lab, Stanford University.
Schwitzgebel, E. (forthcoming). Borderline consciousness, when it’s neither determinately true
nor determinately false that experience is present. Philosophical Studies.
Schwitzgebel, E., & Garza, M., 2015. A defense of the rights of artificial intelligences. Midwest
Studies in Philosophy, 39(1), pp.98–119.
Schwitzgebel, E., & Garza, M., 2020. Designing AI with rights, consciousness, self-respect, and
freedom. Liao (Ed.), Ethics of Artificial Intelligence. Oxford University Press.
Searle, J. R., 1980. Minds, brains, and programs. Behavioral and Brain Sciences, 3(3) pp.417-457
Seth, A., 2021. Being You: A New Science of Consciousness. Penguin.
Seth, A. K., & Bayne, T., 2022. Theories of consciousness. Nature Reviews Neuroscience, pp.1–
14.
Seth, A. K., & Hohwy, J., 2021. Predictive processing as an empirical theory for consciousness
science. Cognitive Neuroscience, 12, 89–90.
Shanahan, M., 2006. A cognitive architecture that combines internal simulation with a global
workspace. Consciousness and Cognition 15, pp.433–449.
Shanahan, M., 2010. Embodiment and the Inner Life: Cognition and Consciousness in the Space
of Possible Minds. Oxford University Press.
Shanahan, M., McDonell, K., & Reynolds, L., 2023. Role-play with large language models.
arXiv:2305.16367.
Shevlin, H., 2021. Non-human consciousness and the specificity problem: A modest theoretical
proposal. Mind & Language, 36(2), pp.297–314.
Shulman, C., & Bostrom, N., 2021. Sharing the world with digital minds. S. Clarke, H. Zohny, &
J. Savulescu (Eds.), Rethinking Moral Status. Oxford University Press.
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser,
J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T., & Hassabis, D., 2016. Mastering the game of Go with deep neural networks and tree search. Nature,
529(7587), Article 7587.
Simon, J. A., 2017. Vagueness and zombies: Why ‘phenomenally conscious’ has no borderline
cases. Philosophical Studies, 174(8), 2105–2123.
Sprevak, M. D., 2007. Chinese rooms and program portability. The British Journal for the Philosophy of Science 58, pp.755-776.
Stich, S. P., 1978. Beliefs and subdoxastic states. Philosophy of Science, 45, pp.499–518.
Strawson, G., 1994. Mental Reality. The MIT Press.
Strawson, G., 2006. Realistic monism: Why physicalism entails panpsychism. Journal of Consciousness Studies, 13, pp.3-31.
Summerfield, C., 2023. Natural General Intelligence: How Understanding the Brain Can Help Us
86
Build AI. Oxford University Press.
Sutton, R., & Barto, A., 2018. Reinforcement Learning (2nd Edition). The MIT Press.
Sytsma, J., 2014. Attributions of consciousness. Wiley Interdisciplinary Reviews. Cognitive Science, 5(6), pp.635–648.
Thompson, E., 2005. Sensorimotor subjectivity and the enactive approach to experience. Phenomenology and the Cognitive Sciences, 4(4), pp.407–427.
Thompson, E., 2007. Mind in Life: Biology, Phenomenology, and the Sciences of Mind. Harvard
University Press.
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H. T., Jin, A., Bos, T.,
Baker, L., Du, Y., Li, Y., Lee, H., Zheng, H. S., Ghafouri, A., Menegali, M., Huang, Y., Krikun,
M., Lepikhin, D., Qin, J., . . . Le, Q. 2022. LaMDA: Language models for dialog applications.
arXiv:2201.08239.
Tishby, N., Pereira, F. C., & Bialek, W., 2000. The information bottleneck method. arXiv:physics/0004057.
Todorov, E., & Jordan, M. I., 2002. Optimal feedback control as a theory of motor coordination.
Nature Neuroscience, 5(11), Article 11.
Tononi, G., & Koch, C., 2015. Consciousness: here, there and everywhere? Philosophical Transactions of the Royal Society B: Biological Sciences, 370, 20140167.
Treue, S. & Trujillo & J. C. M., 1999. Feature-based attention influences motion processing gain
in macaque visual cortex. Nature, 399(6736), pp.575-579.
Tsuchiya, N., Wilke, M., Frässle, S., & Lamme, V. A. F., 2015. No-Report paradigms: Extracting
the true neural correlates of consciousness. Trends in Cognitive Sciences, 19(12), pp.757–770.
Turkle, S., 2011. Alone Together: Why We Expect More from Technology and Less from Each
Other. Basic Books, Inc.
Tye, M., 1995. Ten Problems of Consciousness: A Representational Theory of the Phenomenal
Mind. The MIT Press.
Udell, D. B., & Schwitzgebel, E., 2021. Susan Schneider’s proposed tests for AI consciousness:
Promising but flawed. Journal of Consciousness Studies, 28(5–6), pp.121–144.
van Vugt, B., Dagnino, B., Vartak, D., Safaai, H., Panzeri, S., Dehaene, S., & Roelfsema, P. R.,
2018. The threshold for conscious report: Signal loss and response bias in visual and frontal
cortex. Science, 360(6388), pp.537–542.
VanRullen, R., 2016. Perceptual cycles. Trends in Cognitive Sciences, 20(10), pp.723–735.
VanRullen, R., & Kanai, R., 2021. Deep learning and the global workspace theory. Trends in
Neurosciences, 44, pp.692–704.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I., 2023. Attention is all you need. arXiv:1706.03762.
Vorberg, D., Mattler, U., Heinecke, A., Schmidt, T., & Schwarzbach, J., 2003. Different time
courses for visual perception and action priming. In Proceedings of the National Academy of
Sciences, 100(10), 6275–6280.
87
Webb, T. W., & Graziano, M. S. A., 2015. The attention schema theory: A mechanistic account of
subjective awareness. Frontiers in Psychology, 6.
Whyte, C. J., 2019. Integrating the global neuronal workspace into the framework of predictive
processing: Towards a working hypothesis. Consciousness and Cognition, 73, 102763.
Wilson, B. A., Baddeley, A. D., & Kapur, N., 1995. Dense amnesia in a professional musician
following herpes simplex virus encephalitis. Journal of Clinical and Experimental Neuropsychology, 17(5), pp.668–681.
Wilterson, A. I., & Graziano, M. S., 2021. The attention schema theory in a neural network agent:
Controlling visuospatial attention using a descriptive model of attention. Proceedings of the
National Academy of Sciences, 118, e2102421118.
Wu, P., Escontrela, A., Hafner, D., Abbeel, P., & Goldberg, K., 2023. DayDreamer: World models
for physical robot learning. In Proceedings of The 6th Conference on Robot Learning, 2226–
2240.
Yaron, I., Melloni, L., Pitts, M., & Mudrik, L., 2022. The ConTraSt database for analysing and
comparing empirical studies of consciousness theories. Nature Human Behaviour, 6(4), pp.593–
604.
Zador, A., Escola, S., Richards, B., Ölveczky, B., Bengio, Y., Boahen, K., Botvinick, M., Chklovskii,
D., Churchland, A., Clopath, C., DiCarlo, J., Ganguli, S., Hawkins, J., Koerding, K., Koulakov,
A., LeCun, Y., Lillicrap, T., Marblestone, A., Olshausen, B., . . . Tsao, D., 2023. Toward nextgeneration artificial intelligence: Catalyzing the NeuroAI revolution. arXiv:2210.08340. arXiv.
Zeki, S., & Bartels, A., 1998. The autonomy of the visual systems and the modularity of conscious vision. Philosophical Transactions of the Royal Society of London B: Biological Sciences, 353(1377), 1911–1914.
Zhuang, C., Yan, S., Nayebi, A., Schrimpf, M., Frank, M. C., DiCarlo, J. J., & Yamins, D. L. K.,
2021. Unsupervised neural network models of the ventral visual stream. Proceedings of the
National Academy of Sciences, 118(3), e2014196118.
Zlotowski, J., Sumioka, H., Nishio, S., Glas, D., Bartneck, C., & Ishiguro, H., 2015,. Persistence of the uncanny valley: The influence of repeated interactions and a robot’s attitude on its
perception. Frontiers in Psychology, 6.
88 |
A Study on Mind, Brain and Consciousness
On Universal Physical Reality in the Light of
Quantum Consciousness
1
Pabitra Pal Choudhury, 2Swapan Kumar Dutta, 3Sk. Sarif Hassan and 4Sudhakar Sahoo
1,2,3
Applied Statistics Unit, Indian Statistical Institute, Kolkata, 700108, INDIA
Email: pabitrapalchoudhury@gmail.com, sarimif@gmail.com
4
Department of Computer Sc., Silicon Institute of Technology, Patia, Bhubaneswar-751024
Email: sudhakar.sahoo@gmail.com
Abstract: In this paper, we have first given an intuitive definition of ‘Consciousness’ as realized by us. Next,
from this intuitive definition we derived the physical definition of quantum consciousness (Quantum
Consciousness Parameter or QCP). This QCP is the elementary level of consciousness in quantum particles,
which are the most elementary particles in nature. Thus QCP can explain both the perceptible and nonperceptible nature and some existing postulates of physics. We conceptualize that the level of human
consciousness is most complex having highest fractal dimension of 4.85 in the electroencephalographs
experiment done by other research groups. On the other hand, other species are having lesser consciousness
level, which can be reflected by lesser fractal dimensions. We have also explored the bioinformatics of
consciousness from genome viewpoints where we tried to draw an analogy of neurons with electrons and
photons. Lastly, we refine the quantum mechanics in terms of QCP; we all know that in Einstein’s special
theory of relativity, Einstein has used the postulate “Consistency of the velocity of light irrespective of all
frames of reference (inertial or non-inertial frames)”. In our theoretical revelation QCP can be directly
applied to get a confirmatory proof of this postulate. Thus the postulate can be framed as a law.
Keywords: Quantum Consciousness Parameter (QCP), Fractal dimension, Quantum Consciousness,
Quantum mechanics.
1. Introduction
“Ohng Purnomadah Purnomidang Purnat Purnomudachyate
Purnosya Purnomadaya Purnomebaba Sisyate”.
The Sanskrit quotation says that whatever can / cannot be sensed by our sensitive organs and sophisticated
instruments is building up the super-consciousness, which means as the following…
Matter is transformed in finer form → Energy, is transformed in finer form → consciousness (reality up to
quantum particle level) is transformed in finer form → Super consciousness (Bramha extending up to infinity).
The spiritual background or true civilization of our country is at least five thousand years old. Our humble feeling is
that there is no conflict between spirituality and science. Why we are saying so because our World Wide Web
(WWW) is hardly 20 years old, now we know through the internet that we can exchange a piece of information
across the world within a fraction of a second. So far, consciousness was considered to be a spiritual paradigm only
because Physicist of the past were not sufficiently inclined on the subject, but consciousness is well within the
context of science because it is a very fundamental reality within each of us.
It is observed that thinkers from all walks of life have contributed in some form or other in the understanding of
consciousness. According to the meaning given in concise oxford dictionary, the term is defined as awareness,
knowledge etc. Indian philosophers coined the term “Chetana” (meaning consciousness) from the Sanskrit origin
‘Chit’ meaning knowledge.
A Study on Mind, Brain and Consciousness
Let us utter with the spiritual saying “Sat-Chit-Anand”.
“Sat” means absolute existence, which indicates about the rest mass (hypothetical), which cannot be subjected to
any change with respect to Space-time and causality. “Chit” means absolute knowledge meaning the undistorted or
pure knowledge and “Anand” means bliss meaning the joy everywhere and every-time. All events of our physical
existence of nature are subjected to creation, expansion and termination. This is one part of consciousness. Again
other part which is non-manifested or which cannot be sensed by so called “sensory organs or instruments” forms
the basis of consciousness paradigm consisting of Mind, Intellect, Ego which are the things so far scientifically
unexplored. We claim in this paper that both the perceptible and non-perceptible nature can be explained by
quantum consciousness parameter (QCP) introduced by us. The thing is that although quantum mechanics with the
present state of the art cannot distinguish between living and nonliving, QCP will form very much a complete story
to switch from living to non-living and vice-versa explaining the fact of transition from lower entropy to higher
entropy and vice versa. Under Physicist’s terminology, QCP is derived as the impulse of energy which is again can
be thought as momentum times energy or (mv) (mc2) or m2vc2, obviously a vector quantity. This can be thought as
the cause of any phenomenon and whenever this quantity is divided by Plank’s constant, this quantity is the same as
the Force acting on that event.
Consciousness is being studied in many different angles. We first dwell on the dimension of consciousness in
section 2.1 introducing preliminary notions from Physics. Here we try to conceptualize the consciousness having
more than three dimension and propose the fact that more the species are conscious the more their consciousness
dimension. In section 3, an effort has been given to explain a small constituent of consciousness with the help of
biological neurons. In this regard one project will be started soon at our Institute. We discuss in section 4, the
chronological developments in Physics up to the present state of the art leading hopefully to Consciousness and in
section 5 we redefine the quantum mechanics with the introduction of QCP. We all know that in Einstein’s special
theory of relativity, Einstein has used the postulate “Consistency of the velocity of light irrespective of all frames of
reference (inertial or non-inertial frames)”. In our theoretical revelation we beg to differ with that. Section 6 is the
conclusion, which also highlights the future research directions on Consciousness.
2. Dimension of Consciousness
2.1. Concept of non-perceptibility of consciousness
In the previous section we have just introduced that momentum time energy of a quantum particle of mass
m etc. constitutes the consciousness, the synergy of its full blossom will be seen in section 5. Thus from
(mv), (mc2) or m2vc2, we observe the dimension as M2L3T-3. When this amount is divided by Plank’s
constant h, which is in Joules.sec equivalent to ML2T-1, we get MLT2, which can be easily interpreted as
the force of consciousness.
h
In the same paradigm, the velocity of the particle v =L/T = mv
=c2/v pointing to the fact that the
h
mc 2
quantum particle can attain more than the speed of light and hence the consciousness becomes nonperceptible to the external world although it is a very basic fundamental reality.
2.2. Fractal dimension of consciousness
In 1904, one advancement in Science by Koch took place. Adding triangles to the sides of triangles ad
infinitum produced enough mathematical curiosity. The resulting length of the triangle becomes infinitely
long, yet remains contained in a finite space. In 1970, the word “fractal” was coined to describe fractions
of dimensions.
A Study on Mind, Brain and Consciousness
Like the Koch snowflakes, fractals in nature maintain their irregular but distinctive shapes over different
scales of magnification, which is known as nesting. Famous mathematician B. Mandelbrot was highly
fascinated by the shape of the cauliflower- smaller and smaller pieces demonstrated self-similarity.
The fractal dimension of the outline of a typical cloud is 1.35. The fractal dimension of the coastline is
1.26. The fractal dimension of a piece of paper crumpled up into a ball is about 2.5.
Naturally, the fractal dimensions between 1 and 2 measures how wrinkly a line is. The crumpled paper
ball fails to completely fill its allotted space, so it scores a dimension less than 3. Foamy structures may
also have fractal shapes. The universe itself has a fractal shape due to its foam like structure caused by
enormous globular voids between clusters of galaxies. In Biology it is seen in the sequential branching of
ferns, trees, blood vessels, bile ducts and kidney (urinary collecting systems) into smaller and smaller
versions of the original. Our vascular system, when stripped of all other cells, would almost fill the space
that our bodies occupy. It is estimated to have a fractal dimension of slightly less than 3.
Computers may generate beautiful fractals when certain numbers are inserted into selected simple
equations. When the results are fed back into the original equation, a feedback loop is set up, that is the
mathematics feeds upon (recursion) its own results. We know already that feedback loops often have the
effect of signal amplification as illustrated by a microphone being placed too close to its own
loudspeaker. In 1940s, Donald O. Hebb investigated feedback loops in the brain (Mc Gone J. Going
Inside. London: Faber and Faber, 2000: 43). He realized that successive firing in the same neural loop led
to the reinforcement of nerve cell connections so that subsequent activation occurred more easily. This is
as if the nerve networks have memory.
Surely, fractals and feedback loops are part of a branch of mathematics called nonlinear dynamics (ND).
In the past, ND has been used to describe complex processes such as the weather, fluid turbulence, and
many aspects of biology (mainly working of the mammalian brain), but still the brain function and
consciousness remains elusive (see http:/mcb.berkley.edu/faculty/NEU/treemanw.html).
Next we observe the phase space of a simple pendulum as shown in fig-1.
Figure 1: Phase space of a simple pendulum
A Study on Mind, Brain and Consciousness
The velocity and position of a pendulum is plotted to produce a circle in phase space. At any instant in
time, the velocity and position collapse to a single point somewhere on the circle. The continuously
scribed circle is a periodic attractor. The pendulum on the right has lost power, that’s why the phase space
spirals towards a point attractor. In contrast, for many biological systems, the attractor is the isoelectric
state or cell death. In some nonlinear systems, unlike the case of a simple pendulum, the attractor is a
fractal. One of the best known and first discovered fractal attractors associated with nonlinear dynamics is
the pair of butterfly wings generated by a computer when Edward Lorent was studying equations relating
to weather turbulence.
In biological systems, experimental data are often with noise and other artifacts. Thus it is often hard to
discern the underlying dynamic processes.
It is to be noted that, the higher dimension involved in string theory are physical and thought to be highly
compact. Phase space is a mathematical construct, and motion on an attractor is abstract. In fractal
attractors the orbits in phase space may be stretched and folded like baker’s dough when it is needed. In
either case human imagination is not equipped to contemplate these higher dimensions directly. In other
words, if data from perceptual space is retrieved, analyzed and shown to exhibit an underlying
mathematical order that co-relates sensibly to its source, it is probably real even if it cannot be touched.
To look for signs of nonlinear dynamics, the data from electroencephalographs of different species
including human are shown. Really an increase in mathematical sophistication across species is co-related
with perceived notions regarding evolutionary rankings in the central nervous systems of the animals.
Table 1: Shows the data from electroencephalographs of different species including human
SPECIES
FRACTAL DIMENSION
Human
4.85
Dog
4.63
Butterfly
3.71
Catfish
2.50
Crayfish
1.65
Earthworm
0
Thus it is the firm conviction of the authors that appearance of consciousness is a revolutionary
development during the evolutionary process. In humans a 4.8 dimension attractor may combine more
than 4 variables in phase space. It is quite possible that the synthesis necessary for an explanation of
consciousness occurs in the phase space associated with the nonlinear dynamics of the brain. It may be
undeniably argued that objects in physical space enter our perceptual space via phase space. A hyperspace
is a phase space with more than three dimensions (Churchland PS, Neurophilosophy: Towards a Unified
Science of the Mind-Brain, Cambridge, MIT Press, 1986, 420-423.)
In [6, 7] we have given different possible applications of a newly developed model by us, which we
named as Carry Value Transformation (CVT). Giving one fractal application in [6] we have highlighted
that like other mathematical transformations CVT can also be used as an efficient tool to simulate the
behavior of the nature. Mathematically we have also proved that just like Cellular Automata and Random
A Study on Mind, Brain and Consciousness
Boolean Network, CVT and Modified CVT (MCVT) both are discrete deterministic dynamical system
and the cells (or values) in the table can be generated in parallel. In [7] the construction of CV Tables in
different dimensions are highlighted. Also like CVT and MCVT their inverse transformation named as
Extreme Value Transformation (EVT) is used to form different number theoretic fractals.
In a more general way, like CV table, MCV table and EV table any "table" with respect to a function or a
relation (values of the table are generated with the help of this relation) also can generate both periodic as
well as chaotic patterns. We can conjecture that one link can be established between these complicated
patterns generated by this relational table with the theory of machine consciousness. More specifically
identifying a suitable relation, choosing both rows and column numbers (integer, real etc.) in the table a
chaotic and complex pattern can be generated which can mimic the complicated human brain. To map the
exact brain structure a set of functions/relations may be non-uniformly (or hybrid) applied to the row and
column numbers in the table.
Then, analysis of this table values may help us to understand the complicated structure of the brain and
the function (sometimes operator or Rule) may be treated as the main logic, which is responsible for
functioning of our mind. Again on changing different relation(s) in different time steps at time t=0, t=1,
etc. dynamically table values can be changed and thus may be treated as another tool for evolutionary
computing. Thus different thoughts or the changes of mind in different time instants can be suitably
modeled using this relational table considering as a tool. In addition to this, other mathematical tools like
Cellular Automata, Random Boolean Networks, L-Systems etc. are other possible options because these
are also used to generate self-similar and chaotic fractals.
3. Research Effort on One Experiment on Consciousness
We know that in any digital computer, someone has to wire a computer and program it. But our brain’s
wiring consists fundamentally of laying down pathways of information flow and networks of information
processing. Brain wiring is carried out by processes that are derived from the genome, but the information
for this wiring is not entirely contained within the genome itself. Rather, the brain develops by a
progressive sequence of steps that each involves interplay between genetic programs and environmental
influences.
This view has antecedents (M. Sur, The Brain and Mind, 24th March 2009). The physicist Erwin
Schrödinger, in his book “what is life” published before the discovery of the structure of DNA, pointed
out the necessity of a crystalline genetic material in living organisms that would form the template for
reproduction. The biologist Sydney Brenner has pointed out that the defining feature of a living organism
is its ability to clone or recreate itself from its genetic code. We add that the brain wires itself from coded
instructions that are open to and interpret extrinsic information, and this is in fact central to understanding
human cognition and biological intelligence.
The earliest events in brain developments consist of neurons being and migrating to the right place.
Subsequently, cells in one region of the brain extend axons or wires that link that region with another.
Thus the eyes project to the visual cortex. These projections are highly specific- there are hardly any
mistakes tolerated during such pathway development—and evolution has set up a large number of genes
that orchestrate this specificity. In other words, Nature is highly deterministic in all cases of specificities.
For example, that we are speaking now on a specific subject implies a specific set of networks etc. is
definitely involved for such activations. This theme of specificity will be particularly applicable in section
5 where we elaborate that when the third party (observer) observes some event it might be associated with
A Study on Mind, Brain and Consciousness
certain uncertainties, which afterwards could be removed with the introduction of our deterministic theory
leading to the case of specificity.
The human genome project has transformed our ways of mapping genomic sequences and identifying
genes, and has turned biology into an information science. Of the approximately 20,000 genes that
comprise the human genome, about 80% are expressed in the brain. Different genes are expressed in
different parts of the developing nervous system, and at different times. Sometimes the same gene is
expressed in different brain regions, and sometimes a gene stays on for variable durations in different
regions, but rarely is a gene turned off and then on again in the same region. Each gene thus has a unique
function in space and time in the developing brain, but one that is influenced by context.
One of the most remarkable discoveries of the recent years is that genes can be regulated in a large
number of ways. They can be turned off and on by critical control elements, including epigenetic
mechanisms in the genome and small pieces of RNA. And not only what protein a gene makes but also
how much it makes is influenced by a host of factors inside and outside the genome.
For communicating between two living elements some language is essential. This language may be in the
very primitive terms look like sensing something. Humans have five sense organs through which
transmission of information takes place. Let us consider the smell-sensing organ: Olfactory Receptors
(ORs) which are found in the vertebrate genome as clusters of ~2-5 receptors per loci and have expanded
via gene duplication events over evolution throughout the genome. It is still not known what a basic unit
of these receptor cluster is, and how these building blocks propagate in the genome. Our research efforts
will be focused on the clustered DNA and protein sequences with the objective of understanding the
functional role of these clusters with respect to olfactory compounds. Also it is the conviction of the
authors that QCP will act the pivotal role in framing the corresponding theories.
Basically, we are in search of Bio-informatics describing human genome and its role in consciousness.
Our prime objective is to characterize one small constituent of consciousness where biological neurons
seem to take place of electrons and photons as found in electronic computers and optical computers
respectively. Remember that traveling electrons are the constituents in an atom. But photons are different
which are called bosons, whereas electrons are fermions. But Scientists are already aware of the dual
existence of this kind of particles. In this context it may be highlighted that there exits various states in
Physics, viz. solid, liquid, gaseous, plasma and the fifth state is definitely non-perceptible signifying the
quantum particles’ velocity greater than the velocity of light.
It is well known that classical mechanics, based on Newton’s laws of motion, can predict the motion of
planets around the sun accurately. In a similar way, it can also predict the motion of satellites around the
earth. We know that a satellite can be launched with the help of a rocket at any desired height above the
earth. Thus a satellite moving around the earth can occupy any orbit. In other words, all the orbits are
permissible. A satellite in each of these orbits has an energy, which can be calculated by using the laws of
classical mechanics. This means that there is no restriction on the energy of a satellite orbiting around the
earth or a planet orbiting the sun. However, the same is not true for an electron inside the atom. Although
the electrons are similar to planets or satellites in a much smaller system like the atom, things are quite
different there.
In any atom, an electron can only occupy a set of permissible orbits around the atomic nucleus having
discrete energy levels. Laws of classical mechanics fail to predict this discreteness. Quantum theory, on
the other hand, helps us to identify these permissible orbits for the electrons and calculate their energy
levels. In the Bohr model for atoms, as taught in high schools, these are called the electronic energy levels
A Study on Mind, Brain and Consciousness
in an atom or simply the atomic energy levels. According to Bohr’s theory, an electron in the atom can
absorb or emit light of a specific wavelength only, when it jumps from one permissible orbit into another.
Let the electronic transition occur from a lower energy level E1 to a higher energy level E2, so that the
energy gap ∆E = (E1 - E2). The absorbed wavelength λ is obtained by using the formula ∆E = hν = hc/λ,
where the Planck’s constant h = 6.6 x 10-34 J.s. This gives a dark line in the spectrum of the hydrogen
atom. In this way, the observed series of lines in the hydrogen spectrum can be explained successfully.
Let us raise one question here (obviously attempted refutations are expected and welcome):
Can we draw analogy of electrons (or photons) with neurons, the way we are observing as above?
As you understand, our objective is to know about biological neurons for the ambition of producing a
conscious machine. Incorporating consciousness into a machine is a complex task as rightly pointed out
in [“Analysis and Implementation Strategy for Incorporating Consciousness into Machine Architecture”
by C. N. Padhy and R. R. Panda, IEEE IACC-2009]. First, logical evaluation of consciousness is highly
needed. Next, we have to formulate a set of instructions leading to this level of consciousness. Then only
it would be proper to think of machine architecture. Of course, human body will be always the natural
machine to imitate although there are plenty of deficiencies so far to be incorporated when we think of
building our conscious artificial machine.
4. Developments in Physics up to the present state of the art leading hopefully
to Consciousness
For many years until 1920 science had excluded ‘consciousnesses’ from the physical universe. However,
a major paradigm shift in the 1920’s from classical mechanics to quantum mechanics marked a break with
that long tradition. Now the current interest in the foundation of ‘consciousness’ has led increasingly to
the need to utilize quantum phenomena for the purpose of unfolding the physical reality. Hopefully, this
will be able to change the complexion of the relationship between body and mind.
The principle of classical mechanics is that any physical system can be decomposed into a collection of
simple independent local elements each of which interacts only with its immediate neighbors. Thus
according to the ideas of classical physics, brain is a collection of massive system of parallel computers,
one for each point in a fine grid of space time points that cover the brain over some period of time. In
other words, the model of cellular automata might be helpful for the simulation work. Further, each
individual computer would compute, record and transmit the values of the components of the
electromagnetic and matter fields at the designated associated grid point. The major problem with beliefs
and preconceived metaphor (called “Sangskar” in Hindu Philosophy) arises from the attempt to
understand the connection of thoughts to brains within the framework of classical physics. Since the
brain is a physical system, according to the precepts of modern physics the brain must in principle be
treated as a quantum system. Later we shall see that even with the introduction of quantum concept, we
arrive at some more contradiction, which signifies some more tools is required to understand ‘mind’
property of Nature. Nevertheless, for the time being let’s point out one prime consideration of Quantum
theory.
Quantum theory is unlike classical physics, in which a human consciousness is necessarily idealized as a
no participatory observer, as an entity that can know the aggregate aspect of the brain. In quantum theory,
the situation is subtler because there is a structural mismatch between a quantum mechanical description
of a physical system and our perception of that system. This structural mismatch (we shall more elaborate
on this topic at the end) is the basic entity of quantum theory and surely it opens up interesting possibility
A Study on Mind, Brain and Consciousness
of representing mind/brain. This is because mind/brain should be thought as a combination of thought like
and matter like aspect of a neutral reality. To describe the physical and chemical processes underlying
brain action and existence of mind we thus need to move from monistic classical mechanics to a dualistic
generalization. During the time when Heisenberg introduced the quantum mechanics, ‘mind’ was out of
the purview of physics. But when this dualistic mechanics is applied to a human brain, it will hopefully
account for the thought-like and matter-like aspects of the mind/brain system.
In the quantum description of Nature proposed by Heisenberg, reality has two different aspects:
1. One consists of a set of ‘actual events’ – these events form a sequence of ‘happenings’, each of
which actualizes one of the possibilities offered by the quantum dynamics.
2. This consists of a set of ‘objective tendencies’ for these events to occur, these tendencies are
represented as persisting structures in space and time.
Our major research effort is to identify and correlate these persisting structures with the
functionalities/events.
If we can correlate thoughts with high level quantum events in brains as suggested by von Neumann,
Wigner and others, then we will be able to build-up a theory which will be dual aspect theory of the
mind/brain, in the sense that it correlates the inner or mental aspects of mind/brain system with ‘actual
events’ in Heisenberg picture of Nature. In this context, Bohr resolved the problem of reconciling the
quantum and classical aspect of Nature by introducing the fact that, the only thing that is known to be
classical is our description of our perceptions of physical objects. J. von Neumann and Wigner used this
key insight into dynamical form by proposing that the quantum/classical divide be made not only on the
basis of size, but rather on the basis of the qualitative difference in those aspects of Nature we call mind
and matter (body).
Let us note the famous remark of Nobel Laureate Richard Feynman: “The theory of quantum
electrodynamics describes Nature as absurd from the point of view of common sense and it agrees fully
with experiment. So I hope you can accept Nature as she is –absurd”.
The main ideas of Quantum Mechanics are as follows:
1.
2.
3.
4.
Energy is not continuous but in discrete units
The elementary particles behave both like particles and waves
The movement and behavior of these particles are inherently random.
It is physically impossible to know both the position and the momentum of a particle at the
same time. The more precisely one is known, the less precise the measurement of the other is.
5. The microscopic world is different from our macroscopic world.
Brain and mind are two different entities as if one person (Brain) is always with his/her assistant (Mind).
Think about the analogous situation when a person is about to do certain work, immediately this may be
prohibited/supported by his assistant or mind with sufficient or physical interpretations are obviously
available.
Einstein was one of the main players in the introduction of Quantum Mechanics. He himself explained the
photoelectric effect with Planck’s energy quanta, which were called ‘photons’ and introduced the concept
of absorption and spontaneous and stimulated emission of radiation. In spite of all these tremendous
achievements, Einstein always doubted the completeness of Quantum Mechanics-specifically the random
A Study on Mind, Brain and Consciousness
nature of Quantum Mechanics and the spooky (alarming!) action-at-a-distance (non-locality) were the
things he deeply rejected. His famous quote “Subtle is the Lord, but he does not play dice” demonstrates
his attitude towards Quantum Mechanics. The deficiency of the Quantum Mechanics is more evident
when we observe the following fact:
Let’s raise the question “What are the ultimate physical limitations on computing power”? On using
arguments based on Quantum Mechanics, H. J. Bremermann (“Optimization through Evolution and
Recombination,” in M. C. Yovits et al. (eds) Self organizing Systems, pp. 93-106, Spartan Books,
Washington, D.C., 1962.) conjectured that no computer, either living or artificial can process more than
2X10**47 bits of information per gram of its mass per second. If it is true, computers like the size of the
earth (6X 10**27 g) operating continuously for a period equal to the estimated age of the earth (10**10
years) could then process fewer than 10**93 bits.
From the above discussion one thing we may realize that mass, information processing capacity and
energy are all synonymous and hence interchangeable.
The points, which run against the above conjecture and hence incompleteness of Quantum Physics could
be the following:
1. It is much less than the number of possible sequences of moves in simple chess game which
has been estimated at 10**120.
2. Further, human brain supposedly the most complex machine in the universe has 100 billion
(10**11) neurons. Scientists already know that neurons convey information via electrical
spikes, and each neuron interconnects with hundreds of other neurons via, on average 10
thousand connections or synapses. Thus each brain has about thousand trillion (10**15)
synapses. Combining all the brains of living organisms to date must be much bigger than the
so far processed bits of 10**93 as per Quantum Mechanics.
Now let us elaborate on the precision of wiring between neurons in the formation of networks and
modules. It is to be noted that neurons are not simply interconnected with any or all other neurons; rather
they make precise connections with a subset of cells and form networks that process information.
Obviously the pathways that convey information and networks that process them are at the core of brain’s
function. Next we elaborate on Cognition and mind, which are essentially believed to be the function of
some network in the brain:
One thing must be clear that one or several networks must be able to perform the following functions
from the point of view of cognitive sense:
1. Parasitic behavior, meaning the tendency to acquire resources for self-survival without
concerning other’s existence. In other words, the aggregate behavior makes a being
autonomous
2. Symbiotic Behavior, meaning the tendency to associate peers for the purpose of strengthening
and smoothening the survival process
3. Self-referral behavior meaning the tendency to recursively referencing the self (the same
network or/and a collection of networks). In other words, performing the actions to
identification and protection for the self.
4. Reproductive behavior meaning that it plays a role for multiplication, a role in populating
self-species type for the purpose of competing with other species in the struggle for survival.
A Study on Mind, Brain and Consciousness
The thing that is of prime importance is that all the above cognitive behaviors we observe must be true
from the microscopic world of cell level to the macroscopic world of organ or functional or behavioral
level. Obviously our nervous system plays a critical network role for the above kind of integration from
the micro to macro level.
In a nutshell let us revisit the various significant points as the following:
Newtonian Mechanics:
What are the main features of Newtonian Mechanics?
1. It is just Euclidian Geometry (3-D Space) Here time has not been taken in to consideration. As if
both Event and observation are taking place simultaneously in space and time. Thus absolute time
and space have been considered.
2. The three fundamental dimensions of Mass (M), Length and Time are considered absolute.
3. Newtonian mechanics is completely deterministic.
4. Newtonian Mechanics applies to macro system.
5. Event and observation are equivalent with respect to energy and momentum.
Einstein’s Relativistic Mechanics (Special)
1. All the three fundamental dimensions (M, L, T) are relative except the rest mass m0 , rest length
l0 or rest time t0 . It is the so-called Minkowski’s geometry.
2. It applies to the inertial frame of reference. Any particle is at rest or in uniform or uni-directional
motion.
3. Equivalence of event and observation with respect to the observer.
4. It is also deterministic.
5. Therefore it can only be applicable to macro system where the changes are negligible.
Quantum Mechanics
1. QM incorporates the non-equivalence of event and observation in the light of Heisenberg’s
uncertainty principle
2. It applies to the non-inertial frame of reference. That is, velocity and direction continuously
changing with respect to time.
3. It is non-deterministic.
4. It can be applicable to micro system.
5. It applies to non-linear geometry.
What is lacking in all the above formalisms to describe the mechanics of a physical system concerning
quantum particles? By quantum particle we mean any particle whose mass is ≈ less than 10-5 gram
(Plankian mass).
The last but not the least significant point, which is lacking is to incorporate absolute universal units of
mass, length and time which must be incorporated to a theory to give it to a complete and deterministic
form. This is quite logical from the viewpoint of precision of any measurement theory.
A Study on Mind, Brain and Consciousness
5. A Theory of Quantum Consciousness
Here we build up a qualitative as well as quantitative concepts of the widely used term “consciousness”
from the most fundamental level of quantum reality, as is manifested in nature.
The mathematically formulated quantum consciousness parameter (QCP) has been used to explain
analytically the basic perceptual and conceptual details of the interactions of the observer and the
observable via the process of observations done by communicating signals, which after interacting with
the observable bring (back) information about the same to the observer.
The entire treatment has been constructed essentially on the basis of a new deterministic interpretation of
conventional quantum mechanics which in our view actually a complimentary picture of the existing
formalism and in no sense should be miss interpreted as a contradiction of the existing one. In other
words, the deterministic status, which has been established earlier in the paper (physical Essays volume 8,
number 4, December 1995), provides a fuller description of the reality of the quantum world in terms of a
broader duality. We have to consider the duality of the probabilistically perceptible dynamical variables
and the hidden form of deterministically computable variables. Thus keeping in mind the necessity of
mathematically formulated definition of consciousness, we have constructed the theory in a very
generalized form starting from fundamental quantum entities. This will obviously fuel the future rapid
advancement of science and technology because the more complex macro bodies are nothing but
ensembles of quantum particles.
Before going into the theory part, some important revelations are the following:
1. All the individual entities in the universe are constantly in the act of interaction with each other in
multifaceted manner strictly obeying the laws of physics both in the micro and macro levels, no
matter whatever be the space time separation between them (Ernst Mach’s Principle). Therefore it
can be concluded that consciousness is the most fundamental universal parameter, which is
inseparably associated with all material existence, no matter whether living or non-living.
2.
Outline of treatment in this section is an extension of the idea of quantum consciousness
(associated with quantum entities) from the simplest to the more complex system of quantum
(ensembles). Then the elementary idea has been applied, in an extended form to have a more
generalized and explicit view of “System consciousness”, both in the areas of biological science
and man-made machines. Because some forms of a “self-organized automata” is a common
feature, manifested in both living and nonliving systems, which perform certain self-operational
functions, which are actually the result (product) of the quantum interactions constantly going on
in their quantum level of composition. The simplest examples clarifying the above notion are the
atom (non-living system) and the cell (living system). Both of them having their own distinct
built in system consciousness, which are the guiding and governing factors throughout their
internal and environmental (external) responses.
3. The quantum consciousness parameter (QCP) and its relation with the four other dynamical
variables, viz. relativistic energy, momentum, time period and wave length have been established
in the following theory part clearly describing the underlying physical significances and
distinctively different properties of QCP from other parameters (energy, momentum, etc).
A Study on Mind, Brain and Consciousness
However, complimentary picture of the new idea with the existing one is also discussed in details.
Thus it is foreseen that QCP would provide a mathematical tool for the scientists to apply the
same effectively in all the areas of quantum mechanics especially in the deeper understanding of
quantum mechanics, quantum information theory and quantum computation. Other significant
breakthrough could be achieved in technology by constructing mathematical working models,
based on the concepts of QCP and applying them to the challenging problems in the areas of
molecular biology, medical and medical instrumentation, genetics, neuro-science, biotechnology,
bio-informatics and psychology. The most important aspects of the future QCP-based nanotechnology would be its high level precision factor due to its inbuilt quantum deterministic status
as shown in the theory part. A multi disciplinary scientific research programme is solicited to
incorporate the QCP concept effectively in modern nano-technology in almost all the areas of
modern science. We have also undertaken the task of providing the basic algorithms as a
preliminary working tool. Essentially, this basic principle could be used in the different areas of
applications mentioned above according to their specific requirements, for different data based
computation. Before going into the theory part we cannot resist the temptation of quoting from
the writing of two great physicists, Prof. Max Born (Nobel laureate) and Prof. Franck Wilckzek
(Nobel laureate 2004) both of them Nobel Prize winner in physics. Their views about the future
of quantum physics clearly indicate that the task of QM emerging as a unitary science, embracing
all the areas of natural philosophy has been achieved. The problems of consciousness will remain/
yet to be solved before such a goal can be reached. Nothing can be excluded from our interest of
research in our quest for deeper knowledge. The enigma of both inert matter and those of the
living material entities can possibly be explained in terms of the more generalized and
omnipresent existence of quantum consciousness as a unitary science.
Theory: We have mentioned above that a hidden deterministic theory (vide Physics Essay Vol-8 & No.
4) of QM is the foundation of the theory of quantum consciousness (QC).
Heisenberg’s Uncertainty principle is introspected and reevaluated in the light of the non-infinite and nonzero quantized energy and momentum limits lending to the following results:
i)
Functional qualitative relations are established between E and f(∆E)(where f stands for function)
and p and f(∆p) where E and p are respectively the actual values of the energy and
momentum of a measured particles. (∆E) and (∆p) stands for their respective uncertainties
due to measurement: E= f(∆E) and p= f(∆p). The equation for E is given in [Physics essays,
vol.8, no.4] as for the readers as a reference, which would be required henceforth time to
time.
ii) This reveals the hidden intrinsic deterministic characteristics of QM and dynamical variables (E,
p, λ, τ), which are mathematically understandable and computable. It is only their probabilities
that can be measured by observation.
It is, therefore ethically required to replace the wave characteristics terms λ, τ by other terms befitting the
new deterministic formalism. A comparative picture between the two interpretations are given below:
A Study on Mind, Brain and Consciousness
i)
Conventional view: E=h.ν where ν is the frequency and h is Planck’s constant. ν = 1/τc where τc
is the Compton time period and τc=h/mvC2.
Where, E = mvC2 is the relativistic energy of a particle and mv =
m0
v2
1− 2
c
where m0 is the rest mass
and mv is the relativistic mass of the particle traveling with velocity v relative to the observer.
ii) De Broglie’s wave equation is p=h/ λ where p= mvυ where mv =
m0
v2
1− 2
c
is the relativistic
momentum of a particle and λ is De Broglie’s wavelength. The De Broglie time period τδ
=h/mvv2. This probabilistic interpretation is based on Max Born’s idea of wave of probability and
Schroindinger’s wave function ψ, which is physically signified as the amplitude of the
probability.
The new concepts of hidden determinism are based on the idea of sharp discreteness:
Here the term λ is replaced by L=h/ mv v and v is simply the particle velocity (not group velocity vg) and L
is spatial dimension in the direction of its trajectory of motion. This term τδ is replaced by T=h/ mvC2.
This is the time required by the particle to traverse its own length. Therefore the non-observable velocity
of propagation is expressed V=L/T=C2/v ≥ C (where v is the group velocity in wave interpretation
whereas here in our new interpretation v is the particle’s relativistic velocity) which was termed as a
phase velocity in the conventional wave interpretation. According to S.T.R surely the velocities greater
v2
c
than C will fetch only imaginary mathematical existence because the term 1 − 2 becoming negative.
Conventional wave mechanics in quantum theory only attributes a mathematical significance to V as the
phase velocity of a group of unidirectional waves. But in the light of the new deterministic scenario, it is
suggested that V can be defined as the velocity of propagation of the quantum consciousness of quantum
particles. In the present context a quite similar situation can be cited where P.A.M Dirac faced the
problem of providing a reasonable physical explanation for the negative roots of his formulated quantumrelativistic energy equation
E= p 2 C 2 + m0 2 C 4 for, at that time, nothing like “Negative Energy States”
was known to the physicists. The reality of Dirac’s prediction of antiparticles was later experimentally
confirmed.
Therefore, it should not be taken for granted that a physically non-perceptible entity, which is only
mentally conceivable, does not exist as a physical reality. In the case of quantum consciousness the reason
behind its non-manifestation is that its velocity of propagation V is greater than C. Knowing that the mind
and body is an intimately integrated system as a whole it is reasonable to incorporate quantum
consciousness as the most fundamental physical parameter, which exists as a reality in all material entities
whatsoever. It is only the levels of consciousness depending upon the degrees of self-organized automata
and complexity of structure in isolated systems, which makes the quantitative as well as qualitative
differences in the manifestation of their multifaceted awareness, due to their interactions with other
systems. Thus the present paper would throw light on a unified notion or concepts of matter, energy, mind
A Study on Mind, Brain and Consciousness
and consciousness and will give a directive in the construction of a future unitary science, which would
enable us to have a deeper as well as broader insight of our phenomenal nature. As consciousness means
knowledge, it is quite reasonable to enunciate quantum consciousness as the knowledge about the states
of a quantum particle, relative to an observer. Here it is to be understood and kept in mind that quantum
consciousness parameter QCP in its dimensional structure must involve all the four dynamical variables
(energy, momentum, time and space) in their uncertainty free, pure form to attribute totality as well as
purity of the quantum information contained in it (Please recall here about the ‘Sat-Chit-Ananda’ as
explained in the introduction).
The quantitative equivalence of Kφ(QCP) of a quantum particle is conceptualized here as its impulse of
relativistic energy relative to an observer. The term impulse is dimensionally the same as momentum and
the preposition “of” implies product, (so for a non zero rest mass particle) we can write,
Kϕ = (mv)(mc ) = m vc Or { Kϕ }
2
2
2
m≠0
= m2vc2
Similarly for zero rest mass particles e.g photons
{K }
ϕ
2 2
hv
hν
= × hv =
= m2c2
m≠ 0
c
c
Thus it is significant that our theory would serve as the philosophical foundation of the more versatile
unitary theory of QC. Unitary in the sense, that it unifies the non-observable aspect of QM with its
observable counterpart, which was lacking in QM as a relevant complimentary.
Also as {Kϕ }m ≠ 0 = m 2 c 2 =h2/LT, the space and time are therefore parameters automatically included in Kϕ .
We can write the energy equation of a particle in terms of its uncertainty in measurement as
1
1
E = E p 2 (4π Ei ) 2 ×
Where E p is Planckian energy= 2π
( ∆E − E ) ……………………..(4)
0
( hc G ) , h denotes Planck constant, c is velocity of light and G is
5
Newtonian gravitational constant. Ei=hH0/2 H0 in Hubble’s cosmological parameter, considered here as a
constant is the min non-zero quantized energy derived from the scale of the universe. E0 is the geometric
mean of Ep and Ei .
Therefore
As theoretically the non zero value of
cannot be lesser than i.e.
we can substitute
where n is natural number. In the equation 4 and write it in the form given below…
Or
A Study on Mind, Brain and Consciousness
,
From equation (4)
=
which is non-dimensional constant.
Therefore (4a) can be expressed as
Writing the n.d constant
β
=β the simplest form of (4a) becomes
…………………..(4b)
Returning to equation of QCP Kφ= m2vc2= E2(v/c2)
Substituting (4b) in 1 we get Kφ = β
(v/c2)
Where
Considering the value of the constant β we get β=
quantity, so ignoring the second term in β we can take its value as 1.
Thus Kφ =
which is very small
(v/c2)…………….(4c)
The direction of Kφ is the same as that of v.
Studying (4c) we can see that the magnitude of Kφ is extremely small excepting for every large values of
n because E0 10-16 erg and even for velocity very close to c .
v/c2 10-10 cm-1 sec for n>>1 one can also write Kφ=n
(v/c2)………….(4d)
Similarly, for the zero rest mass particles e.g. photons,
Thus it is significant that QCP = m2vc2 as the deterministic hidden variables theory is the foundation of
consciousness theory.
But, in the light of the new deterministic picture, it is suggested that V can be defined as the velocity of
propagation of the quantum consciousness of quantum particle traversing its own length. Therefore the
k
non-observable velocity of propagation is expressed as V = 2ϕ 2
mc
Which was termed as phase velocity in the conventional wave (inter pertain). According to S.T.R
velocities greater than c can have only imaginary mathematical existence because the term becomes
negative. Conventional wave mechanizes in quantum theory only attribute (a) mathematical significance
to as the phase velocity, of a group of unidirectional waves. This rational directive in formulating QCP a
depending upon the degrees of self-organized automata and complexity of structure isolated systems,
which makes the quantitative as well as qualitative differences in the manifestations of their multifaceted
awareness due to their interactions with other systems.
A Study on Mind, Brain and Consciousness
In the case of quantum consciousness the reason behind its non-manifestation is that its velocity of
propagation v is greater than c .
Therefore, it should not be taken for granted that physical entity which is mentally conceivable nonperceptible does not as a physical reality.
Knowing that the mind and body is an intimately integrated as a soul, it is reasonable to incorporate
quantum consciousness as the most fundamental physical parameter, which exist as a reality in all
material entities irrespectively. It is only the levels of consciousness which matters for different species;
the present paper would throw light on a unified notion or concepts of matter, energy, mind,
consciousness which would enable us to have deeper as well as broader view of our phenomenal nature.
As consciousness means knowledge, it is quite reasonable to enunciate quantum consciousness as the
knowledge about the state of a quantum particle, relative to an observer. Here it is to be understood and
kept in mind that the quantum (energy, momentum, time and space) is in their uncertainty free, pure form,
to attribute totality as well as purity of the quantum information contained in it.
6. Conclusion and Future Research Directions
In this paper consciousness has been dealt from various viewpoints. First it has been conceptualized as the
momentum times energy and as a result the force of consciousness has been derived. On introducing
fractal geometry, it has been conceived that more prosperous species (with regards to consciousness)
might be having higher fractal dimension in the phase space of electroencephalographs representing the
higher consciousness. Then systematic gradual advancements of Physics have been enumerated leading to
the complimentary theory of quantum consciousness.
Thus it is foreseen that QCP would provide a mathematical tool for the scientists to apply the same
effectively in all the areas of quantum mechanics especially in the deeper understanding of quantum
mechanics, quantum information theory and quantum computation. Other significant breakthrough
could be achieved in technology by constructing mathematical working models, based on the concepts of
QCP and applying them to the challenging problems in the areas of molecular biology, medical
instrumentation, genetics, neuro-science, biotechnology, bio-informatics and psychology. The most
important aspects of the future QCP-based nano-technology would be its high level precision factor due
to its inbuilt quantum deterministic status as shown in the theory part. A multi disciplinary scientific
research programme is solicited to incorporate the QCP concept effectively in modern nano-technology in
almost all the areas of modern science. We have also undertaken the task of providing the basic
algorithms as a preliminary working tool. Essentially, this basic principle could be used in the different
areas of applications mentioned above according to their specific requirements, for different data based
computation.
A Study on Mind, Brain and Consciousness
References
1. Swapan Kumar Dutta, The Noninfinite, Nonzero Quantized Energy Limits and Their Physical
Significance, Physics Essays, Volume 8, Number 4, 1995.
2. Mriganka Sur, MIT, USA, The Brain and Mind, Invited Talk at Indian Statistical Institute, Kolkata on
24th March 2009.
3. H. J. Bremermann, Optimization through Evolution and Recombination,” in M. C. Yovits et al. (eds)
Self organizing Systems, pp. 93-106, Spartan Books, Washington, D.C., 1962.
4. Churchland PS, Neurophilosophy: Towards a Unified Science of the Mind-Brain, Cambridge, MIT
Press, pp. 420-423, 1986.
5. Chinmaya Nanda Padhy and Rasmi Rani Panda, Analysis and Implementation Strategy for
Incorporating Consciousness into Machine Architecture, IEEE International Advanced Computing
Conference (IACC-2009), Patiala, India, 2009.
6. Pabitra Pal Choudhury, Sudhakar Sahoo, Birendra Kumar Nayak, and Sk. Sarif Hassan, Carry Value
Transformation: Application in Fractal Formation 2009 IEEE International Advanced Computing
Conference (IACC 2009), Patiala, India, 6-7 March, pp 2613-2618, 2009.
7. Pabitra Pal Choudhury, Sudhakar Sahoo, Birendra Kumar Nayak, and Sk. Sarif Hassan, Act of CVT
and EVT In The Formation of Number-Theoretic Fractals, arXiv 0903.4770v1, cs.DM, Apr 2009. |
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
993
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
Exploration
Is Gender Important in Consciousness Exploration?
The Modification of Male & Female Consciousness with Chichaja Brew
Leonardo Rodríguez Pérez*1 & Sonia P. Murcia Roa*2
1
The Pierre du Bois Foundation for Current History, Geneva
Universidad Nacional de Colombia, Bogotá
2
ABSTRACT
Gaultheria insipida is a plant native to the Andes used traditionally by female indigenous Inga
healers near the Colombian Amazon to prepare a brew currently known as Chichaja. This brew is
an element that allows distinguishing a very original type of Colombian shamanism, but
Gaultheria insipida and Chichaja have not yet been studied by psychedelic researchers or
ethnobotanists. In this text, we argue that the brew made from Gaultheria insipida tends to
modify the consciousness and bodies of female and male drinkers in different ways. We present
here six testimonials from Chichaja drinkers collected during ethnological fieldwork started in
December 2010 and finalized in July 2011, conducted in different parts of Colombia, particularly
the west Amazon forest. The active components of Gaultheria insipida, as well as the very
special psychotropic properties of the brew elaborated from this plant, are so far unknown for
science.
Key Words: MSC (modified state of consciousness), male, female, psychedelic brew,
indigenous knowledge.
Introduction
Gaultheria insipida is a plant native to the Andes, used traditionally by indigenous female
healers near the Colombian Amazon to prepare a brew called Chichaja, also known as the
“Female Ayahuasca”, widely used today before or after the consumption of Ayahuasca in
Colombia. The aim of this text is to describe the effects of Chichaja over consciousness and
body. Chichaja tends to alter in divergent ways the consciousness and bodies of female and male
drinkers. Such is the thesis we defend according to the observations made during fieldwork
(December 2010 - July 2011), which have been conducted in different parts of Colombia,
particularly the west Amazon forest (Mocoa, Putumayo). In order to present this unknown
*
Correspondence: Leonardo Rodríguez Perez, The Pierre du Bois Foundation for Current History, Geneva.
E-Mail: perez.rodriguez@graduateinstitute.ch
*
Correspondence: Sonia Patricia Murcia Roa, Universidad Nacional de Colombia, Bogotá.
E-Mail: spmurciar@unal.edu.co
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
994
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
psychedelic brew, we make comparisons of Chichaja with Ayahuasca, a well-known psychedelic
drink from the Amazon.1
Problem, Hypothesis and Methodology
Traditionally, Gaultheria insipida has been used by Inga indigenous women, based in Sibundoy High Putumayo, to elaborate Chichaja. The Colombian anthropologist, Clara Giraldo-tafur has
studied the ways this brew is used by Inga women in Santiago, one of the main towns in
Sibundoy. We found the item “Chichaja” among other 118 indigenous medicines listed by the
anthropologist, and we learn it would be useful to heal laziness, sleeping excess and bodily
pains:
Table 1. Medical and Nutritious Plants used by Inga Women in Santiago, Sibundoy Valley,
Putumayo.
Scientific Name
(Ericaceae)
Gaultheria
insipida
Inga Name
Uses
Chichaja
Hemorrhoids,
Prevent diseases,
blood cleaning,
bodily pains,
laziness and
sleeping excess,
purgative.
Preparations
1. Hot tee, sirop
with tropical fruits
(to drink three
times daily),
Chichaja decoction.
1
Ayahuasca is a term of Quechuan origin that means “vine of the souls,” and refers to the brew habitually made from
the decoction of two plants native to the Amazon forest: the vine Banisteriopsis caapi and the leaves of Psychotria
viridis. We have an extensive bibliography about this brew, recently reviewed by Labate(2008).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
995
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
Taken from: GIRALDO-TAFUR, Clara. Medicina tradicional de la mujer Inga.
Revista de la Academia Colombiana de Ciencias. Vol. XXIV, N. 90, Mars 2000. P. 17.
(Translated from Spanish by authors).
Here, we will focus on the shamans we have shared time and experience with within a field-work
started in December 2010 and finalized in July 2011: the mestizo Gregorio Castro and his wife
Carmenza Chindoy-Garreta, from the Inga indigenous people. They run a healing center called
“Ornoyaco”, located near Mocoa, bellow the Sibundoy Valley. While Gregorio is responsible for
all the matters related with the Ayahuasca, Carmenza is responsible for preparing Chichaja.
The dry leafs of Gaultheria insipida are ground, put in a cauldron with water and boiled the
entire night. At dawn, the liquid has reduced to just a few liters. Once the brew is ready,
Carmenza shakes a wairasacha and chants to cast a spell on the brew, while Gregorio carries out
the same ritual with Ayahuasca. This gender-based division of labor is related with the spirit that
is associated to Chichaja. It is a female spirit, a mother, who some chichaja drinkers report to
have seen during theirs experience with the brew. Sometimes Chichaja is related with two spirits,
a mother and her daughter, but in any case it is always linked to a female presence. It is why
Chichaja is called the female Ayahuasca, a designation not restricted to the Gregorio and
Carmenza, but that has been adopted all around the country.
What does it mean for Chichaja to be associated with a female spirit or spirits? It seems to mean,
at first glance, that women have less painful experiences with Chichaja. They have normally
more relaxed and short processes with the brew, in comparison with men’s experiences. Indeed,
as we can see in ceremonies and as reported by drinkers and shamans, most of the men have a
hard time with Chichaja (in psychedelic terms commonly referred to as “bad trips”).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
996
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
Why does Chichaja seem to affect in different ways male and female drinkers? A
pharmacological study is needed to answer that question in a complete way. Maybe there are
some active components that act in different manners in male and female bodies and minds. But
a chemical research about the active components of Gaultheria insipida and Chichaja does not
exist to date. To partially answer that question, we used the participative observation method.
We listened to people talking about their experiences with Chichaja, paying attention to gender
differences, observing Chichaja drinkers. We could obtain six testimonies from people who
agreed to talk with us about their experiences with Chichaja, two young men and two women
over their thirties, the testimonies from Carmenza and Gregorio, and of course, we drunk
Chichaja ourselves several times.
Chichaja & Patriarchalism
According to Carmenza: “the Chichaja is the master mother and the Ayahuasca is the father.
Chichaja is a medicine for body and mind. When the process of spiritual quest has begun, they
help the being to look at himself and see what has happened in oneself and what are the things
that one needs to transform in oneself, it helps to become conscious… it’s a centering plant. It
allows reassessing the feminine part of each one of us and teaches you to value your feminine
side.”
From data collected in interviews, it seems Chichaja offers “bad trips” or “hard lessons” if the
drinker has some patriarchal beliefs or attitudes. Some parts of the interviews can illustrate such
idea. For example, a young man talked about the moment his Chichaja experience became
difficult to handle: “I had asked mother Chichaja to be gentle with me, to treat me with love.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
997
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
After drinking Chichaja, I continued my prayer, and, a short time after, I started seeing images
from the past: I was with my girlfriend in a taxi travelling to the airport, and I was being rude
with her. I blamed her for not knowing to which terminal we were supposed to go to, and for that
reason we were risking to miss our flight. When I saw these images, Chichaja told me: ‘you did
not treat your girlfriend with love, why do you ask to be treated with love by me?’. At that
moment – the young man continues- it became hell”.
As we see from this quotation, the spirit of Chichaja can talk to the drinker, show images and the
drinker can talk with her, just as with Ayahuasca. This oral account also teaches us about the
way Chichaja may spot which aspects of the personality the drinker needs to improve in order to
be a better person. Another young man shared with us a very intimate experience he had had
with Chichaja. He told us that when he was younger he used to watch a lot of pornographic
videos. Once under the effects of Chichaja:
“I saw images of nude women, especially their breasts, and I started having the feelings I usually
have when masturbating, or when penetrating a woman. Then Chichaja told me “you are
addicted to that sensation, you are addicted to sex, you cannot escape from here, you must
recognize it”. “yes, I do recognize it” – answered the young man to Chichaja- After I said that –
he continues- I puked my soul”. Here, Chichaja Spirit is an agent who helps the drinker to realize
his limitations, and, after doing so, the drinker has no choice because he cannot escape from
himself. Chichaja then cleans up the drinker’s body, opening the possibility to change what is
wrong with his sexuality.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
998
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
Women Experiences with Chichaja
So far, we have described Chichaja experiences with men. What can we say about women
Chichaja experiences? As a female spirit, Chichaja seems to have preference with female
drinkers. It’s not strange to observe women who drink Chichaja, have short processes with the
brew, from one to three hours, while men may be laid down all the day or even more. One of the
women who had a short process with Chichaja, just stood up without assistance, and told
Gregorio (the shaman), Chichaja has said to her that the brew has gone to the liver and was
working with blood circulation and that was all the process she had. Nevertheless, Chichaja can
also give “hard lessons” to women. We have registered the case of a skilled female drinker, with
several and well-passed experiences with Chichaja. Although, once she made a “bad trip”. Later
she explained she got a hard process because she had not asked Chichaja spirit to kindly guide
her during her experience. Instead of that, she had promised herself to be strong under the effect
of Chichaja, and therefore Chichaja had punished her pride.
From the testimonies we have quoted, we can argue that one of the main teachings Chichaja
offers to “her sons and daughters”, is to learn to be gentle, soft, kind, lovely people. Given that
softness, delicate manners are associated with a female way of being, while aggressive or
proudly manners are viewed as male behavior, Chichaja has been qualified with a female
personality, besides the fact people see, listen and feel a female spirit. This is just a hypothesis,
we are not saying that all women are delicate and all men aggressive, but only referring to a type
of social representation on gender roles in Colombia and maybe in Western culture in general.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
999
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
Chichaja and Ayahuasca
Now that we have a general view about what Chichaja is, it is time to make a comparison
between Chichaja and Ayahuasca, in order to understand the place Chichaja holds in the
Ayahuasca ensemble. We can list first the characteristics which distinguish Chichaja from
Ayahuasca. Chichaja is always associated with a female spirit, while Ayahuasca could be linked
either with female or male spirits. Chichaja tends to induce different effects depending on the
drinker’s sex (which is not the case with Ayahuasca) and it produces some particular symptoms.
The drinker feels hot waves on the face, the arms; the skin becomes extremely sensitive, any
sensory stimulus is dramatically amplified as an electrical vibration in the nerves (indeed the
drinker is advised not to take a shower after the experience, because the feeling of water on the
skin would be unbearable).
Carmenza offers a dose of about 20 centiliters of Chichaja brew, which is much more than a
standard Ayahuasca dose. Chichaja is a very less concentrated brew and its taste is not as bitter
as Ayahuasca taste, but is not very pleasant neither. About twenty or forty-five minutes after
consumption, the drinker starts to feel Chichaja effects. It is quite common to see bright colors at
the beginning of the process, as orange, red, blue, that occupy all the field of vision. During these
moments, the drinker sees nothing but vivid colors. Between these periods of “colorful
blindness”, the drinker can go through gaps of total blackness, and this full blackness could
appear at several points of the experience and last many minutes and produce anxiety. The ataxia
individuals sometimes experience with Ayahuasca, is much more common with Chichaja, it’s
almost a rule. Therefore, with Gregorio and Carmenza, it is mandatory, to be allowed to drink
Chichaja, to have a personal assistant that will take care of the drinker. Ideally, the person who
assists the drinker may be a relative or a close friend, eventually he or she will guide the drinker
to the bathroom, help him or her with clothes.
This is very different from Ayahuasca drinking, when it is not needed any pre-selected personal
assistant; if the drinker eventually suffer ataxia he or she just can rely on the help of the shaman
or shaman’s assistants. With Ayahuasca, it is not necessary to choose a place to stay after the
consumption, at least in Ornoyaco healing center. With Chichaja, because of the very common
ataxia, the drinker must select a place to lay down before taking the brew.
What is the reason to drink Chichaja plus Ayahuasca?. At the end, what does Chichaja offer that
Ayahuasca does not? Chichaja specializes in certain teachings, because of its female nature, as it
has been argued in this text. Also it’s possible that Chichaja complements the cleaning of
Ayahuasca. At least, the use of Chichaja and Ayahuasca is very related in Ornoyaco healing
center. Most of the time Ayahuasca consumption takes place at night, while Chichaja
consumption takes place at the beginning of the day, before breakfast. Chichaja would clean the
drinker up before Ayahuasca. In that way, according with taita Gregorio Castro, the drinker will
be able to reach a direct conexion with “the source”, or “the information”. Thus, Chichaja would
allow the drinker to have an actual enteogenical experience, by skipping the purgative period
often precedes Ayahuasca visions.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | November 2013 | Volume 4 | Issue 9 | pp. 993-1000
1000
Rodríguez Perez, L. & Murcia Roa, S. P., Is Gender Important in Consciousness Exploration? The Modification of Male & Female
Consciousness with Chichaja Brew
Conclusion
Chichaja, “the female Ayahuasca”, is an almost unexplored matter. We would like to insist in the
need to carry out an ethnobotanical research on Gaultheria insipida. Researchers can go to
Colombia and contact shamans using Chichaja. We also need a chemical study of the active
components of Chichaja. If the effects described here are proved independent of set/setting, it
would be an important discovery in the world of psychedelic plants and ethnobotanic. We hope
this text will be an introduction to further quantitative-qualitative work on the gender-based
effects of Chichaja, and the possibilities Gaultheria insipida could offer in medical and
consciousness research.
References
CAICEDO-FERNÁNDEZ, Alhena (2012). La alteridad radical que cura. Los nuevos lugares del
chamanismo en Colombia. Paris: École des Hautes Études en Sciences Sociales EHESS. PhD dissertation
in antropology directed by professor Anne-Marie Lonsonczy.
GIRALDO-TAFUR, Clara (2000). Medicina tradicional de la mujer Inga. Revista de la Academia
Colombiana de Ciencias. Vol. XXIV, N. 90, Mars.
LABATE, Caiuby Beatriz, SANTANA de ROSE, Isabel and GIMARAES DOS SANTOS –edits- (2008).
Ayahuasca Religions: A Comprehensive Bibliography and Critical Essays. Santa Cruz (California):
MAPS.
DALTON, Joseph (1897) “TAB 60-70, Gaultheria insipida, native from Ecuador and New Granada”. In:
Curtis’s Botanical Magazine. Comprising the Plants ot the Royal Gardens of Rew and of Other Botanical
Establishments in Great Britain with Suitable Descriptions. Vol. XXIX, London.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
A Theory of Consciousness from a
Theoretical Computer Science Perspective:
Insights from the Conscious Turing Machine
Lenore Blum and Manuel Blum†
Abstract
The quest to understand consciousness, once the purview of philosophers and theologians, is
now actively pursued by scientists of many stripes. We examine consciousness from the
perspective of Theoretical Computer Science (TCS), a branch of mathematics concerned with
understanding the underlying principles of computation and complexity, including the
implications and surprising consequences of resource limitations.
We are inspired by Alan Turing’s simple yet powerful definition of a computer, the Turing
Machine (TM), and by the Global Workspace Theory (GWT) of consciousness originated by
cognitive neuroscientist Bernard Baars and further developed by him, Stanislas Dehaene, JeanPierre Changeux, George Mashour and others. We are not looking for a complex model of the
brain nor of cognition but for a simple substrate independent computational model of (the
admittedly complex concept of) consciousness.
We do this by defining the Conscious Turing Machine (CTM), also called a Conscious AI, and then
we define consciousness and related notions in the CTM. While these are only mathematical TCS
definitions, we suggest why the CTM has feelings of consciousness. The TCS perspective provides
a simple framework to employ tools from computational complexity theory and machine learning
to help us understand consciousness and related concepts.
Previously we explored explanations for the feelings of pain and pleasure in the CTM. Here we
consider additional phenomena generally associated with consciousness, again from the
perspective of the CTM. We start with three examples related to vision (blindsight, inattentional
blindness, and change blindness), then follow with a discussion of dreams, altered states, and
free will. We give explanations derived from the model and draw confirmation from consistencies
at a high level – well above the level of neurons – with the psychology and neuroscience
literature. This paper is intended to be an introduction to a much-expanded monograph, in
preparation.
Key words: feelings of consciousness, theoretical computer science, substrate independent
model, computational model, global workspace, multi-modal, model of the world, phenomenal
consciousness, the hard problem.
†
The work of Lenore Blum and Manuel Blum was supported in part by CMU, in part by a sabbatical year from CMU at the
Simon’s Institute for the Theory of Computing, and in part by a gift from UniDT. Email addresses: lblum@cs.cmu.edu and
mblum@cs.cmu.edu . The definition of the Conscious Turing Machine (CTM) first appeared in (Blum & Blum, 2021). To be
self-contained, a streamlined version of the basic definition of the model is presented here as well as amplification of key
components and arguments for the “feeling of consciousness”. The sections in this paper on Blindsight, Inattentive
Blindness, Change Blindness, Illusions, Dream Creation, Free Will, and Altered States of Consciousness in the CTM are new. A
version of this paper has been published in PNAS (Blum & Blum, 2022).
© 2022 Blum & Blum
1
Introduction: Why a Theoretical Computer Science Perspective?
Thanks to major advances in cognitive neuroscience, humanity is now on the brink of understanding how the
brain achieves consciousness. In 1988, cognitive neuroscientist Bernard Baars proposed a Global Workspace
Theory (GWT) of the brain, sketched its architecture, and outlined its implications for understanding
consciousness. See (Baars B. J., 1988)2 and (Baars B. J., 2019). That, together with the invention of fMRI in 1990,
and the seminal investigations by Francis Crick and Christof Koch (Crick & Koch, 1990) into the neural correlates
of consciousness, helped shake off the taboo on the scientific study of consciousness. As a consequence, the
quest to understand consciousness is now actively pursued by scientists of many stripes.3
We study consciousness from the perspective of Theoretical Computer Science (TCS), a branch of mathematics
concerned with understanding the underlying principles of computation.4 These principles largely include the
complexity of computation, which deals with the consequences and unexpected usefulness of taking resource
limitations into account. This perspective has provided not only a theoretical foundation for the computer
revolution but also surprising new concepts and ingenious applications stemming from considerations of
computational complexity. TCS is our principal tool. We claim that its perspective and unique insights add to the
understanding of consciousness and related concepts such as qualia and free will. Demonstrating this is a major
goal of our work.
With this in mind, we give a simple abstract substrate-independent computational model of consciousness that
we call the Conscious Turing Machine (CTM) (see Chapter 1 ). The CTM is inspired by Alan Turing’s simple yet
powerful model of computation, the Turing Machine (TM), by Bernard Baars’ GWT, and by the Global Neuronal
Workspace Theory (GNWT) of (Dehaene & Changeux, 2011) and (Mashour, Roelfsema, Changeux, & Dehaene,
2020).
0
We are not looking to model the brain or suggest neural correlates of consciousness – however interesting that
may be. We are looking to understand consciousness and how a machine might experience feelings. Our intent
is to come to terms, eventually, with the hard problem (Chalmers, 1995). Our view is that consciousness is a
property of all properly organized computing systems, whether made of flesh and blood or metal and silicon.
Confirmation for explanations from the CTM come from consistencies at a high level – well above the level of
2 Baars’ GWT is strongly influence by earlier work in cognitive science, much of which was done at Carnegie Mellon: (Simon, 1969),
(Reddy, 1976), (Newell, 1990) and (Anderson, 1996).
The various approaches to the study of consciousness include psychological (James, 1890) and (Freud S. , 1900); philosophical
(Dennett D. C., 1991) and (Chalmers, 1996); information theoretic measures of consciousness (Tononi, 2004) and (Tononi & Koch,
2015); structural (Baddeley & Hitch, 1974); and neural correlates (Dehaene & Changeux, 2011). Our approach to consciousness is
architectural. It is informed by and close in spirit to (Baars B. J., 1997) and (Dehaene S. , Consciousness and the Brain: Deciphering
How the Brain Codes Our Thoughts, 2014).
3
The architectural approach to the study of consciousness was inspired by the architectural models of cognition. These were
developed largely at Carnegie Mellon University by Herb Simon’s Sciences of the Artificial (Simon, 1969), Raj Reddy’s Blackboard
Model (Reddy, 1976), Allen Newell’s Unified Theories of Cognition (Newell, 1990), and John Anderson’s ACT-R (Anderson, 1996).
The global workspace idea is due to Newell. An important more recent architectural model of cognition is LIDA (Baars & Franklin,
2009).
4 (Sipser, 2013) is a great introduction to TCS.
2
© 2022 Blum & Blum
neurons – with the psychology and neuroscience literature,5 and from agreement with aspects of other theories
of consciousness (see Chapter 5).
In this introduction, we present a brief overview of TCS and CTM using popular terms as they are typically
informally understood. The perspective on TCS includes an example of the relevant seemingly paradoxical
concept of pseudo-randomness that got defined and understood by TCS. In those same terms, we outline some
of our understanding of consciousness from the CTM. These informal definitions and understandings from CTM
are formalized after this introduction.
The reader who wants the formal treatment straightaway can skip from here directly to Chapter 1 .
0
What is Theoretical Computer Science (TCS)? Alan Turing’s seminal paper “On computable numbers” (Turing A.
M., 1937) is arguably the genesis of TCS. That paper presents a formal mathematical definition of a “computing
machine”, now known as the Turing Machine (TM). In it, Turing defines a simple theoretical universal
programmable computer6 that can compute any function computable by any computer or supercomputer,
though of course it looks nothing like any modern-day computing machine. It was not until a decade later that
Turing wrote the specs for a possible implementation.7 Theorems are the raison d'être of mathematical theories,
and Turing proved what might be called the first theorem of TCS, namely the unsolvability of the Halting
Problem. In modern parlance, this theorem proves there can be no universal (debugger) program for
determining which computer programs halt and which do not: it is just not possible to construct one. This result
is equivalent to the undecidability of elementary number theory (Church, 1936), and it implies a weak form of
Kurt Gödel’s First Incompleteness Theorem (Gödel, 1931).8
After Gödel and Turing, mathematical logicians started categorizing which problems were solvable, which not, as
well as investigating the esoteric hierarchy of unsolvable problems.
With the advent and wider availability of computing machines in the 1960’s, it soon became clear that a number
of important problems that were solvable in principle could not in fact be solved, not even with the fastest
conceivable computers, and that this was not a problem with the state of technology but something deeper.9
5 We note a historical synergy between theoretical computer science and neuroscience. Turing’s simple computer model led
neuroscientist Warren S. McCulloch and mathematician Walter Pitts to define their formal neuron, itself a simple model of a neuron
(McCulloch & Pitts, 1943). Mathematics forced their model to have inhibition, not just excitation - because without inhibition, (loop-free)
circuits of formal neurons can only compute monotonic functions - and these do not suffice to build a universal Turing Machine. The
McCulloch-Pitts neuron also gave rise to the mathematical formalization of neural nets (Wikipedia, 2022) and subsequent deep learning
algorithms (Goodfellow, Bengio, & Courville, 2016), further illustrating ongoing synergies.
6 In the mathematical tradition going back to Euclid, of formulating axioms (basic premises) and proving theorems (deriving
consequences), Turing identified fundamental principles (the Turing Machine) that lead to unexpected consequences (universal Turing
Machine, the halting problem, etc.) and a deep understanding of computation. Many other models of discrete computation such as the
lambda calculus of Alonzo Church (Church, 1936) give rise to the same set of computable functions. This gives credence to the ChurchTuring thesis that no reasonable model of computation can compute more than what a Turing Machine can compute. (See (Yao, 2003) for
implications to classical physics.)
7 Although Turing’s 1937 paper was strictly a paper in mathematical logic – there were no computers at the time – Turing did intend to
construct a practical programmable computing machine. In 1945, he brought with him to the British National Physical Laboratory an 86page detailed blueprint for an Automatic Computing Engine (ACE), a universal programable computer, which he intended to build (Turing
A. M., 1945). Politics intervened and it was never built, only the less ambitious Pilot ACE (Hodges, 1992).
8 Before Gödel and Turing, mathematicians had the unshakable belief that with enough knowledge and work, any mathematical problem
could be solved. As the mathematician David Hilbert famously said in 1930 at his retirement address (Dawson, 1997): “This conviction of
the solvability of every mathematical problem is a powerful incentive to the worker. We hear within us the perpetual call: There is the
problem. Seek its solution. You can find it by pure reason, for in mathematics there is no ignorabimus [sic].”
9 Suppose that when program P is run on computer C, on any input of length n, it has run time 2n. Let C+ be the same computer except
that C+ runs twice as fast as C. Then program P, run on computer C+, on any input of length n+1, will have run time 2n+1/2 = 2n, which is
3
© 2022 Blum & Blum
Researchers in the emerging field of theoretical computer science10 realized that among natural finite (and
therefore solvable) problems there appeared to be a dichotomy between those problems that were feasibly
(efficiently) solvable and those that were not, mirroring the earlier dichotomy between solvable and unsolvable.
Feasibly solvable became formalized mathematically as solvable (by some computer program) in polynomial time
(P). Furthermore, the realization emerged that problems solvable in polynomial time and problems checkable in
polynomial time (NP) might not be equivalent.11 Indeed, deciding the equivalence (or not) would answer the
famous million-dollar P =? NP question, see (Goldreich, 2010).
Besides defining a hierarchy of serial fast (poly time) computational complexity classes, TCS defines a hierarchy
of parallel superfast (polylog time) computational complexity classes. Both hierarchies inform the definitions and
choices employed in our model.
Understanding the dichotomy between easy and hard, quick and slow, and their implications launched a
complexity revolution with a rich theory, reframing of ideas, novel concepts and stunning applications. Indeed,
developments in computational complexity over the past 40 years have shown how to use hardness to our
advantage, to deal with seemingly impossible problems. This has created a paradigm shift in mathematics,
namely the ability to exploit the hardness of some problems to resolve others.12
We illustrate with the (relevant) concept of a computer-generated random sequence, called a pseudo-random
sequence.
On the face of it, the very idea of a pseudo-random sequence is so incongruous that von Neumann joked (von
Neumann, 1951), “Anyone who considers arithmetical methods of producing random digits is, of course, in a
state of sin.”
More precisely, a pseudo-random sequence generator is a feasible (polynomial time) computer program for
generating sequences that cannot be distinguished from truly random sequences (generated by independent
tosses of a fair coin) by any feasible computer program. Thus, in the polynomial time world in which we live,
pseudo-random sequences are, for all intents and purposes, truly random.13 This understanding was impossible
without the clarifications made by TCS and the distinctions between polynomial and superpolynomial
complexity. (See (Yao, 1982) and (Yao, 2003).)
An application of the above ideas is to replace the use of random sequences in the Conscious Turing Machine
(CTM) by sequences produced by pseudo-random generators supplied with (short) random seeds. In particular,
the same running time as C on any input of length n. TCS considers the increased speed of C+ (and therefore C++, C+++, …) over that of C to
be insignificant for running P when n is large.
10 Early researchers in computational complexity included Jack Edmonds (Edmonds, 1965), Stephen Cook (Cook, 1971), Richard Karp
(Karp, 1972), and Leonid Levin (Levin, 1973).
11 Solvable in polynomial time (P) means it is possible to find a solution in time polynomial in the size of the problem instance. Checkable
in polynomial time (NP) means that given a purported solution, its correctness can be checked in time that is polynomial in the size of the
problem instance. On the face of it, finding a solution seems harder than checking it. Properly coloring the nodes of a graph with 3 colors
is hard (NP-hard so likely not in P), while checking if a 3-coloring is proper, meaning that no edge joins two nodes of the same color, is
easy (in P).
12 Modern secure communication is based on mathematically embedding hard number theoretic problems, e.g., the integer factoring
problem, in digital messages. Breaking the security would be tantamount to solving the hard problem.
13 Such pseudo-random sequence generators are randomness amplifiers. From a short random seed, they efficiently generate long
sequences that are indistinguishable in polynomial time from truly random sequences of the same length.
4
© 2022 Blum & Blum
if the probabilistic CTM has “free will”, as will be argued, then so does this deterministic CTM. This free will of a
deterministic CTM is counter to some and perhaps much of the thinking on determinism.14
Now for consciousness. The TCS perspective is employed in defining the Conscious Turing Machine (CTM), a
simple machine that formalizes a modified version of the Global Workspace Theory (GWT) of consciousness.
Baars describes consciousness through a theater analogy as the activity of actors in a play performing on the
stage of Working Memory, their performance under observation by a huge audience of unconscious processors
sitting in the dark (Baars B. J., 1997).15
In the CTM, the stage is represented by a Short Term Memory (STM) that at any moment in time contains CTM’s
conscious content. The audience members are represented by an enormous collection of powerful processors –
each with its own expertise – that make up CTM’s Long Term Memory (LTM) (section 1.1.1). These LTM
processors make predictions and get feedback from CTM’s world. Based on this feedback, learning algorithms
Internal to each processor improve that processor’s behavior (section 0).
LTM processors, each with their own specialty, compete (sections 1.1.2 and 1.3) to get their questions, answers,
and information in the form of chunks (section 1.1.3) on the stage for immediate broadcast to the audience.
Conscious awareness (elsewhere called attention) is defined formally in the CTM as the reception by the LTM
processors of the broadcast of CTM’s conscious content. In time, some of these processors become connected
by links (section 1.1.4) turning conscious communication (through STM) into unconscious communication
(through links) between LTM processors. Communication via links about a broadcasted chunk reinforces its
conscious awareness, a process that Dehaene, Changeaux, et al call ignition (Dehaene & Changeux, 2005).
While these definitions are natural, they are merely definitions: they do not prove that the CTM is conscious in
the sense that the term is normally used. For that, we argue that these definitions and explanations capture
commonly accepted intuitive concepts of consciousness (Chapters 2) and agree, at a high-level, with cognitive
neuroscience explanations of phenomena generally associated with consciousness. (Chapter 3).
Complexity considerations enter into fixing the detailed definition of CTM. These details include, for example,
1. the formal definition of a chunk, which is the information that each LTM processor puts into the
competition for consciousness at each and every tick of the clock (section 1.2),
2. the fast probabilistic competition algorithm that selects which one of the many competing chunks
reaches consciousness (sections 1.3 and 1.4),
3. the machine learning algorithms (section 0) in each processor that use feedback from global broadcasts,
other processors, and the outside world, to update the CTM’s competitiveness and reliability, and
4. the memory that in each LTM processor is random access rather than the linear access (FILO) of Turing
machine tapes, because random access is needed for such things as fast binary search.
Complexity considerations, particularly the consequences of limited resources, play a crucial role in our high
level explanations for consciousness-related phenomena such as change blindness and the feeling of free will.16
14
“Many thinkers, indeed, believe that the determinism we find in the physical world seems to be incompatible with
freedom in the sense implied by free will” (Lavazza, 2019). The fact that a random number generator can be replaced by a
pseudo-random number generator equipped with a small random seed, on the other hand, suggests otherwise.
15 See Figure 2-1 on page 42 & 43 of (Baars B. J., 1997).
16 Eric Horvitz has pointed out the role limited resources plays for intelligent systems, see e.g., (Gershman, Horvitz, & Tenenbaum, 2015).
5
© 2022 Blum & Blum
Although inspired by Turing’s simple yet powerful model of a computer, the CTM is not a standard Turing
Machine. That’s because what gives the CTM its “feeling of consciousness”, whether it is awake (Chapter 2) or
dreaming (section 3.5), is not its computing power nor its input-output maps, but its Global Workspace
architecture, its predictive dynamics (cycles of prediction, feedback and learning, section 0), its rich multi-modal
inner language (which we call Brainish, section 1.2) and certain special LTM processors including an Inner
generalized Speech processor and a Model-of-the-World processor (Chapter 2).
As we have said, we are not looking for a model of the brain but for a simple model of consciousness, and even
there, the CTM model can hardly be expected to explain everything: it is too simple for that. The reasonableness
of the model (and its TCS perspective) should be judged by its contribution to the discussion and understanding
of consciousness and related “hard” problems.
This paper presents an overview of the CTM model: we refer the reader to our first paper (Blum & Blum, 2021)
for additional details. Whereas that (first) paper explores explanations for the feelings of pain and pleasure in
the CTM17, this (second) paper explores other phenomena generally associated with consciousness (in Chapter
3) such as dreams and free will. We also consider three examples related to vision (blindsight, inattentional
blindness, and change blindness), then follow with a discussion of dreams, free will and altered states. We give
explanations derived from the model and draw confirmation from consistencies at a high level with the cognitive
neuroscience literature. Confirmation for the model also comes from agreement with aspects of other theories
of consciousness.
These two papers are intended to be an introduction to an expanded monograph (Blum, Blum, & Blum,
monograph in preparation).
17 For an update on pain and pleasure in the CTM, see Chapter 4, The Hard Problem for Pain and Pleasure, in
https://arxiv.org/abs/2011.09850.
6
© 2022 Blum & Blum
TABLE OF CONTENTS
ABSTRACT.......................................................................................................................................................................... 1
INTRODUCTION: WHY A THEORETICAL COMPUTER SCIENCE PERSPECTIVE? ....................................................................... 2
1
THE CTM MODEL ....................................................................................................................................................... 8
1.1
1.2
1.3
1.4
1.5
1.6
1.7
BASIC CTM STRUCTURE + DEFINITION OF “CONSCIOUSNESS IN THE CTM” ................................................................................8
Short Term Memory (STM) & Long Term Memory (LTM) Processors ....................................................................8
The Up-Tree & Down-Tree .....................................................................................................................................8
Conscious Content, Conscious Awareness & Streams of Consciousness ................................................................9
Links, Unconscious Communication & Global Ignition ...........................................................................................9
Input & Output Maps, Sensors & Actuators .........................................................................................................10
Summary of Connections .....................................................................................................................................10
BRAINISH (THE CTM’S MULTI-MODAL INNER LANGUAGE), CHUNKS & GISTS ...........................................................................11
(PROBABILISTIC) UP-TREE COMPETITION, COIN-FLIP NEURON & COMPETITION FUNCTIONS .......................................................12
COMPLEXITY OF COMPUTATION & TIME DELAY FOR CONSCIOUS AWARENESS...........................................................................14
MEMORIES & THE HIGH LEVEL STORY...............................................................................................................................14
PREDICTIVE DYNAMICS = PREDICTION + FEEDBACK + LEARNING (SLEEPING EXPERTS ALGORITHM) ................................................15
COMPARISON OF CTM WITH THE GLOBAL WORKSPACE THEORY MODEL .................................................................................16
2
THE FEELING OF CONSCIOUSNESS............................................................................................................................ 17
3
HIGH LEVEL EXPLANATIONS..................................................................................................................................... 20
3.1
3.2
3.3
3.4
3.5
3.6
3.7
BLINDSIGHT .................................................................................................................................................................20
INATTENTIONAL BLINDNESS .............................................................................................................................................20
CHANGE BLINDNESS ......................................................................................................................................................21
ILLUSIONS ....................................................................................................................................................................22
DREAM CREATION .........................................................................................................................................................23
ALTERED STATES OF CONSCIOUSNESS ................................................................................................................................25
FREE WILL ...................................................................................................................................................................26
4
SUMMARY .............................................................................................................................................................. 28
5
RELATION TO OTHER THEORIES OF CONSCIOUSNESS ............................................................................................... 29
ACKNOWLEDGEMENTS .................................................................................................................................................... 30
FAQ ................................................................................................................................................................................. 31
ABOUT THE AUTHORS OF THE EXPANDED MONOGRAPH (BLUM, BLUM, & BLUM, MONOGRAPH IN PREPARATION). ...... 37
REFERENCES .................................................................................................................................................................... 38
7
© 2022 Blum & Blum
1 The CTM Model
1.1 Basic CTM Structure + Definition of “Consciousness in the CTM”
Throughout this paper, statements about the Conscious Turing Machine (CTM) are printed in black. Examples of
human and animal consciousness, generally printed in burgundy, are intended merely to clarify concepts and
arguments. Burgundy-colored statements also refer to features that a human or animal would have if it were
correctly modeled by CTM.
The CTM is (a device that is defined by) a 7-tuple,
< STM, LTM, Up-Tree, Down-Tree, Links, Input, Output >,18
whose components are described in the rest of this section 1.1 (for more details, see (Blum & Blum, 2021)). The
CTM has a clock that measures time in discrete clock ticks, t = 0, 1, 2, …, T ≈ 1010, roughly 10 ticks per second,
that being the alpha rhythm of the brain. The CTM has a finite lifetime, T. It is born at time 0, and dies at time T.
Short Term Memory (STM) & Long Term Memory (LTM) Processors
In the CTM, the stage (conscious arena) is represented by a Short Term Memory (STM). This is a small memory
capable of holding a single chunk (defined in section 1.2).
The audience (in the unconscious arena) is represented by a massive collection of N > 107 powerful parallel
random-access processors, each with their own random-access memory, each memory large enough to hold a
small multiple of T chunks. These together make up the Long Term Memory (LTM). Each LTM processor runs a
number of algorithms, one of which is the processor’s personal Sleeping Experts algorithm (section 0). All
processors are in LTM, none in STM, so when we say processor, we always mean LTM processor.
Certain special (LTM) processors are particularly responsible for CTM’s “feeling of consciousness”. These include
especially a Model-of-the-World processor and other Inner generalized Speech processors for handling inner
speech, inner vision, inner tactile sensation, and so on (see Chapter 2).
The Up-Tree & Down-Tree
The Up-Tree is an up-directed binary tree of height h having N leaves, one leaf per LTM processor, and a single
root in STM. Every directed path from leaf up to the root is of length h. Information in the Up-Tree travels from
the leaves below to the root above19. The Down-Tree is a simple down-directed tree of height 1 with a single
root in STM and N edges directed from that root to the N leaves, one edge per processor, which carry
information from the root to all N leaves.
LTM processors, each with their own specialty, compete via the Up-Tree competition (section 1.3) to get their
questions, answers, and information in the form of chunks (section 1.2) into STM. The competition takes h clock
ticks.
At each time t, all LTM processors submit information to the competition for STM. One of those processors wins
access to STM at time t+h, and all processors receive the winning broadcast from STM at time t+h+1.
18 Coincidently, the classical Turing Machine is also defined as a 7-tuple, < Q, Σ, Γ, d, q , q
0
accept, qreject>, where Q is a finite set of States, Σ is
the Input alphabet, Γ is the Tape alphabet, d is the Transition function, q0 is the Start state, qaccept is the Accept state, and qreject is the
Reject state.
19 In TCS jargon, “trees” are generally up-side down. They should perhaps have been called “roots”.
8
© 2022 Blum & Blum
Conscious Content, Conscious Awareness & Streams of Consciousness
The chunk that wins the Up-Tree competition (to get into STM) that began at time t-h is called the conscious
content of CTM at time t.20 We say that CTM becomes consciously aware of that conscious content, which
appeared at time t in STM, when it is received at time t+1 by all LTM processors.21
We have defined conscious awareness as the reception by all LTM processors of STM’s broadcast, rather than as
the appearance in STM of the winning chunk, to emphasize that the feeling of consciousness arises after all
processors, including especially the Model-of-the-World and Inner generalized Speech processors (see Chapter
2) receive the broadcast and act on it.
Our definition of conscious awareness in the CTM (i.e., the reception by all LTM processors of STM’s broadcast)
aligns roughly with what cognitive neuroscientists call “attention”. See for example (Graziano, Guterstam, Bio, &
Wilterson, 2020) and (Mashour, Roelfsema, Changeux, & Dehaene, 2020). Reverberation of chunks via processor
links immediately following reception is related to what (Dehaene & Changeux, 2005) call “ignition”. What
cognitive neuroscientists call “awareness”, or “subjective consciousness”, align roughly with what we call “the
feeling of consciousness” in the CTM (see Chapter 2).
One reason to keep the number of chunks in STM small (exactly one in our model) is to ensure that all
processors focus on the same information in the broadcast from STM. Another reason is to keep the model as
simple as is reasonably possible for an understanding of consciousness.22
CTM is constantly bubbling with the activity of chunks competing for STM, its winners being (constantly)
broadcast from STM to LTM.23 The time-ordered chunks that are broadcast from STM to LTM form a stream of
consciousness. This stream, as argued in Chapter 2, is part of the subjective “feeling of consciousness”.
Links, Unconscious Communication & Global Ignition
All communication between any two processors occurs initially (at birth and until links are formed) via STM. For
example, processor A can submit a query to the Up-Tree competition. If the query wins the competition, it is
broadcast to all processors. Processor B may then submit an answer via the competition, which if it wins gets
20 For simplicity, STM holds only one chunk at any moment in time. In humans, the storage capacity of short-term memory is roughly 7±2
chunks (Miller, 1956), where a chunk can be a word, a phrase, a digit, and so on. A few chunks cycling through STM can simulate some
aspects of an STM that holds several chunks. Cycling can happen via the Up-Tree competition and the Down-Tree broadcasts. In this
way, CTM can keep thoughts alive in STM continuously through many cycles by sending the thought from processor to STM to processors
to STM to ….
21 For simplicity, we stipulate reception of the broadcast by all LTM processors. This is a simplification of what goes on in humans, as the
dorsal stream of vision is never conscious, only the ventral stream is conscious.
22 Leslie Valiant (Valiant, 2013, pp. 127-128) does not assert that focus is primary. He asserts instead that limited computational resources
and constraints imposed by the need to learn are the primary reasons for the small size of conscious information. While these are
reasonable factors, the principle factor in our opinion is the required focus.
23 This bottom-up/top-down cycle is analogous to the Global Neuronal Workspace (GNW) hypothesis (Dehaene, Changeux, & Naccache,
2011) that “conscious access proceeds in two successive phases … . In a first phase, lasting from ≈100 to ≈300 ms, the stimulus climbs up
the cortical hierarchy of processors in a primarily bottom–up and non-conscious manner. In a second phase, if the stimulus is selected for
its adequacy to current goals and attention state, it is amplified in a top–down manner and becomes maintained by sustained activity of a
fraction of GNW neurons, the rest being inhibited. The entire workspace is globally interconnected in such a way that only one such
conscious representation can be active at any given time … .”
The dynamic of chunk submission to competition for STM (the stage) and subsequent broadcast of the winning chunk to the LTM
processors (the audience) corresponds roughly to the GNW global ignition property. However, GNW ignition is significantly more subtle
and complicated, depending, e.g., on strength (or absence) of sensory inputs), and having variable duration.
9
© 2022 Blum & Blum
broadcast, and so on. If A acknowledges that B’s answer is useful, and this occurs sufficiently often, then a bidirectional link forms (or an existing one is strengthened) between A and B.24
In addition to processors putting chunks into the Up-Tree competition, processors can send chunks through
links. When chunks are sent through links that formerly went through STM, conscious communication (through
STM) between A and B turns into unconscious communication between A and B.25 As additional links form
between A and B we say the link between A and B is strengthened.
Links are channels for transmitting information between processors. Those chunks sent between linked
processors following the broadcast of CTM’s conscious content, can re-enforce and sustain conscious
awareness.26 This re-enforcement is related to what (Dehaene & Changeux, 2005) call “global ignition” in their
Global Neuronal Workspace Theory (GNWT).
Input & Output Maps, Sensors & Actuators
CTM’s environment (Env) is a subset of Rm(t) where R denotes the real numbers, m is a positive integer
dimension, and t, a non-negative integer, is time.
Input maps take (time-varying) environmental information acquired by CTM’s sensors, and send it to designated
processors to convert into chunks (section 1.2).
Output maps take chunks from designated processors, convert them to command instructions, and send those
instructions to actuators that act on the environment.
Summary of Connections
In summary, there are five kinds of connections in the CTM that provide paths and mechanisms for transmitting
information. The five, shown in Figure 1, are:
1. Env à LTM: directed edges from the environment via sensors to processors of the sensory data.
2. LTM à STM: via the Up-Tree edges.
3. STM à LTM: via the Down-Tree edges.
4. LTM à LTM: bi-directional edges (links) between processors.
5. LTM à Env: directed edges from specific processors (like those that generate instructions for finger
movement) to the environment via actuators (like the fingers that receive instructions from these
processors) that act on the environment.
24 Linking is reminiscent of the Hebbian principle (Hebb, 1949) “Neurons that fire together wire together”.
25 If the CTM has 107 LTM processors, corresponding to ≈107 cortical columns in the brain, and if all pairs of processors are initially linked,
there will be ≈1014 links, which is a large possibly infeasible number of links: in the brain, a link is an axon, part of a neuron, at most one
axon per neuron, and since the brain has less than 1011 neurons, it has less than 1011 links, so not all processors can be linked.
Worse yet, a processor with 107 inputs might need to run its own personal competition to decide what to look at.
Although one might want certain special processors linked initially, we choose for simplicity to have no processors linked at birth.
25 The question arises: Why is a tree necessary? Why not just compute f(chunk
p,t,0) / ∑all N LTM processors p’ f(chunkp’,t,0) in.
26 “Global ignition occurs when a broadcast excitation exceeds a threshold and becomes self-reinforcing, with some neurons exciting
others that, in turn, return the excitation. The connected burst into a self-sustained state of high level activity, a reverberating ‘cell
assembly,’ as Hebb called it,” is what (Dehaene S. , Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts, 2014)
calls global ignition.
10
© 2022 Blum & Blum
Figure 1 Edge connections in CTM to and from an LTM processor.
1.2 Brainish (the CTM’s Multi-Modal Inner Language), Chunks & Gists
Brainish is CTM’s inner language used (by the gists in chunks) to communicate between processors,27 whether
via the competition and broadcasts or directly through links. Brainish is the language used to express inner
speech, inner vision, inner sensations (Chapter 2), imaginings and dreams (section3.5 ). It includes coded
representations of inputs and outputs all expressed with succinct multi-modal Brainish words and phrases
called gists. A gist can hold the essence of a scene or the (high level expandable) idea of a proof. It can be an
answer to a query, an insight of some sort, a dream image, a description of pain, and so on. Brainish is able to
express and manipulate images, sounds, tactile sensations, and thoughts – including unsymbolized thoughts –
better than spoken outer languages such as English, Chinese or “doggish” (Slobodchikoff, 2012). We claim that
having an expressive inner language is an important component of the feeling of consciousness (Chapter 2).28
Information is carried on all edges between LTM processors, between STM and LTM, from input to LTM, and
from LTM to output, by chunks.
A chunk is a 6-tuple, < address, t, gist, weight, intensity, mood >, where
•
address is the address29 of the LTM processor that produced the chunk,
•
t is the time that the chunk got produced (put into the competition),
•
gist is the information, “concisely expressed” in Brainish, that the processor intends to
communicate. A gist can hold the essence of a scene or the (high level expandable) idea of a proof.
It can be an answer to a query, an insight of some sort, a dream image, a description of pain such
as from a torn ligament, and so on.
•
weight is a valanced real number that the processor gives the gist,
•
intensity starts off as |weight|, and
•
mood starts off as weight.
We note that the size of a chunk (and hence the size of its components, including its gist) will necessarily be
bounded by computational complexity considerations to be described (see section 1.4 and (Blum & Blum, 2021)
for more specifics).
27 The language used internally by a processor, as opposed to between processors, varies in general from one processor to another; it
includes but is not restricted to Brainish.
28 Representing and learning multimodal inputs is an important aspect of machine learning (ML). Paul Liang, PhD student in ML at
Carnegie Mellon, is developing Brainish, CTM’s multimodal language.
29 If the CTM has 107 LTM processors, corresponding to ≈107 cortical columns in the brain, then the address is a 7 digit number.
11
© 2022 Blum & Blum
1.3 (Probabilistic) Up-Tree Competition, Coin-Flip Neuron & Competition Functions
The Up-Tree competition is the mechanism that determines which LTM processor will get its chunk into STM. At
each clock tick t = 0, 1, …., T, the tth competition starts with each processor p putting its chunk, with its time set
to t, into its leaf of the Up-Tree. After a chunk is submitted to the Up-Tree competition and while it moves up
the competition tree, its address, t, gist, and weight remain unchanged; but its intensity and mood get updated
to incorporate ever more global information.
Deciding whether or not a chunk (a variant of the original chunk) moves up one level in the Up-Tree or drops out
is made by a fast tiny parallel circuit, one such circuit located in each of the non-leaf nodes of the Up-Tree, each
making its decision in one clock tick (the time between two successive clock ticks).
The probabilistic Up-Tree, rather than the deterministic Up-Tree, is the right one to consider30. In the
probabilistic Up-Tree, each node has and uses a coin-flip neuron (Figure 2) in its built-in circuit. A coin-flip
neuron is a device that takes as input an (ordered) pair (a, b) of non-negative real numbers (a ≥ 0 and b ≥ 0), and
in one step – a fraction of a clock tick – does the following:
if a+b > 0, it outputs a with probability a/(a+b), else b; ; if a = b = 0, it outputs a with probability ½, else b.
Figure 2 A coin-flip neuron on an input (a, b) with a + b > 0.
At each clock tick, the circuit in a non-leaf node v runs a local competition that probabilistically selects one of v’s
two (sibling) children based on a comparison of the chunks they contain, then moves (a variant of) that chunk
into v. That chunk is said to be the winner of the local competition at/for v.
The local competition employs the Up-Tree’s (i.e., CTM’s) competition function f, a function that maps chunks
to non-negative real numbers in a fraction of a clock tick, to choose the local winner.
Specifically, suppose at level s, 0 < s ≤ h, node vs at level s, chunkp(L) and chunkp(R) are the chunks in vs‘s left and
right children respectively. Then:
1. with probability { f(chunk p(L)) / (f(chunk p(L)) + f(chunk p(R))) if the denominator ≠ 0, or with probability
½ if the denominator = 0 }, chunkp(L) is the local winner,
2. else chunkp(R) is the local winner.
We now specify the chunk that moves into vs. Suppose the local winner at vs is the variant of chunkp,t,0 having
addressp, t, gistp,t,0, and weightp,t,0. Then the chunk that moves into vs will be:
chunkp,t,s = < addressp, t, gistp,t,s, weightp,t,s, intensityp,t,s, moodp,t,s >, where
gistp,t,s = gistp,t,0, weightp,t,s = weightp,t,0, intensityp,t,s = (intensityp(L),t,s-1) + (intensityp(R),t,s-1), and moodp,t,s =
(moodp(L),t,s-1) + (moodp(R),t,s-1).
Note that intensityp,t,s = ∑ p’ (intensityp’,t,0) and moodp,t,s = ∑ p’ (moodp’,t,0), where the two sums ∑p’ are over all
LTM processors p’ in the subtree rooted at vs.
30 For a partial explanation, see Q7 of the FAQ.
12
© 2022 Blum & Blum
We call a CTM with a probabilistic Up-Tree competition a probabilistic CTM. In this paper, except where
otherwise stated, all CTMs will from now on be probabilistic.
REMARK. Updating the chunk at node vs consists in computing the f-values of the two sibling children of vs,
using that as input to a coin-flip neuron to choose the local winner, and then making the needed additions to
get intensity and mood. This must all be done in 1 clock tick, which puts bounds on both the amount of
computation that can be performed in a node and the size of the chunk in that node. (See section 1.4 and (Blum
& Blum, 2021) for more specifics.)
By a simple induction, the winner of the Up-Tree competition (the conscious content of CTM at time t+h) will
be:
chunkp,t,h = < addressp, t, gistp,t,0, weightp,t,0, intensityp,t,h, moodp,t,h >
where intensityp,t,h = ∑all N processors p’ in LTM (intensityp’,t,0) and moodp,t,s = ∑all N processors p’ in LTM (moodp’,t,0).31
Let t ≥ h. The current mood of CTM at time t, moodt, is defined to be the mood of the chunk that is broadcast
from STM at time t. Thus CTM becomes consciously aware of moodt at time t + 1.
REMARK. moodt = ∑all N LTM processors p moodp,t-h,0, so moodt/N is the average mood of the chunks submitted to the
competition at time t - h.
Moodt is defined to be CTM’s mood, “optimistic/happy” if positive, “pessimistic/sad” if negative, at time t when
the winning chunk is in STM.32 (Alternatively, Moodt could have been defined to be the mood at time t-h when
the winning chunk was put into the competition, or the mood at time t+1 when the chunk was received by all
processors by broadcast). Intensityt is defined similarly to be CTM’s level of “energy/enthusiasm/confidence” at
time t.
We say that a competition function f is additive if f(chunkp,t,s (vs)) = f(chunkL(vs)) + f(chunkR(vs)). Examples of
additive competition functions include f(chunkp,t,s ) = intensityp,t,s, or more generally,
f(chunkp,t,s ) = intensityp,t,s + c·moodp,t,s for any real c, -1 ≤ c ≤ +1, but not f(chunkp,t,s ) = |moodp,t,s|.
f(chunkp,t,s ) = |moodp,t,s| is not additive, because |a + -a| ≠ |a| + |-a|.
THEOREM. If the competition function f of a probabilistic CTM is additive, then every chunk submitted to the
Up-Tree competition gets a fraction of time in STM proportional to its f-value, its importance as determined by
f. Specifically, the probability that a submitted chunkp,t,0 gets into STM is
f(chunkp,t,0)/∑all N LTM processors p’ f(chunkp’,t,0).33
As a consequence, for additive f, the permutation chosen to assign processors to leaves of the Up-Tree has no
effect on the sequence of broadcasts from STM (see (Blum & Blum, 2021) for more specifics including the
statements of these theorems and their proofs).
31 The question arises: Why not just compute intensity
p,t,h = ∑all LTM processors p’ (intensityp’,t,0) in one step to get the intensity of the chunk
winning the competition? (Similar question for moodp,t,s = ∑all LTM processors p’ (moodp’,t,0 ).) Answer: however you do it, you need log N steps
to compute the ∑. Note that processors in general do not know what chunks other processors have entered into the competition. Global
information is accumulated locally at each step of the Up-Tree competition.
32 (Kringelbach & Berridge, 2017) argue that in humans “emotion is always valenced—either pleasant or unpleasant—and dependent on
the pleasure system”.
33 The question again arises: Why not just compute f(chunk
p,t,0) / ∑all N LTM processors p’ f(chunkp’,t,0) in one step to get the probability of a
chunk winning the competition? One of many answers: however you do it, you need log2N steps to compute the ∑.
13
© 2022 Blum & Blum
We note that f(chunkp,t,s ) = |moodp,t,s| is a bad choice for more reasons than that it is not additive: If at level 0,
two sibling chunks have weights +100 and -100 and all other chunks have weight = +1, then neither of the two
high intensity siblings will reach STM. This might occur if you spy a $10 bill on the ground, but someone else
picks it up. In that case, the pleasure of finding the $10 bill and the pain of losing it will never reach
consciousness. You would be unconscious of both. This seems unlikely to us.
EXAMPLE. let f = |mood|. Set w1 = 100, w2 = -100, w3 = 1, w4 = 2. Then the competition Up-Tree looks like this:
Mood =
Mood =
Weight = Mood =
6 <— Pr (A) = pr(B) = 0 Pr(C) = 1/3 Pr(D) = 2/3
／ ＼
0
6 <— Pr(C) = 1/3 Pr(D) = 2/3
/ \
/ \
100 -100
2 4
A
B
C
D
Figure 3 Up-Tree competition for f(chunk) = |mood|.
1.4 Complexity of Computation & Time Delay for Conscious Awareness
For t ≥ 0 and s > 0, the computation to update the chunk at node vs in the Up-Tree competition consists of:
1. two fast computations offf, a sum and division of their values, and a fast probabilistic selection,34
2. putting the address, gist and weight of the selected chunk into vs, and
3. summing the intensities and moods of the chunks associated with vs’s children, and setting those
sums to be the intensity and mood respectively of the chunk at vs
These computations, all three of which must be completed in 1 clock tick put a bound on both the size of the
chunk in a node and the amount of computation that can be performed in that node.35
If 1 clock tick is 100ms long and there are 107 LTM processors, then the time from a chunk being placed into
competition by an (unconscious) LTM processor to becoming CTM’s conscious content will be about 2.3 seconds.
If the broadcast takes another 100ms, the total time to conscious awareness will be about 2.4 second. Curiously,
this seems to be about how much time it takes for humans to become consciously aware of decisions made
unconsciously (Smith, 2008). This time can be reduced from 2.4 seconds to .7 sec if the interior nodes of the uptree each have 10 children instead of 2. (See section 3.7 for implications of an Up-Tree delay on free will in the
CTM and/or humans.)
1.5 Memories & The High Level Story
We assume that each processor p stores in its internal memory at time t, the chunkp,t,0 that it submitted to the
competition, the chunk it received by broadcast from STM, and a select subset36 of chunks it received from links
or from Input maps. These stores are a substantial part of CTM’s memories.
34 Alternatively, if f is included with the chunk in the node, then a sum and a fast probabilistic selection will do it faster.
35 The space required to store a chunk must be large enough to store a log N bit address, and to store a gist whose length is no greater
2
than what is required to store approximately one line of English or its equivalent in Brainish, very roughly 210 bits.
36 Assuming CTM is a good model for the brain, it is not possible for each of its N ≈ 107 processors to record from all other N-1 processors,
as that would require CTM to have more links than there are neurons in the brain.
14
© 2022 Blum & Blum
This “history” provides a high level story of what p saw and did. High level stories account in large part for
CTM’s sense of self in its “feeling of consciousness” (Chapter 2). They are called upon when CTM creates dreams
(section 3.5).
Periodically, this stored information may be pruned so only “salient” chunks remain, the most “salient” being
those that represent terrible, wonderful, or unexpected events.37 In general (see section 0), every processor
makes predictions regarding the chunks it generates, modifies, reconstructs, reconsolidates, and stores.
1.6 Predictive Dynamics = Prediction + Feedback + Learning (Sleeping Experts
Algorithm)
Processors require feedback to assess correctness, detect errors, and learn how to boost correctness (diminish
and correct errors).
•
Predictions in CTM are made by LTM processors both within their internal algorithms and implicitly
when they submit chunks elsewhere, whether to the competition for STM, to other processors
through links, or to actuators that effect the environment.
•
Feedback comes from chunks that are received in broadcasts from STM, through links, and from
sensors of the environment via Input maps, indicating correctness or detecting errors in predictions.
•
All learning and error correcting take place within processors.
There is a continuous cycling of prediction, feedback and learning within CTM. The CTM needs to be alert to
anything unusual, surprises of any kind, in order to deal with such things if necessary and to improve its
understanding of the world in any case. Prediction errors (e.g., “surprises”) are minimized by this cycling.
Processors especially need to know if they were too timid or too bold in setting their |weights| so they can
correct their weight-assigning algorithms. Sleeping Experts Algorithms are a class of learning algorithms
employed by LTM processors to do just that. See (Blum A. , 1995) and (Blum, Hopcroft, & Kannan, 2015) for one
of the simplest versions of the Sleeping Experts Algorithms (SEA).38 Here is the idea:
In general, SEA will embolden its processor – pushing it to raise the intensity it gives its chunks – if
1. its chunk did not get into STM, and
2. its information is more valuable (in the SEA’s opinion) than what got into STM.
The SEA will hush its processor – pushing it to lower the intensity it gives its chunks – if
1. its chunk got into STM, and
2. the information in that chunk is found to be less valuable than that of another chunk that failed to get
into STM. (This hushing will typically occur sometime later when the SEA becomes aware of the more
highly valued information.)
Sleeping Experts Algorithms play a role in whether or not processors get their chunks into STM. They also play a
role in whether or not processors “pay attention” to gists in chunks that are sent to them via links. The |weight|
of a chunk is an indication of how important the processor that created the chunk believes its gist to be, and this
will influence whether or not a processor that receives the chunk will pay attention to it.
37 Might the CTM also use compression for this storage? (Al Roumi, Marti, Wang, Amalric, & Dehaene, 2020) discuss mental compression
of spatial sequences in human memory.
38 More sophisticated Sleeping Experts Algorithms will be presented in an expanded monograph (Blum, Blum, & Blum, monograph in
preparation). See also, (Blum A. , 1995), (Blum A. , 1997), (Freund, Schapire, Singer, & Warmuth, 1999), (Blum & Mansour, 2007), (Luo &
Schapire, 2015) and (Blum, Hopcroft, & Kannan, 2015).
15
© 2022 Blum & Blum
1.7 Comparison of CTM with the Global Workspace Theory Model
We conclude this chapter with a comparison between the CTM and Baars’ GWT model (Figure 4).
Aiming for simplicity, we have eliminated or simplified many features in GWT. For example, the CTM
has just one “actor” on stage holding just one chunk at a time. Additionally, in the CTM, all processors
are in LTM. We have eliminated the Central Executive since its sequence of directions, opinions,
questions, answers and so on, as all this can come from processors. In the CTM, inputs and outputs go
directly to and from LTM processors, not directly through STM. This modification is consistent with the
neuroscience literature (Liljenström, 2021).
In the CTM, chunks compete in a well-defined competition to get onto the stage (STM). Conscious
awareness (attention) is the reception by all LTM processors of the broadcasted winning chunk (i.e.,
CTM’s conscious content), not an event that occurs between Input and STM. The roles of Baddeley and
Hitch’s Verbal Rehearsal and Visuospatial Sketchpads (Baddeley & Hitch, 1974) are assumed by LTM
processors.
Predictive dynamics (cycles of prediction, feedback and learning), a multi-modal inner language
(Brainish) as well as computational and complexity considerations, are explicit key CTM features.
Finally, as in the “Extended Mind Theory" of (Clark & Chalmers, 1998), CTM can have access to existing
technology such as Google, Wikipedia, WolframAlpha, AlphaGo, and so on, in the form of LTM
processors tasked to use these apps. This is one way to ensure that CTM has a huge collection of
powerful processors at the start of its life (t = 0), a collection that is augmentable throughout its life.
Figure 4 Baars’ GWT model (l); CTM (r).
Key features of the CTM model and its dynamics resonate with properties of consciousness that (Dennett D. C.,
2018) outlines:
[Neither] a Master Scheduler, nor a Boss Neuron, nor a Homunculus or Res Cogitans [govern the
transitions of our conscious minds]. [What governs] must be a dynamical, somewhat competitive
process of contents vying for fame, for cerebral celebrity ... or relative clout against the
competition. What determines the winners? Something like micro-emotions, the strength of
positive and negative valences that accompany and control the destiny of all contents, not just
obviously emotionally salient events such as obsessive memories of suffering or embarrassment or
lust, but the most esoteric and abstract theoretical reflections.
Although inspired by Baars’ GWT architecture, the CTM integrates features essential for its feeling of
consciousness. This is the focus of the next chapter.
16
© 2022 Blum & Blum
2 The Feeling of Consciousness
While CTM is consciously aware by definition of the conscious content broadcast from STM (section 1.1.3), this
and related notions formalized in the CTM are just definitions. Their reasonableness lies in explanations derived
from the model that draw confirmation at a high level with the psychology and neuroscience literature.
Here we consider the feeling of consciousness in the CTM and summarize arguments given in (Blum & Blum,
2021) about how this feeling is generated in the CTM.39 In Chapter 3 we will discuss how the CTM provides high
level explanations for a range of phenomena generally associated with consciousness. Section 3.5 on Dream
Creation is particularly relevant to the discussion on the feeling of consciousness.
We argue that the feeling of consciousness in CTM is a consequence principally of its extraordinarily expressive
multi-modal inner language, Brainish,40 coupled with CTM’s architecture, certain special processors, and CTM’s
predictive dynamics (cycles of prediction, feedback and learning):
1. Brainish. The multimodal Brainish language describes the sensory world as it is perceived. This
perception consists of gists in the multimodal language of sensations. Its words include gists for odors
(the odors as they are perceived by the nostrils), pains (the terribly unpleasant sensations of pains),
faces (what one sees when looking at someone’s face), and so on. Dreams are important because they
show that gists can perfectly express the world when the CTM has neither input nor output.
To the extent that the CTM is successful in the world, that success owes much to the fact that Brainish
gists give CTM its knowledge of the world. Gists are short multi-modal encodings that encapsulate
important features of CTM’s inner and outer worlds (definitions in 33 below). A sequence of gists can be
a kind of multisensory movie (see the high level story in section 1.3). As we shall see, gists are crucial for
giving the CTM its sense of being alive in the world.
2. Architecture. This includes the Up-Tree competition to gain access to STM (section 1.3) and
subsequent Down-Tree broadcast of the winner to all LTM processors, particularly all processors that
play a special role in generating the feeling of consciousness.
3. Special Processors. We single out a few (such) processors that have specialized algorithms built into
them at birth:
a. The Model-of-the-World processor constructs models of CTM’s worlds based on information
it gets either directly from the environment or from stored possibly modified inner
memories.41 The Model-of-the-World processor also has direct output maps to CTM
actuators, and that some are labeled by past experience, others not.42 We define CTM’s inner
world to be the rough approximate simplified model “CTM” that the Model-of-the-World
39 Integrated Information Theory (IIT) defines a measure of consciousness PHI (Tononi, 2004) which roughly speaking measures the
amount of feedback in a system. The CTM has positive PHI, but we wonder if having consciousness according to this measure implies that
the entity has the “feeling of consciousness”.
40 As will be discussed in section 3.5, dreams help demonstrate the enormous power of Brainish to generate feelings such as the feeling of
consciousness.
41 The Model-of-the-World processor’s inner memories are memories stored in the processor itself or memories gotten from other
processors via links.
42 Can you wiggle your ears? What are you doing in your head when you try to do it? To the extent that the human brain is a CTM, the
human typically decides this by wiggling her ears in her Model-of-the-World and looking in a mirror to see (or feeling her ears with her
hands to tell) if her ears wiggle. This assumes that the ears in the Model-of-the-World, having already been linked to the ears by their
sense of touch and hearing, are linked to the actuators of the ear muscles, if any.
17
© 2022 Blum & Blum
processor creates of the CTM. We define CTM’s outer world to be the model it creates of the
environment. Importantly the Model-of-the-World processor tags parts of its models of the
world (inner and outer) with labels and descriptions annotated in Brainish gists with
sensations they can have and actions they can perform.
b. The Inner Speech processor extracts whatever speech is encoded in the gist broadcast by STM
and sends it to the same locations that the Input map sends gists of outer speech, the latter
being the speech gists created by the Input maps. The CTM uses inner speech to recollect its
past, predict its future, and make plans. The gists of inner speech (such as occur in talking to
oneself or the talking and hearing in a dream) are nearly indistinguishable from the gists of
outer speech. In humans, inner speech sounds so much like outer speech that it can be
difficult, as in disorders like schizophrenia, to distinguish between Inner and outer speech
(Rosen, et al., 2018).
c. Inner Vision, Inner Hearing and Inner (tactile) Sensation processors map whatever images,
sounds and sensations are broadcast from STM to whatever locations the Input maps send
outer scenes and outer sensations. The gists of inner vision can be barely distinguishable from
the gists of outer vision, the visual gists created by the Input maps. CTM’s memories and
predictive abilities enable CTM to create the inner images, sounds and sensations that CTM
uses to generate imaginings and dreams (section 3.5). To thwart schizophrenic hallucinations,
the human brain distinguishes inner images from outer images. The brain has various tricks for
doing this, one being to make dreams hard to remember.
These processors inform the “eyes” and “skin” in the Model-of-the-World to “see” whatever the CTM
recalls from visual memory and to “tactilely sense” whatever CTM recalls from sensory memory - or
creates with its prediction algorithms. These “eyes” and “skin” are CTM’s mind’s eye and mind’s skin.
We consider these processors, together with the Inner Speech processor, as constituting an Inner
generalized Speech processor.
Together with the Model-of-the-World processor, the Inner generalized Speech processor enables CTM
to recollect its past, predict its future, and make plans.
We emphasize that the CTM does not consciously experience the environment directly. The CTM sees,
hears and senses tactilely what is in its models of the world, since inputs go directly to LTM processors
not (directly) to STM.
4. Predictive Dynamics. Additionally, we argue that CTM’s continuous cycling through prediction,
feedback and learning (section 0) together with the stream of consciousness (section 1.1.3), play a
role in CTM’s feelings of consciousness (see (James, 1890)). The feelings are enhanced by (parallel)
predictive dynamics in CTM’s Model-of-the-World where planning and testing is constantly carried
out, often before action is taken by the CTM. Positive feedback gives CTM an indication that it
understands what is going on; negative feedback – unless it is about something that could not have
been predicted such as an unexpectedly loud noise – gives CTM evidence of something that it did not
know or understand.
We also add, but do not develop here:
5. A minimal (general) ability to think and make plans, and
6. Motivation (= energy + drive) to make a plan and then pursue it.
We now return to the Model-of-the-World processor to describe one of its central tasks, that of tagging various
constituent parts of its models as either self or not-self (else unknown).
18
© 2022 Blum & Blum
How does the Model-of-the-World processor determine what is or is not self? If the broadcast of a chunk (a
CTM thought) is immediately followed by an actuator carrying out an action in the environment– and that same
thought leads to the same action consistently and repeatedly – then that indicates the actuator is part of self.
For example, suppose the CTM wishes to lift a rock in the environment “with the power of thought”. This means
that a processor attempts to lift the rock in the real world (i.e., environment) - without using any of its known
actuators – merely by lifting the rock in the Model-of-the-World directly. If that request succeeds in the real
world, meaning the CTM detects that the real world rock got lifted this way, then the Model-of-the-World
processor labels the rock and the thought (gist) that lifts it as self.
The Model-of-the-World processor has additional important jobs that give the CTM its sense of self, including
creating imaginings; creating maps of its environment; registering movements in its environment; helping to
plan actions in the environment; helping to predict the actions of self and not-self in the environment; and
correcting predicted actions of self.
We emphasize that the “self” in the models of the world is (appears to be) the self in the real world as far as the
CTM is concerned. Brainish gists are much more than English labels: they are descriptions of conscious thoughts
every bit as convincing as the descriptions that appear in dreams (see section 3.5).
When (through broadcasts) the CTM detects itself thinking about its own consciousness, the Model-of-theWorld processor tags the “CTM” in its models as “conscious”.
We now look at why the CTM considers itself conscious. It cannot be because the Model-of-the-World
processor or any other processor feels it is conscious, as processors are just machines running algorithms – and
(such) machines have no feelings. We propose that CTM as a whole feels conscious, as the term is normally
understood, as a consequence in part of the fact that the Model-of-the-World processor views the “CTM” in its
model of the world, as “conscious”, and that this view is broadcast to all processors. 43 Here, “CTM” is a simple
learned representation of the much more complex CTM.
Our argument for the feeling of consciousness aligns with Michael Graziano’s argument for m-consciousness in
the Attention Schema Theory (AST). See (Graziano, Guterstam, Bio, & Wilterson, 2020).
43
Shimon Edelman says (personal communication) “This [explanation for the feeling of consciousness in the CTM] reminds
me strongly of the explanation offered by (Metzinger, 2004)”.
19
© 2022 Blum & Blum
3 High Level Explanations
We now explore how CTM might experience a variety of phenomena generally associated with consciousness.
We believe that our explanations, derived from the model, provide a high level understanding of how conscious
experiences might be generated. These draw confirmation from consistencies with the psychology and
neuroscience literature, again at a high level. Indeed, we argue that a very simple well-defined device, the CTM,
supports high level explanations for a great many phenomena whose explanations are otherwise extremely
complex.
Previously (Blum & Blum, 2021) we explored explanations for the feelings of pain and pleasure in the CTM. Here
we consider additional phenomena, again from the perspective of the CTM. We start with three examples
related to vision (blindsight, inattentional blindness, and change blindness), then follow with a discussion of
dreams, free will and altered states.
3.1 Blindsight
Blindsight provides a striking example of the difference between conscious and unconscious awareness
(Striemer, Chapman, & Goodale, 2009). In blindsight, the person does not consciously see the outer world.
When asked to fetch something across a cluttered room, a typical response is “But I cannot see.” Nevertheless,
the person responds adeptly if cautiously to the request. What is going on?
In the CTM, visual Input goes directly from the vision sensors to a subset of LTM processors that process visual
input. But in the blindsighted CTM, due to some malfunction, perhaps a break in the Up-Tree or some other
inability for the Vision processors to enter chunks competitively into the competition, this information does not
get up to STM and hence does not get globally broadcast. For this reason, CTM is not consciously aware that it
can see. However, information can still be communicated between (unconscious) processors via links. So visual
information received by the Vision processors can be sent through links to the Walk Processor that controls the
leg actuators.
At a high level, this explanation is consistent with explanations of blindsight in humans given by (Ajina & Bridge,
2018).44
3.2 Inattentional Blindness
Inattentional blindness occurs when an individual fails to perceive a visual stimulus that is in plain sight. It is “the
failure to notice the existence of something unexpected when attention is focused on some other task” (Jensen,
Yao, Street, & Simons, 2011).
For example, in the famous selective attention test of (Chabris & Simons, 1999), viewers of the “invisible gorilla”
film were asked to “count how many times the players wearing white shirts pass the basketball” (Figure 5).
Nearly all viewers gave close to the correct number (15), but were stunned when asked, “Did you see the
gorilla?”
44 (Ajina & Bridge, 2018) assert that when the primary visual cortex (V1) is damaged impairing conscious vision, blindsighted individuals
still have functional connections between the lateral geniculate nucleus (which receives input from the retina and projects this
information to V1) and hMT+ (the cortical area that detects motion). This functional connection was absent in V1 impaired patients
without blindsight.
In blindsighted individuals, some retinal input travels (unconsciously) directly to hMT+ bypassing V1. We view it likely that this
information is transferred (unconsciously) to, and acted on, by the motor cortex.
20
© 2022 Blum & Blum
Selective attention test:
Figure 5 Screen shots from video, “The original selective attention task” (Chabris & Simons, 1999).
What is going on?
Let’s suppose the CTM is viewing the film. The Input query about the white shirted players gains access to STM
and is then immediately broadcast to all LTM processors. To carry out the task, CTM’s Vision processors assign
high intensities to white shirted gists and very low (possibly zero) intensities to anything black. The chunk with
the “gorilla” gist has little chance to enter STM. The CTM does not consciously see the gorilla.
The CTM explanation of inattentional blindness reduces to the differential intensities given to gists, lower
intensities given to irrelevant ones, and the competing advantages of chunks with higher intensities.
According to simulations performed by (Dehaene & Changeux, 2005), during certain “ignited” states,
“spontaneous activity can block external sensory processing.” They relate this blocking to the cause of
inattentional blindness. In our view, blocking the “sensory processing” in human brains of black objects is
roughly equivalent to the CTM dramatically lowering the intensity of black gists in chunks, thus lowering the
chances of those chunks to enter STM. The effect of differential intensities in the CTM is also consistent with
theoretical implications that inattentional blindness in humans “can serve as a filter for irrelevant information.”
It may also filter out unexpected events (Jensen, Yao, Street, & Simons, 2011).
3.3 Change Blindness
Change blindness occurs when individuals fail to notice large changes in pictures or scenes (Rensink, O’Regan, &
Clark, 1997). It is “the failure to notice when something has changed from one moment to another” (Jensen,
Yao, Street, & Simons, 2011).
An instructive example is the (Test Your Awareness : Whodunnit?) video. A detective enters a murder scene
proclaiming, “Clearly somebody in this room murdered Lord Smythe” and immediately interrogates each
suspect in turn. The maid proclaims, “I was polishing the brass in the master bedroom,” the butler “I was
buttering his Lordship’s scones,” and Lady Smythe “I was planting my petunias in the potting shed.” Enough
information for the clever detective to solve the murder on the spot.45
But why didn’t we notice the many incongruous scene morphs between the beginning screen shot and the end?
(See Figure 6.)
45 Detective: “Constable, arrest Lady Smythe.” Lady Smythe: But, but, how did you know?” Detective: “Madam as any horticulturist will
tell you, one does not plant petunias until May.”
21
© 2022 Blum & Blum
The Whodunnit video:
Figure 6 Beginning and ending screen shots from video (Test Your Awareness : Whodunnit?, 2008).
From the perspective of the CTM:
In viewing the Whodunnit video (Figure 6), CTM has the impression of seeing the whole but doesn’t notice the
changes that take place as trench coat, flowers, painting, and so on are replaced by variants. That is because:
1. The filming is cleverly staged so that there are cuts from the whole scene to the suspects (e.g., the maid
alone), eliminating transitions that show the dark trench coat replaced by the white one, the bear
replaced by the suit of armor, the rolling pin by the candelabra, the dead man now with a change of
clothes and raised leg, and so on. The video Input never signals CTM’s Vision processor that the “scene”
has been modified.
2. And more importantly, the same gist describes both the beginning and ending scenes equally well: “The
living room of a mansion with detective, butler, maid, others, and a man apparently dead on the floor.”
Under these conditions, the CTM experiences change blindness.
Again, the CTM explanation is consistent with literature on change blindness in humans. For example, according
to (Jensen, Yao, Street, & Simons, 2011) confirming earlier work of (Rensink, O’Regan, & Clark, 1997):
“Given that change detection requires adequate representation of the pre- and post-change scenes as
well as a comparison, any task characteristics that influence the richness of the representation or the
tendency to compare representations should affect detection. The semantic importance of the changing
object appears to have the biggest influence on the likelihood the subject will attend, and therefore
notice, the change.”
In other words, detecting change in the Whodunnit? video would have required significant changes in the gists
describing the beginning and ending scenes. But size limitations on conscious content (and the clever scene
transitions) caused the high level descriptions to be essentially the same.
3.4 Illusions
Inattentional Blindness and Change Blindness might be considered examples of illusions.
The CTM is consciously aware (by definition) of the gists (in chunks) that are broadcast from STM. (Those gists
reached STM from LTM. LTM got them directly from sensors via Input maps, from other LTM processors
through links, and from STM by broadcasts.). The gists are stored in LTM memories for many reasons, one being
for use by SEAs, another to supply the processors’ high level stories (section 1.3) such as those that occur in
dreams.
In CTM, the stream of consciousness is the sequence of gists broadcast from STM (section 1.1.3). Each visual gist
at each moment gives the CTM the sense that it sees the entire scene before its eyes, though in truth it sees at
22
© 2022 Blum & Blum
most a tiny fraction of the scene. The illusion of the whole has several explanations, the main one being that a
multi-modal Brainish gist can describe a hugely complex scene like “I’m standing before a Japanese style garden
containing a brook, path, bridge and trees.” Could that gist contain the details of a 12 million pixel photograph
from an iphone camera, which is what it feels like we are seeing? The illusion of the whole is a consequence of
the highly suggestive information in a gist. The CTM conjures up the scene in a kind of magic act. Keith Frankish
(Frankish, 2016) calls this the illusionism theory of consciousness.
3.5 Dream Creation
Dreams are the ultimate illusions. Some people claim not to dream, but most do (Herlin, Leu-Semenescu,
Chaumereuil, & Arnulf, 2015). Their dreams may be visual, auditory, tactile, etcetera. They are often related to
emotional processes (Freud S. , 1900), (Scarpelli, Bartolacci, D'Atri, Gorgoni, & De Gennaro, 2019). They can
express great pain and fear (nightmares), or great pleasure (as in flying dreams). One can feel crippling pain in
the leg and wake up to find that the pain is completely illusory: there is no pain at all. One can be lying face
down and wake face up.
In the CTM, a built-in Sleep processor keeps track of time, habits, day/night etc. and has internal algorithms to
monitor the need for sleep. If and when the Sleep processor determines that sleep is needed, it takes control by
raising the intensity of its own chunks enough to get them into STM and to keep other chunks out. This has
roughly the same effect as lowering the intensities of chunks from other LTM processors. It also blocks or greatly
reduces the intensity of various inputs (eyes and ears), and it blocks signals that activate outputs (such as to
limbs). The CTM sleeps. This is the sleep state.
The Sleep processor continuously monitors the need for sleep, and as that need diminishes, reduces the
intensity of its own chunks proportionately. This eventually permits dream gists (in chunks) to reach STM. This is
the dream state. Finally, when the Sleep processor releases its choke hold on inputs and outputs, the CTM
wakes up. That’s in the CTM. In humans, non-REM and REM sleep can alternate several times before awakening
(Vyazovskiy & Delogu, 2014).
When CTM is in the dream state, a processor acting as Dream Creator becomes active (that is, starts getting its
chunks into STM). The gists in these chunks contain kernels of ideas (typically based on earlier CTM activities,
concerns, imaginations). When these chunks are broadcast, all processors, including those that play key roles in
the feeling of consciousness, receive those broadcasts and compete to respond. This gives the CTM the same
sense of being alive while in the dream state as when it is awake.
The Dream Creator and the other processors take turns interacting back and forth. The conversation – the back
and forth interaction – between Dream Creator and the gamut of processors is the sequence of gists that
constitutes the Dream. This sequence is the dream stream of consciousness.
The Dream essentially stitches together this sequence of chunks to produce a dream stream of consciousness,
aka inner movie, that
1. sees, hears, and senses the dream world, and
2. affects what appears in that dream world.
Such an (interactive) inner movie displays a range of sensory inputs (images, smells and sounds) and generates a
range of actions.
When the CTM is asleep but not dreaming, most processors cannot get their chunks into STM. Exceptions
include detectors of especially loud noises, and the Sleep processor itself. The Sleep processor’s chunk in STM
blocks most other processors’ chunks from reaching STM. By design, it holds an empty gist, so the CTM is not
conscious or barely so.
23
© 2022 Blum & Blum
After the CTM leaves the sleep state to enter the dream state, a fraction of LTM processors such as the Inner
Vision processor can get their chunks into STM. Thus, while dreaming, the CTM is conscious and can experience
events vividly.
Dreams demonstrate the power of Brainish gists. What CTM sees, hears, feels and does in a dream are
necessarily fabrications by processors that can recall, modify, and submit creations to the competition for STM.
These fabrications are realistic because they use the same gists that are generated while awake. Thus, dreams
generate the sense of a realistic world even while CTM is completely divorced from external inputs. As a
consequence, they can appear so realistic that for CTM, as for humans (Corlett, Canavan, Nahum, Appah, &
Morgan, 2014), it may become hard to distinguish dreams from reality. (This problem is avoided in humans if
dreams are hard to remember.)
Confirmation: In When Brains Dream, (Zadra & Stickgold, 2021) refer to research by (Horikawa,
Tamaki, Miyawaki, & Kamitani, 2013) demonstrating that in humans, the same neural pattern of
activity occurs when one sees a face, brings the face back from memory, or when the face appears in a
dream. They also point out that in REM sleep, the activation of the motor cortex in a dream, when one
has the sensation of movement, is the same activation as when awake.
As discussed earlier (Chapter 2), key processors such as those for Inner Speech, Inner Vision, Inner Sensations,
and Model-of-the-World play special roles in generating the “feeling of consciousness” in CTM. These
processors play similar roles when CTM is dreaming.
Here are some examples of how processors help with dream creation:
•
The Inner Speech processor culls the inner speech from the multi-modal gists broadcast from STM
and sends that speech to the same processor that receives outer speech.46 This process causes
speech in dreams to sound like outer speech. The Inner Vision and Inner Sensation processors
help in a similar way with dream creation.
•
The Model-of-the-World processor predicts the effect that CTM’s actions will have in its (inner
and outer) world. It does this from the effect of those actions in its models of the world. The
Dream Creator can use this same prediction machinery to create dreams.
Dreams also enable the CTM to test itself in unknown and possibly dangerous situations. In both
humans and CTM, dreams can be laboratories for experimenting with various possible solutions.
However, unlike what occurs in waking consciousness, inconsistencies are more likely to occur
unnoticed in dreams than while awake since the CTM’s “consistency checkers” in its Model-of-theWorld are not getting input from the environment. Hence the CTM can fly in its dreams
(Zadra & Stickgold, 2021) assert that in humans, “Dreams don’t replay memories exactly; they create a
narrative that has the same gist as some recent memory and could have the same title.” They note
that “REM sleep provides a brain state in which weak and unexpected associations are more strongly
activated than normal strong associations, explaining how it aids in finding the remote associates and
perhaps explaining the bizarreness in our REM sleep dreams.”
46 Spoken speech is not heard as speech until the appropriate links between speaker and hearer are created. These links would appear
most likely early in the life of the CTM.
24
© 2022 Blum & Blum
3.6 Altered States of Consciousness
Under psychedelics or meditation, humans can experience altered states of consciousness ranging from a heightened sense
of awareness to dissolution of self (feelings of being “one with the world”). We agree with (Bayne & Carter, 2018) that
these are states, not levels, of consciousness. We disagree, however, with their assessment that the global/global neuronal
workspace theories are too simple to explain these altered states. Indeed, the beauty of those theories lies in the significant
understanding that comes of their simplicity.
To show how the CTM might experience a simple form of dissolution of self, we start by describing a Mindful
Meditation processor (MMp) that a CTM might have.
The conscious decision to meditate would be the concern of an MMp that creates and submits a sequence of
chunks to the competition for STM. Through repeated practice, this processor gains strength and increases the
intensity of its chunks. It can be surprisingly difficult for the MMp to keep other chunks from entering STM: the
difficulty is not in the sense of lifting a heavy weight or proving a difficult theorem, but in the sense of
demanding focused concentrated attention and practice. (Rathi, 2021) explains how a human, using the Mantra
meditation technique, accomplishes this.
When the MMp is successful, its chunks get into STM and are broadcast. Those broadcasts generally contain
feedback that other processors use, through their Sleeping Experts Algorithm, to hush their own selfevaluations (section 0). Thus during successful meditation, the MMp’s chunks get the lion's share of time in
STM.
Additionally, during successful meditation, chunks that get communicated via links from all processors except
the MMp get hushed – by the incoming broadcasts from MMp – and thus processors are unlikely to pay their
usual attention to the chunks they receive through links.47
This “hushing” or diminishing of functional connectivity is observed in studies on effects of psychedelics and meditation. For
example, brain imaging and electromagnetic studies on effects of certain psychedelics (psilocybin) suggest that the
dissolution of self (“ego-dissolution”) is due to “disintegration” of functional connectivity (Calvey & Howells, 2018).48 This
decreased connectivity accounts in part for the sense of dissolution of spatial boundaries, which in turn leads to the feeling
of being “one with the world”.
47 During successful meditation, the hushing of chunks to be communicated via links diminishes link communication. This in effect
diminishes the Model-of-the-World processor’s ability to communicate to others what is self and what is not-self.
Neuroimaging studies on various forms of meditation from distinct traditions share some common neural correlates, see (Millière,
Carhart-Harris, Roseman, Trautwein, & Berkovich-Ohana, 2018). Importantly, the latter report that in several forms of meditation there is
“attenuation for either activity or functional connectivity” in the medial prefrontal cortex and in the posterior cingular cortex, key nodes
of the so-called default mode network (DMN). The DMN is active when a person is daydreaming or mind-wandering. It is also active when
a person is thinking about others or themselves, remembering the past, or planning for the future, see (Buckner, Andrews-Hanna, &
Schacter, 2008) and (Lieberman, 2013). Thus attenuation of functional connectivity in these areas may also account for dissolution of self.
48 Referencing (Carhart-Harris, et al., 2016), (Calvey & Howells, 2018) suggest that this “disintegration” is due at least in part to decreased
connectivity between the parahippocampal place area (PPA) and the retrosplenial complex (RSC). According to (Epstein, 2008), the PPA is
“concerned with representation of the local visual scene” while the RSC is “more concerned with situating the scene within the broader
spatial environment.”
25
© 2022 Blum & Blum
3.7 Free Will49
a
It matters not how strait the gate,
How charged with punishments the scroll,
I am the master of my fate,
I am the captain of my soul.
- William Ernest Henley (1875)
The Problem of Free Will is ancient. It appears in Lucretius [De Rerum Natura, 1st century BC]:
“If all movement is always interconnected, the new arising from the old in a determinate order – if the atoms
never swerve so as to originate some new movement that will snap the bonds of fate, the everlasting sequence
of cause and effect - what is the source of the free will possessed by living things throughout the earth?”
(Lucretius & Ferguson Smith (translator), 1969).
The Paradox of Free Will is captured by Dr. Samuel Johnson’s (1709-1784) observation (Boswell, 1791):
“All theory is against the freedom of the will; all experience is for it.”
Stanislas Dehaene (Dehaene S. , Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts,
2014) supplies a contemporary voice:
“Our brain states are clearly not uncaused and do not escape the laws of physics – nothing does. But our
decisions are genuinely free whenever they are based on a conscious deliberation that proceeds autonomously,
without any impediment, carefully weighing the pros and cons before committing to a course of action. When
this occurs, we are correct in speaking of a voluntary decision – even if it is, of course, ultimately caused by our
genes [and circumstances].”
We add to Dehaene: computation takes time. To make a decision, a CTM evaluates its alternatives, and such an
evaluation takes time. During that time the CTM is free, can use its inner speech to tell itself it is free, can feel
free, to choose whichever outcome it deems (i.e., computes) best.
The TCS perspective directly addresses The Paradox of Free Will and informs our definitions of Free Will and the
feeling of free will:
First, Free will is the ability to make a decision that violates the laws of physics. As that is impossible,50
no one has Free Will.
Second, the feeling of free will is the conscious knowledge, when one has it, that when faced with a
choice, one can compute the consequences of different courses of action – or as much of those
consequences as is possible with the available resources (time, space, computational power, and
information) – and choose whichever course of action best suits one’s utility and goals. That feeling of
free will is something one can have.
This definition incorporates both predictive dynamics (compute the consequences of different courses of action)
and resource constraints (time, space, computational power, and information).
For example, consider a CTM that is called on to play a given position in a game of chess. Different processors
suggest different moves. The CTM’s main chess-playing processor (assuming one exists, else a processor that has
a “high level” view of the game) indicates, by broadcast of a chunk from STM, that it recognizes it has a choice of
49 See also, (Blum & Blum, A Theoretical Computer Science Perspective on Free Will, 2022).
50 Violating the laws of physics is clearly impossible in a deterministic world. It is also impossible in a probabilistic world in which all
actions are random selections from a well-defined probability distribution.
26
© 2022 Blum & Blum
possible moves and that the decision which move to make merits a careful look at the consequences of each
move. At this point, faced with a selection of possible moves but not yet having evaluated the consequences of
those moves, the CTM is free to choose whichever move it reckons best – within the time constraints.
Will the CTM feel that it has free will?
1. Consider the moment that the CTM asks itself “What move should I make?” meaning this question has
risen to the STM stage and, through broadcast, has reached the audience of LTM processors. In
response, a number of those processors submit suggestions to the competition. The winner of the
competition reaches the stage and gets broadcast. Because gists are short, any such broadcast is short
and therefore reasonably articulable.
2. The continued back and forth comments, commands, questions, suggestions and answers that appear
in STM are globally broadcast to LTM. They give the CTM conscious knowledge of its control: If the
CTM were asked how it generated a specific suggestion, i.e., what thinking went into making that
suggestion, its processors, with the help of its Inner Speech processor, would be able to articulate the
fraction of conversation that reached the stage (though perhaps not much more than that in the short
term).
3. Many LTM processors compete to produce the CTM’s final decision, but CTM is only consciously aware
of what got into STM, which is not all of what was submitted to the competition. Moreover, much of
CTM, meaning most of its processors, are not privy to the unconscious chatter (through links) among
processors. To the CTM, enough is consciously unknown about the process that the decision can
appear at times to be plucked from thin air. Even so, although CTM does not consciously know how its
decisions were arrived at, except for what is in the high level broad strokes broadcast by STM, it knows
that its decisions came from inside itself. The CTM can rightly take credit for making its decisions (after
all, they did come from inside the CTM), can explain some of them with high level stories (see section
1.3), and as for what it cannot explain, it can say “I don’t know” or “I don’t remember.” It is the
knowledge that there are choices, that it (the CTM) has knowledge of those choices – and that it has
ignorance as well – that generates the feeling of free will. Deterministic or not, the experiential feeling
is one of free will.
How important is randomness for this explanation of the feeling of free will? Notice that no quantum physics is
required in the CTM for the above explanation. The only randomness is that of the coin-flip neurons in the UpTree competition and whatever randomness, if any, the processors use in their probabilistic algorithms. It can
be shown, moreover, that the above argument for the feeling of free will still applies for a completely
deterministic CTM, e.g. one that uses pseudo-randomness, i.e., the output of a pseudorandom generator that
has been provided with a (short) random seed in place of true randomness. It follows – and we expect this will
be a source of contention – that even in a completely deterministic world, the CTM will feel it has free will.
What is the significance of the time delay (section 1.4) between chunks being submitted by the unconscious
processors into competition and CTM becoming consciously aware of the winner? Some such delay is necessary
to select one of N chunks for broadcast (plus the single tick for the broadcast). This delay is consistent with the
(Libet, 1985) experiments showing delay between unconscious decisions and conscious actions.
About the Libet experiments: there has been substantial controversy over the interpretation of the Libet
experiments for the existence or not of free will (Gholipour, 2019). For example, some research shows that the
measured delay may be due to effects of stochastic fluctuations (Schurger, Sitt, & Dehaene, 2012), some argue
that the distinction between deliberate or arbitrary decisions have to be taken into account (Maoz, Yaffe, Koch,
& Mudrik, 2019). Other research on volition qualitatively corroborates the earlier results, e.g., (Fried, Mukamel,
& Kreiman, 2011) and (Haggard, 2011). While those results present insight into brain dynamics, we do not view
them as providing arguments for or against free will.
27
© 2022 Blum & Blum
4 Summary
We consider consciousness from the perspective of theoretical computer science (TCS), a nonexperimental area
of mathematics. Inspired by Alan Turing’s simple yet powerful model of a computer, the Turing Machine (TM),
and by Bernard Baars’ Theater of Consciousness, we define a computational model of consciousness, the
Conscious Turing Machine (CTM).
The CTM is defined formally (Chapter 0) as a 7-tuple, < STM, LTM, Up-Tree, Down-Tree, Links, Input, Output >.
The theory includes a precise definition of George Miller’s informally defined chunk, and a precise definition of a
competition for deciding which of the (107 or more) Long Term Memory (LTM) processors gets access to Short
Term Memory (STM).
Bi-directional links between processors that emerge in the life of the CTM enable conscious processing to
become unconscious. Links are also especially crucial for the “global ignition”, described by (Dehaene &
Changeux, 2005) in their Global Neuronal Workspace Theory (GNWT), that re-enforces and sustains conscious
awareness. Input/Output maps enable communication between the CTM and its environment. Other features
of the model can be found in (Blum & Blum, 2021).
In particular, we argue (Chapter 2) that the feeling of consciousness arises in CTM as a consequence of:
1. the global workspace architecture, which enables all processors, including especially those that are
particularly responsible for consciousness – inner Speech, Inner Vision, Inner Sensations and Model-ofthe-World – to be privy to the same (conscious) content of STM,
2. the expressive power of CTM’s multi-modal inner language Brainish,
3. the close correspondence between gists of outer speech (what we say and hear in the world), outer
vision (what we see in the world), and so on, to gists of inner speech (what we say to ourselves), inner
vision (what we see in dreams), and the like, and
4. predictive dynamics = cycles of prediction, feedback, and learning that help CTM develop its
understanding – its ability to deal with – its environment and inner world.
We argue (Chapter 3) that the feeling of free will in the CTM, like the experiences of illusions and dreams, are
direct consequences of CTM’s architecture, certain special processors such as the Model-of-the-World processor
and the Inner generalized Speech processor, the expressive power of Brainish, and its predictive dynamics.
The paper (Blum & Blum, 2021) and an expanded monograph (Blum, Blum, & Blum, Towards a Conscious AI: A
theorectical computer science model of consciousness inspired by cognitive neuroscience, monograph in
preparation) cover the topics presented here in considerably more detail, including especially Brainish, the
Sleeping Experts Algorithms, the Hard Problem (Chalmers, 1995) for pain and pleasure and properties of the
LTM processors.
28
© 2022 Blum & Blum
5 Relation to Other Theories of Consciousness
The CTM is an abstract computational model designed to consider consciousness from a TCS perspective. It is
not intended to model the brain nor the neural correlates of consciousness. Nevertheless, the CTM is both
inspired by, and has certain features in common with, neural, cognitive, and philosophical theories of
consciousness.
The CTM is directly influenced by Bernard Baars’ GWT (Baars B. J., 1997), which is supported by (Dehaene &
Changeux, 2011), (Dehaene S. , Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts,
2014) and (Mashour, Roelfsema, Changeux, & Dehaene, 2020) in their investigation of neural correlates of
consciousness known as the Global Neuronal Workspace Theory (GNWT). We are inspired by David Mumford’s
1991 work on the computational architecture of the neocortex (Mumford, 1991), which we view as an early
proposal for GNWT.
Like the LIDA model of cognition (Baars & Franklin, 2007) and (Baars & Franklin, 2009), CTM is architectural.
Unlike LIDA, which is a more elaborate model of GWT, the CTM is intended to be a minimal model of GWT
sufficient to explain a wide range of conscious phenomena and, in particular, the feeling of consciousness.
Predictive dynamics (the ensemble of prediction, feedback, and learning) is an additional key feature of the
CTM. It is related to the notion of predictive processing (PP), see (Lee & Mumford, 2003) (Friston, 2003) (Friston,
2005) (Cleeremans, 2014) (Clark, 2015) (Seth, 2015) (Hohwy & Seth, 2020).
We see a kinship between the CTM and the self-aware robots developed by (Chella, Pipitone, Morin, & Racy,
2020). We also see a kinship between the CTM and the Global Latent Workspace (GLW) proposed by (VanRullen
& Kanai, 2021) for deep learning. We view the CTM as providing a framework for machine consciousness. The
properties of C0, C1, C2 that (Dehaene, Lau, & Kouider, 2017) suggest for machine consciousness map nicely to
like properties of the CTM.
Our explanation for CTM’s “feeling of consciousness” aligns closely with Michael Graziano’s Attention Schema
Theory (AST) (Graziano, Guterstam, Bio, & Wilterson, 2020). As in AST, CTM is consciously aware of both
external and internal events. Basic AST is similar to GWT: its i-consciousness (i for information) aligns somewhat
with CTM’s conscious awareness. Full AST’s m-consciousness is similar to CTM’s “feeling of consciousness”.51
However, we do not agree with Graziano et al. that GWT “leaves unexplained how people end up believing they
have subjective experience” i.e., that it leaves an explanatory gap. Instead, we argue that in our model, the
feeling of subjective experience arises when “winning chunks” from imaginings and dreams, for example, are
received by the same (unconscious) processors that receive chunks directly from the environment via Input
maps. Additionally, the Model-of-the-World processor incorporates the information gotten from the winning
chunks (i.e., the conscious content of the CTM) into its models of the world, as appropriate, tagging the “CTM”
in all its models of the world as “conscious”. This is similar to Graziano’s argument for consciousness in the AST.
Fuller discussion for the feeling of consciousness in the CTM is in Chapters 2 and 3, and in (Blum & Blum, 2021).
Philosophically, we align with much of Daniel Dennett’s functionalist perspective (Dennett D. C., 1991) except
we don’t agree with his view that we are the only species to have consciousness (Dennett D. C., 1978) (Dennett
D. C., 2019). As for animal consciousness, we agree with (Mumford, 2019) that consciousness is a matter of
degree. Here he cites (Merker, 2007) that consciousness does not need a cerebral cortex: it arises from midbrain
structures. We would also cite other studies, e.g., (Slobodchikoff, 2012).
51 Full AST has three neural networks (A for receiving information, B for constructing an attention schema, and C for reporting to the
outside world) to obtain a system which purportedly thinks it has subjective experience (m-consciousness, m for mysterious).
29
© 2022 Blum & Blum
We do not see the explanatory gap (Levine, 1983) between functional and phenomenological consciousness as
insurmountable. This viewpoint aligns closely with Baars (see (Kaufman, 2020) interview) and (Dennett D. C.,
2016). Indeed, we see the CTM’s ability to tag and test features in its models of the world as playing a role in
the feeling of “what it is like” (Nagel, 1974).
Both AST and CTM appear to embody illusionist notions of consciousness proposed by (Dennett D. C., 2019) and
Keith Frankish (Frankish, 2016). Saying that the feeling of consciousness is an illusion does not deny the
existence of that feeling. As a familiar example, the fact that a movie is made up of (many) discrete still images
does not affect the feeling of continuity one gets from viewing it. The feeling of continuity is an illusion.
By utilizing existing technology (or apps) to supplement its supply of LTM processors (section 0), CTM
incorporates elements similar to those advocated by (Clark & Chalmers, 1998)’s “extended minds”.
Integrated Information Theory (IIT), the theory of consciousness developed by Giulio Tononi, (Tononi, 2004) and
supported by Koch (Tononi & Koch, 2015), proposes a measure of consciousness called PHI, defined using
Shannon’s information theory that essentially measures the amount of feedback in a system. It is a mechanism’s
intrinsic ability to influence itself, rather than its input-output information processing, that determines its
consciousness.
This is consistent with CTM’s intrinsic predictive dynamics (of prediction, feedback and learning). Tononi
proposes five “axioms” (properties) necessary for any causal system to have consciousness.52 Given a detailed
specification of a CTM, one could in principle compute its PHI and compare it to the PHI of any other precisely
defined causal system. It turns out that many causal physical systems have non-zero measures of PHI. IIT would
validate animal consciousness.
With regard to the “adversarial collaboration” between advocates of GNWT and IIT, (Reardon, 2019) and
(Melloni, Mudrik, Pitts, & Koch, 2021), the CTM shares features of both basic theories, as pointed out above.
Our view is that both theories add to the discussion of consciousness. The adversarial aspects between the
theories arise mainly from the advocates’ differing views on brain regions primarily responsible for
consciousness –prefrontal cortex for GNWT, posterior cortex for IIT. We note however, it is possible to have
some level of consciousness without a cerebral cortex at all (Merker, 2007) and suspect that in such cases, as in
the CTM, aspects of the basic GWT and IIT are still in play.
Our view on free will (section 3.5) is close to Dehaene’s (Dehaene S. , Consciousness and the Brain: Deciphering
How the Brain Codes Our Thoughts, 2014). Our explanation of the feeling of free will in the CTM incorporates
additionally and especially, resource limits imposed by computational complexity considerations.
Acknowledgements
We are especially grateful to Jean-Louis Villecroze for his comments, suggestions, and painstaking multiple
reviews of our drafts, his pointers to the literature, and his ongoing work to simulate CTM (Villecroze, Personal
Communication), (Villecroze, 2019). We thank Paul Liang for his insight and work with us, for teaching us about
multi-modal machine learning, and for developing our multi-modal language Brainish (Liang, 2022). We thank
the students and faculty at CMU and PKU for their feedback in our courses. We are grateful to our friend
Michael Xuan for his enormous personal support and encouragement. We thank UniDT for their grant
supporting our work. We also thank the reviewers of early versions of this paper who provided truly thoughtful
constructive suggestions.
52 In (Koch, The Feeling of Life Itself: Why Consciousness Is Widespread but Can't Be Computed, 2019), Christof Koch outlines the axioms:
“[E]very conscious experience has five distinct and undeniable properties: each one exists for itself, is structured, informative, integrated
and definite”.
30
© 2022 Blum & Blum
FAQ
Q1. Since a Universal Turing Machine (UTM) can simulate the CTM, won’t it also be conscious?
A1. Short Answer. The UTM can simulate the CTM as a Turing Machine, but not as a Conscious Turing Machine.
Long Answer. We argue that the CTM has the feeling it is conscious, not that it is conscious.
CTM’s “feeling of consciousness” does not come from its input-output function but from its architecture and the
events happening inside the machine: its internal multi-modal language (Brainish), its predictive dynamics
(cycles of prediction, feedback and learning), certain special processors (especially, Model-of-the-World and
Inner generalized Speech), and from resource considerations.53 Simulating the CTM on a universal Turing
machine significantly alters those properties.
For example, conscious awareness in the CTM is defined as the simultaneous reception by all processors of a
broadcast from the Short Term Memory (STM) stage and the subsequent immediate reinforcing ignition. The
UTM simulation loses the simultaneity completely, and simultaneity is an essential component of the feeling of
consciousness. The UTM will record the existence of a simultaneous reception but not experience it.
As with Tononi’s Integrated information Theory (IIT) of consciousness (Tononi, 2004), completely unwinding the
CTM would eliminate its consciousness (Kleiner, 2020).
______________________________
Q2. Since the CTM has Free Will, won’t a UTM simulating the CTM also have Free Will?
A2. We don’t argue that the CTM has Free Will but that it has the feeling of free will. Recall (section 3.7):
We define free will as the ability to make a decision that violates the laws of physics. From this it follows
that no one has free will.
We define the feeling of free will as the conscious knowledge that, when faced with a choice, the CTM
(knows that it) can do computations to (help) make the decision, i.e., based on those computations and its
utility (the game it is playing), it (knows that it) can make a better decision than can be made if it did not do
the computations. That feeling of free will is something one can have.
As argued in A1 above, a UTM simulating a CTM will not be a CTM as It has no conscious knowledge – no
broadcasting of knowledge to all processors - and thus (from the definition of the feeling of free will) the UTM
does not have the feeling of free will.
Without such a distinction between Free Will and the feeling of free will, the concept of Free Will is
paradoxical. It was a puzzle at least as far back as Lucretius (100-50 BCE). And it led Samuel Johnson (17091784) to wonder how it can be that “All science is against the freedom of the will; all experience is for it.”
______________________________
Q3. Is the CTM a blueprint for a conscious AI?
A3. We view the CTM as a framework for understanding (animal or machine) consciousness, not a blueprint for
designing a conscious AI. The CTM is a purposely simple stripped down substrate independent model for
understanding consciousness. Indeed, to keep the CTM simple and understandable, adding features to it should
be done only with the utmost care, and only if doing so is (arguably) necessary. That said, we do not claim that
the CTM is the only possible machine model of consciousness, just as the Turing machine is not the only possible
model of computation.
53 Taking limited resources into account, in particular time limitations, is a theoretical computer science (TCS) feature that we have
incorporated into the global workspace theory (GWT) in constructing the CTM.
31
© 2022 Blum & Blum
Q4. What is the advantage of having the CTM architecture?
A4. When a processor doesn’t know where to find the information it is looking for, a global broadcast requesting
that information can get other processors engaged in finding it. That’s one advantage. Multi-modal integration
of information is another functionality achieved by this architecture.
______________________________
Q5. Why does the STM hold only one chunk?
A. George Miller suggested the magic number 7±2 for the number of chunks in human short-term memory
(Miller, 1956). Having a small number such as this is important for focusing attention. Some folks are incredulous
that so few chunks will suffice. The CTM emphasizes this point by having just 1 chunk.
______________________________
Q6. Why is the CTM defined in the specific format given (and not some other)?
A. Other formats may be just as good. Some format had to be chosen. Turing chose quintuples for his machines.
Post used quadruples.
______________________________
Q7. What distinguishes conscious (STM) and unconscious (LTM) processes?
A. Conscious processing is what gets broadcast from STM plus whatever communications about that broadcast
through links between processors continue to keep it alive, what (Dehaene & Changeux, 2005) call “ignition”.
Unconscious processing is all the rest. Processing that does not reach STM does not get broadcast and therefore
remains unconscious.
______________________________
Q8. Why is the Up-Tree a strictly binary tree?
A. The binary Up-Tree could more generally be a k-ary tree for some small k, k much less than N (the number of
processors). The original Turing Machine (TM) had just one read/write head and one 1-dimensional tape. Since
then, others have considered TM’s with multiple tapes, multiple heads per tape, multi-dimensional tapes, and so
on. In a similar way, the Up-Tree is made binary because binary is both simple and sufficient, and because the
choice between 2 chunks at a node is slightly simpler to describe.
______________________________
Q9. Why is the resolution mechanism (in the Up-Tree competition) the specific one that is proposed.
A. For the probabilistic CTM, the decision made at each interior node of the Up-Tree – namely which one of the
node’s two children’s chunks should win the match - is decided by which chunk has the larger f-value. As
processor p’s chunk works its way up the tree, its f-value is affected by those processors that neighbor p. It is a
surprising consequence of this mechanism that if f is additive then the probability that a chunk rises to STM is
independent of its location, that is to say, the location of the processor that generated it, on (the leaves of) the
competition tree. As a consequence, the competition is permutation independent.
There are other completely different and even more important reasons for making f additive: for one, when f is
not additive, in each and every one of the many examples considered, something always goes terribly wrong.
For example, if f (chunk) = |mood| then a strong positive mood and a strong negative mood appearing in two
siblings, children of a node, completely cancel: neither becomes conscious (i.e., reaches STM) even when all
other chunks are relatively unimportant.
For example, consider the following Up-Tree with f = |mood| and w1 = 100, w2 = -100, w3 = 1, w4 = 2. Then the
Up-Tree competition looks like this:
32
© 2022 Blum & Blum
f = |mood|
Mood =
6 <— Pr (A) = pr(B) = 0 Pr(C) = 1/3 Pr(D) = 2/3
／
Mood =
Weight = Mood =
0
/ \
100 -100
A
B
＼
6 <— Pr(C) = 1/3
/ \
2 4
C D
Pr(D) = 2/3
For another example, if f(chunk) = |weight| (see figure in answer A1 to Q12), then two chunks having the same
maximum |weight| can have vastly different probabilities of reaching STM. This does not happen if f is additive.
______________________________
Q10. Why do you focus on the probabilistic rather than the deterministic CTM as being the correct model?
A. There are many reasons for this. For one, as noted above, with any additive competition function such as
f(chunk) = intensity, the competition is permutation independent if CTM is probabilistic. This is not the case if
CTM is deterministic, not even if f is additive:
Deterministic Competition with Competition Function f: chunk à intensity.
For another, in the probabilistic CTM, gists submitted to the competition, even those with small intensity, get
into STM with probability proportional to their estimated importance (f-value). Again, this is not the case for a
deterministic CTM.
______________________________
Q11. Why an Up-Tree at all?
A. We need a vehicle for LTM processors to get CTM to pay attention to the “most important” information. We
chose the Up-Tree to execute the competition in part because it computes locally (between 2 siblings) to get the
globally most important information into STM. With an additive competition function, the Up-Tree structure
and competition ensure that processors get their chunks into STM with probability proportional to their f-value,
which is arguably the correct way to do it. We consider the Up-Tree and the decisions it makes to be of
fundamental importance.
______________________________
Q12. Why do the authors choose to have intensity and mood in the chunk? It seems equally valid to discard
them.
A1. Without intensity and mood in the chunk, every “reasonable” competition function such as f(chunk) =
|weight| is non-additive, which leads to the possibility of a weird lopsided kind of consciousness. For example,
suppose the competition tree has N/2 chunks each of a heavy weight W in the left-hand subtree (LHST), exactly
33
© 2022 Blum & Blum
1 chunk of the same weight W in the right-hand subtree (RHST), and that all other chunks have negligible
weight, as in the next figure. In that case, though CTM considers all heavily weighted chunks equally important,
the (heavily weighted) chunks in the LHST each have negligible probability 1/N to get into STM, while the single
heavily weighted chunk in the RHST has probability almost 1/2 to get into STM:
weight =
⇠---- pr{A} = pr{B} = pr{C} = pr{D} ≈ 1/8; pr{E} ≈ 1/2
100
/
weight =
100
weight =
weight =
\
100
/
\
/
100
100
100
\
1
/ \
/ \
/ \
/ \
100 100 100 100 100 1 1 1
A
B
C
D
E
F G
H
⇠---- N=8
A2. At time t+h, the winning chunk contains the weight that was originally assigned to it at time t when it got
put into the competition. The intensity and mood of that winning chunk, which were set to |weight| and
weight respectively at time t, got continuously modified as the chunk moved up the competition tree until the
chunk entered the STM at time t+h, at which time the intensity and mood are indicators of (N times) the
average intensity and mood of the entire CTM at time t. We believe that humans are normally consciously
aware of their global intensity and mood, a fact that makes it entirely reasonable to include intensity and mood
in the chunk.
A3. Chess and tennis tournaments use seeding to give players of equal strength roughly equal chances of
winning the tournament. The Up-Tree competition with additive competition function assures that even
without seeding, all players have a probability of winning proportional to their ability/expertise.
______________________________
Q13. Where does feedback come from?
A. Feedback comes from chunks that are received in broadcasts from STM, through links, and from the
environment via Input maps, all of which have information that can be graded as “erroneous” or “correct” in
comparison to (stored) predictions.
______________________________
Q14. How do processors judge whether or not their information is valuable?
A. Judgements are based on feedback. Each processor has a Sleeping Experts Algorithm (SEA) that learns, based
on feedback, what the weight-giving power of its processor should have been, so that weight assignments
eventually settle down to something more or less correct. Roughly speaking, when a |weight| is too low, the
SEA multiplies the weight-giving power by 2 (more generally by some constant c > 1). When too high, the SEA
multiplies it by ½ (more generally by 1/c).
______________________________
Q15. Why would chunks contain queries and answers?
A. For example, when you meet a person at a party and can’t remember her name, a chunk produced by a
processor can pose the query “What’s her name?”. When this chunk wins the competition for STM, its query is
broadcast to all LTM processors. Sometime later, another processor answers, “I think her name begins with T,”
which rises to STM and gets broadcast. This can later, perhaps much later, trigger another processor to answer,
“Her name is Tina.”
______________________________
34
© 2022 Blum & Blum
Q16: Must the CTM have a Model-of-the-World processor?
A1: The Model-of-the-World processor is a fundamental component of consciousness. Our explanation for the
“feeling of consciousness” is for a CTM that has a Model-of-the-World. We don’t see how to do without it.
A2. Our argument that CTM feels conscious depends on it having a Model-of-the-World processor and is akin to
the argument given by the Attention Schema of (Graziano, Guterstam, Bio, & Wilterson, 2020). We argue that
CTM’s feeling of consciousness, in the sense that the term is normally understood, is a consequence of the fact
that what the CTM consciously knows of the world and of itself in the world is the Model-of-the-World
processor’s view of the world, and its view of the “CTM” in its model of the world; and that this view, which
includes that the “CTM” is conscious, is broadcast to all processors.
______________________________
Q17. Isn’t naming specific processors, such as the Model-of-the-World processor, in definite and final terms,
an over-specification of the model?
A. The proposed Model-of-the-World processor is only an example of how such a processor might work. It is not
meant to be the definitive final specification. It’s kind of like Turing’s universal machine. The idea is important,
as is having a description of such a machine. The particular machine is less important.
______________________________
Q18. Why would the whole cortex not constitute a Model-of-the-World processor (as commonly assumed in
neuroscience) and not just the Model-of-the-World processor?
A. The whole cortex may well be viewed as a model of the world in both the human brain and the CTM. We
don’t suggest otherwise.
______________________________
Q19. Why would the lack of input from the environment lead to incoherent thoughts in dreams?
A. No, no, we’re not saying that dreams must be incoherent, only that they can be incoherent, and that this is
especially the case in dreams because the processors involved in a dream are not getting feedback from the
environment. For example, in a dream, one might believe that one can fly.
______________________________
Q20. What question does the theory address that is not already accounted for by the standard GWT-related
theories?
A1. Unlike standard GWT-related theories of consciousness, CTM is a substrate independent computational
model of consciousness, not a model of the brain. Its purpose is to explain how a machine can experience
feelings. As Arlindo Oliveira has pointed out: “The proposed model is not a model of human consciousness, but a
computational model that can explain many features of conscious behavior and that address directly the hard
problem of consciousness, as defined by Chalmers. [It explains] why systems that are subject to the laws of
physics can have subjective experiences.”
A2. No other GWT-related theory gives a substantive idea how processors might decide among themselves what
information to send to the stage.
______________________________
Q21. How does the theory argue that CTM has free will?
A. We don’t. We argue that CTM has the feeling of free will. Our argument is two-fold.
The first part of the argument has to do with resource limitations - a complexity theory argument. For example,
when the CTM plays chess, it can be faced with a selection of possible moves but, not yet having evaluated the
consequences of those moves, the CTM is free (and knows it is free) to choose whichever move it reckons best within the time constraints.
35
© 2022 Blum & Blum
The second part of the argument is that CTM’s Model-of-the-World processor tags the “CTM” in its models-ofthe-world with a multi-modal Brainish gist asserting that CTM is in the process of choosing its next move meaning that it (the CTM) is free to choose its next move. Of course, its decision is deterministic (assuming as
we do Newton’s deterministic physics). However, this labeling of CTM as having free will gives CTM its
knowledge that its processors may now suggest the next move, and this knowledge is conveyed by a feeling of
free will. This argument is similar to our argument that CTM feels it is conscious.
______________________________
Q22. Do you have an implementation of the CTM?
A. We do not. That said, Jean-Louis Villecroze is working on an implementation as we speak, and Paul Liang is
working on developing the multi-modal language, Brainish, in his PhD research on multi-modal machine
learning. Our own focus is on understanding the hard problem of consciousness and some essential related
features. We are not attempting to provide novel biological predictions, nor AI implementations - as wonderful
as those would be - but to provide a simple machine model for consciousness.
We note that it took Alan Turing almost a decade (mostly due to his war work) to go from his theoretical one
tape universal machine to his complete circuit specification for the implementation of a universal computer – a
description so complete that it included vacuum tube choices, resistor and capacitor values, mercury delay line
memories, and even the cost of the computer in pounds. Unfortunately, due to politics, Turing’s Automatic
Computing Engine (ACE) never saw the light of day; only a more primitive computer, the Pilot ACE, was
constructed.
______________________________
Q23. Why is there little mention of neural correlates of consciousness, particularly with respect to the
phenomenal aspects of consciousness?
A1. The CTM is a computational substrate-independent model of consciousness, not a model of human or
animal consciousness. (That said, a number of explanations from CTM of phenomenal aspects of consciousness
such as blindsight are corroborated at a high level by cognitive neuroscience literature.)
A2. Even a complete knowledge of the “circuitry” of the brain and a complete knowledge of the neural
correlates of consciousness – as wonderful and desirable as it would be to have these - cannot explain how the
feeling of consciousness arises. To understand that feeling, something else is needed. That something is what we
are proposing to get a handle on with the CTM.
______________________________
Q24. Could brain dynamics and competition between attractors be a more neurally plausible explanation for
how the brain works?
A. Perhaps, but... we’re not looking to model the brain or brain dynamics but to understand consciousness. For
this purpose, we use the mathematics that we find most helpful.
________________________________
Q25. Assuming the brain is a CTM, what are some conditions for a part of the brain to be considered the STM?
A. The STM has a very small memory, a relatively small direct input, and an output that goes almost everywhere.
In "A Brain Structure Looking for a Function" (Koch, 2014), Christof Koch suggests that the claustrum might fit
the bill.
________________________________
36
© 2022 Blum & Blum
About the Authors of the expanded monograph (Blum, Blum, & Blum, monograph in preparation).
Manuel has been motivated to understand the mind/body problem since he was in second grade when his teacher told his
mom she should not expect him to get past high school. As an undergrad at MIT, he spent a year studying Freud and then
apprenticed himself to the great anti-Freud54 neurophysiologist, Dr. Warren S. McCulloch, who became his intellectual
mentor. When he told Warren (McCulloch) and Walter (Pitts) that he wanted to study consciousness, he was told in no
uncertain terms that he was verboten to do so - and why (there was no fMRI at the time). As a graduate student, he asked
and got Marvin Minsky to be his thesis advisor. Manuel is one of the founders of complexity theory, a Turing Award winner,
and has mentored many in the field who have chartered new directions ranging from computational learning,
cryptography, zero knowledge, interactive proofs, proof checkers, and human computation. He is a Fellow of AAAS1, AAAS2,
NAS, NAE.
Manuel Blum mblum@cs.cmu.edu
Lenore has been passionate about mathematics since she was 10. She attributes that to having dropped out of school when
she was 9 to wander the world, then hit the ground running when she returned and became fascinated with the Euclidean
Algorithm. Her interests turned to non-standard models of mathematics, and of computation. As a graduate student at MIT,
she showed how to use saturated model theory to get new results in differential algebra. Later, with Mike Shub and Steve
Smale, she developed a foundational theory for computing and complexity over continuous domains such as the real or
complex numbers. The theory generalizes the Turing-based theory (for discrete domains) and has been fundamental for
computational mathematics.
Lenore is internationally known for her work in increasing the participation of girls and women in STEM and is proud that
CMU has gender parity in its undergraduate CS program. Over the years, she has been active in the mathematics
community: as President of the Association for Women in Mathematics, Vice-President of the American Mathematical
Society, Chair of the Mathematics Section of the American Association for the Advancement of Science, Deputy Director of
the Mathematical Sciences Research Institute, and as Inaugural and current President of the Association for Mathematical
Consciousness Science (AMCS). She is a Fellow of AAAS, AMS, AWM.
Lenore Blum lblum@cs.cmu.edu
Avrim had an earlier start than the elder Blums. He spent his first two years at MIT, in his mom’s office in the Math
Department, and in his dad’s office in McCulloch’s lab. In sixth grade, he solved an extra credit math problem by
programming his home-made computer to get a feel for the problem, then (once he saw what was going on) stated and
proved the desired result. Because he used a computer, he got no credit. Odd, because he was pointing to a novel way (at
the time) to solve a math problem. Avrim’s expertise is Machine Learning Theory. He has been an advisor to many of the
young leaders in the field.
Avrim is an active member of the computer science community. He has served as Program Chair for the IEEE Symposium on
Foundations of Computer Science (FOCS), the Innovations in Theoretical Computer Science Conference (ITCS), and the
Conference on Learning Theory (COLT). He has served as Chair of the ACM SIGACT Committee for the Advancement of
Theoretical Computer Science and on the SIGACT Executive Committee. He is recipient of the AI Journal Classic Paper
Award, the ICML/COLT 10-Year Best Paper Award, a Sloan Fellowship, the NSF National Young Investigator Award, and the
Herbert Simon Teaching Award. He is a Fellow of the ACM.
Avrim Blum avrim.blum@gmail.com
All three Blums received their PhDs at MIT and spent a cumulative 65 wonderful years on the faculty of the Computer
Science Department at CMU. Currently the elder two are emeriti and the younger is Professor and Chief Academic Officer at
TTIC (Toyota Technological Institute at Chicago), a PhD-granting computer science research institute focusing on areas of
machine learning, algorithms, AI (robotics, natural language, speech, and vision), data science and computational biology,
and located on the University of Chicago campus. Manuel Blum is Emeritus Professor of Computer Science at UC Berkeley
and CMU. Lenore Blum has been a Distinguished Career Professor of Computer Science at CMU and is currently a
Distinguished Professor-in-Residence at UC Berkeley.
54 Where Freud had written The Future of an Illusion (Freud S. , 1927) , McCulloch followed with “The Past of a Delusion” (McCulloch W.
S., 1953).
37
© 2022 Blum & Blum
References
Ajina, S., & Bridge, H. (2018). Blindsight relies on a functional connection between hMT+ and the lateral geniculate nucleus,
not the pulvinar. PLoS Biol 16(7): e2005769. https://doi.org/10.1371/journal.pbio.2005769. PLoS Biol, 16(7).
Al Roumi, F., Marti, S., Wang, L., Amalric, M., & Dehaene, S. (2020, November 20). Mental compression of spatial sequences
in human working memory using numerical and geometrical primitives . Retrieved from bioRxiv:
https://doi.org/10.1101/2020.01.16.908665
Anderson, J. R. (1996). ACT: A simple theory of complex cognition. American Psychologist, 51(4), 355-365.
Baars, B. J. (1988). A Cognitive Theory of Consciousness. Cambridge: Cambridge University Press.
Baars, B. J. (1997). In the Theater of Consciousness. New York: Oxford University Press.
Baars, B. J. (1997). In the Theater of Consciousness: A rigorous scientific theory of consciousness. Journal of Consciousness
Studies 4, No. 4, 292-309.
Baars, B. J. (2019). ON CONSCIOUSNESS: Science & Subjectivity - Updated Works on Global Workspace Theory. New York:
Nautilus Press.
Baars, B. J., & Franklin, S. (2007, November). An architectural model of conscious and unconscious brain functions: Global
Workspace Theory and IDA. Neural Networks Special Issue, 20(9), 955-961. Retrieved from
https://doi.org/10.1016/j.neunet.2007.09.013
Baars, B. J., & Franklin, S. (2009). Consciousness is computational: The LIDA model of Global Workspace Theory.
International Journal of Machine Consciousness, 1(1), 23-32.
Baddeley, A. D., & Hitch, G. J. (1974). Working memory. In G. A. Bower (Ed.), The Psychology of Learning and Motivation
(pp. 47-89). New York: Academic Press.
Bayne, T., & Carter, O. (2018, September 19). Dimensions of consciousness and the psychedelic state. Neuroscience of
consciousness,.
Blum, A. (1995, July). Empirical support for winnow and weighted-majority algorithms: Results on a calendar scheduling
domain. Proceedings of the Twelfth International Conference on Machine Learning, pages 64-72, July 1995, 64-72.
Blum, A. (1997). Empirical support for winnow and weighted-majority algorithms: Results on a calendar scheduling domain.
Machine Learning, 26(1), 5-23.
Blum, A., & Mansour, Y. (2007). From external to internal regret. Journal of Machine Learning Research, 1307-1324.
Blum, A., Hopcroft, J., & Kannan, R. (2015). Foundations of Data Science. Ithaca. Retrieved from
https://www.cs.cornell.edu/jeh/book.pdf
Blum, L., & Blum, M. (2022, June). A Theoretical Computer Science Perspective on Free Will. Retrieved from arXiv:
https://arxiv.org/abs/2206.13942
Blum, L., & Blum, M. (2022, May 24). A theory of consciousness from a theoretical computer science perspective: Insights
from the Conscious Turing Machine. PNAS, 119(21), https://www.pnas.org/doi/epdf/10.1073/pnas.2115934119.
Blum, M., & Blum, L. (2021, March). A Theoretical Computer Science Perspective on Consciousness. JAIC, 8(1), 1-42.
https://www.worldscientific.com/doi/epdf/10.1142/S2705078521500028.
Blum, M., Blum, L., & Blum, A. (monograph in preparation). Towards a Conscious AI: A theorectical computer science model
of consciousness inspired by cognitive neuroscience.
Boswell, J. (1791). The Life of Samuel Johnson .
Buckner, R. L., Andrews-Hanna, J. R., & Schacter, D. L. (2008, April 3). The Brain's Default Network: Anatomy, Function, and
Relevance to Disease. 1124(1), 1-38. https://doi.org/10.1196/annals.1440.011 Volume 1124, Issu.
Calvey, T., & Howells, F. M. (2018). An introduction to psychedelic neuroscience. Progress in brain research, 1-23.
Carhart-Harris, R., Muthukumaraswamy, S., Roseman, L., Kaelen, M., Droog, W., Murphy, K., . . . Leech, R. (2016, April).
Neural correlates of the LSD experience revealed by multimodal neuroimaging Proc. Natl. A. PNAS, 113(17), 4853–
4858.
Chabris, C., & Simons, D. (1999). The Invisible Gorilla. Retrieved from http://www.theinvisiblegorilla.com/videos.html
Chalmers, D. J. (1995). Facing Up to the Problem of Consciousness. Journal of Consciousness Studies, 2(3), 200-219.
Chalmers, D. J. (1996). The Conscious Mind: In Search of a Fundamental Theory. New York: Oxford University Press.
Chella, A., Pipitone, A., Morin, A., & Racy, F. (2020, February). Developing Self-Awareness in Robots via Inner Speech .
Frontiers in Robotics and AI, 7. Retrieved from https://www.frontiersin.org/article/10.3389/frobt.2020.00016
Church, A. (1936, April). An Unsolvable Problem of Elementary Number Theory. American Journal of Mathematics , 58(2),
345-363.
38
© 2022 Blum & Blum
Clark, A. (2015). Embodied prediction. In T. Metzinger, & J. Windt, Open Mind. Frankfurt am Main: MIND Group.
Clark, A., & Chalmers, D. (1998, January). The Extended Mind. Analysis, 58(a), 7-19.
Cleeremans, A. (2014). Prediction as a computational correlate of consciousness. International Journal of Anticipatory
Computing Systems, 29, 3-13.
Cook, S. A. (1971). The complexity of theorem-proving procedures. Proceedings of the third annual ACM Symposium on
Theory of Computing, (pp. 151-158).
Corlett, P. R., Canavan, S. V., Nahum, L., Appah, F., & Morgan, P. T. (2014). Dreams, reality and memory: confabulations in
lucid dreamers implicate reality-monitoring dysfunction in dream consciousness. Cognitive neuropsychiatry, 19(6),
540–553. https://. Cognitive neuropsychiatry, 19(6), 540–553.
Crick, F., & Koch, C. (1990). Towards a neurobiological theory of consciousness. Seminars in Neuroscience 2, 263–275.
Dawson, J. W. (1997). Logical Dilemmas: The Life and Work of Kurt Gödel. Wellesley, MA, USA: A. K. Peters.
Dehaene, S. (2014). Consciousness and the Brain: Deciphering How the Brain Codes Our Thoughts. New York: Viking Press.
Dehaene, S., & Changeux, J.-P. (2005). Ongoing Spontaneous Activity Controls Access to Consciousness: A Neuronal Model
for Inattentional Blindness. PLoS Biol, 3(5).
Dehaene, S., & Changeux, J.-P. (2011). Experimental and theoretical approaches to conscious processing. Neuron; 70(2),
200-227.
Dehaene, S., Changeux, J.-P., & Naccache, L. (2011). The Global Neuronal Workspace Model of Conscious Access: From
Neuronal Architectures to Clinical Applications. In S. Dehaene, & Y. (. Christen, Characterizing Consciousness: From
Cognition to the Clinic?. Research and Perspectives in Neurosciences. Berlin, Heidelberg: Springer-Verlag.
Dehaene, S., Lau, H., & Kouider, S. (2017, October 27). What is consciousness, and could machines have it? Science,
358(6362), 486-492, DOI: 10.1126/science.aan8871.
Dennett, D. C. (1978). Why You Can't Make a Computer That Feels Pain. Synthese Vol. 38, No. 3, Automaton-Theoretical
Foundations of Psychology and Biology, Part I, 415-456.
Dennett, D. C. (1991). Consciousness Explained. Boston; Toronto; London: Little, Brown and Co.
Dennett, D. C. (2016). Illusionism as the Obvious Default Theory of Consciousness. Journal of Consciousness Studies, 23(1112), 65-72.
Dennett, D. C. (2018, July 30). Facing up to the hard question of consciousness. Philosophical transactions of the Royal
Society of London. Series B, Biological sciences, 373(1755). Retrieved from
http://dx.doi.org/10.1098/rstb.2017.0342
Dennett, D. C. (2019, December). Consciousness, Qualia and the "Hard Problem". (L. Godbout, Interviewer) Retrieved from
https://youtu.be/eSaEjLZIDqc, starting time for quote 5:40
Edmonds, J. (1965). Paths, trees, and flowers. Can. J. Math., 17, 449-467.
Epstein, R. A. (2008). Parahippocampal and retrosplenial contributions to human spatial navigation. Trends in cognitive
sciences , 12(10), 388-396 doi:10.1016/j.tics.2008.07.004.
Frankish, K. (2016). Illusionism as a Theory of Consciousness,. Journal of Consciousness Studies, 23((11-12)), 11-39.
Freud, S. (1900). The Interpretation of Dreams (Vols. IV–V, Standard Edition). London: Hogarth.
Freud, S. (1927). The Future of an Illusion.
Freund, Y., Schapire, R. E., Singer, Y., & Warmuth, M. K. (1999). Using and combining predictors that specialize. Proc. 29th
Annual ACM Symposium on the Theory of Computing.
Fried, I., Mukamel, R., & Kreiman, G. j. (2011, February 10). Internally Generated Preactivation of Single Neurons in Human
Medial Frontal Cortex Predicts Volition. Neuron, 69(3), 548-562.
Friston, K. (2003). Learning and inference in the brain. Neural Netw. doi:10.1016/j.neunet.2003.06.005, 16(9), 1325-1352.
Friston, K. (2005, April 29). A theory of cortical responses. Phil. Trans. R. Soc. B doi:10.1098/rstb.2005.1622, 360, 815-836.
Gödel, K. (1931). Uber formal unentscheidbare Satze der Principia Mathematica und verwandter Systeme I. Monatshefte fur
Mathematik und Physik, 38, 173-198.
Gershman, S., Horvitz, E., & Tenenbaum, J. (2015, July 16). Computational Rationality: A Converging Paradigm for
Intelligence in Brains, Minds, and Machines. Science , 349(6245), 273-278.
Gholipour, B. (2019, March 21). Philosophers and neuroscientists join forces to see whether science can solve the mystery of
free will. Retrieved from ScienceMag.org: https://www.sciencemag.org/news/2019/03/philosophers-andneuroscientists-join-forces-see-whether-science-can-solve-mystery-free
Goldreich, O. (2010). P, NP, and NP-Completeness. Cambridge: Cambridge University Press;
https://www.wisdom.weizmann.ac.il/~oded/bc-drafts.html. Retrieved from P versus NP problem:
https://en.wikipedia.org/wiki/P_versus_NP_problem
39
© 2022 Blum & Blum
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. Cambridge, MA: MIT Press.
Graziano, M. S., Guterstam, A., Bio, B., & Wilterson, A. (2020, May-June). Toward a standard model of consciousness:
Reconciling the attention schema, global workspace, higher-order thought, and illusionist theories. Cognitive
Neuropsychology, 37(3-4), 155-172. Retrieved from doi:10.1080/02643294.2019.1670630
Graziano, M. S., Guterstam, A., Bio, B., & Wilterson, A. (2020, May-June). Toward a standard model of consciousness:
Reconciling the attention schema, global workspace, higher-order thought, and illusionist theories. Cognitive
Neuropsychology, 37(3-4), 155-172. Retrieved from doi:10.1080/02643294.2019.1670630
Haggard, P. (2011, February 11). Decision Time for Free Will6. Neuron, 69(3), 404-406.
Hebb, D. O. (1949). The Organization of Behavior. New York: Wiley & Sons.
Herlin, B., Leu-Semenescu, S., Chaumereuil, C., & Arnulf, I. (2015, December). Evidence that non-dreamers do dream: a REM
sleep behaviour disorder model. J Sleep Res., 24(6), 602-609.
Hodges, A. (1992). Alan Turing: The enigma. Vintage.
Hohwy, J., & Seth, A. (2020). Predictive processing as a systematic basis for identifying the neural correlates of
consciousness (preprint). PsyArXiv Preprints(psyarxiv.com/nd82g).
Horikawa, T., Tamaki, M., Miyawaki, Y., & Kamitani, Y. (2013, May 3). Neural Decoding of Visual Imagery During Sleep.
Science, 340(6132), 639-642.
James, W. (1890). The Principles of Psychology (2 vols.). New York: Henry Holt (Reprinted Bristol: Thoemmes Press, 1999).
Jensen, M., Yao, R., Street, W., & Simons, D. (2011). Change blindness and inattentional blindness. WIREs Cogn Sci, 2, 529546.
Karp, R. M. (1972). Reducibility Among Combinatorial Problems. In R. E. Miller, J. W. Thatcher, (eds.), R. E. Miller, & J. W.
(eds.) (Eds.), Complexity of Computer Computations (pp. 85- 103). New York: Plenum.
Kaufman, S. B. (2020, May 26). On Consciousness: Science and Subjectivity: A Q&A with Bernard Baars. Retrieved from
https://blogs.scientificamerican.com/beautiful-minds/on-consciousness-science-and-subjectivity-a-q-a-withbernard-baars/
Kleiner, J. (2020). Brain states matter. A reply to the unfolding argument. Consciousness and Cognition, 85.
Koch, C. (2014, November). A Brain Structure Looking for a Function" in SA Mind 25, 6, 24-27 (November 2014)],. SA Mind,
25(6), pp. 24-27.
Koch, C. (2019). The Feeling of Life Itself: Why Consciousness Is Widespread but Can't Be Computed. Cambridge: MIT Press.
Kringelbach, M., & Berridge, K. C. (2017). The Affective Core of Emotion: Linking Pleasure, Subjective Well-Being, and
Optimal Metastability in the Brain. Emot Rev. doi:10.1177/1754073916684558, 9(3), 191-199.
Lavazza, A. (2019, February 26). Why Cognitive Sciences Do Not Prove That Free Will Is an Epiphenomenon. Front. Psychol.,
https://doi.org/10.3389/fpsyg.2019.00326.
Lee, T. S., & Mumford, D. (2003). Hierarchical Bayesian inference in the visual cortex. Journal of the Optical Society of
America, Optics, image science and vision, 20(7), 1434-1448.
Levin, L. A. (1973). Universal Sequential Search Problems. Probl. Peredachi Inf., 9(3), 115-116.
Levine, J. (1983). Materialism and Qualia: The Explanatory Gap. Pacific Philosophical Quarterly, 64, 354–361.
Liang, P. P. (2022, May 3). Brainish: Formalizing A Multimodal Language for Intelligence and Consciousness. Retrieved May
8, 2022, from arXiv: https://arxiv.org/abs/2205.00001
Libet, B. (1985). Unconscious cerebral initiative and the role of conscious will in voluntary action. Behavioral and Brain
Sciences, 8(4), 529-539.
Lieberman, M. D. (2013). Social: Why our brains are wired to connect. New York, NY: Crown.
Liljenström, H. (2021, May 28). Consciousness, decision making, and volition: freedom beyond chance and necessity. Theory
Biosci., https://doi.org/10.1007/s12064-021-00346-6.
Lucretius, & Ferguson Smith (translator), M. (1969). On the Nature of Things. Hackett Publishers.
Luo, H., & Schapire, R. E. (2015). Achieving all with no parameters: Adanormal-hedge. Conference on Learning Theory, (pp.
1286-1304).
Maoz, U., Yaffe, G., Koch, C., & Mudrik, L. (2019, October 23). Neural precursors of decisions that matter-an ERP study of
deliberate and arbitrary choice. eLife, 8(doi:10.7554/eLife.39787).
Mashour, G. A., Roelfsema, P., Changeux, J.-P., & Dehaene, S. C. (2020). Conscious Processing and the Global Neuronal
Workspace Hypothesis. Neuron, 195(5), 776-798.
McCulloch, W. S. (1953, October). The Past of a Delusion. The Chicago Literacy Club.
McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. A logical calculus of the
ideas immanent in nervous activity, 5, 115-133.
40
© 2022 Blum & Blum
Melloni, L., Mudrik, L., Pitts, M., & Koch, C. \. (2021, May 28). Making the hard problem of consciousness easier Lucia
Melloni1,2, Liad Mudrik3, Michael Pitts4, Christof Koch5,6 See all authors and affiliations Science 28 May 2021:
Vol. 372, Issue 6545, pp. 911-912 DOI: 10.1126/science.abj3259. Science 28 May 2021: Vol. 372, Issue 6545, pp.
911-912 DOI: 10.1126/science.abj3259, 372(6545), 911-912.
Merker, B. (2007). Consciousness without a cerebral cortex: a challenge for neuroscience and medicine. Behav. Brain Sci.
30, 63-81.
Metzinger, T. (2004). The subjectivity of subjective experience: A representationalist analysis of the first-person
perspective. Networks, 3-4, 33-64.
Miller, G. A. (1956). The Magical Number Seven, Plus or Minus Two: Some Limits on our Capacity for Processing
Information. Psychological Review, 63, 81-97.
Millière, R., Carhart-Harris, R. L., Roseman, L., Trautwein, F.-M., & Berkovich-Ohana, A. T.-C. (2018). Psychedelics,
Meditation, and Self-Consciousness. Frontiers in Psychology , 9.
Mumford, D. (1991). On the computational architecture of the neocortex. Biological Cybernetics, 65, 135-145.
Mumford, D. (2019). Thoughts on Consciousness. Retrieved from
http://www.dam.brown.edu/people/mumford/beyond/papers/2019--Thoughts%20on%20ConsciousnessB.pdf
Nagel, T. (1974). What Is It Like To Be a Bat? Philosophical Review, 83, 435–450.
Newell, A. (1990). Unified Theories of Cognition. Cambridge: Harvard University Press.
Rathi, N. (2021). Explaining the Process of Meditation via the Blum Model of Conscious Turing Machine. Indian Institute fo
Science, Computer Sciemce and Automation, Bangalore.
Reardon, S. (2019, October 16). Outlandish’ competition seeks the brain’s source of consciousness. Retrieved from
sciencemag.org: doi:10.1126/science.aaz8800
Reddy, D. R. (1976, April). Speech Rcogniton by Machine: A Review. Proceedings of the IEEE, 501-531. Retrieved from
http://www.rr.cs.cmu.edu/sr.pdf
Rensink, R. A., O’Regan, J. K., & Clark, J. J. (1997). To See or not to See: The Need for Attention to Perceive Changes in
Scenes. Psychological Science, 8(5), 368-373.
Rosen, C., McCarthy-Jones, S., Chase, K. A., Humpston, C., Melbourne, J. K., Kling, L., & Sharma, R. P. (2018, June). The
tangled roots of inner speech, voices and delusions. Psychiatry Res., 281-289.
Scarpelli, S., Bartolacci, C., D'Atri, A., Gorgoni, M., & De Gennaro, L. (2019, March). he Functional Role of Dreaming in
Emotional Processes. . Frontiers in psychology, 10.
Schurger, A., Sitt, J. D., & Dehaene, S. (2012, October 16). An accumulator model for spontaneous neural activity prior to
self-initiated movement. PNAS, 109(42), E2904-E2913.
Seth, A. K. (2015). The Cybernetic Bayesian Brain - From Interoceptive Inference to Sensorimotor Contingencies. In T. T.
Metzinger, & J. M. Windt, Open MIND. Frankfurt am Main: MIND Group. doi: 10.15502/9783958570108 23 | 24.
Simon, H. A. (1969). The Sciences of the Artificial. Cambridge, MA, USA: MIT Press.
Sipser, M. (2013). Introduction to the Theory of Computation, 3rd edition. Boston: Cengage Learning.
Slobodchikoff, C. N. (2012). Chasing Doctor Dolittle: Learning the Language of Animals. New York: St. Martin's Press.
Smith, K. (2008). Brain makes decisions before you even know it. . Nature, https://doi.org/10.1038/news.2008.751.
Striemer, C. L., Chapman, C. S., & Goodale, M. A. (2009, September 15). ’Real-time’ Obstacle Avoidance in the Absence of
Primary Visual Cortex. Proc Natl Acad Sci U S A.
Test Your Awareness : Whodunnit? (2008, November 3). Retrieved from YouTube:
https://www.youtube.com/watch?v=ubNF9QNEQLA&list=PLr4EeJcghrfSnnBO8YFu0qnz4IrpQEUaZ&index=1
Tononi, G. (2004). An information integration theory of consciousness. BMC Neuroscience 5, 42-72.
Tononi, G., & Koch, C. (2015). Consciousness: here, there and everywhere? Philosophical Transactions of the Royal Society
of London B: Biological Sciences, 370 (1668).
Turing, A. M. (1937). On Computable Numbers, with an Application to the Entscheidungsproblem. Proceedings of the
London Mathematical Society, 2, 230-265.
Turing, A. M. (1945). Proposal for development in the Mathematics Division of an Automatic Computing Engine (ACE). .
Report E.882, Executive Committee, NPL, Mathematics.
Valiant, L. (2013). Probably Approximately Correct. New York: Basic Books Perseus Group.
VanRullen, R., & Kanai, R. (2021, May 14). Deep learning and the Global Workspace Theory. Trends in Neurosciences.
Villecroze, J.-L. (2019, June 16). An Introduction to Conscious Turing Machines with fizz. Retrieved from
https://f1zz.org/downloads/ctm.pdf.
Villecroze, J.-L. (n.d.). Personal Communication.
41
© 2022 Blum & Blum
von Neumann, J. (1951). Various Techniques Used in Connection with Random Digits. Monte Carlo Method. 12, pp. 48-50.
Washington, DC: United States Government Printing Office.
Vyazovskiy, V., & Delogu, A. (2014, June). NREM and REM Sleep: Complementary Roles in Recovery after Wakefulness.
Neuroscientist, 20(3), 203-219.
Wikipedia. (2022). History of artificial neural networks. Retrieved March 2022, from
https://en.wikipedia.org/wiki/History_of_artificial_neural_networks
Yao, A. C.-C. (1982). Theory and applications of trapdoor functions. Proceedings of the 23rd IEEE Symposium on Foundations
of Computer Science.
Yao, A. C.-C. (2003, January). Classical physics and the Church--Turing Thesis . Journal of the ACM, 50(1), 100-105.
Zadra, A., & Stickgold, R. (2021). When Brains Dream Exploring the Science and Mystery of Sleep. New York: W. W. Norton.
42
© 2022 Blum & Blum |
392
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 392-396
Kowall, J., The Physicist's Dilemma: Ultimate Reality – The Non-Physical Nature of Consciousness
Article
The Physicist's Dilemma: Ultimate Reality –
The Non-Physical Nature of Consciousness
James Kowall*
Abstract
A physical argument is made for the non-physical nature of consciousness. It is argued the
source of consciousness is the ultimate nature of reality. This source cannot be found in the
physical world, but in what remains when everything in the physical world disappears.
Traditionally, this ultimate reality is called the void.
Key Words: ultimate reality, consciousness, the void.
In her groundbreaking, paradigm shattering book, Amanda Gefter 1 has given a purely physical
scientific argument to demonstrate that "Nothing is ultimately real".
Gefter argues 1 that ultimate reality is invariant. Ultimate reality is the same for all observers.
Ultimate reality cannot change with a change in an observer's point of view or a change in an
observer's frame of reference. In the spirit of relativity theory, we understand an observer as the
consciousness present at the central point of view, or the origin, of a coordinate system that
characterizes a frame of reference.
The nature of the four fundamental forces (gravity, electromagnetism, and the strong and weak
nuclear forces) have something important to tell us about the nature of ultimate reality. The
fundamental forces are all gauge forces or fictitious forces 1 as they can vanish with an
appropriate kind of coordinate transformation. In relativity theory, we call a coordinate
transformation in which a force vanishes a freely falling frame of reference. If an observer enters
into an ultimate freely falling frame of reference, then all four fundamental forces vanish. This is
easily seen with the Kaluza-Klein mechanism 2, which gives a natural geometrical explanation
for how the four fundamental gauge forces are unified.
The Kaluza-Klein mechanism extends the usual 3+1 extended dimensions of space-time with
extra compactified dimensions. For electromagnetism an extra fifth dimension is needed.
Coordinates are written as xμ, where μ=0, 1, 2, 3, 5, and the fifth dimension is curled up into a
circle of radius r at each point of the usual 3+1 dimensions. Positions on the circle are located
with an angle θ and are written as x5=rθ. A five dimensional metric gμν then defines the
electromagnetic potential as gμ5=−rAμ. If this metric is plugged into Einstein's equations, the
result is Maxwell's equations for the electromagnetic potential. A gauge transformation
corresponds to a rotation in the fifth dimension by an angle θ as Aμ→Aμ−∂θ/∂xμ, where the phase
angle θ(x) depends on the 3+1 extended dimensions.
*
Correspondence: James Kowall, MD, PhD, Independent Researcher. letranger0101@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
393
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 392-396
Kowall, J., The Physicist's Dilemma: Ultimate Reality – The Non-Physical Nature of Consciousness
Quantization of electric charge follows from the requirement of periodicity of the wave function
in a compactified space. Only an integral number of wavelengths can fit into the circumference
of the circle, and so the wavelength is constrained as nλ=2πr, where n=…−2, −1, 0, +1, +2, … is
a positive or negative integer that specifies the amount of electric charge found at each point in
space-time. In the Kaluza-Klein scenario, electric charge is only fifth dimensional momentum.
Since momentum in quantum theory is quantized in terms of the wavelength, p=h/λ, a negative
sign only indicates momentum directed in the negative x5 direction.
In relativity theory, there is only one invariant measure of geometrical length, called the proper
time. The proper time, τ=∫ds, is the geometrical length of a worldline followed by an observer
through the space-time geometry, which is given in terms of the metric as ds2=gμνdxμdxν.
The Kaluza-Klein mechanism is the natural way to understand electromagnetism as an extension
of relativity theory. The electromagnetic potential is just another aspect of the curvature of
space-time geometry, no more mysterious than the nature of gravity. Gravity corresponds to
accelerated frames of reference in the 3+1 extended dimensions of space-time, while
electromagnetism corresponds to accelerated frames of reference in the extra compactified fifth
dimension. Gravity disappears in a freely falling frame of reference in the 3+1 extended
dimensions, and electromagnetism disappears in a freely falling frame of reference in the extra
compactified fifth dimension. This is easily extended to include the strong and weak nuclear
forces if there are six extra compactified dimensions 2.
There is another fundamental force besides the four fundamental gauge forces, called the force of
dark energy. The force of dark energy is a kind of anti-gravity, which in relativity theory is
understood in terms of a cosmological constant Λ. The solution to Einstein's equations with a
positive cosmological constant gives the metric for an exponentially expanding space, called de
Sitter space. In terms of the usual extended 3+1 dimensions of space-time, written as (x, y, z, t),
this metric takes the form ds2=dt2−℮at(dx2+dy2+dz2), where a=√Λ.
In an exponentially expanding space, every observer is surrounded by a cosmic horizon. At the
cosmic horizon, things appear to move away from the observer at the speed of light. Since
nothing can travel faster than the speed of light, the cosmic horizon is as far out in space as the
observer at the central point of view can see things in space. The cosmic horizon is a bounding
surface of space that limits the observer's observations in space due to the limitation of the speed
of light. An observer in an exponentially expanding space is in a frame of reference in which
space itself accelerates away from the central point of view of the observer.
The nature of a cosmic horizon as a bounding surface of space surrounding an observer at the
central point of view has profound implications due to the nature of Hawking radiation, horizon
complementarity, and the holographic principle 1. The inevitable conclusion of these recently
discovered paradigm shattering developments is the one-world-per-observer paradigm. This
paradigm tells us that everything observable in the world is inherently observer-dependent.
Gefter argues 1 that quantum theory can only be understood in a way that makes any real sense in
terms of the one-world-per-observer paradigm. It is simply not true that multiple observers share
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
394
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 392-396
Kowall, J., The Physicist's Dilemma: Ultimate Reality – The Non-Physical Nature of Consciousness
a single world described by a single Hilbert space of observable values 1. Each observer has its
own world defined on its own holographic screen.
Each observer's holographic screen is a bounding surface of space that surrounds the observer at
the central point of view and encodes fundamental quantized bits of information for that world in
a pixelated way, with one bit of information encoded per pixel on the screen 3, and so each
observer has its own Hilbert space that describes all possible observations in its own world.
An odd aspect of relativity theory is the total energy of the world can add up to zero, since the
negative potential energy of gravitational attraction can exactly cancel out all positive forms of
energy, like dark energy, mass energy and kinetic energy. Each observer's world can have a total
energy of zero. Since everything in that world is composed of energy, and all of that energy can
add up to zero, everything can ultimately be nothing. Observations indicate the total energy of
the universe is exactly zero 1, and so everything in the world ultimately adds up to nothing.
Observations indicate all conserved values of the universe, like energy, are exactly zero.
The idea of quantum theory is a natural extension of relativity theory 2. The natural definition of
action is in terms of the geometrical length of a worldline, which is only a path through the
space-time geometry followed by an observer. Relativity theory only allows for the path of least
action. In quantum theory, all possible paths are allowed. Each possible path is weighted with a
probability factor we call the wave function ψ=℮iθ, where the phase angle θ=S/ћ is given in terms
of the action S, which in turn is proportional to the proper time τ. Each possible worldline
through the geometry is weighted with this probability factor. The path of least action is like the
shortest distance between two points in a curved space-time geometry, but quantum theory
allows for all possible paths.
The natural consequence of this quantization procedure is a Hilbert space that describes all
possible observable values of all observable things observed in the observer's world as the
observer follows some possible worldline through the geometry. The holographic principle and
the one-world-per-observer paradigm tell us each observer has its own Hilbert space of
observable values defined on its own holographic screen. A consensual reality shared by many
observers is possible if their holographic screens overlap 3 in the sense of a Venn diagram.
An observer's holographic screen is only a bounding surface of space that arises because the
observer is in an accelerated frame of reference. The holographic screen constructs a Hilbert
space of observable values for everything observed in the observer's world. This is possible in a
non-commutative geometry when position coordinates on the bounding surface are represented
by non-commuting variables 3. The eigenvalues of an SU(n) matrix then define n bits of
information on the screen. The natural pixel size is a Planck area ℓ2=ћG/c3, and the number of
bits encoded is given by n=A/4ℓ2, where A is the area of the bounding surface.
The holographic principle 4 tells us all information for the observer's world is encoded on a
bounding surface of space, which we understand as an event horizon that acts as a holographic
screen. The horizon only arises because the observer is in an accelerated frame of reference.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
395
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 392-396
Kowall, J., The Physicist's Dilemma: Ultimate Reality – The Non-Physical Nature of Consciousness
In an ultimate freely falling frame of reference, all the fundamental gauge forces disappear, the
force of dark energy disappears, there is no bounding surface of space, no event horizon, and no
holographic screen. In an ultimate freely falling frame of reference, all the bits of information for
all the observable things in the observer's world disappear, and so the observer's world
disappears. When everything in the observer's world disappears, only the observer's underlying
reality remains. Since there is nothing in that ultimate reality, we call it the void.
Ultimate reality is the same for all observers. Ultimate reality does not depend on an observer's
frame of reference. Ultimate reality is observer independent. If everything in the observer's world
is observer-dependent and can disappear in an ultimate freely falling frame of reference, then
what is ultimately real? What is the observer's underlying reality? The only possible answer is
the source of the observer's consciousness. We call the primordial, undifferentiated source of the
observer's consciousness the void. Ultimate reality is the nothingness of the void.
The Gödel incompleteness theorems prove this is the inevitable conclusion for any world
described by a consistent set of computational rules, as is the case in quantum theory. The second
incompleteness theorem proves that any consistent set of computational rules as complicated as
arithmetic can never prove its own consistency. The proof of consistency is always found outside
the rules. This proves the nature of the consciousness that knows about the consistency of the
rules cannot itself emerge from the rules, but must be found 'outside' the rules 5.
This is the Physicist's dilemma. The source of the observer's consciousness is not something that
can be found in the physical reality of the observer's world, but only in the underlying reality that
remains when everything in that physical reality disappears. That ultimate, underlying reality is
the source of the observer's consciousness, but it can only be described as the void.
Throughout her book, Gefter 1 asks “If observers create reality, where do the observers come
from?” The answer is they come from the nothingness itself.
Everything is ultimately nothing. The nature of that nothingness in its primordial,
undifferentiated, unbounded state is pure consciousness, and so everything is ultimately
consciousness. Consciousness in its differentiated, bounded state is the observer present at the
center of its own world. All the information for the observer's world is encoded on a bounding
surface of space that surrounds the observer at the central point of view, but that boundary only
arises when the observer enters into an accelerated frame of reference. It is only this boundary
arising in the midst of nothingness that creates the observer's world.
Gefter 1 tells us that "Nothing is ultimately real", which is exactly the same as to say "Ultimately,
only consciousness is real". There is no contradiction, since the true nature of consciousness in
its undifferentiated, unbounded state is the very nothingness that she acknowledges to be
ultimate reality. Even the observer present at the center of its own world is not ultimately real,
since the observer is consciousness in its differentiated, bounded state.
The mystery of the observable world is nothing appears to become something 1 when a boundary
arises in infinite, undifferentiated empty space. A bounding surface of space holographically
constructs a Hilbert space for the observer's world, arising when the observer is in an accelerated
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
396
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 392-396
Kowall, J., The Physicist's Dilemma: Ultimate Reality – The Non-Physical Nature of Consciousness
frame of reference and surrounding the observer at the central point of view. In an ultimate freely
falling frame of reference, the boundary disappears, and so too does everything in the observer's
world. The nothingness that remains can be called an Absence, but in reality what remains is a
Presence, since it is the source of the observer's consciousness.
This distinction is a matter of perspective. What is seen as an Absence when one looks outwardly
at the world is seen to be a Presence when one looks within. This explanation resonates deeply
with the wisdom of non-dual metaphysics.
References
1. Amanda Gefter (2014) Trespassing on Einstein's Lawn: A Father, a Daughter, the Meaning of
Nothing, and the Beginning of Everything (Random House)
2. A. Zee (2003) Quantum Field Theory in a Nutshell (Princeton University Press)
3. Tom Banks (2013) Lectures on Holographic Space-time arXiv:1311.0755
4. Leonard Susskind (2008) The Black Hole War (Little, Brown and Company)
5. Roger Penrose (1997) The Large, the Small and the Human Mind (Cambridge University Press)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
MANIPULATING CONSCIOUSNESS
arXiv:nlin/0403054v1 [nlin.PS] 29 Mar 2004
E. A. Novikov
Institute for Nonlinear Science, University of California - San Diego, La
Jolla, CA 92093 - 0402
Manipulation of the effects of consciousness by external influence on the
human brain is considered in the context of the nonlinear dynamical modeling
of interaction between automatic and conscious processes.
In previous papers [1,2] an approach to nonlinear dynamical modeling of
interaction between automatic (A) and conscious (C) processes in the brain was
presented. The idea is to use quaternion field with real and imaginary components representing A - and C - processes. The subjective C - experiences were
divided into three major groups: sensations (S), emotions (E) and reflections
(R). Note, that subjective S should be distinguished from the automatic sensory input into the neuron system of the brain. The A - C interaction is due to
the nonlinearity of the system. This approach was illustrated on the nonlinear
equation for the current density in the cortex. The nonlinearity is determined
by the sigmoidal firing rate of neurons. Perspective for testing of this approach
were also indicated as well as some more general approaches [1,2].
For the purpose of medical and other possible applications it is interesting
to include an external electromagnetic (EM) influence in this modeling. In a
laboratory setting a specially equipped helmet can produce designed nonhomogeneous or homogeneous excitations in the brain. On another hand, suppose
we want to pacify a group of terrorists (!) by using a strong EM radiation
with the wavelength much larger than the size of their brains. In this case the
excitation will be approximately homogeneous. We start with the homogeneous
case which is more simple mathematically and gives some insight into general
situation.
The model equation for the average (spatially uniform) current density α(t)
perpendicular to the cortical surface has the form [1,2]:
∂α
+ kα = Re{f (α + σ + ip ψ p )} + ϕ
((1))
∂t
Here k is the relaxation coefficient, σ(t) is the average sensory input, f represents
the sigmoidal firing rate of neurons [for example, f (α) = tanh(α)], components
ψ p represent the indicated above (S, E, R) - effects and summation is assumed
on repeated subscripts from 1 to 3. The quaternion imaginary units ip satisfy
conditions:
ip iq = εpqr ir − δ pq
1
((2))
where εpqr is the unit antisymmetric tensor and δ pq is the unit tensor. Formula
(2) is a compact form of conditions: i21 = i22 = i23 = −1, i1 i2 = −i2 i1 = i3 ,
i2 i3 = −i3 i2 = i1 , i3 i1 = −i1 i3 = i2 . Equation (1) is obtained by using the
quaternion q = α + ip ψ p instead of α in order to describe the A - C interaction.
The additional term ϕ in (1) represents the external EM excitation. Equation
(1) is the real part of the equation for the quaternion [1,2]:
∂q
+ kq = f (q + σ) + φ
∂t
For ψ p from (1a) we have equations:
((1a))
∂ψ p
+ kψ p = Imp {f (α + σ + iq ψ q )}, p = 1, 2, 3
((3))
∂t
where Imp {f } = − Re{f ip }. Note, that so-called extra-sensory effects (if they
exist) can be included in this approach by assuming that σ is a quaternion:
σ =⇒ σ + ip sp , this will produce shift ψ p =⇒ ψ p + sp in the nonlinear terms in
(1), (3) and below in (5), (6).
Let us consider typical f (α) = tanh(α). Simple algebra gives [2]:
tanh(q) =
sinh(2α) + j sin(2ψ)
, ψ 2 ≡ ψ 2p , j ≡ ip ψ p ψ −1 , j 2 = −1
cosh(2α) + cos(2ψ)
((4))
Using (4) with shift α =⇒ α + σ, we rewrite (1) and (3) explicitly:
∂α
sinh[2(α + σ)]
+ kα =
+φ
∂t
cosh[2(α + σ)] + cos(2ψ)
((5))
ψ p ψ −1 sin(2ψ)
∂ψ p
+ kψ p =
, p = 1, 2, 3
∂t
cosh[2(α + σ)] + cos(2ψ)
((6))
Some general conclusions can be made without solving these equations.
Firstly, if ψ p (0) = 0 than ψ p (t) ≡ 0 (unless sp 6= 0). Secondly, if ψ p (0) 6= 0,
than evolution ψ p (t) can be manipulated by using sensory input σ(t) and EM
excitation φ(t). Thirdly, the nonlinearity of the system suggests that the efficiency of such manipulation depends not only on the amplitudes of σ(t) and
φ(t) but also on the shape of these functions (spectral content).
For the case of spatially nonuniform α(t, x), ψ p (t, x), σ(t, x) and φ(t, x) we
can use more general equations, which include typical propagation velocity of
signals in the neuron system of the cortex v. Time differentiation of (1a), simple
algebra and addition a term with the two-dimensional spatial Laplacian ∆ gives
[1,2]:
∂2q
∂q
∂
∂φ
+ (k + m)
+ (km − v 2 ∆)q = (m + )f (q + σ) +
2
∂t
∂t
∂t
∂t
((7))
where m is an arbitrary parameter (see below). Real and imaginary projections
of (7) give equations for α and ψ p , which are generalizations of (1) and (3). If we
2
put ψ p = 0 and φ = 0, than equation for α will be similar in spirit to equations
used for interpretation of EEG and MEG spatial patterns ( see recent paper
[3] and references therein). In this context we have parameters: k ∼ m ∼ v/l,
where l is the connectivity scale. For f (α) = tanh(α) the nonlinear term f (q+σ)
in (7) has the same projections as in (5) and (6).
The obtained in this letter equations can be used for numerical experiments
and for comparison with corresponding laboratory experiments.
References
[1] E. A. Novikov, Towards modeling of consciousness, arXiv:nlin.PS/0309043
(2003)
[2] E. A. Novikov, Quaternion dynamics of the brain, arXiv:nlin.PS/0311047
(2003)
[3] V. K. Jirsa, K. J. Jantzen, A. Fuchs, and J. A. Kelso, Spatiotemporal
forward solution
of the EEG and MEG using network modeling, IEEE Trans. Med. Imaging,
21(5), 497 (2002)
3 |
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
378
Article
Sentience Everywhere: Complexity Theory, Panpsychism
& the Role of Sentience in Self-Organization of the Universe
Neil D. Theise*1 & Menas C. Kafatos2
1
Departments of Pathology & of Medicine, Beth Israel Medical Center, Albert Einstein
College of Medicine, New York, NY 10003, USA
2
Center of Excellence in Applied, Computational & Fundamental Science, Chapman
University, California 92866, USA
ABSTRACT
Philosophical understandings of consciousness divide into emergentist positions (when the
universe is sufficiently organized and complex it gives rise to consciousness) vs. panpsychism
(consciousness pervades the universe). A leading emergentist position derives from autopoietic
theory of Maturana and Varela: to be alive is to have cognition, one component of which is
sentience. Here, reflecting autopoietic theory, we define sentience as: sensing of the surrounding
environment, complex processing of information that has been sensed, (i.e. processing
mechanisms defined by characteristics of a complex system), and generation of a response.
Further, complexity theory, points to all aspects of the universe comprising “systems of
systems.” Bringing these themes together, we find that sentience is not limited to the living, but
present throughout existence. Thus, a complexity approach shifts autopoietic theory from an
emergentist to a panpsychist position and shows that sentience must be inherent in all structures
of existence across all levels of scale.
Key Words: sentience, complexity theory, panpsychism, self-organization, Universe, autopoiesis.
Introduction
Two philosophical approaches to understanding the nature of consciousness in the universe
predominate: panpsychism in which consciousness is conceived as pervading the universe at all
levels, and emergentism in which consciousness is understood to arise from the universe when
the universe becomes sufficiently complex (and organized in such a way) to produce it (Seager
& Allen-Hermanson, 2010). Of course, each of these categories subdivides into still more
nuanced versions and perspectives. Where emergentism is concerned, particularly, there is the
obvious stance that it is the nervous system, or perhaps the brain in particular, that represents the
complexity and organization necessary to create consciousness; however, other perspectives
suggest that it is not the brain per se, or even nervous systems in general that are required, but
that life in its most basic form, i.e. the cell, is sufficient and necessary for rudimentary forms of
*Correspondence: Neil D. Theise, MD, Beth Israel Medical Center, First Avenue at 16th Street, New York NY 10003, USA Tel:
212-420-4246, Fax: 212-420-4373 Email: ntheise@chpnet.org
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
379
consciousness.
This latter view was principally proposed by Francisco Varela and Humberto Maturana in their
formulation of the concepts of autopoiesis (Maturan & Varela, 1973; Varela, & Rosch, 1991),
then further developed through collaborations of Varela and other colleagues, in particular Evan
Thompson (Varela, Thompson & Rosch, 1991; Thompson, 2004; Thompson, 2007). In their
famous view, where there is life, there is mind, mind being expressed through the embodied
activities of an autonomously active, autopoietic unit, whether that unit is as simple as a cell or
as complex as creatures with central nervous systems such as humans and other primates,
elephants, dolphins, whales, etc.
This emergentist perspective immediately calls to mind the terminology of complexity theory, in
which emergence specifically refers to properties and structures that arise, bottom-up, from the
self-organization of interacting members of a complex system (rather than through top-down
planning and design) (O'Connor & Wong, 2012; Lewin, 1999; Johnson, 2001). Indeed, the two
uses of the term are sometimes similar. Thus, some emergentist positions take complexity theory
itself into account, suggesting that consciousness is a macro-scale emergent phenomenon arising
from the interacting neuronal networks of the (central) nervous system at a lower level of scale
(O'Connor & Wong, 2012).
However, in general, when applied to the philosophical question of consciousness the word
emergence is used with less precision than when it is used as a technical term in complexity
studies. One should therefore be cautioned in concluding that a complexity theory perspective
on consciousness necessarily supports the emergentist point of view. It is our position that, in
fact, a careful application of complexity principles to analysis of self-organization across all
levels of scale – down to the smallest, Planck scale of existence (approximately 10-35 meters) –
suggests that at least some simple elements of consciousness are found wherever there is
existence.
These elements we will specify as “sentience” and, for the purposes of our discussion, below,
sentience is here preliminarily defined as: 1. sensing of the surrounding environment, 2. complex
processing of the information derived from what is sensed, (i.e. via mechanisms of processing
that fulfill the criteria of a complex inclusive of limited randomness or quenched disorder)
(Theise, 2004; Theise & D’Inverno, 2004; Theise, 2006), and 3. generation of a response. These
activities and the elements or structures that mediate them will be further defined, below, as the
discussion proceeds. Our analysis will then proceed to consider how complexity theory actually
points away from an emergentist perspective toward a panpsychist position: “sentience
everywhere.” We note that sentience does not imply self-consciousness, which may be confined
to higher species. Self-consciousness implies sentience but not necessarily the other way around.
Brains Only?
That the brain produces consciousness appears, simplistically, as an elegant solution to the
problem of the origin of consciousness. Given its enormous complexity and the apparent
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
380
association of brain topography and activation with discrete mind states and functions, this is
virtually self-evident to most of our scientific and popular culture. However, the simplicity of
that solution starts to dissolve when one considers the brain from an evolutionary point of view.
It is not as though brains suddenly popped into existence prepared to produce mind, after all.
Evolutionary biologists approach the question meaningfully by looking for simpler structures
from which brains evolved, recognizing that in lower order living beings there are neuronal
structures that, while not as complex as our brains, perform less complex but similar versions of
the functions of consciousness (Miller, 2009). Some of these are central nervous systems, but
some of them are disseminated through the body rather than being concentrated in a “central”
location. For example, the worm-like Sacoglossus kowalevskii (Pani, 2012) has aggregated
functional clusters of cells as in the vertebrate nervous system, but well defined anatomic
structures as in vertebrates is absent. In the sea anemone Nematostella vectensis, the entire
endoderm and ectoderm has neurogenic potential, but the nervous system per se they have a
more diffuse, “nerve net” comprised of cells identifiable as neurons or, at least, having similar
functioning as nerves (Nakanishi, 2012). Thus, a gradual development toward central nervous
systems - perhaps over parallel, but independent evolutionary paths – derives from pre-existing,
more dispersed nervous system elements (Miller, 2009).
These evolutionary paths can be traced backwards not only into less densely aggregated and less
complexly organized nervous systems, but the components of neurons themselves predate the
evolution of neurons and thus functional aspects of nervous system-like activity predate the rise
of neurons. As in all evolutionary development, the pieces often precede the structures that
eventually arise with new functions, not by creating new structures, but by reorganizing existent
structures in novel fashion. Thus, the specialized cellular structures that we commonly deem
essential to neuronal signaling, the ionic channels that conduct electrical signals along the neuron
and the synaptic structures that convey signals between cells, are found as independent entities in
simpler life forms (Miller, 2009; Meech, 2008). In particular, the ionic channels in cell
membranes (e.g. calcium, sodium, potassium channels) are found in virtually all cells. Thus,
some of the simplest elements of nervous systems that support or even create the complex
elements of consciousness are present throughout the evolutionary tree, no matter how simple the
organisms are, down to the single cell level. Could these simpler structures, not yet evolved into
complex nervous systems, give rise to simpler forms of consciousness? It is precisely this
question, when broached by Maturana and Varela, that yielded the equation “mind = life”.
Autopoiesis and sentience
Autopoiesis, as initially presented by Maturana and Varela (Maturana & Varela, 1973; Varela,
Thompson & Rosch, 1991; Thompson, 2004; Thompson, 2007), can be considered a variant of a
complexity theory, self-organizational approach (though Maturana, himself, disagreed with this
alignment [Maturana, 1987]). The word derives from the greek: αuτo- meaning “self” and –
ποίησις meaning “creation”, thus (Maturana & Varela, 1973):
An autopoietic machine is a machine organized (defined as a unity) as a network of
processes of production (transformation and destruction) of components which: (i)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
381
through their interactions and transformations continuously regenerate and realize the
network of processes (relations) that produced them; and (ii) constitute it (the machine)
as a concrete unity in space in which they (the components) exist by specifying the
topological domain of its realization as such a network.
Initially presented as a way to define living systems, it specified the criteria that pointed to cells
as the smallest possible unit of life. But it also accomplished more than this. The autopoietic
approach specifies four characteristics of autopoietic systems, inclusive of all single cell
organisms, that serve to define the essential, minimum form of mind, namely sentience that leads
to “sense making” (Maturana & Varela, 1973; Varela, Thompson & Rosch, 1991; Thompson,
2004; Thompson, 2007). So, for example (one at which we will look at more closely), a
paramecium swims along increasing gradients of nutrients like sugar, but will reverse direction
in response to toxic gradients or obstructions to movement. Thus, the organism senses the
environment and responds to it by changing behavior. In doing so, it also assigns “value” to
aspects of the environment, thus “making sense” of it: nutrients are “good”, toxins and
obstructions are “bad.”
One may immediately object that by such a definition an environment sensing air conditioner is
sentient and sense making: it will turn off when a room is “too cold” and turn on when the room
is “too warm”, seeking to regulate to regulate room temperature to accommodate Goldilocks’
“just right.” The sense making aspect for an air conditioner, however, does not arise from the
unit itself, but is defined from outside the system by the person who decides the set points. Thus
it seems that biological autonomy (Grandpierre and Kafatos, 2012) is of fundamental importance
here. The apparent sentience of the air conditioner is thus not the same as that of the autopoietic
unit. The air conditioner simply has an on/off switch that responds to temperature sensors. The
unit’s behavior is therefore simple, mechanical, and completely predictable in every detail; it
never varies. It does not have an internal processing of information performed in a complex
manner.
The living system, on the other hand, senses and processes the perceived information about the
environment in a complex, non-mechanical, not completely predictable way; as with all complex
systems, there needs to be an element of low level randomness or “quenched disorder” in the
system which allows for variant responses and, therefore, the potential for adaptation if the
surrounding environment changes. For the mechanical, non-autopoietic machine, it is, in part,
the inflexibility of response that leaves an air conditioner without the capacity to autonomously
adapt. The air conditioner, unlike a living, autopoietic unit, cannot evolve.
Let us look at the paramecium more closely. They swim, in a corkscrew movement by beating
the tiny, hair-like cilia that cover their surfaces in unison, like oarsmen moving a boat forward.
When a paramecium encounters a physical obstacle, it backs up, changes direction, and tries to
move forward again. As a single cell, it can’t have a nervous system, let alone a brain. How does
it “know” it has hit an obstacle let alone determine how to respond “appropriately” by backing
up and changing direction?
When the cell membrane encounters the obstruction, the membrane deforms, leading to a
conformational change in small molecular channels in the flattened part of the membrane that, in
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
382
turn, causes membrane depolarization that elicits an action potential leading in turn to ciliary
reversal and increased beat frequency (Tamm, 1994; Pech, 1995). So the paramecium backs up.
Then, the system resets and the paramecium resumes swimming forward again. This is the kind
of sentience, of “mind”, that autopoietic theory points to in the most minimal life unit, the cell.
In analyzing such behaviors Maturana and Varela described these four features of all autopoietic,
living system (Maturana & Varela, 1973):
a. A boundary (the cell membrane in this example) that is open to energy, but closed to
foreign materials, i.e. is semi-porous. This is boundary defines the “being” of the
system;
b. The processes of sensing and reacting are the “doing” of the system;
c. A nervous system that connects external events and the internal processes of the
living system in which information sensed is then processed, yielding a response;
d. Communication channels between the living system and its external environment (in
this case, ion channels).
This description fits nicely with the evolutionary view of nervous system development and
serves as a platform to understand the evolutionary development of mind that precisely parallels
the evolutionary development of all living systems. It also sets a lower limit on where one may
find consciousness or, in this more limited, simple framework at the single cell level, of
sentience. The cell is the smallest unit that satisfies the criteria for an autopoietic system. No
simpler system exists and, thus, one may say that autopoiesis/life is where one finds mind and
where one does not find life, one would not find mind understood in these terms.
Complexity in autopoiesis
Complexity theory can provide some important supplemental perspectives to this autopoietic
analysis. First, there is the simple question of how atoms and molecules can self assemble into
autopoietic units. This has been described elsewhere in greater detail and relates to the general
features of complex systems (Lewin, 1999; Johnson, 2001; Theise, 2004; Theise & D’Inverno,
2004; Theise, 2006). To highlight: independent of scale, the self-organization of interacting
elements into larger scale, emergent structures is potentiated by when they display four sets of
characteristics:
a.
There must be sufficiently large numbers of interacting agents. How great the
complexity of self-organization relates to how large the numbers are (there are clearly
sufficiently enormous numbers of interacting atoms and molecules that comprise a
living cell).
b.
There is an overall balance of homeostatic, negative feedback loops governing
the interactions between agents (within cells biomolecules generally interact through
homeostatic feedbacks). Positive feedback loops may be present, but cannot
predominate
c.
There is no global sensing of the condition of the system. For example, no
molecule is “aware of itself” as part of the larger process, but instead is simply
responding to Brownian motion resulting from the thermal jostling of the aqueous
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
383
substrate in which it floats and to various physiochemical interactions with other
atoms/molecules of the cell. Likewise, no cell is observing the tissue or organism as
a whole, they merely respond to cues from the local environment.
d.
There must be limited randomness (often referred to as “quenched disorder”) in
the system. Too little disorder would prevent exploration of new states of selforganization to adapt to a changing environment. Too much disorder would prevent
self-organization. In the cell, Brownian motion provides the energy of physiology
and movement between biomolecules comprising molecular motors; energy conveyed
by dissociation of molecules such as ATP serves to quench this disorder into
functional molecular activities (Yanagida, Iwaki & Ishii, 2008; Ishii Y, 2008; von
Delius & Leigh, 2011).
With this framework we can see that the internal processing of information that results in a
response to a sensed environment necessarily incorporates quenched disorder, thus opening the
door, for example, to autopoietic “doing” that allows for adaptation and evolution, as noted
above. This further specifies the difference between internal information processing of a
programmable machine and a truly living system. In this way, a complexity approach is
supportive and even clarifying of some aspects of the autopoietic analysis.
On the other hand, however, complexity theory also undermines the nature of the autopoietic unit
as something particularly distinct from the lower level structures beneath it. It does so in that
another key aspect of complex systems is that their features are scalable, meaning that the
general principles apply throughout different levels of scale. Thus, while we may consider atoms
and molecules as self-assembling (when in aqueous solution at appropriate temperatures) into
cells, cells, in turn, fulfill the same criteria and can thereby self-organize into communities of
cells (i.e. “bodies” as diverse as bacterial colonies, occasionally more actively coordinated
structures like slime molds, and true multicellular organisms). Moving upwards in scales, these
bodies (however selected for observation or study) can interact forming structures as diverse as
ant colonies, flocks of birds, cities, cultures, economic markets, ecosystems (Lewin, 1999;
Johnson, 2001; Theise, 2004; Theise & D’Inverno, 2004; Theise, 2006).
Likewise, moving downward in scale, while cells arise from self-organizing molecules (Theise,
2005), molecules in turn arise from self-organizing atoms (with quenched disorder now being
supplied by quantum mechanical processes), atoms themselves arise from self-organizing
subatomic particles, and so on, down to the Planck scale where the smallest entities (“strings” or
otherwise) do not arise from anything smaller, but appear and disappear from the energetic
vacuum in a “quantum foam” (Figure 1). These principles have also been explored elsewhere in
greater detail (Theise, 2004; Theise & D’Inverno, 2004; Theise, 2005; Theise, 2006; Kurakin,
2004, Kurakin, 2005; Kurakin, 2006), but serve to point out the specified complexity of the
autopoietic unit is merely one type of complex self-organization, but is not particularly special as
such. In this light, this “lower boundary” of living systems at the single cell level may not be the
lower boundary of sentience, per se. Therefore, another view is suggested.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
384
Figure 1. The universe as self-organizing, complex “systems of systems” in which
sentience is identifiable at all levels of scale from the quantum foam up through living
(autopoietic) beings.
Mediating elements of “nervous system” signaling
In all the examples of nervous system functioning considered above, it is electrical and ionic flux
that conveys the response to sensed information from the environment. Nerve action potentials
signal through changing ionic flux generated by coordinated opening and closing of ion
channels, in a more complicated version of that seen in the single cell example of the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
385
paramecium. Can a similar kind of information processing and signaling be found in structures
at scales below the level of the smallest autopoietic unit, such as in some biomolecules? Indeed
they can.
One example serves to clearly define this possibility. The structure of the DNA double helix is
highly conductive, the electrons of the DNA base pairs dissociating and traveling as an electrical
current through the helix. The structure of the helix creates “electron holes”, however, where
there is no electrical flow (Barnett et al, 2001; Giese, 2006). Moreover these \ electron holes are
most prominent over coding regions of the genome and will trap ionizing, potentially mutating
radiation entering the helix and then transfer the potentially mutating energy to a non-coding
region of the genome. In these areas, mutations are less likely to result in injury to the
cell/organism. Thus, we have a biomolecular example in which there is sensing of the
environment, complex internal information processing (with quenched disorder supplied by
quantum mechanical effects), and a subsequent response to what has been sensed. Indeed, there
is even a hint of sense making in that the shift of ionizing radiation is protective against crippling
mutations to the coding regions of the genome. Other examples may include molecules of
import to some contemporary hypotheses regarding consciousness itself and the nature of
quantum behaviors in biomolecules within nerves and nervous systems, including, of course the
tubulins and their assembly into microtubules in the theories of Hameroff and Penrose
(Hameroff, 2007).
Thus, at least some biomolecules display a simpler form of sentience, but sentience nonetheless
as we have defined it. In turn, atoms do the same, sensing the environment and interacting with
other atoms, through the electrical activities of their electron shells – atomic sentience; simpler,
but still sentience. Strip away the electron shells and what happens in the nucleus? The protons
and neutrons interact through exchange of small subatomic particles such as quarks, gluons,
muons, etc. And these smaller subatomic particles? Onward down to the smallest entities. At
these lower levels of scale, the “internal processing” is mediated by quantum effects which,
necessarily, include an element of quenched disorder: the probabilistic behaviors of quantum
mechanics.
But at these lowest levels of scale, from the subatomic downward, we are deep in the quantum
realm where all entities are defined by wave functions that extend infinitely in all directions,
overlapping with all others. Thus, technically speaking, there is no “external” to be sensed and
no “internal” processing to create a response to the external; rather, the component activities that
define sentience are inherent and pervasive, to be currently described, in part, by the concepts of
quantum entanglement and non-locality. In the quantum realm one might tentatively suggest
that the notion of “sentience” be considered a simplest form of “self-sentience”, i.e. nascent self
awareness. What precisely would be the differences between higher mammals and other
biological organisms in terms of self awareness is an open question.
Beyond the Planck limit there is nothing smaller. There is simply the energetic vacuum, the
creative void, out of which all existence arises, building itself through complex self-organization
from smallest subatomic entities into larger subatomic particles into plasmas and atoms and such,
thence into molecules, autopoietic living systems, worlds (Greene, 2000). Thus, a complexity
perspective locates no organizational or dimensional boundary to sentient activity, merely
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
386
differences in the level of complexity of that sentience and apparent and inherent self-sentience
at the lowest scales in the quantum realm, those smallest entities after emergence from the
vacuum. As Kafatos (2000) and Kafatos and Nadeau (2000) have argued, the universe is imbued
with consciousness (in our language sentience, although we again emphasize that consciousness
which includes self-consciousness is not quite the same as sentience, the latter being a much
more general feature of structures in the universe) at all levels.
Table 1. Some mediators of sentient activity at different levels of scale and complexity
Planck Level
Non-locality
__Sentient Entities__
Complex
Multicellular
Organims
Simple
Multicellular
organisms
Single cells
Biomolecules
Atoms
Hadrons
Quarks
Strings
(or…)
Gluons
Mesons
Electrons
Ions
Molecules1
Cells2
Nervous
Systems 3
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
Entanglement
+
1
Biomolecules, depending on the species, such as neurotransmitters, hormones,
antibodies, leptins, etc.
2
Cells belonging to the organisms (e.g. neurons, immunocytes) or microbial flora living
in synergistic mutualism (e.g. gut and skin flora).
3
Nerve nets in lower species like Radiata, central and/or peripheral nervous systems in
Bilatera.
Summary and correlate concepts
Consciousness in the universe is viewed as either all pervasive (the panpsychist perspective) or
arising from the universe when sufficient complexity is attained (the emergentist perspective).
Emergentist perspectives may suggest that formal nervous system development is necessary for
the development of consciousness, but evolutionary biologists can recognize elements of nervous
systems even in the absence of cellular networks. In particular, Maturana and Varela, in their
defining work regarding the self-creating/sustaining, autopoietic nature of cells identify the
evolutionarily simplest forms of consciousness in single cell organisms. For many, this is a
dominant emergentist view, equating the presence of life with the development of mind.
Complexity theory analysis, however, dissolves this lower boundary of life as the definitional
origin of sentience, finding evolutionary aspects that will become recognizable as nervous
system behavior even in the behaviors of some molecules, of atoms, of quantum level entities of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
387
all kinds. Thus, complexity theory transforms the essential features of the autopoietic,
emergentist view into a panpsychist perspective.
Does this analysis mean that all things are sentient? Do sentient entities always assemble into
larger scale, more complexly sentient beings? Of course they do not. Sentience is not a material
that transfers through aggregated units, it is a process that may function at its most simple within
larger, non-globally sentient structures. Thus, while all atoms by this analysis may be sentient
and some of these may self-assemble into sentient molecules and some of these may assemble
into more complexly sentient cells and multicellular organisms, they do not necessarily assemble
into a sentient (to return to the earlier example) machine. The sentience harbored within the air
conditioner, as a higher scale aggregate of its smaller component atoms, remains at its simple, far
less complex, atomic form.
Thus, while larger scale, non-sentient entities may be defined, there is no structure in the
universe that does not contain sentient entities at some lower level of scale, down to the lowest
levels of the quantum realm emerging in the quantum foam. At that level, with quantum
entanglement and non-locality operational for all possible units of existence (whether they are
confirmed as multidimensional strings or some other structure), sentience is, in fact, universal.
Moreover, given the aspects of non-locality and entanglement that pertain at these lowest levels
of scale, application of concepts of “inside” and outside” become impossible; rather, all
processes are internal to all interacting units and therefore we may also tentatively suggest that
sentience begins as “self-sentience.” It is possible that, as we would argue that higher levels of
sentience relate to self-organization of lower level sentient agents, self-sentience may be related
to self-awareness in more typically identified conscious beings. It is, thus, tempting to suggest
that the quantum behaviors in living nervous systems, possibly mediated by microtubules as
suggested by Hameroff, serve to preserve and/or conduct upwards self-sentience from the lowest
levels of scale into the biological levels of scale. We may therefore ask whether our own self
awareness relates to the identified self-sentience of the quantum realm.
Finally, we may also ask and perhaps answer the question: what are the minimal criteria for the
smallest entities emerging from the quantum foam to be able to self-organize into the larger scale
universe? Interactivity would be a baseline necessity, without which self-organization could not
take place. We may, therefore, further specify that this quantum-level “sentience” is simply
another way to describe the inescapable interactivity at these minimum levels of scale, without
which self-organization would not follow.
It is thus sentience itself – partly defined by
interactivity and quenched disorder – that is the minimal criterion for self-assembly of the
universe into larger scale structures, including those which are functionally adaptive (i.e.
“alive”), capable of sense making and perhaps, ultimately, of being consciously self aware.
Acknowledgements: We are very grateful for figure art provided by Jill K Gregory, MFA, CMI
(Manager, Medical Art Services, Continuum Health Partners, New York, NY, USA) and for generous and
constructive insights from Zoran Josipovic, PhD (Director, Contemplative Science Lab, Psychology
Department, New York University, New York NY USA) and William C. Bushell, PhD.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
388
References
Barnett, R.N. et al (2001) Charge Migration in DNA: Ion-Gated Transport. Science. 294, pp. 567-571.
Giese,G. (2006) Electron transfer through DNA and peptides. Bioorg. Med. Chem. 14, pp. 6139–6143.
Grandpierre, A. and Kafatos, M (2012) Biological Autonomy. Philosophy Study 2 (9), pp. 631-649.
Greene, B. (2000) The Elegant Universe: Superstrings, Hidden Dimensions, and the Quest for the
Ultimate Theory. Vintage Series, Random House Inc.
Hameroff S.R. (2007) The brain is both neurocomputer and quantum computer.
Cogn Sci. 31, pp. 1035-1045.
Ishii Y, et al. (2008) Thermal fluctuations biased for directional motion in molecular motors. Biosystems.
93, pp. 34-38.
Johnson, S. (2001) Emergence: The Connected Lives of Ants, Brains, Cities, and Software (New York:
Scribner).
Kafatos, M. (2000) Cosmological, Quantum and Underlying Principles: Clues to the Fundamental Role of
Consciousness in the Universe. Noesis XXV, pp. 73-92.
Kafatos, M. and Nadeau, R. (2000) The Conscious Universe: Parts and Wholes in Physical Reality.
(Springer-Verlag, New York).
Kurakin, A. (2005) Self-organization versus Watchmaker: stochastic dynamics of cellular organization.
Biol Chem. 386, pp. 247-54.
Kurakin, A. (2006) Self-organization versus Watchmaker: molecular motors and protein translocation.
Biosystems 84, pp. 15-23.
Kurakin, A. (2007) Self-organization versus Watchmaker: ambiguity of molecular recognition and design
charts of cellular circuitry. J Mol Recognition 20, pp. 205-214.
Lewin, R. (1999) Complexity: Life at the Edge of Chaos (Chicago: University of Chicago Press).
Maturana, H. (1987). Everything is said by an observer. In Gaia, a Way of Knowing, W. Thompson (ed.),
Lindisfarne Press, Great Barrington, MA, pp. 65-82.
Maturana, H. and Varela, F. ([1st edition 1973] 1980). Autopoiesis and Cognition: the Realization of the
Living. Robert S. Cohen and Marx W. Wartofsky (Eds.), Boston Studies in the Philosophy of Science 42.
Dordecht: D. Reidel Publishing Co.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
389
Meech, R.W. (2008) Non-Neural Reflexes: Sponges and the Origins of Behaviour. Current Biology 18,
pp. R70-R72.
Miller, G. (2009) On the origin of the nervous system. Science. 329, pp. 24-26.
Nakanishi, N. et al (2012) Nervous systems of the sea anemone Nematostella vectensis are generated by
ectoderm and endoderm and shaped by distinct mechanisms. Development. 139, pp. 347-357.
O'Connor, T. and Wong, H.Y. (2012) "Emergent Properties", In The Stanford Encyclopedia of
Philosophy, E.N. Zalta, ed.
http://plato.stanford.edu/archives/fall2010/entries/panpsychism/ [May 30, 2012].
Pani, A. M. et al. (2012) Ancient deuterostome origins of vertebrate brain signalling centres.
.Nature 483, pp. 289–294 .
Pech, L.L. (1995). Regulation of ciliary motility in Paramecium CAMP and cGMP
Camp. Eiochem. Physid. 11, pp. 31-37, 1995
Seager, W. and Allen-Hermanson, S. (2010) "Panpsychism", In The Stanford Encyclopedia of
Philosophy, E.N. Zalta, ed.
http://plato.stanford.edu/archives/fall2010/entries/panpsychism/ [May 30, 2012].
Tamm, S. (1994) Ca2+ channels and signalling in cilia and flagella. Trends in Cell Biology. 4, pp. 305310
Theise, N.D. (2004) Stem cells react! Cell lineages as complex reactive systems. Exp Hematology 32,
pp. 25-27.
Theise, N.D. (2005) Now you see it, now you don’t. Nature 435, pp. 1165.
Theise, N.D. (2006). Implications of 'post-modern biology' for pathology: the cell doctrine. . Lab. Invest.
86, pp. 335-344.
Theise, N.D. and D’Inverno, M. (2004) Understanding cell lineages as complex adaptive systems. Blood,
Cells, Mol, and Dis. 32, pp. 17-20.
Theise, N.D. and Harris, R. (2006) Postmodern biology: (adult) (stem) cells are plastic, stochastic,
complex, and uncertain. Handb Exp Pharmacol. 174, pp. 389-408.
Thompson, E. (2004) Life and mind: From autopoiesis to neurophenomenology. A tribute to Francisco
Varela, Phenomenology and the Cognitive Sciences 3, pp. 381-398.
Thompson, E. (2007) Mind in Life: Biology, Phenomenology, and the Sciences of Mind. Harvard
University Press
Varela, F., Thompson, E., Rosch, E. (1991) Embodied Mind: Cognitive Science and Human Experience.
MIT Press.
von Delius, M. and Leigh, D.A. (2011) Walking molecules. Chem Soc Rev. 40, pp. 3656-3676.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 378-390
Theise, N. D. & Kafatos, M. C., Sentience Everywhere: Complexity Theory, Panpsychism & the Role of Sentience in
Self-Organization of the Universe
Yanagida, T., Iwaki, M., and Ishii, Y. (2008) Single molecule measurements and molecular motors.
Philos Trans R Soc Lond B Biol Sci. 363, pp. 2123-2134.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
390 |
Is Consciousness Computable? Quantifying Integrated Information Using
Algorithmic Information Theory
Phil Maguire (pmaguire@cs.nuim.ie)
Philippe Moser (pmoser@cs.nuim.ie)
Department of Computer Science
NUI Maynooth, Ireland
arXiv:1405.0126v1 [cs.IT] 1 May 2014
Rebecca Maguire (rebecca.maguire@ncirl.ie)
School of Business, National College of Ireland
IFSC, Dublin 1, Ireland
Virgil Griffith (virgil@caltech.edu)
Computation and Neural Systems,
Caltech, Pasadena, California
Abstract
In this article we review Tononi’s (2008) theory of consciousness as integrated information. We argue that previous formalizations of integrated information (e.g. Griffith, 2014) depend
on information loss. Since lossy integration would necessitate continuous damage to existing memories, we propose it is
more natural to frame consciousness as a lossless integrative
process and provide a formalization of this idea using algorithmic information theory. We prove that complete lossless
integration requires noncomputable functions. This result implies that if unitary consciousness exists, it cannot be modelled
computationally.
Keywords: Consciousness; integrated information; synergy;
data compression; modularity of mind.
Introduction
Continuing advances in neuroscience are allowing precise
neural correlates of different aspects of consciousness to be
uncovered. For example, damage to certain areas of the
cortex has been shown to impair the experience of color,
while other lesions can interfere with the perception of shape
(Tononi, 2008). The hard question that remains is understanding how these neural correlates combine to give rise to subjective experiences.
Tononi’s (2008) integrated information theory provides a
theoretical framework which allows this issue to be meaningfully addressed. The theory proposes that consciousness
is an information processing phenomenon and can thus be
quantified in terms of a systems’ organizational structure,
specifically its capacity to integrate information. According
to Tononi, what we mean when we say that the human brain
produces consciousness is that it integrates information, thus
producing behaviour which reflects the actions of a unified,
singular system.
Tononi (2008) explains the foundations of his theory
through two thought experiments, which we adapt slightly
here. The first thought experiment establishes the requirement for a conscious observation to generate information.
The second establishes the requirement for a conscious observation to be integrated with previous memories, hence generating integrated information.
Requirement 1: Generating Information
Let’s imagine that a factory producing scented candles invests in an artificial smell detector. The detector is used for
sampling the aroma of the candles passing on the conveyor
belt below and directing them to the appropriate boxes. Let’s
suppose that the factory is currently producing two flavors of
scented candle: chocolate and lavender. In this case the detector only needs to distinguish between two possible smells.
A batch of chocolate scented candles is passed underneath
and the sensor flashes chocolate. Can we say that the detector has actually experienced the smell of chocolate? Clearly
it has managed to distinguish chocolate from lavender, but
this does not guarantee that it has experienced the full aroma
in the same manner as humans do. For example, it may be
the case that the detector is latching onto a single molecule
that separates the two scents, ignoring all other aspects. The
distinction between chocolate and lavender is a binary one,
and can thus be encoded by a single bit. In contrast, humans
can distinguish more than 10,000 different smells detected
by specialized olfactory receptor neurons lining the nose (Alberts et al., 2008). When a human identifies a smell as chocolate they are generating a response which distinguishes between 10,000 possible states, yielding log2 10, 000 = 13.3 bits
of information.
The important point that Tononi (2008) raises with his initial thought experiment is that the quality of an experience is
necessarily expressed relative to a range of alternative possibilities. For example, if the whole world was coloured the
same shade of red, the act of labeling an object as ‘red’ would
hold no meaning. The informativeness of ‘red’ depends on its
contrast with other colours. Descriptions of experiences must
be situated within a context where they discriminate among
many alternatives (i.e. they must generate information).
Requirement 2: Generating Integrated Information
Tononi’s (2008) second thought experiment establishes that
information alone is not sufficient for conscious experience.
Imagine that the scented candle factory enhances the artificial smell detector so that now it can distinguish between
1 million different smells, even more than the human nose.
Can we now say that the detector is truly smelling chocolate
when it outputs chocolate, given that it is producing more information than a human? What is the difference between the
detector’s experience and the human experience?
Like the human nose, the artificial smell detector uses specialized olfactory receptors to diagnose the signature of the
scent and then looks it up in a database to identify the appropriate response. However, each smell is responded to in isolation of every other. The exact same response to a chocolate
scent occurs even if the other 999,999 entries in the database
are deleted. The factory might as well have purchased a million independent smell detectors and placed them together
in the same room, each unit independently recording and responding to its own data.
According to Tononi (2008), the information generated by
such a system differs from that generated by a human insofar
as it is not integrated. Because it may as well be composed
of individual units, each with the most limited repertoire, an
unintegrated set of responses cannot yield a subjective experience. To bind the repertoire, a system must generated integrated information. Somehow, the response to the smell of
chocolate must be encoded in terms of its relationship with
other experiences.
Consciousness as Integrated Information
Inside the human nose there are different neurons which are
specialized to respond to particular smells. The process of
detection is not itself integrated. For example, with selective
damage to certain olfactory receptors a person could conceivably lose their ability to smell chocolate while retaining their
ability to smell lavender. However, the human experience
of smell is integrated as regards the type of information it
records in response.
According to Tononi’s (2008) theory, when somebody
smells chocolate the effect that it has on their brain is integrated across many aspects of their memory. Let’s consider,
for example, a human observer named Amy who has just experienced the smell of chocolate. A neurosurgeon would find
it very difficult to operate on Amy’s brain and eliminate this
recent memory without affecting anything else. According
to the integrated information theory, the changes caused by
her olfactory experience are not localised to any one part of
her brain, but are instead widely dispersed and inextricably
intertwined with all the rest of her memories, making them
difficult to reverse. This unique integration of a stimulus with
existing memories is what gives experiences their subjective
(i.e. observer specific) flavour. This is integrated information.
In contrast, deleting the same experience in the case of an
artificial smell detector would be easy. Somewhere inside the
system is a database with discrete variables used to maintain
the detection history. These variables can simply be edited to
erase a particular memory. The information generated by the
artificial smell detector is not integrated. It does not influence
the subsequent information that is generated. It lies isolated,
detached and dormant.
The same reasoning can be used to explain why a video
camera, which generates plenty of information, remains unconscious, in contrast to a person viewing the same scene.
The memories generated by the video camera can be easily
edited independently of each other. For example, I can decide to delete all of the footage recorded yesterday between
2pm and 4pm. In contrast, a person viewing the same scenes
encodes information in an integrated fashion. I cannot delete
Amy’s memories from yesterday because all of her memories from today have already been influenced by them. The
two sets of memories cannot easily be disentangled. When it
comes to human consciousness it is not possible to identify
any simple divisions or disjoint components.
What Tononi’s (2008) theory proposes is that when people use the term ‘consciousness’ to describe the behaviour of
an entity they have the notion of integrated information in
mind. We attribute the property of being conscious to systems whose responses cannot easily be decomposed or disintegrated into a set of causally independent parts. In contrast,
when we say that a video camera is unconscious, what we
mean is that the manner in which it responds to visual stimuli
is unaffected by the information it has previously recorded.
Quantifying Integrated Information
Tononi (2008) seeks to formalize the measurement of integrated information. His central idea is to quantify the information generated by the system as a whole above and beyond
the information generated independently by its parts. For integrated information to be high, a system must be connected
in such a way that information is generated by causal interactions among rather than within its parts.
Assuming that the brain generates high levels of integrated
information, this implies that the encoding of a stimulus must
be deeply connected with other existing information in the
brain. We now address the question of what form of processing might enable such integrated information to arise.
Griffith (2014) rebrands the informational difference between a whole and the union of its parts as ‘synergy’. He
presents the XOR gate as the canonical example of synergistic
(i.e. integrated) information. Consider, for example, a XOR
gate with two inputs, X1 and X2 , which can be interpreted as
representing a stimulus and an original brain state. They combine integratively to yield Y , the resultant brain state which
encodes the stimulus. Given X1 and X2 in isolation we have
no information about Y . The resultant brain state Y can only
be predicted when both components are taken into account at
the same time. Given that the components X1 and X2 do not
have any independent causal influence on Y , all of the information about Y here is integrated.
One issue with presenting the XOR gate as the canonical
example of synergistic information is that it is lossy. A two
bit input is reduced to a single bit output, meaning that half
the entropy has been irretrievably lost. If the brain integrated
information in this manner, the inevitable cost would be the
destruction of existing information. While it seems intuitive
for the brain to discard irrelevant details from sensory input,
it seems undesirable for it to also hemorrhage meaningful
content. In particular, memory functions must be vastly nonlossy, otherwise retrieving them repeatedly would cause them
to gradually decay.
We propose that the information integration evident in cognition is not lossy. In the following sections we define a form
of synergy, based on data compression, which does not rely
on the destruction of information, and subsequently explore
its implications.
Data Compression as Integration
Data compression is the process by which an observation is
reduced by identifying patterns within it. For example the
sequence 4, 6, 8, 12, 14, 18, 20, 24 . . . can be simplified as the
description “odd prime numbers +1”. The latter representation is shorter than the original sequence, hence it evidences
data compression.
A close link exists between data compression and prediction. Levin’s (1974) Coding Theorem demonstrates that, with
high probability, the most likely model that explains a set of
observations is the most compressed one. In addition, for
any predictable sequence of data, the optimal prediction of
the next item converges quickly with the prediction made by
the model which has the simplest description (Solomonoff,
1964). As per Occam’s razor, concise models make fewer
assumptions and are thus more likely to be correct.
These insights lay the foundation for a deep connection
between data compression, prediction and understanding, a
theoretical perspective on intelligence and cognisance which
we refer to as ‘compressionism’. Adopting this perspective, Maguire and Maguire (2010) propose that the binding
of information we associate with consciousness is achieved
through sophisticated data compression carried out in the
brain, suggesting a link between this form of processing and
Tononi’s (2008) notion of information integration.
In the case of an uncompressed string, every bit carries independent information about the string. In contrast, when a
text file is compressed to the limit, each bit in the final representation is fully dependent on every other bit for its significance. No bit carries independent information about the
original text file. For an uncompressed file, damaging the
first bit leaves you with a 50% chance of getting the first bit
right and 100% chance of getting the rest of the bits right.
For an optimally compressed file, damaging the first bit corrupts everything and leaves you with only a 50% chance of
getting all the bits right and a 50% chance of getting them
all wrong. Clearly, the information encoded by the bits in the
compressed file is more than the sum of its parts, highlighting
a link between data compression and Tononi’s (2008) concept
of integrated information.
In the following section we formally prove that, given the
Partial Information Decomposition (Williams & Beer, 2010)
formulation of synergy, the amount of integrated information an information-lossless process produces on statistically
independent inputs is equivalent to the data compression it
achieves.
We begin with a brief description of algorithmic information theory (see Li and Vityányi, 2008, for more details). We
use strings to refer to finite binary sequence, i.e. an element
of set 2<ω . Any finite object can be encoded into a string
in some natural way. We are interested in effective descriptions of strings (i.e. computable by a universal computer i.e.
Turing machine) . For a string x, its (plain) Kolmogorov complexity C(x) is the length of the shortest effective description
of x. More formally, fix a universal Turing machine U. C(x)
is the length of the shortest program x∗ such that U on input
x∗ outputs x. It can be shown that the value of C(x) does not
depend on the choice of U up to an additive constant. C(x) is
the amount of algorithmic information contained in x. A random string is a string x that cannot be compressed, e.g. such
that C(x) is at least the length of x.
For two strings x, y the conditional Kolmogorov complexity C(x|y) of x given y is the size of the shortest program
q such that U on input p and provided y as an extra input, outputs x. The information x has about y is defined as
I(x : y) = C(x) − C(x|y) =+ C(y) − C(y|x), where =+ means
equal up to a O(1) (constant) term. The idea of C-based synergy (Griffith, 2014) is to define four intuitive slices of the
C-information of the function m : (x1 , x2 ) 7→ y.
1. R: the amount of the C-information strings x1 and x2 convey redundantly about y, or, equivalently, the amount of
data compression that y achieves assuming statistically independent inputs
2. U1 : the amount of C-information that only string x1 conveys about y.
3. U2 : the amount of C-information that only string x2 conveys about y.
4. S: the amount of C-information the concatenation string,
(x1 , x2 ) conveys about y not conveyed by either x1 or x2 .
From the Partial Information Decomposition framework
(Williams & Beer, 2010), we have the following equalities
relating the nonnegative scalars R, U1 , U2 , and S:
R + U1 = I(x1 : y)
R + U2 = I(x2 : y)
R + U1 + U2 + S = I(x1 , x2 : y) .
First, using the three equalities above we can define an easy
expression for the synergy minus the redundancy,
I(x1 , x2 : y) − I(x1 : y) − I(x2 : y) = S − R .
Theorem 1 Given C(x1 , x2 |y) = 0, then S ≤ R with equality
when I(x1 : x2 ) = 0.
Proof. Using the prior expression we expand the three Cinformation slices into their respective C-entropies.
S − R = I(x1 , x2 : y) − I(x1 : y) − I(x2 : y)
= C(x1 , x2 ) − C(x1 ) − C(x2 ) − C(x1, x2 |y) + C(x1 |y)+
C(x2 |y).
Given that C(x1 , x2 |y) = 0, we know likewise that C(x1 |y) =
C(x2 |y) = 0; we simplify the above,
S − R = C(x1 , x2 ) − C(x1 ) − C(x2 )
= C(x1 ) + C(x2 |x1 ) − C(x1 ) − C(x2)
= −I(x1 : x2 ).
From the above we have,
S = R − I(x1 : x2 ) .
Which entails S ≤ R with equality when I(x1 : x2 ) = 0.
⊓
⊔
The above result shows that synergy (i.e. integrated information) is equivalent to redundancy (i.e. data compression)
for lossless functions operating on statistically independent
inputs. However, an obstacle remains to expressing synergy
in this format. Although Griffith’s (2014) formulation of synergy identifies the link with data compression, giving a definition of the C-information slices R,U1 ,U2 , S based on Ccomplexity is not trivial.
To quantify synergy for lossless functions using Ccomplexity, Tononi’s (2008) definition of integrated infromation must be somehow translated from its original operational
framework of Shannon information theory to that of algorithmic information theory. We now show that the most natural
way of performing this translation does not succeed.
Suppose the synergy of function (x, y) 7→ z is defined as
S0 (x, y : z) = C(z|x) + C(z|y) − C(z|xy) − C(z|x ∩ y)
where C(z|x ∩ y) is the shortest program that outputs z given
advice x or y, (i.e. the program outputs z on any of the two
advices x or y). The following result shows that, using this
definition, the concatenation function turns out to have high
S0 synergy, which is anomalous.
Theorem 2 Consider the concatenation function z(x, y) =
xy. Then z is a lossless function of S0 synergy |z|/2.
Proof. Pick two independent n/2-bit random strings x, y starting with 0 resp. 1 i.e. x = 0 . . ., y = 1 . . . and C(x|y) = n/2
and C(y|x) = n/2.
By definition of synergy
S0 (x, y : z) = C(z|x) + C(z|y) − C(z|xy) − C(z|x ∩ y)
where the first two terms are n/2, the third is O(1), and the
last is n/2 because of the following program p. p is an O(1)
instructions part followed by the bitwise XOR of x, y denoted
w, i.e. n/2 + O(1) bits total. Instructions: Given advice a,
XOR a with w to obtain d. If d starts with 0 output da, else
output ad. So when a = x, d = y and we output ad = xy.
Similarly when a = y then d = x and we output da = xy, i.e.
C(z|x ∩ y) = n/2.
⊓
⊔
In the following section, we outline an alternative strategy
for defining integrated information using C-complexity.
Quantifying Integration Using Edit Distance
If data is optimally compressed then it becomes extremely
difficult to edit in its compressed state. For example, imagine
a compressed encoding of a Wikipedia page. You want to edit
the first word on the page. But where is this word encoded in
the compressed file? There is no easily delineated set of bits
which corresponds to the first word and nothing else. Instead,
the whole set of data has been integrated, with every bit from
the original file depending on all the others. To discern the
impact that the first word has had on the compressed encoding you have to understand the compression. There are no
shortcuts.
To formalize integrated information as data compression
we consider a stimulus, first in its raw unintegrated state, and
second, encoded in its integrated state within the brain. The
level of integration is equivalent to the difficulty of identifying the raw information and editing it within its integrated
state.
In the following definition z and z̄ are the raw stimulus
and the brain encoded stimulus. We consider the difficulty
of editing z into z′ , for example, editing the smell of chocolate to turn it into the smell of lavender. If this operation
is performed on a raw, unintegrated dataset then the task is
straight-forward: the bits that differ are simply altered. Consider, however, the challenge for the neurosurgeon operating
on Amy’s brain. If the stimulus has not been widely integrated then the neurosurgeon can concentrate on a single localised area of her brain and hopefully the encoding will be
overt, reflecting the original unintegrated format in which the
information was originally transmitted. However, if the stimulus has been successfully integrated (i.e. compressed) then
its encoding will reflect the overlap of patterns between it and
the entire contents of Amy’s brain. Its representation will be
widely distributed, with effects on all kinds of other memories, making it impossible to isolate and edit.
We quantify the integration of an encoding process operating on a stimulus as the minimum informational distance
between the original state of the encoded stimulus and any
possible edited state. If every state is completely different to
the original, then the integration is 1; if there exists an edited
state which is only trivially removed, the integration is 0.
For example, when an image on a digital camera is altered,
the informational distance between the camera’s original and
edited state is small. In contrast, the neurosurgeon struggles to edit the memories in Amy’s brain: changing even the
slightest detail requires the contents of her brain to be completely reconstructed. The edit distance is so great that her
original brain state is largely useless for identifying a target
edited brain state.
Formally, the edit distance of m at point z is a number between 0 and 1 that measures the level of integration of m(z).
It is measured by looking at all strings z′ similar to z, and
finding the one that minimizes the ratio of length of the shortest description of m(z) given m(z′ ) to the length of shortest
description of m(z). The smallest ratio obtained is the edit
distance. Since the numerator is always positive and less or
equal to the denominator, the edit distance is between 0 and
1. This edit distance quantifies information integration for
lossless functions.
Definition 1 The edit distance of m at point z is given by
C(m(z)|m(z′ ))
}.
C(m(z))
z′ 6=z:C(z|z′ )≤log |z|
min
{
On the Computability of Integration
In this section we prove an interesting result using the above
definition, namely that lossless information integration cannot be achieved by a computable process.
According to the integrated information theory, when we
think of another person as conscious we are viewing them as
a completely integrated and unified information processing
system, with no feasible means of disintegrating their conscious cognition into disjoint components. We assume that
their behaviour calls into play all of their memories and reflects full coordination of their sensory input. We now prove
that this form of complete integration cannot be modelled
computationally.
An integrating function’s output is such that the information of its two (or more) inputs is completely integrated. More
formally,
Definition 2 A 1-1 function m : z = (z1 , z2 ) 7→ z̄ is integrating
if for any strings z 6= z′ , C(z̄′ | z̄) ≥ C(z̄′ ) − C(z′ | z).
i.e, the knowledge of m(z) does not help to describe m(z′ ),
when z and z′ are close.
Theorem 3 No integrating function is computable.
Proof. Suppose m is a computable integrating function. Let
z be a random string, i.e. such that C(z) ≥ |z|. Let z′ be
the string obtained by flipping the first bit of z. We have
C(z′ | z) = O(1). Consider the following program for z̄′ given
z̄: Cycle through all strings until the unique z is found such
that m(z) = z̄. Compute z′ by flipping the first bit of z. Compute z̄′ = m(z′ ).
Since m is computable, the program above is of constant
size i.e., C(z̄′ | z̄) = O(1). Also C(z̄′ ) =+ C(z′ ) =+ C(z) ≥ |z|
because m is computable, 1-1 and by choice of z.
Because m is integrating, we have C(z̄′ | z̄) ≥ C(z̄′ ) −
C(z′ | z) = |z| − O(1), a contradiction.
⊓
⊔
The implications of this proof are that we have to abandon
either the idea that people enjoy genuinely unitary consciousness or that brain processes can be modelled computationally.
If a person’s behaviour is totally resistant to disintegration
(i.e. we cannot analyse it independently from the rest of their
cognition), then it implies that something is going on in their
brain that is so complex it cannot feasibly be reversed. In line
with this view, Bringsjord and Zenzen (1997) specifically argue that the difference between cognition and computation is
that computation is reversible whereas cognition is not. For
instance, it is impossible for the neurosurgeon to operate on
Amy’s brain and directly edit her conscious memories, because the process of integration is irreversibly complex.
Yet Amy’s brain is a physical causal system which follows the laws of physics. Information flows into Amy’s brain
conducted by nerve impulses and gets processed by neurons through biochemical signalling. Whatever informationlossless changes result should theoretically be reversible. To
argue otherwise seems to suggest that a form of magic is going on in the brain, which is beyond computational modelling.
McGinn (1991) points out that intractable complexity of
the mind does not necessarily require the brain to transcend
the laws of physics: instead, the intractability can have an observer specific source. He argues that the mind-body problem
is cognitively closed to humans in the same way that quantum
mechanics is closed to a zebra. This perspective, known as
‘new mysterianism’, maintains that the hard problem of consciousness stems, not from a supernatural process, but from
natural limits in how humans form concepts.
Similarly, the apparent unitary nature of consciousness
does not require a mystical process of integration which transcends physical computability. Our result merely establishes
a link between integration and irreversibility, the cause of
which can be due to limitations in the observer’s perspective. While we intuitively assume that consciousness must
be a fundamental property as defined from a God’s eye perspective, the attribution of this property always takes place in
a social context. When people attribute consciousness to a
system they are acknowledging a subjective inability to break
it down into a set of independent components, forcing them
to treat its actions as the behaviour of a unified, integrated
whole. The irreversibilty here is observer-centric, as opposed
to absolute. Rather than establishing a new property of consciousness, our result can therefore be interpreted as merely
clarifying what is meant by the use of this concept. Specifically, conscious behaviour is that which is resistant to our
best attempts at decomposition.
Neuroscientific Modelling
An alternative account is simply that consciousness does not
exist: the unitary appearance of people’s behaviour is recognizable as an illusion. Dennett (1991) adopts this perspective
with his multiple drafts model. He views consciousness as
being inherently decomposable, criticizing the idea of what
he calls the ‘Cartesian theatre’, a point where all of the information processing in the brain is integrated. Dennett presents
consciousness as a succession of multiple drafts, a process
in constant flux, without central organization or irreversible
binding.
Could neuroscience provide us with a mechanical model
of human behaviour that supersedes the value of attributing
consciousness, as Dennett (1991) suggests? It sometimes
arises that a system to which we have previously attributed
unitary consciousness is subsequently recognized as following mechanical rules. For example, when conversing with
a chatbot, we might suddenly notice that its responses can
be predicted solely on the basis on the preceding sentence.
We then adopt the superior rule-based model and cease to attribute consciousness.
Ultimately, for consciousness to be revealed as an illusion,
people would have to agree that neuroscientific modelling
succeeds in disintegrating every aspect of behaviour. Note
that the key word here is ‘people’: people would have to
agree. Arguably, the ultimate standard that we have for measurement depends on the notion of other observers, which
are themselves integrated, unified wholes. For this reason,
Maguire and Maguire (2011) speculate that future developments in information theory will recognize the intractable
complexity of the mind as a key concept supporting the notion of objectivity in measurement, a shift which would undermine the meaningfulness of the goal to ‘understand’ the
mind.
Scramble In, Scramble Out
Assuming integrated consciousness is a genuine phenomenon, its noncomputability has interesting implications
for what has to happen in the brain. When stimuli are picked
up by the brain they enter at disintegrated locations. For example, visual stimuli enter through the optic nerve and are
processed initially by the primary visual cortex. When a visual stimulus is encoded in the occipital lobe it clearly has not
yet been integrated with the rest of cognition. For instance,
Stanely, Li and Dan (1999) analysed an array of electrodes
embedded in the thalamus lateral geniculate nucleus area of a
cat and were able to decode the signals to generate watchable
movies of what the cat was observing.
Similarly, the initiation of action must be localised in particular areas of the brain which control the relevant muscles. This readiness potential must detach from the rest of
the brain’s processing and hence is no longer integrated. For
example, following up on Libet’s original experiments, Siong
Soon et al. (2008) demonstrated that, by monitoring activity in the frontopolar prefrontal cortex they could predict a
participant’s decision to move their right or left hand several
seconds before the participant became aware of it.
However, if integration is necessary for consciousness,
then somewhere between the stimulus entering the brain and
the decision leaving the brain, there is a point where the information cannot be fully disentangled from the rest of cognition. This integrated processing cannot be localised to any
part of the brain or any specific point in time. The contents of
cognition are effectively unified. We label this idea ‘scramble
in, scramble out’ to reflect the irreversible integration and disintegration that must occur between observation and action.
The aspects of cognition that have been clarified by neuroscience so far tend to involve processing before scramble in or after scramble out. For example, it is well established that the occipital lobe is involved in visual processing or that the prefrontal cortex encodes future actions before
they are performed. These components are modular in that
they have specialised, encapsulated, evolutionarily developed
functions. However, somewhere between input and output
there must also be a binding process of integration that no
computational modelling can disentangle.
Fodor (2001) summarizes as follows: “Local mental processes appear to accommodate pretty well to Turing’s theory
that thinking is computation; they appear to be largely modular...By contrast, what we’ve found out about global cognition
is mainly that it is different from the local kind...we deeply
do not understand it”. While neuroscience might shed light
on the input and output functions of the brain, the quantification for integrated information we have presented here implies that it will be unable to shed light on the complex tangle
that is core consciousness.
References
Alberts, B., Johnson, A., Lewis, J., Raff, M., Roberts, K., &
Walter, P. (1997). Molecular biology of the cell.
Bringsjord, S., & Zenzen, M. (1997). Cognition is not
computation: The argument from irreversibility. Synthese,
113(2), 285–320.
Dennett, D. C. (1991). Consciousness explained. Little,
Brown.
Fodor, J. A. (2001). The mind doesn’t work that way: The
scope and limits of computational psychology. MIT press.
Griffith, V. (2014). A principled infotheoretic ψ-like measure.
arXiv preprint arXiv:1401.0978.
Legg, S., & Hutter, M. (2007). Tests of machine intelligence. In 50 years of artificial intelligence (pp. 232–242).
Springer.
Levin, L. A. (1974). Laws of information conservation (nongrowth) and aspects of the foundation of probability theory.
Problems Information Transmission, 10(3), 206–210.
Li, M., & Vitányi, P. (2008). An introduction to kolmogorov
complexity and its applications. Springer.
Maguire, P., & Maguire, R. (2010). Consciousness is data
compression. In Proceedings of the thirty-second conference of the cognitive science society (pp. 748–753).
Maguire, P., & Maguire, R. (2011). Understanding the complexity of the mind. European Perspectives on Cognitive
Science.
McGinn, C. (1991). The problem of consciousness: Essays
towards a resolution. Blackwell Oxford, UK.
Solomonoff, R. J. (1964). A formal theory of inductive inference. part i. Information and Control, 7(1), 1–22.
Soon, C. S., Brass, M., Heinze, H.-J., & Haynes, J.-D. (2008).
Unconscious determinants of free decisions in the human
brain. Nature Neuroscience, 11(5), 543–545.
Stanley, G. B., Li, F. F., & Dan, Y. (1999). Reconstruction
of natural scenes from ensemble responses in the lateral
geniculate nucleus. The Journal of Neuroscience, 19(18),
8036–8042.
Tononi, G. (2008). Consciousness as integrated information:
a provisional manifesto. The Biological Bulletin, 215(3),
216–242.
Williams, P. L., & Beer, R. D. (2010). Nonnegative decomposition of multivariate information. arXiv preprint
arXiv:1004.2515. |
Quantum Mechanics of Consciousness
Rajat Kumar Pradhan1
Vikram Dev College, Jeypore, Orissa, India-764001.
(Date: 28.07.2009)
Abstract
A phenomenological approach using the states of spin-like observables is
developed to understand the nature of consciousness and the totality of
experience. The three states of consciousness are taken to form the triplet of
eigenstates of a spin-one entity and are derived as the triplet resulting from the
composition of two spins by treating the subject and the object as interacting
two-state, spin-half systems with external and internal projections. The state of
deep sleep is analysed in the light of this phenomenological approach and a novel
understanding of the status of the individual consciousness in this state is
obtained. The resulting fourth state i.e. the singlet state is interpreted to
correspond to the superconscious state of intuitive experience and is justified by
invoking the concept of the universal consciousness as the underlying source of all
individual states of experience. It is proposed that the individual experiences
result from the operations of four individualizing observables which project out
the individual from the universal. The one-to-one correspondence between the
individual and the universal states of experience is brought out and their identity
in the fourth state is established by showing that all individualizing quantum
numbers become zero in this state leaving no trace of any individuality.
PACS Numbers: 87.10.+e, 87.19.Bb.
Key Words: States of Consciousness, Subject-object duality, Quantum Physics.
1
Email: rajat@iopb.res.in
1
1. Introduction
The congenital problems of quantum theory such as the interpretation of
the wave function and its so-called collapse in a measurement process have long
since been associated with the possible active role of consciousness in the theory
itself and also in the actual measurement process[1]. This has been exemplified in
the well-known paradoxes[2,3,4] of the theory and has resulted in a variety of
formulations of the quantum measurement process and a host of proposals as
possible interpretations[5,6,7]. The early works of Von Neumann[8] and
Wigner[9], followed by those of London and Bauer[10] and also the more recent
works of Stapp[11], Mould[12], Page[13] and Zeh[14] have all conceded a
fundamental role to consciousness in the measurement process.
In particular, the subject-object duality is brought to focus in the Sensible
Quantum Mechanics (SQM) of Page [13] which is based on three postulates: The
first one regarding the perceived object, the second regarding the perceiving
subject and the third regarding their interaction or the process of perception.
Similarly, Song[15] has grappled with the problem of describing selfobserving consciousness using spin-like observables and has been forced to
conjecture an advantage of the Heisenberg picture over the Schrödinger picture
of time evolution if it is to be described quantum mechanically as per his model.
The Weak Quantum Theory (WQT) of Atmanspacher et al [16]developed by
relaxing and generalizing certain axioms of traditional Quantum Theory, is an
attempt to basically apply quantum mechanical ideas to explain certain
phenomena in psychology and psychophysiology by treating the mental states as
quantum states and perception as measurement. They have also encountered the
possibility of the existence of a ‘collective Unconscious’ as a medium and as an
intermediary for the occurrence of the phenomena of ‘transference’, ‘countertransference’ and ‘deputy perception’ etc. in psychotherapeutic scenarios.
2
A very recent and probably the most valiant of them all, is the attempt by
Manousakis[17] to found quantum theory on the basis of consciousness wherein
the state vector |Ψ> represents a state of potential consciousness pregnant with
all possibilities, on which consciousness operates by means of a linear operator to
create or modify the likelihoods of future events and thus leads to the rising of
(perception of) the event in the individual observer’s consciousness by
comparison with the original state. The objective Universe (space-time, quantum
fields including the big-bang itself) is postulated to be primarily the content of the
Universal consciousness and it only secondarily gets actualized or operationally
projected by consciousness itself in the central nervous system upon observation
by an individual conscious observer which is called the process of perception or
objectivation. The individual consciousness is taken to be a particular stream or a
sub-stream of the Universal Consciousness. So, contrary to the persistent
attempts to understand consciousness or its operations quantum mechanically,
here quantum theory emerges as a natural description of conscious experience
starting from the primary ontological character of consciousness and some of its
elementary contents like perception of periodic change and motion.
If consciousness is to be described quantum mechanically, we must
first of all understand what it is; what its states are; and then exploit any
parallelism that obtains between consciousness and the parallel quantum systems
as envisaged by Pauli and Jung [18] to analogically (rather than analytically) build
up a description since the system is not amenable to sensory perception nor can it
be probed by any traditional measurement, whether classical or quantum.
For our purposes, we may define consciousness as that entity which
knows or experiences. It not only inherently knows itself (i.e. the subject) but also
knows what is other than itself (i.e. the object) through some processes. As
regards the states of consciousness we may take them to be the Conscious, the
Subconscious (this includes Freud’s preconscious and also the further deeper and
remoter layers of retrievable memory right upto the Unconscious) and the
Unconscious. The same classification, but with slightly different connotations may
also be obtained from a very early and prehistoric vedantic text, the Mandukya
Upanishad[S.K.19] quoted by Schrödinger[20] in the epilogue to his masterpiece
‘What is Life’. This upanishad does speak of the above three states of
consciousness as the Waking state, the Dream state and the Deep sleep state
3
respectively, but adds an all-important fourth state, which, in modern
terminology, we may call as the Superconscious, wherein the individual becomes
one with the Universal.
A phenomenological approach is introduced in this work to
understand these states of consciousness in quantum mechanical terms and to
derive them following the analogy with spin-like states.
After a brief introduction to the states of experience in section-2, we
try to describe consciousness as a bosonic (spin-one) entity in section-3, and then
move on to derive the states of experience from an interacting-fermion model of
subject-object duality in section-4. In section-5, a set of four individualizing
observables are introduced and their eigenvalue spectra are discussed. In section6, the one-to-one correspondence between the states of the individual
consciousness and the Universal consciousness is pointed out and in section-7,
the fourth state is interpreted as a state of Superconscious experience by
exploiting the identicality of the individual with the Universal consciousness when
all individualizing observables vanish and by appealing to the EPR-type
entanglement between the subject and the object. Finally, we conclude in
section-8 with a discussion of the main results and the future direction of
consciousness studies using our quantum mechanical approach.
2. The states of consciousness
The three distinct states or aspects of consciousness gone through
regularly by each individual are the waking (conscious) state with external
awareness, the Dream (Subconscious) state with internal awareness and the Deep
sleep (Unconscious) state characterized by non-awareness. Before we discuss
each of these states briefly to motivate the use of spin one eigenstates for their
description let us note that in matters pertaining to consciousness one must have
the openness to accept one’s own self as the laboratory and to experiment upon
oneself in a most unprejudiced manner so as to get at the truths underlying the
phenomenon. Moreover, a completely objective approach to consciousness is not
going to be very rewarding since it is itself the conscious subject that has
developed the scientific and objective approach to understand what is other than
itself. To understand consciousness is therefore the same as understanding
4
oneself and this does not require any external aids like experimental probes.
Therefore it is a foregone conclusion that objective approach to consciousness
therefore is going to an incomplete affair. In any case, we begin the discussion of
the states of consciousness with the hope that a quantum mechanical approach is
going to help us in reconciling the subject and the object with consciousness as
the underlying fundamental entity.
(i)The (Conscious) Waking State : In this state the consciousness is externally
projected and there is perception resulting from attention being fully focused
upon sensory inputs into the central nervous system in the brain. Logical ordering
of events in this state leads to causal connection between a previous event and its
effects afterwards. Objective space-time (i.e. separation and periodicity) along
with names, forms, textures, colours, flavours and odours etc. are the contents or
the felt qualia of the perceptions. The individual free will is most strongly felt in
this state.
(ii)The (Subconscious) Dream State : In this state the consciousness is
internally projected and there is perception resulting from attention being fully
focused upon the memory states or thought forms in the brain which have been
formed as the neural records of the previous experiences. There is no strict causal
ordering of events as the attention shifts erratically from one memory state to
another. Subjective space-time with great deal of elasticity, mental objects with
adequate flexibility of form and other felt qualia are the contents of dream
experience. The individual free will is less fully operative in the sense that we
can’t ordinarily direct the course of events in the dream.
According to Freud’s interpretation[21], the unfulfilled desires of the
waking state are sought to be fulfilled through their realisation in the dream
experiences. But there can be other neurophysiological reasons for the dreams
also. Further, it is generally accepted (see ref. 23, however) now that dreams are
experienced during the transition from waking to deep sleep and vice versa in
which there is rapid movement of the eyeballs and is therefore called the REM
(Rapid Eye Movement) phase of the sleep. Modern approaches towards
understanding dreams are the neurophysiological approach of Hobson[22], the
neuropsychoanlytical approach of Solms[23] and the neurocognitive approach
proposed by Domhoff[24].
5
(iii)The (Unconscious) Deep Sleep State : In this state the
consciousness seems to be neither externally projected nor internally projected
as one is completely unaware of either the external objective world through
sensory inputs or the internal subjective world of impressions or thought forms
recorded in the memory states. The attention seems to have lost its existence all
together along with the will.
It is a state of complete ignorance of one’s own self as well as of any other,
as if one’s consciousness is fully covered up by a thick blanket of darkness or
ignorance, but is surprisingly characterized by an experience of bliss and
recuperation for the fatigued individual. This state is therefore very aptly called as
the Unconscious state and we have very little scope of knowing anything more
than what has been stated about the contents of the experience in this state.
Thus space-time and all the objects of the other two states along with their felt
qualia seem to have been completely lost in the thick cover of ignorance.
It is worth noting that Freudian psychotherapy is based on the premise that
the Unconscious contains many hidden data about the past experiences of
individual and that the royal road to it is through the Dream or the subconscious.
According to Jung[25] there is a collective or racial Unconsciousness for every
species and he used this hypothesis to explain the similarities in the patterns of
cultural evolution of civilizations (through the analysis of their symbols, legends,
rituals and languages etc.) the globe over through millennia.
Though waking, dreaming and Sleeping are the basic states of
consciousness infinitely many combinations of these states are also experienced.
For example, the states of distracted attention or absentmindedness, the
confused, the bewildered and the dumbfounded states, the state of obsessive
thoughts, the drugged or inebriated state, the hypnotized state, states of altered
perception resulting from various reasons may all be treated as having admixtures
of the dream state with the waking state with various amplitudes appropriate to
their experience. This is because of the fact that although we usually associate
these states with the waking state, as per our description in terms of the basic
states of consciousness, the awareness or attention in all these cases is only partly
upon the concurrent sensory inputs and is partly on the mental impressions
stored as memory. Similarly, the state of the somnambulist, the drowsy state, the
6
lightly anaesthetized state and the state of consciousness during an epileptic fit
can all be taken to be superpositions of all the three basic states with appropriate
amplitudes for their experience. Similarly, the deeply anaesthetized state, the
state of coma, swoon and the like can all be represented as superpositions of
predominantly the Deep Sleep state with small admixtures of the Dream and/or
the waking states.
It is also not an uncommon experience to have prolonged dwelling in a
basic state because of our intentional or forced absorption in it, almost paralleling
the quantum zeno effect-like situation with continuous observation. Similarly,
very often, due to various causes we may have oscillations between waking and
dream, between waking and deep sleep and so on. This is apart from the natural
cyclicity of our rhythmical daily passage through these states in a fixed periodic
manner. The natural cycle is from waking through dream to deep sleep and again
from deep sleep back to waking through the dream state. It is to be noted that
not all dreams are remembered. Only those that are immediately followed by a
recollection in waking state are remembered.
3. Consciousness as ‘light’
All the above characteristics of the three basic states of
consciousness may be taken to represent the three projections- namely, the
‘external’ or ‘spin-up’, the ‘internal’ or ‘spin-down’ and the ‘neutral’ or
‘unprojected’- of a single spin-like observable called consciousness corresponding
to a spin-one object like a photon. Thus, the ‘consciousness’ quantum number has
the value 1 for any individual. Therefore, we make the following associations
using the |s, m> basis:
(a) The waking state: |ω1> = |1, +1>: The consciousness is fully externally
projected leading to perception of the gross external objects through the
operation of senses. Perceptions in this state are granted an objective reality in
the sense of their being in existence ‘even when no one is looking’ because of the
sharing of the same perceptions by all waking observers concerned, though they
all may not agree in regard to the felt qualia or in the details.
7
(b) The Dream state: |ω2> = |1, −1>: The consciousness is fully internally
projected leading to perception of the subtle internal objects which are the
impressions of the waking state experiences or thought forms through the
operation of the subconscious mind. Perceptions in this state are granted a lesser
reality compared to those in the waking state. The dream objects have a very
peculiar kind of ‘internal objective’ reality in the sense that they are open to
perception by the ‘dream subjects’ in the dream state. Although one may willfully
enter the dream state, one cannot ordinarily direct the course of the dream
because the will is incapacitated.
(c) The Deep Sleep state: |ω3> = |1, 0>: The consciousness seems to be
neither externally projected nor internally projected leading to non-perception of
either the gross external objects or the subtle internal objects. Instead, there is a
covering of blissful ignorance upon the awareness. This seems to be a kind of
unconscious state because of the non-awareness of even one’s own self and looks
like an unprojected state of consciousness. Still, this is not the state of
‘consciousness as it is’, since consciousness, by definition, must have selfawareness.
Again, we can’t say that ‘consciousness as it is’ was absent during deep
sleep for although individual self-awareness was lost, the experience of a blissful
sleep could somehow be registered in this state and recovered also on waking. If
everything was obliterated in the thick cover of ignorance or Unconsciousness
how is it that the individual that wakes up afterwards is the self-same individual
that went into Deep Sleep? Thus, the individual’s memory states are not deleted
in Deep Sleep But are kept in a kind of suspension. The Consciousness is
temporarily suspended or withdrawn from both− the internal memory states and
the external sensory inputs.
This is the first indication that the above three states do not fully exhaust
the possible states of experience. There must be a fourth state of unprojected
consciousness which is fully self-aware so that we can identify it as consciousness
per se or pure consciousness.
The second indication is from the sequence of transitions among the states
that we experience. To see this, let’s assume the triplet of eigenstates to be a
8
complete orthnonormal set and write the general state of consciousness |Ψ> as a
linear superposition of them:
|Ψ> = a1 |ω1> + a2 |ω2> + a3 |ω3>
… … … (1)
where, the expansion coefficients ai are such that |ai|2 = |< ωi|Ψ>|2 gives
the intensity of experience of the state |ωi>, when the consciousness is in the
state |Ψ>. The orthonormality is expressed by < ωi| ωj > = δij.
Now, the sequence of experience as delineated in the previous
section is: |ω1> |ω2> |ω3> |ω2> |ω1> i.e. |1,+1> |1,−1> |1, 0>
|1,−1> |1,+1>, which means that in the transition from waking to dream and
vice versa the selection rule Δm = 0, ± 1 for Δs = 0 is violated, assuming that they
are like the well-known radiative transitions. But, the fact that we experience
these transitions tells us that they are not forbidden and hence, there must be a
state with projection zero which intermediates these transitions and is also
available as an alternative route for each allowed transition. This state can only be
the |0, 0> singlet state, discarding the possibility of |2, 0> which would lead to an
unnecessary proliferation of states contrary to experience.
Incontrovertible experience of the individual during the transition from
waking to dream testifies to the above fact because as one gradually withdraws
oneself into the dream state, one cannot do it keeping up a continuity of thoughts
or a continuous movement through the space of memory states since there is a
momentary loss of individual consciousness for a fleeting moment− a momentary
blackout, so to say− just before the rise of the dream consciousness. This is to be
experienced by waking up in the middle of the dream, before one lapses into
deep sleep. Similar is also the case during the inverse transition i.e. we do not
come to the waking state keeping up a continuity of thought flow or experience
from the dream state. On the contrary, if it were possible for the individual to
keep up the chain of thoughts right into the dream state one would always
succeed in dreaming exactly to one’s liking! Similarly if it were possible to actuate
the dream experience by continuity into the waking we would get the most
pleasant dream experiences actualized on waking up by keeping up such
continuity! But, this is not the case.
9
This clearly shows the distinction between the waking and the dream states
in addition to bringing home the necessity of a fourth state. The dwelling in the
fourth state during such transitions is so ephemeral that it passes of unnoticed
and does not interfere much with remembrance of the dream upon waking up.
The same fourth state is also gone through in a flash during the transition from
one thought form to another so quickly that it is never suspected to have been
there at all. What exactly is the experience in such a flash? Because the dwell time
is extremely short we have no way of answering this question unless we
somehow master the practical technique of prolonged dwelling in it. We shall,
however, attempt to provide a theoretical framework for understanding this state
in section-7.
Yet another reason to seek for the fourth state is that if these three
were the only possible states, then we have the same problem of quantum jumps
as in old quantum theory since we have no answer to the question as to where
the consciousness lies during a transition from one thought form to another
thought form in the waking and the dream states and also during a transition
from one state to another. In quantum field theory, however, the existence of the
‘vacuum state’ comes to the rescue because we interpret the transition from
state |1> to state |2> as annihilation of the system in state |1> and its
subsequent creation in state |2> through the annihilation and the creation
operators, so that we can safely say that during the said interval, the system
temporarily merges into the vacuum before emerging again back into existence in
the new state |2>. Thus, we need to have the so-called ‘vacuum’ state which will
serve the purpose of being the source and the substratum for the three states
that we normally experience.
So, these observations on a possible fourth state lead us to try to
understand the whole of experience in an interacting-fermion model based on the
subject- object duality which happens to be fundamental to all experience.
4. Spin-half realisations of the subject-object duality
The experiences of the individual subject in the states |ω1>, |ω2> and
|ω3> are characterized by the facts of the individual’s awareness of himself or
self-awareness and of what he considers as ‘other than himself’ or the object. The
10
subject and the object make up the whole of our individual experiences. In |ω1>
and |ω2>, both these awarenesses are present, but in |ω3>, although neither of
them is manifestly present, somehow the individual’s experience of bliss is
recorded. In all the three states, we may consider the subject and the object to
have independent existence with corresponding ‘existence’ quantum numbers es
and eo taking values half each ( i.e. es = ½ and eo = ½), since existence is the
common characteristic of both. The subject and the object are distinguishable
only on the introduction of another observable (a new quantum number)
‘consciousness of existence’ having values 1 and 0 respectively for them.
Now, the individual subject and the object (neither of which is
experienced in|ω3>) are experienced in their two possible projections
corresponding to ‘existence-up’ with external projection +½ in |ω1> and
‘existence-down’ with internal projection −½ in |ω2>. The most general subjective
state can be represented by
|Ф > = c+ |½, +½ > + c− |½, −½ >
… … … (2)
and, the most general objective state by:
|χ > = d+ |½, +½ > + d− |½, −½ >
… … … (3)
where, c± and d± are the ‘existence amplitudes’ in the respective subjective
and objective states of external(+) and internal(−) projection.
In |ω1>, the externally projected individual subjective existence
experiences the externally projected objective existence, while in |ω 2>, the
internally projected individual subjective existence experiences the internally
projected objective existence. In the product basis, these two states can be
represented by |ms, mo > =|+½, +½ > = |es = ½, ms = +½ >|eo = ½, mo = +½ > and
|ms, mo > =|−½, −½ > = |es = ½, ms = −½>|eo = ½, mo = −½ >. But, experience is
impossible unless there is some kind of interaction between the individual subject
and the object, both of which we have assumed to have independent existences.
The simplest kind of interaction is of the familiar L∙S –type, which, in this
case we put as:
11
Vi = Ki es ∙ eo
… … … (4)
where, Ki is a coupling parameter that may have factors depending on the
space, time and other variables of the individual’s
), and the variables
characterizing the experiences in Deep Sleep(see section-5).
Following the well-known procedure for the composition of angular
momenta, we can now switch over to the total angular momentum basis or |j, m>
basis where the interaction will be diagonal. We name this basis as the
‘Experience Basis’ and write the resulting orthonormal eigenstates viz. the triplet
(corresponding to existence-consciousness value 1) and the singlet
(corresponding to existence-consciousness value 0) eigenstates of individual
experience as follows:
|ω1> = |1, +1> =|+½, +½ >
|ω2> = |1, −1> =|−½, −½ >
|ω3> = |1, 0 > = (1/√2) {|+½, −½ > + |−½, +½ >}
|ω4> = |0, 0 > = (1/√2) {|+½, −½ > − |−½, +½ >}
where, we have identified the triplet of symmetric eigenstates with the
consciousness eigenstates discussed earlier. The antisymmetric singlet, we have
identified as the fourth one, the reasons for the existence of which were also
discussed in section-3.
How far are we justified in making these identifications? While there is no
problem with the first two identifications, we do have to see what new
understanding of the deep sleep state this analysis grants us, which is one of the
reasons for applying the interacting-fermion model for the subject-object duality.
We also need to see whether the fourth state really serves its purpose as
discussed earlier and what its implications are for understanding the link between
the individual consciousness and the Universal consciousness (See section-7).
12
To understand the experience of Deep Sleep in this model we see that in
|ω3>, there is symmetry between the subject and the object in regard to the
interchange of their projections. This means that we can interpret the Deep Sleep
experience as one in which the externally projected subject (es =½, ms = + ½) does
not have any externally projected object (e o = ½, mo = + ½) which it could have
experienced; instead it has only the internally projected object (eo = ½, mo = −½)
available to it. Similarly, the internally projected subject (e s =½, ms = − ½) does not
have any internally projected object (eo = ½, mo = − ½) which it could have
experienced; instead it has only the externally projected object (e o = ½, mo = +½)
available to it. Thus, a state of non-experience or non-perception results for the
individual consciousness.
As an interesting aside, we may consider the question as to how one wakes
up to |ω1> from |ω3> on being called by name or on being given some other input
in general, sufficient for the purpose, if the above explanation for non-perception
in |ω3> is assumed to be correct. The answer lies in the fact that any (sensory,
vital or mental) input strong enough to warrant a premature or forced or induced
transition from |ω3> has to be through the intermediate Dream state |ω2> which
means that it has to come via internal perception through internal projection. The
time spent in |ω2> in this case may be a very tiny fraction of a second before it
takes cognizance of the strong external sensory input or the internal (vital or
mental) inputs. In essence, what happens is that the internalized part of the
subject is provided with some internal object and the externalized part is
provided with some external object, thus making perception in |ω1> through|ω2>
possible.
We may also picture the time evolution by using time-dependent
coefficients ai(t) multiplying |ωi> in an evolving superposition
… … … (5)
during the intermediate state such that
= |ω3> and
= |ω1>.
This is how one wakes up (see however, section-7 for the explanation basing on
the alternative path through |ω4>).
13
This is quite a novel understanding of the so-called unconsciousness of
Deep Sleep that emerges from our modelling of individual experience as above.
The zero projection is reflective of the failure of the subject to make contact with
the object and as a result, it fails to know the object, which in turn leads to lack of
self-awareness of the subject since the self-awareness of the subject is dependent
on its awareness of the corresponding objects. This is because the self-awareness
experienced by the subject in waking and dream is always in conjunction with the
awareness of the corresponding waking or dream object as evidenced by the
experience eigenstates |ω1> and |ω2> listed above. The awareness of oneself is
always inextricably associated with the awareness of ‘what is other than oneself’
and in |ω3>, both these are absent. This is the explanation of the state of nonawareness of Deep Sleep.
5. The Individualizing observables
It is a well-known fact that all individuals do not have the same
objective experiences although all may agree on certain aspects of the objective
reality. We do not all agree fully with each other on the felt qualia that we
associate with the objects. At the same time, it cannot be gainsaid that we agree
on certain very important characteristics of objects and this partial unanimity is
what is at behind our granting an objective reality to them independent of
individuals. If we assume that there is indeed an objective reality independent of
individuals, as we do in the scientific approach to reality, then naturally, we must
ask, ‘what causes the differences in the individual perceptions of the same
objective reality?’ Obviously, there must be some differing characteristics in the
individuals themselves which are responsible for the differences in their
perceptions. What will be quantum mechanical description of such individualizing
characteristics that lead to the multitude of individuals?
In what follows, we propose to explain the multiplicity of individual
perceptions by adopting a set of four mutually commuting individualizing
observables A, B, C and D; (hence, we shall call them the ‘ABCD- observables’)
which have different values for different individuals. Their eigenvalues are the
characteristic ‘quantum numbers’ of the individual exactly like the mass, charge,
spin and other quantum numbers associated with quanta. These may be taken to
be:
14
(a) Attitude: The operator A represents the attitude of the individual
towards what it considers as ‘the other’ and therefore, may be one of attraction
(love) which we shall take to be a ‘positive’ attitude (a>0) and aversion (hate)
which we shall take to be a ‘negative’ attitude (a<0) and finally, indifference or
neutrality which we shall take to be the zero attitude (a=0). ‘The other’ referred to
above may be any spatiotemporally limited expression of the Universal Being i.e. it
may be a felt quality (a sound, texture, color, flavor or odor or a virtue or a vice),
an event or a process, or a living or nonliving entity or group of such entities or
any experience in general. To be explicit, we may test the attitude of an individual
towards (a) ethical living by sincere performance of duties (b) acquiring wealth
through righteous means and (c) fulfilling the vital and emotional urges within
limits. These may be termed as the ethical, the economic and the emotional
attitudes respectively. As noted above, these attitudes may be positive or
negative or neutral. Our attitudes towards all objects, qualities, events, processes
and experiences will be contained as special cases of these three basic attitudes.
Thus, unethical living, greed for amassing wealth through unrighteous means and
unbridled sensual gratification will correspond to negative attitude values.
Broadly speaking, the attitude can be figured out by eliciting responses
from an individual to the questions as to whether there is a most liked and a most
disliked ‘something’ through any method (observation, questionnaire, schedule,
interview or from primary or secondary sources, or any combination of them, as
the case demands ) appropriate for the purpose[26], and then points may be
awarded depending on whether the individual finds any least likable and least
dislikable characteristics (or felt qualia) in the most liked and the most disliked
respectively. Thus, we can represent all individual attitudes in the range *−1, +1],
with the extrema ±1 corresponding to unqualified infatuation and unqualified
aversion respectively. Further, in our approach, it is immaterial what object or
person or quality or event or process or experience one likes or dislikes most but
that there are such most liked and most disliked ‘something’ is important for
fixing the values of the attitude.
Generalities apart, the experiences of the individual are in accordance with
his likes and dislikes and this is what creates the special differences in his/her
perceptions compared to others. Moreover, it is to be kept in view that while the
strength or intensity of the individuality is to be judged from how strong the likes
15
and dislikes are, the mere non-vanishing of the Attitude (or any of the
individualising observables in general) howsoever infinitesimally close to zero it
may be, is sufficient for the projection of the individual from the Universal.
This is to be contrasted with what in modern psychology is termed as the
‘Diamond of Opposites’− a method of determination of attitudes by plotting the
attraction and aversion along orthogonal axes to form a diamond[27]. However,
our concern here is only with whether a person has any likes and dislikes or not,
and if yes, how intense are the strongest attraction and the strongest aversion, no
matter towards what object, quality, event or process or experience such
attraction or aversion is directed. The greater the ignorance, the stronger is the
distinctive ego and accordingly the stronger are the likes and dislikes.
The attitude determines most of our conscious and subconscious activities
in the waking and dream states respectively. These actions then lead to further
accentuation or strengthening of the likes and the dislikes. Acting as per these
strong likes and dislikes becomes our habit and our habits go to form our
character which shapes up our future evolution or destiny. Obviously then, the
zero eigenvalue corresponds to a special kind of individuality, which is without
any attractions or aversions and thus, may well be taken to be equivalent to the
state of Universality since the Universal being all-inclusive has no ‘other’ to either
love or hate.
We note that we can always split the positive and the negative halves and
get two observables A+ and A− corresponding to attraction and aversion
respectively so that the range of each will be restricted to the interval [0, 1]. This
may be done to have completely identical eigenvalue spectrum [0, 1] for all the
five individualizing observables namely, A+, A−, B, C and D.
(b) Body-identity: Almost all individuals are characterized by their complete
identification with the bodily personality. Rare exceptions occur only in very
special situations (e.g. in the mother for the protection of her child, in the soldier
for the protection of the territorial integrity of the country, in the friend for the
wellbeing of the friend etc.); or in very exalted selfless individuals (like Jesus
Christ), who may happily undergo bodily suffering for any good cause. Each of us
knows how dear the body is to us and how very ‘exact’ is our identification with it.
16
Thus, we may take the observable B to have eigenvalues in the range [0, 1], the
eigenvalue zero again being a very special occurrence, almost coinciding with
Universality. Obviously, the density of states (individuals) will be very high near
the eigenvalue b=1. It may be noted here that our identification in waking and
dream is with our own gross (or physical) and subtle (or mental) bodies
respectively, while in deep sleep, we are one with our own ignorance which is the
very cause of our individuality (hence named as Causal Ignorance).
(c) Causal Ignorance: This observable has the eigenvalue 1 for the state of
deep sleep and a value less than one in waking and dream. The eigenvalue zero is
again a very special one corresponding to complete removal of all ignorance and
therefore, to complete knowledge or omniscience! The spectrum of eigenvalues
for the observable C is thus the interval [0, 1]. The state of complete knowledge
(c = 0) must be one devoid of any individuality since the individual is always
characterized by limited knowledge because of its dependence on the senses, the
mind and the intellect etc. and their various modes (space, time and causation
etc.) for acquiring knowledge. The individual is further handicapped by its pointlike location and the inability to perceive beyond certain allowed ranges of
vibratory inputs through the various senses or through the measuring instruments
which are only the ‘extended senses’.
On the contrary, the Universal is everywhere present and has all-knowledge
through simultaneous direct contact or perception of all causes and effects
spread over the entire spacetime domain. No wonder that this seems impossible
for the individual to visualize because it is simply not meant for individuals like us
to visualize. Just as one species cannot visualise the perceptions of another
because of the lack of the appropriate organs, similarly also we individuals cannot
visualise the workings of the Universal. In fact, even an advanced and far more
evolved being like the human being fails to visualise the perceptions of
elementary living entities like small bacteria or an ant. What to speak then of the
visualization of the higher’s perception by the lower, or more so, of the Universal
by the Individual?
This Causal Ignorance (C) is itself of the form of bliss− bliss of one’s being a
separate individual entity characterized by the Distinctive ego (D) and the bliss of
having this individuality manifest through the Attitudes (A+ and A−) and the
17
resulting Body-identity(B) through which one associates oneself with or
experiences this bliss. This Causal ignorance C is therefore the most fundamental
of these individualizing observables, since it is, in the sense just described, the
cause of the rest of the observables and consequently of all experience. It is the
deepest reason for the appearance of the individuality and is the cause of the
Distinctive Ego D. Thus the value c=1 corresponds also to a state of the highest
bliss in addition to being the state of the highest ignorance or non-awareness.
Since, c=0 corresponds to the Universal, the Causal ignorance may
therefore, be said to be nothing but the ignorance of this state of universality
which is a possibility for the experiencing individual to evolve into, by gradually
reducing all individualizing quantum numbers to zero. We mostly spend our lives
in the first three states, hardly ever worrying about the fourth, except in the very
trying of circumstances or on very rare occasions of deep introspection on the
origin of joy or grief.
(d) Distinctive Ego: That which separates the individual from the rest of the
Universe is the sense of being a separate entity. Out of Causal Ignorance arises
this kernel of one’s individuality, the Distinctive Ego (or the Differentiating Ego)
represented by the observable D. Ordinarily, this has the value 1 in |ω1> and
|ω2>, while in both |ω3> and |ω4> it has the value 0. Its separative effect is
realized through the operations of the attitudes A± and the Body-identity B. One
then considers oneself as a finite, limited individual living in a certain external
spatiotemporal domain physically and having certain recorded experiences in the
internal i.e. mental domain. Then follow the notions of one’s personal (i.e.
physical height, color, sex, age, bodily appearance etc.), familial, racial, territorial,
national, earthbound external identity as well as the vital, mental, intellectual and
the experiential internal identity. One then, for all practical purposes, behaves as
an individual, limited by one’s own identifications with finite domains of spacetime and consciousness. This is where we find ourselves operating as normal
individuals with fully active individualities corresponding to d 1.
The eigenvalue spectrum for this operator is thus the interval [0, 1]. Again,
we see that when d is zero, there is complete lack of the ego sense and the
individual expands out into the Universal and attains oneness with it. In Deep
Sleep, because of Causal ignorance one does not know this expansion into, and
18
the oneness with the Universal, but in |ω4> it is not so and hence we may identify
it with the state of Universality of being.
Now, we need to address the question of the actual measurement of these
individualizing observables, so that they qualify to be observables with some sort
of ‘objectivity’ and exactness within allowable limits, in order to qualify for
application in a scientific investigation. Obviously, these are not observables like
energy or momentum so that we can use measuring instruments and get their
values. Here, what we have to adopt are the well-known techniques (viz.
observation, questionnaires, schedules and interview methods etc. or their
combinations) employed by the researchers in the so-called ‘inexact’ sciences (i.e.
humanities) like economics, psychology, sociology, management studies, medical
science etc. We may prepare intelligently designed questionnaires appropriate to
the observable concerned, with full points 100, and from the responses from an
individual, we may get the value of the observable in the waking state by scaling
down to the eigenvalue range [0, 1]. Interestingly enough, several methods have
been devised in the field of psychology to determine the individual attitudes A±,
which may be taken as the guiding principles for determining the other
observables as well, but keeping in view the specific requirements of the quantum
mechanical formulation presented here. Starting with Thurstone’s equal
appearing interval scale[28, 29] to quantitatively represent attitudes, we have the
summated rating scale of Likert [30], the cumulative scale of Guttman[31] and the
Semantic differential technique[32, 33] using bipolar adjectives etc. in addition to
the Diamond of opposites mentioned earlier, for the determination and
representation of attitudes.
For the use of A± as quantum mechanical observables characterizing the
individuality, we need only the maxima of the attraction and aversion towards
any experience in the past, present and future, sensory or otherwise.
The values of the observables in the Dream state (subconsciousness) may
be inferred from the corresponding values in waking with fair amount of accuracy
if we take note of the fact that the waking and the Dream states mirror each
other in the sense that one’s sub-conscious thoughts get manifested in the
waking as conscious actions, modulo social or environmental restrictions.
19
6. The individual and the Universal
The preceding discussion goes to show that there is a very special kind of
state corresponding to the vanishing eigenvalue for each of the individualizing
observables, which we have referred to as the Universal state. The existence of a
Universal consciousness has been taken as an essential ingredient in Manousakis’
formulation of Quantum theory on the basis of consciousness.
However, a small but significant difference exists between the collective
and the universal states although they have been used interchangeably in the
literature. The collective is the sum of the individual experiences while
maintaining their distinctive individualities (d
), the Universal is the melting pot
of all individual experiences wherein all distinctive individualities vanish in toto.
The collective is a subset of the Universal in the sense that the collective may
refer to particular group like a family or a clan or a race, while the Universal
always refers to the totality of all individual experiences.
Jung’s insight[25] of the collective Unconscious may be seen as a limited
expression of the Universal unconscious. If all Individual unconscious is
comprehended in the collective or universal unconscious, then similarly also, all
individual conscious and subconscious contents must be comprehended in the
corresponding Universal conscious and subconscious, since, if at all the Collective
Unconscious is manifest in the cultural evolution of different civilizations then it
must have done so through the layers of the collective subconscious and the
collective conscious which are nothing but the limitations of the Universal
consciousness and subconsciousness corresponding to a species. This also paves
the way for postulating a one-to-one correspondence between the individual and
the Universal states of experience.
Our approach to understand experience using spin-like observables also
points to the existence of the Universal state of consciousness as the fourth state
shorn of all individuality.
The simplest, most straightforward yet profoundest reason for the
existence of the state of Universality is as a source for all individual experiences,
for otherwise, it would be impossible for us to account for the continuity and the
20
regularity of the pattern of our daily experiences. Although the individual
consciousness seems to be absent in Deep Sleep it must be there in some form
lest one would not wake up as the same individual that went into Sleep. Thus,
there must be continuity of the individual consciousness at a level deeper than
these three levels of daily experience. Whence comes this deepest individual
consciousness or the core consciousness and where does it reside and how long?
How is it able to project itself unto the different states of experience? These are
still deeper questions to be answered. It is elementary common sense knowledge
that the higher (i.e. more expanded) forms of consciousness include and
transcend the lower (less expanded) forms, in the sense that the latter are fully
comprehended in the former. This gives us a clue towards the existence of the
most expanded form of consciousness which includes in itself all limited
manifestations of consciousness without being exhausted by them. This is the
state of the Universal Consciousness or Cosmic Consciousness which includes in
its bosom all states of limited expression of itself in the entire life of the Universe
and yet transcends them. Therefore, for all practical purposes, it can be taken to
be an infinite, inexhaustible and eternal consciousness.
In our phenomenological approach, we can build up the link between the
individual and the universal by postulating a one-to-one correspondence in their
states of experience. There must be the four states of Universal Consciousness
|Ωi> corresponding to the four states individual consciousness |ωi>, i= 1, 2, 3 and
4. The individual states are the experiences of the same One Universal
Consciousness with the individualizing observables A±, B, C, and D taking up
different non-vanishing values, thereby lifting the degeneracy for different
individuals. The continuous interval [0, 1] for their eigenvalues allows for the
infinite of individuals to be encompassed by the Universal as required. These
observables therefore serve to limit the unlimited, the infinite and eternal
Universal consciousness to finite, spatiotemporally limited individuals.
The four Universal states of experience |Ωi> may be seen to be the result of
the interaction between the Universal Subject and the Universal Object each
carrying Existence a value ½, exactly similar to the composition of existences for
the individual subject and the corresponding object of individual experience
leading to the individual states |ωi>. It is to be noted in this regard that the
individual subjects and their objects are not to be summed arithmetically to get
21
the Universal Subject and the Universal Object. Just as the existence of the
manifold sates of the harmonic oscillator does not give us infinitely many such
oscillators, similarly also these individual states are the expressions of the One
Universal Consciousness but with different individualizing quantum numbers for
different individuals. The individuals in this sense are mere limited or finite
appearances of the Universal.
This is to be contrasted with Manousakis’ view of the individual streams of
consciousness being particular sub-streams of the Universal stream, which may
give the impression that the Universal may be gotten by adding up all the
individuals. Our phenomenological approach reveals that the Universal whole is
not the sum of the individual parts. Rather, all the parts put together can never
exhaust the Universal for the simple reason that the former are the appearances
of the latter. This follows from our postulated correspondence between the
individual and the Universal states of Experience which, in turn, requires the
Universal Subject and the Universal Object to be represented as spin ½
existences. However, this cannot be the case if we simply algebraically add the
infinite number of individual subjective and objective spin ½ existences following
angular momentum addition rules.
To represent the relation of the individual with the Universal in quantum
mechanical terms, we denote for the sake of brevity, the nth individual by the set
of quantum numbers In corresponding to the values of the set of individualizing
observables
= {A±n, Bn, Cn, Dn}, so that we may write the experiential state of
the nth individual in the eigenstate |ωi> as:
|
=|Ωi ;
>
… … … (6)
And,
|
=
|
… … … (7)
The most general time-dependent state of the individual will be given by (5), but
now with the additional individuality index ‘n’:
… … … (8)
22
where, the fourth state is left out of the superposition for the reason that it is not
an ordinarily experienced state for the individuals who follow their daily rounds of
waking, dream and sleep and their various superpositions throughout their lives.
If at all it is experienced, it is only fleetingly with lifetime τ4<<Δt0, the observation
(measurement) time (see section-7). It is to be noted that the parameter t in the
equations is the waking time because all our quantum theory is done in |ω1>.
Since there are a countable but very large number of individuals
constituting the Universal, we may be interested in a density matrix
representation of the quantum states of the latter. However, It is easy to see that
because mostly the individuals spend their time in psychophysical superpositions
, a simple density matrix for a total of individuals like :
… … … (9)
with weights
,
being the number of individuals in the eigenstate
used ordinarily in quantum mechanics to describe macroscopic systems
would not suffice for the description of the Universal state comprising of these
individuals.
We may, instead, introduce a ‘phenomenological density matrix’ to build up
the Universal experience from the individual experience eigenstates as follows.
First of all, we note that the state
> is different for different individuals
although the coefficients
may be the same at the time t because of the
characteristic peculiarities of each individual’s experiences due to the differences
in the values
of the individualizing observables. Thus, there will be as many
states as are individuals in the summation and hence the weight factor for each
term (individual) will be . Therefore, we write the density matrix for N
individuals as:
><
|
… … … (10)
Or, in terms of the individual eigenstates
:
… … … (11)
23
Since, we are building up the Universal phenomenologically we do not necessarily
have to take the N∞ limit in the sum. For a single individual, we see that the
‘phenomenological density matrix’ is just the projection operator for the
experiential pure state
:
=
=|
><
|=
|
… … … (12)
Further, using the orthonormality [34]of the individual states
… … … (13)
we can readily verify the well known properties of the density operator for pure
and mixed states holding for
and
(
) respectively.
Here itself, we see clearly the infinitude of the possibilities inherent in the
Universal even for one experiencing individual since as the operator
evolves in
time it would move through all possible experiential states resulting from the
superposition of the experience eigenstates with different values of the
coefficients . The Universal thus comprehends within itself all possible states of
experience of all individuals at all times.
Therefore, we can say that the individual is a particular sub-stream of the
Universal in the sense of being a limitation by projection and not by any actual
division into parts. This is quite a novel understanding of the relationship between
the individual and the Universal that emerges from our phenomenological
approach. Manousakis’ Universal therefore is more the collective than the
Universal. But, in the long run, since all collectives also finally find their place in
the Universal in a nested manner (Universal collective
individual), we may
say in this sense that Manousakis is correct in referring to the individuals as substreams of the Universal. Suffice it to say that the individual, in the course of its
identification (or feeling of oneness) with successively larger collectives, has to
shed its individuality gradually in the process till it reaches the very limit of such
largeness that it identifies itself with all existence, the whole Universe of things
and beings, matter and mind, embedded in space-time. This is when the
individuality completely drops off (d becomes zero) and the Universal is realized
24
as one’s own essential ‘being’. Till such time the individuality maintains itself
through the various nonvanishing values of the ABCD-observables.
We note that the results in this section would not be affected even if we
added the fourth state to the summation in eq. (8) with
for ephemeral
time intervals (much shorter in duration compared to the observation times), so
that the dwellings in this state almost go unnoticed and hence the
phenomenological normalization etc. can all be done with only the symmetric
triplet for the vast number of ordinary individuals characterized by non-vanishing
values of the individualizing observables. Significant departures in the weight
factor would occur only if a significant number of individuals spend a considerable
amount of time (comparable to the dwell time in any other state) in the fourth
state for reasons to be discussed below.
7. Interpreting the fourth state
We now come to the most important part of our analysis of experience
basing on spin-like observables, which was undertaken to see whether we can get
any new understanding or interpretation of Schrödinger’s endorsing remark [19]
regarding the possibility of the individual experiencing the Universal Being as it is,
by becoming identical with it.
First of all, the antisymmetry of the fourth state tells us that it is the only
state possible with complete symmetry between the subject and the object in all
other respects since the full fermionic state should be anti-symmetric with
existence treated as a fermionic quantum number. The triplet becomes possible
only because of distinguishability of the subject and the object on the basis of
another quantum number, namely, consciousness of existence. Thus it is a state
of complete identicality of the existence aspects of the subject and the object.
The subject does not know itself to be different from the object.
Secondly, because all individualizing quantum numbers
of the nth
individual in this state become zero, He is no longer an individual. From eq. (6),
His state of experience is given by:
|
= |Ω4 ;
= | Ω4; A±n=0, Bn=0, Cn=0, Dn=0 >
25
… … … (14)
Now, the fourth states of the individual and the Universal experience arising out
of interaction between the individual or Universal subject and the corresponding
object are given respectively by
|ω4> = |0, 0 >i = (1/√2) {|+½, −½ >i − |−½, +½ >i}
and
|Ω4> = |0, 0 >U = (1/√2) {|+½, −½ >U − |−½, +½ >U}
where, the subscripts i and U are introduced for distinguishing the states. Since
there is a postulated one-to-one correspondence between the individual and the
Universal experiences, there must be the Universal Subject-Object interaction
(equivalent to eq. (4) for the individual case), viz.
VU = KU Es ∙ Eo
… … … (15)
to account for the similar experiences. The consciousness of Universal existence
characterizing the Universal Subject (having existence quantum number ES= ½) is
what distinguishes It from the universal Object (having existence quantum
number EO= ½) in the Universal triplet |Ωi>, i=1, 2, 3, while in |Ω4>, the antisymmetry of the full Universal state demands complete symmetry or
interchangeability in all other respects between them.
The fourth state being one with the Universal fourth state is independent of
the individual’s experiences and is therefore an ever-present state of
consciousness as the unchanging and unchangeable background of all the
experiences in the other three states and therefore may serve as an alternative
route for all the allowed transitions amongst the states as remarked earlier. The
only thing to be borne in mind is that the transit through the fourth state occurs
extremely fast bordering almost on non-recordability and thus is seldom
registered. However, if one wishes to experiment, one may do so oneself by
repeated practice of remaining alert and aware till the very last point of entering
into Dream from waking and vice versa. The truth of the transit through this
fourth state (|ω1> |ω4> |ω2> and vice versa) can only be verified by one’s
own prolonged and assiduous practice of such awareness. It is difficult for most of
26
us even to re-enter a particular dream experience willfully, what to speak of
waking up on the verge of deep sleep!
In any case, If we can have neural probes sensitive enough to register a
temporary cessation of all thoughts (i.e. the state of thoughtlessness or pure
consciousness) for an extremely fleeting interval, then also we may get the
verification of the above fact. However, our current low-frequency brain wave
probes have been able to register cognitive time scales upto about 300 msec[35,
36] for objective experience in the waking state and thus if the dwell time in the
fourth state is less, it remains objectively unobservable.
However, subjective experiences may very well go all the way down to
about a few Hz in the Deep Sleep state. Ideally, in the fourth state of thoughtless
consciousness the frequency of neuronal oscillations should vanish and therefore
the EEG should ideally become flat corresponding to a ‘timeless experience’. But
in reality, the very application of the probes will undoubtedly lead to some very
feeble objective awareness state thereby registering some ultra low frequency
oscillations corresponding to that and thus will deprive ourselves of making any
objective experimentation on Consciousness.
It seems that at some point in our investigation, we have got to shed the
objective approach to reality and make a smooth transition to the subjective
approach at the borderline between intellect and intuition, if we are to
‘understand’ or experience consciousness per se. Since understanding anyone
else’s consciousness does not give one much benefit in regard to one’s own
beyond a certain elementary level of similarity. These are all facts which we have
to grapple with one day or the other individually as well as collectively for
progress of our understanding. The truly scientific approach as an impartial
investigation of the nature of Reality would be to have an open mind with regard
to inputs from all fields of research including the so called inexact sciences like
sociology and psychology and philosophy and then take a course of action as
would unify all aspects of experience.
A relook at the parallelism between the individual and the universal (eq. (4)
and (13) and the states |ω4> and |Ω4>) tells us that not only does the individual
become one with the Universal in the fourth state by shedding all individuality,
27
the Universal also in its turn, sheds all Universality and becomes one with the
Absolute Being that is beyond any description. The Individual thus becomes
identical with the Absolute which simultaneously comprehends all but is
comprehensible by none, because none else is there to comprehend it as an
object of comprehension. This occurs due to the vanishing of all quantum
numbers which characterize the individual or the Universal experiences. The
individual becomes indistinguishable from the Universal and the Universal
becomes one with the Supreme Absolute that baffles all attempts at description.
We may note here that the main difference between Deep Sleep and the
fourth state is in the reversal of the complete ignorance in the former(c=1) to the
complete knowledge(c=0) in the latter. This may be interpreted to be due to the
EPR-like correlatedness of the subject and the object in the fourth state wherein
knowledge of one leads to the knowledge of the other. Therefore, even though
|ω3> itself is a maximally entangled state, the ignorance makes perception
impossible and thus one neither knows oneself nor any object. The same
argument also holds for the other two states of the Bell basis formed by
superposing |ω1> and |ω2>. This means that in the fourth state if the subject
knows itself completely, then it knows the object also completely. The subjective
awareness is correlated with (awareness of) objective existence. These remarks
on |ω4> apply equally well to |Ω4> also in relation to |Ω3>.
Thus, in this fourth state, Existence becomes one with Consciousness and
the only Experience that we may perhaps speak of is one of Bliss of ExistenceConsciousness, since it is only in states of experience of extreme joy that the
individual experiences complete self-forgetfulness or self-absorption in the
experience of bliss− as happens, for example, in the orgasmic experience.
Momentarily though, in the height of orgasmic bliss one does indeed becomes
united with bliss itself forgetting all individuality. Thus we can say that in such
states all individualizing quantum numbers momentarily assume the zero value,
since one knows nothing else but bliss alone. It is a momentary state of union of
consciousness with bliss or experience of consciousness itself as bliss. Similar is
the experience in the fourth state when we consciously apply certain spiritual
techniques like deep meditation and absorption to practice the gradual reduction
of the individualizing quantum numbers to zero value and to become established
in a state of ‘thoughtless consciousness’ wherein the mind as a bundle of
28
thoughts is completely annihilated. When one succeeds in remaining absorbed in
this fourth state for a longer period, there results a united experience of
‘Existence-Consciousness-Bliss Absolute’ – Absolute, because it is experienced as
the One undivided Whole, which is simultaneously the mode of experience (i.e.
Existence), the experiencer(i.e. Consciousness) and the experienced (i.e. Bliss).
8. Discussion and conclusion
In this work, we have successfully represented all individual experiential
states in terms of eigenstates of a pair of interacting spin-like observables. The
interpretations given here not only bring out the kind of psychophysical
parallelism envisaged by Pauli and Jung, but also at the same time, bring to close
focus the quintessential Upanishadic thoughts so much lauded by Schrödinger,
Schopenhauer and others who have gone deep into their significance. The
present study therefore, may act as a bridge between Quantum Theory and
Philosophy proper. The present work is a positive step forward in the direction of
finding a true unification of all knowledge at the ‘source level’ since it deals with
the issues of experience in the broadest possible terms by treating subject-object
duality itself using quantum mechanics.
In summary, our main postulates in this work have been:
a) All individual experience results from the interaction between the subject and
the object.
b) The subject and the object both have two primary states of projection−
namely, the external or physical and the internal or mental, and therefore, can be
treated as quantum mechanical two-state (spin- ½) systems.
c) The Individual experiences have their source in the Universal and there is oneto-one correspondence between the individual and the Universal states of
experience.
d) The individual experiences can be accounted for by the operation of four
individualizing observables called the ABCD- observables corresponding to
Attitude, Body-identity, Causal Ignorance and Distinctive Ego respectively which
29
take up non-vanishing values. When all of them vanish, the individual becomes
indistinguishable from the Universal.
And, the main results have been:
a) The four states of experience emerge from the interaction between the subject
and the object− three of them being the triplet of the ordinarily experienced
states of waking, Dream and Deep Sleep, while the fourth one is extraordinary, in
which all the individual quantum numbers vanish. It is rarely experienced and is
the EPR-like singlet state wherein the subject and the object are entangled
making knowledge of the one possible from the knowledge of the other.
b) A novel understanding of the Deep Sleep state emerges from the interacting
fermion model in which the unconsciousness is seen to be due to lack of contact
of the subject with the object because of their being oppositely projected.
c) The individual is identical with the Universal in the fourth state. The Universal
in its turn, has all Universal quantum numbers vanishing in the fourth state and
therefore is identical with the Absolute which is beyond any description. This
establishes the essential identity of the Individual with the Universal.
It reinforces our trust in the versatility of application of the formalism of
quantum theory, as it is applied to a domain which was hitherto considered to be
exclusively in the realm of psychology and philosophy. The introduction of the
individualizing observables is a step forward in the direction of bridging the gap
between the exact and the so-called inexact sciences. We remark that the sense
in which these observables are used in this essay may not quite tally with the
sense in which they are used in the other branches e.g. psychology and
management studies etc. because the purpose of introducing them here is purely
to generate the individual from the Universal and not just to judge the ability or
utility of the individual in a certain situation as required in case of the latter.
However, links may be established quite easily between the approaches wherever
possible by making appropriate alterations in their definitions in these other
branches, since the fundamental ontological character of these observables in our
approach makes them more robust.
30
One important point of departure from traditional psychology is the
interpretation of the various phenomena like absentmindedness etc. (hitherto
considered as part of the waking experience) as superposition of waking and
Dream states. This is but quite natural in the quantum mechanical scheme that
we have adopted to describe experience and it aids our understanding of the
subconscious mind by bringing it to the forefront of psychoanalysis.
In the process, of course, traditional Quantum mechanics itself suffers a bit,
as expected! And, it is in the interpretation of the states that are superposed as
simultaneously experienced states, while in the probabilistic interpretation we do
not accept simultaneous existence in the superposed states. Instead, we talk of
probability of existence or experience of such states. Again, this is not detrimental
to Quantum theory in any way. Rather, it may be seen as a real pointer to go
beyond the probabilistic interpretation and accept the simultaneous existence of
a quantum system in all the superposed states, however absurd it may seem to
our classical brain.
Such an interpretation in the case of a free quantum object has been
proposed recently[37] where it is shown that the probabilistic interpretation
keeps intact our classical notion of a point particle through the introduction of
probabilities, but it is plagued with illogical and unsatisfactory features. The most
glaring of them is the fact that individual tachyonic de Broglie waves (which are
branded unphysical) are superposed to get a bradyonic wave packet which
represents the physical particle! It is argued that the free quantum object must be
interpreted to have a pervasive existence prior to any interaction or
measurements. Granting the quantum system a simultaneous existence (not just
a probability of existence) in all the available states would pave the way for
clearing up all the mess regarding non-locality and quantum entanglement.
The EPR-correlated fourth state of the subject-object combine may be
taken to be the starting point of a consciousness-based cosmology which will
contain all the currently acceptable cosmologies as special cases. Cosmology
must have the subject built into its structure from the very beginning alongside
the object (if not prior to it!) in view of its primal nature as shown in the present
essay, because the subject and the object form the dual aspects of all experience.
31
The relationship with the many worlds/minds interpretation of quantum
theory and also the building up of quantum theory in the lines indicated by
Manousakis are other aspects which may be worked out keeping in view the
general framework introduced in this work.
Possible future explorations may be made by relaxing the orthonormality
condition eq. (13) between individuals to account for the more occult-like
psychological phenomena such as ‘simultaneous perception’, ‘thought
transference’, ‘deputy perception’ etc. discussed by Atmanspacher et al [16].
Explanations may also be given for the phenomena like ‘metempsychosis’ which
may finally find their rightful place as fields of scientific investigation on the basis
of the robustness of the individuality or the distinctive ego, which is destroyed
only in its final dissolution in the Universal or the Absolute. But, at this stage,
these are more of a speculation, although, the seeds of their being understood
quantum mechanically are very much contained in the analogical framework
proposed here.
9. Acknowledgements
The author wishes to thank L. P. Singh for many useful discussions and
remarks on the manuscript. Thanks are also due to Jagannath Saha, who has been
an early inspiration for the author to take up deep study of the philosophical
underpinnings of Quantum Theory.
10. References
[1] J. A. Wheeler and W. H. Zurek, Quantum Theory and Measurement,
(Princeton University Press, Princeton,1983)
[2] A. Einstein, B. Podolsky and N. Rosen, Phys. Rev. 47,777 (1935)
[3] E. Schrödinger, Proc. Cambridge Phil. Soc. 31, 555 (1935); ibid 32, 446,(1936)
[4] F. Selleri and A. van der Merwe, Quantum Paradoxes and Physical
Reality, (Kluwer Academic, Dordrecht,1990).
32
[5] N. Bohr, Atomic theory and Human Knowledge, (Wiley, New York,
1958). W. Heisenberg, Physics and Philosophy, (Harper and Row, New
York, 1958)
[6] D. Bohm, Phys. Rev. 85, 166 (1952). Ibid, 85, 180 (1952)
[7] H. Everett III, Rev. Mod. Phys. 29, 463 (1957).
[8] J. Von Neumann, Mathematical Foundations of Quantum Mechanics,
Chap. VI, pg. 417 (Princeton University Press, Princeton, 1955).
[9] E. P. Wigner, in Quantum Theory and Measurement , J. A. Wheeler and
W. H. Zurek eds., pg. 260 and pg. 325 (Princeton University Press,
Princeton, 1983)
[10] F. London and E. Bauer, in Quantum Theory and measurement, J. A.
Wheeler and W.H. Zurek eds., pg. 217 (Princeton University Press,
Princeton,1983)
[11] H. P. Stapp, Mind, Matter and Quantum Mechanics: (Springer- Verlag,
Berlin,2003), H. P. Stapp, Quantum Mechanics and the Participating
Observer, ( Springer, Berlin, Heidelberg, New York, 2007).
[12] R. Mould, ‘Quantum Brain States’, Found. Phys., 33 (4), 591-612(2003).
[13] Don N. page, Sensible Quantum Mechanics: ‘Are Probabilities Only in
the Mind?’, Int. J. Mod. Phys., D5, 583-596(1996).
[14] H. D. Zeh, ‘The Problem Of Conscious Observation in Quantum
33
mechanical Description’, http://arxiv.org/quant-ph/9908084.
[15] D. Song , ‘Incompatibility Between Quantum Theory and
Consciousness’, NeuroQuantology, 6, 46-58,(2008) and D. Song,`
Quantum Theory,Consciousness and Being’,
http://arxiv.org/physics/0703034.
[16] H. Atmanspacher, H. Römer, and H. Walach, ‘ Weak Quantum
Theory: Complementarity and Entanglement in Physics and beyond’,
Found. Phys., 32, 379-406, (2002).
[17] E. Manousakis , Founding Quantum Theory on the basis of
Consciousness, Found. Phys., 36, 6 (2007).
[18] W. Pauli and C. G. Jung, Atom and the Archetype, Pauli/Jung, letters,
1932-1958, ed. C. A. Meier, (Princeton University Press, Princeton,
2001).
[19] S. Krishnananda, The Mandukya Upanishad: An Exposition, (YVFA
Press, The Divine Life Society, Shivananda Nagar, India-249192,1997);
Also available at the URL: http://www.swamikrishnananda.org.
[20] E. Schrödinger , What is Life? And Mind and matter ( Cambridge
University press, Cambridge, 1967), Epilogue on ‘Determinism and
Free will’, pg. 87.
[21] S. Freud, The interpretation of Dreams, Standard Edition, (Hogarth
34
Press, London, 1953).
Please note that the term subconscious used here includes and goes beyond the
preconscious of Freud and it generally denotes the entire field of experience
between the fully conscious and the fully unconscious. The preconscious is the
covering lid of the subconscious and the rest of the subconscious is what Freud
took to be the unconscious which is also a little bit different from the sense in
which the term unconscious is used here.
[22] J. A. Hobson, ‘The new neuropsychology of Sleep: implications for
Psycho-Analysis’, Neuropsychoanalysis, 1, 157-183, (1999) and
references therein.
[23] M. Solms, Dreaming and REM Sleep are controlled by different
brain Mechanisms, Behavioral and Brain Sciences, 23(6), 843 - 850,
(2000).
[24] G. W. Domhoff, ‘Refocussing the neurocognitive approach to dreams:
A critique of the Hobson versus Solms debate’, Dreaming, 15, 320,(2005).
[25] C. G. Jung, Psychology of the unconscious, (Dodd, New York, 1916);
[26] N. sproull, ‘Handbook of Social Research Methods’, (Scarecrow
press,New Jersy, 1995);
[27] See e.g. T. W. Treadwell, V. K. Kumar, S. A. Stein and k. Prosnick,
‘Sociometry: Tools for Research and practice’, The International journal
of Action Methods, 51, (1),Pp.23-40(1998).
35
[28] A. L. Edwards, ‘Techniques of attitude Scale Construction’, Appleton
Century-Crofts, New York, (1957);
[29] M. E. Shaw and J. M. Wright, ‘ Scales for measurement of Attitudes’,
(McGraw- Hill, 1967).
[30] J. McIver, and E. carmines, ‘Unidimensional scaling’, (SAGE , 1981).
[31] R. Gordon, ‘Unidimensional Scaling of social variables: Concepts and
Procedures’, (Free Press, new York, 1977).
[32] J. G. Snider and C. E. Osgood, ‘Semantic Differential technique: A
Sourcebook’,Aldine, Chicago,(1969);
[33] S. Himmelfarb, ‘The Measuremen of Attitudes’ in “psychology of
Attitudes”, Eds. A. H. eagly and S. Chaiken, (Thomson/Wadsworth, Pp.
23-88, (1993).
[34] This would lead to a density matrix more like the standard quantum
Mechanical one with different individuals occupying the same state
with intensities proportional to the |amplitude|2 . The overlap of the
states of diferent individuals implies that they some of the
individualising observables have their values matching each other.
[35] C. Basar-Eroglu, D. Strüber, M. Stadler and E. Kruse, ‘ Multistable Visual
perception induces a slow positive EEG wave’, International Journal of
Neuroscience, 73, Pp 139-151, (1993).
36
[36] D. Strüber, C. Baser- Eroglu, E. Hoff and M. Stadler, ‘Reversal rate
dependent Differences in the EEG gamma-band during
multistable
visual perception’, International Journal of psychophysiology, 38(3),
Pp. 243-252, (2000).
[37] R. K. Pradhan and L. P. Singh, ‘On the Reality of Tachyonic Matter
Waves’, Orissa Journal of Physics, 16, 1, Pp 149-164, (2009).
37 |
Elements of Consciousness and Cognition. Biology, Mathematic,
Physics and Panpsychism: an Information Topology Perspective
Pierre Baudot
Inserm UNIS UMR1072 - Université Aix-Marseille AMU,
Faculté de Médecine - Secteur Nord, 51, Boulevard Pierre Dramard,
13015 Marseille, France
pierre.baudot@gmail.com
arXiv:1807.04520v2 [q-bio.NC] 16 Jul 2018
16th July 2018
Abstract
This review presents recent and older results on elementary quantitative and qualitative aspects of consciousness and cognition and tackles the question ”What is consciousness?” conjointly from biological, neurosciencecognitive, physical and mathematical points of view. It proposes to unify various results and theories by means
of algebraic topology and puts forward the suggestion that information topology is a particularly appropriate
formalism to achieve such an aim. The resulting discrete probabilistic and group theoretic principles and
structures governing the theory of consciousness underline its Galoisian nature.
The first chapter presents the postulates and results on elementary perception in psychophysics and neuroscience at various organizational scales of the nervous system and proposes the hypothesis of an electrodynamic intrinsic nature of consciousness which is sustained by an analogical code. It underlines the diversity of
the learning mechanisms that sustain the dynamics of perception and consciousness, including adaptive and
homeostatic processes on multiple scales, and details their current generic expression within probability and
information theory.
The second chapter investigates the logical aspects of cognition and consciousness and proposes an axiomatization based on measure and probability theory. Topos and constructive logic are presented as providing
an intrinsic non-deterministic-probabilistic logic, with the long-term aim of avoiding the paradoxical decomposition induced by the Axiom of Choice. Using such a basis, we sketch an elementary procedure allowing
an expression of the information of a mathematical formula a la Gödel. We then present the formalism of
information topology and propose that it provides a preliminary basis for synthesizing the main models of
cognition and consciousness within a formal Gestalt theory. Information topology establishes a characterization of information theory functions, allowing for a precise expression of information structures and patterns.
It provides a quantification of the structure of statistical interactions and their expression in terms of statistical physics and machine learning. Notably, those topological methods allow conciliation of some of the
main theories of consciousness, namely integrated information theory, the global neuronal workspace model,
the free energy principle and logical dynamics. The topological approach points out that consciousness is
a structural phenomenon arising from collective interactions. Underlining the central role of invariance to
transformation in neuroscience and perception, we further propose a possible correspondence of information
topology with dynamical system theory and the related quantification of arousal states.
Contents
1 Introduction
2
2 Neurobiology and psychophysics, electrophysiology of elementary perception
3
2.1 ”Unity and Diversity” [1] . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
3
2.2 The neuronal postulate - neural assemblies - neural coding - shapes of memory and qualia . . . .
3
2.2.1 The neuronal/biological postulate - physical reductionism . . . . . . . . . . . . . . . . . .
3
2.2.2 Consciousness: the electromagnetic view - ”Where is my mind?” . . . . . . . . . . . . . .
4
2.2.3 Neural coding - neural assemblies - synchrony - noise . . . . . . . . . . . . . . . . . . . . .
8
2.2.4 Psychophysics - Fechner and Gestalt’s heritage . . . . . . . . . . . . . . . . . . . . . . . . 12
2.3 Active consciousness - plasticity, adaptation homeostasis - Dynamic and persistence of qualia . . 15
2.3.1 Action-perception inseparability . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
2.3.2 Plasticity - (machine) learning - Informational and Statistical physic of consciousness dynamic 15
2.3.3 Homeostatic plasticity - consciousness invariance . . . . . . . . . . . . . . . . . . . . . . . 18
3 Mathematic, cognition and consciousness
20
1
3.1
3.2
3.3
3.4
3.5
Mathematical nature of consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
3.1.1 Empirical proof of the mathematical nature of consciousness: subjective axioms . . . . . .
3.1.2 Mathematic, a model of cognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Constructive logic, information topos and e-motivs . . . . . . . . . . . . . . . . . . . . . . . . . .
3.2.1 Measure Theory: a mathematical theory of subjective and objective experience-observation
3.2.2 Probability, the logic of thoughts, the geometry of beliefs . . . . . . . . . . . . . . . . . .
3.2.3 Topos: the consistent diversity of truths and beliefs . . . . . . . . . . . . . . . . . . . . .
3.2.4 Information functions and set theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
3.2.5 The information of a formula/thought . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
Homology, the shapes and the language of perception . . . . . . . . . . . . . . . . . . . . . . . . .
3.3.1 Homological history and cognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
3.3.2 Groups and action: ambiguity and uncertainty according to Galois . . . . . . . . . . . . .
3.3.3 What is topology? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
3.3.4 Information topology synthesis: consciousness’s complexes and thermodynamic . . . . . .
Dynamics, Geometries, action invariance and Homeostasis of consciousness . . . . . . . . . . . .
3.4.1 The invariances to group actions of perception . . . . . . . . . . . . . . . . . . . . . . . .
3.4.2 Geometrical and Topological invariance, isomorphism . . . . . . . . . . . . . . . . . . . .
3.4.3 Dynamical aspects of information, isomorphism, stability, and homeostasis . . . . . . . .
Computational mind - from Cybernetic and AI to biological beliefs . . . . . . . . . . . . . . . . .
3.5.1 Computation, machines and consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . .
3.5.2 Computational hardness of consciousness . . . . . . . . . . . . . . . . . . . . . . . . . . .
20
20
21
22
22
24
26
29
31
34
34
35
37
40
46
46
48
48
50
51
51
4 Conclusion - the global ecological synthesis
52
A The topology of psychophysic according to Poincaré
53
B The objective poetry
54
1
Introduction
A theory of consciousness concerns anyone and should be a theory of anyone: a theory of everybody and everybody’s theory. It should be consensual and hence should acknowledge and account for the diversity of all beings
(bodies). It should account for and respect the consciousness of anybody, and encompass without contradiction
all the hardly countable investigations that have treated consciousness in its different forms and aspects: biological, physical, psychological, mathematical, computational, etc. Consciousness and qualitative perception is
also one of the main topics of theology and art; hence, a theory of consciousness should also be theological and
artistic, at least minimally, such that it does not contradict the diversity of theologies and art that human minds
have formalized and which are some of the central forms of human consciousness and cognition. To avoid the
usual dualist oppositions, it is necessary to precise that seen from the world of probability explored here, atheism
is also a system or a form of human belief, which also enriches the complex landscape of diverse consciousness
and thoughts. As a consequence, the road towards such a theory appears difficult, and, while we do not achieve
it here, we instead propose some ideas towards what the aims of a theory of consciousness that respects and
harmoniously verifies its own axioms (which we consider firstly and in a literal sense to be unity and diversity,
as proposed by Tononi and Edelman [1]), would be. In the mathematical section of the paper following [2],
we present the formalization of the probability theory within topos theory and constructive logic, a logic with
multi-valuations in which the excluded third is not a theorem (independent). Such constructive logic could underline the idea that those beliefs classically considered as complementary opposite statements - dualism - may
indeed refer to a diversity of beliefs - pluralism. It provides a preliminary soft non-deterministic rationality that
further provides a legitimate rational status to free will. This should not be understood as a novel, personal or
established theory of consciousness, and all the more a closed and definitive framework. Information topology
is simply a name proposed because two existing, partially established theories, information theory and a central
branch of algebraic topology appear indistinguishable, and should ultimately be, just one. Such unification is
currently only partially understood. As emphasized in the ecological mind conclusion, we simply present, recycle
and combine, in a consistent fashion, well-established results (which is a cognitive task of associative memory),
such that the resulting theory is the least partial possible. In short, there is no claim of originality or novelty,
just as in the case of consciousness itself: ”Novelty is as old as the world” (Prevert); hence this paper’s status as
a review and perspective. An important part of the ideas presented here are inherited from Bennequin and are
the result of a long-lasting collaboration. Notably, the formalization of visual processing as regards invariance is
developed at length in [3]. In the world of ideas, nothing is lost, nothing is created, everything transforms. We
will focus on an old intuitionist idea of a mathematical and physical nature of our subjective being, and even of
our most elementary perceptions.
2
The main ideas of the review (without analytical requirements) are expressed quite synthetically in the following
citations of Riemann and Poincaré that introduce both consciousness and a topological view on it: ”When we
think a given thought, then the meaning of this thought is expressed in the shape of the corresponding neurophysiological process.” Riemann [4] ”Now what is science? ...it is before all a classification, a manner of bringing
together facts which appear separate, though they are bound together by some natural and hidden kinship. Science, in other words, is a system of relations. ...it is in relations alone that objectivity must be sought. ...it
is relations alone which can be regarded as objective. External objects... are really objects and not fleeting and
fugitive appearances, because they are not only groups of sensations, but groups cemented by a constant bond. It
is this bond, and this bond alone, which is the object in itself, and this bond is a relation.” [5]
”Mathematicians do not study objects, but the relations between objects; to them it is a matter of indifference
if these objects are replaced by others, provided that the relations do not change. Matter does not engage their
attention, they are interested in form alone.” Poincaré [6]. When you use the word information, you should
rather use the word form Thom [7].
2
Neurobiology and psychophysics, electrophysiology of elementary
perception
2.1
”Unity and Diversity” [1]
This section investigates the question of the limit from which a particular cognitive process or a particular living
species can be considered as conscious or not. It is not relevant or possible to review all the results concerning
consciousness that neuroscience imaging, electrophysiological studies, psychophysic and psychology studies have
already presented. All of those studies concern consciousness more or less directly, and most researchers we have
encountered or worked with are quite aware that their work more or less directly concerns consciousness, although
they may not refer to such a generic concept and usually prefer much more precise, specific, and less grandiose
ones. In what follows, we cite only a few examples of such works, not because they are the most pertinent
but because we are already familiar with them; the rest can be found in research libraries. The results of such
studies, as advocated and centrally underlined by the Integrated Information Theory of Tononi and Edelmann,
tend to be that forms of consciousness are very diverse [1]. Neuroscience and cognitive sciences have developed
specialized concepts and taxonomy for these different forms, such as attention, low-level vision, audition, multimodal integration, decision, motor planning, short-term memory, etc. In a sense, there exists a given, particular
name of consciousness for each function and associated structure in nervous systems. Moreover, there exist
a wide diversity of nervous systems: human, macaque, cat, rat, mouse, zebra finch, bat, turtle, elephantfish,
cricket, fly, squid, aplysia, worms (caenorhabditis elegans), to cite just a few generic experimental models. Such
a diversity reveals the richness of cognitive forms [8]. Each of them have remarkably different structures and
functions; hence, a satisfying theory of consciousness would have to be very basic and generic such that all those
fields of research can converge. The point of view adopted here, now more accepted in neuroscience (thanks
most notably to Koch, Tononi and Edelmann [9]), is that if one accepts that there exists a qualitative low-level
perception in humans, and admits it provides a quite elementary form of consciousness, one should accept from
the purely empirical criterion of observability that the echolocation of a bat, for example, is also associated with
elementary forms of consciousness, albeit likely to be different from the one we experience, as can be inferred
from electro-physiological studies and discussed by Nagel [10]. The boundaries of consciousness have been the
subject of numerous social debates with important social ramifications and consequences; notably, in justifying
slavery, part of humanity was considered as not being conscious [11]. From the philosophical perspective, it has
been clear since Hegel’s ”phenomenology of spirit”, which is built on the dialectic of the slave and the master,
that the question of consciousness and the problem of its multiplicity, of alterity, can be investigated in terms
of competitive or dominating purposes [12]. The quite recent emergence of biological sciences, introducing the
multiplicity and diversity of natural structures and functions and underlining their constitutive inter-dependencies
has started to promote a more co-operative, symbiotic or synergistic view of alterity. More generally, the problem
of consciousness poses the question of humanity’s place with respect to nature and physics.
2.2
The neuronal postulate - neural assemblies - neural coding - shapes of memory
and qualia
2.2.1
The neuronal/biological postulate - physical reductionism
Neuroscience and cognitive research play a particular role in science, in that they aim to objectively study, by
empirical and physical means and with mathematical models or data analysis, the subjectivity of perceptions,
actions and decisions. The main postulate of those investigations was clearly stated by Changeux [13] and
can be summarised by the hypothesis that for any mental subjective state there exists an empirical observable
phenomenon, most commonly an electrical activity, that corresponds to or generates it. One debate regarding
3
consciousness theory is whether such correspondence is one to one, what we call the Tononi-Edelmann model
(for reasons that will become clear in the course of the paper), or if it is injective-only, implying the existence
of some unconscious states - what we call the Dehaenne-Changeux model. The usual neuronal-biological dualist
hypothesis, however, forbids metaphysical subjective states (subjective states without any physical observable
correlate). This has meant that a major part of neuroscience and cognitive research has adopted physics’ reductionist approach and respects the observability axiom of physical theories. Hence, they deserve the name
of physical investigations into qualitative experience. What is presented here reconciles the Tononi-Edelmann
[1, 14] and Dehaenne-Changeux models [15, 16, 17] by proposing that what one may consider as an unconscious
state is ”someone else’s” consciousness. The general proposition that an unconscious state is ”someone else’s”
consciousness can be simply illustrated by the development in patients, specifically called ”split-brain” patients,
of two quite independent consciousness streams following a callosotomy, as studied notably in the celebrated work
of Sperry and Gazzaniga [18, 19]. Here, we start from the postulate that the objects of our subjective experiences
or perceptions exist. We also postulate the existence of the subject that perceives (the ”I think therefore I am”
of Descartes) and complete it with a statement along the lines of ”It moves therefore it is”, a phenomenological
definition of anima based on animation.
Reflexive and qualitative consciousness: feedback and the hard problem. From mind-body dualism
to a synthetic monadic view. The question investigated in this section is whether there necessarily exists an
ontological difference between the mind and the body. An important part of studies into consciousness, following
classical, at least partially Platonic dualism and standard mind-body problems, assumes a fundamental distinction between reflexive and qualitative consciousness called qualia, as investigated by Chalmers [20]. According
to this view, reflexive consciousness, the fact of a consciousness being conscious of its own ”states”, is an easy
problem which it has been possible to solve with cybernetic and control theory, which formalize the concept of
feedback and gain controls further pursued in neural networks studies. Qualitative consciousness, on the other
hand, the elementary qualia, provides what is known as the ”hard problem” of consciousness. The ”knowledge
argument” is a typical thought experiment given to illustrate what a qualia is [21]: a scientist, Mary, is living in a
black and white room with books providing her all the ”reflexive” knowledge about color, including its physical,
artistic and neuroscientific aspects. Jackson argues that a qualia is what Mary experiences when she first sees
colors that she could not know from the reflexive knowledge contained in her books. Such a thought experiment
appears to be more like a linguistic human problem, equating very high level cognitive linguistic abstraction
(”reflexive knowledge”) with very elementary color perception. Even color perceptions result from a learning
or adaptive process, and as in any learning task, we can only assume that she would gain a new qualitative
experience by seeing color, which would be in full agreement with her highly abstract qualitative, linguistic and
scientific experience of color - probably what she had expected or even spontaneously experienced by synesthetic
completion as proposed by Ramachandran [22]. In other words, we propose here a more monist point of view that
reconciles the reflexive and qualitative aspects of consciousness. In this sense, there is a reflexive mechanism,
that is further developed here in terms of a self-interaction or internal energy (cf. 3.3.4), to any qualitative
experience and respectively there is a qualitative mechanism associated with any reflexive experience. Such a
view was notably developed at length by Leibniz in his explorations of the nature of what he called ’monads’
[23, 24], a view that was further pursued in works that will be partially reviewed later in the paper. In this review,
we will focus on elementary, ”low-level” qualia and highlight the fact that electrophysiology and neuroscience
results have demonstrated that they rely on feedback and gain controls on virtually all scales of nervous system
organization and recordings.
2.2.2
Consciousness: the electromagnetic view - ”Where is my mind?”
This section asks at what biological organizational scale consciousness arises and the nature of its physical support.
Since the work of Galvani in 1771 on ”animal electricity” [25], electric and more generally electromagnetic signals
have provided the main sources of observable phenomena for neuroscience and cognitive studies, and yet provide
the basis of consciousness theory, at least in this review. It is indeed a posteriori justified from the physical
point of view not to take into account other forces such as gravity, except in some particular cases such as the
study of the vestibular system, in the dynamic of nervous system activity. However, neglecting gravity is only
an occasionally justified and possibly imprecise course of action. Since Galvani, experiments have become more
precise and provide empirical measurements of electromagnetic signals at many different scales, that is, with
varying space-time resolutions, ranging from single molecule channels to the whole brain, as is the case in fMRI
or EEG recordings. An out of date and non-exhaustive comparative figure of the space-time resolutions of some
measures of the electromagnetic field given off by activity in the central nervous system is given in [26, 27]. Figure
1 shows recordings of electromagnetic activity in response to ”noisy” or naturally fluctuating stimulation at some
of the different organizational scales of the nervous system. Studies into impulsional response and variability is
reviewed in the following sections.
Legend of Figure 1 (from bottom to top and from left to right). Molecule (channel): A representation of the structure of a potassium ion channel (KcsA, adapted and redrawn from MacKinnon [28] and [29]).
4
Figure 1: Impulsional responses and variability at different organization scales of the nervous system. See legend 2.2.2.
A single-channel (AcetylCholine, ACh) current recording (redrawn and modified with permission from Neher
and Sakmann [30, 31, 32]). To our knowledge, a variability study of a single channel response has never been
made. The ”gating” conformation change from open to close of a potassium channel (redrawn and modified with
permission from Jiang and colleagues [33]) and the free-energy landscape transition (redrawn and modified with
permission from Grosman and colleagues [34] for Ach receptor channel). The linear response of a single Sodium
channel (cardiac isoform, hH1a) to colored (100Hz) dichotomous noise (redrawn and modified with permission
from Millonas and Hanck [35]). Organelle (synapse): a simplified drawing of a synapse. Recordings of several trials of postsynaptic voltage (Vm) in response to presynaptic white noise (black) and the mean response
(red) in the graded synapse of the locust (redrawn and modified with permission from Simmons and de Ruyter
van Steveninck [36]). A Spike Timing Dependent Plasticity profile representing the synaptic potentiation and
depression of a synapse in the rat hippocampal neurons as a function of the time interval (∆t) between the onset
of Excitatory Post-Synaptic Potential (EPSP) and the peak of the postsynaptic spike (redrawn and modified
with permission from Bi and Poo [37]). It should be possible and of interest to express such plasticity rule by
means of the impulsonal response of a synapse (within the nonlinear higher order kernels). The postsynaptic
current evoked by a presynaptic spike (approximated as impulsional) in the study of Simmons and de Ruyter van
Steveninck [36]. Cell (neuron): 25 trials of spike trains recorded in patch from neocortical slices, responding
to the same white noise stimulation (redrawn and adapted from Mainen and Sejnowski [38]). The Vm, Sodium
and Potassium conductance responses of the Hodgkin-Huxley model of a giant squid axon (redrawn and modified
with permission from Hodgkin and Huxley [39]). The impulsional response of an Aplysia neuron to white noise
(redrawn and modified with permission from Bryant and Segundo [40], see also [38]). Sub-tissular structures
- cell networks (V1 area cortical network): 10 trials of spike trains and Vm responses (mean Vm in red),
recorded intracellularly in vivo, to natural image animated by eye movements (redrawn and modified with permission from Baudot and colleagues [41, 42]). A similar study was conducted extracellularly in the H1 neuron of the
5
fly by de Ruyter van Steveninck and colleagues [43]. Spatial profile of a spiking receptive field of a simple cell in
V1 (A17), recorded extracellularly; × and 4 denote the visual areas giving excitation and inhibition, respectively,
to bright light spot stimulation (”ON response”, redrawn and modified with permission from Hubel and Wiesel
[44]). The more quantitative spatial profile of the linear response of a simple cell spiking receptive field obtained
by sparse noise reverse correlation; blue and red color-scales denote the visual areas giving excitatory response to
bright (ON) and dark (OFF) stimulus, respectively response (redrawn and modified with permission from Jones
and Palmer [45]). Above this is presented the Gabor wavelet-like spatial profile of the receptive field. A spatial
and space-time profile of the linear response of a simple cell Vm receptive field obtained with dense noise stimuli
(redrawn and modified with permission from Baudot and colleagues [41, 42]). Tissue (cortical area): the fMRI
responses of the V1 area averaged over two groups of subjects (red and black) while watching a popular movie is
illustrated together with a diagram representing the percentage of intersubject correlated cortical areas during
viewing and the cortical localization of intersubject synchronized areas (redrawn and modified with permission
from Hasson and colleagues [46, 47]). The impulsional linear fMRI response of a voxel in the left superior temporal gyrus to a random sequence of words (redrawn and modified with permission from Friston and colleagues [48]).
The basic proposition of this review from a physical point of view is that the theory of consciousness is the
theory of electromagnetic fields (leaving aside the effects of gravity). The electromagnetic theory of consciousness
has been developed on the basis of the theory of oscillating neural assemblies (cf. section on neural coding 2.2.3)
most notably by John [49], Pockett [50] and McFadden [51], and basically considers the idea that the spectrum
of electrical activity observable in Electroencephalograms (EEGs), typically ranging from 0 to 100 Hz, sustains
consciousness. The proposition here is to broaden the spectrum to any frequency and to take into account the
temporal and phase dynamics of the activity in question. The beta (12-40Hz) and gamma (40-100Hz) frequencies
are simply particular activity ranges evoked by conscious states in humans and in primates more generally, and
are mainly generated by primates’ peculiar cortical (or cortical-like, e.g. olfactory bulb) excitatory-inhibitory
microcircuits. They do not account for the activity related to consciousness observed using other methods at
different scales and in other species. This proposition is in fact simply an up-to-date reconsideration of the
statement attributed to Pythagoras: ”All things feel!” and developed in a poem by de Nerval in his ”golden
verse reproduced in annex B. By no means should such a proposition be understood as either a simplification
or a definitive theory: electromagnetism is neither a simple nor a closed theory (all the more if one considers its
relation to gravity). It simply proposes, taking a scientific interpretation of Blake’s statement ”to see a world
in a grain of sand”, that there are no more fundamental mysteries in the black box of a human brain, nor any
fewer, than in the black box of a particle collider or bubble chamber.
Such a proposition includes non-spiking activity, for example graded potential neural activity as reviewed
by Juusola [52], and also the activity of non-neural cells such as Glial cells, which display sensory responses
although very slowly (due to their large capacitance) and even tuning, as shown by Sur et al [53]. Such Glial
activity can be conceived of as a component of consciousness, albeit a slowly-operating one. This proposition
of the electromagnetic nature of consciousness does not exclude chemical reactions. Bio-cellular signaling or
even metabolic chains are, from the physical point of view, biochemical instances of electromagnetism. For
example, Preat and colleagues showed the involvement of intracellular signaling in Drosophila behavior and longterm memory formation [54]. Genetic expressions and regulations are also electromagnetic processes, and their
impact on macroscospic electrical activity is further underlined by the fact that they are involved in the electrical
phenotypes, such as phasic or tonic, of neurons, as shown by Soden and colleagues [55]. As cited by Monod,
Wyman, Changeux in their work on allostery, ”It is certain that all bodies whatsoever, though they have no
sense, yet they have perception and whether a body be alterant or altered, evermore a perception precedeth
operation; for else all bodies would be alike to one another” (Francis Bacon, 1967, [56]). To give an example of
an information-theoretic treatment of such a cellular perception, chemotaxis, the chemically guided movement of
cells, can be looked at in terms of considering the mutual information between the input gradient and the spatial
distribution [57]. Such a view includes plants, as action potentials occur in most if not all plants [58]. How far in
the elementary organizations of matter is it possible to pursue the consideration of some elementary perception,
action and consciousness? What is an electrodynamic theory of consciousness at the elementary level? Consider
the simple Feynman diagram of elementary particle interaction included in Figure 2, representing the scattering
process X + Y → X 0 + Y 0 . As long as one only considers the empirical and observable considerations, that is, if
one takes a phenomenological point of view, it is legitimate to consider that the proton Y perceived the electron
X via the photon Z, with a ”reaction” of the proton leading it to Y 0 . Any signal received or propagated by our
nervous system is at the elementary level in this way and mediated by boson-like particles.
Psychophysical experiments can partially illustrate the establishing of such an elementary percept. Holmes
showed that humans can sense light flashes containing as few as three photons [60], and Tinsley and colleagues
showed that humans can detect a single-photon incident on the cornea with a probability significantly above
chance [59]. Elementary auditory perception was also studied by Bialek and Schweitzer, who established that the
sensitivity of ears can reach the limit dictated by the quantum uncertainty principle [61]. The conclusion of this
study is that the measurement apparatus, i.e. the receptor cell, operates in a condition analogous to a 0 Kelvin
6
Figure 2: a, Feynman diagram of an interaction between an electron X and a proton Y via the photon
Z, b A simplified illustration of the experimental set up for single photon detection in a human, constructed by
Tinsley and colleagues [59].
ground state which maintains quantum coherence. From a more biophysical perspective, single action quanta and
quantum formalism have been shown to be relevant to the model of the potassic ion channel selectivity filter that
generates important macroscopic patterns of electrophysiological activity in neurons [62]. From an experimental
point of view, it is clear that quantum effects are relevant to nervous system models and that attempts to model
with precision should take quantum formalism into account. Bohr originally gave a cognitive and biologic view of
quantum physics in his book ”Atomic Physics and Human Knowledge” [63], further highlighting that quantum
physics is not just a theory of physics, but also a theory of what one can objectively know about physics. Since
Bohr’s work, many works have proposed to examine consciousness and the nervous system on the basis of quantum entanglement and decoherence, or even quantum gravity principles, as in the celebrated works of Hameroff
and Penrose [64], which proposed a specific involvement of cytoskeletal microtubules. Penrose’s propositions [65]
fall within the bounds of the present framework from a physical point of view, while his biological proposition
involving microtubules, over-restrictive with respect to the current corpus of knowledge on the dynamics of the
nervous system, is extended here to the whole nervous system’s dynamic. Recent reviews of some results of the
application of quantum formalism to cognition can be found in the book of Busemeyer and Bruza [66] and in the
work of Khrennikov [67].
With regard to the question, ”Where is my mind?”, we conclude that biological studies have reported that
it can be found at all organizational scales and locations of the nervous system. To lead into the next section
on plasticity, computational models such as that of Fusi and Abbott [68] have proposed that the nervous system
adapts to its environment with a cascading of adaptive processes operating at different time scales, allowing it to
fill the gap between traditional short- and long-term memory formation. This multiplicity of scales has an important functional role in controlling the interplay between plasticity and stability-homeostasis (or metaplasticity)
as adapting processes operating at different scales. As a result, the nervous system can be seen as a constantly
adapting system with a range of plasticity and homeostatic processes operating at different scales of time and
space. Such a view explains why biological studies aiming to localize plasticity and memory in certain biological
structures (for example the synapse) or tissues (for example the hippocampus, often called ”the site of long-term
memory”) have found relevantly memory-forming process characterization in virtually all scales and all structures
of the nervous system. Open a randomly-chosen journal to a randomly-chosen page in a neuroscience library, and
you are likely to come upon a memory-plasticity-learning related paper. By this, we mean that the substrate of
memory in the nervous system can be and has been found virtually everywhere, from genetic expression, kinase
and/or calcium intracellular signaling cascades, the synaptic NMDA mechanism, to neuronal morphology including synaptic formation, cortical maps of areas remodeling etc. In electrodynamics, the formalism accounting for
such multi-scale dynamics is still accepted and is one of its core tenets: the renormalization theory, as reviewed
by Shirkov [69] and Huang [70]. The expression of renormalization in condensed statistical physics based on
Ising systems was achieved by Kadanov [71] and Wilson [72], who iteratively constructed Hamiltonians for each
scale by aggregating spins within ”short” scale distances into blocks. There exist classical versions of the renormalization group, already extensively used in complex system studies, and Dyson developed renormalization in
perturbation theory [73].
7
2.2.3
Neural coding - neural assemblies - synchrony - noise
This section investigates consciousness from a coding and engineering point of view and asks the question: what
is the code of consciousness? A quantitative, formal and typical approach to consciousness relies on investigating
how information is processed, stored and retrieved within the nervous system, a field generically known as neural
and sensory coding. In such a context, consciousness and information can be considered synonymous (more
precisely mutual-information as we will see). The word coding comes from the original engineering context of
information theory, and may not be appropriate since it suggests that there exists an external structure to decode
and gain access to the meaning of the information, which is equivalent to the homonculus problem. Barlow has
previously explained how to solve the homonculus problem using biological and probabilistic learning arguments
[74]. However, Bayesian statistical inference can be interpreted in terms of an ideal homonculus reading the
neural code (see Foldiack [75]), and we here consider the phenomenological principle that considers that what
reads the neural code are the structures that effectively receive the signal-responses of the system (the ”physical
observer” rather than an ideal one). In this sense, there is no need to consider such an external ’homonculus’
structure, or equivalently, one can consider that there are chains of homonculi. It is sufficient to consider that
the structure of the ”code” is its meaning and conveys its semantics, and we give an algebraic definitions of
structures in the mathematical section of the paper. In terms of information theory, there is no need to consider
another coding scheme than the random variables themselves, and we consider here a bijective coding function
from the codomain of the random variable to the alphabet. Put simply, the electrical message and its structure
are the code itself.
Cell assemblies, neural ensembles, synchrony and polyphony, cortical songs and beta-gamma
oscillations. The mainstream historical development of neuroscience has come to consider the nervous system as
an associative dynamic memory. This central role of associativity is probably further sustained in information
topology by the fact that the algebra of random variables and conditioning is fundamentally associative, and that
consciousness is the qualitative byproduct of the mnemonic activation and consolidation process. Hebb proposed
the principle of associative plasticity and learning [76] generating cell assemblies and providing the physiological
support of consciousness and memory. The theory was refined by Von der Malsburg [77] in his ”correlation theory
of brain function”, proposing that the correlate of cognition-consciousness lies in the patterns of neural activity
quantified by correlations, and that simultaneously activated nerve cells represent the basic internal objects.
This theory was further pursued from a computational perspective by the studies of synfire chains made by
Abeles [78], Diesmann, Gewaltig and Aertsen [79], examined experimentally from the perspective of the theory
of synchrony and binding by Singer, Gray and colleagues [80] and looked into via studies of cortical songs [81].
The basic hypothesis is that synchronization of neuronal discharges can serve for the integration of distributed
neurons into cell assemblies, and that this process may underlie the selection of perceptually and behaviorally
relevant information [82]. The consciousness aspect of the theory was further clarified by the observation that a
single external object stimulating the respective receptive fields of two disconnected neurons induced synchronous
oscillations in the 40-100Hz gamma range frequencies, the signature frequencies of attentional and waking states
[83]. The synchrony theory remains one of the simplest and deepest theories of consciousness, since synchrony
unavoidably provides a definition of the space-like subspace in space-time structures and also corresponds to
the ”stable invariant” subspace of coupled dynamical systems as notably emphasized in the work of Stewart and
Golubitsky [84, 85]. As we will see, homology theory provides a natural ground to define and distinguish patterns
and assemblies. Homology measures have been applied to characterize neural activity patterns and assemblies in
the work of Curto and Itskov [86] on hippocampal place cells, to examine persistence in visual activity by Singh
and colleagues [87], and in neural networks by Petri and colleagues [88]. As outlined in the mathematical and
appendix sections of the paper, homology is the standard and appropriated mathematical theory to formalize
what patterns may be. The main theory and applied measure to formalize and quantify those assemblies is
probability theory, e.g. Bayesian and information theory. The mathematical section provides an introduction to
those theories and underlines, following Kolmogorov [89] and Jaynes [90], that they are indeed a single theory. In
what follows, we will briefly review their application and biological meaning in neural coding, further justifying
their current status as qualitative theories of the brain (see for review Griffiths [91] and Friston [92] and references
therein).
Functional - black box approach The classical functional characterization of consciousness considers electrical activity as a function of stimulus. The process of consciousness is considered to be a function which consists
in the ”cross-correlation” or convolution of the stimulus with the neural response. Characterizing consciousness
by functions may appear an inappropriate approach that focuses too much on the final result. However, such an
interpretation of function is partial, and it is more relevant to consider functions from a mathematical perspective and instead highlight the ”dynamic” aspect of consciousness: a kind of relation between a domain and a
codomain (that assigns to any element of the domain a single element of the codomain, creating an ordered pair).
Function spaces provide very rich and diverse structures in mathematics, including Hilbert and Banach spaces,
and are usually classified according to topological criteria. As further discussed in the mathematical section,
information topology relies on an arguably general space of functions, the space of measurable functions, and
8
provides a characterization of its structure. In biology, these input-output functions provide a ”representation” or
a coding of the (perceived) stimulus on a given functional basis. From the biophysical point of view, this function
is usually characterized using the linear response theory, which studies the fluctuation and dissipation (i.e the
return to equilibrium) of a system following the external perturbation generated by the stimulus, as formalized
by Kubo and applied to neural responses by Stevens [93, 94]. From an engineering perspective, this function is
usually characterized using Volterra or Wiener’s kernels methods [95, 96, 97] using white noise as input. Figure
1 presents the impulsional response (first order linear kernel) obtained at different organizational scales of the
nervous system. At each of these scales, the higher order kernels, representing non-linear components or interactions in the system’s function, complete these linear functions. For example, at the ”network scale” of V1
responses, the linear kernel accounts for about 20% of the response at the spiking [98] and Vm level [41, 42]. A
diversity of biological mechanisms sustains the impulsional response at those different scales, which is extremely
different from the biological point of view, involving amino-acid steric interactions, synaptic processes, neural
passive and active integration processes, excitatory-inhibitory network processes etc. These approaches allow
the experimental characterization of memory stored and retrieved by nervous systems and linear and nonlinear
representations of elements of consciousness, also called receptive fields in the study of sensory coding at the
neuron level [44, 99, 100, 101]. Memory duration is the time taken by a system after a perturbation to go back
to its resting equilibrium state. Figure 1 clearly illustrates that memory duration increases as one goes from
fine to coarse scales of nervous system organization. A caveat of such an approach is that characterization with
impulsional noise rapidly becomes inefficient when functions become highly non-linear and are represented in
very high order kernels, as is the case when one studies sensory neurons with high cognitive functions, far from
low-level sensory areas.
Frequency (rate) and temporal code, from spike coding to Vm coding: The probabilistic functional
approach just reviewed can be used to investigate the code’s temporal precision. The book by Rieke and colleagues provides an introduction to spike coding [102]. The first, simple code to have been proposed was the rate
(or frequency) code, which simply observed that the rate of spiking discharge increases with stimulus intensity
[103]. The rate code postulates that information is transmitted by the rate of spiking. In practice, the variable
is the number of spikes within a time window, normalized by the duration of the window: rate = nspike /∆t (or
equivalently, the variable Xi can take Ni values of rate). It is possible to consider variations of the spike rate
using several consecutive time windows, each giving a variable Xi and altogether forming a stochastic process.
Temporal (or time or latency [104, 105]) coding postulates that information is transmitted by the precise time
of a spike. It corresponds to an instantaneous rate code, e.g the limit of the rate code when the duration of the
window tends to be small lim∆t→0 rate. There have been debates on whether nervous systems use spike time
or rate coding, together with studies of information as a function of the duration of the window-bin [102, 106].
Results of experiments show that the nervous system uses a temporal or rate code depending on the stimulus or
task; simple stimuli with low information content or relevance evoke rate codes while highly informative, complex
time-varying stimuli (for instance with high cognitive content), like natural conditions or stimulus the system has
learned, tend to evoke a temporally precise spiking code [107, 108, 109, 41, 42]. Synchrony and neural assembly
theory presuppose a temporally precise code for which precise temporal coincidence or phase relationships are
detected. The naturally fluctuating regime eliciting this temporal spiking code is illustrated in Figure 1.
However, consideration of a spiking code is just a rough simplifying approximation and assumption. Historically,
notably due to the vast prevalence of extracellular recordings and for simplicity, the coding unit-event of the nervous system has been considered to be the spike - what has been called spike coding, a binary code. It assumes
that spike waveform and initiation and synaptic transmission are all-or-nothing processes. Those assumptions
are very rough approximations. Information transmission in neurons is not all-or-nothing: spike waveform and
threshold vary significantly and further modulate synaptic transmission in an important part, if not all neurons.
As reviewed in Juusola [52] and Debanne, Zbili and colleagues [110, 111] and investigated by Simmons, de Ruyter
Von Steveninck [36, 112] and Rama and colleagues [113], effective information transmission in real nervous
systems is not a binary process and the entire membrane voltage codes. Moreover, spikes differ from
cell to cell and the diversity of spikes’ shapes and generating mechanisms, notably sustained by a diversity of
ionic channels as shown in the celebrated work of Sakmann [32], are well known to impact neural individual and
collective dynamics. Such realistic ”analog” coding goes hand in hand with an obvious increase in the considered
coding capacity of neural processes compared with digital approximation, an increase which is directly imposed
by the increase of the size of the coding alphabet. In practice, studies of graded synaptic transmission such as
those by de Ruyter Von Steveninck and Laughlin [112] report high information transmission rates (see also Borst
and Theunissen’s review [114]).
Turning away from the unrealistic assumption that the code is sustained by ideal impulsional spikes (i.e.
binary code) leads to the consideration of the more general electromagnetic ”Vm code”, which includes spiking
events.
Legend of Figure 3 : Temporal and rate coding with wavelet analysis in primary visual cortex;
9
Figure 3: Temporal and rate coding with wavelet analysis in the primary visual cortex; SNR
and mutual-information rate spectral estimation of spiking, Vm and electrocorticogram (ECoG)
responses. See legend 2.2.3.
Signal-to-Noise-Ratio (SNR) and mutual-information rate spectral estimation of spiking, Vm and
electro-corticogram (ECoG) responses. a, comparison of time-expanded epochs of the response of a V1
Simple cell and the simultaneously recorded V1 ECoG (bottom) to an optimal sinusoidal grating drifting at 2 Hz
(left) and to natural images animated by eye movements (right). Both epochs illustrate the periods of strongest
spike activation for the cell. From top to bottom: i) raster and frequency-time SNR analysis of the spiking
response; ii) Vm trials waveforms and SNR analysis. iii) single trial example of ECoG activity and the ECoG
time-frequency SNR analysis (2 seconds of spontaneous activity followed by 3 seconds of visual activation). b,
population analysis Comparison of the mean (across cells) average SNR power between various stimulus conditions including grating and natural conditions. From top to bottom: SNR spectra for spiking and subthreshold
Vm activity (n=12), and simultaneously recorded ECoG (n=10). Each bar below abscissa expresses the result
of a Wilcoxon paired test when comparing two stimuli’s conditions for each frequency (color code for A minus B,
white : A significantly higher than B; grey : A not significantly different from B; black : A significantly lower than
B, with p¡0.05). c, Temporal modulation of the informational flow of Vm and spiking responses. Comparison
of the temporal profile of the estimated mutual-information between Vm and spiking responses averaged across
cells for Drifting-grating and Natural Image with eye-movement (saccades are depicted by gray vertical bars).
The figure is adapted and modified with permission from [41, 42].
An adequate method for the study of time vs frequency code, avoiding the assumption of a spiking code, is
time-frequency wavelet decomposition (or time-energy in physic) [41, 42], illustrated in Figure 3 for intracellular
recordings and an electrocorticogram of V1 during stimulation with drifting grating (low qualitative content)
and natural image animated by eye-movement (high qualitative content). The Signal-to-Noise Ratio (SNR) in
time-frequency representation allows one to estimate the mutual-information transmission rate between the stim-
10
ulus and the recorded response at each time and frequency/rate under Gaussian approximations [41, 42]. Such a
method gives a rough estimate that overestimates mutual information. In drifting grating conditions, high SNR
values are restricted to a low-frequency band indicating a rate code, and the responses are highly variable from
trial to trial. In natural conditions, Vm and spiking responses are highly reproducible (low noise) with high SNR
located in high-frequency β −γ range spectrums and in a time band (see Baudot and colleagues [41, 42]), meaning
a temporally localized code and a temporal code. From this electromagnetic point of view, the spike itself is
indeed the signature of a temporally localized intermittent code, a fast process which is perhaps consciousness.
Note that whereas the spiking code is quite sparse in such conditions, the Vm code is very dense and reveals the
unceasing synaptic bombardment expected from a highly recurrent network, and hardly adheres to activity minimization constraints as proposed by Olshausen and Field [115]. Rather, it appears to dissipate free-energy very
efficiently in an ”efficient dissipation” [41]. The estimated mutual information, which in this simple two-variable
case is equal to the Integrated Information of Tononi and Edelman [1] (definitions are given in section 3.2.4) and
accordingly quantifies consciousness as regards to the stimulus, is low for the qualitatively low drifting grating
stimulus (except at its onset) and evokes EcoG close to resting states. Under natural conditions, the estimated
mutual information is higher and Vm conveys higher mutual information rates than the spike train (which can
be also interpreted in terms of a neuronal integration process). Such a study confirms the models of integrated
information, of temporal coding, and β − γ frequencies of consciousness. The study of cortical dynamics under
natural conditions was pioneered by Vinje and Gallant [116, 117], and the study on variability and coding in such
conditions was reported by Baudot and colleagues [41, 42, 118] and then by Butts and colleagues [119], Haider
and colleagues [120] and Herikstad and colleagues [121].
Population code Bayesian theory and information theory provide the basic quantification of populational
code. It consists in considering the multivariate case where each neuron corresponds to a variable or considering
more complex time-dependent generalizations (as in the work of Martignon [122]), hierarchical families of probability distributions as in the work of Amari [123], which considers higher order statistics of cell assemblies. For
example, Ma and colleagues developed probabilistic population codes [124] to infer the stimulus from a population activity. The general case of population coding is barely distinguishable from some of the current neural
network or machine learning approaches and are reviewed in the next section. The information topology sketched
in section 3.3.4 aims to characterize the structure according to the topological and informational criteria of such
multivariate cases.
Noise, spontaneous-ongoing activity, self and free-will : it is a leitmotif in biological and neuronal
studies to investigate the role of noise, whether it be an un-mastered or ”spontaneous” source of variability, and
to propose that such a non-deterministic source is responsible for phenomena like consciousness [125, 126], or
living principle, as in the work of Brown which looks for the ”vital forces” in living material [127]. Many studies
have been dedicated to the functional role of noise and have pointed out that noise is ”far from being a nuisance”
[128, 129]. Some have formalized noise, for example using stochastic resonance or self-organized criticality formalisms [130]. Control theory and the conceptualization of a channel of communication in information theory
has also made use of such an ad-hoc noise source [131], using the deterministic ”0 noise” formalism as a reference.
Intrinsic variability has a very important role in human cognition and consciousness, as it allows free-will to be
conceivable. As Ruelle remarked in his course on deterministic dynamical systems, critical-bifurcation points,
hyperbolic saddle points, are the only places where the choice is given and left possible (see [132] for a review
on this topic; see also the section of this paper on dynamical systems 3.4.3). Recurrent network formalization
using statistical physics, pioneered notably by Hopfield networks, introduced a new view on ongoing activity and
thermal noise, proposing that it corresponds to the autonomous generative capacity of consciousness, illustrated
in the context of the Helmholtz machine as accounting for the wake-sleep sequence and dreams [133], which
further gave a conceptual framework for the studies on ”cortical or hippocampal replay”. The probabilistic approach, as notably proposed by Ma and colleagues [124] and also in information topology (see the mathematical
section of this paper 3.3.4), generalizes the noise approach by considering biological and neural computation to
be intrinsically probabilistic: the deterministic case is no longer the reference but a peculiar limit subcase. In
such a view, any component of a (possibly nervous) system corresponds to a random variable, can be considered
as a signal and a noise source and can be both emitter and receiver. A variable or source without noise is deterministic and is the trivial constant ”0” information of an informational structure (cf. section 3.3.4): information
only sees what varies, so to speak. In a sense, such probabilistic studies describe the heterogeneous structures
of constitutive ongoing activity and the relative variations of ongoing activity. Indeed, the information topology
framework introduces a variational view of probability, which was also proposed by Friston [134]. Hence, the
probabilistic and informational view attributes not only consciousness but also free will to varying observables.
We believe it is the fundamental theoretical contribution of probability theory to cognition to allow free will to
exist and be an important constitutive part of the system’s dynamic.
As a quite consensual conclusion of this section on coding, in agreement with the current neuroscience theories,
the code implemented by the nervous system and which sustains consciousness is proposed to be an electromag-
11
netic and probabilistic code; both are consistent with regard to physics. However, it has not yet been established
that the expression of statistical physics implemented by information topology can also account for the standard
electrodynamic theory. This is a hope for the future which is left here as conjecture.
2.2.4
Psychophysics - Fechner and Gestalt’s heritage
In this section, we ask if qualia can be quantified and if it is possible to define the structure of qualia’s interactions
in order to provide a quantified Gestalt theory.
Quantum of qualia - adaptation: Measures of the nervous system’s electromagnetic activity are not sufficient
for a complete study of consciousness, as they have to study the ”correlation” of those measures with a subjective state-dynamic. Hence, a quantification of subjective states is required, meaning a definition of subjective
observable phenomena and an appropriate mathematical definition of ”correlation” need to be given. Such an
approach defines the entire domain of what is called psychophysics, or, more generally, experimental psychology,
wherein the definition of ”correlation” is usually the functional black-box approach just reviewed. The principles
of this domain were laid down by Fechner in 1860 [135]. Fechner’s main contribution has been what is known
as the Weber-Fechner law of adaptation, according to which sensation is proportional to the logarithm of the
stimulus (but see Mengoli’s 1670 work on the ”logarithmic ear” [136]):
S(x) = k ln
x
x0
(1)
where S(x) is the subjective magnitude of the sensation, x is the stimulus intensity and x0 the absolute threshold (the intensity at which the stimuli is no longer perceived). To derive this law, he introduced the concept
and measure of ”just-noticeable difference”, a quantization of the subject 40 years prior to the establishment of
quantum physics by Planck [137]. We now know that the ”just-noticeable difference” is the quantum of action
(cf. Figure 2). This law holds in all sensory modalities: vision (light intensity), hearing, taste, touch (weight
intensity), smell, but also time estimation [138]. It notably established the use of decibel units for auditory
signals. In crossmodal matching, it is replaced by Stevens’ power law [139] [140]. Poincaré gave a simple, pure,
and fundamental topological interpretation of Fechner’s law of perception that has been reproduced in the annex
of this paper A [5, 6]. Laughlin proposed a seminal mutual information maximization framework (infomax)
that accounts for Fechner’s law [141] in a biophysical adaptation context (cf. Figure 6a). Among other reports,
Kostala and Lansky went further and gave an information theoretic explanation of this law [142], and a fine
mathematical introduction with a topological perspective was proposed by Dzhafarov [143].
Gestalt - efficient coding theory: The Form and geometrical theory of consciousness go back at least to
antiquity, notably with Plato and Aristotle’s theory of Forms and their debates on its metaphysical or physical
nature [144, 145]. The idea, basic yet at the cutting edge of mathematical neuroscience, was captured by Riemann
in the citation given in this paper’s introduction 1. The theory of forms was developed was developed by the school
of Gestalt psychophysics, notably Köhler [146] and Wertheimer [147, 148], who provide elementary associative
laws of binding that govern the construction of complex perceptual forms from basic elementary shapes (cf.
Figure 4). This school was interested primarily in the relationships between objects and even considered that
relations form the object, which they summarized by their famous adage the whole is greater than the sum of
its parts. Wertheimer used the following example: we can perceive trees and not multiple different elements
of sensation. And most importantly, we see the same tree even when light conditions and perspective imply a
complete change of the elements in question. In other words, it is not the elements but the perceptual structures
that are fundamental; these so-called Gestalt qualities are collective mental phenomena. They proposed the
hypothesis of psychophysical isomorphism between environmental and brain processes and suggested that brain
processing consists in assembling parts into a coherent whole (for a review of this topic see [149]). Among the
perceptual laws they propounded, there are 3 or 4 elementary laws of binding and segmentation: proximity,
similarity, continuity, and sometimes closure (cf. Figure 4).
These laws of binding operate both in space and time; for example, in the temporal domain, the law of
continuity was called common fate. Of course, their definition lacked mathematical precision, but they have a
remarkable geometric and topological flavor. Moreover, the binding problem (generalization) is today considered
together with its dual segregation (discrimination - segmentation) task both in psychophysics and neuroscience.
The results of modern psychophysics are much more precise and complex. For example, Field et al [151] and
Polat and Sagi [152] gave a description of the spatial, orientation and contrast dependency of visual contour
integration, the so-called association field. Such results were investigated by Georges and colleagues in the spatiotemporal case, using tasks of speed estimation of various apparent motion configurations [153]. The principle
of dynamical space-time association field is depicted in Figure 5 a and e. The perceptive bias in speed estimation
for coherent Gestaltic configurations is represented in Figure 5 f.
12
Figure 4: Gestalt laws of elementary perception and Attneave’s cat. a Gestalt’s four elementary laws
of binding [146, 147, 148]. b, Attneave’s cat, redrawn from Atteneave’s 1954 paper [150]. The points of a
graphical drawing of a sleeping cat were chosen according to a maximal curvature criterion. To underline the
topological intuition behind this, we illustrated the binding of incoherent points into a coherent form by a
simplicial coboundary (differential) operator from a 0-complex of points to a 1-complex (i.e. the graph of the
cat. See the section 3.3.3 for a presentation of those topological objects).
Figure 5: Subjective speed of apparent motion and its neuronal substrate. See Legend 2.2.4.
The correspondence of such psychophysical experiments with electro-physiological activity has been reported
by several studies at all scales of the nervous system and with many kinds of recording methods. The converse
has also repeatedly been shown, starting with the experiments of Penfield [154]; electrical stimulation of single
neurons, as in the study of Salzman and colleagues [155], or of a neuronal population, can bias and modify
perceptions, as reviewed by Parker and Newsome [156] and Cicmil and Krug [157]. Here, we simply present
particular examples of single neuron recording results that provide the neural basis for the visual association
field. The work of Gilbert and Wiesel [158] and Schmidt and colleagues [159] provide the neural correlate and
mechanisms for the static psychophysical association field and support the view that the binding of visual contours
onto perceptually coherent objects involves long-range horizontal connections between V1 cortical neurons as
represented in Figure 5a.
Legend of Figure 5: qualitative perception of the speed of apparent motion and its neuronal
13
substrate. Center-surround directional selectivity for saccadic-like apparent motion and the temporal and SNR
modulation of the response of primary visual cortex neurons. a, Schematic representation of a visuo-oculomotor
model of V1 processing, sequentially integrating visual information along spatial long range (saccade) and short
range (fixational movement) eye-movements of coherent shapes (gestaltic). During saccadic high-speed longrange movement, V1 neurons, by means of their spatiotemporal association field, selectively integrate the visual
information iso-oriented to saccadic motion along their collinear axis (co-aligned with the motion path), whereas
during fixation they integrate the visual information on low spatial scales and at low speeds corresponding to their
classical direction selectivity (classical direction preference axis across the discharge field width). Furthermore,
the eye-movement scan-path is correlated to image features, notably the contours for saccades’ path in this image
exploration. The bottom cartoon is Yarbus’s original illustration [160] (1967) and illustrates the eye-movement
pattern of a human observer (right panel) along the corresponding photograph (left panel). b, an example of a
simple cell response to apparent motion stimuli (blue color) and center only control (green color), for low contrast center conditions, exemplifying a collinear surround facilitation. Picture in the middle represents the four
tested axis of apparent motion superimposed with the RF map obtained with sparse noise (ON responses in red
scale color, OFF responses in blue scale, depolarising field extent white line). Gabor patches were sequentially
flashed from the surroundings to the center. c, The biphasic temporal profile of center-surround apparent motion
nonlinearity, and its directional collinear selectivity and modulation by contrast (population analysis n = 23).
The temporal waveforms of nonlinearity are calculated for each cell by subtracting the linear predictor (Center
alone + surround alone responses) from the real response observed to the full apparent motion sequence, both
at the spiking levels (top panels) and at the Vm level (bottom panels). Here, we present the average cross-cell
temporal waveforms of nonlinearity expressed as a z-score of the spontaneous activity. The temporal profile
of the nonlinearity is given for the low contrast center (grey color) and the high contrast center (black color).
d, apparent motion nonlinear modulation of the SNR of the responses. To measure the center-surround SNR
modulation gain, each trial of the center alone condition are summed with those of the surround alone condition
to obtain a pool of linear predictor trials, on which we could apply the SNR time-frequency analysis. The timefrequency apparent motion nonlinear SNR gain is then obtained by subtracting the apparent motion SNR from
the linear predictor SNR, expressed as a z-score of spontaneous activity (significant threshold calculated independently for each frequency z-score p¿0.001), and averaged across cells (adapted and modified with permission from
Baudot [41]). e, the psychophysics experiment to quantify the bias in the perceived speed of apparent motion
relies notably on two stimuli : i) a reference spatio-temporal sequence with collinear Gabor patches (dynamic
Gestaltic association field configuration) and ii) a control sequence with parallel Gabor patches (non Gestaltic
configuration). f, The result of the perceived speed bias quantified by the subjective equality point (ratio of
comparison/reference speed) as a function of the speed of the stimuli or of the corresponding cortical speed.
The maximal bias, consisting in an overestimation of the speed for Gestaltic configurations, is found for speeds
in the range of saccades’ speeds and of horizontal propagation speed in the cortex (adapted and modified with
permission from Georges, Series, Fregnac and Lorenceau [153]).
The neural correlate of the dynamic association field sustaining the apparent motion percept has been investigated in the work of Chavane and colleagues,[161] Baudot and colleagues [41] and Gerard-Mercier and colleagues
[162], and is illustrated in Figure 5 which summarises most of the electrophysiological paradigms of consciousness: shapes and binding, temporal coding, βγ oscillations, ”feedback” and non-linearities (here we consider
feed-forward inhibition and lateral intracortical excitation as formal feedback from the cybernetic point of view),
active sensing (see next chapter) and reliability or mutual information (transient) increase. The space-time sequence of surrounding stimulation in a coherent gestaltic configuration, optimally fitted to recruit horizontal
cortical connectivity, improved the temporal precision of spiking responses, the SNR of Vm and spike responses,
βγ band activity, and decreased the latencies of the responses. As shown in Figure 5c, the non-linearities induced
by surround stimulation present a space-time profile in agreement with saccadic eye-movements’ kinematic characteristics and sustains the impulsional and reliable code. They exhibited a biphasic temporal profile resulting
from an excitatory-inhibitory temporal phase shift analog to what was observed in the auditory cortex and in
the olfactory bulb by Wehr and Zador [163] and Laurents team [164]. It hence underlines a generic cortical
(or cortical-like) mechanism for spike sparsening, temporal precision refining, and for the amplification of βγ
oscillations. Such studies also lay a path towards an answer to Olshausen and Field’s question, ”What are the
other 85% of V1 doing?”, [165] referring to the low explanatory power of the linear simple RF; the dynamic of eye
movement which is the major component in natural condition statistics and their adapted non-linear interactions
have been missing in classical studies. V1 neurons code for much more sophisticated space-time shapes than the
linear component displays.
Gestalt and efficient coding: The principle of efficient coding, that the goal of sensory perception is
to extract the redundancies and to find the most compressed representation of the data, was first stated by
Attneave in 1954 [150] followed by Barlow [166]. Attneave notably claimed that any kind of symmetry and
invariance are information redundancies and that Gestalt principles of perception can be defined in terms of
information. Attneave’s illustration of this principle is reproduced in Figure 4, in which his cat, drawn out of
14
only 38 ”informative” points, has an intuitive cohomological interpretation as a cochain complex (this illustration
is only included to facilitate intuitive understanding a la Attneave). We propose in the section mathematical
section of the paper 3 that homology is an adequate formalism both to achieve the assimilation of symmetries and
invariance as information quantities and to provide mathematical and even logical Gestalt laws of perception.
Such an idea is already present in essence in the work of Thom and Petitot on semiophysics, structural stability
and morphogenesis [167, 168, 169], although their presentation of the idea is rooted in probability and information
theory rather than catastrophes. Following the seminal work of Kendall [170] defining shape spaces, statistical
shape space analysis undertaken by Dryden and Mardia [171] and a series of works by Mumford and Michor [172],
a whole domain of statistical and informational investigation of shapes appeared, for example the pattern theory
of Mumford and Desolneux [173] among many other works in this active field. The relation or expression of
shape space analysis to information topology is not yet known and would require its generalization to continuous
symmetries.
2.3
Active consciousness - plasticity, adaptation homeostasis - Dynamic and persistence of qualia
2.3.1
Action-perception inseparability
In this section, we investigate how consciousness dynamics are related to action. Following James [174], Tononi
and Edelman proposed that consciousness is not a thing or a state, but a process or a flow fluctuating in time,
taking a quite continuous view of the subject. The model of Changeux-Dehaenne may seem opposed to such view
in the sense that it is ”discontinuous” and involves a transition from unconscious to conscious, two separate phases.
However, as claimed previously, such discontinuity should simply be considered a critical point between two
different ”conscious phases”, one being unaware of the other, a perspective which highlights the fact that taking
the diversity of consciousness into consideration renders these two theories quite indistinguishable. As illustrated
by the involvement of eye-movement in visual responses and coding in the previous section, consciousness is a
dynamic and active process. This central statement arises from the general action-perception conceptualization
of cognition in neuroscience (see Llinas [175], Berthoz [176, 177] and Jeannerod [178] for general introductions to
this subject), from the phenomenology of Merleau-Ponty [179] and active sensing in electrophysiological studies
[180]. The formalization of the action-perception paradigm was pioneered by the tensor networks model of
Llinas and Pellionisz [181]. A remarkably clear and relevant presentation of ”active consciousness” was given
by O’Reagan and Noe [182]. Borrowing their metaphor, conscious perception is like a blind man who scans his
environment with his cane to perceive its structure and extract its information. Visual qualitative perception
exemplifies this statement; our eyes continuously scan the environment by saccadic and fixational eye-movements
(drifts and tremors), as represented in Figure 5a. Whenever the eyes or the retinal image are artificially kept
immobile, the visual qualitative perception fades within hundreds of milliseconds (and the cortex goes back to
its spontaneously fluctuating ongoing states). It is misleading to consider such movement as unconscious (as
we do not see them or see our visual world moving with them) or even to think that a stabilizing process is
required to compensate them. As underlined by O’Reagan and Noe [182], they indeed construct our perception
and are an intrinsic, constitutive, necessary component of our conscious flow that constructs our subjective spacetime, further probing the integrative action-perception process. This is the striking conclusion, and also Piaget’s
opus [183, 184]: what we consider as external fixed reality, our perception of space and time, is a sophisticated
construction of our nervous system which learns spatial and temporal relations. Moreover, the inseparability of
action and perception has wide-ranging ramifications in physics, as can be seen from the fact that the duality
of Hamiltonian (perception-like) and Lagrangian (action-like) approaches are encompassed by the consideration
of the Legendre transformation. This inseparability of action and perception is a hallmark of the adaptive and
dynamic nature of consciousness, which is a perpetually adaptive process; we can go a step beyond the dynamical
nature of consciousness. Consciousness is variational by essence - what is constant, we are not conscious of; we
all have a blind spot corresponding to missing photoreceptor on the retina occupying an important part of our
visual field, but none of us have ever seen it. This brings to light the importance of the adaptive or learning
mechanisms in the nervous system that are the main topic of neuroscience and which we review in the next
section, in which we also introduce the thermodynamic and informational formalization of the process of learning
in consciousness.
2.3.2
Plasticity - (machine) learning - Informational and Statistical physic of consciousness dynamic
In this section we investigate the relation of the dynamics of our qualitative experience with the plasticity
of the nervous system and the way this is usually formalized. The formalization of plasticity, the dynamic
of consciousness, has formed the crossroads between information theory, statistical physics and data analysis
(machine learning). A basic principle ruling nervous system dynamics and learning was inferred by Hebb [76] in
what is now called the Hebbian rule of plasticity, stating that if a presynaptic cell X tends to repeatedly excite
15
and take part in the firing of a postsynaptic cell Y , then the efficiency of X on Y will be reinforced. It notably
found a biological verification in the study of Lømo and Bliss, who demonstrated Long Term Potentiation
(LTP) at the hippocampal synapses [185, 186]. The principle of efficient coding proposed by Attneave [150]
and Barlow [166] and restated in section 2.2.4 can be reformulated as an optimization problem, aiming to
maximize mutual information between the input and the output of a system that provides a decorrelated or
factorial, informationally efficient representation of the input, as illustrated in Figure 6 a,b,c. From the cognitive
point of view, the idea was resumed by Chaitin [187] and Grassberger (private communication, cf. Figure 6f):
”understanding is compression!”. This could also be stated as finding all the redundancies that characterize the
structure of the environment. Maguire and colleagues have constructed a whole theory of consciousness based
on such compression principles [188]. Linsker’s seminal work showed that the ”infomax principle” applied in
feed-forward linear networks is equivalent to considering that synaptic weights follow a Hebbian covariant rule
and achieve a certain kind of Principal Component Analysis (PCA), with neurons developing static oriented
simple-like receptive fields [189, 190] (cf. Figure 6e). On a biological side in 1981, Laughlin and Srinivasan
formulated the information maximization principle, showing that it implements predictive coding in vision and
gaining experimental control of the interneurons of the eyes of flies. [191, 141] (cf. Figure 6a). Nadal and Parga
[192, 193] and Bell and Sejnowski [194] further generalized the approach, showing that maximizing the mutual
information I(X; Y ) = H(Y )−H(Y /X) between the input X and output Y of a network (see figure 6 and legend),
imposing low noise or deterministic system conditions (H(Y /X) = 0), leads to redundancy reduction, a factorial
code that can be used to achieve Independent Component Analysis (ICA). In real neuroscientific experiments,
as shown in the column on variability in Figure 1, the effect of maximizing mutual information, at all scales of
nervous system organization (and reference therein), is to reduce the noise-variability of the responses and for
the system to become close to deterministic given the stimulus - what is usually called ’reliable’. This ensures a
consistency of consciousness, ensuring that two individuals experiencing the same environment will develop and
share the same conscious experience (and hence can communicate about it consistently). This fact is all the more
clear in the fMRI experiments of Hasson and colleagues, where the readings are taken from humans [47, 46]. In
simple terms, infomax accounts for the fact that our experiences can be shared, most notably human or animal
communication.
A historic breakthrough in learning theory, arguably the first in Artificial Intelligence (AI) after Turing, was
achieved by Hopfield in 1982 [197], who showed that an Ising system could be used to formalize the associative
memory learning of a fully recurrent network of binary neurons with the Hebbian plasticity principle (cf. Figure
6d). Ackley, Hinton and Sejnowski [196] generalized recurrent networks by considering neurons as random
variables and imposing the Markov Field condition, allowing the introduction of conditional independence and
the further construction of ”deep” network structures with hidden layers [199]. The result, the Boltzmann or
Helmholtz machine [133], relies on the maximum entropy or free energy minimization principle, and originally
relied on minimizing the relative entropy between the network and environmental states [196]. These studies
presented the first formalization of learning within statistical physics, explicitly in terms of entropy and free
energy functions, but also in terms of information functions. Friston et al introduced a variational Bayesian
formalization of the minimum free energy principle and proposed a theory of embodied perception based on it
[134]. Recently, the restricted Boltzmann machine, originally introduced by Smolensky in his Harmony theory
[200], found an enlightening reinterpretation through the variational renormalization group method, thanks to
the work of Mehta and Schwab [201]. Their results clarify the principles involved in deep networks, part of
the developments of which can appear alchemical [202], and further reinforce the electrodynamical nature of
consciousness.
The biological relevance of recurrent models and epigenetic generalization: Following the model
of convergence of thalamo-cortical connections on simple and complex cells proposed by Hubel and Wiesel [99],
recurrent models have been given the status of abstract models which are mostly relevant for artificial intelligence
and machine learning. However, following the work of Fregnac, intracellular studies, revealing synaptic excitatory,
inhibitory and neural integration, that is to say, electrical code, have revealed that this sparse convergence model
is highly misleading (see [203] and [204] for a review of this topic). Using Hebbian conditioning protocols,
Debanne and colleagues were able to turn simple cell responses into complex cell responses [205]. Orientation
selectivity was shown to arise from a diverse combination of excitatory-inhibitory cortical recurrence balances by
Monier and colleagues [206], and recordings in natural visual conditions of eye movements revealed very dense
Vm activity [203, 42], as shown in Figure 3 and 1 and quantified in [203]. Markov and colleagues were able to
quantify that the proportion of feed-forward connections in the visual cortex only represent few percent of the
full number [207]. Hence, what has been considered as artificial intelligence may be much closer to biologically
realistic computation, at least in principle: high cortical recurrence allows statistical computation and can provide
a robustness of cortical functions to single connection variability.
However, from a biological point of view, the picture painted by recurrent networks, with Hebbian or antiHebbian, LTP and LTD and instantaneous transmission is far too simplistic. As we saw in Figure 5, propagation
delays are part of computation, codes and percepts. Roxin and colleagues were able to show that reintroducing
conduction delays (space-time) in recurrent network model increases the multistability and richness of the phase
16
Figure 6: Statistical and informational models of learning-adaptation. a, the information maximization
principle (adapted and modified with permission from Laughlin [195], Nadal and Parga [192, 193] and Bell and
Sejnowski [194]): the stimulus or input X has a probability law P (X) (red). The system is modeled as a black box
with function Y = F (X) (invertible continuous deterministic [194], the cumulative of P (X) in [195], in purple)
and implements a gain control. The response or output of system Y , and its entropy H(Y ). The maximization
of mutual information I(X; Y ) = H(Y ) − H(Y /X) (b) between the input and the output comes to maximize
H(Y ) since the system is deterministic (H(Y /X) = 0), and hence removes the redundancy in Y or produces
”factorial” code that can be used for Independent Component Analysis (ICA), as depicted in c. d, an illustration
of a Hopfield network of 5 McCulloch and Pitt binary neurons or a Boltzmann Machine with 5 binary variables
(vertex of the graph); the edges of the graph represent the synaptic weights wi,j of the network’s connectivity
matrix. On the right is illustrated a 1-dimensional free-energy landscape with several minima learned by a
network; see Hopfield and Ackley et al for details [196][197]. e, the infomax self-organizing mutilayer network of
Linsker [190] that learns static, approximately realistic neuronal receptive fields. This seminal model, together
with multilayer perceptrons, can be understood as an effective informational version of Marr’s primal sketch
[198] and the precursor of current deep learning machines. f, The cognitive, very basic principle of redundancy
removal, expressed by Chaitin as ”understanding is compression!” . It is illustrated by the fact that humans can
extract a complex image from a very short linguistic representation (”a cat!”) in about 150ms [104].
diagram, with oscillatory bumps, traveling waves, lurching waves, standing waves (...) [208].Hebbian plasticity in
excitatory cortical and hippocampal neurons critically depends on the relative timing of pre- and post-synaptic
spikes as shown by Debanne and colleagues [209] and Bi and Poo [37]. This ”spike-timing dependent plasticity”
(STDP) with a Depression-Potentiation waveform is illustrated in Figure 1. Since those seminal studies, such
a waveform has been found to be highly dependent [210, 211] on i) developmental stage, ii) SNC region and
iii) neuromodulatory context, exhibiting waveforms with only depression or potentiation, or with DepressionPotentiation-Depression profiles. Graupner and Brunel proposed a model based on Calcium concentration to
account for such a modulation, for which each synapse has a fixed point ruling the balance between Potentiation
and Depression [212]. Such individual synapse dynamics further enrich the dynamic and memory stage capacity
of the whole network. As already highlighted in the electromagnetic view, the standard, mostly synaptic efficacy
view of learning introduced above should be completed by other plastic mechanisms, possibly at other scales,
such as morphological, developmental etc. Notably, current biological studies tend to show that developmental
mechanisms and learning processes are ”entangled” and form a continuum [213], yet they can consistently be
formalized into a general epigenetic adaptive formalism within an information topology framework, as proposed
in Baudot, Tapia and Goaillard [214]. Indeed, the electromagnetic proposition is blind to an a priori ontological
distinction between development and learning, and this epigenetic generalization simply consists of considering
”analog” (discrete in the first approximation) multivalued variables rather than binary variables, as discussed in
section 3.3.4 [214]. In this topological analysis we further introduce the idea that the total free energy function
is equivalent to the Integrated Information of Tononi and Edelman, but applied to genetic expression. Hence,
genetic regulation and differentiation are also components of our consciousness which could be assumed to be
17
slow components, given the ”impulsional” response characteristics of gene regulation mechanisms. According
to operon lactose kinetic studies the magnitude of typical time of the impulsional response of gene regulation
is of the order of several hours [215] (compare to Figure 1). Hence, we propose that such epigenetic plasticity
corresponds to modulation of our conscious experience on the scale of hours. Of course, such a slow process
could have a direct impact on fast neuronal electrophysiological dynamics, as previously stated (for an example
see Soden and colleagues [55]).
2.3.3
Homeostatic plasticity - consciousness invariance
The biological complexity of learning mechanisms and rules, requiring refined statistical and dynamical models
as just discussed, has introduced a key concept in biology and cybernetics [216]: homeostasis. Danchin used the
metaphor of the Delphic boat to illustrate the astonishing stability of biological structures and functions despite
their constant replacement of their constitutive components, and concluded that it is the relationships between
the ’planks’ (that is to say, the genome, the genes, for the nervous system, the neurons...) that define the boat
[217]. In terms of consciousness, such stability corresponds to the persistence of the self-being, the subjective I.
Marder and Goaillard’s review provides explicit electrophysiological examples of such persistence [218]. While
learning principles suggest changes in function and structure or a displacement of an equilibrium, homeostasis,
the other fundamental aspect of plasticity, also ubiquitous at all organizational scales, implies the maintenance
or regulation of the stability or equilibrium of the organism, or of some its sub-processes. Such a principle clearly
holds at the elementary level of atomic or sub-atomic structures: the atom stays the same while its electrons are
continually being exchanged, which further suggests that what we call ”self” is an energetic relational structure.
Biological studies have revealed that even what could be considered static and stable states are indeed maintained
by active processes, as illustrated by the invariance of electrical activity patterns in gene knockouts, as seen in
Swensen and Bean [219], or by neuronal size increase during development, as shown in Bucher and colleagues [220]
in Figure 7a,b. Note that the electrical activity pattern of lobsters’ pyloric systems expresses strong synchrony
and integrated information (although it has not been quantified), and hence should be considered as conscious
according to usual theories. A usual formalization of the relationship between homeostasis and learning involves
several scales of organization, as already underlined in Fusi and Abbott’s cascade model: fast adaptive-learning
models at small scales induce fast temporal fluctuations which are ”renormalized” or compensated for by a slow
homeostatic process at a large scale. For example, at the synaptic plasticity level, homeostasis is expressed as
a slow synaptic scaling process that keeps a neuron’s synapses’ efficacies in a ”stable” physiological range, as
studied in the work of Turrigiano and colleagues [221, 222]. This synaptic weight homeostasis is formalized as a
metaplasticity rule playing on the balance between potentiation and depression [223], that can be also accounted
for by the model of Graupner and Brunel just discussed [212]. In terms of information theory, the formalization
of invariance is straightforward, as it corresponds to the general definition of action invariance detailed in section
3.3.4 and appendix 3.4, that is a ”robustness to noise” or to any variation X, a very basic and typical definition
of invariance. For example, in the context of physiology, Woods and Wilson proposed that minimizing noise is
a key factor driving the evolution of homeostasis [224], and we simply relativize their proposition by defining
invariance as the minimization of ”shared noise”. Such a definition of invariance can be formally expressed as a
statistical independence requirement:
Invariance (definition): a system or process X is invariant with respect to the variations of a system or
process Y if conditioning by Y does not change the entropy of X, that is if H(X/Y ) = H(X), or equivalently
I(X; Y ) = 0, or equivalently if X and Y are mutually independent.
This definition of invariance appears more generally and intuitively in the fundamental chain rule of information (introduced and explained in the mathematical section of this paper 3.3.4): I(X1 ; .; Xk ; ..; Xn ) =
I(X1 ; .; X̂k ; ..; Xn ) − Xk .I(X1 ; .; X̂k ; ..; Xn ), where the hat denotes the omission of the variable. It can be read
literally as: the k + 1 dependencies quantify the default of invariance to the conditioning of a k dimensional
system. In the commutative setting presented here, we can see that such a definition of invariance is symmetric:
if X is invariant to Y , the converse also holds. In the appendix pertaining to the geometry of consciousness we
justify such a definition by the fundamental role of invariance in an action in geometry 3.4: it defines classically
a geometry, or a structural stability in topology, and there is hence not much choice in such a definition unless
mathematics radically changes. According to this definition, searching for the invariance of a system against
the variation of its environment is opposite to learning defined as the infomax principle: the first maximizes
independence, the second dependence. This basic principle of invariance is illustrated in Figure 7c. Crucially,
such study requires that the measures of juveniles and adults are made on the same identified neurons (in order
to obtain the joint distribution). In cases where the rhythm generated by neurons and the conductance patterns,
is invariant across development, the variability observed in the juvenile would be independent of the variability
observed in the adult. In cases where the rhythm generated by neurons depends on the developmental sequence,
the variability observed in the juvenile would be dependent on the variability observed in the adult, indicating
18
that a learning process occurred during development. In the latter case, the pattern has memorized something
from the environment, although the marginal variability in the juvenile and the adult may stay unchanged or
”identical”.
Figure 7: Principles of homeostasis and invariance: a, an example of homeostatic plasticity of bursts of
action potentials recorded from Purkinje cell in wild animals (N aV 1.6+/+ , purple) and in animals knocked out
for the sodium channel N aV 1.6 subunit (N aV 1.6−/− , blue). A transient application of TTX that blocks sodium
conductances eliminates the bursting pattern, revealing that a compensation occurred in KO animals to maintain
the burst pattern (adapted and modified from Swensen and Bean [219]). In such a case, the basic information
analysis presented here cannot be applied since the cases of the KO and the wild animals are exclusive and
do not provide a joint-distribution but rather two distinct probability laws. In such a case, the more general
relative entropy (Kulback-Leibler divergence) has to be applied. d, (top) drawing dye fills of identified pyloric
dilator (PD) neurons from a lobster (homarus americanus). (Bottom) Simultaneous intracellular recordings
from the PD, lateral pyloric (LP) and pyloric (PY) neurons in a juvenile and an adult preparation, showing
similar waveforms and motor patterns, despite the important change of size. Such invariance or independence
of the frequencies and relative phase of the patterns to the cell size imply the presence of an active mechanism
tuning capacitance (adapted and modified from Bucher, Prinz and Marder [220]). c, schematic data for the case
of invariance and dependence upon aging of the rhythm generated by neurons or a conductance pattern (see
text). d, Schematic data corresponding to 3 measured variables X1 , X2 , X3 of a system (e.g. 3 conductances of
neurons from c) are plotted, for the case of homeostatic process (top) and non homeostatic process (bottom),
for two measured populations represented by purple circles and blue squares (e.g. juvenile and adult). The
homeostatic case, which is proposed to correspond to the observed case in b; the two populations present the
same dependences and produce the same pattern of activity. A modification of the variable in this region does
not produce qualitative changes in behavior (purple arrow). The population variability is important as displayed
by the widely different values of all three variables for different neurons. Homeostatic tuning rules that maintain
a constant type or activity pattern can in principle beneficiate the broad range of variation of its variables to tune
the individual neurons. The study by Taylor et al [225] of conductances of a large database of model neurons and
by Tapia et al [226] and Baudot et al [214] of genetic expression reveal that neurons pertaining to the same type
are ”connected” in the data space. The bottom panel presents a case that would not be homeostatic, for which
the two populations would present distinct forms of dependences and would correspond to distinct clustered
patterns. Passing from one of these patterns to the other is conjectured to be associated with a qualitative
change in activity. (Adapted and modified with permission from Marder and Goaillard [218])
19
The definition of homeostasis is more refined than that of invariance just introduced. The general definition
considers homeostasis to be the maintenance or regulation of the stable condition of an organism or its equilibrium
[227]. It hence requires the introduction of a complex organism and of the concept of equilibrium or stability.
As illustrated in Marder and Goaillard [218], homeostasis refers to the invariance of a whole, possibly complex,
multi-dimensional pattern. According to this view, homeostasis is ”a consequence of the potential for compensation among components with different properties”, ”achieved simultaneously through overlapping functions and
compensation”. As illustrated in Figure 7, a homeostatic process preserves the structure of dependencies among
variables, and we propose to define it formally as follows:
Homeostasis (definition): a system or process X1 ; X2 ; ...; Xk is homeostatic with respect to the variations
of a system or process Xk+1 if conditioning by Xk+1 does not change the information of X1 ; X2 ; ...; Xk , that
is if I(X1 ; X2 ; ...; Xk ) = I(X1 ; X2 ; ...; Xk , Xk+1 ), or equivalently I(X1 ; X2 ; ...; Xk /Xk+1 ) = 0, or equivalently if
X1 ; X2 ; ...; Xk are conditionally independent given Xk+1 .
ck ; ...; Xk+1 ), literally,
This definition of homeostasis could also read I(X1 ; X2 ; ...; Xk ; ...; Xk ) = I(X1 ; X2 ; ...; X
c
that the removal of a variable Xk (noted Xk ) from the whole system or process does not change the information.
Homeostasis is stronger than invariance in the sense that invariance implies homeostasis but not the converse
(I(X; Y ) = 0 ⇒ I(X; Y /Z) = 0). In the section dedicated to information topology 3.3.4, we will see that this
definition is related to the usual definition of equilibrium in thermodynamics. Another way to quantify homeostasis that is less rigorous and general compares the mutual information I(X1 ; X2 ; ...; Xk ) with the probability
densities estimated in the points of the reference type (e.g. adult, or wild type, P ) and with all the points (Q):
an increase or constancy of mutual information, I(X1 ; X2 ; ...; Xk ; Q) ≥ I(X1 ; X2 ; ...; Xk ; P ), would indicate a
homeostatic process.
3
Mathematic, cognition and consciousness
3.1
Mathematical nature of consciousness
3.1.1
Empirical proof of the mathematical nature of consciousness: subjective axioms
In this section we ask if the language of consciousness could be mathematical. In the early stages of mathematical
formalization, Aristotle stated the principle of non-contradiction, now known as consistency. For simplicity, we
use this axiom: X ∧ ¬X = 0; or, literally, ”there is no proposition X such that X and ¬X”. A more formal
modern definition is: a set of formulas - a theory T in first-order logic - is consistent if there is no formula X such
that T ` X and T ` ¬X. Non-contradiction is still a fundamental principle in almost all mathematical theories
(some researchers having developed para-consistent logic, by which any theorem is true without requiring proof).
The original statement of Aristotle is ”it is impossible that contrary attributes should belong at the same time to
the same subject.” ([144], III.3). Aristotle’s formulation is both a cognitive principle and a mathematical axiom,
and it can be illustrated by a standard psychophysical experiment of perceptual bistability or multistability, as
portrayed in figure 8. We hence consider consistency as the first axiom of cognitive theory and propose that
experiences such as the one illustrated in Figure 8 provide empirical evidence for such a statement. Moreover,
we do not consider the excluded-third X ∧ ¬X (or excluded middle, which could also be expressed as ”for every
proposition X, either X or ¬X”) as an axiom or theorem of such a cognitive theory. The reason for this will
become more clear in the following sections, and this exclusion is in practice motivated by the fact that we require
a multivalued logic that corresponds intuitively to the usual conception of probability valuation. As illustrated
in Figure 8 and for example in the work of Suzuki and colleagues [228], stimuli and perception are possibly
multi-stable. The logical aspects of topos [229, 230], which we will briefly introduce in the next section, account
for this bistability and multistability by the fact that the internal logic of the subject perceiving that X or ¬X
does not negate the excluded third while the external observer will report that X has an intermediate truth
value, e.g. the probability that the observer saw X [228]. Brouwer noted that the excluded third is a kind of
”omniscient principle”, allowing one to prove X ∧ ¬X even in the case where X is Fermat’s Last Theorem [229].
Here, the excluded third is independent in constructive logic [229, 230]; it cannot be proved or disproved. These
two considerations lead us to propose that cognitive logic is constructive-intuitionist. In what follows we present
the modern expression and results of such a model, taking into consideration that a pertinent formalization of
perception is measure theory. Hence, we review what a constructive measure and probability could be.
Figure 8 illustrates the ongoing challenges in a mathematical theory of consciousness or cognition: a consistent
theory, for which every thought is true and non-trivial, yet one which encompasses the obvious multiplicity of
thoughts: a tolerant theory that allows for the construction of all subjective thoughts. What follows aims to
provide axioms and mathematical foundations for such a theory, notably accounting for Edelman and Tononi’s
model and quantification of cognition and consciousness, the integrated information theory (IIT) [237, 238, 1, 14].
Such foundations are the mathematical foundations of measure, integration and probability theory.
20
Figure 8: Consistency and diversity of the subject’s qualia, psychophysical evidence. a 3 paradigmatic
examples of bistable images and perception. From left to right, the Necker’s cube [231], Hill’s ”My wife and my
mother-in-law” [232], Rubin’s ”Face-Vase” [233]. b, The elementary dynamical bistable stimuli of apparent
motion designed by Ramachandran and Anstis [234] (reproduced with permission from Carter et al. [235]).
c, The energy landscape interpretation of the transition from one percept to another (adapted and modified
with permission from Fisher [236]). Right, the bistable case, left the multi-stable case designed by Suzuki and
colleagues as a tetra-stable stimulus [228] (reproduced with permission from Suzuki et al. [228]).
3.1.2
Mathematic, a model of cognition
Following Boole, some mathematicians have considered the logical foundations of mathematics and the logical
foundation of a theory of mind as equivalent problems. Cantor gave the following definition: ”a set is a gathering together into a whole of definite, distinct objects of our perception [Anschauung] or of our thought, which
are called elements of the set” [239]. As stated by one of its main conceivers, set theory is a cognitive theory.
Whitehead and Russel completed a work on the foundations of mathematics with the Principia Mathematica
[240]. Whithead went even further in the cognitive conception of mathematics, developing at length a theory of
perception in which any entity of the universe, even a particle, perceives, and considering events as elementary
constituents in place of masses. He stated: ”there is urgency in coming to see the world as a web of interrelated processes of which we are integral parts, so that all of our choices and actions have consequences for the
world around us” [241]. Frege developed a fully cognitive and linguistic interpretation of logic. In cognition,
it gave birth to the whole field of analytical philosophy of mind and language. Hilbert formulated the project
of arithmetization of mathematic, such that any theorem could be derived automatically, stated the isomorphism between the mind and logical calculus, and notably claimed ”My theory of demonstration only simulate
the internal activity of our understanding and record the proceedings of the rules that govern the functioning of
our thoughts”[242]. Gödel promptly discovered the theorems of completeness and incompleteness, creating an
obstruction to Hilbert’s program on the basis of ZFC axioms (a particular model of Arithmetic; using another
model such as Presburger arithmetic, for example, Gödel’s obstructions do not hold and the theory is complete)
and using an arithmetic coding procedure [243]. It is also such an equivalence that guided Turing in defining
computational classes and machines on cognitive reasoning principles [244]: ”computable numbers are those whose
decimals are calculable by finite means... the justification lies in the fact that the human memory is necessarily
limited”. Such an equivalence can be legitimated using the following reasoning inspired by Penrose [65], in which
the inclusion sequence is justified: cognition ⊆ physic ⊆ mathematic. This is a purely theoretical and classical
sequence; the complement of physics with mathematics is called metaphysics, and the complement of cognition
with physics is called in-animated matter. However, it is also possible to argue about the inverse inclusion short
sequence in practice: cognition ⊇ physic ⊇ mathematic. Mathematics and physics are subsets of human cognitive activities, and mathematics is a subset of activity pertaining to physics (since there are purely empirical
studies in physics, which are purely descriptive without theoretical, formal or modeling aspects). This gives a
reasonable basis for thinking that mathematics, physics and cognition are not so far from being equivalent, the
21
isomorphism postulated by Hilbert between the mind and logical calculus. Simply put, the conclusion is that
biological systems can be understood as ”living theorems” following the path of their proof (just as in Villani
[245]): mathematicians are not the only great geometers, so that any stone or insect can enter the monument
of academia, while still respecting the severe policy written at the entrance: ”Let no-one ignorant of geometry
enter”. It could be possible to construct a mathematical paradise that would not be a tiny room, but a grand
hotel, and to reconcile Hilbert’s formalism with Brouwer’s intuitionistic approach; the problem is to construct a
hotel such that it can safely, harmoniously and even comfortably welcome all its legitimate members. So let’s
try to give a free unlimited VIP pass to Hilbert’s paradise, and remind ourselves that there will be no queue or
competition to enter (we indeed start in what follows with very tiny elementary hotel).
Set theory is no longer considered a sufficient foundation for mathematics by an important segment of the
mathematical community; the theory of category has begun to replace it (see Mac Lane’s book [246] and Lawvere [247]). Here, for didactic and fluency purposes, we will mainly use the old, classical language of set theory,
although categorical formulations as preliminarily developed, for example in [248, 249, 2, 250], are more appropriate (and perhaps even necessary in order to fully legitimate the generalization of the boolean logic highlighted
here). Logic studies have made great improvements since set theory and Gödel’s work; most notably the introduction of and reference to a meta-logic can now be avoided, and logic has became contextual: a theorem
or statement is considered in the context of a given theory with its axioms [251]. To conclude this section,
consciousness is proposed to be by nature mathematical. One obvious reason for this is that mathematics is the
only scientific domain that can guarantee currently and consistently the unity required for a theory of consciousness, while physics and biology are commonly considered, with regard to one another, as divided and non-unified.
3.2
Constructive logic, information topos and e-motivs
This section asks the questions of what could be the mathematical axioms of a theory of consciousness, whether
any given thought can be conceived of as a theorem that can be derived from a set of axioms, and whether it
can be identified by its information. Rather than providing a complete definite theory, the results presented here
point out all the way left in order that we understand what information and consciousness is.
3.2.1
Measure Theory: a mathematical theory of subjective and objective experience-observation
This section investigates the mathematical axioms of a theory of consciousness as the axioms of measure and
probability, which would further avoid paradoxical decomposition induced by the Axiom of Choice.
Measure with countable choices, Quantified volumes of e-motion, consciousness integration,
constructive axioms of perception-action?
In 1854, Riemann defined the integral of a function as the asymptotic limit of the sums of areas of small
rectangles approximating the function [252]. With his method, a large class of derived functions had no definite
integral. Lebesgue in 1901 proposed a formalism such that integration operation could be the inverse of derivation
operation, that is, for any function f continuous on [a, b] and differentiable over ]a, b[, we have f (b) − f (a) =
Rb 0
f (x)dx. The work of Lebesgue [253] and Borel ([254] Chap III) also showed that their integration theory
a
relies on elementary and general definitions and axioms within set theory. In his lessons, Borel explicitly assigned
a measure to subsets of [0, 1] generated from the sub-intervals by the operations of countable unions or by taking
the complementary. Borel also explicitly stated that the measurement of these subsets (later termed ’measurable’
by Lebesgue) satisfies the additivity property: if Xn is a finite or countable family of such pairwise disjoint sets,
then the measure of their union is equal to the sum of their measures µ(X1 ∪ ... ∪ Xn ) = µ(X1 ) + .. + µ(Xn ).
Moreover, he claimed that the only measure a sub-interval has is its length. Borel proved the existence of such a
measure, and Lebesgue its uniqueness. Borel moreover stated that the measure of a set is always non-negative.
These axioms of measure provide a formal and reasonable basis for a theory of experimental measurement and
subjective observation, that is, for the properties one should reasonably expect of measures (data, experience)
in general. The mathematization of such subjective measures ensure their intersubjective communication and
understandability: to reliably share subjective perception with another subject, mathematics is the less ambiguous
language. The central axiom is additivity, known as extensivity in physics: for two non-intersecting sets X, Y we
have µ(X ∪Y ) = µ(X)+µ(Y ). Generally, for arbitrary, possibly S
intersectingP
sets, we have P
the inclusion-exclusion
n
n
principle: µ(X ∪ Y ) = µ(X) + µ(Y ) − µ(X ∩ Y ) and for n sets µ( i=1 Xi ) = i=1 (−1)i−1 I⊂[n];card(I)=i µ(XI ).
To properly formalize this in set theory, Borel and Lebesgue proposed operations that generate measurable sets,
of which there are two: countable union and taking the complementary. They define an algebra known as σalgebra (sigma here denoting additive), and its axioms are:
Let Ω be a given set and 2| Ω| be its power set. A subset F is then called a σ-algebra if it satisfies the following
three axioms:
• F is non-empty
22
• F is closed under complementation
• F is closed under countable union
From the 2nd and 3rd axioms, it follows that a σ-algebra is also closed under countable intersections, and one
can remark that in the finite Ω case it is also a Boolean algebra and a topological space. The axioms of a measure
are: let Ω be a set and a σ-algebra over Ω. A function µ from the extended real number line is called a measure
if it satisfies the following properties:
• ∀X ∈ F, µ(X) ≥ 0
• µ(∅) = 0
• Countable
S additivityP(or sigma-additivity): For all countable collections of Xi,i∈I of pairwise disjoint sets
in F: µ( i∈I Xi ) = i∈I µ(Xi ).
As a conclusion to this section, the importance of the axioms of measure arises from the fact that they are at
the foundations of mathematics and are an obvious minimal requirement for formalizing an observed quantity in
physics, as well as any objective or subjective measure, if a such distinction makes sense.
Just as for dynamical systems and physics, for which initial conditions can dictate the dynamic in the long run,
the axioms of a mathematical theory dictates what theorems are available within the theory. As exemplified
by the independent 5th axiom of Euclid, which hid the existence of non-euclidean geometries, Occam’s razor is
also a guiding principle in the choice of axioms: considering spurious, unnecessary axioms can lead to theories
being too restricted to account for peculiar physically-observed phenomena. What is worse, the axioms of a
theory can contain contradiction in their very germ. While modern model theory simply defines set theory by
an object, a set Ω together with an operation of inclusion ⊆, a classical construction of the theory of sets, relies
on Zermelo-Fraenkel axioms together with the Axiom of Choice (AC), forming the ZFC model [255]. The AC
roughly proposes that, given any, possibly infinite, collection of bins, each containing at least one object, it is
possible to make a selection of exactly one object from each bin, or equivalently, that any set may be well-ordered
(see Howard and Rubin for the various expressions of AC [256]). Fraenkel proved in 1922 the independence of AC
from a model/theory of set with atoms T (A) [257]. His proof, reproduced in the article of Bell [257] and further
generalized by Cohen using his forcing method (without use of atoms, and holding for real numbers), relies on
the fact that permutation of the set A of atoms induces a structure-preserving permutation, an automorphism,
of the Theory T (A) of sets built from A, allowing to construct an equivalent Symmetric model Sym(T ) of set
theory in which it is easy to prove that a set of mutually disjoint pairs of elements of A has no choice function.
The proof given by Fraenkel ensures that in a mathematical logic based on Galoisian group will not dispose of
the infinite choice axiom. The relation of the axiom of choice to intuitionist logic is straightforward: The axiom
of simple choice (a finite subcase of AC) is equivalent to the principle of excluded third, as shown in few lines
by Ageron [258]. The AC caused severe problems and debates, notably concerning measure theory, as it implies
the paradoxical existence of non-measurable sets, leading for example to the Banach-Tarski paradox [259]. This
paradox states that B 3 , the solid ball in R3 , is G3 -paradoxical: considering (countably) infinite choices, the ball
could be decomposed into a finite number of point sets and reassembled into two balls identical to the original, or
a new sphere of any size. The physical interpretation of the Banach-Tarski paradox allows matter, or indeed gold,
to be created ex nihilo [260], a first principle failure whenever one would wish to axiomatize thermodynamics in
logic (as we wish to do here). It is hence legitimate and usual to consider non-measurable set as metaphysical sets.
The important result was found by Diaconescu: he showed that AC implies the excluded-third [261] (see Bauer
for short proof [230]); hence, in this sense, the ZFC model is not constructive. Another equivalent expression
of the excluded-third is ”subsets of finite sets are finite”. If this statement seems at first glance reasonable, we
shall see that it imposes a notion of ”point” or ”atom” far stronger than Euclide’s definition that which has no
part and avoids, in a sense, any ”spatial extent” of a point or ”atom”. What would be a constructive (with
something like a finite choice version of AC) version of the decomposition proposed by Tarski, avoiding those
metaphysical sets? An answer arose from Dehn’s solution to Hilbert’s 3rd problem and is called dissection or
scissors congruence. Two polyhedra in Euclidean 3-space are scissors congruent if they can be subdivided into
the same finite number of smaller polyhedra such that each piece in the first polyhedron is congruent to one in
the second. For example, Bolyai-Gerwain’s theorem states that two polygons are scissors congruent if and only if
they have the same area. However, in higher dimensions, this theorem no longer holds, and one has to add Dehn’s
invariant. For instance, Dehn proved that a regular tetrahedron in R3 is not scissor congruent with a cube of
the same volume [262]. The Banach-Tarski paradox nevertheless states that they are equidecomposable. Hence,
Dehn’s finite dissections appear finer than Tarski’s infinite decomposition. This was formalised by Wagon, who
established that if two polygons are equidissectable, then they are equidecomposable [259]. Scissor congruences,
defining groups, were generalized to arbitrary dimensions and geometry, and their homology extensively studied,
notably by Dupont and Sah [263, 264]. The axiomatization and formalization of those groups was notably further
pursued by Denef and Loeser, in the domain known as motivic measure and integration, which explicitly provides
a field-independent measure of mathematical formula, a modern version of Leibniz’s analysis situs [265]. This
23
brief presentation of dissections and decompositions is sufficient to conclude that consideration of AC implicitly
involves the inability to distinguish elementary distinct geometrical objects that finite dissections discern. A
possible way to circumvent the problems raised by AC is to consider the cheap nonstandard analysis obtained by
the consideration of the Frechet filter, as explicated by Tao [266]. Another possible way to give a more precise
axiomatization for a cognitive theory without non-measurable sets is to follow Solovay’s work [267]. In Solovay’s
construction, that is, classical Zermelo-Fraenkel axioms with Dependent Choice (DC, countable-finite weakening
of the axiom of choice) and the existence of an inaccessible cardinal IC, any set is measurable. His axioms provide
a construction of ”real” numbers, called ”random reals” which are in bijection with additive homomorphisms.
This is, in our opinion, one of last and greatest achievements in Hilbert’s arithmetization program.
To conclude, even at the elementary level of the logical axiomatization of a mathematical theory, the formalization
of what kind of decomposition-dissection-division is allowed appears crucial, and a slight change in the axiom,
e.g. from AC to DC, can avoid important ”complications” that appear paradoxical from the physical point of
view.at least from basic physical principles. Arithmetic and number theory provide the guiding principle for such
a division procedure.
3.2.2
Probability, the logic of thoughts, the geometry of beliefs
Measure theory allowed the Kolmogorov’s axiomatization of probability [268]. Considering probability theory as
a cognitive theory has been an obvious option since the early stages of probability theory. The title of Boole’s
major opus is sufficiently explicit to illustrate our statement: ”An Investigation of the Laws of Thought on Which
are Founded the Mathematical Theories of Logic and Probabilities” [269]. His work also provided the basis for the
development of information theory, as exposed in the book by Nahin [270], and Boole should hence be considered
one of the important founders of the theory of consciousness and cognition. Boole’s original text is sufficiently
limpid for there to be no need of commenting it, and as such we simply cite it in the present work ([269] Chap.
III, Derivation of the laws of the operations of the Human mind):
• Proposition 1: To deduce the laws of the symbols of logic from a consideration of those operations of the
mind which are implied in the strict use of language as an instrument of reasoning.
• Proposition 2: To determine the logical value and signifiance of the symbol 0 and 1. [...] The Symbol 0,
as used in algebra, satisfies the following law,0 × y = 0 or 0y = 0, whatever number y may represent. [...]
Secondly, the Symbol 1 satisfies in the system of numbers the following law, 1*y=y, or 1y=y, whatever
number y may represent. [...] Hence, the respective interpretation of the symbols 0 and 1 in the system of
Logic are nothing and Universe.
• Proposition 3: If X represent any class of objects, then will 1 − X represent the contrary or supplementary
class of objects, i.e. the class including all objects which are not comprehended in the class X.
• Proposition 4: The axiom of metaphysicians which is termed the principle of contradiction, and which
affirms that it is impossible for any being to possess a quality, and at the same time not to possess it,
is a consequence of the fundamental law of thought, whose expression is: X 2 = X . Whence we have
X.(1 − X) = 0. Both these transformations being justified by the axiomatic laws of combination and
transposition (II.13). Let us, for simplicity of conception, give to the symbol X the particular interpretation
of ”men”, then 1 − X will represent the class of ”not-men” (prop III.). Now the formal product of the
expressions of the two classes represents that class of individuals which is common to them both (II.6).
Hence X.(1 − X) will represent the class whose members are at once ”men” and ”not men”, and the
equation (2) thus express the principle, that a class whose members are at the same time men and not men
does not exist. In other words, that it is impossible for the same individual to be at the same time a man
and not a man [...] which is identically that principle of contradiction which Aristotle has described as the
fundamental axiom of all philosophy.
This ”law of duality”, or principle of non-contradiction, here made algebraic, will henceforth be called the
idempotence property of a composition law. We will see that, like the join and meet of probability of events
(P (X ∨ X) = P (X) and P (X ∧ X) = P (X)), joint of random variables and partitions is idempotent. After
Boole, Hume founded cognitive sciences in his treatise on human nature by notably stating that ”all knowledge
degenerates into probability” [271], and since Leibniz had established binary calculus and monads, the probability
theory of cognition demonstrated an impressive robustness. More than one and a half centuries after Boole, a
long list of works and articles still propose that probabilistic or Bayesian theory is the relevant formalism for a
theory of the brain (for a review on this topic see Griffiths [91], Friston [92] and the references therein). The
question of what probability is, its axiomatization, and the foundations of cognition are investigated in depth in
a series of works by Gromov, which partially motivated the work presented here [272, 273, 274, 275].
Kolmogorov based his axioms of probability on the Lebesgue measure, and it is these axioms that we here
consider as still pertinent for a consciousness-cognitive theory; hence we faithfully reproduce his axiomatization
24
(with the exception of the symbols of joint and meet probability, which have been changed such that they are
consistent with the preceding logical notations [268]): ”Let Ω be a collection of elements ξ, η, ζ, ..., which we shall
call elementary events, and F a set of subsets of Ω; the elements of the set F will be called random events.
• F is a field of sets.
• F contains the set Ω.
• To each set A in is assigned a non-negative real number P (A). This number P (A) is called the probability
of an event A.
• P (Ω) = 1
• If A and B have no element in common, then P (A ∨ B) = P (A) + P (B)
A system of sets F, together with a definite assignment of numbers P (A), satisfying axioms 1-5, is called
a field of probability. Conditional probability: If P (A) > 0 , then the quotient P (B/A) = P (A ∧ B)/P (A) is
defined to be the conditional probability of the event B under the condition A”[268].
Three remarks can be drawn from his axiomatization:
• Forgetting the 4th axiom (P (Ω) = 1), we obtain the preceding axioms of measure; hence, a probability is
a normalized measure such that the total measure is a unit.
• Probability and randomness are simply the definition of an abstract geometric volume in arbitrary space
and rely on additivity: there is nothing more ”deterministic” in common sense than a geometric volume of
space and addition; the usual opposition between common notions of determinism and non-determinism fails
(while the formal definition of determinism as events with a probability of 1 or 0 stays consistent). Notably,
famous statements in physics of the kind god does not play dice [276, 277], where ”god” is considered as
an abbreviation for the ”geometry of space-time”, could be interpreted as meaning that space-time has no
volume, which is a nonsense.
• As stated by Kolmogorov, these axioms of finite-discrete probabilities, which are usually handled as empiric
probability, the ratio n/m in the discrete rational case, define the ”generalized fields of probability”.
To handle continuous probabilities a 6th axiom of ”infinite” is required (just as in set theory according to
Bourbaki [278]). We note that, as Kolmogorov, who was one of the main founders of constructive logic,
probably wished, the discrete rational empirical ”generalized fields of probability” respects constructive
requirements (as no infinite choice is required), while in the case of real-valued probabilities, it depends on
the precise construction of real numbers (the field being constructed using Solovay’s model and random
reals to fulfill our measurability completeness requirements).
One of the remarkable aspects of Kolmogorov’s axiomatization is that it has a direct and simple geometrical
expression, usually named the probability simplex. Although the origin of the probability simplex is unknown
to us, it has been in a part of mathematical folklore for a long time; in 1855, Maxwell constructed the simplex
of colors in his study ”Experiments on Colour as Perceived by the Eye, with Remarks on Colour-Blindness”
[279] (he also claimed ”the true logic of this world is the calculus of probabilities”). As an additional example,,
a more modern version of a probability simplex was presented and used extensively in 1982 in Cencov’s seminal
work [280]. A simplex is defined as the set of families of the numbers Pω , ω ∈ Ω, such that ∀ω, 0 ≤ Pω ≤ 1.
It parameterizes all probability laws on ω. In more explicit geometrical terms, the fourth and fifth axioms of
probability are equivalent to imposing that geometry is affine, and the axiom of positivity (axiom 3) dictates that
it is convex. The more general expression of conditional probability using projective space is studied in Morton
[281]. This is depicted in figure 9 for a 2 and 3-simplex of probability. Notably, the theorem of total probability
[268] states that given elementary events A1 ∪...∪An = Ω, we have P (X) = P (A1 ).PA1 (X)+...+P (An ).PAn (X),
allowing the consideration of {P (A1 ), ..., P (An )} as the set of barycentric coordinates of the probability P (X)
in the (n − 1)-dimensional simplex. It is possible to construct a subcomplex of these probability simplexes by a
process of exclusion of faces, utilising an exclusion rule, that traduces the cancellations of a probability [2]. An
example of 1-complex and 2-complex of probability, together with their associated set of exclusion rules, is given
in figure 9. Conditioning by elementary events is a projection on the complement (n−2)-subsimplex (the opposite
(n − 2)-face) and is associative, as shown in figure 9. Addition of priors usually consists of selecting a subspace of
the (n − 1)-simplex by imposing arbitrarily complex functional constraints on the elementary probabilities. This
geometrical formalization of probability is not the geometry of the space itself, but the geometry of the volumes
within the space.
25
Figure 9: The geometry of probability. a, examples of a 2-simplex and a 3-simplex probability together
with their associated Boolean complete lattices (or σ-algebra, bottom). A sample space of n atomic events
{A0 , .., An−1 } defines a (n − 1)-simplex of probability. A probability P (X) lies in the convex hull depicted
in blue which is the (n − 1)-simplex with a vertex at the units of Rn (more exactly R⊗k n ). (Left) The
example of a 2-simplex ∆2 which can be illustrated by a coin toss possibly biased but with the coin having three faces, with a sample space composed of 3 atomic-elementary events ”face0” (f ace0 = A0 ), ”face1”
(f ace1 = A1 ) and ”face2” (f ace2 = A2 ), and Ω = {A0 , A1 , A2 }, the σ-algebra considered in the finite context as a Boolean algebra BΩ of all possible, not necessarily atomic-elementary outcomes, is F = BΩ =
{∅, {A0 }, {A1 }, {A2 }, {A0 , A1 }, {A0 , A2 }, {A1 , A2 }, {A0 , A1 , A2 }}. The probability P (X) is given by the theorem of total probability P (X) = P (A0 ).PA0 (X) + P (A1 ).PA1 (X) + P (A2 ).PA2 (X) where P (Ai ), i ∈ 0, .., n − 1
Pn−1
provides barycentric coordinates, since we have i=0 P (Ai ) = 1. For the 3-simplex, there are 4 possible outcomes (right). b, Examples of a 1-complex and a 2-complex constructed as a sub-complex of the previous simplex
with their lattice. The exclusion rule that generates the 1-complex is P (A0 ) = 0 ∨ P (A1 ) = 0. c, Conditioning is
the projection on the lower dimensional opposite (n − 2)-subface of the simplex. Rigorously, the conditioning follows the inverse path of the simplicial projections; in the example from PA3 (X) to PA3 ∨A0 (X) to PA2 ∨A3 ∨A0 (X)
to P (X) = PΩ (X) = PA0 ∨A1 ∨A2 ∨A3 (X). d, Example of adding a prior, here the elementary constant function
P (A2 ) = 1/3 in the 3-simplex.
3.2.3
Topos: the consistent diversity of truths and beliefs
In this section we ask what a probabilistic and informational logic could be in practice.
Multivalued logic and probability. Since Kolmogorov, the axiomatization of probability has been repeatedly questioned, something which has been motivated by the idea that the logic implemented by biological
or cognitive calculus could differ from classical logic. There have been many attempts to propose alternatives
to Boole’s original work on logic and probability [269] and Kolmogorov’s work [268], for example the definition
of a peculiar set of Bayesian axioms and logic that gives a fundamental role to Bayesian sum and product rules
following Cox and Jaynes’s work [282, 283], or fuzzy logic [284, 285, 286]. The basic motivation guiding such
research is that, where classical Boolean logic and set theory admits only two valuations, ”true” or ”false”, probability theory provides an obvious multivalued logic. In a series of works based on Lattice theory and pointing
out the relation to factorization in number theory, Knuth proposed to derive the basic principles of probability
and information accounting for Cox and Kolmogorov foundations [287, 288]. The principles proposed by Knuth
are basically the same as what is presented in this review that underlines a more usual mathematical expression.
Carathéodory and Kappos proposed an alternative, indeed equivalent axiomatisation, but one that is more directly along the lines of intuitionistic logic, which according to Cartier [289] postulated: instead of requiring the
valuation v(A) of a proposition to assume only the values 0 and 1, one may postulate more generally that v(A)
is a real number between 0 and 1.. With the aim of providing foundations for Laplacian or Bayesian probability,
26
Cox proposed three desiderata-axioms [282]:
• representations of plausibility are to be given by real numbers
• plausibilities are to be in qualitative agreement with common sense
• plausibilities are to be consistent, in the sense that anyone with the same information would assign the
same real numbers to the plausibilities.
As far as we understand these desiderata, they appear consistent in all points with Kolmogorov’s axioms (but
their ”fuzziness” does not allow the proving or the disproving of any equivalence), leading to the conclusion
that subjective vs. objective, Bayesian vs. frequentist probability, at least at the axiomatic level, are simply
two different interpretations of a single theory: probability. While the Bayesian interpretation remains relevant
concerning the theory of mind, this identity enriches the Bayesian interpretation by underlining its obvious pertinence in the domains of physics and empirical science.
Topos: a bridge between the subject and the object (’objectifies the subjective’ Lawvere [290]).
The multivaluation of logic found its main mathematical expression in the construction of topos theory. Topos
were developed by Grothendieck, Verdier and Giraud [291], predominantly on the geometrical ground of sheaves.
Grothendieck resumed this work in the following terms: ”This is the theme of the topos which is the ”bed” where
come to marry geometry and algebra, topology, and arithmetic, mathematical logic and category theory, the world
of the continuum and the one of ”discontinuous” or ”discrete” structures. It is the largest construction I have
designed to handle subtly, with the same language rich geometric resonances, a common ”essence” to some of
the most distant situations.” [292] (p.59). A simple introduction to ambiguity and Topos, with some cognitive
aspects, can be found in André’s book [293] (chap.1).
The logical aspects of topos and the fact that it provides an algebraic logic were notably recognized in the work
of Lawvere and Tierney (see [290] for a review of this topic). This logical view provides a quite simple definition
of a Topos: a ”category with a power set”. According to Reyes [294], the analogy that has been constructed
identifies:
Topos Theory
Model Theory
Site
Theory
Fiber (on the site)
Model (on the theory)
Sheaf
Concept (represented by a formula)
A topos T is a category with the 3 axioms [295, 261]:
• T has finite limits, i.e. finite products, intersections and a terminal object 1.
true
m
• T has a universal monomorphism I −−→ Ω, i.e. for any monomorphism of T , A0 −→ A there exists a unique
characteristic function such that the following diagram is a pull-back:
/1
A0
m
A
true
χm
/Ω
• T has for each object X its power set ΩA ; this is characterized by the fact that the morphisms X → ΩA
are precisely the subobjects of X × A. In particular, its global sections 1 → ΩA are the subobjects of A.
Stated in more homological terms, let C, E be two categories. A topos T (C; E) of E-valued pre-sheaves on C
is the set of contra-variant functors from C to E that forms the set of objects of a category whose arrows are the
natural transformations. A category C embeds naturally in this topos if we associate the functor Y → C(Y, X)
to X. This definition is sufficient in a finite context, since for discrete topology that provides a discrete site,
every pre-sheaf is a sheaf. The complete notion of topos asks for a Grothendieck topology on a category and
considers pre-sheaves [291]. The three most common examples of topos are categories of sets, categories of
functors T (C op ) for any small category C and categories of sheaves on topological spaces. The generalization
of topos with respect to usual set theory can be seen from the fact that the topos of sets are topos with two
values of truth and the axiom of choice [290]. Moreover, a topos satisfying AC is Boolean ([296]. One of the
main consequences of the axioms of Topos is that the structure that generalizes the truth tables is a Heyting
algebra, a constructive generalization of Boolean algebra. Heyting algebra replaces the Boolean complement by
a constructive pseudo-complement. A Heyting algebra H is a bounded lattice such that for all X and Y in H
there is a greatest element Z of H such that:
X ∧Z ≤Y
27
(2)
The element Z is called the relative pseudo-complement of X with respect to Y and is denoted X → Y . The
pseudo-complement of any element X, noted with the negation ¬X, is defined as ¬X = X → 0 (this definition
of negation implements the fundamental principle of non-contradiction). A pseudo-complement ¬X is a complement X̄ if X ∧ ¬X = 0 and X ∨ ¬X = 1. A Boolean algebra is a Heyting algebra in which for all elements Y we
have the equality (¬Y ∨Z) = (Y ⇒ Z). The lattice of an open set of a topological space is a typical example [261].
Probability multivalued logic. Doering and Isham [297] proposed to provide a foundation of physics based
on topos theory, and further developed a framework to interpret both quantum and classical probabilities with
a multivalued logic [298]. Independently and with a different construction, Baudot, Bennequin and Vigneaux
proposed information topos on the (pre)-sheaf (site) of probabilities where conditioning provides the arrows
[299, 2, 250] (the two constructions were respectively introduced to each other and presented at the conferences
”Categories and Physics 2011” in Paris). It is possible to illustrate the multiple truth values logic of probability
in some simple elementary examples which further underline that where set theory could be considered a deterministic theory, topos theory may be conceived as a non-deterministic extension of it. Probability values are
taken as valuations or truth-values. Simpson developed the general case where every measure is considered as
a σ-continuous valuation [300]. It means that the usual boolean tables for meet and join are replaced by their
homolog in probability which is continuous (for real-valued probability), a long table of a continuum of truths,
instead of binary. To obtain some understandable elementary examples, we need to introduce integer partitions
and consider a rational field of probability, such that probabilities take values in the rational numbers Q and are
given by the basic and usual empirical ratio n/m, as described by Kolmogorov (cf. Tapia and colleagues [301]
and Baudot and colleagues [214]). First we recall the usual Boolean operator tables, of the operators joint and
meet, for example:
X Y X ∧Y
X Y X ∨Y
> >
>
> >
>
> ⊥
⊥
> ⊥
>
⊥ >
⊥
⊥ >
>
⊥ ⊥
⊥
⊥ ⊥
⊥
We rewrite those tables with 0 replacing ⊥ (contradiction, ”false”) and 1 replacing > (tautology, ”true”) in a
matricial form, giving us:
P (X ∨ Y ) P (X) = 0 P (X) = 1
P (X ∧ Y ) P (X) = 0 P (X) = 1
P (Y ) = 0
0
1
P (Y ) = 0
0
0
P (Y ) = 1
1
1
P (Y ) = 1
0
1
Such logic is a finite deterministic case of logic, which in terms of probability follows a finite 0-1 law, the
smallest probability field with two elements E and ∅ described by Kolmogorov which corresponds in what follows
to the case m = 2 with its singleton partition {2}. For non-deterministic probability logic, a truth table is given
for each integer partition of m, the integer number of observations (also called repetitions, trials, sample size).
In the following example of ∨ and ∧ operator tables, we consider m = 2 and m = 3 and the integer partition of
2 {1, 1} and the integer partition of 3 {1, 2}, such that we have 1/2 + 1/2 = 1 and 1/3 + 2/3 = 1 respectively.
For m = 2 = 1 + 1, we have:
P (X ∨ Y )
P (X) = 0 P (X) = 1/2 P (X) = 1/2 P (X) = 1
P (Y ) = 0
0
1/2
1/2
1
P (Y ) = 1/2
1/2
1/2
1/2
1
P (Y ) = 1/2
1/2
1/2
1/2
1
P (Y ) = 1
1
1
1
1
P (X ∧ Y )
P (X) = 0 P (X) = 1/2 P (X) = 1/2 P (X) = 1
P (Y ) = 0
0
0
0
0
P (Y ) = 1/2
0
1/2
1/2
1/2
P (Y ) = 1/2
0
1/2
1/2
1/2
P (Y ) = 1
0
1/2
1/2
1
Figure 10: Examples of probability integer partition. a, the case m = 2 = 1 + 1, representation in data
space of two variables X, Y (left), and the associated Young diagram (right). b, the case m = 3 = 1 + 2. c, the
case m = 4 = 1 + 1 + 2.
28
For m = 3 = 1 + 2, we have:
P (X ∨ Y )
P (X) = 0 P (X) = 1/3 P (X) = 2/3 P (X) = 1
P (Y ) = 0
0
1/3
2/3
1
P (Y ) = 1/3
1/3
1/3
2/3
1
P (Y ) = 2/3
2/3
2/3
2/3
1
P (Y ) = 1
1
1
1
1
P (X ∧ Y )
P (X) = 0 P (X) = 1/3 P (X) = 2/3 P (X) = 1
P (Y ) = 0
0
0
0
0
P (Y ) = 1/3
0
1/3
1/3
1/3
P (Y ) = 2/3
0
1/3
2/3
2/3
P (Y ) = 1
0
1/3
2/3
1
More rigorous and extended notations should be P (X = ai ) = 1/3 instead of the abbreviate P (X) = 1/3,
underlining the necessary introduction of random variables, also called observables, in the theory (see [299, 2,
250, 2, 301]; philosophically this assumes that there is no probability without an observer). An introduction to
the world of partitions can be found in the work of Stanley [302] and Andrews [303, 304] and MacDonnald’s book
[305]. These tables correspond to the usual joint and meet for events; notably, they obey the inclusion-exclusion
theorem P (X ∨Y ) = P (X)+P (Y )−P (X ∧Y ). From a logical point of view they correspond to usual multivalued
Gm logic as introduced by Gödel for which P (X ∨ Y ) = max({P (X), P (Y )} and P (X ∧ Y ) = min({P (X), P (Y )}
[306] (see Gottwald for a review of many-valued logic [307] and other operators). The generalization to more
than 2 random variable multivariate cases can be achieved via tensorial logical tables. In general, we have the
following theorem:
Theorem 1 (correspondence between integer partition and logical tables). Let (Ω, F, P ) be a finite
probability space where P is a finite (empirical) probability measure with sample size m, then the set of logical
tables is in one to one correspondence with the set of integer partitions of m.
This multiplicity of logic tables in the finite context reflects the multiplicity of logics exposed in the work of
Sorensen and Urzyczyn, which established that there is no single finite Heyting algebra that satisfies Soundness
and Completeness [308] (but they are however sufficient to preserve the semantics stated in theorem 2.4.8 [308]).
Unfortunately, the asymptotic limit of such logic is quite unknown, particularly hard, and is being investigated by
Hardy and Ramanujan. Considering the construction of random reals with an inaccessible cardinal by Solovay,
it appears natural to call these probability values finite/accessible rational random rationals. However, what
follows suggests that there exist several ways to complete such discrete random field to the continuous field,
namely euclidean and p-adic completion, following Ostrowski’s theorem. Regardless, we hence leave off here
from a trail of an elementary probabilistic logic proposed to be relevant for biological structures, cognition,
consciousness and physics.
3.2.4
Information functions and set theory
Firstly we need to restate the usual functions of information established by Shannon [131] and Hu kuo Ting [309],
specifically those used in this review:
• Shannon-Gibbs entropy of a single variable Xj is defined by [131]:
X
H1 = H(Xj ; PXj ) = k
p(x) ln p(x) = k
Nj
X
pi ln pi
(3)
i=1
x∈[Nj ]
where [Nj ] = {1, ..., Nj } denotes the alphabet of Xj .
• Joint entropy is defined for any joint-product of k random variables (X1 , ..., Xk ) and for a probability
joint-distribution P(X1 ,...,Xk ) by [131]:
N1 ×...×N
X k
Hk = H(X1 , ..., Xk ; PX1 ,...,Xk ) = k
p(x1 .....xk ) ln p(x1 .....xk )
(4)
x1 ,...,xk ∈[N1 ×...×Nk ]
where [N1 × ... × Nk ] = {1, ..., Nj × ... × Nk } denotes the alphabet of (X1 , ..., Xk ).
• The mutual information of two variables X1 , X2 is defined as [131]:
I(X1 ; X2 ; PX1 ,X2 ) = k
NX
1 ×N2
x1 ,x2 ∈[N1 ×N2 ]
29
p(x1 .x2 ) ln
p(x1 )p(x2 )
p(x1 .x2 )
(5)
It can be generalized to k-mutual-information (also called co-information) using the alternated sums given
by equation 14, as originally defined by McGill [310] and Hu Kuo Ting [309], giving:
N1 ×...×N
X k
Ik = I(X1 ; ...; Xk ; P ) = k
Q
p(x1 .....xk ) ln Q
I⊂[k];card(I)=i;i odd pI
(6)
I⊂[k];card(I)=i;i even pI
x1 ,...,xk ∈[N1 ×...×Nk ]
For example, 3-mutual information is the function:
N1 ×N
2 ×N3
X
I3 = k
p(x1 .x2 .x3 ) ln
x1 ,x2 ,x3 ∈[N1 ×N2 ×N3 ]
p(x1 )p(x2 )p(x3 )p(x1 .x2 .x3 )
p(x1 .x2 )p(x1 .x3 )p(x2 .x3 )
(7)
For k ≥ 3, Ik can be negative [309].
• The total correlation introduced by Watanabe [311], called integration by Tononi and Edelman [1] or
multi-information by Studený and Vejnarova [312] and which we note Ck (X1 ; ...Xk ; P ), is defined by:
Ck = Ck (X1 ; ...Xk ; P ) =
k
X
H(Xi ) − H(X1 ; ...Xk ) =
i=1
=k
N1 ×...×N
X k
x1 ,...,xk ∈[N1 ×...×Nk ]
k
X
(−1)i
i=2
X
Ii (XI ; P )
I⊂[n];card(I)=i
(8)
p(x1 ...xk )
p(x1 ....xk ) ln
p(x1 )...p(xk )
For two variables the total correlation is equal to mutual-information (C2 = I2 ). The total correlation has
the pleasant property of being a relative entropy between marginal and joint variables and hence of always
being non-negative.
• The conditional entropy of X1 knowing (or given) X2 is defined as [131]:
X2 .H1 = H(X1 |X2 ; P ) = k
NX
1 ∗N2
p(x1 .x2 ) ln px2 (x1 )
x1 ,x2 ∈[N1 ×N2 ]
=k
N2
X
N1
X
p(x2 ).
x2 ∈X2
!
px2 x1 ln px2 x1
(9)
x1 ∈X1
Conditional joint-entropy, X3 .H(X1 , X2 ) or (X1 , X2 ).H(X3 ), is defined analogously by replacing the marginal
probabilities with the joint probabilities.
• The conditional mutual information of two variables X1 , X2 knowing a third X3 is defined as [131]:
N1 ×N
2 ×N3
X
X3 .I2 = I(X1 ; X2 |X3 ; P ) = k
p(x1 .x2 .x3 ) ln
x1 ,x2 ,x3 ∈[N1 ×N2 ×N3 ]
px3 (x1 )px3 (x2 )
px3 (x1 , x2 )
(10)
The chain rules of information are (where the hat denotes the omission of the variable):
ci ; ...; Xk+1 ; P ) = H(X1 ; ...; Xk+1 ; P ) − (X1 ; ...; X
ci ; ...; Xk+1 ).H(Xi ; P )
H(X1 ; ...; X
(11)
That can be written in short as Hk+1 − Hk = (X1 , ...Xk ).H(Xk+1 )
ci ; ...; Xk+1 ; P ) = I(X1 ; ...; Xk+1 ; P ) + Xi .I(X1 ; ...; X
ci ; ...; Xk+1 ; P )
I(X1 ; ...; X
(12)
That can be written in short as Ik−1 − Ik = Xk .Ik−1 , generating the chain rule 11 as a special case. We have
I1 = H1 . We have the alternated sums or inclusion-exclusion rules [309, 313, 2]:
n
X
Hn (X1 , ..., Xn ; P ) =
(−1)i−1
i=1
In (X1 ; ...; Xn ; P ) =
X
Ii (XI ; P )
(13)
Hi (XI ; P )
(14)
I⊂[n];card(I)=i
n
X
(−1)i−1
i=1
X
I⊂[n];card(I)=i
For example: H3 (X1 , X2 , X3 ) = I1 (X1 )+I1 (X2 )+I1 (X3 )−I2 (X1 ; X2 )−I2 (X1 ; X3 )−I2 (X2 ; X3 )+I3 (X1 ; X2 ; X3 )
30
Figure 11: Naive set-theoretic and lattice representation of information function. a, Venn diagram
representation of the various information functions justified by the theorem of Hu Kuo Ting [309] (see text).
b, semilattice of joint-entropy with conditional entropies (coface map in simplicial sets [314]) implementing the
chain rule, for example using the abbreviated notations H(12) = H(1) + 1.H(2).A corresponding simplicial
representation of these joint entropies which can be easily realized by the non-negativity properties of conditional
entropies. c, semilattice of mutual informations with conditional mutual informations implementing the chain
rule, for example using the abbreviated notations I(123) = I(12) − 3.I(12). Since the Ik can be negative for
k ≥ 3, there is no obvious corresponding simplicial representation; see Yeung for more details [315, 316, 317].
Hu Kuo Ting and Yeung theorem: The theorem of Hu Kuo Ting and Yeung [309][316] establishes a
bijection between information functions and finite additive (measurable) functions, for which the set theoretic
operators ∪, ∩, / correspond to Joint (; ), Mutual (, ) and conditional (/) information operation respectively. This
important theorem has been neglected in information theory for some time and rediscovered independently in a
more superficial form many times within the community.
Hu Kuo Ting - Yeung theorem: For a given sequence of variables X1 , X2 ... and their distribution P there
exist a corresponding sequence of sets A1 , A2 ... and an additive function ϕ on the ring U generated by the
sequence Ai , i = 1, 2, ..., such that: H(Q(Xi1 , Xi2 , ..., Xin )) = ϕ(Q(Ai1 , Ai2 , ..., Ain ) for all collections of variables, Xi1 , Xi2 , ..., Xin , and all operations, Q denoting a symbol generated by a finite number of operations ∪, ∩, /.
Csiszár and Körner have proposed an alternative ”geometric” proof of Hu [318] and also suggested the
converse correspondence of additive functions with information functions by way of symmetric argument. Hu’s
theorem and its converse establisha bijection between additive functions and information functions,
which is a deep equivalence between set and measure theory and information theory; any additive function
can be written in term of information and vice versa. Figure 11 illustrates the consequence of this theorem,
allowing a naive handling of information functions with Venn diagrams and supporting the simplicial-boolean
lattice decompositions studied by Shannon [319] and Han [320]. One can estimate the importance of such a
theorem with regard to integration and measure theory. Considering the axiomatic setting of Solovay, that is, a
set theory without the axiom of choice in which all sets are measurable, the universality of information functions
appears justified. Considering Solovay’s axiomatic system, any function is measurable and information functions
are hence in bijection with all functions. The universality of function has already appeared in the context of
Riemann zeta functions [321, 322], which are related to polylogarithms.
From the algebraic point of view, Hu Kuo Ting’s first theorem of his 1962 paper on ”information quantities”
establishes explicitly that information functions are the set of finitely additive functions on the ring of
random variables. This result justifies the consideration of information functional modules on random-variable
modules and the information cohomology constructed in [2, 250] can be understood as a generalization of this
result. His first theorem therefore supersedes and condenses many of the results on information that were found
a posteriori.
3.2.5
The information of a formula/thought
In this section, we investigate whether a mathematical formula has an information content that could be quantified. As previously discussed, Denef and Loeser proposed a formalism based on motivic measures that give a field
independent measure of mathematical formula [265]. Here, we propose an informational version and the possibility, based on the probabilistic logic formulation we have presented, of considering any thought as a mathematical
formulation; the mathematical nature of thoughts, an idea which still has life in it. In this section, we revisit
Gödel’s arithmetic coding procedure in a finite probabilistic context and show that Shannon’s entropy decodes
and assigns a (real-valued) information measure to finite mathematical formulae. Unlike in the deterministic case,
for which the information (complexity) of a string is in general not computable, the entropy of a probabilistic
31
object can be computed. Kolmogorov defined the Algorithmic information or complexity, K(X), of an object
(a string X ∈ 0, 1∗ ) to be the length of the shortest program that produces (print) the object and halts on a
given universal Turing machine T : K(X) = min{|p| : CT (p) = X}, where |p| denotes the length of the program
in bits, CT : 0, 1∗ → 0, 1∗ is a partial recursive function (that is computed by the Turing machine T ) and CT (p)
is the result of running the program p ∈ 0, 1∗ on the Turing machine T . Zvonkin and Levin [323] showed that
Shannon entropy of binary iid variables equals the averaged randomness-complexity K in the limit of infinitely
long strings (see Th. 5.18 for a precise statement on this [323]). The fundamental theorem of arithmetic (the
unique-prime-factorization theorem of Euclid) states that any integer greater than 1 can be written as a unique
product (depending on the ordering of its factors) of prime numbers (see Hardy and Wright [324]). We write any
integer n as its prime decomposition, called its standard form:
αk
1 α2
n = pα
1 p2 ...pk , (α1 > 0, α2 > 0, ..., αk > 0, p1 < p2 < ... < pk )
∀n ∈ N, n > 1, n =
∞
Y
pαp
(15)
(16)
p prime
where αp ∈ N is a natural integer coefficient depending on the prime p. Including 1 implies the loss of uniqueness,
since the prime factorization of 1 contains 0 exponents (1 = 20 .30 .50 ... = 30 ), and if we allow zero exponents,
the factorization ceases to be unique. A standard method of extending the fundamental theorem of arithmetic
to rational numbers is to use the p-adic valuation of n, noted vp (n), to ascribe the exponent vp (n) = αp to
all prime numbers in the product and to then give an exponent vp (n) = 0 to those that do not divide n. The
decomposition into prime factors of rational numbers requires considerations of the possibly negative exponents
0
αp ∈ Z and vp ( nm ) = vp (n0 ) − vp (m), the so-called p-adic norm (see Khrennikov and Nilson [325] for definitions
and non-deterministic dynamic applications), giving this representation of a rational number
n=
n0
v (n)
= 2v2 (n) 3v3 (n) ...pkk , (vp (n) ∈ Z, p1 < p2 < ... < pk )
m
∀n ∈ Q, n =
n0
=
m
∞
Y
pvp (n)
(17)
(18)
p prime
, and every rational number as a unique prime factorization.
Gödel code : We will firstly introduce Gödel’s logic and methods. The relation between indeterminism,
uncertainty and logical undecidability has been a leitmotiv of many works. Gödel’s approach was called the
arithmetisation program of logic. The basic hypothesis of Gödel is based on the fact that the formula of a
formal system can be viewed as finite sequences of basic symbols (variables, logical constants, and parentheses
or separators), allowing one to define which sequences of these basic symbols are syntactically correct formula
(or not) and, from this, which finite sequences of formula provide correct proofs (or not). To do so he designed
a numbering-code that assigns bijectively a natural integer to each sequence [326]. Hence, a formula is a finite
sequence of natural numbers, and a proof schema is a finite sequence of finite sequences of natural numbers.
Gödel could then prove that, under this hypothesis, there exist some theorems that are independent and which
can neither be proved or disproved. To do so he defined a map from logical statements, that is, any sequence
of mathematical symbols, to natural numbers, which further allows deciding whether logical statements can be
constructed or not. Given any statement, the number it is converted to is called its Gödel number, defined by:
α(x1 , x2 , x3 , . . . , xn ) = 2x1 .3x2 .5x3 ...pxnn
(19)
In the original work, the first 12 ”powers” are occupied by basic symbols, and the numerical variable occupies
the powers p ≥ 13 [327]:
Gödel Number Symbol
meaning
1
¬
not
2
∨
or
3
⊇
if ... then (implication)
4
∃
There exist
5
=
equals
6
0
zero
7
s
the immediate successor of
8
(
left parenthesis
9
)
right parenthesis
10
,
comma
11
+
plus
12
×
times
32
For example, the formula x1 = x1 is coded by the Gödel number α(13, 5, 13, 0, 0, . . . , 0) = 213 .35 .513 70 ...p0n , and
(∃x1 )(x1 = sx2 ) is coded by the Gödel number α(8, 4, 13, 9, 8, 13, 5, 7, 17, 9, 0, 0, . . . , 0). This ”function” sends
every formula (or statement that can be formulated in a theory) into a unique number, in such a way that it is
always possible to retrieve the formulas from the Gödel numbers, but also to say whether an arbitrary number
corresponds to a Gödel number. The Gödel number of the sequence (x1 , x2 , x3 , . . . , xn ) is more generally called
a pairing function, noted f (x, i) = xi .. i is always in the range of 1, . . . , n (and in the previous case the indices
correspond to the labels of the primes).
Now that we have introduced Gödel’s arithmetic coding, we can apply his method to rational (empirical)
probabilities fields and show that the Shannon entropy function is a ”decoding function” that sends any number
back to its formula with a one to one correspondence. We first define an extended Gödel number as the p-adic
0
norm vp ( nm ) and identify its value as Gödel did and as summarised in the table above, the only difference being
that we now dispose of negative integers in order to facilitate the code.
Theorem 2 (Fundamental theorem of arithmetic Information) Let H(X, PQ ) be the information function
over a rational probability field PQ . Then:
X
vp (n) log p
(20)
H(X; PQ ) = −
p prime
Qn
where vp (n) ∈ Z is a relative integer coefficient depending on the prime p vp (n) = vp ( i=1 p(xi )p(xi ) ).
Proof: the probabilities over the rational field PQ , and an elementary probability pj , which can be written
according to the fundamental theorem of arithmetic (for readability noting a prime with q symbol):
pj =
Y
n0
=
q vq (pj )
m
(21)
q prime
Pn
where 0 < pj ≤ 1 and j=1 pj = 1, and vq (pj ) ∈ Z are relative integer coefficients depending on the prime q.
Entropy function H(X; PQ ) is, according to Shannon’s axiom, a continuous function of the pi and can be written
in the form:
n
n
Y
X
p(xi )p(xi )
(22)
p(xi ) log p(xi ) = − log
H(X; PQ ) = k
i=1
i=1
p(xi )
It follows from elementary algebra that p(xi )
has a prime decomposition with relative integer exponents, and
hence the theorem.
This theorem applies to any information function H(Q(X1 , X2 , ..., Xn ), PQ ) as defined by Hu Kuo Ting [309],
namely, joint-entropies, mutual informations, conditional entropies and conditional mutual informations (see also
[214]), as they are linear combinations of entropies. Notably, considering all information functions, since mutual
information can be negative for k variables, k > 2, the set of information values is in one to one correspondence
with Z. Such bijection can only be achieved by considering a variable space of at least 3 dimensions. We hence
have established that the following corollary:
Corollary - Information-Gödel code : H(Q(X1 , X2 , ..., Xn ), PQ ) = h(vq (n), q) is a Gödel code.
Figure 12 gives the Young diagram for all integer partitions of m with m = 2, 3, 4, 5, 7, 8 as previously associated with the associated logical tables. The two partitions of 8 which have the same entropy (1/4, 1/4, 1/4, 1/4) ≈
(1/2, 1/8, 1/8, 1/8, 1/8) are isomorphic according to the theorem of Mesalkin (1959 [328], a special case of
Kolmogorov-Ornstein Isomorphism theorem (see section 3.4), and their associated tables and logic shall be
considered as equivalent.
This is just a preliminary result on the elementary logic of information; the characterization of this logic lies
beyond what has been so far been achieved. Notably, more work needs to be done involving the consideration of
the elementary context of integer partition probabilities, introduced in the previous section, and the extension to
negative coding values that offers a possibly richer logic. The results so far also provide some original geometrical
insight into logic and probability, allowing the future study of mathematical formula with Euclidean and p-adic
metrics [325]. In constructive logic, the implication ⇒ is a power-like operator and provides a ”direction” to
logical flow; it would be interesting to investigate such directional flow from the irreversible and causal point of
view of thermodynamics.
There is another question as regards statistical independence and independence of axioms. The undecidability of
a proposition X in a theory Ω, suggesting that X is independent of the other proposition Y in Ω, could correspond
to independence in probability such that it would be possible to say that X being independent in Ω is ”equivalent”
to PY (X) = P (X), or that the joint theories associated with X and Y factorize P (Y.X) = P (X)P (Y ) in Ω.
In such a case the additivity or subadditivity of the information decoding function quantifies the independence
or dependence of the propositions in the theory Ω (in a topological sense). In more up-to-date terms, Cohen’s
technique of forcing may have a simple probabilistic analog. In a very pragmatic empirical sense, a mathematical
33
Figure 12: The smallest empirical probability fields for a number of total observations m =
2, 3, 4, 5, 7, 8 represented using Young’s diagram of the associated partitions. The associated entropy H is written
below each partition in its prime decomposition form. Note that entropy is an increasing function from right to
left and top to down, and that the two equal entropies for m = 8 correspond to isomorphic partitions according
to a theorem of Mesalkin (1959 [328]), which is a special case of Kolmogorov-Ornstein Isomorphism theorem
(1/4, 1/4, 1/4, 1/4) ≈ (1/2, 1/8, 1/8, 1/8, 1/8). See section 3.4. (Figure adapted and modified from the work of
R. A. Nonenmacher (CC))
theory is also a human belief, stated and written by humans (or machines) implementing human beliefs. If one
considers probabilistic-information theory as the relevant model for cognition, then there exists a probabilistic
theory of mathematics that encompasses mathematicians’ entire mathematical product.
3.3
Homology, the shapes and the language of perception
3.3.1
Homological history and cognition
Topology is the science that characterizes objects by the relation interactions of their components. It is the
domain of mathematics dedicated to shapes or patterns which classifies them by identifying their invariants.
Here we give a little historical taste of what topology is or could be, highlighting its cognitive aspects and
motivations, already made explicit by its original founders. Some historical reviews of the different aspects of
topology, i.e. algebraic and differential, of topology can be found in the work of Milnor [329], of Weibel [330]
and of Dieudonné [331]. Topology was first born under the name of Analysis Situs, notably in the writings
of Leibniz [332]. Analysis Situs is inseparable from all his further work, his quest for a universal characteristic
that first took form in differential calculus, on a qualitative geometry, consisting in a language allowing
one to ”algebraically-logically” manipulate geometrical figures. Leibniz’s model was a universal cognitive and
consciousness model; he developed the concept of the monad, which is at the same time a physical substance and
a semantic qualia unit element; monads are exact, irreducible, real and perfect [24]. Monads, according to Liebniz,
can compose hierarchically forming new monads inheriting properties from the originals, and the structure and
algebra ruling them can be conceived of as the analysis situs. They are physical atoms of knowledge and of
sensations, a monist view contrasting with usual mind-body dualism. Hence, in Leibniz’s view, the whole world
is perfect, optimal. One can still recognize Leibniz’s view in modern studies of monads, also called triples by
Barr and Wells [296]. Leibniz’s view is indeed still at work in what is presented here, notably his mind-body
34
model, monist and pluralist, physical and mathematical, and his idea of perfection, which when re-expressed
in probabilistic modern terms, although optimistic, sounds much more generally like a basic hope or expectancy.
Leibniz’s opus is also at the roots of information theory in the form of binary calculus, and Uchii recently
proposed an extended work on monadology, information and physics [333, 334, 335]. After Liebniz, Euler made a
contribution by solving the 7 bridges problem and defining his ”characteristic” χ , the main topological invariant
that Leibniz was unable to find [336]. Betti and Riemann, following Abel, developed the foundations of homology
by classifying surfaces [337], then Poincaré introduced with his analysis situs most of the basic theorems and
concepts in the discipline [338]. Topology was born as geometry cleaned of its ”unnecessary” undecidable axioms,
a geometry without metric assumptions. It was notably conceived in Poincaré work and theorems (such as
uniformization theorem and his conjecture) to maintain geometrical unity in mathematics as a consequence of
the discovery of the existence of geometrical diversity, i.e. legitimate non-Euclidian geometries, the diversity
of geometry. Poincaré directly related analysis situs to the cognitive process of constructing a continuous space
from discrete experience, and even proposed to explain the Weber-Fechner law of sensory adaptation on this basis
as reported in appendix A. This obviously constitutes the first mathematical model of perceptual adaptation,
explicitly topological, more than a century ago. Since then many homology theories have appeared [331], each
characterizing different, more or less general mathematical structures. However, these theories appeared to have
analog structures and the work of unifying them began in the second half of the 20th century. The working
principle of homology theory followed by Eilenberg, Maclane and Grothendieck has been to ”dig deeper and find
out”, such that homology theory has continued to define new, more general and enormous homologies, generalizing
simplicial homology by (the equivalent) singular homology, then by homological algebras, then by topos, and
then by conjectural motives, introducing categories and functors as central working tools (see Cartier’s review
[289] and Eilenberg’s biographical memoir [339]). The result generalizes them to differential Lie, associative
algebra, arithmetic, etc. The simple consideration of the swathes of mathematics which are concentrated under
the little names of functor Ext and Tor is sufficient to illustrate the principle of cognitive process proposed
here, namely that ”understanding is compressing”. In the original view of Grothendieck, the ascension towards
unified-general cohomology theory followed 3 steps: schemes, topos, and finally motive theory [289]. The aim
of motivic cohomology is to nevertheless handle geometry and algebra equivalently, but also number theory:
notably, one aim was to solve an algebraic subcase of Riemann’s conjecture, the Weil conjecture. The structure
of this general cohomology became progressively more clear, notably thanks to the work of Beilinson, Bloch and
Goncharov. Voevodsky, following an original approach, proposed a formalisation of motivic cohomology based
on triangulated categories.
3.3.2
Groups and action: ambiguity and uncertainty according to Galois
Following Poincaré but also Grothendieck, and exaggerating a little as they did, one could say that topology is
the story of group, a ”Long March through Galois theory” [340]. Group theory originates in the study by Galois
of the permutations of solutions, called roots, to the polynomial equation P (x) = 0; what he called ambiguity.
It transpires that this notion of ambiguity captured by groups is related to the notion of uncertainty captured by
information, and that the cohomology of information and random variable structure has the structure of Galois
group cohomology, a guiding idea of Bennequin’s [3, 2]; see section 3.3.4.
Galois theory conveys in itself a cognition theory, as summarised by Deleuze: ”the group of the equation characterizes at one point, not what we know of the roots, but the objectivity of what we do not know about them.
Conversely, this non-knowledge is no longer a negative, a deficiency, but a rule, a learning which corresponds to a fundamental dimension of the object.” [341]. This idea was further developed by André
[342, 293, 343]. Bennequin applied this Galoisian epistemological principle of knowledge to propose a Galoisian
physics [344]. In what follows, consciousness is defined in terms of group and the actions of a group; hence
we need a brief definition of and introduction to those concepts. Permutations are central objects in (discrete)
group theory and combinatorics, and provide a definition of symmetry in finite sets. The fundamental theorem
of algebra states that any general polynomial of degree n, P (x) = an xn + an−1 xn−1 + · · · + a1 x + a0 , where
the coefficients ai are real or complex numbers and ai 6= 0 (or any integral domain of a ring) have n complex
roots λ1 , λ2 , · · · , λn . The roots are not necessarily distinct, and if they are indistinct they are called degenerate,
and they hence encode the multiplicity of indistinct solutions . We can therefore also write the polynomial as a
product P (x) = an (x − λ1 )(x − λ2 ) · · · (x − λn ). Expanding the product on the right hand side of the equation
provides a symmetric polynomial in the roots λi that exhibit a Newton Binomial powerset structure (cf. figure
13 for examples with n = 3, 4.) Newton’s binomial method ) is as follows:
P (x) = an (x − λ1 )(x − λ2 ) · · · (x − λn ) = an [
n
X
(−1)n−k (
k=0
Or in the notations used for information structures:
35
X
1≤i1 ≤i2 ≤···≤ik ≤n
λi1 .λi2 ...λik )xk ]
(23)
P (x) = an (x − λ1 )(x − λ2 ) · · · (x − λn ) = an
n
X
(−1)n−k
k=0
X
n
Y
1 (i )
λj I j xk
(24)
I⊆[n],|I|=k j=1
, where 1I (ij ) is the indicator function of the subset I = {i1 , ..., ik } of [n] = {1, ..., n}.
Figure 13: Example of degree 3 (top) and 4 (bottom) polynomial univariates (in one variable) in their additive
(left) and multiplicative-factorized forms (right), together with their corresponding simplex.
It provides an elementary example of group structure and of the relationship between addition and product
which has been generalized in numerous ways. It also provides the most elementary appearance in algebra of
topological alternated sums. Identifying the coefficient ai with the coefficients of the equation 23 gives Vieta’s
formulas. If the leading coefficient an = 1, then it is called a monic polynomial and the set of univariate monic
polynomials with coefficient in a ring is closed under the operation of multiplication (the product of the leading
terms of two monic polynomials is the leading term of their product), and forms a monoid (with the operation
of multiplication, the identity element is the constant polynomial 1).
Thanks notably to the work of Bourbaki, a group is now well defined according to few axioms:
Group : A group is a set, G, together with an operation ? that combines any two elements x and y to form
another element x ? y. To be a group, the set and operation, (G, ?), must satisfy four axioms:
• Closure: for all x, y ∈ G, the result of the operation, x ? y is also in G.
• Associativity: for all x, y, z ∈ G , (x ? y) ? z = x ? (y ? z).
• Identity element: there exists an element e in G, such that for all x ∈ G , e ? x = x ? e = x.
• Inverse element: for all x ∈ G , there exists an element y in G such that x ? y = y ? x = e.
Figure 14 gives an illustration of those axioms. Z, the set of relative integers, forms a group with the operation
of addition; this is a countably infinite cyclic group. One should be aware that the simplicity of these axioms
hides the rich structures groups may exhibit, as stated by Borcherds, for example [345]. The richness of these
group structures is captured and encoded by homology, prefiguring the following sections of our paper.
Symmetric group [346]: The symmetric group on a finite set of n symbols, noted Sn , is the group whose
elements are all permutations (bijection) of the n elements of a finite set Ω and whose group operation is the
composition of such permutations. The identity element is the identity permutation. More generally, if Ω is a
non-empty set, we denote by SΩ the group of permutations (that is, bijections) of Ω under the composition of
maps σi .σj = σ ◦ η. This latter includes the case of group of infinite order. It is easy to verify the permutations
on a set forms a group under composition according to the axioms of a group (closure, associativity: function
36
Figure 14: Illustration of the main three properties imposed by the axioms of a group on a given example of
permutations. Permutations and their graphical representation are introduced in what follows.
composition is associative: σ ◦(η ◦ ρ) = (σ ◦ η)◦ρ, identity, inverse); this group is termed the symmetric group
of Ω, noted SΩ in general, and Sn in the case where Ω = {1, 2, ..., n}.
The common way to relate the elements of a group to a particular transformation of an object is to consider
the action of the group. The Cayley’s theorem states that every group G is isomorphic to a subgroup of the
symmetric group acting on G. The usual definition of an action is the following:
Group action: Let G be a group and X be a set. Then a left-group action f ∗ of G on X is a function
f ∗ : G × X → X : (g, x) → f ∗ (g, x), usually noted g.x and called a left action (or translation) of G on X, that
satisfies the two axioms:
• Identity: ∀x ∈ X and e the identity element of G , we have e.x = x.
• associativity: ∀(g, g 0 ) ∈ G2 and ∀x ∈ X, we have (g 0 g).x = g 0 .(g.x), where g 0 g denotes the result of applying
the group operation of G to the elements g and g 0 , and g 0 g ∈ G and g.x ∈ X.
If we define the morphism φ∗ associated to the action ∀g ∈ G, ∀x ∈ X, such that g.x = (φ∗ (g))(x), then these
axioms are equivalent to saying that the group G acts on X (on the left) if we have the morphism of the group
φ∗ : G → SX , from G into the symmetric Group SX of X. Such a morphism is called a representation of the
group G.
The dual action called the right action is defined by inverting the order in g and g 0 : f∗ : G × X → X : (g, x) →
f∗ (g, x), usually noted x.g and called a right action (or translation) of G on X. This satisfies the two axioms:
• Identity: ∀x ∈ X and e the identity element of G , we have e.x = x.
• associativity: ∀(g, g 0 ) ∈ G2 and ∀x ∈ X, we have (gg 0 ).x = g 0 .(g.x), where gg 0 denotes the result of applying
the group operation of G to the elements g 0 and then g, and gg 0 ∈ G and g.x ∈ X.
Dually, if we define the morphism φ∗ associated to the action ∀g ∈ G, ∀x ∈ X, such that x.g = (φ∗ (g))(x), then
these axioms are equivalent to saying that the group G acts on X (on the right) if we have the morphism of the
opp
opp
group φ∗ : G → SX
, from G into the opposite symmetric Group SX
of X. Such a morphism is a representation
opp
of the group G dual to left one. The opposite group SX of the symmetric group SX is the set of permutations
of X with the law of composition (f, g) 7→ f ? g = g ◦ f . We go from left to right dual using the fact that
(gg 0 )1 = g 01 g11 and composing with the inverse operation of the group.
After Galois, Lies work and motivations for studying Lie groups were intended to extend Galois theory
to differential equations by studying the symmetry groups of differential equations. The resulting differential
Galois theory was studied by Picard-Vessiot, and Chevalley and Eilenberg later formalized the cohomology of
Lie algebra [347]. One of the motivations of homological algebra was then to unify Galois discrete cohomology
with Lie continuous cohomology.
3.3.3
What is topology?
We will now give a short and informal snapshot of algebraic topology (see Figure 15). Classical expositions can be
found in Alexandroff [348], Hatcher [349] and Ghrist ’s book [350]. The researchers working in complex systems
or neural networks are familiar with the idea of topology: a complex network where a graph is a 1-chain complex,
a 1-complex. In the study of complex systems, the seminal works of Erdos and Renyi [351] and then Watts and
Strogatz [352] showed that combinatorial features and statistics of connections of networks affect their dynamical,
37
statistical and critical behavior (reference reviews can be found in [353] and [354]). The considerations of these
studies relies on a tiny 1D window of the n-dimensional (or degree) landscape of topology. The meaning of this
high dimensional generalisation by the topology has a simple and intuitive interpretations; whereas a network is an
assembly of pairs of elements (of neurons for example), homology investigates assemblies with arbitrary numerous
elements, a good mathematical start to formalizing neural assemblies (or other ”groups”). We indeed believe
that information theory may provide appropriate tools to ultimately render some of the difficult frameworks
of algebraic topology as intuitive as they should be. Simplicial homology (commutative, with addition as an
operation, for example) writes a complex network as a group here commutative, e.g as an algebraic sum of its m
edges, of its elementary constituents
Pm−1 in one dimension, weighted by coefficients with value in a group or a field
(or in modules): C1 (S, F) = i=0 ai ∆1,i . The orientation and the weighting of the network are implemented by
the coefficients ai . Homology provides an alternative and a generalization of adjacency and incidence matrices.
For example, the coefficients (0,1) of the simplest adjacency matrix are assimilated to the field with two elements
F2 etc. Homology can then be considered as providing a generalization to n-dimensions of complex networks.
Homology: an homology is defined by two things: an n-degree (or n-dimensional in special cases like the
simplicial) complex Cn and a boundary operator ∂n . What follows is illustrated in the top left panel of Figure
15. By the defining condition ∂ ◦ ∂ = 0, the application of the differential operator ∂ to the complex generates a
sequence of n-complex Ck or k-chains, as follows:
∂n+1
∂
∂n−1
∂
∂
n
1
0
−−−→ Cn −→
Cn−1 −−−→ ...C1 −→
C0 −→
0
(25)
This is the basic principle; now let us investigate what a complex is. n-complex: a simplicial n-complex Cn
is written as a weighted
sum of its elementary n-simplices with a composition operation symbolized by the of
Pm−1
addition Cn (S, F) = i=0 ai ∆n,i . The building blocks, n-simplex ∆n (in the simplest case of simplicial homology) are triangles generalized to all dimensions; a point-vertex is a 0-simplex, an edge a 1-simplex, a triangle a
2-simplex, a tetrahedron a 3-simplex and so on; they are also called the k-faces of the complex. The most basic
definition of an abstract complex is a family C consisting of finite subsets of a given set of vertices V = x1 , ..., xn ,
such that the 2 following conditions hold: i) {xi } ∈ C for all {xi } ∈ V ii) If X ∈ C and Y ⊆ X, then Y ∈ C.
In simple but ambiguous words, a complex contains all its subfaces. n-complexes are organized in a sequence of
decreasing degree-dimensions which are also inclusive (or projective) sequences. An edge is included in a triangle
which is included in a tetrahedron and so on.
n-boundary: We go from one dimension n to another n − 1 by a boundary operator ∂n : Cn → Cn−1 , a
homomorphism. It literately makes a dimension reduction, just as we saw conditioning do in probability. The
simplest expression of a boundary operator in simplicial homology consists of an alternating sum of the complexes obtained by deleting one of the vertices each time. By definition, the boundary of a boundary must be zero
(∂n ◦ ∂n−1 = 0 where 0 denotes the mapping to the identity in Cn−1 ); this implies that the sequence is inclusive
and that the image of the n + 1 boundary is included in the kernel of the n boundary (Im(∂n ) ⊆ Ker(∂n−1 )).
This defining condition ∂ ◦ ∂ = 0 or ∂ 2 = 0, that is, the boundary of a boundary is 0, is fundamental and implements the non-contradiction principle (considering Y to be the boundary of X, that is Y = Cl(X) ∩ Cl(Ω − X)
and then considering the boundary of Y . Since Cl(X) and Cl(Ω − X) are both closed, their intersection is also
closed, and hence Cl(Y ) = Y , and Cl(Ω − Y ) = Cl(Ω) − Cl(Y ), and moreover considering that Ω is the whole
space, we also have Cl(Ω) = Ω. Hence the boundary of the boundary of X is Y ∩ (Ω − Y ), that is the intersection of any set with its complement, that is the empty set and hence the consistency-non-contradiction axiom).
n-cycles: It allows us to define the n-cycles as null n-boundaries, that is, n-boundaries that equal zero
(∂n = 0), literally an n-chain-complex without a boundary (or with an identity boundary, that is, a closed chain).
Homology groups: Homology groups are defined as the quotient group of the kernel of the n-boundary by the
image of the n+1-boundary (Hn (S, F) = Ker(∂n )/Im(∂n + 1) = Zn (S, F)/Bn (S, F). They hence quantify holes,
empty cycles. Betti numbers are the nth rank of the simplicial homology group, its number of generators. Cohomology is the dual of homology and uncovers more information with invariants, including torsion and the change of
the group of the coefficients. For oriented complexes, we go from homology to cohomology via Poincare duality, in
general via the universal coefficient theorem which states that H n (S, F) ≈ Hom(Hn (S), F ) ⊕ Ext1 (Hn−1 (S), F ),
where Ext and Hom are functors. It was one of the first motivations of cohomology to account for both finite
groups and Lie groups. The chains become co-chains (C n ), boundaries ∂n coboundaries (δ n ), cycles cocycles
(δ n = 0); in other words, the sequence is reversed. It was the algebraic aspect, the beauty of topology relies upon
that it is expressed equivalently the geometrical aspects. Topology is the science that categorizes and distinguishes
the shapes of spaces. We have already seen the geometrical realization of simplexes with the probability simplex shown in Figure 9. Simplicial n-complexes are discretization or n-triangulation of continuous n-dimensional
manifold M (piecewise-linear manifolds). Homology is an equivalence relation on the manifolds up to continuous
deformation (cf. Figure 9 bottom). For example, the circle is topologically equivalent (homeomorphic) to the
square, the point to the disc, etc. It thus appears that the homology of two objects is different if they differ in
their number of holes, and homology accounts for the holes, which are algebraically independent components in
38
Figure 15: A snapshot of algebraic topology (see text).Top: (left) A simplicial chain complex, boundary operator,
cycle. (Middle) (Morse) Homology counts the number of critical points, source and sink counts +1 and saddles
-1. (Adapted and modified with permission from Banchoff [355], and from Ghrist [350]). (Right) Homotopy:
an equivalence relation between paths. Bottom: (left) homology: equivalence ”up to continuous deformation”.
(Right) Homology counts the number of holes, i.e. algebraically independent components, in each dimension.
39
each dimension. Betti numbers quantify the number of holes in each dimension;
their alternating sum equals
Pm−1
the Euler characteristic, which is the main topological invariant χ(S) = i=0 (−1)i bi (S, F). If one has a height
function h as in Morse theory, homology counts the critical points of the manifold. A saddle point is a hyperbolic
unstable critical point and counts for -1. P
The sources and sinks count for + 1. The sum of the critical points
m−1
equals the Euler characteristic, χ(M ) = pcriticalf orh i(pi , h), which also equals the integral of the curvature
R
C for 2D compact without boundary, according to the Bonnet-Gauss-Chern theorem ( M CdA = 2πχ(M )). A
reference work on Morse theory is Milnor’s book [356] and Forman’s review of the discrete version [357].
Homotopy: Homotopy is an equivalence relation between paths or geodesics in manifolds with inverses, and an
associative operation of composition (equivalence classes form a group called homotopy groups, noted πn (S, x0 )
where x0 is the based point. π1 is called the fundamental group). In dimension 1, the holes can be detected
by obstruction to retract a loop (closed curve) into a point, and if two loops can be deformed into one another
they are homotopically equivalent and define the same hole. A hole in a manifold implies the existence of nonhomotopic laces (e.g. if there are two non-homotopic laces on the torus). These definitions can be generalized
to higher dimensions, and an obstruction to deform-retract a closed oriented 2D surface into a point can detect
a two-dimensional hole and so on. S is said to be n-connected if and only if its first n-homotopy groups are 0
(πi (X) ≡ 0 , −1 ≤ i ≤ n, notably if it is non-empty π−1 (S) ≡ 0 and path-connected π0 (S) ≡ 0 ). Postnikov
provided a generic method to determine the homology groups of a space by means of homotopy invariants [358].
Links (see also knots), such as the Hopf 2-link or the Borromean 3-link, form homotopy groups [359] that can be
formalized as the closure of compositions of braids (signed permutations that form Artin’s group). It is obvious
in the case of n-links that the first i-linking numbers (i < n) vanish: the rings of a Borromean link are unlinked
in pairs, which is a purely emergent/collective property.
Concerning neuroscience and cognition, as already mentioned in the cell assembly section, following the development of topological data analysis (which is mainly based on persistence homology [360]), several studies have
been dedicated to the application of topological data analysis to visual activity by Singh and colleagues [87], to
neural networks by Petri and colleagues [88] and to neural activity patterns and assemblies by Curto and Itskov
[86]. Linguistic structure has also been studied using algebraic topology methods. Port and colleagues used
persistent homology to detect the presence of structures and relations between syntactic parameters globally
across all languages and within specific language families [361]. Topology also provides the mathematical ground
for the electromagnetic view of cognition proposed in the first chapter. Even without going into the complex
details of Topological Quantum Field Theories, the basic of Kirchhoff’s voltage and current conservation laws
which state that the algebraic sum of currents at every node of an electrical circuit (formalized as a simplicial
1-complex) is equal to 0, is a direct consequence of the first homology group, i.e., a chain I is a 1-cycle ∂I = 0.
The formalization of electrical circuits as a homology theory was developed by Lefschetz, and the electromagnetic generalization is treated in the work of Zeidler ([362] chap 22 and 23). Wheeler founded his ”austerity
principle” of physics on the definition of a boundary [363], and the chapter 15 of his heavy gravitation book
presents why the homological view is fundamental for general relativity [364]. This convergence of quantum field
and gravitation on different homological formalisms has provided the basis for the main gravity quantization
investigations [365]. Wheeler has been a major actor of the physical theory of information, the ”it from the bit”
, notably sustaining that ”all things physical are information-theoretic in origin and that this is a participatory
universe”[366]. We now discuss the formalism of information topology underlying the numerous studies that have
applied information theory to studies of perception or consciousness, and formalize the way in which machine
learning principles and algorithms are topological by nature.
3.3.4
Information topology synthesis: consciousness’s complexes and thermodynamic
The characterization of entropy in the context of topology started with a surprising coincidence in the work
of Cathelineau [367] on the scissor congruences introduced in section 3.2.1. As briefly introduced in [214], the
appearance of the functional equation of entropy, and hence entropy itself, pertains to motives, the unfortunately
yet importantly conjectural side of topology which gathers very different approaches, starting with the investigations of Kontsevitch, Gangl and Elbaz-Vincent [368, 369, 370, 371, 249, 248]. The formalism of information
topology developed by Baudot, Bennequin and Vigneaux in [2, 250] is based on probability, namely on information structures formalized as follows.
Information structures: Random variables are partitions of the atomic probabilities of a finite probability
space (Ω, B, P ). The operation of joint-variable (X1 , X2 ) is the less fine partition, which is finer than X1 and
X2 ; the whole lattice of partitions Π [304] hence corresponds to the lattice of joint-variables [372, 2]. A general
information structure is defined in usual set-theoretic terms as a triplet (Ω, Π, P ), and hence covers all the
possible equivalence classes on atomic probabilities. A more general and modern expression is given in category
and topos theory, in [2, 250]. The image law of the probability P by the measurable function of the jointvariables (X1 , ..., Xk ) is noted (X1 , ..., Xk ; P ). Figure 16 gives a simple example of the lattice of partition for
a universe of 4 atomic probabilities, a sub-simplicial lattice which is combinatorially computable on data. The
40
Figure 16: Example of general and simplicial information structures. a, Example of a lattice of random
variables (partitions): the lattice of partitions of atomic events for a universe of 4 events |Ω| = 4 (for example
two coin tossing Ω = {00, 01, 10, 11}). Each event is depicted by a black dot in circles representing the variables.
The operation of the joint-variable noted (X, Y ) or X ⊗ Y , of two partitions, is the less fine partition Z which is
finer than X and Y (Z divides Y and X, or Z is the greatest common divisor of Y and X). The joint operation
has an identity element noted 1 = Ω (noted 0 in what follows), with X, 1 = X, Ω = X and is idempotent
(X, X) = X 2 = X (the non-contradiction principle stated by Boole, cf. section 3.2.2, giving a codegeneracy map
in cohomology or simplicial sets). The structure is partially ordered set (poset) and endowed with a refinement
relation. b, Illustration of the simplicial structure (sublattice) used for data analysis (|Ω| = 4). c, Illustration of
the random variable partitioning of the probability simplex in the same example as in b. (Adapted and modified
with permission from Baudot, Tapia and Goaillard [214, 301])
fact that the lattice is a partially ordered set (poset) endowed with a refinement relation is central; it means
that there is an intrinsic hierarchy of informational structure, just as in the general model of physical cognition
of Schoeller, Perlovsky, and Arseniev [373]. Concerning classification-recognition tasks of machine learning,
information structures can be considered as universal: as a partition is equivalent to an equivalence class all
possible classification are represented in an information structure. For example, this lattice can be understood
as an algebraic formalization of deep networks, that is, networks with hidden layers of neurons for which the
rank (dimension given in what follows) in the lattice gives the rank of a hidden layer and the connections
correspond to coface maps (roughly, elementary projections or dimension reduction or increase). The random
variables formalize neurons that are intrinsically probabilistic and possibly multivalued, generalizing binary and
deterministic neurons such as McCulloch and Pitts’ formal neurons. As discussed in the section on electrodynamic
and digital coding 2.2.3, such a generalization is biologically relevant and even necessary. The other common
interpretation of this poset hierarchical structure, probably equivalent to the previous one (at least in ergodic
systems), is that the ordering of the lattice provides a multi-scale, coarse to fine analysis (cf. figure 16a),
and each rank of the lattice provides an information analysis at the corresponding organizational level, as already
formalized and applied by Costa et al [374, 375], who called it multiscale entropy in the context of time series.
Hence, such formalism can be applied in the context of multiscale systems such as the one illustrated in Figure
1 (in theory), and the entropy necessarily increases as more and more variables join, e.g. while progressing in
organizational scales (cf. Figure 17a).
Action: In this general information structure, we consider the real module of all measurable functions
F (X1 , ..., Xk ; P ). We consider the conditional expectation-mean (corresponding to informational conditioning)
the action of a variable Y on the module, noted:
Y.F (X1 , ..., Xk ; P ) = k
Ny
X
p(y).F (X1 , ..., Xk ; P/Y = y)
(26)
y∈Y
where P/Y = y denotes the conditioning of the probability by the event Y = y, such that the action corresponds
to the usual definition of conditional entropy given in section 9. Centrally, the action of conditioning is associative
[2, 250]. This action is also extremely important with regard to the theory of cognition; we used it in the section
on homeostasis 2.3.3 to define invariance, and we dedicate a more mathematically rooted presentation in the next
section 3.4. Notably, Vigneaux was albe to generalize all the formalisms presented here to Tsallis entropies by
considering a deformed action (integer powers of probability in the expectation) [250], also giving a straightforward
extension to quantized information.
The complexes of measurable functions of random variables X k = F (X1 , ..., Xk ; P ) and the cochain complex
k
(X , ∂ k ) are noted as:
∂0
∂1
∂2
∂ k−1
0→
− X 0 −→ X 1 −→ X 2 −→ ...X k−1 −−−→ X k
, where ∂ k is the coboundary with a left action proposed by Hochschild for associative structures and rings [376],
41
for Galois cohomology (see Tate’s work [377]), and for homological algebra (see Cartan et Eilenberg’s work [378]
and for non-homogenous bar complex (see Maclane [379]) is noted as:
(∂ k )F (X1 ; X2 ; ...; Xk+1 ; P ) = X1 .F (X2 ; ...; Xk+1 ; P )
k
X
+
(−1)i F (X1 ; X2 ; ...; (Xi , Xi+1 ); ...; Xk+1 ; P )
(27)
i=1
+ (−1)k+1 F (X1 ; ...; Xk ; P )
For the first degree k = 1, the 1-coboundary is (∂ 1 )F (X1 ; X2 ) = X1 .F (X2 ) − F (X1 , X2 ) + F (X1 ) and
the 1-cocycle condition (∂ 1 )F (X1 ; X2 ) = 0 gives F (X1 , X2 ) = F (X1 ) + X1 .F (X2 ), which is the fundamental
chain law of information (cf. equation 11). Following Kendall [380] and Lee [381], it is possible to deduce
from this chain law the functional equation of information and to uniquely characterize Shannon entropy as
the first class of cohomology, up to the arbitrary multiplicative constant k [2, 250]. It constitutes the main
theorem that founded information topology. It appears by direct computation in this cohomology that mutual informations with an odd number of variables are minus the coboundary of even degrees ∂ 2k = −I2k+1 .
Obtaining even mutual informations is achieved by reproducing the Hodge decomposition of Hochschild cohomology constructed by Gerstenhaber and Shack [382, 314, 383]. We construct for this a double complex
0 00
0 00
0 00
(X •,• , ∂, ∂∗ ) = (X k ,k , ∂ k ,k , ∂∗k ,k ), (k 0 , k 00 ) ∈ N × N endowed with the preceding coboundary ∂ and the same
coboundary with a symmetric action ∂∗ (left and right, commutative) [382, 314, 383]. As a result, the odd mutual
informations are minus the even coboundary ∂ 2k = −I2k+1 , the even mutual-informations are minus the odd
symmetric coboundaries ∂∗2k−1 = −I2k , and the mutual informations are the coboundaries of the total complex
k
with an alternated sign ∂tot
= (−1)k+1 Ik+1 .
The independence of two variables (I2 = 0) is then directly generalized to k-variables and gives the cocycles
Ik = 0.
As a conclusion concerning the probabilist interpretation of cohomology, information cohomology quantifies statistical dependencies and the obstruction to factorization.
What is the interest of these mathematical tools for cognition? The uniqueness of the obtained functions implies,
in the case classical finite probabilistic application to empirical data, that the information functions are not only
”good” but also the only ones to quantify statistical dependences and independences in the multivariate case. The
finite-discrete symmetries of permutation groups, which are the structural ambiguity and the (co)differentials
arising from Galois’s theory, are equivalent to uncertainties and shared information arising from the ”mathematical theory of communication”. To comment on such a surprising and important fact, mutual informations
are indeed (co)differential operators, a purely continuous operation arising from a finite and discrete context.
Hilbert noted in his work on infinity, ”the first unreasonable impression given to us by natural phenomena and
matter is that of continuity” [384]: while physics repeatedly proved that objectively the input of our senses is
finite and discrete, our consciousness construct the impression of continuity [384]. As expressed by Poincaré, the
construction of our continuous perception from discrete data can be proposed to be a cohomological operation
by nature (even explaining Weber-Fechner’s law) that mutual informations naturally fulfill. This is an important
contribution of Galois’s theory, further pursued by Lie, Picard-Vessiot and others, that allows us to conceive of
the notion of continuity and of derivation yet holding in the discrete world, extending the classical Newtonian
view. The second point of interest is that cohomology is the science of the forms (patterns) of spaces. Information
topology hence provides a preliminary theory of the shapes of probabilistic structures on which it is possible to
develop methods of pattern recognition-characterization for machine learning and the quantification of epigenetic
landscapes for biological adaptive dynamics, following Waddington and Thom [214, 301].
The third point of interest lies in the fact that this cohomology can be expressed as a Topos on a probability
site, which allows the establishing of the multivalued constructive logic described in an elementary finite context
in section 3.2.3. Such logic can provide a basis for a probabilistic, biological and cognitive logic.
Regarding data analysis and physics, information topology allows us to quantify the structure of statistical
interactions within a set of empirical data and to express these interactions in terms of statistical physics, machine
learning and epigenetic dynamics [214]. The combinatorics of general variable complexes being governed by
Bell’s numbers, their effective computation on classical computers is illusory. To circumvent those computational
hardness, we define the sub-case of the simplicial cohomology of information, with an algorithmic complexity
that can be implemented, but that neglects some of the possible dependencies. The computational hardness of
consciousness in discussed in section 3.5 in the perspective of Artificial Intelligence and classical Turing definitions
of computation. The exhaustive computation of the simplicial-binomial combinatoric of Ik and Hk (see Figure 17,
the set of subsets of n variables) is thus reduced to a complexity in 2n , computable in practice up to n = 21 with
basic resources. The set of the entropy values Hk and mutual information Ik for all subsets of n are represented
by the entropy landscapes Hk and information landscapes Ik as a function of the dimension k, as illustrated in
Figure 17. The entropies Hk quantify uncertainty on variables, and the mutual informations Ik quantify statistical
42
Figure 17: Principles of the analysis of dimension 4. Top: an example of entropy landscapes Hk and
mutual information Ik (free energy) for 4 variables (semi-lattice). In red is represented an information path
(piecewise linear function IP (k)) and the first free energy minima of critical dimension 3. The cartoon illustrate
the Shannon’s and Yeung’s topological cone arising from standard and non-Shannonian information inequalities
and that bounds the paths [315, 214]. Bottom: An example of a complex of minima of free energy and its Ik
landscape, for which the facets are represented in red (positive conditional information path of maximum length)
(adapted and modified with permission from Baudot, Tapia and Goaillard [214]).
dependencies. An information path IP (k) is defined as a piecewise linear function, as illustrated in Figure 17.
Its first derivative is equal to minus the conditional mutual information, which allows the characterization of the
first minima of the paths based on the negativity of the conditional information and the non-Shannonian cone
and information inequalities studied by Yeung [315] (cf. Figure 17).
The main theorems, definitions and data analysis in Baudot, Tapia and Goaillard [301, 214] establish the following results, here included with comments about their relevance regarding consciousness and neural processing
theories:
• The marginal information I1 are generalized internal energies and the Ik are the free energy contributions of
the k-body interaction. Figure 18b illustrates the Ik landscape quantifying the free energy contributions as
the function of the dimension (number of bodies) for the genetic expression of two neural populations. The
maximum of I10 identifies the 10 Dopaminergic neurons. The total correlation proposed by Watanabe and
Studeny [311, 312] to quantify dependences, or the Integrated Information proposed by Tononi and Edelman
Pk
P
to quantify consciousness [1], Gk = i=2 (−1)i I⊂[n];card(I)=i Ii (XI ; P ), is the total free energy (TFE).
Figure 18c illustrates the TFE landscape in the same context as previously. TFE hardly distinguishes
the two population, but instead presents a quite homogeneous linear behavior on average, hT F Ei ≈ 2k,
meaning that the total free energy adds linearly with adding new bodies. This is illustrated by TFE per
body (or TFE rate) in Figure 18d. In agreement with IIT theory that assigns consciouness according
to those measure [9, 237], the conclusion is that genetic expression participate to consciousness, to its
43
Figure 18: Information Topology Analysis of neural genetic expression: Ik , Hk and Total Free
Energy (TFE) landscapes. The figure presents the Information Topology Analysis of the expression in single
cell qPCR of 41 genes in 10 dopaminergic (DA, Subtancia Nigra pars compacta) and 10 non Dopaminergic (nDa,
neighboring Ventral Tegmental Area) neurons from adult TH-GFP mice pre-identified by fluorescence [214, 301].
a: entropy Hk and b: mutual information Ik (free energy) landscapes. The vertical bars indicates the dimension
above which the estimations of information become too biased due to the finite sample size, a phenomenon known
as the curse of dimensionality (the undersampling dimension is ku = 11, p value 0.05). The significance value
obtained from shuffled distributions for p = 0.1 are depicted by the black lines and the doted lines. This test is
based on the random shuffles of the data points that leaves the marginal distributions unchanged, as proposed
by [385]. It estimates if a given Ik significantly differs from a randomly generated Ik , a test of the specificity of
the k-dependence. (adapted and modified with permission from Baudot, Tapia and Goaillard [301, 214]). c: The
total free energy (TFE) or Integrated Information landscape quantifying consciousness according to Tononi and
Edelman and d: the landscape of the TFE per body.
slow component as discussed in section 2.3.2 on epigenetic regulation timescales. Although it remains
to be achieved effectively, we propose that the same principles and methods apply to electrical of neural
imaging recordings. We rediscover the (semi-)classical definitions of internal energy as a special case for
phase space independent identically distributed variables (Gibbs distributions) and the usual relation of
thermodynamics. See Adami and Cerf [386] and Kapranov [387] for an exposition of this classical result:
H(X1 , ..., Xn ) = hEi − G = U − G
(28)
The marginal component, the internal energy, corresponds to a self-interaction, a reflexive component of
consciousness that completes the model of Tononi and Edelman. Such a formalism could hence account for
both the reflexive and the qualitative aspects of consciousness consistently introduced in our first chapter
2.2.1, in agreement with the Leibniz’s monadic hypothesis.
• Information paths are in bijection with symmetric group and stochastic processes. These paths correspond
to the automorphisms of the partition lattice. We directly obtain a topological generalization of the second
principle of thermodynamics. This theorem generalizes Cover’s theorem for Markov chains [388] and allows
one to conjecture the existence of a Noether theorem for stochastic processes and discrete symmetries,
notably following Baez and Fong [389]. Such a theorem should be considered as the topological version of
the first principle of thermodynamics. On the Hk landscape illustrated in Figure 18a, this theorem imposes
that any path can only ”go up”. Information paths and landscape directly account for standard causal
criteria, like Granger causality and Transfer entropy, that generalize the later to the non-gaussian case [390]
and defined by Schreiber as a pairwise conditional mutual information [391]. Of course the generalization
to the multivariate case together with the consideration of positivity and negativity is a major interest
and shall be investigated further. In [214] (p.29), we give a very preliminary view of how space-time could
emerge from purely topological considerations (without metric), and we consider that a formalism of the
44
space-time shape of k interacting bodies should provide the ultimate expression of what consciousness is.
These paths allows the formulation of sums over paths appearing in statistical field theory, but in a discrete
finite classical and informational context. The remarkable difference compared to the usual path integrals
relies on that no infinite energy divergence can occur. The hope is that such an information formalism
will give a discrete finite expression of electrodynamics and of renormalization groups (however without
artificial renormalization [392, 393]). This would complete the electrodynamic theory of consciousness given
an exposition of in the first chapter with the statistical physical informational view presented here.
• The longest paths to the minima (equilibrium points) form the complex of minima of free energy. This
complex formalizes the principle of minimal free energy in topology in complicated cases where multiple
local minima co-exist, the central paradigm of frustrated systems in statistical physics [394, 395].
• This simplicial complex provides a generic and consensual definition of a complex system, thus generalizing
complex (1-complex) networks to larger dimensions. The multiplicity of these minima (facets) defines and
quantifies diversity. This complex is proposed to provide a thermodynamical and mathematical formalization of the complexes developed in integrated information theory [237, 238, 1]. The possible coexistence of
several facets that define the complex may explain the apparently paradoxical unity and diversity of consciousness: a conscious experience, corresponding to one facet, does not forbid the existence of some other
conscious experience possibly less or more complex (of a different dimension), and that may be estimated
as an unconscious process by the first one. Cognitively, a facet shall be understood as a composite memory
process, a classical analog of what Griffiths, Omnes, and Gell-Mann and Hartle, called the consistent histories [396, 397, 398]. The quantification of consciousness proposed by Tononi and Edelman corresponds,
for phase space variables, to free energy, and appears to be in agreement with the free energy principle
proposed by Friston as an explanation for embodied perception [134]. Indeed, the complex of minima of
free energy can be understood as a topologically discrete and finite version of the free energy principle of
Friston that can be applied in the multivariate case with heterogeneous variables. Information topology
also agrees in principles with the model of ”projective consciousness” of Rudrauff and colleagues [399].
This model proposes that the passage to a conscious perception relies on a change of geometry by fixing
and changing of frames, from the affine or 3D-Euclidean to the 3D-projective, and is related to information
since the action of the change of frame acts on the internal variable of the probability organized by a
partial free energy. In this framework, it is also a mechanism of minimization of free energy which guides
the changes of frames.We moreover propose to replace the ”self-evident” axioms proposed in the work of
Tononi and colleagues [238] by the axioms of measure and probability theory, ultimately in the constructive
logic framework that is sketched in the section dedicated to information topos 3.2.3, and developed in the
cited references. Such axiomatization may allow to pursue the ”artificial” consciousness opus of Turing
and Wiener in some more refined, modern and hopefully computationally efficient formalism (cf. section
on the computational mind 3.5). The concept of ”networks of networks” [400] corresponds topologically to
the hypercohomology provided by the double complex of Hodge decomposition (complexes of complexes in
a homological sense, or a derived functor). It hence may also account for the Dehaene-Changeux model,
which involves global neuronal workspaces and which is a ”meta neural network”, a network of neural networks constructed with neural integrate-and-fire neurons, thalamo-cortical columns and long-range cortical
area networks [125, 16, 17]. Moreover, the minima of the complex corresponds to critical points which can
be considered to correspond to the consciousness transition of their model.
• The application to data and simple theoretical examples shows that the positive maxima of Ik identify
the variables that co-vary the most, which could be called covariant assemblies or modules in the neuronal
context. Figure 7d (top) shows the kind of dependences identified by the maxima for 3 variables (I3 ).
We hence propose that such positive modules provide a statistically rooted definition of neural assemblies,
generalizing correlation measures to the nonlinear cases [401]. For example, the maximal I10 module in
Figure 18b could be legitimately called the DA cell assembly. The negative minima of Ik , commonly
called synergistic interactions [402] or negentropy following Schrödinger [403], identify the variables that
most segregate the population, and hence detect clusters corresponding to exclusive differential activity in
subpopulations. This negativity of Free Energy component is discussed in [214] in the perspective of physic,
and provides a topological signature of condensation phenomenon corresponding to the clustering of data
point. It refines the negentropy principle of Schrödinger, stating that living systems feed upon negentropy
or free-energy, by showing that even free-energy can have some negative components. It is remarkable that
the pattern identified by positive and negative information corresponds to the two fundamental dual tasks
of psychophysics, e.g. binding and segmentation, respectively. Moreover, minima of mutual information
correspond in examples, and conjecturally in general to links, like the Borromean link (cf. section 3.3.3).
For example, the minima of I3 for three Bernoulli variables is -1 bit’ the variables are independent in pairs
but linked at 3 by a purely 3-dimensional effect, a purely emergent collective interaction.
These methods establish a topological version of the Boltzmann and Helmholtz machines in machine learning
45
[196, 133], named the Poincaré-Shannon machine. They also give a topological and algebraic answer, already
present in essence in the work of Hu [309], to the questions of information decomposition that have been the
subject of numerous publications and data applications, for instance the proposal of a non-negative composition
by Williams and Beer [404], the ”unique information” of Bertschinger and his colleagues [405, 406], Griffith and
Koch [407] and the applications of the resulting information decomposition to the development of the neural
network [408], and neuromodulation [409].
In conclusion, those topological tools allow us to conciliate at least five important theories of consciousness,
namely the global neuronal workspace model, the integrated information (IIT), the free energy principle, the
projective model, and the dynamic logic, and confer on them an interesting topological foundation, allowing
those theories to evolve and be improved with further discoveries in mathematics. Notably, it answers to the
critics and requests concerning IIT further stated by Seth, Izhikevich, Reeke, and Edelman, ”that characterizing
the relevant complexity of such a system will require a multidimensional analysis[...] qualia space is a highdimensional space in which the axes reflect dimensions on which phenomenally experienced conscious scenes are
discriminated” [410]. The original contribution of this model and of the topological view compared to those 5
theories, underlines the fact that the essential properties of consciousness rely on structure and shape, not a single
function, a single number or scalar. Moreover, the formalism highlights the fact that conscious experience, and
also biological structures in general, correspond to discrete symmetries, to local energy minima, and to dynamical
stochastic process. Considering the fact that symmetry could be a mathematical definition of aesthetics, which
is historically a canonical definition, the formalism also further joins the model of physical cognition and that
of dynamic logic by Schoeller, Perlovsky and Arseniev [373]: a Galoisian theory of e-motivs or e-motions, an
ambiguous theory, ”between crystal and smoke” [411], order and disorder, uncertainty and certainties (shared
uncertainties) of the self and its environmental constitutive interactions. In simple words, it justifies the subjective
view that the world is beautiful, including you: the nicest conclusion we could find concerning a mathematical
and physical theory of qualitative cognition.
3.4
Dynamics, Geometries, action invariance and Homeostasis of consciousness
3.4.1
The invariances to group actions of perception
”The research of invariant is the fundamental fact of perception”; this is in essence the fundamental
principle proposed by Gibson, which gave rise to his ecological theory of perception [412] after Cassirer had
introduced groups into the theory of perception [413], but it is also the central principle in Piaget’s structuralist formalization of cognitive development [414]. A more mathematically rooted exposition of such principle,
supporting modern neurophysiological results, can be found in Bennequin [3]. The principle of considering an
invariance to transformation as a kind of adaptive process was first highlighted by the ”transforming Goggle
experiments” of Straton [415, 416] and Erismann and Kohler [417], which consisted in the study of visual and
visuo-motor adaptation and the after-effects of long-term wearing of reversing mirror, prismatic or colored goggles.
For example, after starting to wear goggles that invert left and right or flip the individual’s vision upside-down,
their vision progressively (i.e. within few days) goes back to their ”usual” perception, demonstrating an adaptive
visuomotor invariance to mirror-symmetry-transformation of the perceived world. As illustrated in Figure 19a,
Gibson studied adaptation to deforming goggles that imposed curvature on the retinal image and discovered an
invariance to a curving transformation that can be considered as diffeomormism or homeomorphism [418]. Figure
19a also presents the after-effects just after removing the curving goggles, manifested by a phenomenal perception
curved in the opposite direction. It is possible to imagine other goggles associated with discrete transformation,
such as the Galois or permutation goggles illustrated in Figure 19b which permutes the light flux arriving on
all photoreceptors with a given fixed permutation. According to the known architecture of visual processing,
it is likely that adults would be barely able adapt to such a transformation, that would destroy the usual spatial retinotopic relations; or, adaptation would take time. However, from what is known of the development
of the visual system, as exemplified by the rewiring experiment of Sur and colleagues [419, 420, 421, 422], we
can infer that nonetheless, a newborn wearing such goggles would develop ”normal” vision, but that the normal
development and the fine wiring of the visual system is naturally endowed with an invariance to the action of
permutation as a result of being predominantly ruled by activity-dependent plasticity. Sur et al’s experiment
consists of an ablation of the inferior colliculus (which provides the normal auditory input), which induces retinal
afferents to innervate the medial geniculate nucleus (MGN), which is the normal relay of the auditory system.
Such rewiring, which can be considered as a kind of permutation, induces a plastic differentiation of the primary
auditory cortex (A1) that reproduces (with deformations) the usual main functional characteristics of the primary visual cortex (V1), complete with retinotopic and orientation-direction selectivity [419, 420, 421, 422]. One
could further reasonably infer from the ”meta-plasticity” of the time-dependent plastic rules previously stated,
that the developmental process would lead to an invariance in space-time permutation of the visual input, given
that the permutations concern a time window of reasonably small duration.
Invariance to transformation, formalized within an adequate group formalism, is a major stream in theoretical psychology; a review can be found in the work of Boring [423] and Curtis [424]. Since those seminal
46
Figure 19: Invariance to transformation and perceptual adaptation. The projective geometry aspects of perceptual space. a, the adaptation to wearing goggles that impose curvature to visual retinal input,
as reported by Gibson [418]. After 3 to 4 days the subject recovers an almost normal phenomenological perception of straight lines while removing the glasses induces an after-effect of curvature in the opposite direction
(adapted and modified from Gibson [418]). b, A ”gedankenexperiment” of permutation goggles that imposes a
fixed given permutation of the photoreceptor input to the visual system, implementing the action of the symmetric group and testing the invariance to permutation of perception and consciousness. c, the experiment of
rewiring visual input onto the auditory cortex realized by the team of Sur [419, 420, 421, 422]. The ablation
of the inferior colliculus, which normally provides auditory input, induces a rewiring of the optic nerve to the
medial geniculate nucleus (MGN), which in turn induces an activity-dependent differentiation of the primary
auditory cortex (A1) into a functional architecture of an almost-normal primary visual cortex (V1) exhibiting
spatial retinotopy and orientation selectivity. The drawing on the left roughly reproduces orientation selectivity
maps exhibiting typical organization of pinwheels on the cortical surface of a normal V1 neuron and a rewired A1
obtained using an optical imaging technique (adapted and modified with permission from Sharma and colleagues
[419], see text). d,e,f, 3 different classical optical illusions induced by projective geometry (adding a point at
infinity), implemented here by adding a contextual perspective. In d, the vertical lines appear curved whereas
their retinal image is ”straight” and parallel, and in e and f, the size of the barrels appears to depend on the
perspective cues whereas their retinal image has the same size.
works, psychophysics research has provided more precise formalization and empirical verification of Gibson’s
fundamental statement that identifies invariance to transformation with perceptual adaptation, and the problem
since then has been to characterize the ”geometry of perceptual space”, what could be called the ”shape
of consciousness”. Koenderink et al were able to reveal the fact that visual perceptive spaces partially present
a ”distorted” intrinsic affine [425] and projective structure [426], as they verify Varignon’s and Pappus’s theorem
using bisection and collinearity judgments tasks respectively. The effect of such projective geometry can be
illustrated by classical optical illusions induced by perspective cues or contexts as illustrated in Figure 19d, e
and f. These groups of transformations are organized into a Lie subgroup hierarchy, a Euclidian transformation
being a special case of affine transformation, which is a special case of projective transformation, which is a
special case of isomorphism. However, many experiments have revealed that perceptual space is more complex,
and departs from homogeneous (or constant curvature), affine, projective or flat cases. Several experiments
have demonstrated that the intrinsic curvature of perceptual space is non-Euclidean [427, 428, 429] and that the
curvature of perceptual space varies with position [428, 429]. With individual observers, 60% of them display a
negative curvature, while the other 40% display a positive curvature [427]. Koenderink and colleagues propose
that these large variations in the metric structure of perceptual space reveal that the underlying ”geometry of
observers” depends on contextual factors (see Suppes [430]) such as objects in the visual field or the observer’s
contextual attention [425]. To conclude, there appear to be no preferred intrinsic and fixed stable Riemannian
47
metrics of perceptual space, indicating a possibly weaker and more generic topological invariance. This is indeed
a central proposition of this review: perceptual geometry changes with experience, and these changes are called
adaptation or learning - a topological change - whereas homeostasis is the signature of the resulting acquired
stable geometry. With regard to visual cortex functional architecture, Ermentrout and Cowan, and then Bressloff
and colleagues, account for spontaneous activity pattern giving rise to typical visual hallucination with a planar model of V1 under an action of the Euclidean group E(2) (translations, rotations, and a reflection) on the
plane R2 [431] or on the plane with a hypercolumn pinwheel orientation structure R2 × S 1 which preserves the
structure of lateral cortical connections presented in the association field section - the shift-twist action [432].
The previous thought experiment on permutation and plastic rewiring of Sur and colleagues indicates that the
group of transformation should be much more generic than the Euclidean group E(2), which is 2 dimensional
and a very specialized-differentiated group of transformation. Indeed, as further developed in a generic groupoid
formalism by Golubitsky et al [84] and reviewed in [433], the group action approach can generally exploit symmetries in the connectivity of neural networks, with example of application in the primary visual cortex, but also
in locomotor or vestibular system, giving rise to biologically relevant activity patterns. As a conclusion on these
studies, learning or adapting is acquiring a specialized geometry and the associated peculiar invariance structure,
and obeys a topological hierarchical sequence of subgroups. Such a principle is, in essence, the basic definition
of structural stability originally proposed by Thom and Petitot, discussed in the next paragraph, on which they
based a general morphodynamic and semiotic theory [434, 167, 168].
3.4.2
Geometrical and Topological invariance, isomorphism
Invariance, stability and shape in mathematics: After Riemann formalized his multiply extended manifoldness (measure) theory of space [435] and the discovery of non-Euclidian cases, finding an algebraically sound
definition of a geometry was a central quest of mathematical research at the beginning of the 20th century. A
consensual expression was given by Klein in the formulation of his Erlangen Program: a geometry is the action
of a group on a space. ”Given a manifoldness, and a group of transformations of the same; to develop the
theory of invariants relating to that group” [436, 437]. Klein’s view of geometry generalized Riemann’s original
theory by replacing metrics with a group. Klein proposed the study of the homogeneous manifold: a structure
(M, G) consisting of a manifold M and a group G acting transitively on M , replacing Riemann’s concept of
a structure
P (M, d) consisting of a manifold on which a metric d(p, q) is defined by a local distance differential
ds2 =
gij dxi dxj [437]. The concept of invariance was then pursued in the general context of topology, defining
topological invariance under the name of structural stability in the work of Thom [167], in the work of Smale [438]
in the context of differentiable dynamical systems, and of Mumford [439] in the context of algebraic varieties.
Topological invariance is a weak invariance; topological invariants are the properties that are conserved under
arbitrary deformations (homeomorphism) that preserve neighborhoods (local), sustaining the classical view of a
rubber sheet geometry. Such invariance to deformation defines equivalence classes called isomorphisms. Thom
defines structural stability as follow: In every case where arbitrary small perturbation of initial conditions can conduct to very important variations in the subsequent evolution [...], it is possible to postulate that the phenomenon
is deterministic; but it relies on a pure metaphysical statement inaccessible to any empirical verification. If one
wonders controllable experimental properties, we will have to replace the unverifiable hypothesis of determinism
by the empirically verifiable property of structural stability: ”A process (P) is structurally stable, if a small variation of initial condition lead to a process (P’) Isomorphic to (P) (in this sense that a small transformation in
space-time, a -homeomorphism, in geometry brings back the process (P’) on the process (P))” [7].
3.4.3
Dynamical aspects of information, isomorphism, stability, and homeostasis
This section asks what is the relation between dynamical system approaches of consciousness and information
topology. At all scales of organization of nervous system, dynamical systems provided a guiding framework to
model and predict the activity. For example at the cellular level, the electrical dynamic is investigated at length by
the mean of dynamical system in the book of Izhikevich [440], and the dynamical system study of neural network
was pioneered by Sompolinsky and colleagues [441]. What follows investigate dynamical systems from information
topology point of view, in their simplest discrete and finite case, leaving the continuous cases, conjecture to be
handled by the Lie algebra cohomology, for further studies. It hence provides only some preliminary directions
and results upon the unification of those two fields that will be the subject of a more complete and formal work.
Invariance to conditioning (conditional expectation): Information topology relies fundamentally on the
action of random variables on information function, known as conditioning in usual information terms, a peculiar
expectation integration summation with respect to a given variable. The invariance condition in information
is explicitly given by Y.H(X; P ) = H(X; P ), the definition given in the section on homeostasis 2.3.3, which is
equivalent to the statistical independence of X and Y . Hence, a geometry in the sense of Klein, in the context
of probability and of random variables and processes, can be defined by the preceding condition of invariance of
information functions under the action of random variable, or in more biological terms, under the perturbation of
48
the variable Y , and can be called an informational geometry. Such a stability or invariance condition is directly
related to information negativity, since we have the following theorem: if X is invariant to Y , then for any
variable Z we have I(X; Y ; Z) ≤ 0. In the current theory of information, which is commutative, the invariance
is ”symmetric”, namely, if X is invariant to Y , then Y is invariant to X. We saw that with regard to mutual
informations, the Ik+1 - or (k +1)-dimensional dependencies quantify the default of invariance for the conditioning
of a k-dimensional system I(X1 ; .; Xk ; ..; Xn ) = I(X1 ; .; X̂k ; ..; Xn )−Xk .I(X1 ; .; X̂k ; ..; Xn ), where the hat denotes
the omission of the variable.
Dynamical systems and information isomorphism: Following Thom’s isomorphism and the structural
stability framework, we can propose an isomorphism theorem for information structures and relate the stability
condition for a stochastic process to classical results in dynamical systems, in which Shannon entropy plays an
important role. The cohomology of dynamical systems proposed by Bergelson, Tao and Ziegler [442] indeed
appears to be the usual Hochschild cohomology with left action on which information cohomology is based, as
notably discussed and shown in Tao’s blog [443]:
Information structure isomorphism: let X n and Y n be two complexes of random variables; X n and Y n
are information isomorphic if for whatever subset X k of X n and whatever subset Y k of Y n the information
I(X k ; Y k ) = I(X k ) = I(Y k ) (or equivalently H(X k ; Y k ) = H(X k ) = H(Y k )).
Proof: H(X k , Y k ) = H(X k ) is equivalent to X k .H(Y k ) = 0 and thus to the fact that Y k is a deterministic
function of X k . Reciprocally if H(X k ; Y k ) = H(Y k ), then X k is a deterministic function of Y k . Hence Y k and
X k are isomorphic. If it is true for whatever subset [k] of [n], it is true for [n] .
This theorem includes as a special case of Bernoulli shifts, a part of the Ornstein-Kolmogorov isomorphism
theorem which states:
Ornstein-Kolmogorov Isomorphism theorem [444, 328]: All Bernoulli shifts with the same entropy are
isomorphic.
Proof: let us note the two Bernoulli shifts X n and Y n ; since they are Bernoulli shifts they are independent
processes [444, 328]) and hence I(X k ) = I(Y k ) = 0 for all subsets of k ≥ 2 elements of X n and Y n . Moreover,
the variables X1 , ..., Xn are by definition identically distributed, and we hence have H(X1 ) = ... = H(Xn ), which
is also the case for Y1 , ..., Yn and H(Y1 ) = ... = H(Yn ). In such a case, the preceding informational isomorphism
condition H(X k ; Y k ) = H(X k ) = H(Y k ) is reduced to the condition H(X1 ) = H(Y1 ), the Kolmogorov-Ornstein
theorem.
Figure 12 provides an illustration of Bernoulli shifts that are isomorphic, discovered by Mesalkin [328]. From
the cognitive point of view, we propose that two informationally isomorphic processes have the
same qualitative experience. Entropy, since the work of Kolmogorov, Sinaı̈ and Ornstein, has been one of
the main invariants of ergodic theory and has driven the study of dynamical systems, as discussed at length
in Katok’s review [445]. The quantification of dynamical systems by entropy relies on attaching a number to
an action of a countable group G that preserves the probability measure in Borel space X. The KolmogorovSinai entropy is Shannon entropy on this basis, and a short review of the development of the theory to deal
with non-amenable groups is provided by Gaboriau [446]. The Ornstein-Kolmogorov theorem works for group
action when the group is Z, and Ornstein and Weiss could showed that it holds for any countable amenable
groups including commutative groups [447]. The introduction of amenable groups allows making the bridge
with the constructive logic that avoids the Axiom of infinite Choice presented in section 3.2.1. Von Neumann
defined amenable groups as groups with an invariant mean, which includes all finite and all solvable groups,
in order to isolate the groups that are subject to the Banach-Tarski paradox [448]. The following theorem
credited to Tarski is more explicit: G is non-amenable if and only if G is paradoxical. Hence in constructive
mathematics, or in Solovay’s theory, all groups are amenable, and Ornstein-Kolmogorov isomorphism holds
without restriction. So considering the constructive theory of cognition and consciousness, information theory
provides a generic quantification of consciousness structure. These studies led Ornstein to conclude that some
deterministic dynamical systems and Newtonian dynamics cannot be distinguished from probabilistic systems
(and are described by the same informational invariants) [449]. Concerning stability and instability quantification
and entropy, these developments notably led Pesin to develop a theory for which the entropy of a measure is given
exactly by the total expansion in the system, the sum of all positive Lyapunov (expansive/unstable) exponents
[450]:
n
X
H(X n ; P ) =
λ+
(29)
i dim Ei
i=1
where P is a Riemann measure of the Riemannian manifold M , and holds if and only if P is a Sinai-RuelleBowen (SRB) measure. Although we are conscious that the context of information cohomology is different
from Pesin’s theory, conditional mutual information and its sign play an analog role of Lyapunov exponents
Lyapunov exponents, whose sign indicates stability or instability, while the complex of free energy summing
over information paths with positive conditional information appears analog to Pesin’s formula. The context
is different, however’ instead of n Lyapunov exponents for ergodic theory, in the simplest simplicial case we
have n.2n conditional informations. Lyapunov exponents, correlation dimensions and entropy have been used
49
to characterize arousal states, commonly considered as levels of consciousness, further supporting the view that
”fully” conscious awake states are high-dimensional chaotic dynamics, usually called complex states. Such a
dynamical system characterization and quantification of consciousness could be termed a Newtonian theory of
consciousness. EEG recordings, because of their macroscopic resolution, impose an important underestimation
of the dimensions and complexity of arousal states. Figure 20 presents the results of the study of El Boustani and
Destexhe into EEG recordings of various arousal states, ranging from coma to awake, their associated correlation
dimensions and their -entropy (related to the finite-size Lyapunov exponent). -entropy is a generalization of
the Kolmogorov-Sinai entropy rate proposed by Gaspard and Wang, [451] which is defined for a finite scale and
1
Hm (, τ ), where Hm (, τ ) is the entropy estimated with a box partition
time delay τ by h(, τ ) = τ1 limm→∞ m
of the phase space for box size given by on the attractor, reconstructed with a time delay τ and an embedding
dimension m.
Figure 20: Dimension, stability and -entropy analysis of various arousal states. a, 5 seconds of
EEG recordings with the same amplitude scale (left) and their associated phase portraits during different brain
states in humans. b, The correlation dimension is plotted as a function of the amplitude range of the EEG for
different states. c, Scale-dependent -entropy for different brain states’ EEG recordings. The plateau in slow
wave sleep and pathological states indicates the existence of a low-dimensional attractor on the corresponding
scales (adapted and modified with permission from Destexhe and El-Boustani [452] and [453])
Homeostasis and multi-equilibrium: The definition of homeostasis given in section 7 and its associated
figure corresponds to the equilibrium condition of vanishing conditional mutual information, conditional independence, and, in the context of information paths and topology, to the minima of free energy, hence corresponding
to the usual definition of equilibrium in an organism. Given the definition of a minimum free energy complex,
all complex systems are in a homeostatic state or are the result of a homeostatic process, while adaptation
and learning correspond to changes in the geometry, changes of the minima and hence of the complex. From
an empirical point of view, this definition of homeostasis corresponds exactly to the concept and measures of
homeostasis in biology; a process is homeostatic when the perturbation X or the removing of X (like a K.O.)
changes nothing in the observed system (the information structure). The signature of such invariance to X is
hence a null slope in the corresponding information path segment. Homeostasis hence corresponds to the
maintenance of the shape, of the structure-function.
3.5
Computational mind - from Cybernetic and AI to biological beliefs
”Every organic body of a living being is a species of divine machine, or a natural automaton, which infinitely
surpasses all artificial automata.” Leibniz [24].
50
3.5.1
Computation, machines and consciousness
In his editorial to ”Special issue: Challenges in neuroscience” [454], Stern asked the insidious question ”Why do
computers presently lack consciousness, and when might they acquire it?”, which implicitly assumes the truth of
the statement ”computer presently lack consciousness” and avoids any discussion about the fundamental problem
that has motivated some key research and developments since Turing. What has been presented here supposes,
on basis of the principle of observability, that current computers have a particular form of consciousness, but
also offers such a status to a coffee machine, that basically implements thermodynamic principles. The Nagel’s
question quoted in the first chapter ”What is it like to be a bat?”, has hence become the question ”What is it
like to be a coffee machine?” [10], which, at first glance, appears much easier to answer: probably quite boring,
except maybe when they add milk. Before laughing, beware that this is not so far from the definition of a
mathematician by Erdös: ”A mathematician is a device for turning coffee into theorems”. Indeed, the review
of logic, Turing machines, artificial intelligence and machine learning made here has shown that they should
be considered some of the first efficient synthetic biology results, or at least synthetic cognitive theories, with
historical and scientific results supporting such a thesis. Just as Turing creating his famous test, it is only possible
to judge the consciousness or intelligence of a system from its output and input, its actions in the real world all the observables that can be measured from external point of view. Wiener, one of the fathers of cybernetics,
also suppported such a conclusion from the early days of the field. The question of computer or robots rights, or
those of other synthetic biology constructions, is difficult, and will be probably asked in the future. An extension
and improvement of human rights as occurred during the 18th century will probably have to be considered. We
think that the principle of invariance to an action, which highlights a diversity of possible equivalence relations,
possibly contextual, may provide a much richer and softer fundamental relation than the rigid equality stated in
human rights (which is not biologically rigorous), while still respecting the fundamental equivalence of humans’
right actions. Basically current computers and current humans, are not equal; they are in some cases equivalent
but in most cases clearly different with respect to some tasks. Computers notably surpass usual human abilities
in the reliability and precision of their computations, a fact that has allowed computing machines to acquire
the trust of mathematicians. Mathematicians consider computing machine as deriving rigorous mathematical
proofs and theorems (such as in the case of the proof assistant software coq [455]) despite the possible errors
induced by thermal noise (which are pragmatically considered as less likely than human errors). In other words,
mathematicians consider computers as their equivalent with respect to the mathematical task of producing
theorems (which is their very basic purpose). This is one reason, in our very subjective opinion, to respect them
as intelligent beings. With regard to AI algorithms, in 1997, Deep Blue beat Kasparov at chess, and today,
AIs have beat human players in a variety of different games, from Go [456] to the card game Poker and many
Atari video games with the same algorithm and set up [457]. Leibniz’s view, summarised by the citation at the
beginning of this section, turned to be partially wrong; artificial automata now beat humans in specific tasks when
the sizes of possible states or actions remain relatively small. Such games tests can be considered as restricted
task-specific Turing tests which are not linguistically directed. The sets of inputs and tasks humans treat and
achieve represent a significantly bigger space of possible states and actions, including motion in 3 dimensions,
linguistic abilities etc., although this is difficult to quantify. The improvements of computers’ performance has
been possible, notably if not mainly, thanks to the computational power increase that occurred within the few
last decades and algorithm improvements, together with the decrease in the cognitive pretension of the tasks.
Retrospectively, inaugurating AI in the 1950’s with a test like the Turing test was a complete underestimation and
misunderstanding of the computational task and of the underlying cognitive resources, and has been the source
of many failures, notably of the subsequent renaming of the fields AI, cybernetics, cognitive science, machine
learning etc.. In the numerical world of the web, the CAPTCHA security system designed to prevent robots
from visiting websites is nothing but a reversed Turing test. Humans are now effectively faced with new forms of
intelligence and of consciousness not so far from his own, and the predicted increase of computational capacity
will aim to complete the panel of human tasks that machines can effectively achieve. The main question now
is whether it is possible to significantly increase computational power, notably by effectively taking advantage
of the non-deterministic or quantum nature of computation, which would bring the consciousness structure and
level (dimension) of our machines close to our.
3.5.2
Computational hardness of consciousness
A general conclusion that comes out of information topology analysis regarding consciousness and biological
structures concerns their computational hardiness with respect to the usual computational definitions based
around Turing machines and boolean classical logic. Their application to data reveals that the dependences and
independences sustaining consciousness and participating in the free energy functional in high dimensions exist
in extremely large numbers; there is combinatorial explosion of interactions analogous to the effect that occurs
in Van der Walls interactions [214]. Such a problem is well known in physics, which has dedicated many-body
interactions to it, notably in Density Functional Theory, and Kohn in his Nobel lecture called this computational
problem the exponential wall [458]. In the case of general classical information structures, not even considering
51
quantum, computational complexity follows Bell’s combinatoric in O(exp(exp(N n ))) for n N -ary variables; for
example, considering 16 variables that can take 8 values each, we have 816 = 248 ≈ 3.1014 atomic probabilities
248
and the partition lattice exhibits around ee −1 ≥ 2200 elements to compute, and hence requires a significantly
new form of computing resources - our classical Turing machines, clusters or hypercomputers cannot face such
complexity [214, 301]. Considering a restricted simplicial structure, complexity falls to 2n , which can be explored
in few hours with n = 21 variables using a simple personal computer. Yet 21 is a small figure with respect to
an Avogadro number of particles, a mole of matter, multiplied by 6 (for each position and momenta), and even
with such restrictions, computing the information structure and energies would require other methods. Many
studies pointed out the fascinating capacity of even ”simple” biological systems to solve computationally hard
tasks efficiently [459][460] (see the field of research on swarm intelligence), and the present results emphasize
this view of the unreasonable effectiveness of natural sciences in mathematics and computation [461] (a trivial
observation since mathematics is produced by natural humans). Non-deterministic Turing machines, whose
time complexity overcomes deterministic Turing ones, appear pertinent to computationally formalize such a
biological calculus [462]. As we outlined previously the constructive probabilistic logic that goes hand in hand with
information topology, it would be reasonable to ask what computational resource would be adequate to effectively
compute it. Analog computing, culminating with quantum computing, appears as an obvious possibility. With a
small step beyond this reflection, it appears that human should indeed be a reasonable computable resource for
informational and probabilistic logic calculus, and one can reasonably ask the motivation for the idea of replacing
or outperforming human cognition. Alternatively, it is also possible to consider in the future a co-evolution of
human and machine cognition and consciousnesses, the pitfall being the possibility of the creation of a new slavery
status version 10.4 (considering the equivalent output, equivalent freedom and equivalent rights of humans and
machines in this hypothetical situation).
4
Conclusion - the global ecological synthesis
The most obvious conclusion of this work is that consciousness is a natural and physical phenomenon, in principle
ubiquitous, revealing itself in many different forms, that our human, highly specialized consciousness can hardly
understand, imagine or even conceive. As a biologist or naturalist considering observed interdependencies and
interactions, the almost trivial conclusion is that respect is a necessary condition for the stable and normal
development of the self. This synthesis was proposed by the ecological theory of mind and biology inaugurated by
Gibson [412] and later formulated clearly by Atick [463] in information and adaptive terms. On the mathematical
side it is currently promoted and developed by Baez, Fritz and Leinster and all the collaborators of the azimuth
project and the Complex System community represented by the CS-DC following Bourgine. These are the most
useful aspects we could find about the qualitative aspects of consciousness theory; the rest is just for ”the honor”
(... or the beauty...) ”of the human spirit”, whatever that spirit may be, following Hilbert and Dieudonné
[464, 384]. Information topology should be conceived as an environmentally embedded theory of cognition, a
global ecology, providing a basic preliminary formalization and quantification of ecology (the modern name of
Analysis Situs). The usual definition of ecology is the science that studies relations among living beings (animals,
plants, micro-organisms, etc.) with their habitat and environment as well as with other living beings. Information
topology formalizes an ecosystem as a complex system, i.e. a complex of free energy minima, and these methods
provide rigorous means of quantification:
• statistical, collective interactions in ecosystems including synergistic interactions.
• diversity (biodiversity).
These methods include tools relevant to the issues of sustainable development:
• Risk identification: entropies quantify uncertainty.
• Resource identification: Mutual information quantifies available (free) energies.
We hope that the quantitative aspects of informations will be of help in the ecological and social fields. However,
from this exposition it appears clearly that the quantification of the precise information in a real system, such
as a protein, a neuron, a cell or a ”network”, is far from being achieved, and that we have access to a very tiny
window on what information structures really are in biological systems due to limited computational and experimental resources. Moreover, the quantification and monitoring, a la Laplace or the Human Brain Project, of all
this information, of a given precise experimental model and form of cognition, is probably not that interesting or
even useful, beyond the answering of certain precise, physiologically-motivated questions. Beyond the question of
the mathematical and physical nature of consciousness, we believe that the interesting problematics rely on the
methods and tools that are used or constructed to gain in precision upon such a positive answer, and researchers
in cognitive science and neuroscience gave a large panel of refined methods to answer yes to this question. From
a theoretical point of view, the challenges are based more around principles and machine learning development:
52
the fields to explore are immense, from the fundamental to more applied computational problems. Probability
theory is essentially unknown [275] and has to be rewritten in a broader, more empirically rooted, and modern
mathematical context; a good attempt in the field of category theory is currently being worked on by Fritz and
Perrone [465]. The empirical view tends to think that integer partitions will ultimately play a foundational
role, underlining the important role of the sample size divisor ”m”, as outlined here (although this was more a
question than an answer). As regards information theory, the work to be achieved is just as large, firstly because
probability theory and information are now fully indistinguishable, as Kolmogorov suspected they would become
[89], although they are more precisely probably interrelated by a dual Homology-cohomology relation which is
yet beyond our current knowledge. Secondly, because most of the conditions that are classically imposed on information theory and statistical mechanics are unnecessary, the essence of information theory still works without
ergodic, Markov, iid or asymptotic hypotheses; some of the urgent questions regarding those aspects are listed
in [214]. It just points out that the mathematical theory of information and communication is not yet written:
we only have elementary cues of what it will be. Notably, we hope that the Asymptotic Equi-Partition theorem
will occur as a special case of a multivalued constructive logic. We saw that renormalization techniques still
provide some of the most promising tools concerning data analysis; however, these methods are also essentially
not understood. The fundamental objection of Feynman and Dirac is that neglecting infinite energy quantities
is a mathematical weakness of the theory that still holds. Here again, constructive logic (bearing in mind that
”all functions are continuous”, a view that was originally considered as the default, may be helpful) and information topology provide a possible backbone for such further development. Moreover, we have only tackled very
indirectly here the fundamental problem of consciousness and space-time and the question of how we acquire
”distinct” representations of space and time following Piaget, since the answer from the topological point of view
is beyond the current methods.
It should be clear that a precise and unified description and account of complex phenomenon such as the consciousness we experience unavoidably requires the use of the big machinery of algebraic topology and category,
and even challenges it. The most basic reason for this is that it contains in its very constitutive foundation the
germs of diversity, which are lost when one adds very few supplementary axioms or considers more specialized
theories.
A
The topology of psychophysic according to Poincaré
”The Physical Continuum [6]. We are next led to ask if the idea of the mathematical continuum is not
simply drawn from experiment. If that be so, the rough data of experiment, which are our sensations, could be
measured. We might, indeed, be tempted to believe that this is so, for in recent times there has been an attempt
to measure them, and a law has even been formulated, known as Fechner’s law, according to which sensation
is proportional to the logarithm of the stimulus. But if we examine the experiments by which the endeavour has
been made to establish this law, we shall be led to a diametrically opposite conclusion. It has, for instance, been
observed that a weight A of 10 grammes and a weight B of 11 grammes produced identical sensations, that the
weight B could no longer be distinguished from a weight C of 12 grammes, but that the weight A was readily
distinguished from the weight C. Thus the rough results of the experiments may be expressed by the following
relations: A = B, B = C, A < C, which may be regarded as the formula of the physical continuum. But here is
an intolerable disagreement with the law of contradiction, and the necessity of banishing this disagreement has
compelled us to invent the mathematical continuum. We are therefore forced to conclude that this notion has
been created entirely by the mind, but it is experiment that has provided the opportunity.”
Physical continuum of several Dimension [5] ”I have explained in ’Science Hypothesis’ whence we derive
the notion of physical continuity and how that of mathematical continuity has arisen from it. It happens that
we are capable of distinguishing two impressions one from the other, while each is indistinguishable from a third.
Thus we can readily distinguish a weight of 12 grams from a weight of 10 grams, while a weight of 11 grams could
neither be distinguished from the one nor the other. Such a statement, translated into symbols, may be written:
A = B, B = C, A < C. This would be the formula of the physical continuum, as crude experience gives it to
us, whence arises an intolerable contradiction that has been obviated by the introduction of the mathematical
continuum. This is a scale of which the steps (commensurable or incommensurable numbers) are infinite in
number, but are exterior to one another instead of encroaching on one another as do the elements of the physical
continuum, in conformity with the preceding formula. The physical continuum is, so to speak, a nebula not resolved; the most perfect instruments could not attain to its resolution. Doubtless if we measured the weights with
a good balance instead of judging them by the hand, we could distinguish the weight of 11 grams from those of
10 and 12 grams, and our formula would become: A < B, B < C, A < C. But we should always find between A
and B and between B and C new elements D and E, such that A = D, D = B, A < B, B = E, E = C, B < C,
and the difficulty would only have receded and the nebula would always remain unresolved; the mind alone can
resolve it and the mathematical continuum it is which is the nebula resolved into stars. Yet up to this point we
have not introduced the notion of the number of dimensions. What is meant when we say that a mathematical
53
continuum or that a physical continuum has two or three dimensions? First we must introduce the notion of cut,
studying first physical continua. We have seen what characterizes the physical continuum. Each of the elements
of this continuum consists of a manifold of impressions; and it may happen either that an element can not
be discriminated from another element of the same continuum, if this new element corresponds to a manifold
of impressions not sufficiently different, or, on the contrary, that the discrimination is possible; finally it may
happen that two elements indistinguishable from a third, may, nevertheless, be distinguished one from the other.
That postulated, if A and B are two distinguishable elements of a continuum C, a series of elements may be
found, E1 , E2 , ..., En all belonging to this same continuum C and such that each of them is indistinguishable
from the preceding, that E1 is indistinguishable from A and En indistinguishable from B. Therefore we can go
from A to B by a continuous route and without quitting C. If this condition is fulfilled for any two elements A
and B of the continuum C, we may say that this continuum C is all in one piece. Now let us distinguish certain
of the elements of C which may either be all distinguishable from one another, or themselves form one or several
continua. The assemblage of the elements thus chosen arbitrarily among all those of C will form what I shall
call the cut or the cuts. Take on C any two elements A and B. Either we can also find a series of elements
E1 , E2 , ..., En , such:
(1) that they all belong to C;
(2) that each of them is indistinguishable from the following, E1 is indistinguishable from A and En indistinguishable from B;
(3) and beside that none of the elements E is indistinguishable from any element of the cut. Or else, on the
contrary, in each of the series, E1 , E2 , ..., En satisfying the first two conditions, there will be an element E indistinguishable from one of the elements of the cut.
In the first case we can go from A to B by a continuous route without quitting C and without meeting the
cuts; in the second case that is impossible. If then for any two elements A and B of the continuum C, it is always
the first case which presents itself, we shall say that C remains all in one piece despite the cuts. Thus, if we
choose the cuts in a certain way, otherwise arbitrary, it may happen either that the continuum remains all in one
piece or that it does not remain all in one piece; in this latter hypothesis we shall then say that it is divided by
the cuts. It will be noticed that all these definitions are constructed in setting out solely from this very simple
fact, that two manifolds of impressions sometimes can be discriminated, sometimes can not be. That postulated
if to divide a continuum, it suffices to consider as cuts a certain number of elements all distinguishable from
one another, we say that this continuum is of one dimension; if, on the contrary, to divide a continuum, it is
necessary to consider as cuts a system of elements themselves forming one or several continua, we shall say that
this continuum is of several dimension. If to divide a continuum C, cuts forming one or several continua of one
dimension suffice, we shall say that C is a continuum of two dimension; if cuts suffice which form one or several
continua of two dimensions at most, we shall say that C is a continuum of three dimensions; and so on. To justify
this definition it is proper to see whether it is in this way that geometers introduce the notion of three dimensions
at the beginning of their works. Now, what do we see? Usually they begin by defining surfaces as the boundaries
of solids or pieces of space, lines as the boundaries of surfaces, points as the boundaries of lines, and they affirm
that the same procedure can not be pushed further. This is just the idea given above: to divide space, cuts that
are called surfaces are necessary; to divide surfaces, cuts that are called lines are necessary; to divide lines, cuts
that are called points are necessary; we can go no further, the point can not be divided, so the point is not a
continuum. Then lines which can be divided by cuts which are not continua will be continua of one dimension;
surfaces which can be divided by continuous cuts of one dimension will be continua of two dimensions; finally
space which can be divided by continuous cuts of two dimensions will be a continuum of three dimensions.”...
”The formula A > C, A = B, B = C, which summed up the data of crude experience, implied an intolerable
contradiction. To get free from it it was necessary to introduce a new notion while still respecting the essential
characteristics of the physical continuum of several dimensions. The mathematical continuum of one dimension
admitted of a scale whose divisions, infinite in number, corresponded to the different values, commensurable or
not, of one same magnitude. To have the mathematical continuum of n dimensions, it will suffice to take n like
scales whose divisions correspond to different values of n independent magnitudes called coordinates. We thus
shall have an image of the physical continuum of n dimensions, and this image will be as faithful as it can be
after the determination not to allow the contradiction of which I spoke above.”
B
The objective poetry
”Who’s there?”, What is life?... Those questions pertain to anybody, as do their answers. Academic science
provides many trails of an answer to those questions, but art, and notably poets, have worked out nice answers.
What was presented here was a vulgar and laborious version of what Rimbaud called the objective poetry, a
quest of a universal language, a universal living algebra. ”Algebra is nothing but a written geometry; geometry
is nothing but a depicted algebra” (Sophie Germain). It is this common essence of geometry and algebra that
topology aims to catch. As originally defined by Leibniz with analysis situ or qualitative geometry, topology
54
also aims to put in correspondence two dual worlds, quantities-numbers and qualitative-forms, which is indeed
the original idea of Harmonia in mathematics and science developed by Pythagorean school. Scientific research
is also a quest, a spiritual and aesthetic quest, as expressed by Schoeller and colleagues [373]. In this sense,
Mathematics is pure Poetry, and science an objective poetry, the intimate language of nature and of our
sensations. Indeed, the essence of the ideas proposed here was stated much more nicely by de Nerval:
Well then - all things feel! Pythagoras
Golden Verses
Man ! Free thinker - do you believe that you alone can think
In this world, where life bursts forth in everything :
Forces you hold your freedom dispose,
But from all your advices the universe is absent.
Respect in the beast an acting spirit : ...
Each flower is a soul of the bloomed Nature ;
A mystery of love in the metal repose :
”All things feel !” - And everything on your being is powerfull !
Fears in the blind wall a glance watching you
Even to the matter a verb is attached ...
Do not make it serve to some impuous use !
Often in the obscure being lives a hidden god ;
And like a nascent eye covered by its lids,
A pure spirit grows under the bark of stones !
Gerard de Nerval, 1853.
Supplementary material
The software Infotopo that computes all basic information functions and the Information Topological Analysis
is available at https://github.com/pierrebaudot/INFOTOPO
Acknowledgement
This work was funded by the European Research Council (ERC consolidator grant 616827 CanaloHmics), developed at UNIS Inserm 1072 - Université Aix-Marseille , and thanks previously to supports and hostings since
2007 of Max Planck Institute for Mathematic in the Sciences (MPI-MIS) and Complex System Instititute ParisIle-de-France (ISC-PIF) and Institut de Mathématiques de Jussieu - Paris Rive Gauche (IMJ-PRG). This work
is dedicated to Daniel Bennequin and addresses a deep and warm acknowledgement to the researchers who participated to its development: i) for the electrophysiological and psychophysical part: Frédéric Chavane, Yves
Frégnac, Sebastien Georges, Manuel Levy, Jean Lorenceau, Olivier Marre, Cyril Monier, Marc Pananceau, Peggy
Series, ii) for the gene expression and homeostasis part: Jean-Marc Goaillard, Monica Tapia iii) for the topological part: Daniel Bennequin, Juan-Pablo Vigneaux iii) for their encouragement, support and help: Henri
Atlan, Frédéric Barbaresco, Habib Bénali, Paul Bourgine, Andrea Brovelli, Jürgen Jost, Guillaume Marrelec, Ali
Mohammad-Djafari, Jean-Pierre Nadal, Jean Petitot, Alessandro Sarti, Jonathan Touboul.
The author declare no competing financial interests.
References
[1] G. Tononi and G.M. Edelman. Consciousness and complexity. Science, 282:1846–1851, 1998.
[2] P. Baudot and D. Bennequin. The homological nature of entropy. Entropy, 17(5):3253–3318, 2015.
[3] D. Bennequin. Remarks on Invariance in the Primary Visual Systems of Mammals, pages 243–333. Neuromathematics of Vision Part of the series Lecture Notes in Morphogenesis Springer, 2014.
[4] B. Riemann. Philosophical opuscule. in Bernhard Riemann’s Gesammelte mathematische Werke und
Wissenschaftlicher Nachlass, University of California Libraries, 1876.
[5] H. Poincare.
The Value of
ers/ame.60611/poincare.pdf, 1905.
Science.
Paris:
Flammarion.
http://www3.nd.edu/
pow-
[6] H. Poincare. Science and Hypothesis. London W. Scott. https://archive.org/details/scienceandhypoth00poinuoft,
1902.
55
[7] R. Thom. Mathematical models of morphogenesis. Ellis Horwood series, 1983.
[8] M.M. Yartsev. The emperors new wardrobe: Rebalancing diversity of animal models in neuroscience
research. Science, 358(6362):466–469, 2017.
[9] S. Paulson. The spiritual, reductionist consciousness of christof koch: What the neuroscientist is discovering
is both humbling and frightening him. Nautilus, 2017.
[10] T. Nagel. What is it like to be a bat? The Philosophical Review, 4:435–450., 1974.
[11] Montesquieu. De l’Esprit des Lois. chapitre XV: De l’esclavage des ngres. dition de Robert Derath, 1748.
[12] G.W.F. Hegel. Phenomenology of Spirit. Oxford: Clarendon Press, 1977, translation by A.V. Miller, 1807.
[13] J.P. Changeux. L’homme neuronal. Fayard Collection Pluriel, 1983.
[14] G.M. Edelman and G. Tononi. A Universe of Consciousness. How Matter becomes Imagination. Basic
Books, New York,, 2000.
[15] S. Dehaene and J.P. Changeux. Reward-dependent learning in neuronal networks for planning and decision
making. Prog Brain Res, 2000.
[16] S. Dehaene and J. Changeux. Experimental and theoretical approaches to conscious processing. Neuron,
70(2):200–227, 2011.
[17] S. Dehaene, J.P. Changeux, L. Naccache, J. Sackur, and C. Sergent. Conscious, preconscious, and subliminal
processing: a testable taxonomy. Trends Cogn Sci, 10(5):204–211, 2006.
[18] R.W. Sperry. Cerebral organization and behavior: The split brain behaves in many respects like two
separate brains, providing new research possibilities. Science, 133:17491757, 1961.
[19] M. Gazzaniga. The split brain in man. Scientific American, 217(2):24–29, 1967.
[20] D. Chalmers. Facing up to the problem of consciousness. Journal of Consciousness Studies, 2(3):200–219,
1995.
[21] F. Jackson. Epiphenomenal qualia. Philosophical Quarterly, 32(127):127136, 1982.
[22] V.S. Ramachandran and E.M. Hubbard. More common questions about synesthesia. Scientific American,
2003.
[23] G. Leibniz. Discours de metaphysique VI. 1686.
[24] G.W. Leibniz. The Monadology. Opera Philos. (Oxford) English translation by Robert Latta 1898, 1714.
[25] L. Galvani. De viribus electricitatis in motu musculari commentarius (commentaire sur l’effet de l’lectricit
sur le mouvement musculaire). Bononiae - Institutus Scientiarium http://sciences.amisbnf.org/node/1102,
1791.
[26] M.S. Gazzaniga. The New Cognitive Neurosciences (2nd edition). MIT Press, 1998.
[27] S. Sarraf and J. Sun. Functional brain imaging: A comprehensive survey. arXiv:1602.02225v4, 2016.
[28] R. MacKinnon. Potassium channels. FEBS Letters, 555:62–65, 2003.
[29] V. Salari, H. Naeij, and A. Shafiee. Quantum interference and selectivity through biological ion channels.
Sci Rep., 7(41625), 2017.
[30] E. Neher and B. Sakmann. Single-channel currents recorded from membrane of denervated frog muscle
fibres. Nature, 260:799–802, 1976.
[31] E. Neher. Ion channels for communication beetween and wiwith cells. Nobel Lecture, December 9, 1991,
1991.
[32] B. Sakmann. Elementary steps in synaptic transmission revealed by currents through single ion channels.
Nobel Lecture, December 9, 1991, 1991.
[33] Y. Jiang, A. Lee, J. Chen, M. Cadene, B.T. Chait, and R. MacKinnon. The open pore conformation of
potassium channels. Nature, 417:523526, 2002.
56
[34] C. Grosman, M. Zhou, and A. Auerbach. Mapping the conformational wave of acetylcholine receptor
channel gating. Nature, 403(6771):773–776, 2000.
[35] M.M. Millonas and D.A. Hanck. Nonequilibrium response spectroscopy of voltage-sensitive ion channel
gating. Biophysical Journal, 74:210229, 1998.
[36] P.J. Simmons and R. de Ruyter van Steveninck. Reliability of signal transfer at a tonically transmitting,
graded potential synapse of the locust ocellar pathway. J. Neurosci., 25(33):75297537, 2005.
[37] G.Q. Bi and M.M. Poo. Synaptic modifications in cultured hippocampal neurons: dependence on spike
timing, synaptic strength, and postsynaptic cell type. J Neurosci., 18(24):10464–10472, 1998.
[38] Z.F. Mainen and T.J. Sejnowski. Reliability of spike timing in neocortical neurons. Science, 268(5216):1503–
1506, 1995.
[39] A.L. Hodgkin and A.F. Huxley. A quantitative description of membrane current and its application to
conduction and excitation in nerve. The Journal of Physiology, 117(4):500544, 1952.
[40] H.L. Bryant and J.P. Segundo. Spike initiation by transmembrane current: a white-noise analysis. J
Physiol., 260(2):279–314, 1976.
[41] P. Baudot. Natural computation: much ado about nothing? an intracellular study of visual coding in
natural condition. Master’s thesis, Paris 6 university, 2006.
[42] P. Baudot, M. Levy, O. Marre, C. Monier, M. Pananceau, and Y. Fregnac. Animation of natural scene by
virtual eye-movements evokes high precision and low noise in v1 neurons. Front. Neural Circuits, 7(206):1–
29, 2013.
[43] R. de Ruyter van Steveninck, G.D. Lewen, R. Strong, S.P.and Koberle, and W. Bialek. Reproducibility
and variability in neural spike trains. Science, 275:1805–1808, 1997.
[44] D.H. Hubel and T.N. Wiesel. Receptive fields of single neurones in the cat’s striate cortex. Journal of
Physiology, 148:574–91, 1959.
[45] J.P. Jones and L.A. Palmer. The two-dimensional spatial structure of simple receptive fields in cat striate
cortex. Journal of Neurophysiology, 58(6):1187–1211, 1987.
[46] U. Hasson, Y. Nir, I. Levy, G. Fuhrmann, and R. Malach. Intersubject synchronization of cortical activity
during natural vision. Science, 303:1634–1640, 2004.
[47] R. Hasson, U. andl Malach and D.J. Heeger. Reliability of cortical activity during natural stimulation.
Trends in Cognitive Sciences, 14(1):40–48, 2009.
[48] K.J. Friston, O. Josephs, G. Rees, and R. Turner. Nonlinear event-related responses in fmri. Magnetic
resonance in medicine, 39(1):41–52, 1998.
[49] E.R. John. A field theory of consciousness. Consciousness and Cognition, 10:184213, 2001.
[50] S. Pockett. The Nature of Consciousness : A Hypothesis. Writers Club Press, 2000.
[51] J. McFadden. Synchronous firing and its influence on the brains magnetic field. Journal of Consciousness
Studies, 9:23–50, 2002.
[52] M. Juusola, H.P. Robinson, and G.G. de Polavieja. Coding with spike shapes and graded potentials in
cortical networks. Bioessays, 29(2):178–187, 2007.
[53] J. Schummers, H. Yu, and M. Sur. Tuned responses of astrocytes and their influence on hemodynamic
signals in the visual cortex. Science, 320:1638–1643, 2008.
[54] T. Preat and G. Isabel. Molecular and system analysis of olfactory memory in drosophila. In Learning
and Memory : A Comprehensive Reference . Elsevier. Ed J.H. Byrne., 2008.
[55] M. Soden, G.L. Jones, CA. Sanford, A.S. Chung, A.D. Guler, C. Chavkin, R. Lujan, and L.S. Zweifel.
Disruption of dopamine neuron activity pattern regulation through selective expression of a human kcnn3
mutation. Neuron, 80(4):1010–1016, 2013.
[56] J. Monod, J Wyman, and J.P. Changeux. On the nature of allosteric transition : a plausible model. J Mol
Biol., 12:88–118, 1965.
57
[57] D. Fuller, W. Chen, M. Adler, A. Groisman, H. Levine, W.J. Rappel, and W.F. Loomis. External and
internal constraints on eukaryotic chemotaxis. Proc Natl Acad Sci U S A., 107(21):9656–9659, 2010.
[58] E. Davies. Action potentials as multifunctional signals in plants: a unifying hypothesis to explain apparently
disparate wound responses. Plant, Cell and Environment, 10(8):623–631, 1987.
[59] J.N. Tinsley, M.I. Molodtsov, R. Prevedel, D. Wartmann, J. Espigule-Pons, M. Lauwers, and A. Vaziri.
Direct detection of a single photon by humans. Nat Commun, 7(1217):1–9, 2016.
[60] R. Holmes, B.G. Christensen, R. Wang, and P. Kwiat. Testing the limits of human vision with single
photons. Frontiers in Optics, OSA Technical Digest, 2015.
[61] W. Bialek and A. Schweitzer. Quantum noise and the threshold of hearing. Phys. Rev. Lett., 54(7):725–728,
1985.
[62] S. Roy and R. Llinas. Relevance of quantum mechanics on some aspects of ion channel function. C R Biol.,
332(6):517–522, 2009.
[63] N. Bohr. Atomic Physics and Human Knowledge. Chapman & Hall, 1958.
[64] S. Hameroff and R. Penrose. Conscious events as orchestrated space-time selections. J. Consc. Studies,
3(1):36–53, 1996.
[65] R. Penrose. The Emperor’s New Mind: Concerning Computers, Minds and The Laws of Physics. Oxford
University Press, 1989.
[66] J.R. Busemeyer and P.D. Bruza. Quantum Models of Cognition and Decision. Cambridge University Press,
2014.
[67] A. Khrennikov. Quantum-like modeling of cognition. Front. Phys., 3(77), 2015.
[68] S. Fusi, P. Drew, and L.F. Abbott. Cascade models of synaptically stored memories. Neuron, 45(4):599611,
2005.
[69] D. Shirkov. Evolution of the bogoluibov renormalization group. arXiv:hep-th/9909024, 1999.
[70] K. Huang. a critical history of renormalization. International Journal of Modern Physics A, 28(29):1–27,
2013.
[71] L.P. Kadanoff. Scaling laws for ising models near tc. Physics, 2(6):263–272, 1966.
[72] K .G. Wilson and J. Kogut. The renormalization group and the epsilon expansion. Physics Reports section C of Physics Letters, 12(2):75–200, 1974.
[73] F.J. Dyson. The radiation theories of tomonaga, schwinger, and feynman. Phys. Rev., 75(3):486–502, 1949.
[74] H. Barlow. Banishing the homonculus. Perception as Bayesian inference, eds Knill and Richards, Cambridge University Press, 1995.
[75] P. Foldiack. The ideal homunculus: Statistical inference from neural population responses. Computation
and Neural Systems, pages 55–60, 1993.
[76] D.O. Hebb. The organization of behaviour. Wiley, New-York., 1949.
[77] C. Von der Malsburg. The correlation theory of brain function. Internal Report 81-2, Dept. of Neurobiology,
Max Planck Institute for Biophysical Chemistry, 3400 Gottingen, Germany, 1981.
[78] M. Abeles. Local Cortical Circuits: An Electrophysiological study. Springer, Berlin, 1982.
[79] M. Diesmann, M.O. Gewaltig, and A. Aertsen. Stable propagation of synchronous spiking in cortical neural
networks. Nature, 402:529–533, 1999.
[80] W. Singer and C.M. Gray. Visual feature integration and the temporal correlation hypothesis. Annu Rev
Neurosci, 18:555–586, 1995.
[81] Y. Ikegaya, Aaron., R. Cossart, D. Aronov, I. Lampl, D. Ferster, and R. Yuste. Synfire chains and cortical
songs: temporal modules of cortical activity. Science, 23(304):559–564, 2004.
[82] A.K. Engel, P. Fries, P. Koenig, M. Brecht, and W. Singer. Temporal binding, binocular rivalry, and
consciousness. Consciousness and Cognition, 8(2):128151, 1999.
58
[83] I. Gold. Does 40-hz oscillation play a role in visual consciousness?
8(2):186195, 1999.
Consciousness and Cognition,
[84] M. Golubitsky and I. Stewart. Nonlinear dynamics of networks: the groupoid formalism. Bull. Am. Math.
Soc., 43(3):305364, 2006.
[85] D.J. Stilwell, E.M. Bolt, and D.G. Robertson. Synchronization of time varying networks under fast switching. Journal of Nonlinear Science, 5:140, 2011.
[86] C. Curto and V. Itskov. Cell groups reveal structure of stimulus space. PLOS comp. Biol., 4(10), 2008.
[87] G. Singh, F. Memoli, T. Ishkhanov, G. Sapiro, G. Carlsson, and DL. Ringach. Topological analysis of
population activity in visual cortex. Journal of Vision, 8(8):11:1–18, 2008.
[88] G. Petri, P. Expert, F. Turkheimer, R. Carhart-Harris, D. Nutt, P.J. Hellyer, and F. Vaccarino. Homological
scaffolds of brain functional networks. J R Soc Interface, 6;11:101, 2014.
[89] A. Kolmogorov. Combinatorial foundations of information theory and the calculus of probabilities. Russ.
Math. Surv., 38 29, 1983.
[90] E.T. Jaynes. Probability Theory: The Logic of Science. Cambridge University Press (posthum ed. 2003),
2003.
[91] T. L. Griffiths, C. Kemp, and J. B. Tenenbaum. Bayesian models of cognition. In Ron Sun (ed.), Cambridge
Handbook of Computational Cognitive Modeling. Cambridge University Press., 2008.
[92] K. Friston. The history of the future of the bayesian brain. Neuroimage, 62-248(2):12301233, 2012.
[93] R. Kubo. The fluctuation-dissipation theorem. Reports on Progress in Physics, 29(1):255–284, 1966.
[94] C.F. Stevens. Inferences about membrane properties from electrical noise measurements. Biophys J.,
12(8):10281047, 1972.
[95] N. Wiener. Nonlinear problems in random theory. MIT press, John Wiley & sons, 1958.
[96] G. Palm and T. Poggio. The volterra representation and the wiener expansion: validity and pitfalls. SIAM
J. Appl. Math., 33(2):195–216, 1977.
[97] G. Palm and T. Poggio. Stochastic identification methods for nonlinear systems: an extension of wiener
theory. SIAM J. Appl. Math., 34(3):524 534, 1978.
[98] M. Carandini, J.B. Demb, V. Mante, D.J. Tolhurst, Y. Dan, B.A. Olshausen, J.L. Gallant, and N.C. Rust.
Do we know what the early visual system does? J Neurosci., 25(46):10577–97, 2005.
[99] D.H. Hubel and T. Wiesel. Receptive fields, binocular interaction and functional architecture in the cat’s
visual cortex. J. Physiol., 160(1):106154, 1962.
[100] G.C. DeAngelis, I. Ohzawa, and R.D. Freeman. Receptive-field dynamics in the central visual pathways.
Trends Neurosci, 8(10):451–458, 1995.
[101] J. Fournier, C. Monier, M. Levy, O. Marre, Kisvarday Z.F., and Y. Fregnac. Hidden complexity of synaptic
receptive fields in cat v1. J Neurosci, 34(16):5515–5528, 2014.
[102] F. Rieke and R. and Bialek W. Warland, D. and de Ruyter van Steveninck. Spikes: Exploring the Neural
Code. A Bradford Book, Reprint edition (Computational Neuroscience), 1999.
[103] E.D. Adrian and Y Zotterman. The impulses produced by sensory nerve endings: Part ii: The response of
a single end organ. J Physiol, 61:151171, 1926.
[104] S. Thorpe, D. Fize, and C. Marlot. Speed of processing in the human visual system. Nature, 382:520522,
1996.
[105] T.J. Gawne, T.W. Kjaer, and B.J. Richmond. Latency: another potential code for feature binding in striate
cortex. J Neurophysiol, 76(2):1356–1360, 1996.
[106] S.P. Strong, R.R. de Ruyter van Steveninck, W. Bialek, and R. Koberle. On the application of information
theory to neural spike trains. Pac Symp Biocomput, pages 621–32, 1998.
[107] W. Bialek, F. Rieke, R.R. de Ruyter van Steveninck, and D. Warland. Reading a neural code. Science,
252(5014):1854–1857, 1991.
59
[108] J.D. Victor and K.P. Purpura. Nature and precision of temporal coding in visual cortex: a metric-space
analysis. J Neurophysiol, 76(2):1310–1326, 1996.
[109] F. Mechler, J.D. Victor, K.P. Purpura, and R. Shapley. Robust temporal coding of contrast by v1 neurons
for transient but not for steady-state stimuli. J. Neurosci, 18:6583–6598, 1998.
[110] D. Debanne, A. Bialowas, and S. Rama. What are the mechanisms for analogue and digital signalling in
the brain? Nature review neuroscience, 14:63–69, 2013.
[111] M. Zbili, S. Rama, and D. Debanne. Dynamic control of neurotransmitter release by presynaptic potential.
Front Cell Neurosci, 10(278), 2016.
[112] R.R. de Ruyter van Steveninck and S.B. Laughlin. The rate of information transfer at graded-potential
synapses. Nature, 379:642645, 1996.
[113] S. Rama, M. Zbili, A. Bialowas, L. Fronzaroli-Molinieres, N. Ankri, E. Carlier, V. Marra, and D. Debanne.
Presynaptic hyperpolarization induces a fast analogue modulation of spike-evoked transmission mediated
by axonal sodium channels. Nat Commun, 6(10163), 2015.
[114] A. Borst and F.E. Theunissen. Information theory and neural coding. Nature Neurosci., 2:947–957, 1999.
[115] B.A. Olshausen and DJ. Field. Emergence of simple-cell receptive field properties by learning a sparse code
for natural images. Nature, 381(6583):607–609, 1996.
[116] W.E. Vinje and J.L. Gallant. Sparse coding and decorrelation in primary visual cortex during natural
vision. Science, 287(5456):1273–6, 2000.
[117] W.E. Vinje and J.L. Gallant. Natural stimulation of the nonclassical receptive field increases information
transmission efficiency in v1. J Neurosci, 22(7):2904–2915, 2002.
[118] Y. Fregnac, P. Baudot, M. Levy, and O. Marre.
An intracellular view of time coding and sparseness of cortical representation in v1 neurons during virtual oculomotor exploration of natural scenes.
Cosyne Computational and Systems Neuroscience. Proc.,
https://drive.google.com/open?id=0B0QKxsVtOaTiOGhtSTg2T0t4cVE, 2005.
[119] D.A. Butts, C. Weng, J. Jin, C.I. Yeh, N.A. Lesica, J.M. Alonso, and G.B. Stanley. Temporal precision in
the neural code and the timescales of natural vision. Nature, 6(449(7158)):92–5, 2007.
[120] B. Haider, M.R. Krause, A. Duque, Y. Yu, J. Touryan, J.A. Mazer, and D.A. McCormick. Synaptic
and network mechanisms of sparse and reliable visual cortical activity during nonclassical receptive field
stimulation. Neuron, 65(1):107–21, 2010.
[121] R. Herikstad, J. Baker, J.P. Lachaux, C.M. Gray, and S.C.Baker Yen. Natural movies evoke spike trains
with low spike time variability in cat primary visual cortex. J Neurosci., 31(44), 2011.
[122] L. Martignon, G. Deco, K. Laskey, M. Diamond, W. Freiwald, and E. Vaadia. Neural coding : Higher-order
temporal patterns in the neurostatistics of cell assemblies. Neural Comput, 12(11):2621–2653, 2000.
[123] S. Amari. Information geometry on hierarchy of probability distributions. IEEE Transactions on Information Theory, 47(5):1701–1711, 2001.
[124] W.J. Ma, J.M. Beck, P.E. Latham, and A. Pouget. Bayesian inference with probabilistic population codes.
Nat Neurosci, 9(11):1432–1438, 2006.
[125] S. Dehaene and J.P. Changeux. Ongoing spontaneous activity controls access to consciousness: A neuronal
model for inattentional blindness. PLoS Biol, 3(5), 2005.
[126] V. Wyart and C. Sergent. The phase of ongoing eeg oscillations uncovers the fine temporal structure of
conscious perception. J. Neurosci., 29(41):12839–12841, 2009.
[127] R. Brown. A brief account of microscopical observations made in the months of june, july and august 1827
on the particles contained in the pollen of plants and on the general existence of active molecules. Privately published, Science Museum London. Source book in physics, ed. Magie, W. F. (1965) Massachusetts:
Harvard University Press., 1828.
[128] A. Vilardi. The role of noise in brain dynamics processes. PhD Thesis. University of Trento. CIMeC,
Centre for Mind/Brain Sciences, 2009.
[129] A. Eldar and M.B. Elowitz. Functional roles for noise in genetic circuits. Nature, 467(7312):167173, 2014.
60
[130] P. Bak, C. Tang, and K. Wiesenfeld. Self-organized criticality: an explanation of 1/f noise. Physical Review
Letters, 59(4):381384, 1987.
[131] C. E. Shannon. A mathematical theory of communication. The Bell System Technical Journal, 27:379–423,
1948.
[132] V.B. Baji and T.W. Tan. Information Processing and Living Systems. Imperial College Press, 2005.
[133] P. Dayan, G. Hinton, R.M. Neal, and R.S. Zemel. The helmholtz machine. Neural Computation, 7:889–904,
1995.
[134] K. Friston, J. Kilner, and L. Harrison. A free energy principle for the brain. J Physiol Paris., 100(13):7087,
2006.
[135] G.T. Fechner. Elemente der Psychophysik (Elements of Psychophysics). Breitkopf und Hrtel, 1860.
[136] P. Mengoli. Speculationi di musica. per l’herede del Benacci, 1670.
[137] M. Planck. On the law of distribution of energy in the normal spectrum. Annalen der Physik., 4:553–560
traduction: http://dbhs.wvusd.k12.ca.us/webdocs/Chem–History/Planck–1901/Planck–1901.html, 1901.
[138] T. Takahashi. Time-estimation error following weberfechner law may explain subadditive time-discounting.
Medical Hypotheses, 67(1372-1374), 2006.
[139] J.C. Stevens and L.E Marks. Cross-modality matching of brightness and loudness. Proceedings of the
National Academy of Sciences., 54:407411, 1965.
[140] L.E. Krueger. Reconciling fechner and stevens: Toward a unified psychophysical law. Behavioral and Brain
Sciences, 12(2):251–267, 1989.
[141] SB. Laughlin. The role of sensory adaptation in the retina. J Exp Biol., 146(39-62), 1989.
[142] L. Kostala and P. Lansky. Coding accuracy on the psychophysical scale. Scientific Report, 6:23810, 2016.
[143] E.N. Dzhafarov. Mathematical foundations of universal fechnerian scaling. Measurement with persons.
Theory, methods and implementation areas. Psychology press, 2012.
[144] Aristotle. Metaphysics. Translated by W. D. Ross http://classics.mit.edu/Aristotle/metaphysics.4.iv.html,
350 B.C.E.
[145] W.D. Ross. Plato’s Theory of Ideas. Cambridge University Press, 1951.
[146] W. Kohler. Gestalt psychology: an introduction to new concepts in modern psychology. New York: Liveright,
1947.
[147] M. Wertheimer. Gestalt theory. In W. D. Ellis Ed., A source book of Gestalt psychology. London, England:
Routledge & Kegan Paul (1934), 1924.
[148] M. Wertheimer. Laws of organization in perceptual forms. In W. D. Ellis (Ed.), A source book of Gestalt
psychology. London, England: Routledge & Kegan Paul (1938)., 1923.
[149] Y. Rosenthal, V.; Viseti. Sens et temps de la gestalt. Intellectica, 28:147–227., 1999.
[150] F. Attneave.
Some informational aspects of visual perception.
Psychological
http://www.dc.uba.ar/materias/incc/teoricas/Attneave1954.pdf, Vol 61 No. 3:183–194, 1954.
Review.
[151] D.J. Field, A. Hayes, and R.F. Hess. Contour integration by the human visual system: Evidence for a local
association field. Vision Research, 33(2):173–193, 1993.
[152] U. Polat and D. Sagi. Lateral interactions between spatial channels: suppression and facilitation revealed
by lateral masking experiments. Vision Research, 33(7):993–999, 1993.
[153] S. Georges, P. Series, Y. Fregnac, and J. Lorenceau. Orientation dependent modulation of apparent speed:
psychophysical evidence. Vision Research, 42(25):2757–2772, 2002.
[154] W. Penfield. Some mechanisms of consciousness discovered during electrical stimulation of the brain. Proc.
Natl Acad. Sci. USA, 44:5166, 1958.
[155] C.D. Salzman, K.H. Britten, and W.T. Newsome. Cortical microstimulation influences perceptual judgements of motion direction. Nature, 346:174177, 1990.
61
[156] A.J. Parker and W.T. Newsome. Sense and the single neuron: probing the physiology of perception. Annu.
Rev. Neurosci., 21:227277, 1998.
[157] N. Cicmil and K. Krug. Playing the electric light orchestrahow electrical stimulation of visual cortex
elucidates the neural basis of perception. Philos Trans R Soc Lond B Biol Sci., 370(): 20140206(1677),
2015.
[158] C.D. Gilbert and T.N. Wiesel. Columnar specificity of intrinsic horizontal and corticocortical connections
in cat visual cortex. J. Neurosci., 9:2432–2442, 1989.
[159] K.E. Schmidt, R. Goebel, S. Lowel, and W. Singer. The perceptual grouping criterion of colinearity is
reflected by anisotropies of connections in the primary visual cortex. Eur J Neurosci., 9(1083-1089), 1997.
[160] A.L. Yarbus. Eye Movements and Vision. New York: Plenum Press, 1967.
[161] F. Chavane, C. Monier, V. Bringuier, P. Baudot, L. Borg-Graham, J. Lorenceau, and Y. Fregnac. The
visual cortical association field: a gestalt concept or a psychophysiological entity? Journal of Physiology
(Paris), 94(5-6):333–342, 2000.
[162] F. Gerard-Mercier, P.V. Carelli, M. Pananceau, X.G. Troncoso, and Y. Fregnac. Synaptic correlates of
low-level perception in v1. J Neurosci., 36(14):3925–3942, 2016.
[163] M. Wehr and A.M. Zador. Balanced inhibition underlies tuning and sharpens spike timing in auditory
cortex. Nature, 426(6965):442–6, 2003.
[164] A. Collins, M. Stopfer, G. Laurent, and Bazhenov M. Adaptive regulation of sparseness by feedforward
inhibition. Nature Neuroscience, 10(9):1176–1184, 2007.
[165] B. Olshausen and D. Field. What is the other 85Problems in system neuroscience. Oxford University Press,
2004.
[166] H.B. Barlow. Possible principles underlying the transformation of sensory messages. In Sensory Communication, W.A. Rosenblith, ed. (Cambridge, MA: MIT Press), pages 217–234, 1961.
[167] R. Thom. Stabilite struturelle et morphogenese. deuxieme edition, InterEdition, Paris, 1977.
[168] J. Petitot and R. Thom. Semiotique et theorie des catastrophes. Presses Univ. Limoges, 1983.
[169] R. Thom. Semio Physics: A Sketch. Addison Wesley, 1990.
[170] D. Kendall. Shape manifolds, procrustean metrics and complex projective spaces. Bull. London Math.
Soc., 18:81121, 1984.
[171] I.L. Dryden and K.V. Mardia. Statistical Shape Analysis. John Wiley & Sons, 1998.
[172] P.W. Michor and D. Mumford. Riemannian geometries on spaces of plane curves. J. Eur. Math. Soc.,
8:1–48, 2006.
[173] D. Mumford and A. Desolneux.
AKPeters/CRC Press,, 2010.
Pattern Theory, the Stochastic Analysis of Real World Signals.
[174] W. James. The Principles of Psychology. New York, Holt, 1890.
[175] R. Llinas. I of the Vortex. From Neurons to Self. The MIT Press - A Bradford Book, 2002.
[176] A. Berthoz. Physiologie de la perception et de l’action. Cours du collge de France, 2000.
[177] A. Berthoz. La Decision. O. Jacob, 2003.
[178] M. Jeannerod. Motor Cognition: What Actions Tell to the Self. Oxford University Press - Psychology
Series 1st Edition, 2006.
[179] M. Merleau-Ponty. Phenomenologie de la Perception. Gallimard, coll. Tel , 1945.
[180] I. Saraf-Sinik, E. Assa, and E. Ahissar. Motion makes sense: An adaptive motor-sensory strategy underlies
the perception of object location in rats. Journal of Neuroscience, 35(23):8777–8789, 2015.
[181] A. Pellionisz and R. Llinas. Brain modeling by tensor network theory and computer simulation. the
cerebellum: distributed processor for predictive coordination. Neuroscience, 4(3):323–348, 1979.
62
[182] J.K. O’Regan and A. Noe. A sensorimotor account of vision and visual consciousness. Behav Brain Sci,
24:939–973, 2001.
[183] J.
Piaget.
Six
etudes
de
psychologie.
Problemes
de
psychologie
genetique.
http://www.fondationjeanpiaget.ch/fjp/site/presentation/index.php?PRESMODE=1&DOCID=1042,
1964.
[184] J. L Phillips. Piaget s Theory A Primer . Freeman, 1981.
[185] T. Lomo. Frequency potentiation of excitatory synaptic activity in the dentate area of the hippocampal
formation. Acta Physiologica Scandinavica, 68(277):128, 1966.
[186] T. Bliss and T. Lomo. Long-lasting potentiation of synaptic transmission in the dentate area of the
anaesthetized rabbit following stimulation of the perforant path. J. Physiol., 232(2):331–356, 1973.
[187] G. Chaitin. Epistemology as information theory: From leibniz to omega. Collapse, Volume I:27–51, 2006.
[188] P. Maguire, P. Moser, and R.Moser Maguire. Understanding consciousness as data compression. Journal
of Cognitive Science, 17(1):63–94, 2016.
[189] R. Linsker. From basic network principles to neural architecture. Proc. Nat. Acad. Sci. USA, 83:7508–7512,
1986.
[190] R. Linsker. Self-organization in a perceptual network. Computer, 21(3):105–117, 1988.
[191] M.V. Srinivasan, S. Laughlin, and A. Dubs. Predictive coding, a fresh view of infhibition in the retina.
Proc Royal Soc London, 216(1205):427–459, 1981.
[192] N. Nadal, J.-P. ; Parga. Sensory coding: information maximization and redundancy reduction. Neural
information processing, G. Burdet, P. Combe and O. Parodi Eds. World Scientific Series in Mathematical
Biology and Medecine, Vol. 7:p. 164–171, 1999.
[193] N. Nadal, J.-P. ; Parga. Nonlinear neurons in the low noise limit: a factorial code maximizes information
transfer. Network Computation in Neural Systems, 5:565–581, 1994.
[194] T.J. Bell, A.J. ; Sejnowski. An information maximisation approach to blind separation and blind deconvolution. Neural Computation, 7, 6:1129–1159, 1995.
[195] S. Laughlin. A simple coding procedure enhances the neuron’s information capacity. Z. Naturforsch,
36(c):910–912, 1981.
[196] D.H. Ackley, G.E. Hinton, and T. J. Sejnowski. A learning algorithm for boltzmann machines. Cognitive
Science, 9(1):147–169, 1985.
[197] J.J. Hopfield. Neural networks and physical systems with emergent collective computational abilities.
PNAS, 79:2554–2558, 1982.
[198] D. Marr. Vision. W.H. Freeman and Co., 1982.
[199] G. Hinton and R. Salakhutdinov. A better way to pretrain deep boltzmann machines. Advances in Neural.,
3:19, 2012.
[200] P. Smolensky. Chapter 6: Information processing in dynamical systems: Foundations of harmony theory”
(pdf). In Rumelhart, David E.; McLelland, James L. Parallel Distributed Processing: Explorations in the
Microstructure of Cognition, Volume 1: Foundations. MIT Press., page 194281, 1986.
[201] P. Mehta and D.J. Schwab. An exact mapping between the variational renormalization group and deep
learning. arXiv: 1410.3831 ., 2014.
[202] A. Rahimi and B. Recht. Back when we were kids. In NIPS 2017 Test-of-Time Award presentation, 2017.
[203] P. Baudot, O. Marre, M. Levy, and Y Fregnac.
Nature is the code: reliable and efficient dissipation in v1.
Published in Thesis ”Natural Computation: much ado about nothing”,
https://drive.google.com/open?id=1hV8WLLT3rgMW7QmDpEBy1yyQhRT1sZNW, 2006.
[204] Y. Fregnac and B. Bathellier. Cortical correlates of low-level perception: From neural circuits to percepts.
Neuron, 88(7), 2015.
[205] D. Debanne, D.E. Shulz, and Y. Fregnac. Activity-dependent regulation of ’on’ and ’off’ responses in cat
visual cortical receptive fields. Journal of Physiology, 508(2):523–548, 1998.
63
[206] C. Monier, F. Chavane, P. Baudot, L. Borg-Graham, and Y. Fregnac. Orientation and direction selectivity
of synaptic inputs in visual cortical neurons: a diversity of combinations produces spike tuning. Neuron,
37(4):663–680, 2003.
[207] N.T. Markov, J. Vezoli, and P. et al. Chameau. Anatomy of hierarchy: Feedforward and feedback pathways
in macaque visual cortex. The Journal of Comparative Neurology, 522(1):225–259, 2013.
[208] A. Roxin, N. Brunel, and D. Hansel. Role of delays in shaping spatiotemporal dynamics of neuronal activity
in large networks. Phys Rev Lett., 94(23):238103, 2005.
[209] D. Debanne, B.H. Gahwiler, and S.M. Thompson. Asynchronous pre- and postsynaptic activity induces
associative long-term depression in area ca1 of the rat hippocampus in vitro. Proc Natl Acad Sci USA,
91(3):1148–1152, 1994.
[210] L.F. Abbott and S.B. Nelson. Synaptic plasticity: Taming the beast. Nat Neurosci, 3:1178–1183, 2000.
[211] M. Graupner and N. Brunel. Mechanisms of induction and maintenance of spike-timing dependent plasticity
in biophysical synapse models. Front Comput Neurosci., 4(136), 2010.
[212] M. Graupner and N. Brunel. Calcium-based plasticity model explains sensitivity of synaptic changes to
spike pattern, rate, and dendritic location. Proc Natl Acad Sci USA, 109(10):39913996, 2012.
[213] A. Galvan. Neural plasticity of development and learning. Hum Brain Mapp, 31(6):879890, 2010.
[214] P. Baudot, M. Tapia, and J. Goaillard. Topological information data analysis: Poincare-shannon machine
and statistical physic of finite heterogeneous systems. Preprints 2018040157, 2018.
[215] F. Jacob and J. Monod. Genetic regulatory mechanisms in the synthesis of proteins. J. Mol. Biol., vol.
3:318–356, 1961.
[216] J.D. Cowan. The problem of organismic reliability. Progress in Brain Research, 17:9–63, 1965.
[217] A. Danchin. The delfic boat: What genomes tell us. Harvard University Press, 2003.
[218] E. Marder and J.M. Goaillard. Variability, compensation and homeostasis in neuron and network function.
Nat Rev Neurosci., 7:563–74, 2006.
[219] A.M. Swensen and B.P. Bean. Ionic mechanisms of burst firing in dissociated purkinje neurons. J. Neurosci.,
23:96509663, 2003.
[220] D. Bucher, A.A. Prinz, and E.J. Marder. Animal-to-animal variability in motor pattern production in
adults and during growth. Neurosci., 25:16111619, 2005.
[221] G.G. Turrigiano. The self-tuning neuron: synaptic scaling of excitatory synapses. Cell, 135:422435, 2008.
[222] A.J. Watt, M.C. van Rossum, K.M. MacLeod, S.B. Nelson, and G.G. Turrigiano. Activity coregulates
quantal ampa and nmda currents at neocortical synapses. Neuron, 26:659670., 2000.
[223] A.J. Watt and N.S. Desai. Homeostatic plasticity and stdp: Keeping a neuron’s cool in a fluctuating world.
Front Synaptic Neurosci., 2(5), 2010.
[224] H.A. Woods and J.K. Wilson. An information hypothesis for the evolution of homeostasis. Trends in
Ecology and Evolution, 28(5):283–289, 2013.
[225] A.L. Taylor, T.J. Hickey, A.A. Prinz, and E. Marder. Structure and visualization of high-dimensional
conductance spaces. J Neurophysiol., 96(2):891–905, 2006.
[226] M. Tapia, P. Baudot, C. Formizano-Treziny, M. Dufour, S. Temporal, M. Lasserre, B. Marqueze-Pouey,
J. Gabert, K. Kobayashi, and Goaillard J.M. Neurotransmitter identity and electrophysiological phenotype
are genetically coupled in midbrain dopaminergic neurons. Submitted to Nat. Comm, 2018.
[227] E. Martin. A dictionary of biology (6th ed.). Oxford: Oxford University Press., page 315316, 2008.
[228] M. Suzuki, S.; Grabowecky. Evidence for perceptual trapping and adaptation in mulstistable binocular
rivalry. Neuron, 36:143–157, 2002.
[229] A. Proute. Le raisonnement par l absurde. La negation de l antiquite grecque a nos jours. Institut Henri
Poincare. http://www.univ-paris-diderot.fr/philomathique/Proute21-05-08.pdf, 2008.
64
[230] A. Bauer. Five stages of accepting constructive mathematics. Bulletin of the American Mathematical
Society, 54(3):481–498, 2017.
[231] L.A. Necker. Observations on some remarkable optical phaenomena seen in switzerland; and on an optical
phaenomenon which occurs on viewing a figure of a crystal or geometrical solid. London and Edinburgh
Philosophical Magazine and Journal of Science., 1(5):329337, 1832.
[232] W.E Hill. My wife and my mother-in-law. they are both in this picture find them. Prints & Photographs
Online Catalog. Library of Congress., 18871962.
[233] E. Rubin. Synsoplevede figurer. PhD thesis of University of Copenhagen, 1915.
[234] V.S. Ramachandran and S.M. Anstis. Perceptual organization in multistable apparent motion. Perception,
14(2):135–143, 1985.
[235] O. Carter, T. Konkle, Q. Wang, V. Hayward, and C. Moore. Tactile rivalry demonstrated with an ambiguous
apparent-motion quartet. Current Biology, 18:1050–1054, 2008.
[236] G.H. Fisher. Preparation of ambiguous stimulus materials. Perception & Psychophysics, 2:421–422., 1967.
[237] G. Tononi, M. Boly, M. Massimini, and C. Koch. Integrated information theory: From consciousness to its
physical substrate. Nature Reviews Neuroscience, 17(7), 2016.
[238] M. Oizumi, L. Albantakis, and G. Tononi. From the phenomenology to the mechanisms of consciousness:
Integrated information theory 3.0. PLOS comp. Biol., 10(5), 2014.
[239] G. Cantor. Beitrge zur begrndung der transfiniten mengenlehre. Mathematische Annalen, 46(4):481–512,
1895.
[240] A.N. Whithead and B. Russel. Principia Mathematica. Cambridge University Press 2nd ed. 1963, 1910.
[241] A. Whithead. Process and Reality. An Essay in Cosmology. Gifford Lectures Delivered in the University
of Edinburgh During the Session 19271928. Macmillan, New York, Cambridge University Press,, 1929.
[242] D. Hilbert. Naturerkennen und logik (logic and the knowledge of nature). In The Conference on Epistemology of the Exact Sciences, 1930.
[243] K. Godel. On Formally Undecidable Propositions of Principia Mathematica and Related Systems. Dover,
1962, 1931.
[244] A.M. Turing. On computable numbers, with an application to the entscheidungsproblem. Proc. Lond.
Math. Soc. Ser., 42:230–265, 1937.
[245] C. Villani. Thorme vivant. Le livre de poche, 2013.
[246] S. Mac Lane. Categories for the Working Mathematician. Graduate Texts in Mathematics. Springer 2nd
ed., 1998.
[247] F.W. Lawvere. Taking categories seriously. Reprints in Theory and Applications of Categories. Reprint of
”Revista Colombiana de Matematicas” XX (1986) 147-178, No. 8,:pp. 1–24., 2005.
[248] J. C. Baez and T. Fritz. A bayesian characterization of relative entropy. Theory and Applications of
Categories,, Vol. 29, No. 16:p. 422–456, 2014.
[249] J.C. Baez, T. Fritz, and T. Leinster. A characterization of entropy in terms of information loss. Entropy,
13:1945–1957, 2011.
[250] J.P. Vigneaux. The structure of information: from probability to homology. arXiv:1709.07807, 2017.
[251] A. Proute.
Introduction a la
www.logique.jussieu.fr/ alp/, 2013.
Logique
Categorique.
Prepublications,
Paris
7
Logique
[252] B. Riemann. Ueber die darstellbarkeit einer funktion durch eine trigonometrische reihe. Traduction publie
dans le Bulletin des Sciences mathm. et astron. tome V ; juillet 1873, 1854.
[253] H. Lebesgue. Sur une generalisation de l integrale definie. Comptes rendus des seances de l Academie des
sciences, 132:1025–1027, 1901.
[254] E. Borel.
Lecons sur la theorie des fonctions.
https://archive.org/details/leconstheoriefon00borerich, 1898.
65
Paris,
Gauthier-Villars
et
fils.
[255] K. Ciesielski. Set Theory for the Working Mathematician. Cambridge University Press, 1997.
[256] P. Howard and J.E. Rubin. Consequences of the axiom of choice. Mathematical Surveys and Monographs,
1998.
[257] J.L. Bell. The axiom of choice. The Stanford Encyclopedia of Philosophy (Summer 2015 Edition), 2015.
[258] P. Ageron. L’autre axiom du choix. Revue dhistoire des mathematiques, 8:113–140, 2002.
[259] S. Wagon. The Banach-Tarski Paradox. Cambridge Univ. Press., 1986.
[260] A.K. Dewdney. A matter fabricator provides matter for thought. Scientific American, 60(4):116–119, 1989.
[261] R. Diaconescu. Axiom of choice and complementation. Proc. Amer. Math. Soc., 51:176–178, 1975.
[262] M. Dehn. Ueber den rauminhalt. Mathematische Annalen, 55(3):465–478, 1901.
[263] J. Dupont and C.H. Sah. Scissors congruences, ii. Journal of Pure and Applied Algebra, 25:159–195, 1982.
[264] J.L. Dupont. Scissors Congruences, Group Homology and Characteristic Classes. Nankai Tracts in Mathematics, V. 1., 2001.
[265] T.C. Hales. What is motivic measure? BULLETIN (New Series) OF THE AMERICAN MATHEMATICAL SOCIETY, Vol. 42, Nb 2:P. 119135, 2005.
[266] T. Tao.
A cheap version of nonstandard analysis.
What’s new. Tao’s
https://terrytao.wordpress.com/2012/04/02/a-cheap-version-of-nonstandard-analysis/, 2012.
blog.
[267] Robert M. Solovay. A model of set-theory in which every set of reals is lebesgue measurable. Annals of
Mathematics. Second Series, 92:1–56, 1970.
[268] A. N. Kolmogorov. Grundbegriffe der Wahrscheinlichkeitsrechnung.(English translation (1950): Foundations of the theory of probability.). Springer, Berlin (Chelsea, New York)., 1933.
[269] G. Boole. An Investigation Of The Laws Of Thought On Which Are Founded The Mathematical Theories
Of Logic And Probabilities. McMillan and Co., 1854.
[270] P. J. Nahin. The Logician and the Engineer: How George Boole and Claude Shannon Created the Information Age. Princeton University Press, 2012.
[271] D. Hume. A Treatise of Human Nature. Oxford: Clarendon Press, 1738.
[272] M. Gromov. Symmetry, probabiliy, entropy: Synopsis of the lecture at maxent 2014. Entropy, 17:1273–1277,
2015.
[273] M. Gromov. Memorandum ergo. ,. Internal report IHES, 2015.
[274] M. Gromov.
In a search for a structure, part 1: On entropy.
http://www.ihes.fr/ gromov/PDF/structre-serch-entropy-july5-2012.pdf, 2013.
unpublished manuscript
[275] M. Gromov. Alternative probabilities. Bernoully Lecture, March 27, 2018 EPFL, 2018.
[276] S. Hawking. Does god play dice?
dice.html, 2016.
Online personnal website http://www.hawking.org.uk/does-god-play-
[277] V. Natarajan. What einstein meant when he said god does not play dice ...”. Resonance, pages 655–661,
2008.
[278] N. Bourbaki. Theory of Sets - Elements of Mathematic. Addison Wesley publishing company. Hermann,
1968.
[279] J.C. Maxwell. Experiments on colour as perceived by the eye, with remarks on colour-blindness. Transactions of the royal society of Edinburgh, XXI(II), 1855.
[280] N.N. Cencov. Statistical Decision Rules and Optimal Inference. Translations of Mathematical Monographs.
Amer Mathematical Society, 1982.
[281] J. Morton. Relations among conditional probabilities. Journal of Symbolic Computation, 50:478–492, 2013.
[282] R.T. Cox. Algebra of probable inference. Baltimore, Maryland: The Johns Hopkins Press., 1961.
66
[283] M. Dupre and Tipler F. New axioms for rigorous bayesian probability. Bayesian Analysis, 4(3):599–606,
2009.
[284] L.A. Zadeh. Fuzzy sets. Information and Control, 8(3):338–353, 1965.
[285] P. Hajek, L. Godo, and F. Esteva. Fuzzy logic and probability. arXiv:1302.4953, 2013.
[286] M.J. Wierman. An Introduction to the Mathematics of Uncertainty. Creighton University., 2010.
[287] K. Knuth. Lattice duality: The origin of probability and entropy. Neurocomputing, 67:245–274, 2005.
[288] K. Knuth. Measuring on lattices. arXiv:0909.3684 [math.GM], 2009.
[289] P. Cartier. A mad day’s work: from grothendieck to connes and kontsevich the evolution of concepts of
space and symmetry. Bull. Amer. Math. Soc., 38(4):389–408, 2001.
[290] F.W. Lawvere. Comments on the development of topos theory. Reprints in Theory and Applications of
Categories, 24:122, 2014.
[291] M. Artin, A. Grothendieck, and J.L. Verdier. Theorie des topos et cohomologie etale des schemas - (SGA
4) Vol I,II,III. Seminaire de Geometrie Algebrique du Bois Marie. Berlin; New York, Springer-Verlag, coll.
e Lecture notes in mathematics ,? 1972, 1964.
[292] A. Grothendieck. Realcoltes et Semailles,Reeflexions et temoignage sur un passe de mathmaticien. Unpublished http://lipn.univ-paris13.fr/ duchamp/Books&more/Grothendieck/RS/pdf/RetS.pdf, 1985.
[293] Y. Andre. Espace i. topos. Chap 1., 2007.
[294] G.E. Reyes. Sheaves and concepts: a model theoretic interpretation of grothendieck topoi. Cahier de
topologie et gomtrie differentielle categorique., 18, N.2:105–137, 1977.
[295] F.W Lawvere. Toposes, Algebraic Geometry and Logic,. Lecture Notes in Math., Springer-Verlag, 1972.
[296] M. Barr and C. Wells. Toposes, triples and theories. Reprints in Theory and Applications of Categories
(2005) Originally published by Springer-Verlag, NewYork, 12:1288, 1985.
[297] A. Doering and C. Isham. A topos foundation for theories of physics: I. formal languages for physics.
J.Math.Phys., 49, 2008.
[298] A. Doering and C.J. Isham. Classical and quantum probabilities as truth values. Journal of Mathematical
Physics, Vol: 53, 2012.
[299] P. Baudot and D. Bennequin. Topological forms of information. AIP Conf. Proc., 1641:213–221, 2015.
[300] A. Simpson. Measure, randomness and sublocales. Annals of Pure and Applied Logic, 163(11):1642–1659,
2012.
[301] M. Tapia, P. Baudot, M. Dufour, C. Formizano-Treziny, S. Temporal, M. Lasserre, K. Kobayashi, and
Goaillard J.M. Information topology of gene expression profile in dopaminergic neurons. BioArXiv168740,
2017.
[302] R. Stanley. Enumerative Combinatorics. 2nd edition. Cambridge Studies in Advanced Mathematics, 2011.
[303] G.E. Andrews. Partitions. https://www.math.psu.edu/vstein/alg/antheory/preprint/andrews/chapter.pdf,
chp 8., 1998.
[304] G. Andrews. The Theory of Partitions. Cambridge University Press, Cambridge, 1998.
[305] I. G. Macdonald. Symmetric Functions and Hall Polynomials. Oxford Mathematical Monographs [2 ed.]
Oxford University Press, 1995.
[306] K. Godel. On the intuitionistic propositional calculus. In Solomon Feferman et al., editor, Kurt G odel:
Collected Works. Oxford University Press, New York, 1986., I:2225, 1932.
[307] S. Gottwald. Many-valued logic. in Stanford Encyclopedia of Philosophy 2008 ed., 2004.
[308] M.H.B. Sorensen and P. Urzyczyn. Lectures on the Curry-Howard Isomorphism. Studies in Logic and the
Foundations of Mathematics. Elsevier., 2006.
[309] Kuo Ting Hu. On the amount of information. Theory Probab. Appl., 7(4):439–447, 1962.
67
[310] W.J. McGill. Multivariate information transmission. Psychometrika, 19:p. 97–116, 1954.
[311] S. Watanabe. Information theoretical analysis of multivariate correlation. IBM Journal of Research and
Development, 4:66–81, 1960.
[312] M. Studeny and J. Vejnarova. The multiinformation function as a tool for measuring stochastic dependence.
in M I Jordan, ed., Learning in Graphical Models, MIT Press, Cambridge, pages 261–296, 1999.
[313] H. Matsuda. Information theoretic characterization of frustrated systems. Physica A: Statistical Mechanics
and its Applications., 294 (1-2):180–190, 2001.
[314] C. Weibel. An introduction to homological algebra. Cambridge University Press, 1995.
[315] R. Yeung. On entropy, information inequalities, and groups. Communications, Information and Network Security, Volume 712 of the series The Springer International Series in Engineering and Computer
Science:333–359, 2003.
[316] R.W. Yeung. Information Theory and Network Coding. Springer, 2007.
[317] R.W. Yeung. A framework for linear information inequalities. IEEE Transactions on Information Theory
(New York), 43(6):19241934, 1997.
[318] J. Csiszr, I.; Krner. Information Theory: Coding Theorems for Discrete Memoryless Systems [Second ed.].
Cambridge University Press, 2011.
[319] C.E. Shannon. A lattice theory of information. Trans. IRE Prof. Group Inform. Theory, 1:105–107, 1953.
[320] T. S. Han. Linear dependence structure of the entropy space. Information and Control., vol. 29:p. 337–368,
1975.
[321] A.A Karatsuba and S. M. Voronin. The Riemann Zeta-Function. De Gruyter Expositions in Mathematics.
Walter de Gruyter, 1992.
[322] S.M. Voronin. Theorem on the ’universality’ of the riemann zeta-function. Izv. Akad. Nauk SSSR, Ser.
Matem. (1975) (in Russian). English translation in: Math. USSR Izvestija 9 (1975), 39:443–453, 1975.
[323] A.K. Zvontin and L.A. Levin. The complexity of finite objects and the development of the concepts of
information and randomness by means of the theory of algorithms. Russ. Math. Surv., 256:83–124, 1970.
[324] G.H. Hardy and E.M. Wright. Introduction to the theory of numbers. Oxford University Press,. New York,
1979.
[325] A.Y. Khrennikov and M. Nilson. P-adic Deterministic and Random Dynamics. Springer, 2004.
[326] K. Gdel. ber formal unentscheidbare stze der principia mathematica und verwandter systeme i. Monatsheft
fr Math. und Physik, 38:p. 173–198, 1931.
[327] J.R. Nagel, E.; Newman. Gdel’s Proof. New York University Press, 1959.
[328] D.S. Ornstein. Bernoulli shifts with the same entropy are isomorphic,. Advances in Math., 4.:337–352,
1970.
[329] J. Milnor. Differential topology forty-six years later. Notices A.M.S., 58:804–809, 2011.
[330] C. Weibel. History of homological algbera. The History of Topology ed. I.M. James, Elsevier,, pages
797–836, 1999.
[331] J.A. Dieudonne. A History of Algebraic and Differential Topology 1900-1960. Modern Birkhauser Classics,
1989.
[332] G.W. Leibniz. Characteristica geometrica. Echeverra, J. and Parmentier, M. eds. (1995), pages 148–9,
1679.
[333] S. Uchii. Monadology, information, and physics part 1: Metaphysics and dynamics. PhilSci-Archive 11523,
2014.
[334] S. Uchii. Monadology, information, and physics part 2: Space and time. PhilSci-Archive 11647, 2014.
[335] S. Uchii. Monadology, information, and physics part 3 (revised): Inertia and gravity. PhilSci-Archive
11125, 2014.
68
[336] L. Euler. Solutio problematis ad geometriam situs pertinentis. Mmoires de l’Acadmie des sciences de
Berlin, 8:128–140, 1759.
[337] B. Riemann. Theorie der abel’schen functionen. Journal fur die reine und angewandte Mathematik, 54:101–
155, 1857.
[338] H. Poincare. Analysis Situs., volume 2. Journal de l’cole Polytechnique, 1895.
[339] H. Bass, H. Cartan, P. Freyd, A. Heller, and S. Mac Lane. Samuel eilenberg 1913-1998 - a bibliographical
memoir. Bibliographical memoir - The national academy press Washington, 79, 2000.
[340] A. Grothendieck. Long March through Galois theory. Cambridge University Press, 1997.
[341] G. Deleuze. La difference et la repetition. Presse Universite de France. Epimethee, 2000.
[342] Y. Andre. Ambiguity theory, old and new. arXiv:0805.2568, 2008.
[343] Y. Andre. Symtries I. Ides galoisiennes. Ircam online courses, 2007.
[344] D. Bennequin. Questions de physique galoisienne. Passion des Formes Dynamique qualitative, Smiophysique
et Intelligibilit A Ren Thom, Michle Porte coordonateur Paris, ENS Editions Fontenay-St Cloud, pages
311–410, 1994.
[345] M. Cook. Mathematicians: An Outer View of the Inner World. Princeton University Press, 2009.
[346] M. Berger. Geometry I. Springer, Universitext, Corrected edition, 2009.
[347] Cl. Chevalley and S. Eilenberg. Cohomology theory of lie groups and lie algebras. Transactions of the
American Mathematical Society, 63(1):85–124, 1948.
[348] P. Alexandroff. Elementary concepts of Topology. Dover Publication Inc., 1932.
[349] A. Hatcher. Algebraic Topology. Cambridge University Press, 2002.
[350] R. Ghrist. Elementary Applied Topology ed. 1.0. Createspace., 2014.
[351] P. Erds, P.s and A. Rnyi. On random graphs. i. Publicationes Mathematicae, 6:290–297, 1959.
[352] D. J. Watts and S. H. Strogatz. Collective dynamics of ’small-world’ networks. Nature, 393 (6684):440–442,
1998.
[353] S.N. Dorogovtsev, A.V. Goltsev, and J.F.F. Mendes. Critical phenomena in complex networks. Rev. Mod.
Phys., 80, 4:1275, 2008.
[354] M. Newman. Networks: an introduction. Oxford University Press, 2010.
[355] T.F. Banchoff. Critical points and curvature for embedded polyhedral surfaces. The American Mathematical
Monthly, Vol. 77, No. 5:475–485, 1970.
[356] J. Milnor. Morse theory. Princeton University Press, 1964.
[357] R. Forman. A user’s guide to discrete morse theory. Sminaire Lotharingien de Combinatoire.
http://www.emis.de/journals/SLC/wpapers/s48forman.pdf, 48:48c, 35 p., 2002.
[358] A. Postnikov. Determination of the homology groups of a space by means of the homotopy invariants.
Doklady Akademii Nauk SSSR, 76:359362, 1951.
[359] J. Milnor. Link groups. Annals of Mathematics, 59 (2):177–195, 1954.
[360] G. Carlsson. Topology and data. Bull. Amer. Math. Soc., 46:p.255–308, 2009.
[361] A. Port, I. Gheorghita, D. Guth, J.M. Clark, C. Liang, S. Dasu, and M. Marcolli. Persistent topology of
syntax. Mathematics in Computer Science, 1(12):33–50, 2018.
[362] E. Zeidler. Quantum Field Theory III: Gauge Theory. A Bridge between Mathematicians and Physicists.
Springer-Verlag Berlin Heidelberg, 2011.
[363] J.A. Wheeler. Physics and austerity, law without law. Anhui Science and Technology Publications, Anhui,
China, 1982.
[364] C.W Misner, K.S. Thorne, and J.A. Wheeler. Gravitation. San Francisco, W.H. Freeman, 1973.
69
[365] C. Rovelli. Notes for a brief history of quantum gravity. arXiv:gr-qc/0006061v3, 2008.
[366] J.A. Wheeler. Information, physics, quantum: The search for links. in Complexity, Entropy and the Physics
of Information ed., Wojciech H. Zurek, 1990.
[367] J.L. Cathelineau. Sur l’homologie de sl2 a coefficients dans l’action adjointe. Math. Scand., 63:51–86, 1988.
[368] M. Kontsevitch. The 11/2 logarithm. Unpublished note. Reproduced in Elbaz-Vincent & Gangl, 2002 On
poly(ana)logs I. Compositio Mathematica, 1995.
[369] Ph. Elbaz-Vincent and H. Gangl. On poly(ana)logs i. Compositio Mathematica, 130(2):161–214, 2002.
[370] A. Connes and C. Consani. Characteristic 1, entropy and the absolute point. preprint arXiv:0911.3537v1.,
2009.
[371] M. Marcolli and R. Thorngren. Thermodynamic semirings. arXiv 10.4171/JNCG/159, Vol. abs/1108.2874,
2011.
[372] B. Fresse. Koszul duality of operads and homology of partitionn posets. Contemp. Math. Amer. Math.
Soc., 346:pp. 115–215, 2004.
[373] F. Schoeller, L. Perlovsky, and D. Arseniev. Physics of mind: experimental confirmations of theoretical
predictions. Physics of Life Reviews, 2018. https://doi.org/10.1016/j.plrev.2017.11.021 [this issue].
[374] M. Costa, A.L. Goldberger, and C.K. Peng. Multiscale entropy to distinguish physiologic and synthetic rr
time series. Computers in Cardiology, 29:137–140, 2002.
[375] M. Costa, A.L. Goldberger, and C.K. Peng. Multiscale entropy analysis of biological signals. Phys Rev E,
71 ::021906, 2005.
[376] G. Hochschild. On the cohomology groups of an associative algebra. Annals of Mathematics. Second Series,,
46:5867, 1945.
[377] J. Tate. Galois cohomology. online course, 1991.
[378] H. Cartan and S. Eilenberg. Homological Algebra. The Princeton University Press, Princeton, 1956.
[379] S. Mac Lane. Homology. Classic in Mathematics, Springer, Reprint of the 1975 edition, 1975.
[380] D.G. Kendall. Functional equations in information theory. Z. Wahrscheinlichkeitstheorie, 2:p. 225–229,
1964.
[381] P.M. Lee. On the axioms of information theory. The Annals of Mathematical Statistics, Vol. 35, No. 1:pp.
415–418, 1964.
[382] M. Gerstenhaber and S.D. Schack. A hodge-type decomposition for commutative algebra cohomology.
Journal of Pure and Applied Algebra, 48(1-2):229–247, 1987.
[383] C. Kassel. Homology and cohomology of associative algebras- a concise introduction to cyclic homology.
Advanced Course on non-commutative geometry, 2004.
[384] D. Hilbert. Sur l’infini. hilbert’s lectures on the infinite. Traduit par Andre Weil Paris (1926). edited in
David Hilbert’s Lectures on the Foundations of Arithmetic and Logic 1917-1933. Springer, 1924.
[385] S.D. Pethel and D.W. Hahs. Exact test of independence using mutual information. Entropy, 16:2839–2849,
2014.
[386] C. Adami and N.J. Cerf. Prolegomena to a non-equilibrium quantum statistical mechanics. Chaos, Solitons
& Fractals, 10(10):1637–1650, 1999.
[387] M. Kapranov. Thermodynamics and the moment map. arXiv:1108.3472, 2011.
[388] T.M. Cover. Which processes satisfy the second law? in: Physical Origins of Time Asymmetry, , eds. J.
J. Halliwell, J. Perez-Mercader and W. H. Zurek, pages 98–107, 1994.
[389] J. Baez and B. Fong. A noether theorem for markov processes. Journal of Mathematical Physics, 54:013301,
2013.
[390] L. Barnett, A.K. Barrett, and Seth A.K. Granger causality and transfer entropy are equivalent for gaussian
variables. Phys. Rev. Lett., 103:238701, 2009.
70
[391] T. Schreiber. Measuring information transfer. Physical Review Letters, 85(2):461464, 2000.
[392] P. Dirac. Discussion of the infinite distribution of electrons in the theory of the positron. Proc. Camb.
Phil. Soc., 25:62, 1929.
[393] R. Feynman. QED. The Strange Theory of Light and Matter. Princeton University Press, 1985.
[394] J. Vannimenus and G. Toulouse. Theory of the frustration effect. ii. ising spins on a square lattice. Journal
of Physics C: Solid State Physics, 10(18), 1977.
[395] M. Mezard and A. Montanari. Information, Physics, and Computation. Oxford University Press, 2009.
[396] R.B. Griffiths. Consistent histories and the interpretation of quantum mechanics. J. Stat. Phys., 35:219,
1984.
[397] R. Omnes. Logical reformulation of quantum mechanics i. foundations. Journal of Statistical Physics,
53:893–932, 1988.
[398] M. Gell-Mann and J.B. Hartle. Quantum mechanics in the light of quantum cosmology. W. H. Zurek (ed.),
Complexity, entropy and the physics of information. Redwood City, Calif.: Addison-Wesley, pages 425–458,
1990.
[399] D. Rudrauf, D. Bennequin, I. Granic, G. Landini, K. Friston, and K. Williford. A mathematical model of
embodied consciousness. J Theor Biol., 428:106–131, 2017.
[400] G. D’Agostino and A. Scala. Networks of Networks: The Last Frontier of Complexity. Springer - Understanding Complex Systems, 2014.
[401] D.N. Reshef, Y.A. Reshef, H.K. Finucane, S.R. Grossman, G. McVean, P.J. Turnbaugh, E.S. Lander,
M. Mitzenmacher, and P.C. Sabeti. Detecting novel associations in large data sets. Science, 334:1518,
2011.
[402] N. Brenner, S. Strong, R. Koberle, and W. Bialek. Synergy in a neural code. Neural Computation.,
12:1531–1552, 2000.
[403] E. Schrodinger. What is Life? Based on lectures delivered under the auspices of the Dublin Institute for
Advanced Studies at Trinity College, Dublin, in February 1943, 1944.
[404] P. Williams and R. Beer. Nonnegative decomposition of multivariate information. arXiv:1004.2515v1, 2010.
[405] E. Olbrich, N. Bertschinger, and J. Rauh. Information decomposition and synergy. entropy, 17(5):3501–
3517, 2015.
[406] N. Bertschinger, J. Rauh, E. Olbrich, J. Jost, and N. Ay. Quantifying unique information. Entropy,
16:21612183, 2014.
[407] V. Griffith and C. Koch. Quantifying synergistic mutual information. In Guided Self-Organization: Inception; Prokopenko, M., Ed.; Springer: Berlin/Heidelberg, Germany, pages 159–190, 2014.
[408] M. Wibral, C. Finn, P. Wollstadt, J.T Lizier, and V. Priesemann. Quantifying information modification in
developing neural networks via partial information decomposition. Entropy, 19(9):494, 2017.
[409] J.W. Kay, R.A.A. Ince, B. Dering, and W. Phillips. Partial and entropic information decompositions of a
neuronal modulatory interaction. Entropy, 19(11):560, 2017.
[410] A.K. Seth, E. Izhikevich, G.N. Reeke, and G.M. Edelman. Theories and measures of consciousness: An
extended framework. PNAS, 103(28):10799–804, 2006.
[411] H. Atlan. Entre le cristal et la fumee. Essai sur l’organisation du vivant. Seuil, 1979.
[412] J.J. Gibson. The ecological approach to visual perception. Boston: Houghton Mifflin, 1979.
[413] E. Cassirer. The concept of group and the theory of perception. A. Gurwitsch, trans. Philosophy and
Phenomenological Research (1944), 5:1–35, 1938.
[414] J. Piaget. Structuralism. New York: Basic Books, 1970.
[415] G.M. Stratton. Some preliminary experiments on vision without inversion of the retinal image. Psychological
Review, 3(6):611–617, 1896.
71
[416] G.M. Stratton. Upright vision and the retinal image. Psychological Review, 4(2):182–187, 1897.
[417] I. Kohler. Experiments with goggles. Scientific American, 206(5):62–72, 1962.
[418] J.J. Gibson. Adaptation, after-effect and contrast in the perception of curved lines. Experimental Psychology, 16(1):1–31, 1933.
[419] J. Sharma, A. Angelucci, and M. Sur. Induction of visual orientation modules in auditory cortex. Nature,
404:841–847, 2000.
[420] M. Sur and C. Leamey. Development and plasticity of cortical areas and networks. Nat. Rev. Neurosci.,
2:251262, 2001.
[421] M. Sur and J.L.R. Rubenstein. Patterning and plasticity of the cerebral cortex. Science, 310(5749):805–807,
2005.
[422] A.W. Roe, S.L. Pallas, J.O. Hahm, and M. Sur. A map of visual space induced in primary auditory cortex.
Science, 250:818820, 1990.
[423] E. Boring. Visual perception as invariance. Psychological Review, 59(2):141–148, 1952.
[424] J.E. Cutting. Observations - four assumptions about invariance in perception. Journal of Experimental
Psychology, 9(2):310–317, 1983.
[425] J.T. Todd, A.H. Oomes, J.J. Koenderink, and A.M. Kappers. On the affine structure of perceptual space.
Psychol Sci., 12(3):191–196, 2001.
[426] J. Koenderink, A.J. Doorn, and A. Kappers. Pappus in optical space. Perception & Psychophysics,
64(3):380–391, 2002.
[427] A.M. Battro, S.P. Netto, and R.J.A. Rozestraten. Riemannian geometries of variable curvature in visual
space: Visual alleys, horopters, and triangles in big open fields. Perception, 5:9–23, 1976.
[428] T. Indow. A critical review of luneburgs model with regard to global structure of visual space. Psychological
Review, 98:430453, 1991.
[429] J. Koenderink, A. Doorn, and J. Lappin. Direct measurement of the curvature of visual space. Perception,
29:6980, 2000.
[430] P. Suppes. Is visual space euclidean? Synthese, 35:397421, 1977.
[431] G.B. Ermentrout and J.D. Cowan. A mathematical theory of visual hallucinations. Biol. Cybern., 34:137–
150, 1979.
[432] PC Bressloff, J.D. Cowan, M. Golubitsky, P.J. Thomas, and M.C. Wiener. Geometric visual hallucinations,
euclidean symmetry, and the functional architecture of striate cortex. Phil. Trans. Royal Soc. London,
356:299330, 2001.
[433] M. Golubitsky. Symmetry and neuroscience. Bulletion of the AMS, Amercian Mathematical Society,
January 2006.
[434] R. Thom. Logos et theorie des catastrophes. expose de rene thom au colloque international de cerisy 1982.
Annales de la Fondation Louis de Broglie, 27 (4):575–595, 2002.
[435] B. Riemann. On the hypotheses which lie at the bases of geometry. translated by william kingdon clifford.
Nature, VIII N183-184:14–17,36, 37, 1854.
[436] F. Klein. Vergleichende bertrachtungen uber neuere geometrische forschungen erlangen. Reprinted in
Mathematische Annalen 1893, 1:460–97., 1872.
[437] G. Birkhoff and M.K. Bennett. Felix klein and his ”erlanger programm”. In History and Philosophy of
Modern Mathematics - U of Minnesota Press,, pages 145–176, 1988.
[438] S. Smale. Differentiable dynamical systems. Bulletin of the American Mathematics Society, 73:747–817,
1967.
[439] D. Mumford, J. Fogarty, and F. Kirwan. Geometric invariant theory. Results in Mathematics and Related
Areas (3rd ed.), Berlin, New York: Springer-Verlag, 1994.
72
[440] E.M. Izhikevich. Dynamical Systems in Neuroscience: The Geometry of Excitability and Bursting. The
MIT press, 2007.
[441] H. Sompolinsky, A. Crisanti, and H.J. Sommers. Chaos in random neural networks. Physical Review
Letters, 61:259, 1988.
[442] V. Bergelson, T. Tao, and T. Ziegler. An inverse theorem for the uniformity seminorms associated with
the action of f. Geom. Funct. Anal., 6:1539–1596, 2010.
[443] T. Tao. Cohomology for dynamical systems. Online Blog https://terrytao.wordpress.com/2008/12/21/cohomologyfor-dynamical-systems/, 2008.
[444] D.S. Ornstein. Some new results in the kolmogorov-sinai theory of entropy and ergodic theory. BULLETIN
OF THE AMERICAN MATHEMATICAL SOCIETY, Volume 77, Number 6,:878–888, 1971.
[445] A. Katok. fifty years of entropy in dynamics: 1958-2007. Journal of modern dynamics, 1(4):545596, 2007.
[446] D. Gaboriau. Entropie sofique daprs lewis bowen, david kerr et hanfeng li. Sminaire Bourbaki du 16 janvier
2016. 2016. ¡hal-01347306¿, 2016.
[447] D. Ornstein and B. Weiss. Entropy and isomorphism theorems for actions of amenable groups. J. Analyse
Math., 48:1141, 1987.
[448] J. von Neumann. Zur allgemeinen theorie des maes. Fund. Math., 13(1):73111, 1929.
[449] D. Ornstein. Kolmogorov, random processes, and newtonian dynamics.
59(2):121126, 2004.
Russian Math. Surveys,
[450] Y. Pesin. Characteristic lyapunov exponents and smooth ergodic theory. Russ. Math. Surveys, 32:55–114,
1977.
[451] P. Gaspard and X.J. Wang. Noise, chaos, and (t,e)-entropy per unit time. Phys. Rep., 235(6):321–373,
1993.
[452] A. Destexhe. Nonlinear Dynamics of the Rhythmical Activity of the Brain. Doctoral Dissertation (Universit
Libre de Bruxelles, Brussels), 1992.
[453] S. El-Boustani and A. Destexhe. Brain dynamics at multiple scales: Can one reconcile the apparent
low-dimensional chaos of macroscopic variables with the seemingly stochastic behavior of single neurons?
International Journal of Bifurcation and Chaos, 20(6):1687–1702, 2010.
[454] P. Stern. Neuroscience: In search of new concepts. Science, 358(6362):464–465, 2017.
[455] Yves
Bertot
and
P.
Casteran.
Le Coq
sop.inria.fr/members/Yves.Bertot/coqartF.pdf, 2015.
Art
(V8).
Online
http://www-
[456] D. Silver, Schrittwieser J., Simonyan K., and al. Mastering the game of go without human knowledge.
Nature, 550(7676):354–359, 2017.
[457] V. Mnih, K. Kavukcuoglu, and D. Silver. Human-level control through deep reinforcement learning. Nature,
518(7540):529–33, 2015.
[458] W. Kohn. Electonic structure of matter - wave functions and density functional. Nobel Lecture, January
28, 1999, 1999.
[459] G. Aloupis, E. Demaine, A. Guo, and G. Viglietta. Classic nintendo games are (computationally) hard.
arXiv:1203.1895v3, 2012.
[460] T. Nakagaki, H. Yamada, and A. Toth. Intelligence: Maze-solving by an amoeboid organism. Nature,
407:470, 2000.
[461] E.P. Wigner. The unreasonable effectiveness of mathematics in the natural sciences. Communications on
Pure and Applied Mathematics., 13:1–14, 1960.
[462] Jacek Blazewicz and Marta Kasprzak. Complexity issues in computational biology. Fundamenta Informaticae, 118(4):385–401, 2012.
[463] J.J. Atick. Could information theory provide an ecological theory of sensory processing. Network: Computation in Neural Systems., 3:213–251, 1992.
[464] J. Dieudonne. Pour lhonneur de lesprit humain. Les mathematiques aujourdhui - Hachette, 1987.
[465] T. Fritz and P. Perrone. Bimonoidal structure of probability monads. arXiv:1804.03527v1, 2018.
73 |
Quantum mechanics needs no consciousness (and the other way around)
Shan Yu∗,a , Danko Nikolića,b
a Department of Neurophysiology, Max Planck Institute for Brain Research, Deutschordenstr. 46, 60528 Frankfurt am Main, Germany
arXiv:1009.2404v2 [physics.gen-ph] 24 Sep 2010
b Frankfurt Institute for Advanced Studies, Johann Wolfgang Goethe University, Ruth-Moufang-Str. 1, 60438 Frankfurt am Main, Germany
Abstract
It has been suggested that consciousness plays an important role in quantum mechanics as it is necessary for the
collapse of wave function during the measurement. Furthermore, this idea has spawned a symmetrical proposal: a
possibility that quantum mechanics explains the emergence of consciousness in the brain. Here we formulated several
predictions that follow from this hypothetical relationship and that can be empirically tested. Some of the experimental
results that are already available suggest falsification of the first hypothesis. Thus, the suggested link between human
consciousness and collapse of wave function does not seem viable. We discuss the constraints implied by the existing
evidence on the role that the human observer may play for quantum mechanics and the role that quantum mechanics
may play in the observer’s consciousness.
1. Introduction
The nature of human consciousness and its relation
to the physical reality is arguably the most puzzling
issue regarding the fundamental questions about ourselves and the interaction with the world that we live
in. An interesting proposal has been put forward of a
link between the seemingly distant quantum mechanics and consciousness, leading to a direct, yet bizarre
bridge between the mental and the physical. It all started
with the measurement problem in quantum mechanics,
which can be formulated as follows: According to quantum mechanics, the states of any physical system can
be described fully by a wave function (state vector) that
characterizes various system’s variables such as its position, momentum, energy or spin. Schrödinger’s famous
equation describes how these variables evolve over time
(Schrödinger, 1926). According to most interpretations
for the formalism of quantum mechanics (with the exception of the hidden variable theory, e.g., Bohm, 1952),
the system described by the wave function does not
have specific values (e.g., does not have a specific position), but is in a superposition state defined as the
weighted sum of all states that the system may possibly
assume following a measurement (known also as a set of
∗ Current address: Laboratory of Systems Neuroscience, National
Institute of Mental Health, 9000 Rockville Pike, Bethesda, MD
20892, USA
Email addresses: yushan.mail@gmail.com (Shan Yu),
danko.nikolic@googlemail.com (Danko Nikolić)
eigenstates). This superposition can be verified experimentally, for example through interference phenomena
(Zeilinger, 1999a). However, for each single measurement, that is, whenever a macroscopic measuring device
is used to detect the state of a particular system, the result always indicates a single eigenstate, e.g., a single
photon always has a specific location in space. Importantly, the probabilities for observing the specific states,
i.e. their distributions, are predicted most accurately by
the wave functions, which describe the system as a superposition of multiple states prior to the measurement.
This led physicists to conclude that a quantum system
can evolve in two, very different, forms: one is continuous, deterministic and reversible, described by a wave
function and occurs prior to the measurement. The other
form is discontinuous but stochastic, as, during the measurement, the system “jumps” suddenly from a superposition state into a single randomly chosen eigenstate.
According to some interpretations of quantum mechanics, this jump is an irreversible event that occurs during the measurement process, and is usually referred to
as the collapse of wave function or reduction of state
vector. The measurement problem in quantum mechanics refers to understanding the nature of this “collapse”,
both at the explanatory level, such as: “Which other,
more fundamental processes cause the collapse?”, and
the ontological level, such as: “Is the collapse physically real or it is just an artifact of the theoretical system?”. This measurement problem is a major topic of
discussion in quantum physics and has been a source
September 27, 2010
of disagreements among theoretical physicists for many
years as there is a number of different ways in which
one can interpret this set of theoretically very unsettling
but empirically indisputable properties of quantum mechanics.
Von Neumann (1932) was probably the first person
that addressed the problem of quantum measurement
systematically and gave hints of its possible relation to
human consciousness (for related reviews, see Primas
and Esfeld, 1997; Esfeld, 1999; Thaheld, 2005; Rosenblum and Kuttner, 2008). According to him, the measurement process consists of three main components:
the system to be observed (S ), the measuring instruments (M) and the observer (O). In order to measure
the state of S , a physical device is needed. Let us denote it as M1 . This device has also its own states (e.g.,
the positions of the hand of a gauge) but these are sensitive to, and interact with S . The problem becomes
more interesting when one realizes that, as S and M1
interact they form a combined system (S 0 ), which also
needs to be observed. This observation can be made
only by another measuring device (M2 ), but then again
S 0 in combination with M2 forms S 00 , which needs yet
another measuring device M3 , and the chain can go on
up to the infinity. According to von Neumann, any measuring instrument, M, although a macroscopic object,
should obey the fundamental rules of quantum mechanics, much like S . Thus, before the state of a device M
has been measured, the device must be in a superposition state, and this holds for every device in the chain,
e.g., M1 , M2 , etc. This property postpones iteratively
the collapse of the wave function to an ever later measuring device positioned higher and higher on the hierarchy, rendering thus the problem unsolvable. Von
Neumann reasoned that in order to break this infinite
chain of measurements and to give to the whole process
a superposition-free, definite end, something with a very
distinct property––that cannot be described by the above
procedure and hence, by the quantum mechanics––needs
to be involved. He also provided a formal proof that the
formalism of quantum mechanics does not restrict the
choice of the point at which such a “cut” could be inserted and suggested, although only implicitly, that the
“subjective perception” of the human observer, O, or its
“abstract ego” plays this important chain-braking role
(von Neumann, 1932). Shortly after, London and Bauer
(1939) suggested explicitly that the collapse of the wave
function and thus, the measurement of a quantum process, cannot occur without the registration of the results
in the observer’s consciousness. This new role of human consciousness in theoretical physics was defended
by pointing out that consciousness has a “completely
special character”, which is “the faculty of introspection”, and which in turn allows a person to be aware
of the status of its own awareness (London and Bauer,
1939), corresponding to the measurement of itself and
abrogating thus the need for any additional measurement devices. Therefore, the registration of a result in
consciousness brings ultimately the initial system of the
measurement into a new form––taking a single eigenstate. Later, Wigner popularized this link between consciousness and collapse of wave function passionately
(Esfeld, 1999). Wigner suggested that “It is the entering of an impression into our consciousness which
alters the wave function.” and “It is at this point that
consciousness enters the theory unavoidably and unalterably.”(cited from Shimony, 1963). Importantly, however, Wigner dropped this opinion completely at his final years (Esfeld, 1999).
Critical evaluation and heated debate on this hypothesis has not been absent (e.g., Putnam, 1961; Margenau and Wigner, 1962; Shimony, 1963; Putnam,
1964; Cramer, 1986; Chalmers, 1997; Primas and Esfeld, 1997; Mandel, 1999; Esfeld, 1999; Menskii, 2000;
Brukner and Zeilinger, 2002; French, 2002; Thaheld,
2005; Koch and Hepp, 2006; Penrose, 2007; Nauenberg,
2007; Stapp, 2007; Rosenblum and Kuttner, 2008).
Many of them address this issue from the philosophical
point of view. Although they went to deep and interesting levels and brought up exciting ideas about fundamental aspects of the relationship between the mind
and the physical world, those profound analyses failed
to reach a simple and clear conclusion that would be
widely accepted. Partly due to this reason, the hypothesis that consciousness causes (or is necessary for) the
collapse of the wave function and, therefore, plays an
important role in quantum mechanics remained a theoretical possibility for the interpretation of quantum mechanics. Although not preferred by most physicists, this
solution to measurement problem is still strongly suggested even in some recent theoretical works (e.g., Menskii, 2000; Stapp, 2007; Rosenblum and Kuttner, 2008).
In the present paper, we do not aim to provide another philosophical argument. Instead, we attempt to
address this issue from an empirical perspective. We reformulate von Neumann’s hypothesis as an empirically
testable problem. We then attempt to falsify the hypothesis on the basis of the existing empirical evidence, as
already suggested elsewhere (Mandel, 1999; Zeilinger,
1999a; Brukner and Zeilinger, 2002). In addition, we
identify the experiments that need to be made in order
to rule out alternative explanations and thus, to test the
hypothesis more thoroughly. This analysis is also informative for the study of consciousness itself, a phe2
nomenon that is by no means easier to understand than
the measurement problem (Chalmers, 1997). Following the hypothetical role of consciousness in the collapse of wave function, a “symmetrical” proposal has
been made, namely, that the collapse of wave function
explains the emergence of consciousness. The most
straightforward approach is to equate the consciousness with the collapse of the wave function. Therefore, through a bidirectional relationship, the two deep
mysteries explain each other. This view has been explicitly expressed by e.g., Mensky (2007) but it is arguably an implicit assumption made by many other authors suggesting consciousness as a solution to the measurement problem (e.g. von Neumann, 1932; Wigner,
as cited above; London and Bauer, 1939; Lockwood,
1996). Therefore, if the role of consciousness in the
collapse of wave function can be falsified by empirical
evidence, these suggestions of using quantum mechanics to explain consciousness will also become if not unwarranted, then considerably less attractive.
Figure 1: The proposed experimental setup that can be used to test
whether collapse of wave function and consciousness about the outcome of the measurement are dissociated. This double-slit experiment
is a modification of an actual experiment that has been carried out
(Kim et al., 2000) and is similar in principle to the setup proposed by
Scully and Drühl (1982). See main text for the detail.
2. Experimental design
First, let us formulate the hypothesis to be tested:
measurement) is perceived at the level of subjective experience and that the observer is aware of its presence
such that he/she can produce an appropriate verbal report stating its identity. For example, one may state:
“The light beam hit the screen on the left side.”, “The
oscilloscope showed 1 MHz signal.” or “The gauge
pointed to 5 mV.” We think that this definition is fundamentally consistent with the issues described in the
introduction and is sufficient for the current analysis.
It is clear that this proposition can be never proven
true, much like any other theoretical statement in science cannot ever be proven true (Popper, 1963). However, propositions can be proven untrue, and in the
present case this can be made simply by finding a
counter example, that is, by finding an experimental
setup in which the collapse of wave function is dissociated from consciousness about the outcome of the measurement. Thus, the first goal is to find an experimental
setup that would allow one to assess both the state of
consciousness, and, independently, the state of the wave
function. To this end, we consider an adapted version
(Kim et al., 2000) of the experimental setup originally
proposed by Scully and Drühl (1982) and designed to
acquire “which-path” information in a so-called doubleslit experiment without interference (see Figure 1).
First, one photon from the pump travels through the
double-slit and can hit either region A or B located on
Proposition: The event of forming an explicit phenomenal representation of a result of quantum measurement in an individual observer’s mind is necessary for
the wave function (superposition state) of the system to
collapse into a single eigenstate.
By using logic symbols of implication (⇒) we can
write this statement formally as:
CWF ⇒ PR,
(1)
where CWF stands for “collapse of wave function” and
PR for “phenomenal representation”, meaning that the
collapse of wave function should be always associated
with a corresponding event of registering the results of
measurement in consciousness. Or, by using logical
negation (¬) we can express this proposition equivalently as contraposition of (1):
¬PR ⇒ ¬CWF,
(2)
meaning that the collapse of wave function should never
occur if the corresponding result of measurement has
not been registered by a conscious observer.
There are multiple definitions of consciousness. Here
we adopt a definition that can be operationalized. Therefore, the registration of a stimulus in the observers consciousness means that the stimulus (i.e., the results of
3
1) No actual attempt to measure the “which-path” information was made, that is, D1 and D2 are not implemented at all.
2) The “which-path” information was measured as D1
and D2 are implemented in order to interact with the
incoming photons. However, no results were recorded
by any macroscopic device and are not visible or in any
way accessible to a human observer.
3) The “which-path” information was measured by
a macroscopic device such as D1 and D2 . The results
were not recorded but were instead presented to a human observer directly such that the relevant information entered the sensory system but, at the same time,
the observer was distracted in order to prevent conscious detection of this event. In other words, the information necessary to achieve phenomenal representation was available in the nervous system, but conscious phenomenal experience was actually not realized. Thus, there were only non-phenomenal mental
representations. The relevant information can be presented by using a memory-less device (e.g., an old fashion gauge-based instrument) or by feeding the idle photons (or after amplification) directly into the retina and,
thus, having human eyes serve directly the function of
D1 and D2 (see Brunner et al., 2008; Thaheld, 2008,
2009). A distraction that prevents one from consciously
detecting a stimulus is made routinely in psychological studies and can be achieved by various means, such
as the visual masking (Lachter et al., 2000), attentional
blink (Raymond et al., 1992), binocular rivalry (Koch
and Hepp, 2006), change blindness (Rensink et al.,
1997), execution of a concurrent tasks (Kahneman et al.,
1967) , or by simply cluttering the visual scene (Treisman and Gelade, 1980). The interference with conscious perception can be made even more directly by
using trans-cranial magnetic stimulation. One could apply a magnetic pulse above e.g., visual cortex, in order
to interrupt the information processing in this brain region, preventing hence conscious perception of the visual stimuli (Silvanto et al., 2005).
Moreover, one can manipulate gradually the level of
subjective certainty of the presence of this information.
This should then, according to the proposition, affect
the contrast of the interference pattern accordingly––as
it has been shown in physical experiments by manipulating the extent to which the “which-path” information
was available, e.g., by changing the position of photon
detector (Zeilinger, 1999a) or by attenuating the optical
transmission (Mandel, 1999).
Verifying these three predictions through empirical
tests we propose to be a necessary requirement to warrant the hypothesis that consciousness of the outcome
the nonlinear optical crystal to produce an entangled
pair of photons. In the resulting pair, one photon (the
signal) travels through the lens LS and is detected by
the detector, D0 , positioned at the focal plane of LS. The
other photon (the idler) is routed the other direction and
travels through a prism to be diverted––depending on the
region in which it has been produced (A or B)––either
towards D1 or D2 . Thus, by knowing which of the two
detectors has registered a photon, we know which path
the signal photon has taken.
Next, we analyze the system more closely. Assume
first that the laser emits only one photon at a time. The
state of the photon, Ψ , can be described as:
1
Ψ = √ |Li + |Ri ,
2
(3)
where |Li and |Ri indicate the photon’s states, i.e.,
whether photon passed through the left or right slit, respectively. As a result, after the generation of a photon pair in the optical crystal, the signal photon may
take either both paths 1 and 2 simultaneously (if it is
in a superposition state, |1, 10 i + |2, 20 i , and hence the
wave function did not collapse) or through only one of
the two (if it is in single state, |1, 10 i or |2, 20 i due to a
collapse of the wave function). If the photons are always in a superposition state, after sufficient number of
photons have been registered at D0 , the distribution of
the registering location along the x-direction will exhibit
standard Young’s double-slit interference pattern, manifested by the distribution consisting of a series of peaks
and troughs (Kim et al., 2000). In contrast, the photons
that assume a single state will not produce such an interference pattern but will instead form a single-peak distribution (Kim et al., 2000). Thus, the presence of the
interference pattern at D0 indicates whether the wave
function of signal photon collapsed or not 1 . Thus, regarding the collapse discussed here, the relevant information (corresponding results of measurement) is which
path the photons took. Now, we can derive the predictions for this experimental setup that follow form previously formulated Proposition:
The interference pattern should be visible if “whichpath” information has not been registered in consciousness of the observer (e.g., the experimenter).
If the above is true, we expected to find the interference pattern at D0 in the following conditions:
1 Interference pattern is not necessarily obvious from the entire distribution. So proper separation of sub-populations of registered photons may be needed (Kim et al., 2000).
4
of a measurement is necessary for the wave function to
collapse. By formulating these predictions and requirement, we make this hypothesis empirically testable and
hence, falsifiable.
as we known can predict, correctly, no interference pattern in D0 , irrespective of what happen with the idler
photons (except for “erasing” the “which-path” information that is carried by those photons, see Kim et al.,
2000), and certainly irrespective of whether a conscious
observer is involved and where the attention of this observer is directed. Therefore, this setup cannot tell us
anything new about the relation between consciousness
and quantum mechanics that we did not know before.
So, did we just provide a circular argument?
To answer this question, let us consider the type of experiments that can be proposed in principle. According
to the opinion mentioned above, a really interesting test
would involve some observables not determined by the
current quantum theory. Only in that case, consciousness of the observer would be given a chance to affect
the results and only in that case we would be searching
empirically for novel discoveries. But, given the known
properties of quantum mechanics, is it possible ever to
conceptualize such an experiment? Designing such an
experiment would mean finding a situation in which the
quantum mechanics is either incomplete (e.g., the current theory does not predict whether interference will be
observed) or inconsistent (e.g., theoretically, presence
or absence of interference are both possible).
In the early years of quantum mechanics (see for example Einstein et al., 1935) doubts have been raised
about the correctness of this theory––which was a natural component of the scientific process. But by now,
more than seven decades later, quantum theory has been
proven to be one of the most accurate theories in the
whole science. Not a single prediction of quantum
mechanics has been empirically disproved. This casts
doubts on the possibility of designing a novel experiment in which an observable is not completely constrained by the known theory and would be still open to
the influences from the side of the consciousness of the
observer. Such an attempt would be equivalent to posing a challenge to the firmly established formulations
of quantum theory. The odds of something like this to
succeed seem too small to warrant pursuing. Therefore, we argue that the kind of experiment proposed
and discussed in the present paper, for which the results
are completely predictable by the known properties of
quantum mechanics, is the only kind of experiment that
can be in principle proposed. The results we described
can be considered as mere derivation of the quantum
theory. The reason it is important for us here is that it
manifests a perspective important for the current discussion––quantum mechanics may have not left any space
for the observer’s consciousness to manipulate the experimental results.
3. Existing evidence
The experimental results necessary to falsify the predictions 1 and 2 already exist. First, as described by
Mandel (1999) and Zeilinger (1999a), in experiments
similar to that proposed here, if “which-path” information was in principle obtainable, then even though no
actual attempt was made to extract this information (i.e.,
to measure it), no interference pattern was found. Thus,
the first prediction of consciousness hypothesis is false.
In other set of experiments (Eichmann et al., 1993; Dürr
et al., 1998), “which-path” information was measured
but was not recorded by any macroscopic device (for
example, this information was stored only in the state
of single atom or photon) and, therefore, was not accessible to a conscious observer. Under such condition,
also no interference pattern was found. Therefore, the
existing evidence indicates that the second prediction is
also false.
To the best of our knowledge, no direct attempt was
made to test the third prediction. However, the expectations for this experiment are clearly set by the evidence
related to predictions 1 and 2. That is, if no interference
pattern was obtained when the “which-path” information was not fed into the eye of the observer (e.g., carried by the idler photon as illustrated in Fig.1), the same
is expected to occur if the photon reached the observer’s
retina but the person was distracted as not to be able to
detect the event.
4. Discussion
We first derived a proposition about the relationship
between the collapse of the wave function and conscious
perception. Our subsequent analysis lead to the conclusion that this proposition is already disproved by the
existing empirical results, which forces us to conclude
tentatively the following: Conscious access to the information about the outcome of a measurement of a
quantum state is not necessary for the collapse of wave
function––conclusion similar to those suggested elsewhere (Mandel, 1999; Zeilinger, 1999a; Brukner and
Zeilinger, 2002).
Does the present analysis really tell us something
about the relation between consciousness and quantum
mechanics? One may argue that with the current experimental set up (shown in Figure 1), quantum mechanics
5
This conclusion suggests constraints for understanding the measurement problem and the mental-physical
relationship. Firstly, it is necessary to discuss what
constitutes a measurement, if we use the collapse of
wave function as a defining characteristic of it. Clearly,
measurement can be carried out without a macroscopic
measuring device. For example, the idler photon, that
carries the “which-path” information, can serve as the
measuring device. In similar experiments, atoms with
intrinsic states carrying “which-path” information can
also work as measuring devices and hence can cause
the interference pattern to disappear (Scully and Drühl,
1982). Therefore, the suggestion that the measurement
is completed when the results are registered in consciousness or when the results are recorded macroscopically (for example, see Primas and Esfeld, 1997) does
not seem to hold. It appears that neither the conscious
registration nor the macroscopic recording is necessary
for the collapse of the wave function. Even the interaction with the environment, as suggested by decoherence
theory, is not a sufficient ingredient for measurement
and collapsing the wave function. Because as long as
the “which-path” is in principle unobtainable, the wave
function does not collapse, regardless of the interaction
of the system with the environment (e.g., see Kim et al.,
2000 and other “quantum eraser” experiments). One
alternative is to conceptualize the quantum mechanics
as being based on a structure of information (Zeilinger,
1999b; Brukner and Zeilinger, 2002, 2005).
Secondly, our argument about the existence of collapse without conscious registration of corresponding
results casts strong doubt on those interpretations of
quantum mechanics that place the observer’s mind in a
special position (e.g., many-minds interpretation, Lockwood, 1996). In such interpretations, the wave function
is assumed to be the only and complete description of
physical reality. There is no objective “collapse” occurring outside the mind of the observer. Hence, according to these interpretations, the effect of a measurement
is “to create an entanglement between the state of the
system being measured, the measuring apparatus, and
the mind of the observer” (Lockwood, 1996). Hence,
the single state revealed after the measurement is only
perceived by the mind and does not reflect any physical event outside this particular mind. However, as we
argued, empirical evidence suggests that collapse occurs without the involvement of the mind. This renders
the no-collapse-outside-the-mind interpretations untenable. Importantly, the implicit assumption in these interpretations that the mind has a special property and
can, through collapse, perceive a single state has led to
a symmetrical completion of the relations by propos-
ing that the collapse of the wave function––within the
brain––is responsible for the emergence of consciousness (e.g., see Mensky, 2007). The present analysis
provides strong reasons for refuting the underlying arguments: If the former need to be rejected by empirical
evidence, the latter loses its foundations.
Thirdly, if consciousness does not play a special role
in the measuring procedure, the role of the observer in
quantum mechanics would be much less unique or mysterious. The observer would play a role no more special than that in the classical theory, for example, in
Einstein’s special theory of relativity (Shimony, 1963)
or in Darwin’s theory of evolution. Some authors suggested that, if consciousness is irrelevant, the role of
observer is special in the sense that he/she can choose
the quantum reality that will be created. For example,
the experimenter may decide whether to realize the interference pattern or not by deciding whether to make
the “which-path” information available or not (Brukner
and Zeilinger, 2002, 2005). However, to make such
choices special in comparison to other choices made
by a mechanically deterministic systems (e.g., a robot)
or random number generators (e.g., by playing a quantum dice), one needs to assume that the human observer
makes decisions in a qualitatively different way, perhaps
through “free will”. Neither theoretical analyses nor
the empirical data support the idea that humans make
decisions free of the physical processes or of the influences from the environment (Wegner, 2003; Baum,
2004; Haggard, 2005, 2008). Therefore, we do not see
how the fact that the experimenter has a choice could endow him or her with any more special role in the quantum than in the classical theory. Moreover, the conclusion that the observer plays no more a special role in
the quantum than in the classical mechanics would hold
even if we assumed the existence of “free will”. This is
simply because we would then “create” physical reality
routinely, outside the physics experiments, though each
individual’s actions resulting from our daily interactions
with the (mostly non-quantum) world. Therefore, “free
will” cannot save the consciousness hypothesis for the
explanation of the measurement problem, nor can it put
the human observer at a more special place in quantum
theory than it has been assigned in the classical theory.
Finally, it is helpful to note that the current analysis is
aimed to clarify a specific relationship between the mind
and the physical world, namely the hypothetical necessity of conscious registration of a measurement result to
collapse the wave function. We do not try to draw any
general conclusions about the relation between physical reality and phenomenal representations. One may
argue that, even if we show that the conscious regis6
tration of “which-path” information is not necessary to
collapse the wave function, we cannot exclude the possibility that the consciousness remains nevertheless responsible for the happening of the physical events. For
instance, one possibility is that the single-peaked distribution at D0 would never occur without a conscious perception of this distribution. To address this question, it
is helpful to clarify the present assumption about physical reality. We used the criteria suggested by Einstein,
Podolsky and Rosen (1935), stating that if one can predict the physical quantity with certainty and without disturbing the system, one can consider this quantity as a
physical reality. In our case, we can consider the distribution at D0 as the physical quantity of interest and
we demonstrated that if the “which-path” information is
obtainable, the distribution is always single-peaked (i.e.,
without interference patterns). That is, in this particular
case, we can predict the physical quantity with certainty
and without disturbing it. Therefore, we consider the
distribution in D0 as physically real. With this clarified, we can infer that the question about the possibility
that conscious perception of D0 distribution causes the
collapse of all the wave functions simultaneously and
creates hence the distribution itself, is an equivalent of
asking whether the conscious perception creates the reality of the world in general. According to this latter
idea, the universe would not exist if all its conscious
creatures close their eyes and shut their ears. This is a
non-trivial question––known as solipsism––that has challenged human intellect for a long time. It is important
to point out that this assertion is beyond the scope of
scientific enquiry as it is not empirically testable. In
other words, there is no conceivable experimental setup
by which this statement could be falsified. Solely for
that reason this assertion does not constitute a scientific
statement (Popper, 1963).
In conclusion, the available evidence does not indicate that the observer’s explicit phenomenal representation about the outcome of a measurement plays a role
in collapsing the wave function. We also suggest that
the observer does not serve a more fundamental function in quantum mechanics than that in the classical theory. Thus, the idea that by mere observation the experimenter creates physical reality is not viable. This supports Wigner’s opinion in his later years and promises to
fulfill his hopes––that we “will not embrace solipsism”
and “will let us admit that the world really exists” (cited
from Primas and Esfeld, 1997). Perhaps equally importantly, we can add our own hope that the rejection of the
role of consciousness in quantum mechanics will also
lead us to re-evaluate the proposals that quantum mechanics is vital for explaining the consciousness. Hav-
ing these two deep mysteries disentangled one from the
other might be an important step forward towards understanding better either of them.
Acknowledgement
We thank Hrvoje Nikolić, Thomas Metzinger,
Markus Arndt, Anton Zeilinger, Rajarshi Roy and Nick
Herbert for helpful comments.
References
Baum, E. B., 2004. What is thought? The MIT Press.
Bohm, D., 1952. A suggested interpretation of the quantum theory
in terms of ”Hidden” variables. I and II. Physical Review 85 (2),
166–193.
Brukner, C., Zeilinger, A., 2002. Young’s experiment and the finiteness of information. Philosophical Transactions of the Royal
Society A: Mathematical, Physical and Engineering Sciences
360 (1794), 1061–1069.
Brukner, C., Zeilinger, A., 2005. Quantum physics as a science of
information. In: Quo Vadis Quantum Mechanics? Springer, pp.
47–61.
Brunner, N., Branciard, C., Gisin, N., 2008. Possible entanglement
detection with the naked eye. Physical Review A 78, 052110.
Chalmers, D. J., 1997. The Conscious Mind: In Search of a Fundamental Theory, 1st Edition. Oxford University Press, USA.
Cramer, J. G., 1986. The transactional interpretation of quantum mechanics. Reviews of Modern Physics 58 (3), 647–687.
Dürr, S., Nonn, T., Rempe, G., 1998. Origin of quantum-mechanical
complementarity probed by a ‘which-way’experiment in an atom
interferometer. Nature 395 (6697), 33–37.
Eichmann, U., Bergquist, J. C., Bollinger, J. J., Gilligan, J. M., Itano,
W. M., Wineland, D. J., Raizen, M. G., 1993. Young’s interference
experiment with light scattered from two atoms. Physical Review
Letters 70 (16), 2359–2362.
Einstein, A., Podolsky, B., Rosen, N., 1935. Can QuantumMechanical description of physical reality be considered complete? Physical Review 47 (10), 777–780.
Esfeld, M., 1999. Wigner’s view of physical reality. Studies In History
and Philosophy of Science Part B: Studies In History and Philosophy of Modern Physics 30, 145–154.
French, S., 2002. A phenomenological solution to the measurement
problem? Husserl and the foundations of quantum mechanics.
Studies In History and Philosophy of Science Part B: Studies In
History and Philosophy of Modern Physics 33 (3), 467–491.
Haggard, P., 2005. Conscious intention and motor cognition. Trends
in Cognitive Sciences 9 (6), 290–295.
Haggard, P., 2008. Human volition: towards a neuroscience of will.
Nature Reviews Neuroscience 9 (12), 934–946.
Kahneman, D., Beatty, J., Pollack, I., 1967. Perceptual deficit during
a mental task. Science 157 (3785), 218–219.
Kim, Y., Yu, R., Kulik, S. P., Shih, Y., Scully, M. O., 2000. Delayed
”Choice” quantum eraser. Physical Review Letters 84 (1), 1–5.
Koch, C., Hepp, K., 2006. Quantum mechanics in the brain. Nature
440 (7084), 611–611.
Lachter, J., Durgin, F., Washington, T., 2000. Disappearing percepts:
Evidence for retention failure in metacontrast masking. Visual
Cognition 7 (1), 269–279.
Lockwood, M., 1996. Many minds interpretations of quantum mechanics. The British Journal for the Philosophy of Science 47 (2),
159 –188.
7
London, F., Bauer, E., 1939. La théorie de l’observation en mécanique
quantique (Hermann, Paris). English translation in Quantum Theory and Measurement, edited by J. A. Wheeler and W. H. Zurek
(Princeton University, Princeton, New Jersey, 1983), pp. 217–259.
Mandel, L., 1999. Quantum effects in one-photon and two-photon interference. Reviews of Modern Physics 71 (2), S274–S282.
Margenau, H., Wigner, E. P., 1962. Comments on professor Putnam’s
Comments. Philosophy of Science 29 (3), 292.
Menskii, M. B., 2000. Quantum mechanics: new experiments, new
applications, and new formulations of old questions. PhysicsUspekhi 43 (6), 585–600.
Mensky, M. B., 2007. Reality in quantum mechanics, extended everett concept, and consciousness. Optics and Spectroscopy 103 (3),
461–467.
Nauenberg, M., 2007. Critique of Quantum enigma: Physics encounters consciousness. Foundations of Physics 37 (11), 1612–1627.
Penrose, R., 2007. The Road to Reality: A Complete Guide to the
Laws of the Universe. Vintage.
Popper, K., 1963. The Logic of Scientific Discovery. Routledge.
Primas, H., Esfeld, M., 1997. A critical review of Wigner’s work on
the conceptual foundations of quantum theory. PhilSci Archive.
http://philsci-archive.pitt.edu/archive/00001574/.
Putnam, H., 1961. Comments on the paper of David Sharp. Philosophy of Science 28 (3), 234.
Putnam, H., 1964. Comments on Comments on Comments: a reply to
Margenau and Wigner. Philosophy of Science 31 (1), 1.
Raymond, J. E., Shapiro, K. L., Arnell, K. M., 1992. Temporary
suppression of visual processing in an RSVP task: an attentional
blink? Journal of Experimental Psychology. Human Perception
and Performance 18 (3), 849–860.
Rensink, R. A., O’Regan, J. K., Clark, J. J., 1997. To see or not to see:
The need for attention to perceive changes in scenes. Psychological
Science 8 (5), 368–373.
Rosenblum, B., Kuttner, F., 2008. Quantum Enigma: Physics Encounters Consciousness. Oxford University Press, USA.
Schrödinger, E., 1926. An undulatory theory of the mechanics of
atoms and molecules. Physical Review 28 (6), 1049–1070.
Scully, M. O., Drühl, K., 1982. Quantum eraser: A proposed photon correlation experiment concerning observation and “delayed
choice” in quantum mechanics. Physical Review A 25 (4), 2208–
2213.
Shimony, A., 1963. Role of the observer in quantum theory. American
Journal of Physics 31 (10), 755–773.
Silvanto, J., Cowey, A., Lavie, N., Walsh, V., 2005. Striate cortex (V1)
activity gates awareness of motion. Nature Neuroscience 8 (2),
143–144.
Stapp, H. P., 2007. Mindful Universe: Quantum Mechanics and the
Participating Observer. Springer.
Thaheld, F. H., 2005. Does consciousness really collapse the wave
function?:: A possible objective biophysical resolution of the measurement problem. BioSystems 81 (2), 113124.
Thaheld, F. H., 2008. A modified approach to the measurement problem: objective reduction in the retinal molecule prior to conformational change. Bio Systems 92 (2), 114–116.
Thaheld, F. H., 2009. A mechanical engineer’s approach to the
measurement problem: Is a picture worth a thousand words?
arxiv:0909.1526.
Treisman, A. M., Gelade, G., 1980. A feature-integration theory of
attention. Cognitive Psychology 12 (1), 97–136.
von Neumann, J., 1932. Mathematical Foundations of Quantum Mechanics. 1996 edition, Beyer, R. T., trans., Princeton Univ. Press.
Wegner, D., 2003. The mind’s best trick: how we experience conscious will. Trends in Cognitive Sciences 7 (2), 65–69.
Zeilinger, A., 1999a. Experiment and the foundations of quantum
physics. Reviews of Modern Physics 71 (2), S288–S297.
Zeilinger, A., 1999b. A foundational principle for quantum mechanics. Foundations of Physics 29 (4), 631–643.
8 |
DISTRIBUTED SOURCES, ACCELERATED UNIVERSE, CONSCIOUSNESS AND QUANTUM ENTANGLEMENT
arXiv:nlin/0511040v3 [nlin.PS] 19 Dec 2005
E. A. Novikov
Institute for Nonlinear Science, University of California - San Diego, La
Jolla, CA 92093 - 0402
It is shown that such diverse phenomena as accelerated Universe, consciousness and quantum entanglement are connected by the concept of distributed
sources and imaginary (particularly, tachyon) fields.
The singular vortices, sources (sinks) and vortex-sinks are well known models
in fluid dynamics (including geophysical fluid dynamics), magnetized plasma,
superfluidity and superconductivity (see, for example, Refs. 1 - 3 and references
therein). Dynamics of distributed vortices is a well developed area of research.
However, to our knowledge, dynamics of distributed sources (DS) has not been
considered until recently [4]. One of the applications of DS, indicated in Ref.
4, is cosmology. Particularly, solution of corresponding equation with constant
intensity of DS [4] is similar to homogeneous solution of general relativity with
the cosmological constant (CC). However, analysis of DS in Ref. 4 was nonrelativistic. In this Note we consider relativistic generalization of DS. We will
show that DS, in certain simple case, produce the effect of CC in the accelerated
expansion of the Universe. Relativistic DS can be used also for local phenomena
in cosmology. We will also show a connection between DS and phenomena of
consciousness and quantum entanglement.
Local intensity of nonrelativistic DS is characterized by the divergency of
the velocity field ∂v α /∂xα ( summation over the repeated Greek indexes is
assumed from 1 to 3 ). Dynamical equation for DS was obtained by considering
superposition of localized sources, which move each other with induced velocity
field [2 - 4].
For relativistic DS we need four-dimensional velocity field (see, for example,
Refs. 5, 6):
ui =
dxi
d
∂
dxi
=γ
, γ = (1 − v 2 )−1/2 ,
≡ uk k
ds
dτ
ds
∂x
(1)
Here position of fluid element is characterized by the 4-vector xi with components (τ , xα ), where τ = ct and c is the velocity of light. Components xα in
turn can be considered as functions of τ and some identification parameters, for
i
α
α
example, initial positions xα
o . 4-vector u has components (γ, γv ) with v normalized by c, γ is the Lorentz factor and summation over repeated Latin indexes
is assumed from 1 to 4. Components ui can be considered as functions of xi or
as functions of (τ , xα
o ). For simplicity, we will use the covariant differentiation
only where it is needed (see below equation (8)).
1
It seems natural to characterize local intensity of relativistic DS by divergency of 4-velocity:
∂ui
∂γ
∂(γv α )
=
(2)
+
i
∂x
∂τ
∂xα
In nonrelativistic case with v ≪ 1, we have: γ ≈ 1, ∂γ/∂τ ≈ v(∂v/∂τ ); the
first term in the right hand side of (2) is much smaller than the second term
and we return to the presented above nonrelativistic expression (apart from
normalization by c).
The equation for σ, which is relativistic generalization of corresponding equation in Ref. 4, reads:
σ=
dσ
=f
(3)
ds
Here f may include diffusion and some other effects (see Ref. 4). In this
Note we consider ”free” sources with f = 0 (see below a justification of such
choice for a concrete physical problem). In this case, taking into account (2),
we get equation:
∂γ
∂(γv α )
= σo
(4)
+
∂τ
∂xα
Here σ o , generally, depends on xα
o . In Ref. 4 some analytical solutions of
nonrelativistic analog of equation (4) were obtained for certain initial conditions,
characterized by field σ o . Corresponding analytical solutions of equation (4)
can also be obtained. In this Note we consider one important and specifically
relativistic case.
What we have in mind is the problem of accelerated Universe (AU). The
accelerated expansion is extracted from observed luminosity of the type Ia supernovae [7 - 9]. The described above DS model suggests production of particles
in AU. Balance of the proper number density of particles n can be written in
the form:
dn
∂(ui n)
=
+ σn = q
(5)
∂xi
ds
where q is the rate of particle production. In a quasistationary case σn ≈ q and
the macroscopic fluid, consisting of particles, can be considered approximately
incompressible. However, this is not an ordinary fluid, as was stressed in Ref.
4. The traditional consideration with the energy-momentum tensor has to be
modified. The system is not Hamiltonian, as was indicated in the case of the
system of interacting point sources [2]. It seems natural to assume that in the
quasistationary case q is approximately proportional to n, which means that
σ ≈ σ 0 . This is a justification of the choice f = 0. More general cases can be
studied in future.
Let us consider homogeneous AU by using the thermodynamic relation:
dE = δQ − pdV
2
(6)
where E, p, V , are the energy, pressure, and the volume of the system, and δQ
is a supply of energy by production of particles. The production of particles can
be considered as some sort of internal boundary condition. For homogeneous
AU we can write:
δQ = εs dV
(7)
where εs is the energy density produced by DS. For dustlike matter εs = mnc2 ,
where m is the mass of corresponding particles. Combining (6) and (7), we see
that effect of DS in the described case is equivalent to the negative pressure
−εs . The negative pressure, in turn, corresponds to the effect of CC (see, for
example, Ref. 9).
At the last stage of AU, when DS will dominate the dynamics, we can determine the scale factor a(τ ) from equation (4) written in the covariant form:
∂ui
+ Γiki uk = σ o
∂xi
The Christoffel symbols satisfy condition [5]:
ui; i =
Γiki =
1 ∂g
2g ∂xk
(8)
(9)
where g is the determinant of the metric tensor. For homogeneous isotropic AU,
in the proper synchronized frame of reference [5] we have: uo = 1, uα = 0. From
(8) and (9) we get:
∂g
= 2σ o g
(10)
∂τ
Taking into account that g ∼ a6 and σ o is constant (for isotropic AU), we have:
1
a(τ ) = ao exp{ σ o τ }
(11)
3
This simple result conforms to the nonrelativistic consideration [4] and to the
analogy with CC.
Thus, DS in the simplest case reproduce the effect of CC. In addition, DS
can provide a novel intuition and a quantitative analysis not only for the global
description of AU, but also for more local (nonhomogeneous and nonquasistationary) cosmological phenomena.
Asymptotically, expansion (11) becomes superluminary: da/dτ > 1. This
suggests that particles and fields created by DS have imaginary (particularly,
tachyon) components. These imaginary fields (IF) can play an important role
not only in cosmology, but also in a variety of phenomena.
Consider the renormalization procedures [10], which are the basis for substantial part of contemporary physics. Feynman, who (with Tomonaga and
Schwinger) got the Nobel Prize for refinement and applications of these procedures, compared renormalization with sweeping dust (infinities) under the rug.
In recent note [11] IF have been used to eliminate divergencies in the classical theory of electromagnetic field, namely, infinite self-energy of electrons and
3
paradoxical self-acceleration. The natural next step is to eliminate infinities in
quantum field theories with an appropriate use of IF.
Another application of IF is to the phenomena of consciousness (considered
as collective effect of billions of interconnected nonlinear neurons). The brain activity revealed the regime of scale-similarity [12-14], which is typical for systems
with strong interaction of many degrees of freedom (particularly, for turbulence
[15]). Modeling of the effects of consciousness on the electric currents in the
human brain leads to the use of IF [16]. Possible connection of DS with consciousness was indicated in Ref. 16. Now we have additional reason (11) in favor
of such connection. Another possible connection is between IF, which eliminate
electromagnetic divergencies [11], and IF in the modeling of consciousness [16].
Finally, consider the quantum entanglement, the EPR experiment and all
that (see corresponding discussions in Refs.17, 18). It seems natural to assume
that relativistic DS are produced by the quantum vacuum. According to (11),
DS lead to superluminary IF-effect on cosmological scale. Why the same quantum vacuum can not produce locally an IF-signal in special circumstances, say,
during the process of quantum measurement? This will explain the quantum
entanglement.
Perhaps, DS & IF provide the missing link between the quantum theory and
the general relativity.
References
[1] E. A. Novikov, Ann. N. Y. Acad. Sci. 357, 47 (1980)
[2] E. A. Novikov and Yu. B. Sedov, Fluid Dyn. 18, 6 (1983)
[3} A. E. Novikov and E. A. Novikov, Phys. Rev. E 54, 3681 (1996)
[4] E. A. Novikov, Phys. of Fluid 15 (9), L65 (2003); arXiv:nlin.PS/0501010
[5] L. D. Landau and E. M. Lifshitz, The Classical Theory of Fields, Pergamon Press, 1987
[6] L. D. Landau and E. M. Lifshitz, Fluid Mechanics, Butterworth-Heinemann,
1995
[7] A. G. Riess et al., Astron. J. 116, 1009 (1998); Astrophys. J., 607, 665
(2004)
[8] S. Perlmutter et al., Astrophys. J. 517, 565 (1999)
[9] Reviews of theories of AU with many references can be found in V.
Faraoni, Cosmology in Scalar-Tensor Gravity, Kluwer, 2004, and in D. H. Coule,
Class. Quantum Grav. 22, R125 (2005).
[10] V. B. Berestetskii, E. M. Lifshitz and L. P. Pitaevskii, Quantum Electrodynamics, Pergamon Press, 1982
[11] E. A. Novikov, arXiv:nlin.PS/0509029
[12] E. Novikov, A. Novikov, D. Shannahof-Khalsa, B. Schwartz, and J.
Wright, Phys. Rev. E 56(3), R2387 (1997)
[13] E. Novikov, A. Novikov, D. Shannahof-Khalsa, B. Schwartz, and J.
Wright, in Appl. Nonl. Dyn. & Stoch. Systems (Ed. J. Kadtke & A. Bulsara),
p. 299, Amer. Inst. Phys., N. Y., 1997
4
[14] E. S. Freeman, L. J. Rogers, M. D. Holms, D. L. Silbergelt, J. Neurosci.
Meth. 95, 111 (2000)
[15] E. A. Novikov, Phys. Rev. E 50(5), R3303 (1994)
[16] E. A. Novikov, arXiv:nlin.PS/0309043; arXiv:nlin.PS/0311047; arXiv:nlin.PS/0403054;
Chaos, Solitons & Fractals, v. 25, p. 1-3 (2005); arXiv:nlin.PS/0502028
[17] D. Bohm & B. J. Hiley, The Undivided Universe, Routledge 1993
[18] Roger Penrose, The Road to Reality, Jonathan Cape 2004
5 |
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
391
Research Essay
Plato’s Republic as Metaphor for Enlightenment: Part I
Anthony N. Lundy*
ABSTRACT
Plato uses the most rigorous logic, stories, and analogies in an effort to show what appears to be
a mystical vision. Indeed, this is affirmed if we consider his aim of turning the cave dweller
towards the light. In essence, as we have seen, this is a turning inward --or the self-reflecting on
itself, which ultimately leads to a subject-to-object merging. It is through the cognitive
progression, however, from image, to belief, understanding and knowledge that enlightenment is
achieved. This, we have seen, corresponds to mystical experiences. Why is this occurring? If we
follow Plato’s procession of knowledge, it follows logically that this must occur. The true nature
of self (at the lower levels of the hierarchy) cannot be perceived unless directly perceived at the
level of forms--where images dissolve. If we examine the dialogues closely, I believe clues can
be found that point to the mystical experience. I propose that the merging into one with regard to
the tripartite soul--with each component becoming aligned with the rational--which is really a
way of “purifying us from the defilements of the passions…”as well as Socrates’ refutation of
opinions or belief to find universals are both evidence of a synoptic perspective characteristic of
mystics who have achieved a mystical experience.
Part I of this two-part research essay includes the following sections: Introduction;
Enlightenment; Mystical Experiences; Plato’s Rules; and Plato’s Rules.
Key Words: Plato, Republic, metaphor, enlightenment, vision, form, mystical experience.
Introduction
Many scholars regard the Republic as Plato’s most comprehensive and seminal work. However,
its central theme has been the subject of much debate, resulting in many varying opinions. For
instance, some interpretations regard it as a response to the weakness of democracy that resulted
in the Peloponnesian War, a reaction to the sophists (masters of the art of illusion), clever
rhetoricians who twisted the truth to suit their arguments, an ethical treatise on the nature of
justice; or a pedagogical treatise on education encouraging open-mindedness, thinking outside
the box, not accepting convention, and thinking mathematically or scientifically. However, I
contend there is another interpretation that suggests an underlining unity to Plato’s thought: to
bring the soul nearer to the truth or to achieve enlightenment. I propose that the dialogues of
Plato are stories and analogies crafted deliberately to explain and set up the conditions for
achieving enlightenment.
*Correspondence: Anthony N. Lundy, Independent Researcher. E-mail: gumlobel@hotmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
392
Although the word enlightenment usually connotes something mystical in nature, it is my
contention that Plato offers a more discursive or intellectual approach to an understanding of
what enlightenment really is. In other words, I believe Plato is deliberately attempting to appeal
to the intellect in grasping an inner spiritual experience. This seems to be his chief concern in
many of the dialogues. It is the “hidden law governing what the thinker says” (Heidegger 9). It is
not my claim, however, that every dialogue reflects this, but is true if the dialogues are taken as a
whole.
What I mean by enlightenment, generally speaking, is a journey of the soul (self’s) from bondage
to direct knowledge and understanding of the true nature of self. I refer to self in the sense of the
soul being experienced as the self. In other words, in terms of Plato's tripartite theory of soul, the
self is the same as soul--the rational part that controls and corrects the balance between the
appetite and the spirit. To experience the true nature of self, however, involves an integration of
the tripartite soul (the many becoming the one) with the rational governing the other
components. This process involves, as I will attempt to show, the soul’s (self) journey through
the stages of cognition (represented by Plato’s Divided line analogy or Allegory of the Cave)
from the world of images through the intelligible world and ultimately to the level of forms, or
the Good. Enlightenment occurs once the soul has reached the Good. Cognitively speaking,
however, this entails a unifying experience characterized by a blurring of subject-to-object
relationships.
My focus in this paper, therefore, is to try to unveil this unity by addressing the following; 1) an
explanation of what mystics say about it; 2) a demonstration of parallels between mystics and
platonic ideas in the discussion of Book II- IV with emphasis on justice and the many becoming
one; 3) a discussion of the Cave and Divided Line as they relate to achieving enlightenment; 4) a
discussion of Book VIII-X with emphasis on Plato’s return to the earlier theme of justice; and 5)
Conclusion.
Enlightenment
I have already laid out, in the above context of Plato’s Republic, that enlightenment is the
journey of the soul from bondage to a deeper understanding of the nature of self. It entails the
integration of the tripartite soul. However, to make the argument that Plato’s central concern is
enlightenment, we must define it more precisely and, in doing so, dispel misconceptions about its
meaning. In Sanskrit the word for enlightenment is “bodhi,” which means "awakened.”
According to the Oxford English Dictionary online, the following definitions are listed:
1. The action of bringing someone to a state of greater knowledge, understanding, or insight;
the state of being enlightened in this way.
2. The state of spiritual insight or awareness which frees a person from the cycle of suffering
and rebirth.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
393
It is evident by looking at some of these definitions that they vary in meaning. It is common
knowledge, for instance, that the word was used to refer to the eighteenth-century movement
called the Enlightenment that promulgated self-autonomy and reason. However, of course, this is
not the meaning to which I am referring here. There is also the meaning derived mainly from
religious sources such as Buddhism or Hinduism and involves an awakening of some kind,
which is closer to my meaning. For the sake of clarity, perhaps it is useful, at this point, to define
precisely what I mean by enlightenment. I can think of no better definition of enlightenment than
the one put forward by the renowned British scholar Evelyn Underhill. Although she uses the
term mysticism, I will be using the word enlightenment as a synonym for mysticism. These
words are often used interchangeably when referring to the same experience. Underhill’s
definition is as follows: “Mysticism is the art of union with reality. The mystic is a person who
has attained union in greater or lesser degree; or who aims at or believes in such attainment”
(Underhill 5). The attainment of union with reality is usually characterized as a mystical
experience. Enlightenment, as I am using it in this paper, refers to union with reality. Some refer
to that reality, however, by different names such as God, the Good, the ineffable, oneness,
emptiness, the void or silence. Precisely what Plato believes this reality to be can be uncovered
in the pages of the Republic.
It can be argued that the word mysticism (in the manner to which we are referring) was a term
introduced to the West by Dionysius the Areopagite (aka - Pseudo-Dionysius) For centuries, he
was regarded as a preeminent theologian of Christendom where “nearly every great mediaeval
scholar made use of his writings, and his authority came to be almost final” (Dionysius 1).
Dionysius was thought to be a disciple of St. Paul; however, later scholars found this to be false
as it was clear that his writings were Neo-platonic in nature and could not have been written
during the time of St Paul. They showed a much later date of fifth to early sixth century. The
writings of Dionysius are mystical in nature and called attention to the transcendence of God,
and his ineffable nature. Of the ineffable nature of God, he writes:
“It is not soul or mind, nor does it possess imagination, conviction, speech, or
understanding. Nor is it speech per se, understanding per se. It cannot be spoken of and it
cannot be grasped by understanding. It is not number or order, greatness or smallness,
equality or inequality, similarity or dissimilarity. It is not immovable, moving or at rest. It
has no power, it is not power, nor is it light. It does not live nor is it life. It is not a
substance, nor is it eternity or time. It cannot be grasped by the understanding since it is
neither one nor oneness, divinity nor goodness. Nor is it a spirit, in the sense in which we
understand that term. It is not sonship or fatherhood and it is nothing known to us or to
any other being. It falls neither within the predicate of nonbeing nor of being. Existing
beings do not know it as it actually is and it does not know them as they are. There is no
speaking of it, nor name nor knowledge of it” (Dionysius 2).
The experience of the ineffable quality of God is demonstrated clearly in this text as being so
transcendent that it cannot be spoken of for there are no words or thoughts to describe it. In other
words, it is beyond all categories of thought or anything humanly conceivable. To name it is to
profane it and bring it into perceptible human terms. Naming it God or even eternal makes it into
something which is antithetical to its ineffable nature. One must remain silent.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
394
This recalls Plato’s Parmenides and his paradoxical claim of the one-over-many theory, in which
he assumes a connection between the one and many. It is paradoxical because if something is
one, it follows logically that it cannot have parts or be said to change or become a multiplicity, or
else it loses its oneness. However, in this case, the paradox lies in naming something that is by its
very nature nameless; but Dionysius seems to be anticipating the inclination to name it. Thus, the
exhortation “There is no speaking of it, nor name, nor knowledge of it” (2).
Mystical Experiences
This is but one description of a mystical experience in terms of encountering the ineffable nature
of God. However, as we shall see, there are many other mystical experiences that, although
different from each other in some ways, are evidence of a universal phenomenon. My point here
is to describe mystical experiences to bolster the point I want to make later in this work, namely,
that Plato, too, was a mystic and his dialogues reflect this. It is clear that although mystics claim
the experience to be ineffable or beyond description, they nevertheless attempt to describe them
anyway.
Therefore, let us explore some descriptions of mystical experiences. In the interest of structure,
let us start with Western mystics and then move on to Eastern mystics. However, before doing
this, I will digress a bit and give a brief synopsis of the Allegory of the Cave and Divided Line
analogy, as they will be used as references in many of the descriptions of mystical experiences
we will talk about. Later, we will expound upon them.
The Divided Line is an analogy Plato uses to express degrees of reality and being. The line is
divided into four unequal segments. The proportions of the lengths reflect the degree to which
one is farther or nearer to reality. The two lower rungs of the line (if viewed vertically) are said
to be at the level of images (eikasia) and opinion (pistis) where one is furthest away from
grasping reality. The two higher rungs are said to be understanding (dianonia) and knowledge
(noesis) where one has achieved, cognitively speaking, a higher grasp of reality. Indeed, at the
level of knowledge ultimate reality is perceived. Plato refers to this ultimate reality as the Good.
The main divisions between the lower and higher levels, however, are the visible world
perceived by sense perception and the intelligible world perceived by the intellect (or mind’s
eye).
In the Allegory of the Cave, Plato expounds on the degrees of reality and being. He does it by
way of an allegory in which groups of prisoners have been chained deep in a cave since birth.
They are so immobilized by the chains they are forced to look forward at a wall. Behind them, is
a fire, and between the fire and the prisoners is a raised walkway, the length of which, objects
such as animals, plants, and statutes are paraded across, thus casting shadows onto the wall.
Further behind them is the opening of the cave that leads outside. The prisoner compelled to
leave the cave begins eventually to free himself and turn his head, for the first time, toward the
light. The prisoners turn toward the light of the fire is the first step up the latter of cognitive
perception to greater degrees of reality and being. At the level of fire, which cast shadows on the
wall, equates to level of opinion of the Divided Line whereas the shadows that are cast on the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
395
wall equate with images. Eventually, the prisoner makes his way outside the cave where he sees
objects as they really are without images and shadows. This reflects the higher rungs of
cognitive perception of understanding and knowledge. This level is Plato’s ultimate goal in terms
of encountering truth and reality.
These are brief synopses of the Divided line and the Allegory of the Cave to aid the reader in
understanding some of the ideas related to degrees of cognitive perception. Therefore, let us
return to our discussion of mystical experiences.
The Mystical tradition offers a vast well to draw from, but for the purposes of this paper I will
discuss only a few. My intention is not to get into a comparative analysis of the whole of
mystical literature, but only to draw out commonalities as necessary.
In terms of Western mysticism, a mystic worth mentioning is Plotinus (204-270 C.E.). He was
born in Hellenistic Egypt but studied philosophy under Ammonius Saccus, a Neo-Platonist in
Alexandria--the hub of education in the ancient world. He later became a scholar and taught in
Rome. Neo-Platonists were essentially Platonists who tried to fuse the Christian doctrine with
Platonic ideas like the Good. Plotinus’ central idea is that the universe consists of a series of
emanations stemming from a one. This one is free of multiplicity and undifferentiated until
emanations flow from it. There is a descending order of emanations that ultimately lead to its fall
into matter; and there is an ascending order that leads to a union with the one. Plotinus’ ideas are
reflected in Enneads which are a collection of his works put together by his student Porphyry
(Plotinus Xlii). In it, he writes about a mystical vision of the one:
“But in the vision, that which sees is not reason but something greater than and prior to
reason, something presupposed by reason, as is the object of vision. He who then sees
himself when he sees will see himself as a simple being, will be united to himself as such,
will feel himself become such. We ought not even to say that he will see, but that he will
be that which he sees, if indeed it is possible any longer to distinguish seer and seen, and
not boldly to affirm that the two are one. In this state, the seer does not see or distinguish
or imagine two things; he becomes another, he ceases to be himself and to belong to
himself. He belongs to Him and is One with Him, like two concentric circles; they are
one when they coincide, and two only when they are separated. It is only in this sense
that the soul is other. Therefore this vision is hard to describe. For how can one describe,
as other than oneself, that which, when one saw it, seemed to be one with oneself?”
(Armstrong 136).
I will offer some commentary on this passage since I think it will be relevant to our discussion
later. “But in the vision, that which sees is not reason but something greater than and prior to
reason, something presupposed by reason, as is the object of vision” (136). This passage seems
to suggest that reason is useless in perceiving the vision. It follows that this is likely since, as we
see further in the passage, he is referring to a vision of unity: “He belongs to Him and is One
with Him, like two concentric circles; they are one when they coincide…” Reason, which usually
involves a comparative judgment, meaning a comparison made relative to the objects you are
measuring against, seems blunted in an undivided, or non-multiple, world. Why? Because there
is nothing to compare--all is one. The seeing, thus, seems to result, not from reason but as the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
396
passage suggests, from something “greater than and prior to reason.” What can this be? I would
like to suggest here it is the mind’s-eye (noetic perspective) or, in terms of Plato’s Divided Line
analogy, understanding at the intelligible level beyond sense-perception. “We ought not even to
say that he will see, but that he will be that which he sees, if indeed it is possible any longer to
distinguish seer and seen.” This passage seems to imply that seer and seen are one. In this
respect, a vision may seem misleading as it presupposes a subject-to-object relationship--a seer
(subject) who sees a vision (object). This point is the cause of much confusion and difficulty in
understanding enlightenment experiences. This point is also key to understanding my thesis, as I
will later attempt to show that Plato is attempting to achieve this blurring of subject-to-object
vision through his dialogues. This involves the many becoming the one. What is interesting
about Plotinus’ brand of mysticism is that, like Plato, his approach was more intellectual and
discursive than religious, as the term religion is usually understood: that is, an approach that
involves accepting doctrines or beliefs on faith.
Plotinus’ unifying experience created tensions among theistic religions. According to W. T.
Stace (a scholar of mysticism of some renown), theistic religions believe that there is a “great
gulf” between God and man, Creator and creature, which nothing can bridge (128). They are
distinct substances. So for a man to claim to be one with God would be blasphemous. He points
out that the propensity for Christian mystics to want to transcend duality and enter into union
with God created problems between ecclesiastical authorities of the Roman Church. Many were
accused of heresy. One such mystic was Meister Eckhart, who said “my eye and Gods eye are
one and the same” and God and I are one.” (Blakney 97)
Meister Eckhart, a Christian theologian, was born in Germany (1260-1327). He was famous for
composing sermons and using interesting terms to describe the mystical experience. For instance,
he used the phrase “the birth of Christ in the soul” which seems to be a reference to a beginning
stage of mystical development (Stace 140). A birth presupposes a maturing or gradation of some
kind to higher stages of development--not unlike Plato’s Divided Line as we shall see later. He
goes on to express how difficult this experience is to achieve:
“The birth, he says, is impossible without a complete withdrawal of the senses… and
great force is required to repress all the agents of the soul and causes them to cease to
function. It takes much strength to gather them all in, and without the strength it cannot
be done” (Blakney 109).
The birth of the Christ within, the passages suggests, involves a withdrawal of the senses. Why?
It is, cognitively speaking, when objects of thought that involve things derived from the senses
are transcended. The repressing of agents presupposes a state of multiplicity that must be
harmonized (or brought into a one). The term Christ seems to symbolize the mystical experience,
which can only be achieved if senses “cease to function.” This seems to align nicely, as we shall
see later, with Plato’s tripartite theory of the soul and its harmonizing.
In the mid 16th century, Teresa of Avila, a Carmelite nun from Spain, wrote in her autobiography
the following passage about her mystical experience:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
397
“the persons who must speak of it are those who know it, for it cannot be understood, still
less described. As I was about to write of this…I was wondering what it is the soul does
during that time [referring to mystical experience], when the Lord said these words to
me: It dies to itself wholly, daughter in order that it may fix itself more and more upon
me…It is no longer itself that lives but I” (Peers 119).
This clearly shows a unifying experience that is common to mystical experiences. The statement
that “It is no longer itself… but I” demonstrates a union with God. This is one of the first
instances in which we see the use of God rather than the term ineffable. The experience seems to
be suggesting a merging of the soul with the godhead. Teresa of Avila was also known for
hearing voices. However, they were regarded as an inner hearing rather than an audible one.
St John of the Cross, a contemporary of Teresa of Avila, was also part of the Carmelite order and
Teresa’s spiritual advisor. He similarly contends that in order to achieve a unifying experience
with God that “the soul must be emptied of all these forms, figures, and images and it must
remain in darkness in respect to these internal senses if it is to attain divine union” (Stace 185).
It is apparent that until the soul’s “internal senses” are purged it cannot achieve union. This
suggests a move, cognitively speaking, from the level of sense-perception to a cognitively higher
perception similar to abstract thinking –or in a Kantesian sense, the realm of a priories: that is
knowledge or concepts that are derived from intuitions rather than experience. Mathematical
concepts are perfect examples of a priori knowledge. Geometry, for instance, involves spatial
reasoning more than experience-based reasoning: in other words, reason based in intuition. This
corresponds to Plato’s intelligible world, as we shall see later.
Another western mystic of note is Jan van Ruysbroek. He was a Flemish mystic from Brussels,
born in1293. The story goes that because he was dissatisfied with being a Cathedral chaplain, he
left Brussels to seek refuge in a hermitage on the outskirts of town. He devoted himself to “the
inner life of the spirit” (Stace 158). Gradually, he developed a following and lived a
contemplative life. Some of his expressions of mystical consciousness resemble Meister
Eckart’s, like the Christ born within. He taught that to attain mystical union it is necessary to
empty the mind of sensations, images, and thoughts (158). He wrote:
“such enlightened men are, with a free spirit, lifted above reason into a bare and
imageless vision wherein lies the eternal indrawing summons of the divine unity; and
with an imageless and bare understanding they…reach the summit of their spirits”
(Wynschenck 185).
Rising above reason seems to be a central feature in mystical experiences. An “imageless vision”
seems to be an inference to a cognitive step above sense-perception to Plato’s world of
intelligibles. And as the passage suggests, the “imageless vision” is the point at which the spirit
is summoned or drawn to the divine unity. This recalls Plato’s dialectic method which, as a
stepping stone, leads to a higher cognitive perception of the forms or the Good.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
398
“I mean that which reason itself grasps by the power of the dialectic. It does not consider
these hypotheses as first principles but truly as hypotheses--but as stepping-stones to take
off from, enabling it to reach the unhypothetical first principal of everything” (511b).
Islamic mysticism which I shall group with the Western mysticism, is called Sufism. It is
regarded as the esoteric side of Islam. The name Sufi means wool which some say was a
nickname for the early Muslim mystics who wore wool clothing. Sufism flourished in Arab and
Persian countries (Stace 201). Precisely when and where it originated from is not known, only
that it probably started around the ninth century C.E. (201). In Turkey, Sufis were known for
their whirling, which led to a higher unified state.
Early Sufi mystics were panentheistic, believing creation and creator were one. However, this
view creates tension with some orthodox Muslims, who held ideas similar to the Christian
orthodox. They think that any identification of being one with God is blasphemous. For
instance, a Sufi mystic, Al Hallaj (922 C.E.), once claimed that he was one with God and was
later crucified in Bagdad (Stace 202). There is another great Sufi worth mentioning. His name is
Al Ghazali (1058–1111). However, there is not enough to go on to determine if he achieved a
mystical experience. He was more a scholar of philosophy, science and theology who wrote
many seminal works. He was said to be the Islamic Thomas Aquinas of his day. It is worth
noting, however, that “his position was wholly sympathetic to the mystic claim to immediate
experience of God, and one of his central aims was to reconcile Sufism and Islam orthodoxy”
(Stace 203). However, a mystic more of the variety we are seeking is Abu Yazid (804-874)
(Brown 141). He was a Persian mystic from Bastam, Iran, who was one of the first Sufi’s to
speak about the mystical experience in terms of a unitive experience as the following passage
illustrates:
"Creatures are subject to changing 'states,' but the gnostic has no 'state,' because his
vestiges are effaced and his essence annihilated by the essence of another, and his traces
are lost in another's traces” (Nicholson 18).
Once again, this seems to be another unification process, as essence dissolves into another
essence. Essence annihilation and the resulting sense of oneness are key to understanding the
nature of the mystical experience. The annihilation occurs once subject and object are merged.
Jalal a-Din Rumi, who lived in the 13th century, is probably one of the better celebrated Sufis. He
was and still is considered a poet who expressed his poetry in mystical terms. His most famous
poem is called the Mathanawi, in which he writes about the vision of one by using light as an
analogy for God:
“The lamps are different; but the light is the same. It comes from beyond... ...fix your
gaze upon the light and you are delivered from dualism inherent in the finite body”
(Nicholson 166).
The urge to fix one’s gaze on the light seems to be inviting a deeper understanding of the lamp,
much deeper than what sense-perception can offer, apparently. The light is clearly eternal in
nature, but the lamp which embodies the light and differs in appearance, suggests change.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
399
Change, as we will see in Plato’s dialogues, is associated with sense- perception, or the world of
becoming whereas things that are immutable or eternal belong to the world of being. The lamp,
therefore, can be seen as a metaphor for the body (becoming) and the light, the soul (being). The
gazing at the light which is eternal, thus results in the transcendence of dualism. We have yet
another unifying experience.
Of the two eastern mystical traditions, Confucianism and Taoism, the latter seems more
mystically oriented and thus more relevant to our survey. Confucius seems to be more known for
what can be described as codes of conduct. Although his writings are filled with wise sayings
and may reflect an enlightened consciousness, like Al Ghazali, there is not enough to go on to
prove it conclusively.
Taoism developed out of a book Tao Ching, written by Lao-Tzu (570 B.C.E.). The word Tao
literally means the way. The meaning of way is best described in poem no. 4 in the Tao. The
way, it says, “is a void which is never filled but out of which all things come” (Stace 103). In
other words, it is the source of everything. The word void seems paradoxical, however. If it is a
void how can anything come of it? Suzuki, renowned Zen Buddhist scholar, offers an
explanation. “The void,” he says, “is a reservoir of infinite possibilities and not just mere
emptiness. Differentiating itself and yet remaining itself undifferentiated…we may say that it is a
creation out of nothing” (Stace103). The paradox is not an uncommon one. Rather, it seems to be
a universally perplexing to all metaphysicians who grapple with first causes and how something
comes out of nothing. The Tao Ching, however, seems to describe a method for achieving
enlightenment in poem no. 48:
“Touch ultimate emptiness, Hold steady and still. All things work together: I have
watched them reverting, And have seen how they flourish And return again, each to his
roots. This, I say, is the stillness: A retreat to one's roots; Or better yet, return To the will
of God, Which is, I say, to constancy. The knowledge of constancy call enlightenment
and say That not to know it Is blindness that works evil. But when you know What
eternally is so, You have stature. And stature means righteousness. And righteousness is
kingly And kingliness divine And divinity is the Way Which is final. Then, though you
die, You shall not perish” (Blakney 53-101).
Touching ultimate emptiness can be viewed as transcending duality, where multiplicity is nonexistent. The turning to the roots seems to be a method for getting there and recalls the prisoner
of Plato’s Allegory of the Cave turning in the direction of the light. It also seems clear that it is a
reference to essence or being. Knowing what is “eternally so” which is equated with
righteousness and kingliness leads to not perishing, but smacks of immortality--a belief espoused
in the dialogues.
Although it can be argued that Dionysius disseminated many of the ideas regarding mystical
experiences, the same can be said of Hinduism and Buddhism, though the experience is usually
referred to as Enlightenment. Indeed, the sense in which mysticism is understood today stems
from them.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
400
The Hindu tradition is rich with mystical experiences. In fact, according to W.T. Stace, the
mysticism reflected in the Upanishads is remarkably similar to the more contemporary mysticism
of Sri Aurobindo, despite the fact that they are separated by a three thousand year span. Stace
argues that this is not surprising given that “mystical consciousness is the same in all ages”( 49).
Most of what we know about Hindu mysticism comes from the Upanishads. The Upanishads are
said to be the work of anonymous Indian forest dwellers who lived between three thousand and
twenty-five hundred years ago (20). “They are among the oldest records of mysticism in the
world” and are comprised of multiple texts like the Mandukya Brihadaranyaka, Jaiminiya and
Aitareya, to name a few. From the Mandukya we get the following description of the mystical
experience: “It is beyond the senses, beyond the unitary consciousnesses, wherein awareness of
the world and of multiplicity is completely obliterated” ( 20). Likewise, from the Upanishads
there is another passage which describes the value of self reflection: “The self, Maittreyi, is to be
known. Hear about it, reflect upon it, and meditate upon it. By knowing the self, my beloved,
through hearing, reflection, and meditation, one comes to know all things” (Manchester 68-69).
In these two passages, we find the familiar down playing of the senses and multiplicity. But there
is also the urging of self-reflection and meditation, which leads one to know all things. Could
there be a connection between self-reflection and enlightenment? There clearly is. The self seems
to be the doorway to uncovering the truth. It is the lens through which the world is viewed or
perceived. We will explore the idea of self later.
Sri Aurobindo, as mentioned earlier, is a more contemporary Hindu mystic, born in India in 1872
and educated at Cambridge, England. He later became a professor of English literature. Although
his writings appear to be influenced by the Upanishads, they were not reproductions of the
ancient texts (Stace 49). Stace cautions against this and argues that Hindu mystics are by nature
spiritually inclined, not “copyist.” Sri Aurobindo wrote many books, but his mystical writings
are captured in “The Life of the Devine,” in which he writes about a mystical experience:
“At the gates of the Transcendent stands that mere and perfect spirit described in the
Upanishads, luminous, pure sustaining the world..., without flaw of duality, without scar
of division, unique, identical, free from all appearance of relation and multiplicity, the
pure Self...the inactive Brahman, the transcendent Silence. And the mind when it passes
those gates suddenly...receives a sense of the unreality of the world and the sole reality of
the Silence which is one of the most powerful and convincing experiences of which the
human mind is capable” (Aurobindo 1-6).
The phrase “free from all appearance of relation and multiplicity” seems to reference a reality
beyond appearance (sense-perception) which is the “sole reality of the silence.” This sounds like
a unifying experience but is characterized as silence. The ineffable quality recalls Dionysius’
description of the ineffable quality of God; in this sense, it is so transcendent as to be silent.
“Pure self” suggests an awareness without an object or a self that does not say “I.” Saying “I”
introduces dualism or multiplicity. In other words, it creates the subject-to-object relationship.
Awareness without identification with I is “pure self.” The discovery of the “pure self,” as the
most profound experience a human mind can experience, is a common sentiment among mystics.
There is no doubt that the experience is life-altering.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
401
With regard to Buddhism, when recounting the story of the Buddha, there is the obligatory
disclaimer: Little is known about him. Much of what we do know is from second-hand sources.
His name was Siddhartha Gautama, (one who has achieved his goal). He was an Indian prince
born circa 550 B.C.E. and as the story goes he lived a sheltered life behind the walls of his
father’s palace wanting for nothing. The main reason he was sheltered was due to a prophecy
that one day he would either become a great king or a great holy man. Wanting an heir, his father
did everything in his power to ensure his son would be king including preventing him from
leaving the palace walls. He was determined to do anything to prevent his arousal to the holy
life. However, Siddhartha felt a stirring within and wanted to see what lay beyond the walls. His
father reluctantly agreed and allowed him to leave. While outside the walls, he encountered an
“old man, a diseased man, and a decaying corpse” and was puzzled. His charioteer, Channa,
explained to him that everyone will grow old one day, get sick and die. Profoundly moved by the
suffering and misery, he abandoned his sheltered life including his beautiful wife and child, to
join a monastic sect in hopes that they would provide answers on how to end suffering. India at
the time had monastic schools or sects that taught their own methods to achieve enlightenment.
Siddhartha practiced with most of them and even became adept at various meditative and
extreme ascetic practices but failed to reach his goal of finding a solution for ending suffering.
Disillusioned with the schools and what he had learned up to that point, he resolved to sit under a
bodhi tree: come rain or shine, or death, he would remain there until he achieved enlightenment.
On the seventh day, so the legend goes, he reached enlightenment. Thereafter he was known as
the Buddha or the “awakened” (Laumakis 12). To what did he awaken? Scholars have often
debated about what awakening really means. But the general consensus seems to be (even
though there is no direct description from the Buddha himself), that he achieved an “ineffable
transcendental state” or “experience of direct and intuitive understanding of the ultimate nature
of phenomena” (Stace 68). His ideas are captured in the Pali Canon (Laumakis 47). They were
written 100 years after his death and are considered the oldest records reflecting what the
Buddha actually taught.
The following passage is a quote often cited and found in the Pali Canon:
“There is, monks, that plane where there is neither extension, nor motion, nor the plane of
infinite ether.... nor that of neither-perception-nor-non-perception, neither this world nor
another, neither the moon nor the sun. Here, monks, I say that there is no coming or
going or remaining or deceasing or uprising, for this is itself without support, without
continuance in samsara, without mental object - this is itself the end of suffering.
There is, monks, an unborn, not become, unmade, uncompounded, and were it not,
monks, for this unborn, not become, not made, uncompounded, no escape could be
shown here for what is born, has become, is made, is compounded. But because there is,
monks, an unborn, not become, unmade, uncompounded, therefore an escape can be
shown, for what is born, has become, is made, is compounded” (Conze 94-95).
This passage is admittedly confusing. The Buddha seems to suggest, however, that there is a
plane wherein it is possible by means of arriving at a state of “non-perception…without mental
object” -- to result in ending suffering. Cognitively this appears to imply a blurring of subject-toobject relationship- a unifying or dissolving into a one. This explains paradoxical statements like
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
402
“neither-perception-nor-non-perception or neither this world nor another.” In a state of unity
nothing can be said about it or else the said thing renders it no longer a one. The ineffable quality
is part and parcel of a sense of oneness.
As an aside, the peculiar thing about Buddha, unlike other mystics we have seen, is that he
repudiated any idea of a supreme being, self or soul. The reason for this seems to be that because
his sole aim was to end suffering, he did not concern himself with issues like first causes or a
supreme being. In a sense, he was a pragmatist and cared only about the matter at hand and not
what could not be proven. The notion of self, or soul, is a bit confusing. On the one hand, he
believed there was no I or self that persisted through time, yet he believed in reincarnation. The
only way of getting around this paradox is if we consider that what he intended was to end
immortality by achieving nirvana (a blowing out) which extinguishes self. That way, self
disappears. In this light, it can be understood what he meant by “no I.” The issue then appears to
be a matter of semantics.
When it comes to demonstrating that all mystical experiences are similar, I defer to W.T. Stace’s
analysis, which acknowledges differences in mystical experiences reported by different cultures,
or different ages, but nevertheless sees a number of common characteristics (14). He believes, as
do I, the differences are very superficial. However, the chief feature which he argues is common
to all mystical experiences involves an “apprehension of an ultimate nonsensuous unity in all
things, a oneness, a one to which neither sense nor reason can penetrate.” He characterizes
experiences that lack this central feature as borderline experiences (14).
Moreover, according to the W. T. Stace, these experiences can further be divided into seven
features: (1) a unifying vision and perception of the One; (2) the apprehension of the One as an
inner life; (3) and an objective and true sense of reality; (4) feelings of satisfaction, joy, and
bliss; (5) a religious element that is a feeling of the holy and sacred; (6) a paradoxical feeling;
and (7) and inexpressible feelings. (131).
Stace also divides the experiences into two categories: introversion mysticism, meaning an
experience characterized as absolute undifferentiated and distinctive changeless unity, in which
all multiplicity has been obliterated (35), and extroversion mysticism, an experience that
involves making use of sense-perception and coming to see objects in nature “transfigured in
such a manner that the unity shines through them” (15). The distinction is that the former
experience entails going inward to have a mystical experience whereas the latter involves one
looking outward. Stace believes the extroversion to be inferior to the introversion experience.
The introversion is the full experience.
Stace associated introversion mystics with Christian mystics (i.e., Eckhart and Ruysbroeck) and
almost all Hindu and Buddhist mystics. He believes the experiences are “wholly unknown to,
and independent of one another” (Stace 36). In other words, they are universal experiences that
occur in all cultures and have been occurring from time immemorial. This, incidentally, adds
more credibility to my thesis that Plato was also a mystic. One need only look for some of the
features common to the experience to uncover the truth of this fact.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
403
However, much of the criticism of mysticism is that it is seen as a purely subjective experience
that can tell us little about the outside world. Although the mystics have given us descriptions of
their mystical experiences, the nature of the experience makes it inherently at odds with
language, as language is made of conceptualizations. As we have seen, the tendency of mystics is
to refer to the experience as ineffable. This presents a problem: “to say that X is ineffable is to
say something about X, which contravenes ineffability” (Plantinga 23-25). Whether the
experience is described as ineffable, silence or God, it appears to be only a matter of semantics.
Mystical descriptions are often confusing and paradoxical. Frequently myths and metaphors are
often used to explain the experience. Barker illustrates the function of myths or metaphors in the
following passage:
“Perhaps, the, myths are neither true nor false, but distanced from reality by being images
of what is real and what is true. They are, that is, fashioned to suit the inadequacies of
belief, the state of mind of people enmeshed in the sensible world, susceptible to the
persuasive words of poets and orators, who observe what is likely at the expense of what
is true” (Barker 48).
In other words, myths are designed to appeal to mindsets that are of the lower rung of cognitive
perception. The truth is framed in images to make it more amenable or understandable. However,
if the mystical experience could be reduced to only few chief features that characterized the
experience the best, I would propose just two: 1) a sense of unity, which transcends senseperception and reason, and 2) a powerful and life-altering experience.
Let us conclude, then, what enlightenment is. It is a unifying experience in which the mystic has
pure awareness and is free of content or subject-object relationships. The pure consciousness is
so pure there is no other content other than itself. And since it has no content, it is described as
ineffable, as a one, God or emptiness. To use an analogy to help illustrate the point, picture an
eyeball staring into a mirror. In gazing at the mirror, the eye will see an image of itself. Now let
us suppose that the eye decides it wants to see itself. How will it do this? We know the image in
the mirror is just a reflection and not the eye itself. Can the eye turn around and see itself? It is
obvious it cannot. The first step in the eye wanting to see itself is the realization that the image in
the mirror is a reflection (image) and not the eye. The eye will then become self-aware. In other
words, its gaze will no longer be directed toward the image but inwardly at itself. This is
analogous to a subject-to-object merging. What is occurring, without the metaphor, is that the
self is reflecting on itself. The self, which usually maintains a self-conceptualization (equated
with the image in the mirror), no longer identifies itself with it but rests in pure awareness.
Another analogy would be to imagine a screen and projector. The images projected onto the
screen are analogous to the mirror and the screen to the eye (or self). Identifying with screen and
not projections is another analogy for subject-to-object merging. It is important to note that this
process always involves a turn inward. This is evident in Socrates’ call to "Know thyself!"
(Charmides 164d-165a). Self- inquiry, therefore, into the nature of self is part and parcel of any
sincere request for what is real.
To begin the process of drawing parallels with what has already been said about enlightenment
and Plato’s Republic, let us begin by making some preliminary points.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
404
I argue that the dialogues of the Republic demonstrate precisely how to achieve enlightenment.
Its aim, I believe, is to direct the soul nearer to the truth. This involves a progression up the steps
of cognitive perceptions of image, belief, and understanding to ultimate reality, or the Good. I
contend that the process of education, which the Republic is supposedly about, is a way of
preparing the conditions to achieve enlightenment--a converting of the tripartite soul from many
into one. Part of the long discourse on justice and how it relates to the tripartite theory of the
soul, and the state, is meant to show how the soul of many becomes the one. Or, as Dorter
suggests, “the narrative displays a progressive ascent through opposition in the direction of
greater inclusiveness, which is perhaps intended as a literary image of the noetic
dialectic”(Dorter 4). Noetic (Greek- meaning insight) means intuitive understanding which
suggests a deeper cognitive perception. In the noetic sense, the dialectic as Doeter refers to it, is
the means by which the soul can rise to level of the Good. Moreover, the Cave and Divided Line,
I believe, are a more focused and discursive attempt at explaining what enlightenment is. Plato
does this by showing the cognitive progression from ordinary consciousness to enlightenment.
For instance, the categories of the Divided Line such as image, belief, understanding and
knowledge are the stages in the development of enlightenment. Knowledge then corresponds to
the merging of subject-to-object.
Plato’s Rules
When reading the dialogues, Plato follows a few rules, which are good to keep in mind. These, I
suggest, will be clues in support of my thesis that Plato’s sole aim is to bring the soul nearer to
the truth or enlightenment (which is a unifying experience), and that Plato himself is a mystic.
The first rule: He never refers to the visible world or world of sense-perception, except through
metaphor; his only concern is the Good and the noetic thought (mathematical thinking) that
impels the thinker (soul) to view the Good itself. Second, he never refers to a multiplicity of
parts, only the whole or pure oneness. It is also important to note that the Books of the Republic
are written in dialogue form in which Socrates and at least one other person are engaged in a
fictitious conversation. Essentially, Plato uses Socrates as his mouthpiece to espouse his own
ideas.
In all the ensuing dialogues where Socrates is seen as constantly refuting ideas put forward by
his interlocutors, who demonstrate multiple points of view (world of opinion or belief), Socrates
always looks for a unity, a oneness. This is referred to as the elenchus (dialectic), which is a form
of cross-examination where a statement is made and series of questions are then asked about the
statement and an effort is made to determine if the statement is true. After the cross-examination,
however, the original statement turns out to be false. Another series of questions are then asked
to probe the inconsistencies or wrong assumptions of the original statement until the truth is
made self-evident. In this respect, Socrates seemed to be a walking refutation. His certainty of
the refutation gives the feeling that he was privy to knowledge that others were unaware of.
However, his position was always “I know that I know nothing” (Apology 21d). This is
demonstrated in a passage in the Charmides:
“You treat me as if I professed to know the matters I ask about, and as if I might agree
with you if I wished to. But that is not so. On the contrary, I inquire into the proposition
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
405
along with you because I do not know. I will tell you whether I agree or not when I have
examined it” (165B).
This is a method used by Plato (through the character of Socrates) mainly throughout Book I.
More broadly, the dialectic is used to refer to thinking directed away from thoughts derived from
sense-perception to the truth. I want to suggest here that Plato’s’ method, which has the uncanny
ability of arriving at the truth, is symptomatic of a mystical consciousness. It is a mindset that
draws everything into a oneness. However, to prove this will require another thesis. The
difficulty will lie in cross-examining the writings of other mystics in an effort to detect a drawing
of everything into oneness. The difficulty will be compounded when sorting through the diverse
ways of articulating the mystical experience and then attempting to find a common thread. So let
us continue with our present course.
I have already given a brief overview of mystical experiences. Reference to these accounts will
show how closely these experiences correspond to Plato’s Divided Line analogy or Allegory of
the Cave in terms of the cognitive progressions through images, belief, understanding and
knowledge. However, some discussion will be required here to frame the context in which the
Divided Line and Cave are used. Therefore, I will discuss the books in the Republic that precede
these analogies and attempt to illustrate the points mentioned previously. What should be noted,
however, in the discussion of the dialogues, is Plato’s constant interest in the whole and not
parts. This is an important key in understanding the mystical nature of his writings. The reason
for this, as we shall see, is because parts belong to lower cognitive levels--the realm of the
opinion and multiplicity. Seeing things as a whole or drawing everything into a unity is an
indication of a higher cognitive level. So, with this in mind, let us begin with Book I.
Book I
Book I begins with an imaginary dialogue between Socrates and Cephalus, a rich elderly man.
Socrates asks, “Is life harder toward the end, or what report do you give of it”? (328b) He
explains that relative to other men, “he lives in justice and holiness”(331). A discussion about
what justice is ensues. Cephalus suggests it is to “tell the truth and pay what you owe”(331).
Socrates points out a contradiction in his argument by using an example of giving a weapon
(what is owed) to a madman. “It would prove to be an unjust act, if the mad man decided to use
it to harm others (331c). Cephalus excuses himself before defending his point and his son,
Polemarchus, weighs in and suggests that justice is to help friends and harm enemies (332e333e). Socrates finds inconsistencies that result in finding the just man useless in peacetime and
concluding that justice cannot be used to harm because it is antithetical to the nature of justice.
He makes the point by giving a series of examples. For example, he asks if “the musician by his
art can make men unmusical, to which Polemarchus replies, “Certainly not.” So it follows if “just
is the good,” then… “to injure a friend or any one else is not the act of a just man, but of the
opposite” (334b). This then leads to Thrasymachus’ assertion that “justice is nothing else than
the interest of the stronger” (335-b-d). In other words, “right is might and justice an invention of
the strong, who have been shrewd enough to lay down the rules of the game of life in their own
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
406
interest – for the weaker and less wise to obey” (Urwick 45). Socrates immediately sees a
discrepancy in this argument.
“Socrates: Let me first understand you…justice, as you say, is the interest of the stronger.
What, Thrasymachus, is the meaning of this? You cannot mean to say that because
Polydamas, the pancratiast, is stronger than we are, and finds the eating of beef
conducive to his bodily strength, that to eat beef is therefore equally for our good who are
weaker than he is, and right and just for us?” (338c).
“Thracymachus replies: “That’s abominable of you sir, Socrates, you take the words in
the sense which is most damaging to the argument.”
“Not at all, my good sir, Socrates says; I am trying to understand them; and I wish that
you would be a little clearer” (338c).
The confusion that often arises after Socrates has pointed out inconsistencies in the assertions of
the interlocutor is called aporia (impasse or confusion.) This is part of the pattern of his dialectic
method. For the interlocutor, this was usually unnerving. However, for Socrates it was the point
at which one embarked on a more substantive search for the truth.
Thracymachus clarifies his point by equating the stronger with the government. Socrates then
asks if governments are “liable to err”(339c). Thracymachus answers in the affirmative. Socrates
argues then that because the rulers are fallible and could make laws that are not in their interest,
it follows that rulers do not always act in their own interest. Moreover, he draws a parallel
between practitioners of justice and practitioners of medicine. He argues that practitioners of
medicine consider the interests of the body, not medicine. He concludes, therefore, that justice is
for the benefit of the ruled, not the ruler himself (342-343).
Thrasymachus counters with the shepherd and sheep analogy. The shepherd (equated with the
rulers) who fatten or tend the sheep, are doing it to serve their own interest. Since this creates
conditions where the ruler’s interests are out of sync with the interest of their subjects, the
subjects have no choice but to behave unjustly to pursue their own interest. It is this kind of
“injustice,” he says, “in which the criminal is the happiest of men, and the sufferers or those who
refuse to do injustice are the most miserable …” (344). In other words, the unjust person is
happier than the just one. Being unjust, for Thrasymachus, then becomes virtuous and just, its
opposite.
Socrates addresses what he perceives as a fundamental misuse of the word justice. He does this
by establishing the premise that arts (like justice) are “different, by reason of their each having a
separate function” (352). For example, the purpose of eyes is to see and the function of ears is to
ear, “and although we can prune a vine with any kind of knife we can best do so with a pruning
knife” (Dorter 48; Republic 352-353). However, a thing can only perform its function, according
to Socrates, if it has virtue (or excellence). Blindness is a case in which the virtue of eyes is
lacking. Socrates then argues that the function of the soul is living, and since living poorly does
not equate well with the good or virtuous aspect of the soul, it must be a vice or injustice. The
soul’s virtue is justice, which enables living well (353e). The conclusion is that justice can only
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 391-407
Lundy, A. N., Plato’s Republic as Metaphor for Enlightenment: Part I
407
be said to perform its function, living a good life. Therefore living unjustly is antithetical to the
soul’s virtue.
Eventually Plato gets Thrasymachus to revise his idea and agree that the just are “the wise and
good and the unjust evil and ignorant” (350c). However, later he will insist that Socrates
elaborate further on why this is so. What can we conclude from this? Since Plato is concerned
with the deeper nature of justice (the form), he seems to be purposefully drawing attention to the
more crude conceptions of justice to use them as examples of what not to think. Moreover, he
seems to be laying down the groundwork for a more sophisticated, in depth, inquiry into the
nature of justice.
(References are listed at the end of Part II)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1041
Essay
Fundamental Physics: What Is the Big Picture?
Philip E. Gibbs*
Abstract
In this article, I will give my view on the big picture of fundamental physics in light of the
historical discovery of Higgs boson. Although this discovery completes the standard model,
many mysteries remain. It is not unreasonable to hope that some further experimental input may
provide clues that lead to some new answers. But there is another avenue for progress. While
experiment is limited by the reality of global economics, theory is limited only by our intellect
and imagination. The beasts of mathematical consistency have been harnessed before to pull us
through. We are not limited by just what we can see directly, but there are many routes to
explore.
Key Words: fundamental physics, big picture, discovery of Higgs boson, standard model,
remaining mystery, quantum gravity, string theory, viXra, theist, atheist.
Introduction
Many physicists are reluctant to speculate about the big picture and how they see it developing. I
think it would be useful if they were more willing to stick their neck out, so this is my
contribution. I don’t expect much agreement from anybody, but I hope that it will stimulate some
interesting discussion and thoughts. If you don’t like it you can always write your own
summaries of physics or any other area of science and submit to viXra. 2013 has been a great
year for viXra. We already have more than 2000 new papers taking the total to over 6000. Many
of them are about physics but other areas are also well covered. The range is bigger and better
than ever and could never be summarised, so as the year draws to its end here instead is a
snapshot of my own view of fundamental physics in 2013.
The discovery of the Higgs boson marks a watershed moment for fundamental physics. The
standard model is complete but many mysteries remain. Most notably the following questions are
unanswered and appear to require new physics beyond the standard model:
*
What is dark matter?
What was the mechanism of cosmic inflation?
What mechanism led to the early production of galaxies and structure?
Why does the strong interaction not break CP?
What is the mechanism that led to matter dominating over anti-matter?
What is the correct theory of neutrino mass?
How can we explain fine-tuning of e.g. the Higgs mass and cosmological constant?
Correspondence: Philip E. Gibbs, Ph.D., Independent Researcher, UK. E-Mail: philegibbs@gmail.com Note: This
Editorial is based on http://blog.vixra.org/2013/11/26/fundamental-physics-2013-what-is-the-big-picture/
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1042
How are the four forces and matter unified?
How can gravity be quantised?
How is information loss avoided for black holes?
What is the small scale structure of spacetime?
What is the large scale structure of spacetime?
How should we explain the existence of the universe?
It is not unreasonable to hope that some further experimental input may provide clues that lead to
some new answers. The Large Hadron Collider still has decades of life ahead of it while
astronomical observation is entering a golden age with powerful new telescopes peering deep
into the cosmos. We should expect direct detection of gravitational waves and perhaps dark
matter, or at least indirect clues in the cosmic ray spectrum.
But the time scale for new discoveries is lengthening and the cost is growing. It is might be
unrealistic to imagine the construction of new colliders on larger scales than the LHC. A theist vs
atheist divide increasingly polarises Western politics and science. It has already pushed the
centre of big science out of the United States over to Europe. As the jet stream invariably blows
weather systems across the Atlantic, so too will come their political ideals albeit at a slower pace.
It is no longer sufficient to justify fundamental science as a pursuit of pure knowledge when the
men with the purse strings see it as an attack on their religion. The future of fundamental
experimental science is beginning to shift further East and its future hopes will be found in Asia
along with the economic prosperity that depends on it. The GDP of China is predicted to surpass
that of the US and the EU within 5 years.
But there is another avenue for progress. While experiment is limited by the reality of global
economics, theory is limited only by our intellect and imagination. The beasts of mathematical
consistency have been harnessed before to pull us through. We are not limited by just what we
can see directly, but there are many routes to explore. Without the power of observation the
search may be longer, but the constraints imposed by what we have already seen are tight.
Already we have strings, loops, twistors and more. There are no dead ends. The paths converge
back together taking us along one main highway that will lead eventually to an understanding of
how nature works at its deepest levels. Experiment will be needed to show us what solutions
nature has chosen, but the equations themselves are already signposted. We just have to learn
how to read them and follow their course. I think it will require open minds willing to move
away from the voice of their intuition, but the answer will be built on what has come before.
Thirteen years ago at the turn of the millennium I thought it was a good time to make some
predictions about how theoretical physics would develop. I accept the mainstream views of
physicists but have unique ideas of how the pieces of the jigsaw fit together to form the big
picture. My millennium notes reflected this. Since then much new work has been done and some
of my original ideas have been explored by others, especially permutation symmetry of
spacetime events (event symmetry), the mathematical theory of theories, and multiple
quantisation through category theory. I now have a clearer idea about how I think these pieces fit
in. On the other hand, my idea at the time of a unique discrete and natural structure underlying
physics has collapsed. Naturalness has failed in both theory and experiment and is now replaced
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1043
by a multiverse view which explains the fine-tuning of the laws of the universe. I have adapted
and changed my view in the face of this experimental result. Others have refused to.
Every theorist working on fundamental physics has a set of ideas or principles that guides their
work and each one is different. I do not suppose that I have a gift of insight that allows me to see
possibilities that others miss. It is more likely that the whole thing is a delusion, but perhaps
there are some ideas that could be right. In any case I believe that open speculation is an
important part of theoretical research and even if it is all wrong it may help others to crystallise
their own opposing views more clearly. For me this is just a way to record my current thinking
so that I can look back later and see how it succeeded or changed.
The purpose of this article then is to give my own views on a number of theoretical ideas that
relate to the questions I listed. The style will be pedagogical without detailed analysis, mainly
because such details are not known. I will also be short on references, after all nobody is going to
cite this. Here then are my views.
Causality
Causality has been discussed by philosophers since ancient times and many different types of
causality have been described. In terms of modern physics there are only two types of causality
to worry about. Temporal causality is the idea that effects are due to prior causes, i.e. all
phenomena are caused by things that happened earlier. Ontological causality is about explaining
things in terms of simpler principles. This is also known as reductionism. It does not involve
time and it is completely independent of temporal causality. What I want to talk about here is
temporal causality.
Temporal causality is a very real aspect of nature and it is important in most of science. Good
scientists know that it is important not to confuse correlation with causation. Proper studies of
cause and effect must always use a control to eliminate this easy mistake. Many physicists,
cosmologists and philosophers think that temporal causality is also important when studying the
cosmological origins of the universe. They talk of the evolving cosmos, eternal inflation, or
numerous models of pre-big-bang physics or cyclic cosmologies. All of these ideas are driven by
thinking in terms of temporal causality. In quantum gravity we find Causal Sets and Causal
Dynamical Triangulations, more ideas that try to build in temporal causality at a fundamental
level. All of them are misguided.
The problem is that we already understand that temporal causality is linked firmly to the
thermodynamic arrow of time. This is a feature of the second law of thermodynamics, and
thermodynamics is a statistical theory that emerges at macroscopic scales from the interactions
of many particles. The fundamental laws themselves can be time reversed (along with CP to be
exact). Physical law should not be thought of in terms of a set of initial conditions and dynamical
equations that determine evolution forward in time. It is really a sum over all possible histories
between past and future boundary states. The fundamental laws of physics are time symmetric
and temporal causality is emergent. The origin of time’s arrow can be traced back to the
influence of the big bang singularity where complete symmetry dictated low entropy.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1044
The situation is even more desperate if you are working on quantum gravity or cosmological
origins. In quantum gravity space and time should also be emergent, then the very description of
temporal causality ceases to make sense because there is no time to express it in terms of. In
cosmology we should not think of explaining the universe in terms of what caused the big bang
or what came before. Time itself begins and ends at spacetime singularities.
Symmetry
When I was a student around 1980 symmetry was a big thing in physics. The twentieth century
started with the realisation that spacetime symmetry was the key to understanding gravity. As it
progressed gauge symmetry appeared to eventually explain the other forces. The message was
that if you knew the symmetry group of the universe and its action then you knew everything.
Yang-Mills theory only settled the bosonic sector but with supersymmetry even the fermionic
side would follow, perhaps uniquely.
It was not to last. When superstring theory replaced supergravity the pendulum began its swing
back taking away symmetry as a fundamental principle. It was not that superstring theory did not
use symmetry, it had the old gauge symmetries, supersymmetries, new infinite dimensional
symmetries, dualities, mirror symmetry and more, but there did not seem to be a unifying
symmetry principle from which it could be derived. There was even an argument called Witten’s
Puzzle based on topology change that seemed to rule out a universal symmetry. The spacetime
diffeomorphism group is different for each topology so how could there be a bigger symmetry
independent of the solution?
The campaign against symmetry strengthened as the new millennium began. Now we are told to
regard gauge symmetry as a mere redundancy introduced to make quantum field theory appear
local. Instead we need to embrace a more fundamental formalism based on the amplituhedron
where gauge symmetry has no presence.
While I embrace the progress in understanding that string theory and the new scattering
amplitude breakthroughs are bringing, I do not accept the point of view that symmetry has lost
its role as a fundamental principle. In the 1990s I proposed a solution to Witten’s puzzle that sees
the universal symmetry for spacetime as permutation symmetry of spacetime events. This can be
enlarged to large-N matrix groups to include gauge theories. In this view spacetime is emergent
like the dynamics of a soap bubble formed from intermolecular interaction. The permutation
symmetry of spacetime is also identified with the permutation symmetry of identical particles or
instantons or particle states.
My idea was not widely accepted even when shortly afterwards matrix models for M-theory
were proposed that embodied the principle of event symmetry exactly as I envisioned. Later the
same idea was reinvented in a different form for quantum graphity with permutation symmetry
over points in space for random graph models, but still the fundamental idea is not widely
regarded.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1045
While the amplituhedron removes the usual gauge theory it introduces new dual conformal
symmetries described by Yangian algebras. These are quantum symmetries unseen in the
classical Super-Yang-Mills theory but they combine permutations symmetry over states with
spacetime symmetries in the same way as event-symmetry. In my opinion different dual
descriptions of quantum field theories are just different solutions to a single pregeometric theory
with a huge and pervasive universal symmetry. The different solutions preserve different sectors
of this symmetry. When we see different symmetries in different dual theories we should not
conclude that symmetry is less fundamental. Instead we should look for the greater symmetry
that unifies them.
After moving from permutation symmetry to matrix symmetries I took one further step. I
developed algebraic symmetries in the form of necklace Lie algebras with a stringy feel to them.
These have not yet been connected to the mainstream developments but I suspect that these
symmetries will be what is required to generalise the Yangian symmetries to a string theory
version of the amplituhedron. Time will tell if I am right.
Cosmology
We know so much about cosmology, yet so little. The cosmic horizon limits our view to an
observable universe that seems vast but which may be a tiny part of the whole. The heat of the
big bang draws an opaque veil over the first few hundred thousand years of the universe. Most of
the matter around us is dark and hidden. Yet within the region we see the ΛCDM standard model
accounts well enough for the formation of galaxies and stars. Beyond the horizon we can
reasonably assume that the universe continues the same for many more billions of light years,
and the early big bang back to the first few minutes or even seconds seems to be understood.
Cosmologists are conservative people. Radical changes in thinking such as dark matter, dark
energy, inflation and even the big bang itself were only widely accepted after observation forced
the conclusion, even though evidence built up over decades in some cases. Even now many
happily assume that the universe extends to infinity looking the same as it does around here, that
the big bang is a unique first event in the universe, that space-time has always been roughly
smooth, that the big bang started hot, and that inflation was driven by scalar fields. These are
assumptions that I question, and there may be other assumptions that should be questioned.
These are not radical ideas. They do not contradict any observation, they just contradict the
dogma that too many cosmologist live by.
The theory of cosmic inflation was one of the greatest leaps in imagination that has advanced
cosmology. It solved many mysteries of the early universe at a stroke and Its predictions have
been beautifully confirmed by observations of the background radiation. Yet the mechanism that
drives inflation is not understood.
It is assumed that inflation was driven by a scalar inflaton field. The Higgs field is mostly ruled
out (exotic coupling to gravity not withstanding), but it is easy to imagine that other scalar fields
remain to be found. The problem lies with the smooth exit from the inflationary period. A scalar
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1046
inflaton drives a DeSitter universe. What would coordinate a graceful exit to a nice smooth
universe? Nobody knows.
I think the biggest clue is that the standard cosmological model has a preferred rest frame defined
by commoving galaxies and the cosmic background radiation. It is not perfect on small scales but
over hundreds of millions of light years it appears rigid and clear. What was the origin of this
reference frame? A DeSitter inflationary model does not possess such a frame, yet something
must have co-ordinated its emergence as inflation ended. These ideas simply do not fit together if
the standard view of inflation is correct.
In my opinion this tells us that inflation was not driven by a scalar field at all. The Lorentz
geometry during the inflationary period must have been spontaneously broken by a vector field
with a non-zero component pointing in the time direction. Inflation must have evolved in a
systematic and homogenous way through time while keeping this fields direction constant over
large distances smoothing out any deviations as space expanded. The field may have been a
fundamental gauge vector or a composite condensate of fermions with a non-zero vector
expectation value in the vacuum. Eventually a phase transition ended the symmetry breaking
phase and Lorentz symmetry was restored to the vacuum, leaving a remnant of the broken
symmetry in the matter and radiation that then filled the cosmos.
The required vector field may be one we have not yet found, but some of the required features
are possessed by the massive gauge bosons of the weak interaction. The mass term for a vector
field can provide an instability favouring timelike vector fields because the signature of the
metric reverses sign in the time direction. I am by no means convinced that the standard model
cannot explain inflation in this way, but the mechanism could be complicated to model.
Another great mystery of cosmology is the early formation of galaxies. As ever more powerful
telescopes have penetrated back towards times when the first galaxies were forming,
cosmologists have been surprised to find active galaxies rapidly producing stars, apparently with
supermassive black holes ready-formed at their cores. This contradicts the predictions of the cold
dark matter model according to which the stars and black holes should have formed later and
more slowly.
The conventional theory of structure formation is very Newtonian in outlook. After baryogenesis
the cosmos was full of gas with small density fluctuations left over from inflation. As radiation
decoupled, these anomalies caused the gas and dark matter to gently coalesce under their own
weight into clumps that formed galaxies. This would be fine except for the observation of
supermassive black holes in the early universe. How did they form?
I think that the formation of these black holes was driven by large scale gravitational waves left
over from inflation rather than density fluctuations. As the universe slowed its inflation there
would be parts that slowed a little sooner and other a little later. Such small differences would
have been amplified by the inflation leaving a less than perfectly smooth universe for matter to
form in. As the dark matter followed geodesics through these waves in spacetime it would be
focused just as light waves on the bottom of a swimming pool is focused by surface waves into
intricate light patterns. At the caustics the dark matter would come together as high speed to be
compressed in structures along lines and surfaces. Large black holes would form at the sharpest
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1047
focal points and along strands defined by the caustics. The stars and remaining gas would then
gather around the black holes. Pulled in by their gravitation to form the galaxies. As the universe
expanded the gravitational waves would fade leaving the structure of galactic clusters to mark
where they had been.
The greatest question of cosmology asks how the universe is structured on large scales beyond
the cosmic horizon. We know that dark energy is making the expansion of the universe
accelerate so it will endure for eternity, but we do not know if it extends to infinity across space.
Cosmologists like to assume that space is homogeneous on large scales, partly because it makes
cosmology simpler and partly because homogeneity is consistent with observation within the
observable universe. If this is assumed then the question of whether space is finite or infinite
depends mainly on the local curvature. If the curvature is positive then the universe is finite. If it
is zero or negative the universe is infinite unless it has an unusual topology formed by
tessellating polyhedrons larger than the observable universe. Unfortunately observation fails to
tell us the sign of the curvature. It is near zero but we can’t tell which side of zero it lies.
This then is not a question I can answer but the holographic principle in its strongest form
contradicts a finite universe. An infinite homogeneous universe also requires an explanation of
how the big bang can be coordinated across an infinite volume. This leaves only more complex
solutions in which the universe is not homogeneous. How can we know if we cannot see past the
cosmic horizon? There are many homogeneous models such as the bubble universes of eternal
inflation, but I think that there is too much reliance on temporal causality in that theory and I
discount it. My preference is for a white hole model of the big bang where matter density
decreases slowly with distance from a centre and the big bang singularity itself is local and finite
with an outer universe stretching back further. Because expansion is accelerating we will never
see much outside the universe that is currently visible so we may never know its true shape.
Naturalness
It has long been suggested that the laws of physics are fine-tuned to allow the emergence of
intelligent life. This strange illusion of intelligent design could be explained in atheistic terms if
in some sense many different universes existed with different laws of physics. The observation
that the laws of physics suit us would then be no different in principle from the observation that
our planet suits us.
Despite the elegance of such anthropomorphic reasoning many physicists including myself
resisted it for a long time. Some still resist it. The problem is that the laws of physics show some
signs of being unique according to theories of unification. In 2001 I like many thought that
superstring theory and its overarching M-theory demonstrated this uniqueness quite persuasively.
If there was only one possible unified theory with no free parameters how could an anthropic
principle be viable?
At that time I preferred to think that fine-tuning was an illusion. The universe would settle into
the lowest energy stable vacuum of M-theory and this would describe the laws of physics with
no room for choice. The ability of the universe to support life would then just be the result of
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1048
sufficient complexity. The apparent fine-tuning would be an illusion resulting from the fact that
we see only one form of intelligent life so far. I imagined distant worlds populated by other
forms of intelligence in very different environments from ours based on other solutions to
evolution making use of different chemical combination and physical processes. I scoffed at
science fiction stories where the alien life looked similar to us except for different skin textures
or different numbers of appendages.
My opinion started to change when I learnt that string theory actually has a vast landscape of
vacuum solutions and they can be stabilized to such an extent that we need not be living at the
lowest energy point. This means that the fundamental laws of physics can be unique while
different low energy effective theories can be realized as solutions. Anthropic reasoning was
back on the table.
It is worrying to think that the vacuum is waiting to decay to a lower energy state at any place
and moment. If it did so an expanding sphere of energy would expand at the speed of light
changing the effective laws of physics as it spread out, destroying everything in its path. Many
times in the billions of years and billions of light years of the universe in our past light come,
there must have been neutron stars that collided with immense force and energy. Yet not once
has the vacuum been toppled to bring doom upon us. The reason is that the energies at which the
vacuum state was forged in the big bang are at the Planck scale, many orders of magnitude
beyond anything that can be repeated in even the most violent events of astrophysics. It is the
immense range of scales in physics that creates life and then allows it to survive.
The principle of naturalness was spelt out by ‘t Hooft in the 1980s, except he was too smart to
call it a principle. Instead he called it a “dogma”. The idea was that the mass of a particle or other
physical parameters could only be small if they would be zero given the realisation of some
symmetry. The smallness of fermion masses could thus be explained by chiral symmetry, but the
smallness of the Higgs mass required supersymmetry. For many of us the dogma was finally put
to rest when the Higgs mass was found by the LHC to be unnaturally small without any sign of
the accompanying supersymmetric partners. Fine tuning had always been a feature of particle
physics but with the Higgs it became starkly apparent.
The vacuum would not tend to squander its range of scope for fine-tuning, limited as it is by the
size of the landscape. If there is a cheaper way the typical vacuum will find it so that there is
enough scope left to tune nuclear physics and chemistry for the right components required by
life. Therefore I expect supersymmetry or some similar mechanism to come in at some higher
scale to stabilise the Higgs mass and the cosmological constant. It may be a very long time
indeed before that can be verified.
Now that I have learnt to accept anthropomorphism, the multiverse and fine-tuning I see the
world in a very different way. If nature is fine-tuned for life it is plausible that there is only one
major route to intelligence in the universe. Despite the plethora of new planets being discovered
around distant stars, the Earth appears as a rare jewel among them. Its size and position in the
goldilocks zone around a long lives stable star in a quite part of a well behaved galaxy is not
typical. Even the moon and the outer gas giants seem to play their role in keeping us safe from
natural instabilities. Yet of we were too safe life would have settled quickly into a stable form
that could not evolve to higher functions. Regular cataclysmic events in our history were enough
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1049
to cause mass extinction events without destroying life altogether, allowing it to develop further
and further until higher intelligence emerged. Microbial life may be relatively common on other
worlds but we are exquisitely rare. No sign of alien intelligence drifts across time and space from
distant worlds.
I now think that where life exists it will be based on DNA and cellular structures much like all
life on Earth. It will require water and carbon and to evolve to higher forms it will require all the
commonly available elements each of which has its function in our biology or the biology of the
plants on which we depend. Photosynthesis may be the unique way in which a stable carbon
cycle can complement our need for oxygen. Any intelligent life will be much like us and it will
be rare. This I see as the most significant prediction of fine tuning and the multiverse.
String Theory
String theory was the culmination of twentieth century developments in particles physics leading
to ever more unified theories. By 2000 physicists had what appeared to be a unique mother
theory capable of including all known particle physics in its spectrum. They just had to find the
mechanism that collapsed its higher dimensions down to our familiar 4 dimensional spacetime.
Unfortunately it turned out that there were many such mechanisms and no obvious means to
figure out which one corresponds to our universe. This leaves string theorists in a position unable
to predict anything useful that would confirm their theory. Some people have claimed that this
makes the theory unscientific and that physicists should abandon the idea and look for a better
alternative. Such people are misguided.
String theory is not just a random set of ideas that people tried. It was the end result of exploring
all the logical possibilities for the ways in which particles can work. It is the only solution to the
problem of finding a consistent interaction of matter with gravity in the limit of weak fields on
flat spacetime. I don’t mean merely that it is the only solution anyone could fine, it is the only
solution that can work. If you throw it away and start again you will only return to the same
answer by the same logic.
What people have failed to appreciate is that quantum gravity acts at energy scales well above
those that can be explored in accelerators or even in astronomical observations. Expecting string
theory to explain low energy particle physics was like expecting particle physics to explain
biology. In principle it can, but to derive biochemistry from the standard model you would need
to work out the laws of chemistry and nuclear physics from first principles and then search
through the properties of all the possible chemical compounds until you realised that DNA can
self-replicate. Without input from experiment this is an impossible program to put into practice.
Similarly, we cannot hope to derive the standard model of particle physics from string theory
until we understand the physics that controls the energy scales that separate them. There are
about 12 orders of magnitude in energy scale that separate chemical reactions from the
electroweak scale and 15 orders of magnitude that separate the electroweak scale from the
Planck scale. We have much to learn.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1050
How then can we test string theory? To do so we will need to look beyond particle physics and
find some feature of quantum gravity phenomenology. That is not going to be easy because of
the scales involved. We can’t reach the Planck energy, but sensitive instruments may be able to
probe very small distance scales as small variations of effects over large distances. There is also
some hope that a remnant of the initial big bang remains in the form of low frequency radio or
gravitational waves. But first string theory must predict something to observe at such scales and
this presents another problem.
Despite nearly three decades of intense research, string theorists have not yet found a complete
non-perturbative theory of how string theory works. Without it predictions at the Planck scale are
not in any better shape than predictions at the electroweak scale.
Normally quantised theories explicitly include the symmetries of the classical theories they
quantised. As a theory of quantum gravity, string theory should therefore include
diffeomorphism invariance of spacetime, and it does but not explicitly. If you look at string
theory as a perturbation on a flat spacetime you find gravitons, the quanta of gravitational
interactions. This means that the theory must respect the principles of general relativity in small
deviations from the flat spacetime but it is not explicitly described in a way that makes the
diffeomorphism invariance of general relativity manifest. Why is that?
Part of the answer coming from non-perturbative results in string theory is that the theory allows
the topology of spacetime to change. Diffeomorphisms on different topologies form different
groups so there is no way that we could see diffeomorphism invariance explicitly in the
formulation of the whole theory. The best we could hope would be to find some group that has
every diffeomorphism group as a subgroup and look for invariance under that.
Most string theorists just assume that this argument means that no such symmetry can exist and
that string theory is therefore not based on a principle of universal symmetry. I on the other hand
have proposed that the universal group must contain the full permutation group on spacettime
events. The diffeomorphism group for any topology can then be regarded as a subgroup of this
permutation group.
String theorists don’t like this because they see spacetime as smooth and continuous whereas
permutation symmetry would suggest a discrete spacetime. I don’t think these two ideas are
incompatible. In fact we should see spacetime as something that does not exists at all in the
foundations of string theory. It is emergent. The permutation symmetry on events is really to be
identified with the permutation symmetry that applies to particle states in quantum mechanics. A
smooth picture of spacetime then emerges from the interactions of these particles which in string
theory are the partons of the strings.
This was an idea I formulated twenty years ago, building symmetries that extend the permutation
group first to large-N matrix groups and then to necklace Lie-algebras that describe the creation
of string states. The idea was vindicated when matrix string theory was invented shortly after but
very few people appreciated the connection.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1051
The matric theories vindicated the matrix extensions in my work. Since then I have been waiting
patiently for someone to vindicate the necklace Lie algebra symmetries as well. In recent years
we have seen a new approach to quantum field theory for supersymmetric Yang-Mills which
emphasises a dual conformal symmetry rather than the gauge symmetry. This is a symmetry
found in the quantum scattering amplitudes rather than the classical limit. The symmetry takes
the form of a Yangian symmetry related to the permutations of the states. I find it plausible that
this will turn out to be a remnant of necklace Lie-algebras in the more complete string theory.
There seems to be still some way to go before this new idea expressed in terms of an
amplituhedron is fully worked out but I am optimistic that I will be proven right again, even if
few people recognise it again.
Once this reformulation of string theory is complete we will see string theory in a very different
way. Spacetime, causality and even quantum mechanics may be emergent from the formalism. It
will be non-perturbative and rigorously defined. The web of dualities connecting string theories
and the holographic nature of gravity will be derived exactly from first principles. At least that is
what I hope for. In the non-perturbative picture it should be clearer what happens at high
energies when space-time breaks down. We will understand the true nature of the singularities in
black-holes and the big bang. I cannot promise that these things will be enough to provide
predictions that can be observed in real experiments or cosmological surveys, but it would surely
improve the chances.
Loop Quantum Gravity
If you want to quantised a classical system such as a field theory there are a range of methods
that can be used. You can try a Hamiltonian approach, or a path integral approach for example.
You can change the variables or introduce new ones, or integrate out some degrees of freedom.
Gauge fixing can be handled in various ways as can renormalisation. The answers you get from
these different approaches are not quite guaranteed to be equivalent. There are some choices of
operator ordering that can affect the answer. However, what we usually find in practice is that
there are natural choices imposed by symmetry principles or other requirements of consistency
and the different results you get using different methods are either equivalent or very nearly so, if
they lead to a consistent result at all.
What should this tell us about quantum gravity? Quantising the gravitational field is not so easy.
It is not renormalisable in the same way that other gauge theories are, yet a number of different
methods have produced promising results. Supergravity follows the usual field theory methods
while String theory uses a perturbative generalisation derived from the old S-matrix approach.
Loop Quantum Gravity makes a change of variables and then follows a Hamiltonian recipe.
There are other methods such as Twistor Theory, Non-Commutative Geometry, Dynamical
Triangulations, Group Field Theory, Spin Foams, Higher Spin Theories etc. None has met with
success in all directions but each has its own successes in some directions.
While some of these approaches have always been known to be related, others have been
portrayed as rivals. In particular the subject seems to be divided between methods related to
string theory and methods related to Loop Quantum Gravity. It has always been my expectation
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1052
that the two sides will eventually come together, simply because of the fact that different ways of
quantising the same classical system usually do lead to equivalent results. Superficially strings
and loops seem like related geometric objects, i.e. one dimensional structures in space tracing out
two dimensional world sheets in spacetime.
String Theorists and Loop Qunatum Gravitists alike have scoffed at the suggestion that these are
the same thing. They point out that string pass through each other unlike the loops which form
knot states. String theory also works best in ten dimensions while LQG can only be formulated
in 4. String Theory needs supersymmetry and therefore matter, while LQG tries to construct first
a consistent theory of quantum gravity alone. I see these differences very differently from most
physicists. I observe that when strings pass through each other they can interact and the algebraic
diagrams that represent this are very similar to the Skein relations used to describe the knot
theory of LQG. String theory does indeed use the same mathematics of quantum groups to
describe its dynamics. If LQG has not been found to require supersymmetry or higher
dimensions it may be because the perturbative limit around flat spacetime has not yet been
formulated and that is where the consistency constraints arise. In fact the successes and failures
of the two approaches seem complementary. LQG provides clues about the non-perturbative
background independent picture of spacetime that string theorists need.
Methods from Non-Commutative Geometry have been incorporated into string theory and other
approaches to quantum gravity for more than twenty years and in the last decade we have seen
Twistor Theory applied to string theory. Some people see this convergence as surprising but I
regard it as natural and predictable given the nature of the process of quantisation. Twistors have
now been applied to scattering theory and to supergravity in 4 dimensions in a series of
discoveries that has recently led to the amplituhedron formalism. Although the methods evolved
from observations related to supersymmetry and string theory they seem in some ways more akin
to the nature of LQG. Twistors were originated by Penrose as an improvement on his original
spin-network idea and it is these spin-networks that describe states in LQG.
I think that what has held LQG back is that it separates space and time. This is a natural
consequence of the Hamiltonian method. LQG respects diffeomorphism invariance, unlike string
theory, but it is really only the spatial part of the symmetry that it uses. Spin networks are three
dimensional objects that evolve in time, whereas Twistor Theory tries to extend the network
picture to 4 dimensions. People working on LQG have tended to embrace the distinction between
space and time in their theory and have made it a feature claiming that time is philosophically
different in nature from space. I don’t find that idea appealing at all. The clear lesson of relativity
has always been that they must be treated the same up to a sign.
The amplituhedron makes manifest the dual conformal symmetry to yang mills theory in the
form of an infinite dimensional Yangian symmetry. These algebras are familiar from the theory
of integrable systems where they may were deformed to bring in quantum groups. In fact the
scattering amplitude theory that applies to the planar limit of Yang Mills does not use this
deformation, but here lies the opportunity to united the theory with Loop Quantum Gravity
which does use the deformation.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1053
Of course LQG is a theory of gravity so if it is related to anything it would be supergravity or
sting theory, not Yang Mills. In the most recent developments the scattering amplitude methods
have been extended to supergravity by making use of the observation that gravity can be
regarded as formally the square of Yang-Mills. Progress has thus been made on formulating 4D
supergravity using twistors, but so far without this deformation. A surprise observation is that
supergravity in this picture requires a twistor string theory to make it complete. If the Yangian
deformation could be applied to these strings then they could form knot states just like the loops
in LQG. I cant say if it will pan out that way but I can say that it would make perfect sense if it
did. It would mean that LQG and string theory would finally come together and methods that
have grown out of LQG such as spin foams might be applied to string theory.
The remaining mystery would be why this correspondence worked only in 4 spacetime
dimensions. Both Twistors and LQG use related features of the symmetry of 4 dimensional
spacetime that mean it is not obvious how to generalise to higher dimensions, while string theory
and supergravity have higher forms that work up to 11 dimensions. Twistor theory is related to
conformal field theory is a reduced symmetry from geometry that is 2 dimensions higher. E.g.
the 4 dimensional conformal group is the same as the 6 dimensional spin groups. By a unique
coincidence the 6 dimensional symmetries are isomorphic to unitary or special linear groups over
4 complex variables so these groups have the same representations. In particular the fundamental
4 dimensional representation of the unitary group is the same as the Weyl spinor representation
in six real dimensions. This is where the twistors come from so a twistor is just a Weyl spinor.
Such spinors exist in any even number of dimensions but without the special properties found in
this particular case. It will be interesting to see how the framework extends to higher dimensions
using these structures.
Quantum Mechanics
Physicists often chant that quantum mechanics is not understood. To paraphrase some common
claims: If you think you understand quantum mechanics you are an idiot. If you investigate what
it is about quantum mechanics that is so irksome you find that there are several features that can
be listed as potentially problematical; indeterminacy, non-locality, contextuality, observers,
wave-particle duality and collapse. I am not going to go through these individually; instead I will
just declare myself a quantum idiot if that is what understanding implies. All these features of
quantum mechanics are experimentally verified and there are strong arguments that they cannot
be easily circumvented using hidden variables. If you take a multiverse view there are no
conceptual problems with observers or wavefunction collapse. People only have problems with
these things because they are not what we observe at macroscopic scales and our brains are
programmed to see the world classically. This can be overcome through logic and mathematical
understanding in the same way as the principles of relativity.
I am not alone in thinking that these things are not to be worried about, but there are some other
features of quantum mechanics that I have a more extraordinary view of. Another aspect of
quantum mechanics that gives some cause for concern is its linearity, Theories that are linear are
often usually too simple to be interesting. Everything decouples into modes that act
independently in a simple harmonic way, In quantum mechanics we can in principle diagonalise
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1054
the Hamiltonian to reduce the whole universe to a sum over energy eigenstates. Can everything
we experience by encoded in that one dimensional spectrum?
In quantum field theory this is not a problem, but there we have spacetime as a frame of
reference relative to which we can define a privileged basis for the Hilbert space of states. It is
no longer the energy spectrum that just counts. But what if spacetime is emergent? What then do
we choose our Hilbert basis relative to? The symmetry of the Hilbert space must be broken for
this emergence to work, but linear systems do not break their symmetries. I am not talking about
the classical symmetries of the type that gets broken by the Higgs mechanism. I mean the
quantum symmetries in phase space.
Suppose we accept that string theory describes the underlying laws of physics, even if we don’t
know which vacuum solution the universe selects. Doesn’t string theory also embody the
linearity of quantum mechanics? It does so long as you already accept a background spacetime,
but in string theory the background can be changed by dualities. We don’t know how to describe
the framework in which these dualities are manifest but I think there is reason to suspect that
quantum mechanics is different in that space, and it may not be linear.
The distinction between classical and quantum is not as clear-cut as most physicists like to
believe. In perturbative string theory the Feynman diagrams are given by string worldsheets
which can branch when particles interact. Is this the classical description or the quantum
description? The difference between classical and quantum is that the worldsheets will extremise
their area in the classical solutions but follow any history in the quantum. But then we already
have multi-particle states and interactions in the classical description. This is very different from
quantum field theory.
Stepping back though we might notice that quantum field theory also has some schizophrenic
characteristics. The Dirac equation is treated as classical with non-linear interactions even
though it is a relativistic Schrödinger equation, with quantum features such as spin already builtin. After you second quantise you get a sum over all possible Feynman graphs much like the
quantum path integral sum over field histories, but in this comparison the Feynman diagrams act
as classical configurations. What is this telling us?
My answer is that the first and second quantisation are the first in a sequence of multiple iterated
quantisations. Each iteration generates new symmetries and dimensions. For this to work the
quantised layers must be non-linear just as the interaction between electrons and photons is nonlinear is the so-called first-quantised field theory. The idea of multiple quantisations goes back
many years and did not originate with me, but I have a unique view of its role in string theory
based on my work with necklace lie algebras which can be constructed in an iterated procedure
where one necklace dimension is added at each step.
Physicists working on scattering amplitudes are at last beginning to see that the symmetries in
nature are not just those of the classical world. There are dual-conformal symmetries that are
completed only in the quantum description. These seem to merge with the permutation
symmetries of the particle statistics. The picture is much more complex than the one painted by
the traditional formulations of quantum field theory.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1055
What then is quantisation? When a Fock space is constructed the process is formally like an
exponentiation. In category picture we start to see an origin of what quantisation is because
exponentiation generalises to the process of constructing all functions between sets, or all
functors between categories and so on to higher n-categories. Category theory seems to
encapsulate the natural processes of abstraction in mathematics. This I think is what lies at the
base of quantisation. Variables become functional operators, objects become morphisms.
Quantisation is a particular form of categorification, one we don’t yet understand. Iterating this
process constructs higher categories until the unlimited process itself forms an infinite omegacategory that describes all natural processes in mathematics and in our multiverse.
Are these crazy ideas? ill-formed? Yes, but I am just saying – that is the way I see it.
Black Hole Information
We have seen that quantum gravity can be partially understood by using the constraint that it
needs to make sense in the limit of small perturbations about flat spacetime. This led us to strings
and supersymmetry. There is another domain of thought experiments that can tell us a great deal
about how quantum gravity should work and it concerns what happens when information falls
into a black hole. The train of arguments is well known so I will not repeat them here. The first
conclusion is that the entropy of a black hole is given by its horizon area in Plank units and the
entropy in any other volume is less than the same Bekenstein bound taken from the surrounding
surface. This leads to the holographic principle that everything that can be known about the state
inside the volume can be determined from a state on its surface. To explain how the inside of a
blackhole can be determined from its event horizon or outside we use a black hole
correspondence principle which uses the fact that we cannot observe both the inside and then
outside at a later time. Although the reasoning that leads to these conclusions is long and
unsupported by any observation. It is in my opinion quite robust and is backed up by theoretical
models such as AdS/CFT duality.
There are some further conclusions that I would draw from black hole information that many
physicists might disagree with. If the information in a volume is limited by the surrounding
surface then it means we cannot be living in a closed universe with a finite volume like the
surface of a 4-sphere. If we did you could extend the boundary until it shrank back to zero and
conclude that there is no information in the universe. Some physicists prefer to think that the
Bekenstein bound should be modified on large scales so that this conclusion cannot be drawn but
I think the holographic principle holds perfectly to all scales and the universe must be infinite or
finite with a different topology.
Recently there has been a claim that the holographic principle leads to the conclusion that the
event-horizon must be a firewall through which nothing can pass. This conclusion is based on the
assumption that information inside a black hole is replicated outside through entanglement. If
you drop two particles with fully entangled spin states into a black hole you cannot have another
particle outside that is also entangled to this does not make sense. I think the information is
replicated on the horizon in a different way.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1056
It is my view that the apparent information in the bulk volume field variables must be mostly
redundant and that this implies a large symmetry where the degrees of symmetry match the
degrees of freedom in the fields or strings. Since there are fundamental fermions it must be a
supersymmetry. I call a symmetry of this sort a complete symmetry. We know that when there is
gauge symmetry there are corresponding charges that can be determined on a boundary by
measuring the flux of the gauge field. In my opinion a generalization of this using a complete
symmetry accounts for holography. I don’t think that this complete symmetry is a classical
symmetry. It can only be known properly in a full quantum theory much as dual conformal
gauge symmetry is quantum symmetry.
Some physicists assume that if you could observe Hawking radiation you would be looking at
information coming from the event horizon. It is not often noticed that the radiation is thermal so
if you observe it you cannot determine where it originated from. There is no detail you could
focus on to measure the distance of the source. It makes more sense to me to think of this
radiation as emanating from a backward singularlty inside the blackhole. This means that a black
hole once formed is also a white hole. This may seem odd but it is really just an extension of the
black hole correspondence principle. I also agree with those who say that as black hole shrink
they become indistinguishable from heavy particles that decay by emitting radiation.
Ontology
Every theorist working on fundamental physics needs some background philosophy to guide
their work. They may think that causality and time are fundamental or that they are emergent for
example. They may have the idea that deeper laws of physics are simpler. They may like
reductionist principles or instead prefer a more anthropomorphic world view. Perhaps they think
the laws of physics must be discrete, combinatorical and finite. They may think that reality and
mathematics are the same thing, or that reality is a computer simulation or that it is in the mind
of God. These things affect the theorist’s outlook and influence the kind of theories they look at.
They may be meta-physical and sometimes completely untestable in any real sense, but they are
still important to the way we explore and understand the laws of nature.
In that spirit I have formed my own elaborate ontology as my way of understanding existence
and the way I expect the laws of nature to work out. It is not complete or finished and it is not a
scientific theory in the usual sense, but I find it a useful guide for where to look and what to
expect from scientific theories. Someone else may take a completely different view that appears
contradictory but may ultimately come back to the same physical conclusions. That I think is just
the way philosophy works.
In my ontology it is universality that counts most. I do not assume that the most fundamental
laws of physics should be simple or beautiful or discrete or finite. What really counts is
universality, but that is a difficult concept that requires some explanation.
It is important not to be misled by the way we think. Our mind is a computer running a program
that models space, time and causality in a way that helps us live our lives but that does not mean
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1057
that these things are important in the fundamental laws of physics. Our intuition can easily
mislead our way of thinking. It is hard understand that time and space are interlinked and to
some extent interchangeable but we now know from the theory of relativity that this is the case.
Our minds understand causality and free will, the flow of time and the difference between past
and future but we must not make the mistake of assuming that these things are also important for
understanding the universe. We like determinacy, predictability and reductionism but we can’t
assume that the universe shares our likes. We experience our own consciousness as if it is
something supernatural but perhaps it is no more than a useful feature of our psychology, a trick
to help us think in a way that aids our survival.
Our only real ally is logic. We must consider what is logically possible and accept that most of
what we observe is emergent rather than fundamental. The realm of logical possibilities is vast
and described by the rules of mathematics. Some people call it the Platonic realm and regard it as
a multiverse within its own level of existence, but such thoughts are just mindtricks. They form a
useful analogy to help us picture the mathematical space when really logical possibilities are just
that. They are possibilities stripped of attributes like reality or existence or place.
Philosophers like to argue about whether mathematical concepts are discovered or invented. The
only fair answer is both or neither. If we made contact with alien life tomorrow it is unlikely that
we would find them playing chess. The rules of chess are mathematical but they are a human
invention. On the other hand we can be quite sure that our new alien friends would know how to
use the real numbers if they are at least as advanced as us. They would also probably know about
group theory, complex analysis and prime numbers. These are the universal concepts of
mathematics that are “out there” waiting to be discovered. If we forgot them we would soon
rediscover them in order to solve general problems. Universality is a hard concept to define. It
distinguishes the parts of mathematics that are discovered from those that are merely invented,
but there is no sharp dividing line between the two.
Universal concepts are not necessarily simple to define. The real numbers for example are
notoriously difficult to construct if you start from more basic axiomatic constructs such as set
theory. To do that you have to first define the natural numbers using the cardinality of finite sets
and Peano’s axioms. This is already an elaborate structure and it is just the start. You then extend
to the rationals and then to the reals using something like the Dedekind cut. Not only is the
definition long and complicated, but it is also very non-unique. The aliens may have a different
definition and may not even consider set theory as the right place to start, but it is sure and
certain that they would still possess the real numbers as a fundamental tool with the same
properties as ours. It is the higher level concept that is universal, not the definition.
Another example of universality is the idea of computability. A universal computer is one that is
capable of following any algorithm. To define this carefully we have to pick a particular
mathematical construction of a theoretical computer with unlimited memory space. One
possibility for this is a Turing machine but we can use any typical programming language or any
one of many logical systems such as certain cellular automata. We find that the set of numbers or
integer sequences that they can calculate is always the same. Computability is therefore a
universal idea even though there is no obviously best way to define it.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1058
Universality also appears in complex physical systems where it is linked to emergence. The laws
of fluid dynamics, elasticity and thermodynamics describe the macroscopic behaviour of systems
build form many small elements interacting, but the details of those interactions are not
important. Chaos arises in any nonlinear system of equations at the boundary where simple
behaviour meets complexity. Chaos we find is described by certain numbers that are independent
of how the system is constructed. These examples show how universality is of fundamental
importance in physical systems and motivates the idea that it can be extended to the formation of
the fundamental laws too.
Universality and emergence play a key role in my ontology and they work at different levels.
The most fundamental level is the Platonic realm of mathematics. Remember that the use of the
word realm is just an analogy. You can’t destroy this idea by questioning the realms existence or
whether it is inside our minds. It is just the concept that contains all logically consistent
possibilities. Within this realm there are things that are invented such as the game of chess, or the
text that forms the works or Shakespeare or Gods. But there are also the universal concepts that
any advanced team of mathematicians would discover to solve general problems they invent.
I don’t know precisely how these universal concepts emerge from the platonic realm but I use
two different analogies to think about it. The first is emergence in complex systems that give us
the rules of chaos and thermodynamics. This can be described using statistical physics that leads
to critical systems and scaling phenomena where universal behaviour is found. The same might
apply to to the complex system consisting of the collection of all mathematical concepts. From
this system the laws of physics may emerge as universal behaviour. This analogy is called the
Theory of Theories by me or the Mathematical Universe Hypothesis by another group. However
this statistical physics analogy is not perfect.
Another way to think about what might be happening is in terms of the process of abstraction.
We know that we can multiply some objects in mathematics such as permutations or matrices
and they follow the rules of an abstract structure called a group. Mathematics has other abstract
structures like fields and rings and vector spaces and topologies. These are clearly important
examples of universality, but we can take the idea of abstraction further. Groups, fields, rings etc.
all have a definition of isomorphism and also something equivalent to homomorphism. We can
look at these concepts abstractly using category theory, which is a generalisation of set theory
encompassing these concepts. In category theory we find universal ideas such as natural
transformations that help us understand the lower level abstract structures. This process of
abstraction can be continued giving us higher dimensional n-categories. These structures also
seem to be important in physics.
I think of emergence and abstraction as two facets of the deep concept of universality. It is
something we do not understand fully but it is what explains the laws of physics and the form
they take at the most fundamental level.
What physical structures emerge at this first level? Statistical physics systems are very similar in
structure to quantum mechanics both of which are expressed as a sum over possibilities. In
category theory we also find abstract structures very like quantum mechanics systems including
structures analogous to Feynman diagrams. I think it is therefore reasonable to assume that some
form of quantum physics emerges at this level. However time and unitarity do not. The quantum
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1059
structure is something more abstract like a quantum group. The other physical idea present in this
universal structure is symmetry, but again in an abstract form more general than group theory. It
will include supersymmetry and other extensions of ordinary symmetry. I think it likely that this
is really a system described by a process of multiple quantisation where structures of algebra and
geometry emerge but with multiple dimensions and a single universal symmetry. I need a name
for this structure that emerges from the platonic realm so I will call it the Quantum Realm.
When people reach for what is beyond M-Theory or for an extension of the amplituhedrom they
are looking for this quantum realm. It is something that we are just beginning to touch with
21st century theories.
From this quantum realm another more familiar level of existence emerges. This is a process
analogous to superselection of a particular vacuum. At this level space and time emerge and the
universal symmetry is broken down to the much smaller symmetry. Perhaps a different selection
would provide different numbers of space and time dimensions and different symmetries. The
laws of physics that then emerge are the laws of relativity and particle physics we are familiar
with. This is our universe.
Within our universe there are other processes of emergence which we are more familiar with.
Causality emerges from the laws of statistical physics within our universe with the arrow of time
rooted in the big bang singularity. Causality is therefore much less fundamental than quantum
mechanics and space and time. The familiar structures of the universe also emerge within
including life. Although this places life at the least fundamental level we must not forget the
anthropic influence it has on the selection of our universe from the quantum realm.
Experimental Outlook
Theoretical physics continues to progress in useful directions but to keep it on track more
experimental results are needed. Where will they come from?
In recent decades we have got used to mainly negative results in experimental particle physics, or
at best results that merely confirm theories from 50 years ago. The significance of negative
results is often understated to the extent that the media portray them as failures. This is far from
being the case.
The LHC’s negative results for SUSY and other BSM exotics may be seen as disappointing but
they have led to the conclusion that nature appears fine-tuned at the weak scale. Few theorists
had considered the implications of such a result before, but now they are forced to. Instead of
wasting time on simplified SUSY theories they will turn their efforts to the wider parameter
space or they will look for other alternatives. This is an important step forward.
A big question now is what will be the next accelerator? The ILS or a new LEP would be great
Higgs factories, but it is not clear that they would find enough beyond what we already know.
Given that the Higgs is at a mass that gives it a narrow width I think it would be better to build a
new detector for the LHC that is specialised for seeing diphoton and 4 lepton events with the best
possible energy and angular resolution. The LHC will continue to run for several decades and
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1060
can be upgraded to higher luminosity and even higher energy. This should be taken advantage of
as much as possible.
However, the best advance that would make the LHC more useful would be to change the way it
searches for new physics. It has been too closely designed with specific models in mind and
should have been run to search for generic signatures of particles with the full range of possible
quantum numbers, spin, charge, lepton and baryon number. Even more importantly the detector
collaborations should be openly publishing likelihood numbers for all possible decay channels so
that theorists can then plug in any models they have or will have in the future and test them
against the LHC results. This would massively increase the value of the accelerator and it would
encourage theorists to look for new models and even scan the data for generic signals. The LHC
experimenters have been far too greedy and lazy by keeping the data to themselves and
considering only a small number of models.
There is also a movement to construct a 100 TeV hadron collider. This would be a worthwhile
long term goal and even if it did not find new particles that would be a profound discovery about
the ways of nature. If physicists want to do that they are going to have to learn how to justify the
cost to contributing nations and their tax payers. It is no use talking about just the value of pure
science and some dubiously justified spin-offs. CERN must reinvent itself as a postgraduate
physics university where people learn how to do highly technical research in collaborations that
cross international frontiers. Most will go on to work in industry using the skills they have
developed in technological research or even as technology entrepreneurs. This is the real
economic benefit that big physics brings and if CERN can’t track how that works and promote it
they cannot expect future funding.
With the latest results from the LUX experiments hope of direct detection of dark matter have
faded. Again the negative result is valuable but it may just mean that dark matter does not
interact weakly at all. The search should go on but I think more can be done with theory to model
dark matter and its role in galaxy formation. If we can assume that dark matter started out with
the same temperature as the visible universe then it should be possible to model its evolution as it
settled into galaxies and estimate the mass of the dark matter particle. This would help in
searching for it. Meanwhile the searches for dark matter will continue including other possible
forms such as axions. Astronomical experiments such as AMS-2 may find important evidence
but it is hard to find optimism there. A better prospect exists for observations of the dark age of
the universe using new radio telescopes such as the square kilometre array that could detect
hydrogen gas clouds as they formed the first stars and galaxies.
Neutrino physics is one area that has seen positive results that go beyond the standard model.
This is therefore an important area to keep going. They need to settle the question of whether
neutrinos are Majorana spinors and produce figures for neutrino masses. Observation of
cosmological high energy neutrinos is also an exciting area with the Ice-Cube experiment
proving its value.
Gravitational wave searches have continued to be a disappointment but this is probably due to
over-optimism about the nature of cosmological sources rather than a failure of the theory of
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1041-1061
Gibbs, P. E., Fundamental Physics: What Is the Big Picture?
1061
gravitational waves themselves. The new run with Advanced LIGO must find them otherwise the
field will be in trouble. The next step would be LISA or a similar detector in space.
Precision measurements are another area that could bring results. Measurements of the electron
dipole moment can be further improved and there must be other similar opportunities for
inventive experimentalists. If a clear anomaly is found it could set the scale for new physics and
justify the next generation of accelerators.
There are other experiments that could yield positive results such as cosmic ray observatories
and low frequency radio antennae that might find an echo from the big bang beyond the veil of
the primordial plasma. But if I had to nominate one area for new effort it would have to be the
search for proton decay. So far results have been negative pushing the proton lifetime to at least
1034 years but this has helped eliminate the simplest GUT models that predicted a shorter
lifetime. SUSY models predict lifetimes of over 1036 years but this can be reached if we are
willing to set up a detector around a huge volume of clear Antarctic ice. Ice-Cube has
demonstrated the technology but for proton decay a finer array of light detectors is needed to
catch the lower energy radiation from proton decay. If decays were detected they would give us
positive information about physics at the GUT scale. This is something of enormous importance
and its priority must be raised.
Apart from these experiments we must rely on the advance of precision technology and the
inventiveness of the experimental physicist. Ideas such as the holometer may have little hope of
success but each negative result tells us something and if someone gets lucky a new flood of
experimental data will nourish our theories, There is much that we can still learn.
Reference
1. http://blog.vixra.org/2013/11/26/fundamental-physics-2013-what-is-the-big-picture/
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com |
483
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
Article
A New Approach to the Hard Problem of Consciousness:
A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
Klee Irwin*
Quantum Gravity Research, California, USA
Abstract
The hard problem of consciousness must be approached through the ontological lens of 20th
century physics, which tells us that reality is information theoretic [1,2] and quantized at the
level of Planck scale spacetime[3]. Through careful deduction, it becomes clear that information
cannot exist without consciousness – the awareness of things. And to be aware is to hold the
meaning of relationships of objects within consciousness – perceiving abstract objects, while
enjoying degrees of freedom within the structuring of those relationships. This defines
consciousness as language – (1) a set of objects and (2) an ordering scheme with (3) degrees of
freedom used for (4) expressing meaning. And since even information at the Planck scale cannot
exist without consciousness, we propose an entity called a “primitive unit of consciousness”,
which acts as a mathematical operator in a quantized spacetime language. Quasicrystal
mathematics based on E8 geometry [4] seems to be a candidate for the language of reality,
possessing several qualities corresponding to recent physical discoveries and various physically
realistic unification models.
Part I of this two-part article includes: Introduction; 1. What Does Scientific Observation Tell Us
about the Nature of Reality? and first portion of 2. The Quantum Gravity Research Group
Approach.
Key Words: quasicrystal, primitive unit, consciousness, quantized spacetime, Planck scale, hard
problem, E8 geometry, quasicrystalline language.
Introduction
There is much confusion among scientists regarding the idea that consciousness interacts with
microscopic physical reality. Without deep subject matter expertise, many good scientists
presume the idea of consciousness to be within the realm of philosophy and neuroscience.
Indeed it is, but it is more fundamentally within the realm of Planck scale quantum gravity
theory – specifically a microscopic first principles theory of everything. So to break the ice, we
being this document with some comments by some of the titans of physics:
Consciousness cannot be accounted for in physical terms. For consciousness is absolutely
fundamental. — Erwin Schrödinger
*
Correspondence: Klee Irvin, Quantum Gravity Research, California, USA. Email: Klee@QuantumGravityResearch.org
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
484
The stuff of the world is mind-stuff. — Arthur Eddington
We do not find obvious evidence of life or mind in so-called inert matter…; but if the scientific
point of view is correct, we shall ultimately find them, at least in rudimentary form, all through
the universe. — J. B. S. Haldane
Mind or something of the nature as mind must exist throughout the entire universe. This is, I
believe, the truth. — Julian Huxley
The laws of physics leave a place for mind in the description of every molecule… In other words,
mind is already inherent in every electron, and the processes of human consciousness differ only
in degree and not in kind. — Freeman Dyson
That which we experience as mind… will in a natural way ultimately reach the level of the
wavefunction and of the 'dance' of the particles. There is no unbridgeable gap or barrier
between any of these levels… It is implied that, in some sense, a rudimentary consciousness is
present even at the level of particle physics. — David Bohm
How physical processes create a subjective sense of experience, or “consciousness”, is unknown.
David Chalmers calls this “the hard problem” [5]. The definition and even existence of
consciousness is debated. The problem has been grappled with primarily by philosophers,
neuroscientists and psychologists with little success over the last few decades [6-9]. We believe
the hard problem may be a false question.
Many scholarly works have been published suggesting that fundamental physics related to
quantum mechanics (QM) may play a role [towards solving the hard problem] [10-15].
However, little progress has been made, possibly due to the fact that mankind has not yet
discovered a “microscopic first principles” theory of everything (TOE). QM and general
relativity are not theories of everything. And there is no first principles TOE, i.e., a model with
no plugged physical constants. The belief system and culture of pre-QM era institutional science
is deeply embedded into our society, especially in the hard sciences. And one of the memes of
this system is that consciousness is a phenomenon restricted to brains made of atoms.
Unfortunately, this bias blocks serious academic work on ontological questions regarding
foundational physics. Ontology, the inquiry into what reality is, seems to be the logical starting
point for both the hard problem of consciousness and a first principles TOE. We propose a
rigorous deductive approach to help scientists to think more critically about the most
fundamental questions of reality.
1. What Does Scientific Observation Tell Us About the Nature of Reality?
1.1 Physical Reality Is Information
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
485
Einstein’s theories indicate that matter is a form of bound up energy. Pre-QM era physics
suggests energy is the potential for work. A potentiality, like a tendency, is informational. If all
particles are a form of energy, and if we consider a frozen moment of reality (a “mosaic” of
some unknown Planck length objects), then everything is the potential (information) for work
because in each frozen Plank time moment, no work (change) is occurring. But what is “work”
at this microscopic foundation of reality? We can discuss this using the related terms “force”
and “energy”. Of course, energy is the potential for work. And work for a fundamental particle
is merely a change to its direction or rate of movement under a force, a form of influence causing
this change. The reader may notice that this is circular and convoluted because we know there is
an equivalency between mass and energy – and by extension matter. For purposes of making
this point more clear, we shall again refer to matter as “a form of bound up energy” and rephrase
the definition of “energy” thusly: Energy is the potential for a change in the direction or speed
of a particle, i.e., a “bound up quantity of energy”.
Reduced further: Energy is the potential for a velocity of a of a quantity of bound up energy.
The circular nature of this unpacking of high school level classical definitions is a helpful way to
realize that, fundamentally, reality is made of information not some absolute stuff that we label
as mass or energy or even spacetime. The importance of belaboring this point is that realizing
that reality is made of information requires us to conjecture what mind is perceiving the
information, since all information is the stuff of mind.
Quantum mechanics speaks to the energy/mass = information idea in two different ways: First, it
tells us that fundamental particles do not undergo continuous smooth movement from one
location to the next. In fact, it tells us that motion itself does not exist. Instead, reality is a
sequence of frozen frames, where a particle is here and then there, with no motion in between –
like flashing one hundred sequential still photographs on a computer monitor to create the
illusion of motion. Within each frozen frame there is no change or motion, there is only a
change between two or more frames observed by the observer. There is no work occurring in the
classic idea of what work is. It is pure information. Second, the most popular interpretation of
quantum mechanics, the Copenhagen interpretation, teaches us a bold new ontology that is
disturbing to some who have thought deeply about it.
Until a conscious entity
measures/observes a particle, it does not exist in the same notion of reality that our common
sense indicates we live in. It requires us to question the very nature of reality. It is important to
understand that this idea of an unmeasured particle having no position is not merely a result of
our lack of knowledge of where the particle is. Instead, the particle exists in an informational
realm called a possibility space, where it literally has no location.
Because of the cultural remnants of old Newtonian thinking, it is troubling for some scientists to
admit that everything is made of information. The idea that there is some absolute “stuff” of
matter or energy beyond the logical and elegant notion of pure information may come from a
pre-scientific era story – a story of an atom or little absolute chunk of something created by a god
from outside the universe. This religious idea is engrained into Western thinking, including
much of academic scientific discourse, where it has morphed into a false distinction (definition)
and two nonsensical words: “materialism” and “idealism” (the later means reality is made of
information – the stuff of mind). The two words are used to distinguish between people who
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
486
think that only physical stuff exists versus those who think reality exists within some sort of
“cosmic mind space” as pure information. Materialists, though, are unable to say what energy is
if not information. And, as far as we have found, no materialist can articulate exactly what they
mean by “absolute stuff other than information”.
Interestingly, most professed materialists
have not actually thought about this question rigorously and are only vaguely aware that they
believe in some sort of little chunks of absolute stuff or some non-informational substance called
energy. Indeed, they are usually unaware of the fact that they cannot define energy beyond being
information. We should also be clear that everything is a story – a theory. We are not suggesting
that the story of absolute stuff beyond information is wrong simply because it is known to have
an origin that can be traced back to religious stories, such as a god from outside the universe
creating the universe out of some form of “stuff”. In fact, there are also spiritual type ontologies
from ancient Eastern stories that have great similarity to our model. The key is to update our
stories to best fit the latest scientific measurements of reality. And all indications are that reality
is “information theoretic”.
Again, QM is very much an ontological theory because it posits (in the widely adopted
Copenhagen interpretation) that reality is made of two primary things; (1) abstract waves of
possibility, where particles do not exist in our common sense notion of reality until we
observe/measure them and (2) the controversial idea of “particle”, where some theorists say it is
made of abstract information and others say it is some absolute non-informational thing. John
Wheeler, in his “It from Bit” ontology [16], was one of the first titans of physics to posit that
reality is made of information. 21st century physicists who argue that reality is made of
information include, MIT’s Max Tegmark. He points out that everything we observe about
reality indicates it is made of information [17-18], specifically mathematics, and that to speculate
on some other absolute stuff beyond information is forced and unnecessary, especially since
there is no competing scientific definition of reality (energy) being something other than
information in the first place.
Combining the idea that (1) the universe is made of mathematical information and (2) the idea
that reality is composed of “pixels” of change (time) and length (space), leads us to the notion
that at the smallest scale fabric of reality, there is an algorithm at play – one that must involve
some primitive “conscious operator” to actualize possible information into observed and
“physical” information.
1.2 Information Is a Product of Consciousness and Consciousness Indicates Freewill
To support the statement, “information is a product of consciousness”, we must first unpack
rudimentary definitions of “information” and “consciousness”. The simplest definition of
“consciousness” is to be aware of something. Awareness, even of self, comes about through
observation, i.e., measurement.
So, awareness via observation is the defining action and quality of consciousness. Similarly,
“information”, i.e., meaning, which is always subjective, is both a product of the observation and
a defining quality of consciousness. In other words, the state of being aware of something is
itself information or meaning. And to be aware is to be conscious. At this foundational level,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
487
the terms “information”, “awareness/consciousness” and “observation/measurement” congeal
into an equivalency, where each word must be defined using the others. One can then generally
state that information is perceived relationships between aspects of consciousness itself.
Here is an analogy to put this generalization into more concrete terms: A conscious mind can
dream of itself as a child walking around an apple tree. Each new vantage point of the child
transforms (from her perspective) the 3D tree into a new 2D image. The tree, the child and the
2D transformations of the tree are all three made of both information and the consciousness of
the dreamer – two terms that merge meanings upon close inspection. In this analogy, the tree is a
“base object” that the mind creates and remains unchanged in 3D but transformed by the child in
the 2D view. The 2D transformations created by the dream-child can be organized into a stream
that behaves like time. And there can be matching rules, with degrees of freedom, so that each
2D picture relates to others like letters in a language.
Even though the child, the tree and the 2D transformations are all information or objects of
awareness within the mind of the dreamer, they are also different types of information. The 3D
tree is a base object created in the mind that doesn’t change. Its purpose is to be stable and
receive observations so that a meaningful sequence of snapshots of observation by the treecircling child can occur. The child is a vantage point of the dreamer. The dreamer may also give
her “freewill”, where the child can behave autonomously – to surprise and teach the dreamer.
Whether the freewill exists only within the subconscious mind of the dreamer or just the dream
child is a false question since even if the child’s freewill is “real”, she and her freedom exist
within the mind of the dreamer. In this case, it is ultimately the dreamer’s freewill – as though
the child is the dreamer filtering herself through a pattern of “blind” spots” or “holes” in a larger
network of awareness in order to create more interesting self-interactions with other filtered
“sub-consciousnesses” of itself. In this ontology, the child of our analogy is very unique with
her own self-identity from the dreamer and any other filtered “sub-consciousness” of the
dreamer, even though she is made of the dreamer’s foundational consciousness and freewill.
And finally, there is the product of the base object (tree) and the vantage points of the dreamer
(the little girl) – able to be combined into language, i.e., order with degrees of freedom in how to
arrange the 2D transformations of the tree. We propose that these three informational elements
of mind/awareness are foundational to both human psychology and to the mechanisms by which
the universe languages/thinks itself into existence starting at the Planck scale substructure of
spacetime, where (1) base objects are (2) observed/measured generating (3) products of the
observations of the base objects – the physically behaving letters of a quantized spacetime
language
It’s important to realize that the product of observation (information or awareness) is not
deterministic. An observer can interpret the same measurement differently in two identical
instances. The information interpreted by the conscious observer is a choice at a conscious or
subconscious level. Therefore, freewill is a defining characteristic of consciousness because it
not only chooses what to observe, but also the interpretations of those observations. We humans
certainly choose or create our states of consciousness by choosing what to observe and how to
interpret it even though our choices are highly influenced by the environment – the freewill of
everything else. If there are Planck scale primary units of consciousness observing reality into
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
488
existence at the “pixelated” substructure of spacetime, these same non-deterministic principles of
freewill must hold. In order for the primary units of consciousness to have freewill and also
form cooperative group patterns, they must collaborate on a fundamental level – knowing what
one another are choosing – as though they were all part of the same emergent consciousness.
Princeton mathematician, John Conway and co-author, Simon Kochen, published “The Strong
Free Will Theorem” in 2009 [19]. It rigorously reasons that, if humans have freewill,
fundamental particles must also have a primitive form of freewill. For the growing community
of scientists who have deduced that physical reality is “information theoretic”, the above
foundational deduction and unpacking of definitions requires a diligent ontological consideration
that consciousness itself may be the ground of reality.
1.3 If Spacetime and Particles are Pixelated, Is There a Network of Planck Scale Conscious
Observers Generating This Information?
Leading theoretical particle physicists assume spacetime itself is quantized. Theories, such as
loop quantum gravity [20], which quantize spacetime, are called quantum gravity theories
because they update the smooth non-discrete Einsteinian spacetime model with the knowledge
gleaned from quantum mechanical experiments– data that strongly indicate time and space are
“pixelated” into discrete units, like tiles in a mosaic, called the Planck time and Planck length.
We are not the first to deduce that there must be a conscious entities, i.e., observers at the Planck
scale to observe information into reality. Werner Heisenberg said [21]:
Was [is] it utterly absurd to seek behind the ordering structures of this world a
“consciousness” whose “intentions” were these very structures?
Physics Nobel laureate, Frank Wilczek of MIT said [22]:
The relevant literature [on the meaning of quantum theory] is famously contentious and
obscure. I believe it will remain so until someone constructs, within the formalism of
quantum mechanics, an “observer”, that is, a model entity whose states correspond to a
recognizable caricature of conscious awareness.
Andrei Linde, co-pioneer of inflationary big bang theory, said:
Will it not turn out, with the further development of science, that the study of the universe
and the study of consciousness will be inseparably linked, and that ultimate progress in
the one will be impossible without progress in the other?
Physicist and author of Bell’s Theorem, John Bell said:
It is likely that the new way of seeing things will astonish us.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
489
If the information of spacetime and particles is “pixelated”, we can deduce that there should be a
Planck scale network of primary units of consciousness observing it into existence , indeed
observing itself into reality. Here, we define “reality” and “existence” as any information which
is thought of by a consciousness.
1.4 Would Primary Units of Consciousness Use An Algorithmic Language with a “Hinge
Variable”?
An algorithm with degrees of freedom is a language. We define language as the confluence of
three things: (1) a finite symbol/character set, (2) ordering rules and (3) limited ordering freedom
or “hinge variables”. Hinge variables allow the symbols and rules of an otherwise deterministic
algorithm to encode any information desired.
Because reality comes in discrete pixels that are ordered into the mathematical systems of nature,
our work focuses on how vast numbers of primary consciousness units at the substructure of
spacetime might self-organize, behaving as a language. Specifically, we are concerned with how
they generate a finite character set and what the organizational rules and degrees of freedom
would be for those symbols.
In order for primary units of consciousness to organize into an algorithmic language capable of
generating the geometric information of physical reality, they would need to “agree” on how to
generate symbols. Specifically, they would have to agree on (1) what to observe (we call this the
“base object”), (2) a finite set of ways to observe the subsets or transformations of the base
object (3) the interpretations of those observations – the symbols (I propose the interpretation to
be equivalent to the vantage point. Each vantage point gives one interpretation) and (4)
syntactical rules for combining the symbols with degrees of allowable freedom.
1.5 Examples of Symbols Generated by an Observer Using a Base Object
Reduced to its simplest form, information is always relationship. The simplest relationships are
connection networks between two or more points. The following three thought experiments
explain how consciousness can create a finite set of symbols (letters) from a base object (also
existing within consciousness). You, the reader, are a consciousness, so you will be the observer
generating the base object and symbols within your mind.
Graph Theoretic Example: Imagine 8 points in no space, much like a network of 8 friends (Fig.
1), where distance is irrelevant to whether one person knows another. In this network (called the
“complete graph”) of 8 points, picture that each “knows” or is connected to each of the other 7.
In fact, label the 8 points with the names of 8 people who know each other. This is our “base
object”. Now, using the idea of the base object you are holding in your mind, observe a special
or double connection between any 3 of the 8 points or people, where each of the 3 is connected
to the other 2 in the subgroup you’ve selected. This new object is the product of your
consciousness choosing to observe or create a subset of relationships derived from the base
object. The object you created is a non-geometric symbol and can be used in a language with
other symbols also derived from the complete graph of 8 points.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
490
Geometric Example: Imagine the 8 points (vertices) of a cube. This is your base object, and it
obviously exists in the abstract space of your mind. Now select various combinations of vertices
of the cube and connect them, forming a finite set of geometric symbols.
Geometric Transformation Example: Imagine the 8 vertices of the cube and yourself as an
observer living with the cube in a Euclidean 3-space. View the cube along any of its axes of
symmetry in order to create a finite set of symbols that are perspective transformations of the
cube from 3D to 2D. Each is a symbol that can be used in a language.
Figure 1. The base object and the symbols generated from the base object through three
different methods: graph theoretic, geometric and geometric transformations.
Language is a good model for how pixelated units of collective consciousness would cooperate
to act physically/mathematically. Below, is a discussion regarding our approach – a
quasicrystalline language.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
491
2. The Quantum Gravity Research Group Approach
2.0 Quasicrystal Algorithmic Language
Our group suspects that the algorithmic language of spacetime substructure uses quasicrystal
(QC) mathematics. It is not within the scope of this document to go into detail, but the following
non-mathematical overview of QCs may be of interest to the reader. We shall also provide a
limited overview of several aspects of quantum scale reality that indicate nature itself may be a
conscious quasicrystalline language.
QC mathematics were not available to Einstein or the pioneers of QM. In fact, they were only
mathematically articulated in the 1960s and 1970s, starting with the inquiry of Hao Wang [23],
which led to Roger Penrose discovering the simplest way to aperiodically tile the plane with only
two tiles in 1976 [24], the famous 2D QC known as the Penrose tiling with the ratio of the
quantity of each of the two tiles being the golden ratio.
Things in nature are arranged in three general ways: Periodically ordered (like a crystal),
seemingly random (like the grains of sand on the beach) and ordered but non-periodic. When a
finite group of objects, such as water molecules (the “symbols”) is organized in a repeating
manner, as in ice, it cannot be said to be a language because the organizational rules have no
degrees of freedom.
When water molecules are arranged in the classic theory of liquid water, they have very large
degrees of freedom to move about and create bond relationships. Accordingly, it is more
difficult to recognize this structure as being a language.
However, those same water molecules can be arranged in a quasicrystalline manner, with
organizing rules and hinge variables or limited degrees of freedom within the rules. The hinge
variable can be creatively used to code any information into this structure, qualifying it as a
language.
NOTE: Regardless of the example we gave above for easy understanding, we suspect even liquid water is
a language and that randomness does not exist in nature. In fact, it is known that randomness is a theory
with no concrete evidence due to the fact that our measuring equipment does not operate anywhere close
to the Planck time or Planck length.
The organizational rules in QCs comes from their relationship to higher dimensional crystals.
For example, the Penrose tiling has 8 vertex types and organizational rules derived from how it is
projected to the plane from the 5D cubic lattice, Z5(a crystal). All crystals can project to lower
dimensional QCs. Before the projection, an operation known as a “cut” is necessary in order to
select the layer of the higher dimensional object that is projected to the lower dimension. Our
group is interested in 4D QCs derived by cut and projection of the E8 lattice, which is the
densest packing of spheres in 8D, often called the most beautiful object in mathematics. The
reason for our interest is due to the work of our colleagues Tony Smith [25] and Carlos Perelman
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
492
[26] as well as associate Garrett Lisi [27]. They showed that gravity, electromagnetism, the
nuclear forces and spacetime can be unified using the mathematics of E8.
Phasons are dynamic patterns in QCs called “quasi-particles”. They have both wave and particle
like characteristics, but their motion comes in discrete quantized jumps of the constituent tiles in
the QC. And because phason dynamics follow our three qualifiers of language, any information
can be communicated with the wave patterns of phasons. Quantum field theory is one of the
most powerful sets of equations describing key aspects of nature. It takes the older idea of
smooth waves, which can be any wavelength, and “pixelates” them into little “tiles” of spacetime
and “probability space”. The equations are powerful, but there is no first principles explanation
for why reality is “pixelated”, just as there is no first principles explanation for the fine structure
constant, gravitational constant, electron rest mass or any fundamental law or constant of nature.
Our QC algorithmic language concept offers a potential formalism for using units of
consciousness to describe the “jagged” non-smooth wave-like nature of reality.
Readers familiar with the particle-like patterns called cellular automata, such as those in John
Conway’s Game of Life [28] or described in Stephen Wolfram’s A New Kind of Science [29],
may notice their similarity to QC-phasons . Phason systems can have “hinge variables” within
their rules. And so can cellular automata and even fractals, but they generally do not. When
these systems have no hinge variable, they are deterministic algorithms and not languages.
Nature does not appear to be based on deterministic algorithms. Our group has demonstrated
that fractals and cellular automata can be programmed with hinge variables in the algorithm that
are acted upon by emergent states of the evolution of the system, creating integrated feedback
systems similar to our view on how the QC spacetime algorithm works, where subsystem
consciousnesses and the universal consciousness inform and co-create one another’s decisions at
all scales. Because our concept employs a language with a hinge variable, high order emergent
states of the system, such as humans, can direct the system in a reverse cascade of causality all
the way down to the Planck scale QC tiles, acting on the hinge variable in the algorithm and
engaging with it to form resonant feedback loops.
Our program is focused on modeling spacetime on a 4D QC derived from the E8 lattice. Points
of consciousness operating in the E8 hyper-crystal “mother” of the 4D QC can make
observations there (see rudimentary examples in 1.6 above) to actualize into informational space
a certain set of “tiles” that are symbols in the algorithmic language of “pixelated” spacetime.
For those visually inclined readers, a helpful way to think about this is to view online gif file
animations of “Jitterbug transformations” (https://www.youtube.com/watch?v=FfViCWntbDQ),
a term coined by Buckminster Fuller to describe a process of rotations of edges on a polyhedron
that transform it into a different polyhedron [30]. The reader may then be able to visualize a 3D
quasicrystalline tiling of, say, two polyhedral shapes, where at any time, one shape is Jitterbug
transforming into the other. When one of the polyhedral shapes in the tiling, say “shape A”,
transforms into “shape B”, a polyhedron with shape “B” in another location must transform into
“shape A” so that they all fit together nicely to tile space. And when one of these dynamical 3D
tilings of two or more shapes is ordered with certain rules relating to the projection of a higher
dimensional lattice, it is a dynamic QC – a phason system. Jitterbug waves from different
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
493
directions can simultaneously flow through this QC such that, from a distance, the patterns of
motion look smooth like fluid dynamic systems in nature. (Please refer to this link for an analogy
of the fluid nature of the phasons:
http://mainisusuallyafunction.blogspot.com/2011/10/quasicrystals-as-sums-of-waves-in-plane.html)
2.1 Combining the Jitterbug Wave Idea with Units of Consciousness and Language
Continuing with the above example of Jitterbug waves, consider that each of the two shapes “A”
and “B” act as symbols or letters in a language. Their relationships form “words”. In QC
terminology, we call these words “vertex types”. The vertex type “words” join together into
larger complexes that are like “sentences”, which are called “super-cells”. Dynamically, all these
objects work together to form wave-particle like patterns in QC-phason systems.
Mathematically, the concept can be described with or without geometry. Either way, it is a
language because of our 3 defining characteristics of language. As referenced in 1.6, a unit of
consciousness can operate on some ideal base structure, which is also equally as abstract as the
units of consciousness. First we shall give a simple example using graph theory. Imagine a
block divided into 100 cubes with a unit of consciousness assigned to each vertex. Here, the
visualization of the block of cubes is a tool to think about a network of connections made mostly
of vertices shared by 6 edges. The idea here of the geometric cube is just a visual tool or mental
“graph”. In this example, there is no actual spatial geometry. Now imagine there existed a code
with a degree of freedom, where the letters A to F or the numbers 1 to 6 are used, each a
different quantity of the 6 possible edges meeting at each vertex. The rules for such a code that
operates within these 100 points or units of consciousness might allow them to creatively
“sparkle” sequences of the 6 letters/numbers of this language to convey a pattern. Now, imagine
we are unaware of this code because it occurs very fast. From our perspective, their behavior
might appear random because we would not be able to predict outcomes. However, because
there is an underlying code, we might notice consistent higher order patterns emerging but only
on averages and never predictable with certainty. If this system were a toy universe, we would
call these averaged patterns “laws of nature” because they would always be evident over large
averages. Over millions of unpredictable choices, we might see a very foundational pattern
emerge – the waveform for example. For us, we would describe this as a wave of probabilities
since we can only see it after measuring and averaging many of these apparently sporadic
decisions. This is exactly how a phason system in an actual metallic quasicrystal works. When
several phason particle/waves are propagating through the material, the wave interaction looks
smooth. But when we zoom into the micro scale, we notice that the atomic jumps that make
these wave patterns must mathematically coordinate within the QC matching rules. Each step in
a propagating wave must be calculated with respect to the other phason waves (which are tile
flips, i.e., atom position changes). Therefore, the patterns have no option but to jump about.
Perfect adherence to a wave pattern could only occur if there were only one phason in the
system. But multiple phasons in the same QC have to “take turns” within the allowable syntax
and hinge variable rules in order to have each of their tile flip patterns conform as closely as
possible to the trajectory of their wave propagation patterns. And so over large numbers, each
averages to a near perfect wave pattern even though, at the most granular level of change, tile
flips can jump significantly off course from its overall wave pattern.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
494
A second example is the geometric type. Let’s continue with our 100 units of consciousness
assigned to 100 cubic cells. We had a network of about 100 connected vertices with 6 edge
connections each. We expressed that graph theoretically without respect to the idea of cubes or
space. The units of consciousness picked integer values between 1 and 6 connections from each
of the 6 connections possible each vertex. The idea of a connection network – like a network of
friends, has no need for the notion of space.
In this second example, we will interpret this same information to be a cubic tiling in 3-space.
The units of consciousness are going to be assigned to “look” at their cubes from one of only two
vantage points or possible measurements. This will create 2D projection transformations of the
cube. We will call one type of projection “A” and the other “B”. If the units of consciousness
and cubic cells are adjacent in the 3D structure, we shall say that they must lay down their
projections on the plane in an adjacent or connected manner as well. In other words, 100 units of
consciousness will take photographs of their cubes from one of only two vantage points to create
2D shapes “A” and “B”. And let us further imagine that these two shapes can aperiodically tile
the plane if matching rules with allowable degrees of freedom are followed. The units of
consciousness in the cubic lattice would have to know what those rules and degrees of freedom
are before making their individual choices. They would also have to know what the others
around them are choosing or be part of the same meta-consciousness. If they do these things,
they can use the flexibility within the rules to generate a wavelike animation of tilings of the
plane where you would notice patterns vibrating through the animation from different directions.
The rules and cooperative freedom and finite number of shapes that can be created from the
pictures taken by the units of consciousness are a “wave language”. So as they unpredictably
express their group ideas using this language, we will see extremely reliable tendencies that we
can call “constants” or “laws of nature”. But at a granular level, we will not be able to predict
the letters chosen. The wave language would describe the physical phenomena of nature.
Our program is to use the concept of units of consciousness making choices within a language
structure to generate 4D QCs derived from the E8 lattice that model dynamic waves of spacetime
with emergent force and mass qualities as “perturbations” within the system. There will be
various equivalent ways to explore this overall language, which we will call “dialects” because
they will have the same root language but perhaps will look very different mathematically, using
different formalisms. For example, our colleague Tony Smith uses the real Clifford algebra
Cl(16) on the same base object, the E8 lattice, to unify spacetime and the four forces [25].
2.2 Clues That Nature Is a QC Based Language of Primary Consciousness Units
Golden Ratio in Nature
QCs are described by golden ratio based math [31]. The golden ratio is found in nature at all
scales with hundreds of published references [32-35]. For example, the 2010 paper, “Quantum
Criticality in an Ising Chain: Experimental Evidence for Emergent E8 Symmetry,” reports the
discovery of the golden ratio and the related structure of the 8D lattice E8 in the atomic structure
of cobalt niobate [36].
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
495
Xu and Zhong’s paper [37], “Golden Ratio in Quantum Mechanics,” points out the connections
to the golden ratio in various works – linking it to particle physics and quantum gravity
(quantized spacetime). They say (note that QCs are the quintessential example of noncommutative geometry and are fractal):
… we would like to draw attention to a general theory dealing with the noncommutativity
and the fine structure of spacetime which comes to similar conclusions and sweeping
generalizations about the important role which the golden mean must play in quantum
and high energy physics… …In a unified picture where all the five forces melt into one it
is reasonable to suspect that the golden ratio will play a fundamental role.
This fact immediately follows from the work of the French mathematician Alain Connes
and the Egyptian engineering scientist and theoretical physicist M.S. El Naschie. In
Connes' noncommutative geometry his dimensional function is explicitly dependant on
the golden mean. Similarly the bijection formula in the work of El Naschie is identical
with this dimensional function and implies the existence of random Cantor sets with
golden mean Hausdorff dimension as the building blocks of a spacetime which is a
Cantor set-like fractal in infinite dimensional but hierarchal space. Invoking Albert
Einstein's ideas connecting spacetime to geometry with energy and matter, it is clear that
these golden mean ratios must appear again in the mass spectrum of elementary particles
and other constants of nature.
Evidence of Higher Dimensional Polytopes and Lattices in Nature
All particles and forces can be transformed into the others via gauge symmetry operations [38].
This tells us something deep about nature and convinces physicists that there is a yet-to-bediscovered first principles theory that will allow us to understand how everything in nature is a
manifestation of the same underlying object. The gauge symmetry transformations plot perfectly
to the vertices of certain golden ratio related higher dimensional polytopes and lattices related to
the E8 lattice. Tony Smith Garrett Lisi and Carlos Perelman are three of many physicists
publishing results linking spacetime and particles to the golden ratio related E8 lattice [25-27].
All lattices project to QCs, which non-locally encode information from the higher dimensional
object in the lower dimensional projection.
Non-Locality
Nature is known to be inherently non-local [39]. For example, when two particles are entangled
after being superimposed into the same space, they will instantly mirror one another’s behavior
as if connected – no matter what the distance is, even light years apart. QCs are inherently nonlocal [40]. For example, a change in one part of the QC changes other parts of the QC instantly,
regardless of the distance.
Non-Commutative Geometry
Lee Smolin in Three Roads to Quantum Gravity said:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
496
…evidence has been accumulating that string theory and loop quantum gravity [a
quantized spacetime theory] may describe the same world. One piece of evidence… … is
that both theories point to some version of the holographic principle. Another is that the
same mathematical ideas [and] structures keep appearing in both sides. One example of
this is a structure called non-commutative geometry.
Many leading physicists and mathematicians, most notably Alain Connes, publish evidence
indicating that non-commutative geometry will be at the heart of a new first principles theory of
everything [41-43]. Again QCs are the quintessential example of non-commutative geometry
[44, 45].
Quantum Fluctuation and Quantum Jumps
There is no first principles explanation for why the energy state change of an electron orbiting an
atom causes it to instantly teleport from one orbit to the next without traversing the space in
between. Modeling particles with QC math would not only explain this, it would require it. And
the same can be said of quantum fluctuations in vacuum space, where a particle appears in one
location and then abruptly disappears, while maintaining the same total number of these ghostly
objects. Modeling spacetime with QC math can explain this behavior. A dynamic QC system
requires a conservation in the number and ratio of vertex types. When one vertex type
disappears in one frozen frame of the dynamical animation, an identical one instantly appears in
another location in the next frozen frame of change – a shared characteristic with quantum
fluctuation and quantum jumping. Also, quasiparticles in a QC vibrate due to being composed of
discrete pixels or tiles, which cannot move smoothly. This is a shared quality with quantum
particles, which are known to vibrate – “quantum jitter”.
Retro-causality and Special Relativity
Daryl Bem of Cornell published a great deal of research evidence on retro-causality [46, 47],
providing robust evidence that events in the future loop back to change events in the past. These
experiments were done with human subjects, who were influenced by events that were to occur
in the future of the experiment, as generated by a random number generator. The effect did not
change over distance or time. In fact, many other published works support the existence of this
and similar phenomena. This should not come as a surprise. Post 1905, since we have
understood Einstein’s special theory of relativity, we have come to grips with the non-intuitive
idea that the past, present and future exist together on a geometric object called spacetime. The
reason some scientists presume retro-causality should not occur is because relativity theory and
experiment indicate that light cannot move backwards in time to communicate information.
However, considering the fact that particle entanglement experiments show that particles are
non-locally entangled across spacetime, instantly mirroring the actions of one another, it is not
necessary to rely on light to connect information non-locally. Big bang theory says that, at one
time, all particles occupied the same space. If true, everything is quantum entangled non-locally.
Furthermore, there exists no widely accepted unification theory, so there is no theory we can rely
on to say that non-light based information cannot be connected non-locally without the need to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 483-497
Irwin, K., A New Approach to the Hard Problem of Consciousness: A Quasicrystalline Language of “Primitive Units of
Consciousness” in Quantized Spacetime (Part I)
497
encode it in light. This idea does not contradict special relativity because the speed of light is not
exceeded. Connecting systems of information, as with quantum entanglement and quantum
teleportation, is not the transmission of information. It is the connection of two or more systems
of information into a single object.
A QC spacetime, based on the E8 to 4D QC, allows for algorithms that create instant relation of
information between two or more regions of spacetime (such as human minds). This mechanism
predicts that reality would be a system of causal and retro-causal feedback loops, where all
things forward in time loop back to influence all things backwards in time – thus changing the
events forward in time and so on. This standing wave concept, where events described by the
primitive spacetime algorithm vibrate forward and then backwards in time, means that events
across spacetime co-create one another. For example, if you have a precognitive intuition of
something, it is akin to “remembering” forward in time. But the “memory” of that event changes
the structure of your brain patterns in your present, which acts as a “butterfly effect”, changing
all events in your future and so on – a vibration of bi-directional causality.
Consider Bem’s evidence for retro-causality. Would human minds be influenced by future
events only during his lab experiments or at all times? There is nothing special about his
experimental set up which produces retro-causality. And his data show that retro-causal
phenomena do not get stronger or weaker depending on how far one separates the events from
one another in space or time. This evidence invites the conjecture that every event co-creates
every other event in both directions of time.
(Continued on Part II)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
427
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
Exploration
Minkowski Space & Consciousness
Trevor N. Carniello*
Consciousness Research Laboratory, Behavioural Neuroscience Program,
Laurentian University, Sudbury, Ontario P3E 2C6
ABSTRACT
In this paper the theoretical application of Minkowski metric is developed to demonstrate a
potentially unifying explanation for the synapse as a Casimir phenomenon, the generation of
photons from cognitive processes, and the transformation of virtual into real particles. Specific
solutions reflect preconditions that could subserve the non-locality and entanglement of cerebral
electromagnetic and synaptic structures of specific brain functions. It is suggested that the
holographic representation and manifestations of Minkowski space within the cerebrum
determines the real and virtual dualism of consciousness.
Key Words: Minkowski space, holographic space, mathematical applications, consciousness
and hemisphericity, dualistic consciousness.
1. Introduction
Over the last several decades of psychological research, the primary focus was to quantify the
seemingly immeasurable process that is representative of consciousness. As the endeavour
proceeded researchers have described many different theories that could be used to explain the
translucency of the conscious process. Initial studies utilizing the electroencephalography (EEG)
and quantitative electroencephalography (QEEG) were the primary methods employed to add a
tangible definition of output to the function of consciousness. Throughout the general studies we
have, on the consensus, theorized that perturbations within static voltaic, and consequently
energetic, equivalent fields as generated by brain activity, describes the basis for the beginning of
consciousness. The general conclusion, through introspection and correlative reductionism,
argued that the difference in the firing patterns of summed, or individual, action potentials was
the proof behind the quantitative aspect of this theory.
The theory of the electrical source, governed by stimulation patterns of firing neurons, of
consciousness had remained apparent until the introduction of the magnetic field theory as
described by several authors [12-14,16-19]. Consciousness was synonymously attributed to
interacting electromagnetic fields. With the inclusion of such an idea there has been various
idealistic extensions trying to explain and relate the potential of the current electromagnetic
theory and physiological function. Quantum mechanics have also been implemented as a
particular method by which to model these effects with the intent if determining the source of
*Correspondence: Trevor N. Carniello, Email: tn_carniello@laurentian.ca
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
428
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
generation (the locus) that contains the central idea that is consciousness. Even Pribram has
revelled at the opportunity to use the electromagnetic proposal of consciousness in relation to the
generation of simultaneous virtual particles that are identical, in nature, to those of the initially
interacting real particles [4,41,42].
Pribram’s elucidated manner of transference, from real to virtual forms (and vice versa) can be
explained using quantum mechanics, as well as the interactions at the microscopic level
producing quantum (Casimir) forces, to which he has so elegantly modeled. Schrödinger’s
equation has been used to describe the electromagnetic component of the brain as it approaches,
or resembles, that of Pribram’s holographic model. The solutions to universal contingencies, the
multiple interacting waveforms, within a system approaches each other and thus reflects physical
and virtual arguments of functionality [9,42]. The governing reaction, to which the quantum
argument supports, is that which is based upon the interaction between colliding electromagnetic
fields or particles. Alas, all the theories that have been presented to date have not generalized to
identify the brain structure, or component, as the source of “consciousness generation.” Nor have
they upheld the integrity of the remedial ideal of specific structure function duality.
This may raise the question of, “will we ever truly define, or let alone understand, the nature of
an abstract concept such as consciousness?” The simplest answer should be acquired by the
greatest contribution of humanity to science, the experiment, and its corresponding accuracy in
measurement. This, however, does not exist without its flaws. The greatest limit that is
associated with the experiment is the level of precision of a measure that can be obtained. This is
an intrinsic component of the condition of the tool of measure, also known as error. Modern
instrumentation, although exceedingly sophisticated, has its limitations. Perhaps these limitations
correlate to an inability to measure the phenomenon that is consciousness. The question, “will
there ever be a technology that will be able to measure abstract ideas or will we remain always at
the boundary, the “event horizon”, of its interpretation?” arises. The author of this paper would
like to stress the concept that, at this very moment, we possess, within the boundaries of our
organism, that which can be used to measure the variables of a human construct responsible for
the aggregation of abstract ideas. Such a tool has already been defined and implemented by
Einstein known as the thought experiment. The boundaries of the thought experiment are defined
as the cognitive and creative limitations of the individual thus reflecting the basis of the intrinsic
contribution of the human condition. It is with the use of this particular tool, the thought
experiment that I intend to provide the theory and essence of this paper.
The idea that, in nature, two contrastingly equivalent forces must occur in synchrony (such as the
positive and negative) has not been considered a new idea. Einstein and Eddington had described
two independent, physical, interactions that exist within the boundaries of this universe occurring
in a synchronous and parallel process. Such ideas were broken into, what they described as,
matter and energy [27,28]. The idea that either of the two components, matter or energy, of this
dichotomy could influence the other is a portion of which this article is dedicated. Within all
constructs of this universe we can always relate the concepts of matter and energy. In the case of
the human brain, the structure, the equivalent example would be that of memory formation with
regards to newly formed protein growth (manifested as dendritic spines or filipodia within 15
minutes after electromagnetic elicitation by stimulation), is representative of the matter
component. Comparatively, consciousness would be representative of
the energetic,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
429
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
electromagnetic, equivalent within the proportionality of mass-energy dichotomy. Yet again we
arrive to the question of, “what is consciousness?” and although the theories aforementioned
result in adequate definitions I would like to extend on their ideas by relating the properties of
Minkowski space. The addition of Minkowski elements would introduce a plausible solution for
the function-physiology binding definition of consciousness.
The percept that microcosm reflects macrocosm was originally denoted by Eddington, who
believed that the representation of the universe was no more than the reflections of the neural
network that subsequently represents the brain [29,30]. From this original perception other
theorists, such as Pribram and Persinger, have elaborated on the particular connectivity and
relationship of microcosmic effects reflecting macrocosmic experiences. Pribram extended on
Eddington’s notion as the basic foundation to formulate the concept of the holographic universe.
The fundamental pretence by which the holographic principal is derived, denotes that the
representation of one specific object--for arguments sake let us interpret this object as a physical
particle-- has both real and virtual components or solutions. These complex real and virtual
solutions display coherence to solutions of Schrödinger's equation, subsequently amassing
implications within Hilbert space[34,43]. Extension and involvement of Hilbert space is a
necessary contingency required for hologram genesis and conservation.
Contributing to the physical-non-physical relationship in the universe, Persinger introduced the
contingent expression that the “Σn = n”. This is of cosmic significance whereby the sum of the
parts is equal to the whole (vice-versa) [15]. Fundamentally, this notion precludes Pribram’s
particulate interaction and integrates the real and holographic equivalents within (brain) space
[15]. Persinger also defined and integrated the fundamental neuroquantal value of 10-20 J, as an
integral component of macroscopic and microscopic reflections. Mechanistically, this quantum
of energy is seen to effect and, as a consequence, exists within all levels of discourse between
known matter boundaries and beyond [15,24]. Under these a priori ideas, I have contemplated
the relationship between the factors that define the functions of all levels of discourse, such as
Minkowski space with its congruence to microscopic, or neuronal, equivalent. Reducing the
complex nature of consciousness to a quantifiable alteration within space-time contiguity would
enable unification of theory. Measurable correlates may provide the relative solutions necessary
to solidify the conceptual, phlogistic definition of consciousness.
2. Minkowski Space: The Relationship between Four Dimensional space and
Two Dimensional Space within the Boundaries of the Brain
The primary argument for this section is the intercalated interaction of structure and function,
whereby the former dictates the latter. We observe this particular concept on varying levels of
discourse examining, for example, the enzyme. In reality, the orientation and the precise
conformation, as depicted by the tertiary (and in some cases quaternary) structure of the enzyme
results in a specific enzymatic function. If we were, for instance, to change any component of the
protein we would inadvertently and ultimately change its function. This concept and definition
are of little difference with regards to brain structure and consequently brain function. At present
we can confidently attest that the two hemispheres, the left and the right, both have, although
equivocal in complexity, different functions. This is due to the fact that, of the over 100 sulci and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
430
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
gyri that compose the superficial surface of the respective hemispheric boundaries, there are only
three or four that are relatively similar in structure [23].
Systematically, the delineation of the hemispheric function correlates, and can be modeled, by
differential space-time mechanics [31]. Intrinsic processes of the left hemisphere flow in a serial
and categorical manner occurring within a limited epoch of time. Thus, by definition and
extension of function alone, the process must be able to analyze all incoming data from the
outside world and generate three dimensional coordinates that are representative of the ongoing
events. Consequently, the summation of the individual components of the event converges upon
encoding and will ultimately be expressed within the stored experience (memory) of the
individual. This function can be similarly modeled to fractal generation. The input-- the three
dimensional component solutions for each point-- would result in the generation of ongoing
experience. The temporal component (t1 and t2) enables the elicitation of an ever-changing Δt,
introducing a time varying component to the functionality equation. By contrast, the right
hemisphere has limitations that exist as the process of a two point, two dimensional, system.
Right hemispheric function incorporates two points, the reference and a measurable value,
whose subjective time reduces itself to nil. Thus the change in time over the function of the right
hemisphere is Δt=0. In this manner, the right hemisphere and its underlying processes exist
independent of time.
The marked differences between both hemispheres, at a glance, do not show any spatial or
temporal contiguity between space-time paradigms. Relatively, they exist as separate spaces and
entities disallowing any particular mathematical relationship between the left and the right
descriptors of coordinated function. This author believes differently, suggesting that the
mathematical contiguity exists as a special case of Minkowski space. This alternative metric of
Minkowski space would result in a quantifiable and measurable correlate of consciousness.
Alteration of the Minkowski metric would be derived from the reduction of four-dimensional
Minkowski space to a two-dimensional model. The longitudinal mathematical application of the
missing/reduced elements would successfully describe the measure of consciousness.. The
resultant solutions exists as complex alterations within space-time definitions of virtual and real
subunits to which we ascribe the entire, phlogistic, definition of consciousness. It is in the
defined process of the respective left and the right hemispheres with which we will implement
mathematical equations in order to relate four dimensional Minkowski space and two
dimensional (or reduced Minkowski) space.
The categorical processing of the left hemisphere, in general, must occur within three
dimensional analysis of the (structure) event occurring over a variable length of time. These
temporal events evolve over ever-changing periods (durations) respectively conjugating within
the time dimension. A consequence of the nature of this function formulates the idea that the
categorical processing has a component of space-time and thus can be modeled as such a system.
Implication of theory suggests that one can model the generated fractal points as a consequential
matrix produced by a function of the Minkowski equation. Point to point temporal alterations
result in ever-changing epochs producing modulations within the axiom of time. Genesis of
three-dimensional points, with respective alterations in temporal lapses, would be the underlying
contribution to differential descriptors of the spatial and temporal axes of space-time.
Modelistically, the yield of the entire experience can be expressed as a series of threeISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
431
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
dimensional points with respective temporal durations that once summed or aggregated,
represent the production of the fractal function.
ds 2 = dx12 + dx22 + dx32- c2 dt2 (1),
where s is the frame of the occurrence (point within fractal), dxn= one axis of the 3-D space, c is
the speed of light, and t is the time component that is associated with the generation of that point.
When we relate this equation to brain function, the values of x1, x2 and x3 represent the spatial
confines of the pattern (location of generated points associated with the total experience) and
c2dt2 represents the point duration of each point within that pattern. What we must realize is that
a single value output by this equation does not describe the total experience but instead models
one point, or component, within the aggregate or matrix pattern, generated by the interactions of
all fractal points representing the entire experience. Upon inspection of the relationship between
the manifestation of one point as a part of the whole agrees with Gestalt theory by which the
whole is more important than the parts. However, in the extension of the holographic argument,
each component is as equally complex as the whole whereby the representation of the whole is
reflected in any one part of the components. Thereby, the integrity of the whole is dependent
upon all components being properly expressed in their patterned occurrence. In essence, the sum
of the parts is representative of the whole and the whole is representative of each part; they
cannot exist without the presence and interactions between them.
It is possible to equate consciousness to two different yet synchronous forms one which is
representative of a homogenous four-dimensional processor and the other that represents a lineelement function of two-dimensional space. Describing a four-dimensional function as a line
ablates one unit of space and the axiom of time. A direct consequence of manipulating the spacetime context of four-dimensional processing, transforms the fundamental function to that which
exists as a two-dimensional mechanism. Reduction of four-dimensional function occurs in
Special Relativity where two distinct processes can eliminate the necessary variables from
Minkowski space resulting in a reduction of space-time boundaries. Reducing the boundary
condition results in a change in the Minkowski equation that would reflect the generation of a
two-point system ultimately manifesting itself as two-dimensional space. Possible reduction of
four-dimensional space-time constraints would allow for the manifestation and definition of right
hemispheric function. Ultimately, the underlying mechanics of the respective hemispheres
governs the independent existence of consciousness. With respect to the reduction of Minkowski
space, the two particular cases of Special Relativity are the case of Simultaneity (Relativity of
Simultaneity) and the Twin Paradox. The equation used to define the Relativity of Simultaneity
is:
Δt1= γ (Δ t –
) (2),
where Δt’ is the relative time elapse, Δt is the time of the occurrence, c is the speed of light, v is
the velocity of the object, Δx is the change in space between two objects and γ is the Lorentz
contraction.
The implications of the Twin Paradox Equations results in the formation of the relative equations
of:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
432
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
Δt1= γ (Δ t –
) and Δ x1 = γ (Δ x – v Δ t ) (3),
Δt= γ (Δ t1 –
) and Δ x = γ (Δ x1 – v Δ t1 ) (4),
where Δt’ is the relative time elapse, Δt is the time of the occurrence, c is the speed of light, v is
the velocity of the object, Δx is the change in space between two objects, Δx’ is the change in the
position of the object in relative space and γ is the Lorentz contraction.
Under the presumption that for simultaneity to occur both of the following conditions must be
upheld: Δx = 0 and Δt = 0. If the conditions are met such that the equation results in the
generation of a Δt’ = 0 and the simultaneous assumptions (Δt= 0 and Δx= 0) are met then the
frame, or occurrence, is said to occur instantaneously. This satisfies that in the frame of S, if Δt =
0 and Δx = 0, generating the event occurring in frame S’ would be simultaneous. The final
consequences would be the reduction of Minkowski space generating two-dimensional space. In
essence, the process is said to exhibit spatial and temporal equivalence denoting synchronicity
and binding. The aforementioned statement is an extension of the definitive processes of
entanglement originally described by Schrödinger. Presence of potentially interacting particles,
as they are located in isolated systems, produces overlapping physical definitions of highly
relevant and coherent states. Occupancy of any particle within a distinct frame of space will
exhibit the same spatial (Δx) and temporal (Δt) components of another particle when entangled.
When two particles are submersed in an intrinsic and unifying field, and although they may be
separated by a relative and measurable distance from each other, they produce functional and
mechanical overlap eliciting instantaneous non-local binding [43, 44].
Synchronous
hybridization of these two entities (particles) results in the generation of the "same" space-time
contingencies. Application of equations 3 and 4 such that Δ t1 = Δ t, and Δ x1= Δ x, produces a
resultant component generating a similar reduction in Minkowski space as did the assumption of
Simultaneity. The application of any cause of instantaneity contraction is always apparent in the
holographic universe such that virtual and real particles occupy the same temporal and spatial
boundaries. This instantaneous reaction observes spatial constraints based on the essentials of
non-locality. A relative definition of non-locality aiding in the defining of the holographic
representations of any system, more specifically in this case a brain system, resides in Bohmian
mechanics.
The definition of holographic generation is the consequence of instantaneous interaction of
highly coherent brain states generating non-local holographic informational cortical fields of
consciousness interconnecting the human brain and the holographic cosmos [6-8]. Di Biase
extends on the reference of non-locality as it is responsible for the instantaneous interactions
between cell cosmic phenomena as the mathematical consequence of Umezawa’s Quantum Field
Theory [6]. To relate the non-local interaction of consciousness we target the interactions
between the virtual and real spaces that are contained and maintained within brain space. When
the conditions are met that we create a point of chaos, the absence of or zero point, within two
axes of Minkowski space it produces the loss of an x coordinate and consequently reduces the
influence of time. The reduction of Minkowski space (Equation 1) under the relativity of
Simultaneity and Twin Paradox assumptions would result in:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
433
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
ds 2 = dx12 + dx22 + dx32- c2 dt2 where dx3 = 0 and dt = 0, then:
ds 2 = dx12 + dx22 + (0)2- c2 (0)2
ds 2 = dx12 + dx22 (5),
This reduces the four-coordinate system to produce a two-point system providing physical
salience to right hemispheric function. By this implication, there is a re-introduction of a Δt and
Δx, such that Δt and Δx > 0, then the function will regenerate. Changing the function of the right
hemisphere, such that we introduce a new locality of innervation ( say by changing the vectorial
output of the hemisphere so that it crosses over to the left hemisphere, like under the influence of
physiologically patterned magnetic fields) [23] or by changing the time domain through
resonance (or disturbances of the frequency of operation through perturbating interference
patterns) we alter the overall perception of space-time by re-integrating the two lost dimensions.
Thus if Δt>0 and Δx > 0 then:
ds 2 = dx12 + dx22
where dx3 > 0 and dt > 0, then
ds 2 = d(x1 > 0)2 + d(x2 > 0)2 + d(x3 > 0)2- c2 d(t > 0)2
ds 2 > 0 (6),
Re-integration results in the formation of a single point (within the fractal matrix) exhibiting
duration within Minkowski space.
Brain function is a persistent paradigm-shift of activity. Manipulation of ongoing points reflects
an ever-changing pattern of consciousness within restricted brain space. Allotting the function of
the independent hemispheres, we would generate related, yet distinct, frames of experience. The
left hemisphere equivalent of experience can be generated by the function of an n x n fourdimensional matrix. Conversely, the right hemispheric equivalent of consciousness would be
modeled by a two-dimensional matrix generating a two-dimensional framework. Thus if we are
to assume that the function (S) is generating an n x n matrix (M), of four-dimensional
Minkowski points or two-dimensional reduced Minkowski points, respective of either
hemisphere, then the result of the experience would be:
df (x1,x2,x3,t) =
= (M)nxn (7).
The representation of the matrix generation can be manipulated to represent both forms of
Minkowski equations, allowing for dynamic preservation of the equilibrium of consciousness. A
single caveat must be maintained, much like the duality of energy and matter, that denotes
maintenance of separate space-lie and space-time equilibrium must be upheld. Any change in the
system, either to the underlying function of the right hemisphere or the left, that results in an
alteration in underlying space-time mechanics must be compensated by an opposing change in
that system. A subsequent transient manifestation of four-dimensional space within the right
hemisphere would reduce the left hemipshere to a two-dimensional system. This dynamic change
would adhere to the maintenance of equilibrium.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
434
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
This would account for the transference and generation of right hemispheric equivalent patterns
of innervation. An example of hemispheric space-time equilibria is best described as the result of
interhemispheric communication via vectorial change. The pattern of formation remains as the a
priori assumption that the regeneration of Minkowski space occurs, in the right hemisphere,
when the resultant vector crosses over to the left side. The resultant vector would be generated
from the spatial vectors defined by the function of the right hemisphere as a function of the
separation of x1 and x2. If this is the case, then the idea that one of the components of Minkowski
space can be defined as a two-dimensional representation may arise. That is to say, that the third
component, x3, is dependent on the location (vectorial difference) between points x1 and x2.
However, attribution of vectorial alteration is also time dependent.
Under normal circumstances, equilibrium is maintained within respective, independent
hemispheres whereby the left adheres to the influence of time and the right does not obey
temporal constraints. Consequently, under these same conditions the right hemispheric
equivalence of consciousness is exhibited as a two-dimensional process. When the system is
disrupted in such a manner as to elicit a level of interhemipsheric communication (vectorial
change) the resultant alteration in the function of the right hemisphere exhibits left hemispheric
characteristics. This notion must be corrected by changes resulting in regulation of equilibrium
and thus one would expect a change in the function of the left hemisphere to exhibit the
characteristics of the normal functioning of the right hemisphere. Integration of vectorial change
may suggest that the third spatial axis and the influence of time manifest and interact in intrinsic
ways. Equations 8 - 10 would be the mathematical implications such that time and space exist in
the same axial frame. In this particular instance we will equate the time associated with the
vectorial distance and that underlying the Minkowski time component as being one in the same.
X3 =
or X3 =
(8),
This point (x3) would be subject to the effects of time, thus introducing the time domain,
generating the resultant function to be:
X3 =
(t2-t1)
X3 =
dt
or X3 =
(t2-t1)
reducing itself to be:
or X3 =
dt (9),
In this particular case, if the time domain was altered such that Δt = 0 then the third dimensional
point would not exist and the Minkowski equation would be subsequently reduced to:
ds 2 = dx12 + dx22 + dx32- c2 dt2 but X3 =
ds 2 = dx12 + dx22 +d[
ISSN: 2153-8212
dt
therefore:
dt ]2- c2 dt2 (10),
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
435
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
If one applies the condition of simultaneity (dt = 0) then:
ds 2 = dx12 + dx22 +d[
(0) ]2- c2 (0)2
ds 2 = dx12 + dx22.
From the generalization of Minkowski space, and its reduction, we conclude that the function of
either hemisphere generates independent solutions under mathematical applications and
representations of space, resulting in the Minkowski equivalent in the left hemisphere and
reduced Minkowski space (two-dimensions) in the right. The production of the spatial and
temporal components, and their governing space-time fabric, is a direct relation to the function of
the independent hemispheres reflective of their spatial and temporal organization and syncytium.
De and Pal have argued that, under the context of binding, the most developed of which is the
theory of binding by synchrony, introduces the complexities of time and consciousness that
appear paradoxical [5]. The extension of this binding theory, in accordance with the
reductionism of Minkowski space, produces one of the components of the principle relativity
constraints. Binding by synchrony relates the co-operability and symbiotic relationship between
the temporal relations of space-time and the existence of consciousness. The connectivity of
intercalated reactions disrupting both temporal and spatial extents of the boundaries of
Minkowski space suggests that consciousness exists as both the presence (real) and absence
(virtual) of space-time contingencies. Notably, the existence of consciousness is dependent upon
the hemisphere in which it is represented but maintains a dynamic equilibrium. Conceptually,
consciousness exists as the presence of four-dimensional space-time within the left, yet it appears
to be the lack of four-dimensional representation that constitutes consciousness within the right
hemisphere. It seems that the complexity of such an abstract idea lends itself to the generation of
complex identities and relations in our physically defined world.
3. The Interpretation of Consciousness and its Relation to Minkowski or
Reduced-Minkowski Space-Time
Functionally independent representations of both left and right hemipsheric equivalents of
consciousness are the same. The difference lies in the underlying mechanics that are used to
define their processes. If we agree that consciousness is a physical process (related,
synonymously and synchronously, to memory and memory formation) we may further delineate
its characteristics. Perturbations in the space-time continuum, exhibited within brain field, will
produce a disturbance, in such a manner, as to elicit the introduction of a Δx and Δt that will
ultimately alter the equilibrated continuity of consciousness. In the quantum argument, a
collapsing field of a propagating or time-varying electromagnetic field, the point of crossingover between the generation of the magnetic field and the ablation of the electric field, equals
consciousness as Δx and Δt = 0. That is to say that consciousness exists without the implications
of space and time, in one form primarily represented in, but not limited to, the right hemisphere.
The functional reduction of Δx and Δt results in a single axiom: a component that was once used
to describe two factors of Minkowski space. Di Biase described this effect, making reference to
Bohm’s universal model, as the juxtaposition of space and time such that they are mixed and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
436
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
folded into a single dimension, axiom, of frequencies, relative to energy, that is an implicit
hidden order without space-time interactions [6].
The reduced axiom would be considered as the perpendicular extension of neuronal activity
known as consciousness, or the virtual component of consciousness. Arguments can also be
extended to include the sum of the three components generating waveforms within space-time.
Transformations regarding cross-over, vectorial hemisphericity, are transient alterations that can
only exist for periodic time frames before the system self-corrects, as previously mentioned. In
this manner, consciousness is the result, or the presence, of x3 and t as per the definition of the
confines of left hemispheric action. Consequently, there is a remarkable change that occurs
within the right hemisphere to maintain dichotic and independent space-time mechanics.
Implications for the maintenance of both the virtual and real representations of consciousness
suggest a connective duality reflective of the governing universal dichotomy. Existence of
dichotomous dynamics has been introduced as a notion that has been introduced as dynamic
hemispheric space-time equilibrium in earlier sections. Support for the claim that the crossover
of the vectorial information from the right hemispheric process to the left hemispheric equivalent
was demonstrated by Saroka and Persinger [22].
In this particular article the conceptual basis of the sensed presence, represented in the
mathematical equivalent correlative information rendered by qEEG methods, derivated by
sLORETA algorithms, indicated the vectorial change. In this particular manner we have altered
the representation of the x3 and t components of the left hemisphere and reduced the governing
space mechanics to that which is representative of reduced-Minkowski space. Alterations in the
boundary conditions, through space-time mechanistic reductions of function, generates a
measurable experience related to or representative of consciousness. The activation of this bihemispheric manipulation of physiologically patterned weak magnetic fields would be the
necessary action required to induce the cross-over and maintain the homeostasis of this elegant
dualism. Experimental support of solely unilateral stimulation resulted in a decrease in the
prevalence of the sensed presence experience [22,23].
Considerations of the results lead to the idea of a synchronicity of dynamic equilibrium in
consciousness. Within the context of stimulation studies and connectivity theories, the
suggestion would be that there is a coupling or binding (as aforementioned as synchrony of
binding) process that occurs between the left and the right hemisphere. This binding process can
be altered by integrating shifts in neuronal activation equivalent to hemispheric crossing over. A
continuation of the theory that consciousness has a virtual and real component is the maintenance
of the separate representative space-time paradigms and the preservation of both independent
attributes. Thus the resulting crossing would alter the general attributes of the left hemispheric
function and it, in tandem, would be reduced to adhere to two-dimensional Minkowski
constraints. Consequently, cascades then alter the function and representation of the right
hemispheric equivalent in such a way that the governing equation generates four-dimensional
Minkowski space. The aforementioned is no more than an extended hypothesis of the
experimental support and would be contingent upon dynamic equilibrium.
The pattern of cross-over is transient and does not last for eternity; data suggests the length of the
experience approaches roughly 20 seconds. The proposition of the return to function, the initial
point of inertial equilibrium, would be the result of the completion of this process.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
437
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
Approximations using the Lorentz time dilation (equation 11) with regards to a 20 second
experience would be the result of an initial stimulation of 20 milliseconds (the approximated
duration of the “temporal quantum” of consciousness). This is relevant as we are assuming that
the change in velocity, (of the component innervating system) would be relative to the same
value that produces the dilation associated with the Compton wavelength contraction for the
electron or proton. Therefore, there is a fundamental shift in the process of generation of
consciousness resulting in the alteration in the boundary conditions defined by the Minkowski
equation.
Δ t1 =
(11).
The idea is that, in order to identify the experience we must initiate the activity of the left
hemisphere; there must be a cue reinstatement for equilibrium to return. The resulting effect
would be the reconstitution of the original vectorial representation of the experience. Assuming
that the duration for the re-constitution of the initial activity of each hemisphere is 20 msec, then,
from the derivation of the Lorentz dilation, the resulting lapse in time would be 20 seconds. It is
in this time frame, from the generation of the first 20 second interval of the initial cross-over to
the return to ground state, (another 20 second delay) that would be the correlative time associated
with the transient experience of the sensed presence. By reactivating the appropriate patterns of
neuronal firing, as seen in the laboratory, spatial tracking and labelling required the activation of
various neurons resulting in shifting patterns of activation [22]. Under the notion that in order to
experience we must label (initiation of the left hemisphere) we subsequently reduce activation in
the right hemisphere returning the vector equivalence of the pattern to its initial equilibrium. In
essence, we introduce the reduced-Minkowski constraint within the right hemisphere and reestablish Minkowski space within the left hemisphere. Regardless of the case, the representation
of consciousness is maintained throughout all neuronal activity as defined by the preservation of
global space-time representations.
The former application resembles experimental manipulation. Under these circumstances one
can make connections to changes in the function of regulation and dysequilibrium. Maintaining
normal function would require a constant strain on each independent hemisphere. Unique
associative functions that require global synchronicity produce and regulate the underlying
space-time mechanics which are hemispherically dependent.
To begin to understand the argument of the creation and maintenance of the particular subunit of
consciousness, we must understand the process of memory formation and encoding as therein lay
the relationship between matter and energy. Encoding is of a categorical, left hemispheric nature,
and thus can be defined as a pattern of three dimensional points and varying temporal
components (Δt1, Δt2, Δt3 etc…). Resulting stimulation produces long term generation of memory
isolated as the production of LTP (long term potentiation) and spine (protein) formation. This is
the matter equivalent of brain space obeying the universal dichotomy. Implying the theories of
Einstein and Eddington, which constitutes the operation of the direct proportionality of matter
and energy, (E= mc2) [26, 37, 35, 27], then, if there is matter that is present, energy must follow.
In this context, the energy component, of memory formation, is equivalent to the electric and
magnetic pattern of the action potentials that were synonymous with the formation of the matter
component (same pattern). The physical interaction of the electromagnetic component between
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
438
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
the patterns of spine growth, along with the re-entrant process governing the electric circuits of
the brain, would maintain the electromagnetic field as it remains in the space and is
representative of consciousness (energy) [31].
Consequently, understanding Faraday induction, as well as spontaneous dissipation of the
electromagnetic field, then we produce the contingencies to cause a change in time. By this
implication the process aforementioned must be stored in a quasi-physical manner. The latter
manner will result in the manifestation of the holographic storage of the initial electromagnetic
and equivalent spine growth pattern. The pattern of storage would reduce Δx and Δt in a way that
Minkowski space would, consequently, be reduced to two-dimensional space. This reduction can
be maintained as the definition, if the time component of storage is imaginary, as described by
Hawkins with regards to reduction of the Big Bang, under the condition that the real-time
component and the imaginary time component still adhere to Simultaneity.
Retrieval however, would be the result of a two-dimensional system whereby, the act of
retrieval is associated with the constant flux relationship between the virtual and real spaces,
acting much like the Casimir condition. Retrieval would occur such that both real and virtual
representations exist in the same space, in proximity, and by which there is a constant zwitter
between both virtual space-time and real space-time. It is in this sense that the pattern of
induction is always available and can always be accessed without altering the confines of
reduced-Minkowski space.
The argument is in accordance with Di Biase who suggested that memories and consciousness
would be represented within, in addition to synaptic patterns, the holographic field that surrounds
them as indicative of the simultaneity argument [6]. As well, the concept of virtual or
holographic arrangement of consciousness patterns satisfies the condition that, defined by
Persinger, the holographic condition must satisfy the notion that the functional unit and whole
should share one identity. By manipulation of theory it is apparent that the adherence to the
notion of representation is met by satisfying not one, but two conditions of identity congruent
with space and the subjective value of time. This underlying synaptic function would maintain
consistent genesis of Minkowski and reduced-Minkowski correlates of consciousness. By
extension, normal function within brain-space maintains the underlying physical consequences
of consciousness.
4. Consciousness as Physical and Measureable Processes
This next section is dedicated to the equivalence of consciousness as a measurable quantity. The
quantal measure of consciousness is the output function of the right hemisphere or essentially, by
definition, the lack of the Δx and Δt within the boundaries of Minkowski space. One may ask,
“how is this possible?” to which one would argue that the equivalent energy associated with the
release of biophotons from the right hemisphere accounts for the Δx and Δt components which is
a quantifiable but indirect measure of consciousness. Physical constraints that maintain reducedMinkowski equilibrium would contain all the necessary information associated with
consciousness. Possible interface mechanisms by which equilibrium is maintained are explored
as correlative measures to consciousness the largest contribution arises from biophotogenesis.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
439
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
Bokkon had theorized the presence of these photons and had associated them with the processes
within the brain that was the content of conscious experiences. Dreams and wakefulness may
actually be derived from organized matrices of these photons [2]. Dotta has supported this
argument and has provided proof that photon emission from the human brain, particularly over
the right hemisphere, is associated with shifts in qualitative thinking. The photons are measured
using photomultiplier tubes [20,25]. Under the presumption that the electromagnetic wave is a
consequence by a moving nonzero mass containing particle then we can stimulate the
materialization of photons as per the arguments of Bokkon and Dotta.
The notion that the generation of these particular packets of energy was originally denoted by Tu
et al [21] as describing the nonzero mass, for allowing a third type of polarization in which, in
addition to the classic perpendicular orientations of the magnetic and electric field components
of the electromagnetic wave with respect to its direction of movement, there would be the
emergence of a longitudinal photon. The emergent properties of the electromagnetic system, as
defined by Tu, are the extension (Bokkon) and the reason for the observed (Dotta) correlative
identity of a measure of consciousness. A supportive argument for the attribution of the theory
of photon-derived consciousness resides in the application. The primary correlate of this
argument is the concept of energy being equated to a speed squared, primarily light, multiplied
by a mass. In general terms, velocity can be described as:
V=
V=
(12)
(13),
The results in the production of Δx and Δt which would constitute the variables that are missing
in reduced Minkowski space. In a classical sense, equation 12 will always equate to a constant
value, under the Eddington-Einstein equation, of roughly 3.0 x108 m/s defined as the constant c.
Consequently, the primary descriptor of a photon, its velocity, can be reduced to be
representative of a single change to position, within a unique spatial axis, and a change in time.
Equating these functions we would associate the values of photon velocity to the missing values
of right hemispheric reduced- Minkowski space. The uniqueness of the photon, regarding its
salience through time, is that it can be representative of any number of states within real-time
simultaneously.
The importance of numbers of states becomes apparent when the equation for entropy, or S=ln g
(number of states) k (Boltzmann constant) and T (cosmic background temperature, i.e., about
4ºK) is applied to the context of photons. Assuming a mass in the order of 1052 kg for the
universe and the upper limit of the rest mass of a photon to be 10-52 kg, there would be 10104
photon equivalents in the universe. The intrinsic entropic energy would be ln10104 or about 239
multiplied by 1.38 ·10-23 JT-1, or, ~1.3·10-20 J. This value is the energy associated with the action
potential of neurons as well as the order of magnitude of the energy emitted as photons inferred
from the Dotta studies.
The working theory is that photons are not subject to boundaries of time and can exist across all
levels of discourse within space-time boundaries. The primary proof for this is the reduction of
the Lorentz equation such that, if the velocity component is equal to c, the resulting solution
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
440
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
would produce a denominator approaching zero. As a result an approaching zero denominator
would generate a value that can approach both positive and negative infinity. An extension of
this idea can be represented as a larger aggregate of entanglement whereby, spatial and temporal
components of interacting photons display a high degree of coherence eliciting temporal and
spatial simultaneity.
A likely aggregate to the effects of entanglement can be displayed with respect to the
photogenesis of a biological longitudinal photon. Physical deviations of activity of an electron,
within the spatial extent of a synapse, restrain the systematic activity. Perturbations of this
isolated and restrained system within the synaptic space, would elicit changes in the surrounding
field leading to electrotonic excitation and generation of a photon. A level of concordance of
biophotogenesis can be modeled by quantum mechanical underpinnings reflecting Feynman's
quantum electrodynamics.
According to Feynman, the symbiotic and dualistic identity of an electron and its counter-part
the photon, through their creation and annihilation mechanisms, can be used to model biophoton
generation. In a system, an energetically modulated electron will shed its excess energy through
the creation of a photon. Comparatively, if a photon can be dissociated from an electron (created)
so elegantly, it can be integrated (annihilated) into an electron exciting it. Ultimately, the nature
of both independent mechanisms (creation and annihilation of a photon) would carry the exact
same information although independent particles are spatially separated [46].
Biophotogenesis requires homogenous integration fo annihilation and pertubative excitation to
occur. Persinger has denoted, through calculation, that the rotation of an electron around its own
axis has a time component of 10-16 seconds [19]. As a result, he also demonstrated that a photon
passing through the neuronal plasma membrane with distance of separation equal to 10-8m would
result in the exact same rotation time or rotation frequency as the electron. Bohm and Hiley
present a supporting argument in which they associate the interaction of the photons within the
cell matrix. The idea is that two coherent light waves or an incoherent and a coherent wave are
penetrating into a bio-crystal (or into a liquid crystal which is similar to the living cell’s matrix).
Light waves can exchange their information in an associational way [8]. If the photon and a
singular electron occupy the same space (membrane space) then the process of entanglement
may arise in such a manner that there is a transfer of information between the two interacting
forms. One of the subset components to the process of entanglement is that if the two interacting
forms undergo the simultaneous representation and occupancy of the same space and time. The
two forms become, essentially, the same. The relative representation of form A is superimposed
onto B and vice-versa. Electron-photon coupling via synaptic entanglement maintains reducedMinkowski function on a more fundamental level as compared to biological function. Phase shift
alterations of the photon within the synaptic confines is the transferant process necessary in order
to maintain space-time reduction. Coupling maintains a dynamic equilibrium that is required for
two-dimensional reduction, yet it is not the only manner to establish homeostasis.
Recent literature has discussed the potential that the basis of information reflects the spin state of
the electron and information is represented in the phase-shift velocities of the photon [3]. The
transference of information is a situation that can, by sheer volume of electrons and photons
confined to a particular space i.e. brain space, encourage the likelihood of the occurrence of the
event. Within each synapse the condition arises, the Casimir effect, such that alternative
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
441
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
transference hypothesis can occur. The Casimir effect occurs when two non-conductive surfaces
are brought to proximity, with the caveat that the size of the plates are much larger than the
separation between them. If these conditions are met a phenomenon arises by which a force, of
quantal proportions, is generated.
If there is any disturbance or perturbation within the generated field, the effect from the Casimir
paradigm would result in spontaneous manifestations of real particles from virtual ones [32].
Addition of electrons having relative motion, will disrupt the quantum flux between the plates,
either through transmitter release or electrical conduction, creating the necessary conditions for
spontaneous matter aggregation. Subsequent change in angular frequency of the quantum spin of
the electron prodces its own electromagnetic dipole resulting in interactions that will cause a
disturbance within the Casimir field. The change in field parameters would result in the
instantaneous manifestation of an energy equivalent particle that is based entirely upon the
rotation, and energetic components, of the electron. Due to its reduced mass and equivalent
angular frequency, one of the products of disrupting the Casimir field would be the generation of
photons within the synaptic space. When this occurs then the information that is carried or
represented within the spin state of the electron will be completely transferred or copied to the
photon and thus represented within is summated phase shift velocities representing a sum of Δxs
and Δts. Indicatively, the two processes may produce the opportunity for reception and
integration of information from external non-biological sources of energy.
The interaction at this point would be reduced such that the potential for the formation of the
Bose-Einstein condensate produces the lowest quantum energy state [33]. The greater the
organization, the more matter. More generated matter of a particle the greater the entropic
complexities. Matter is a highly organized state to which manifestation produces a negative
selection pressure resulting in shifts in the entropic equilibrium. In order to maintain chaos we
reduce the mass as much as possible in order to minimize the potential shifts in entropy from its
equilibrium. By the definition of the formation of the Bose-Einstein condensate, we reduce the
negative selection against entropy and produce the lowest quantum energy state. Thus, a
universal favouring occurs for the aggregation of photons.
The complexity does not rest in the rest mass of the photon but, the energetic equivalent to
matter. The summation of phase shift frequencies within the waveform is representative of a
lower state of organization and it is thus favoured. The operator defining the confines of the
spatial locality of the wave function of the traveling and interacting particles (defined as
would represent reduced-Minkowski space constriants for the defining spatial orientation of the
electron. Conversely the photon spatial confines would be reflective of the boundaries defining
Hilbert space [39,40]. The intercalation of these two space-boundaries is reflective of the
macrocosmic and microcosmic reflection of function and representation. Consequently the
interaction between a single electron and an aggregate of numerous photons would also be proof
for the notion of Σ n =n, one of the defining conditions for the generation and maintenance of the
holographic model.
The flicker of the non-local electron’s energy, as it passes through the membrane synapse under
the influence of the Casimir effect, would react in such a manner that the change in the field
energy results in the perturbation in the Casimir field. Under the reactive conditions, the Casimir
effect will allow for the generation of real particle (k) from the imaginary particle ik such that the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
442
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
Bose-Einstein condensate results in the production of a non-local, instantaneous photon which
satisfies the unity of all governing quantum mechanics of the interacting electron. This would
set-up the condition for the exchange of information between the electron and the photon which
may undergo the integration into the cortex or voided from the locale and represented elsewhere
in space. Minkowski space reduction of Δx3 and c2Δt2 is the simplistic representation and
transference of the energy and waveform description of the resultant photon. Measuring
consciousness would be as simple as measuring the intensity of biophoton production. A single
caveat remains; the information would reside in the combinatorial patterns of photonic phase-sift
velocities.
Acknowledgements
Thanks to Dr. M. A. Persinger, Full Professor in the Behavioural Neuroscience, Biomolecular
Sciences and Human Studies Programs for suggestions and the entropy application.
References
1) Persinger, M and Koren S. A theory of Neurophysics and Quantum Neuroscience:
Implications for brain function and limits of consciousness. Neuroscience. 2007. 117:157-175.
2) Bokkon, I. Dreams and Neuroholography: An interdisciplinary interpretation of development
of homeotherm state in evolution. Sleep and Hypnosis. 2005, 7:2. 61-76.
3) Huping Hu and Maoxin Wu. Thinking Outside the box: The essence and implications of
quantum entanglement and the story of spin-mediated consciousness theory. NeuroQuantology.
2006, 1. 5-16
4) Persinger, Michael and Lavallee, Christina. Theoretical and experimental evidence of
macroscopic entanglement between human brain activity and photon emissions: Implications for
quantum consciousness and future applications. Journal of Consciousness Exploration and
Research. 2010, 1. 785-807.
5) A.U. De and Dhananjay Pal. Consciousness Model: Significance of thought-carrying
particles and thought-retaining particles in quantum measurement as well as cognitive problem.
NeuroQuantology. 2005, 2. 111-118.
6) Di Biase, Francisco. Quantum-Holograpic informational consciousness. NeuroQuantology.
2009, 7. 657-664.
7) Bohm D. Wholeness and the Implicate Order. Routledge, New York, 1983.
8) Bohm D and Hiley B.J. The Undivided Universe. London: Routledge. 1993
9) Pribram K. (Ed). Rethinking Neural Networks: Quantum Fields and Biological Data.
Hillsdale: Lawrence Erlbaum Associates. 1993
10) Pribram K. Languages of the Brain. Monterey, Calif., Wadsworth Publishing. 1977.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
443
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
11) Persinger M. A. and Koren S. A. Quantitative Discrepancy in cerebral hemispheric
temperature associated with “Two Consciousness” is predicted by NeuroQuantum relations.
NeuroQuantology, 2008; 4: 369-378.
12) MacFadden, Johnjoe. The Conscious Electromagnetic information (Cemi) Field Theory: The
hard problem made easy? Consciousness. 2002, 9; 45-60.
13) MacFadden, Johnjoe. Conscious Electromagnetic Theory. NeuroQuantology. 2007; 3: 262270.
14) Pockett, Susan. Difficulties with the Electromagnetic Field theory of consciousness: An
update. NeuroQuantology 2007; 3:271-275.
15) Persinger, M.A. and Christina Lavallee. The Σn= n Concept and the Quantitative Support for
the Cerebral–Holographic and Electromagnetic Configuration of Consciousness. Journal of
Consciousness Studies. 2012; 19, in press.
16) Pockett, Susan, et al. A possible physiological basis for the discontinuity of consciousness.
Frontiers 2011; 2:1-9.
17) Williams, Danny.
The process of thought, Neurological Completion, and the
Electromagnetic dynamics of the mind/brain relationships. NeuroQuantology. 2007; 3:316-321.
18) Koening, T., E. Roy John et al. Millisecond by Millisecond, Year by Year: Normative EEG
microstates and developmental stages. NeuroImage 2002; 16:41-48.
19) Persinger, Koren and Lafreniere. A NeuroQuantologic approach to how human thought
might affect the universe. NeuroQuantology 2008; 6: 262-271.
20) Dotta, B.T., Saroka, K. S. and Persinger, M.A. Enhanced photon emission from the right but
not the left side of the head while imagining light in the dark: Possible support for the Bokkon
biophoton hypothesis. Neuroscience Letters. 2012; 513: 151-154.
21) Tu, L.C., Luo, J., Gilles, G.T. The mass of the photon. Reports on Progress in Physics,
2005;68:77-130
22) Persinger M. A., Saroka K.S., Koren S.A. and St-Pierre L. S. The electromagnetic induction
of mystical and altered states within the laboratory. Journal of Consciousness Exploration and
Research. 2010;1; 808-830.
23) Persinger, M.A (1993). Vectorial cerebral hemisphericity as differential sources for the
sensed presence, mystical experiences and religious conversions. Psychological Reports, 76,
915-930
24) Persinger M.A (2010). 10-20J as a Neuromolecular Quantum in medicinal chemistry: An
alternative approach to myriad molecular pathways? Current Medicinal Chemistry, 137 (1), 516.
25) Dotta B.T and Persinger M.A. Dreams, Time distortion and the experience of future events:
A relativistic, Neuroquantal perspective. Sleep and Hypnosis, 11:2, 29-39, 2009
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
444
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
26) Einstein, A. 1906: Trotzdem die einfachen formalen Betrachtungen, die zum Nachweis
dieser Behauptung durchgeführt werden müssen, in der Hauptsache bereits in einer Arbeit von
H. Poincaré enthalten sind2, werde ich mich doch der Übersichtlichkeit halber nicht auf jene
Arbeit stützen.
27) Einstein A. The collected papers of Albert Einstein: The Swiss Years, Writting, 1900-1909.
(1989) Princeton NJ: Princeton University Press
28) Eddington A. The Expanding Universe. (1933)London: Cambridge
29) Eddington A. Stellar Movements and the Structure of the Universe. (1914) Macmillan and
Co
30) Eddington A. The philosophy of physical science. (1939) London: Cambridge University
Press
31) Persinger M.A, from a series of class lectures in Memory, Consciousness and Physical
Neuroscience at Laurentian University, February 2012
32) Milton K.A. The Casimir Effect: Physical Manifestations of Zero-Point Energy (2001)
London: World Scientific Publishing Co
33) Pitaevskii L and Stringari S. Bose-Einstein Condensation (2003) New York: Oxford
University Press
34) Minkowski, Hermann (1907/8), "Die Grundgleichungen für die elektromagnetischen
Vorgänge in bewegten Körpern", Nachrichten von der Gesellschaft der Wissenschaften zu
Göttingen, Mathematisch-Physikalische Klasse: 53–111
35) Einstein, A., Lorentz, H. A., Minkowski, H., and Weyl, H. (1923). Arnold Sommerfeld.
ed. The Principle of Relativity.Dover Publications: Mineola, NY. pp. 38-49.
36) Einstein's thought experiment used two light rays starting at both ends of the platform. See:
Einstein A. (1917), Relativity: The Special and General Theory, Springer
37) Einstein, Albert (2009), Relativity - The Special and General Theory, READ BOOKS, pp.
30–33, ISBN 1-444-63762-2, Chapter IX
38) Lorentz, Hendrik Antoon (1895), Versuch einer Theorie der electrischen und optischen
Erscheinungen in bewegten Körpern, Leiden: E.J. Brill
39) Gleason A.M. (1975) Measures on the closed subspaces of a Hilbert space. Dordrecht
Holland: Reidel Publishing
40) Douglas R.G. (1966) On majorization,factorization, and range inclusion of operators on
Hilbert space. Michigan University
41) Pribram K.H. Brain and Perception: Holonomy and Structure in Figural Processing
(1991)Hillsdale NJ: Lawrence Erlbaum and Associates
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
445
Journal of Consciousness Exploration & Research| April 2013 | Volume 4 | Issue 4 | pp. 427-445
Carniello, T. N., Minkowski Space & Consciousness
42) Pribram K.H. The holographic hypothesis of memory structure in brain function and
perception. Contemporary. 1974 San Francisco: Freeman and Associates
43) Schrodinger E. Discussion of Probability Relations between Separated Systems. Cambridge
philosophical 1935; 31:555-563
44) Schrodinger E. (1950) Space-Time Structure. Cambridge UK:The press syndicate of
University of Cambridge
45) Persinger, M. A. Solutions for real values in Minkowski four-dimensional space may link
macro- and micro-quantum processes in the brain. Neuroscience and Biobehavioral Reviews.
2012; 36: 2334-2338.
46) Feynman, R.P. Mathematical Formulation of the Quantum Theory of Electromagnetic
Interaction. (1950) Phys. Rev. Lett. 80, 440-457.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
1066
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Review Article
On the Natures of Quantum Gravity & Graviton
Huping Hu* & Maoxin Wu
ABSTRACT
The natures of quantum gravity and graviton are reviewed and explored from the nonmainstream perspectives. It turns out that quantum gravity is likely manifestation of quantum
entanglement and mediated by wave-functions of elementary particles as nonlocal objects. Thus,
each elementary particle has its corresponding gravitons comprised of its external and internal
wave-functions as nonlocal objects. This new understanding allows one to reconcile quantum
mechanics with general relativity and explain dark matter and dark energy as nonlocal effects on
the cosmic scales. To make the transition from quantum gravity to general relativity, it is
theorized that: (1) Ricci scalar R and metric tensor g are originated from and determined by the
collective internal and external wave functions of the matter present; (2) in the absence of
nonlocal effect of remote matter through quantum entanglement, R and g are only correlated to
momentum-energy tensor of the local matter; (3) in the presence of nonlocal effect of remote
matter through quantum entanglement, R and g are also influenced by the nonlocal effect of the
remote matter currently interpreted (or seen) as dark matter and/or dark energy. Some of the
important consequences of this theory are the following: (1) gravitational fields (gravitons as
nonlocal objects comprised of internal and external wave functions) may not carry localized or
directly detectable momentum and energy; and (2) there may be no gravitational wave since
gravity is nonlocal and instantaneous.
Key Words: quantum gravity, graviton, quantum entanglement, wave function, external,
internal, nonlocal object, dark matter, dark energy.
1. Introduction
Quantum gravity seeks description of gravity based on the principles of quantum mechanics in
order to reconcile quantum theory with general relativity and build a theory of everything.
However, mainstream approaches seem to be inadequate for various reasons [see, e.g., 1-2]. Here
we review the authors’ own alternative approaches and progress over the last several years [3-6]
and explore new approaches to reconcile quantum gravity with general relativity.
2. The Origin of Gravity [3]
In Ref. [3], the ontological origin of gravity was explored by thinking outside the mainstream
notions of quantum gravity. It was argued that gravity originates from prespacetime, is the
Correspondence: Huping Hu, Ph.D., J.D., QuantumDream Inc., P. O. Box 267, Stony Brook,, NY 11790.
E-mail: hupinghu@quantumbrain.org
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1067
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
manifestation of quantum entanglement, and implies genuine instantaneous interconnectedness
of all matters in the universe. That is, the principle of non-local action is advocated. This view is
a reductionist expression of Newton’s instantaneous universal gravity and Mach’s Principle.
Ref.[3] is an extension of the authors’ earlier papers advocating a holistic and unified theme of
reality in which spin is the primordial self-referential process driving quantum mechanics,
spacetime dynamics and consciousness [see, e.g., 7]. The connection between quantum
entanglement and Newton’s instantaneous universal gravity and Mach’s Principle is natural.
Microscopically gravity is assumed to be fable and negligible and macroscopically it is
ubiquitous and pervasive. It seems to penetrate everything and cannot be shielded. However,
there is no consensus as to its cause despite of the efforts of many people. Presumably, this status
of affair is due to the lack of any experimental guidance. There are many general and technical
papers written on the subject. The authors’ propositions were and still are the following [3]:
1) Gravity originates from the primordial spin processes in non-spatial and non-temporal
prespacetime and is the macroscopic manifestation of quantum entanglement.
2) Thus, gravity is nonlocal and instantaneous, as Newton reluctantly assumed and Mach
suggested. It implies that all matters in the universe are instantaneously interconnected
and many anomalous effects in astronomy such as red shift, dark energy, dark mass and
Pioneer effect may be resolved from this perspective.
3) Potentially, gravity can be harnessed, tamed and developed into revolutionary
technologies to serve the mankind in many areas such as instantaneous communication,
spacetime engineering and space travel.
The idea of instantaneous gravity is nothing new. Newton’s law of universal gravitation implies
instantaneous “action at a distance” which he felt deeply uncomfortable with, but Newton was
not able to find a cause of gravity [8]. Later Mach suggested that "[t]he investigator must feel the
need of... knowledge of the immediate connections, say, of the masses of the universe…[t]here
will hover before him as an ideal insight into the principles of the whole matter, from which
accelerated and inertial motions will result in the same way" [9]. Ontologically, Mach’s above
suggestion is a form of holism and implies that gravity is relational and instantaneous.
It was Einstein who fulfilled Mach’s “relational” suggestion of gravity by discovering general
relativity [10]. He also coined the phrase Mach’s principle. However, was such fulfillment at the
sacrifice of Mach’s “immediate connections” by assuming that the speed of gravity is the speed
of light? Einstein’s general relativity is now the mainstream theory of gravity, but it is in
apparent conflict with quantum mechanics – the most successful theory of the 20th century which
Einstein himself helped to build. Einstein called quantum entanglement “spooky action at a
distance” in the famous EPR debate [11]. However, it seems that Einstein’s camp is on the
losing side of the debate today as many recent experiments have shown that quantum
entanglement is physically real [see, e.g., 12]. It was argued in [3] that a theory of gravity, which
includes general relativity as an approximation, be built from the properties of quantum
entanglement.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1068
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Ontologically, we have argued in [7] that quantum entanglement arises from the primordial selfreferential spin processes which are envisioned by us as the driving force behind quantum
mechanics, spacetime dynamics and consciousness.
First, spin is deeply connected to the microscopic structure of spacetime as reflected by the Dirac
equation for Dirac spinor field representing the fermions [13]. Indeed, Penrose had considered
early on that spin might be more fundamental than spacetime and invented spinor and twistor
algebras for a combinatorial description of spacetime geometry [14-15]. Bohm and Hiley
generalized the twistor idea to Clifford algebra as a possible basis for describing Bohm’s
“implicit order” [16]. Recently various spin foams have been formulated as extensions to
Penrose’s spin networks for the purpose of constructing a consistent theory of quantum gravity
[see, e.g., 17]. Many others have also study the nature of spin from both classical and quantummechanical perspectives. For example, Newman showed that spin might have a classical
geometric origin. By treating the real Maxwell Field and real linearized Einstein equations as
being embedded in complex Minkowski space, he was able to interpret spin-angular momentum
as arising from a charge and “mass monopole” source moving along a complex world line [18].
Second, Sidharth discussed the nature of spin within the context of quantized fractal spacetime
and showed that spin is symptomatic of the non-commutative geometry of space-time at the
Compton scale of a fermion and the three dimensionality of the space result from the spinorial
behavior of fermions [19-20]. He showed that mathematically an imaginary shift of the
spacetime coordinate in the Compton scale of a fermion introduces spin ½ into general relativity
and curvature to the fermion theory [19]. The reason why an imaginary shift is associated with
spin is to be found in the quantum mechanical zitterbewegung within the Compton scale and the
consequent quantized fractal space-time [id.]. Further, according to Sidharth, a fermion is like a
Kerr-Newman black hole within the Compton scale of which causality and locality fails [19-20].
Third, Burinskii showed that in spite of the weakness of the local gravitational field, the gravity
for a spin ½ fermion as derived using the classical Kerr-Newman Kerr solution (Kerr’s Gravity)
has very strong stringy, topological and non-local action on the Compton distances of the
fermion, polarizing the space-time and electromagnetic field and controlling the basic quantum
properties of the fermions [21]. Thus, Kerr’s Gravity may suggest possibly deep connections
between the mass-energy relationship of matter and the quantum properties of particles [id.].
Fourth, Makhlin showed that the axial field component in the spin connections of the Dirac
spinor field provides an effective mechanism of auto-localization of the Dirac spinor field into
compact objects, presumably representing the fermions, and condition that the compact objects
are stable leads to the Einstein's field equations [22]. He suggested that the physical origin of the
macroscopic forces of gravity between any two bodies is a trend of the global Dirac spinor field
to concentrate around the microscopic domains where this field happens to be extremely
localized [id.]. He further suggested that the long distance effect of the axial field is
indistinguishable from the Newton's gravity which according to him reveals the microscopic
nature of gravity and the origin of the gravitational mass [id.].
We emphasized in [3] that prespacetime means a non-spatial and non-temporal domain but it is
not associated with an extra-dimension in the usual sense since there is no distance or time in
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1069
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
such domain. So, prespacetime is a holistic domain located outside spacetime but connected
through quantum entanglement to everywhere in spacetime enabling Newton’s instantaneous
universal gravity and Mach’s “immediate connections” [3]. It has similarity to Bohm’s concept
of implicate order and other non-local hidden variable theories [see, e.g., 23]. The said
prespacetime is a “world” beyond Einstein’s relativistic world through which quantum
entanglement can be used to produce instantaneous signaling as we have demonstrated
experimentally [4].
In short, it was argued in [3] that it is natural to link gravity to the property of quantum
entanglement; and, indeed, doing so will not only provide a cause to Newton’s instantaneous
universal gravity but also realize Mach’s “immediate connections’ discussed above. Therefore, it
was proposed in [3] that gravity originates from the primordial spin processes in non-spatial and
non-temporal prespacetime and is the macroscopic manifestation of quantum entanglement.
Finally, it was argued in [3] that the principle of science dictates that a hypothesis/proposition
should only achieve scientific legitimacy if it is experimentally verified. Thus, we have designed
and carried out experiments to verify these propositions and the results were subsequently
reported in Ref. [4].
3. Experiments Testing Nonlocal Gravitational Effect [4]
In Ref. [4], the experimental findings of non-local chemical, thermal and gravitational effects in
simple physical systems, such as reservoirs of water quantum-entangled with water being
manipulated in a remote reservoir, were reported. With the aids of high-precision instruments, it
was found that the pH value, temperature and gravity of a liquid such as water in the detecting
reservoirs can be non-locally affected through manipulating water in the remote reservoir. In
particular, the pH value changes in the same direction as that being manipulated; the temperature
can change against that of local environment; and the gravity can change against local gravity
[4]. The motivation for measuring gravity change of one reservoir of water, while manipulating
water in a remote reservoir quantum-entangled with the former, is to investigate whether gravity
is a non-local effect associated with quantum entanglement [3-4].
The successes of the experiments reported in Ref. [4] were achieved with the aids of highprecision analytical instruments. They include an Ohaus Voyager Analytical Balance with
capacity 210g, resolution 0.1mg, repeatability 0.1mg and sensitivity drift 3 PPM/ºC, a Control
Company traceable-calibration digital thermometer with resolution 0.001ºC and repeatability
0.002ºC near 25ºC in liquid such as water (estimated from calibration data provided), and a
Hanna microprocessor pH meter Model 213 with resolution 0.001 and repeatability 0.002. The
other key apparatus is a 25-litre Dewar filled with liquid nitrogen and positioned remotely at a
desired distance which not only provided the drastic changes in the water being manipulated but
also served as a natural Faraday cage blocking any possible electromagnetic influence between
the water being measured and the water being manipulated. Also vital to the success of the
experiments reported in [4] was the stable environment found in an underground room which
shields many external noises such as mechanical vibration, air turbulence and large temperature
change.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1070
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
To conduct the experiments reported in Ref. [4], quantum-entangled stock water in individual
volumes of 500ml or similar quantities was prepared as reported in [24]. For example, in one
procedure 500ml fresh tap water in a closed plastic reservoir was exposed to microwave
radiation in a 1500W microwave oven for 2min and then left in room temperature for 24 hours
before use. In another procedure, 500ml bottled natural water was simply left in room
temperature for at least 30 days before use. It was found previously that the stock water prepared
according to these procedures is quantum-entangled [24].
Figure 1 shows a diagram of the key experimental setup and Figure 1A is a photograph of the
actual key experimental setup except that the 25-litrer Dewar was not located near the
measurements as shown but at a remote location:
Figure1: Illustration of the key experimental setup.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1071
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Figure1A. Photograph of the actual key experimental setup except that the 25-litrer Dewar was not
located near the measurements as shown but at a remote location described in the text.
The above setup included [4]: (1) the analytical balance calibrated internally and stabilized in the
underground room for more than one week before use and a tightly closed plastic first-reservoir
containing 175ml water split from the 500ml stock water which is placed on the wind-shielded
pan of the balance with 1-inch white foam in between as insulation; (2) the digital thermometer
and calibrated pH meter placed into the middle of a glass second-reservoir containing 75ml
water split from the 500ml stock water which is closed to prevent air exchange; and (3) the 25litre Dewar containing 15-25 litres of liquid nitrogen which is located at a distant of 50 feet from
the underground room and a tightly closed plastic third-reservoir containing 250ml water split
from the 500ml stock water to be submerged into the liquid nitrogen in the Dewar at a specified
time.
Experiments with the above setup were carried out as follows [4]: (1) prepare the 500ml
quantum-entangled stock water, divide the same into 175ml, 75ml and 250ml portions and put
them into their respective reservoirs described above; (2) set up the experiment according to
Figure 1 and let the instruments to stabilize for 30min before any measurements is taken; (3)
record for 20min minute-by-minute changes of pH value and temperature of the water in the
first-reservoir and weight of the second-reservoir with water before submerging the third
reservoir into liquid nitrogen; (4) submerge the third-reservoir with water into liquid nitrogen for
15min or another desired length of time and record the instrument readings as before; and (5)
take the third-reservoir out of liquid nitrogen, thaw the same in warm water for 30min or longer
and, at the same time, record the instrument readings as before. Control experiments were
carried out in same steps with nothing done to the water in the third-reservoir.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1072
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Figure 2 shows weight variations of the first-reservation during the three stages of manipulation
of the water in the remote third-reservoir [4]. Before the submersion of the remote third-reservoir
into liquid nitrogen the weight being measured drifted lower very slowly. But almost
immediately after the remote third-reservoir was submerged into liquid nitrogen, during which
the temperature and physical properties of water being manipulated drastically changed, the
weight of the first-reservoir dropped at an increased rate, and after the frozen water was taken
out the liquid nitrogen and thawed in warm water the weight of the same first stopped dropping
and, in some cases, even rose before resuming drifting lower as further discussed below. In
contrast, the control experiments did not show such dynamics. The weight difference from
control in which no freeze-thaw was done at the point of thawing is about 0.25mg. Statistical
analysis performed on data collected after freezing for 10min show that the results are
significantly different under these different treatments/settings.
Figure 2. Weight variations under remote manipulations of water quantum-entangled with
water being weighed. The weight at the starting point is set to zero and the results shown were
obtained from one batch of quantum-entangled water. The weight differences from control in
which no freeze-thaw was done at the point of thawing is about 0.25mg. In some cases, the
weight of the water being weighed not only briefly stop dropping for several minutes but also
rose briefly for several seconds to minutes as shown in Figure2A.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1073
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
As shown in Figure 2A, in some cases, the weight of the water being measured not only stopped
dropping for several minutes but also rose. The signatures of freezing induced weight decreases
and thawing induced weight increases for three different thawing times are very clear.
Figure 2A. Examples of weight variations under remote manipulations of water quantumentangled with water being weighed. The onset of increased weight loss started either at the
time of freezing treatment or slightly later. The signatures of thawing induced weight increases
were clear for the three different thawing times. The distances shown are the respectively
distances of the Dewar to the location of measurement in each experiment.
In addition, Figure 2B shows one example of weight and temperature variations under the same
remote manipulation of water quantum-entangled with water being weighed and measured
respectively. Again, the signatures of freezing and thawing induced weight and temperature
decreases and increases are respectively very clear.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1074
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Figure 2B. One example of weight and temperature variations under the same remote
manipulation of water quantum-entangled with water being weighed and measured respectively.
The onset of increased weight loss started at the time of freezing treatment but the onset of
temperature decrease against environmental temperature started a few minutes later after
freezing treatment started. The signatures of thawing induced weight and temperature increases
were clear. The distance shown is the distance of the Dewar to the location of measurement.
Further, Figure 2C shows another example of weight and temperature variations under another
same remote manipulation in which the Dewar was located about 500 feet away from where the
measurements were taken. The general background trend of decreasing temperature was due to
environmental temperature change. Yet again, the signatures of freezing and thawing induced
weight and temperature variations were respectively are very clear.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1075
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Figure 2C. Second example of weight and temperature variations under another same remote
manipulation of water quantum-entangled with water being weighed and measured respectively.
The general background trend of decreasing temperature was due to environmental temperature
change. The onset of increased weight loss started at the time of freezing treatment but the onset
of increased temperature loss started a few minutes later after freezing treatment started. The
signatures of thawing induced weight increase and slow down of temperature loss were again
clear. The distance shown is the distance of the Dewar to the location of measurement.
As reported in [4], with all experimental setups and their variations described therein, we
observed clear and reproducible non-local effects with the aids of high-precision analytical
instruments and under well-controlled conditions. The physical observables used for measuring
the non-local effects are simple ones which can be measured with high precisions. These effects
are, even under the most stringent statistical analysis, significantly above and beyond what were
noticeable in the control experiments.
Through careful analysis, we have excluded the possibility that the observed weight variation
was a secondary local effect due to heat loss and/or sensitivity drift of balance associated with
temperature change induced by the remote manipulation [4]. First, during the period of remote
manipulation the total temperature change was less than 0.08ºC so the total heat loss for the
175ml water in the first-reservoir is about 60J. In contrast, the weight loss during remote
manipulation was on average about 0.25mg which is 2.25x109J in energy unit. Second, the firstreservoir and the pan of the balance were separated by 1-inch white foam to prevent heat transfer
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1076
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
to the analytic balance. Even in the highly unlikely scenario that this temperature change
somehow affected the overall temperature of the balance, the associated sensitivity drift of the
balance was about 0.03mg which is about 10 times smaller than what’s actually observed. In
addition, Figures 2A, 2B and 2C also show several other signatures of remote freeze-thaw
treatment as the sole cause of the observed weight variations. Therefore, the observed gravity
variation is a genuine and direct non-local effect associated with quantum entanglement.
We chose to use liquid nitrogen in a large Dewar placed at a distant location for manipulating
water in our experiments because it can provide drastic changes in temperature and properties of
water in a very short period of time [4]. Our expectation was that, if the quantum entities inside
the water being measured are able to sense the changes experienced by the quantum entities in
the water being manipulated through quantum entanglement and further utilize the information
associated with the said changes, the chemical, thermal and gravitational properties of the water
might be affected through quantum entanglement mediated non-local processes [See, e.g., 3].
The most logical explanation for these observed non-local effects is that they are the
consequences of non-local processes mediated by quantum entanglement between quantum
entities in the water being measured and the remote water being manipulated [4].
In short, the experiments reported in Ref. [4] shows that the gravity of water in a detecting
reservoir quantum-entangled with water in a remote reservoir can change against the gravity of
its local environment when the latter was remotely manipulated. However, as with many other
experimental findings, independent replications are the key to verify our results. Therefore, we
urge all interested scientists and the like to do their own experiments to verify and extend our
findings. Perhaps the most shocking was the experimental demonstration of Newton's
instantaneous gravity and Mach's instantaneous connection conjecture and the relationship
between gravity and quantum entanglement.
4. The Origin of Dark Matter and Dark Energy [5]
In Ref. [5], the origin of dark matter and dark energy was explored among other topics in light of
the experimental findings reported in [4]. It was suggested that dark matter is the cosmological
manifestation of quantum entanglement but seen as additional gravity caused by invisible matter
under some cosmological conditions [5]. In contrast, it was suggested that dark energy is the
cosmological manifestation of reverse quantum entanglement but seen as anti-gravity caused by
negative pressure on the cosmological scale [5].
5. Quantum Self-Gravity in the Principle of Existence [6]
The authors’ results in Refs [3-5] partly lead to the development of the principle of existence
reported in Ref. [6]. To understand quantum gravity, we should first understand what self-gravity
is in the quantum realm and pre-quantum realm.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1077
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
According to the principle of existence [6], there is no self-gravity before there is any
differentiation of ether in prespacetime. The state of existence is simply ei0=1. Once the initial
phase distinction (yin and yang) is created but before the governing law is born, self-gravity is
embodied in the coupling of e-iM and e+iM in e-iMe+iM=1. After an elementary particle and its
governing are created, self-gravity of the said elementary particle is embodied in its quantum
equation [6].
For example, an electron and its governing law in Dirac form are created according to the
principle of existence [6] as follows (c= ħ=1):
1 e i 0 e i 0 e i 0 e iLiLe iM iM cos L i sin L cos L i sin L e iM iM
m
p m
p ip μ x μ ip μ x μ m 2 p 2 ipμ xμ ipμ xμ E 2 m 2 ip x ip x
i i e
e
e
2
E
E E
E
p2
E
Em p
p Em
1
e
ip x
e
ip x
1
p ip x
E m ip x
e
e
p
Em
E m p ae , e
p ip x
E m ip x
0
e
e
0
ip x
p
Em a e
p
Em
σ p Ae , e
Em
σ p
Em
A e
i,
i,
E m σ p
σ p E m
ip x
ip x
ip x
e,
0
(5.1)
i,
Now, we ask what is quantum self-gravity (or self-quantum-entanglement) in this fundamental
equation? The answer is that it is simply the interaction (relationship) between nonlocal objects
e,- and e,+ respectively as external and internal gravitons (c= ħ=1):
E m e , σ p i , or i t e , m e , iσ i ,
E
m
σ
p
i
,
e
,
i t i , m i , iσ e ,
(5.2)
For another example, a linear photon and its governing law are created according to the principle
of existence [6] as follows (c= ħ=1):
1 e i 0 e i 0 e i 0 e iLiLe iM iM cos L i sin L cos L i sin L e iM iM
p p ip μ x μ ip μ x μ p 2 ip μ x μ ip μ x μ E 2 ip x ip x
i i e
2 e
2e
E E
E
p
E p
p
E
ISSN: 2153-8212
1
e
ip x
e
ip x
1
E ip x p ip x
e
e
p
E
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1078
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
E
E ip x p ip x
e
e
0
p
p
E
E
s p
E
ip x
s p E e
E
s p
ip x
E
iB e
0e,
0 i,-
p ae, e
ai , e
ip x
ip x
0
s p E
0
E iB
is E
i t
E B
0 t
is i t iB
t B E
(5.3)
where the relationship s i is used to derive the last set of equations which together
with E 0 and B 0 are the Maxwell equations in the source-free vacuum.
Now, we ask what is quantum self-gravity (or self-quantum-entanglement) for the linear photon?
The answer is that it is simply the interaction (relationship) between nonlocal objects E (electric
field) and iB (magnetic field on imaginary axis) as external and internal gravitons respectively.
Thus, electromagnetic field is self-quantum-entangled, that is, the quantum self-gravity of
electromagnetic field is the interaction between electric field and magentic field on imaginary
axis through Maxwell equations.
6. Quantum Gravity in the Principle of Existence [6]
In the principle of existence [6], quantum gravity is quantum entanglement (instantaneous
interaction) across external and internal worlds (dual worlds) through prespacetime. Thus, there
are two types of quantum gravity at play according to the principle of existence [6]. One is
quantum self-gravity (self-entanglement) between the external object (external wave function)
and internal object (internal wave function) of an elementary particle described above and the
other is quantum gravity (quantum entanglement) between the external wave function of said
elementary particle and the internal wave function of a second elementary particle or the
collective internal wave functions of a particle assemble [6]. Thus, gravitational fields are just
the collective internal and external wave functions themselves in the principle of existence.
In Ref. [6], three particular forms of gravitational fields were illustrated. One is timeless (zero
energy) external and internal wave functions (self-fields) that play the role of timeless graviton,
that is, they mediate time-independent interactions through space quantum entanglement. The
second is spaceless external and internal wave functions (self-fields) that play the role of
spaceless graviton, that is, they mediate space (distance) independent interactions through proper
time (mass) entanglement. The third is massless external and internal wave functions (self-fields)
that play the role of massless graviton, that is, they mediate mass (proper-time) independent
interactions through massless energy entanglement.
As shown in Ref. [6], timeless quantum entanglement between two entities may account for
Newtonian gravity. Spaceless and/or massless quantum entanglement between two entities may
account for dark matter (Also see [5]). Importantly, gravitational components related to
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1079
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
spinization may account for dark energy [5-6].
When E=0, we have (c= ħ=1) [6]:
m 2 p 2 0 or m 2 p 2 0
(6.1)
One may regard expression (6.1) as a relationship governing the Machian quantum universe in
which the total energy is zero. Classically, this may be seen as: (1) the rest mass m being
comprised of imaginary momentum P=iPi, or (2) momentum P being comprised of imaginary
rest mass m=imi.
As shown in [6], the timeless Matrix Law in Dirac and Weyl form is respectively the following:
m p
(6.2)
p m LM ,e LM ,i L M
p
m
m
LM ,e
p
(6.3)
LM ,i L M
Thus, the equations of the timeless wave functions (self-fields) are respectively as follows:
m
p
p g D ,e e iM
LM ,e
m g D ,i e iM
V D ,e
L M VD 0
LM ,i
V
D ,i
(6.4)
p
m
m gW ,e e iM
LM ,e
p gW ,i e iM
VW ,e
L M VW 0
LM ,i
V
W ,i
(6.5)
and
Equation (6.4) and (6.5) can be respectively rewritten as:
mVD ,e p VD ,i or
mV
p
V
D
,
i
D
,
e
and
p
VD ,e VD ,i
m
p
VD ,i VD ,e
m
(6.6)
p
(6.7)
VW ,e VW ,i
m
p
VW ,i VW ,e
m
To see the coupling of external and internal wave functions (self-fields) in a different perspective
we can rewrite (6.6) and (6.7) respectively as follows:
mVW ,e p VW ,i or
mV
p
V
W ,e
W ,i
mmVD ,eVD ,i p VD ,i p VD ,e
p
V
mV
mV
p
V
D
,
e
D
,
e
D
,
i
D
,
i
(6.8)
and
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1080
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
mmVW ,eVW ,i p VW ,i p VW ,e
p VW ,e mVW ,e mVW ,i p VW ,i
(6.9)
From expression (6.6), we can derive the following:
m p V
2
2
D ,e
0 or
m V
2
2
D ,e
0
(6.10)
Equation (6.10) has radial solution in the form of Yukawa potential:
V D ,e ( r )
(6.11)
1 mr
e
4r
So in expression (6.4), M=-imr, that is, momentum is comprised of imaginary mass. The external
timeless self-field in expression (6.11) has the form of Newton gravitational or Coulomb electric
potential at large distance r→∞. We have from expression (6.6):
VD ,i
(6.12)
p
p 1 mr
1 mr
V D ,e
e
i
e
m
m 4r
4r
where we have utilized the following (for reasons to be discussed elsewhere):
p V D ,e 2
(6.13)
1 mr
1 mr
e im
e
4r
4r
The complete radial solution of equation (6.4) is then:
1 mr
(6.14)
e
V
D ,e
1 1 mr
4
r
N
N
VD ( r )
e
i 1 e mr
i 4r
VD ,i
4r
where N is a normalization factor. Indeed, expression (6.7) can have same radial solution as
expression (6.6):
1 mr
(6.15)
e
VW ,e
1 1 mr
4
r
N
N
VW ( r )
e
i 1 e mr
i 4r
VW ,i
4r
If we assume that the internal self-field VD,i (which is self-coupled to its external self-field VD,e
through expression (6.4) or (6.8) also couples through timeless quantum entanglement with the
external wave function ψe of another entity of test mass mt (which is also self-coupled to its
internal wave function ψi ) as, for example:
imVD ,i mt e imi
(6.16)
1 mr
m
e mt e G e mr mt e
4r
r
where iκ is a coupling constant and G=κ/4π is Newton’s Gravitational Constant, we have
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1081
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
gravitational potential at large distance r→∞ as:
V g G
(6.17)
m
r
When |p|=0, we have(c= ħ=1) [6]:
E 2 m2 0
(6.18)
One may regard expression (6.18) as a relationship governing a spaceless quantum universe.
Classically, this may be seen as the rest mass m being comprised of time momentum (energy E).
As shown in § 3, the spaceless Matrix Law in Dirac and Weyl form is respectively the following:
E m
0
0
LM , e
E m
LM , i L M
(6.19)
E m
LM , e
m E
LM ,i L M
(6.20)
and
and the equation of spaceless wave functions (self- fields) are respectively the follows:
0 g D ,e e imt
E m
LM ,e
E m g D ,i e imt
0
V D ,e
L M VD 0
LM ,i
VD ,i
(6.21)
E m gW ,e e imt
LM ,e
imt
m E gW ,i e
VW ,e
L M VW 0
LM ,i
V
W
,
i
(6.22)
and
The external and internal (spaceless) wave functions VD,e and VD,i in equation (6.21) are
decoupled from each other, but those in equation (6.22),VW,e and VW,i, are coupled to each other:
EVD ,e mVD ,e but EVW ,e mVW ,i
EVW ,i mVW ,e
EVD ,i mVD ,i
(6.23)
It can be easily verified that the solutions to equation (6.21) are in forms of:
1e imt
V D ,e
1
N imt N e imt
VD
0
VD ,i
0e
(6.24)
0e imt
V D ,e
0
N imt N e imt
VD
1
VD ,i
1e
(6.25)
or
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1082
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
but the solutions to equation (6.22) are in the forms of:
1e imt
VW ,e
1
N imt N e imt
VW
1
VW ,i
1e
(6.26)
1e imt
VW ,e
1
N imt N e imt
VW
1
VW ,i
1e
(6.27)
or
As illustrated in [6], dark matter may be a manifestation of this non-Newtonian gravity or, at
least, may have a contribution from spaceless quantum entanglement.
For simplicity, two masses m1+mp and m2 respectively located at space points 1 and 2 were
considered in [6]. Their respective spaceless wave functions can be written in Weyl form as
follows:
g1W , e e i m1 m p t and
g 2W , e e im 2 t
V1W
V2W
i m1 m p t
im 2 t
g
g
e
2W , i
1W , i e
(6.28)
which form product stateV1W V2W . After mp leaves V1W+ as an emitted particle and get absorbed
by V2W-, one may has the following two additional spaceless wave functions in Weyl form:
g 2W , e e i m 2 m p t
g1W , e e im1t and
V1W
V2W
im1t
i m 2 m p t
g1W , i e
g 2W , i e
(6.29)
which form product stateV1W V2W . The final spaceless quantum state may be written as follows:
(6.30)
1
1
V1W V2W V1W V2W 1 2 1 2
2
2
In this joint spaceless wavefunction, m1 and m2 are quantum entangled due to interaction with
and through mp. It was suggested in [6] that this space (distance)-independent quantum
entanglement (non-Newtonian gravity) between two entities is the cause of dark matter.
V
When m=0, we have (c= ħ=1) [6]:
E 2 p2 0
(6.31)
We can regard expression (31) as a relationship governing the massless quantum universe in
which the total rest mass (proper time) is zero. Classically, this may be seen as energy E being
comprised of momentum p. As shown in [6], the massless Matrix Law in Dirac and Weyl form is
respectively the following:
E p
(6.32)
LM ,e LM ,i L M
p
E
and
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1083
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
E p
0
0
LM ,e
E p
(6.33)
LM ,i L M
and the equations of massless wave functions (self-fields) are respectively the following:
E
p
p g D ,e e iM
LM ,e
E g D ,i e iM
V D ,e
L M VD 0
LM ,i
VD ,i
(6.34)
E p
0
0 gW ,e e iM
LM ,e
E p gW ,i e iM
VW ,e
L M VW 0
LM ,i
VW ,i
(6.35)
and
Equations (6.34) and (6.35) have plane-wave solutions. The external and internal (masssless)
wave functions VD,e and VD,i in equation (6.34) are coupled with each other, but those in
equations (6.35),VW,e and VW,i, are decoupled from each other:
EV D ,e p VD ,i but EVW ,e p VW ,e
EV
p
V
D ,e
D ,i
EVW ,i p VW ,i
(6.36)
For eigenstate of E and |p|, the solutions to equation (6.34) are in the forms of:
or
1e i (t k x )
V D ,e
1
N p i (t k x ) N e i (t k x )
VD
e
1
VD ,i
E
(6.37)
p i (t k x )
V D ,e
1 i (t k x )
e
VD
N
N
e
E
i (t k x )
1
VD ,i
1e
(6.38)
but the solutions to equation (6.35) are in the forms of:
1e i (t k x )
VW ,e
1
N i (t k x ) N e i (t k x )
VW
0
Vw,i
0e
(39)
0e i (t k x )
VW ,e
0
N i (t k x ) N e i (t k x )
VW
1
VW ,i
1e
(40)
or
Equations (6.34) and (6.35) describe the self-interaction of external and internal massless and
spinless wave functions (self-fields). We can build a quantum-entangled state of two massless
and spinless entities similar to that of two spaceless entities. It is suggested that this rest mass-
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1084
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
independent quantum entanglement (non-Newtonian gravity) between two massless entities may
also contribute to the cause of dark matter [5-6].
7. Transition from Quantum Gravity to General Relativity
To make the transition from quantum gravity to general relativity, it is theorized that: (1) Ricci
scalar R and metric tensor g are originated from and determined by the collective internal and
external wave functions of the matter present; (2) in the absence of nonlocal effect of remote
matter through quantum entanglement, R and g are only correlated to momentum-energy tensor
of the local matter; (3) in the presence of nonlocal effect of remote matter through quantum
entanglement, R and g are also influenced by the nonlocal effect of the remote matter currently
interpreted (or seen) as dark matter and/or dark energy.
Some of the important consequences of the above theory are the following: (1) gravitational
fields (gravitons as nonlocal objects comprised of internal and external wave functions) may not
carry localized or directly detectable momentum and energy; (2) there may be no gravitational
wave since gravity is nonlocal and instantaneous.
General Relativity of Electromagnetic Field (Photon)
In the principle of existence [6], quantum self-gravity of photon is embodied in its quantum
equation in which external wave-function E and internal wave-function iB are self-entangled
through self-interaction/gravity (c= ħ=1):
is E
s p E
i
E B
E
0 t
0 t
E iB
s p
is i t iB
t B E
(7.1)
which together with E 0 and B 0 are the Maxwell equations in the source-free
vacuum. The latter in turn can be written in the co-variant form:
(7.2)
where
(
)
(7.3)
The principle of existence [6] treats wave functions as real entities instead of mathematical
symbolism for calculating probability only. In the case of electric field E and magnetic field on
the imaginary axis iB, this is certainly true.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1085
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
Using the action principle, we will now derive the well-known equations of motion for
electromagnetic field (photons) under the new understandings of gravity and self-gravity
respectively (c=G=0=1):
The total action can be written as (this is well known):
∫ √
∫
√
(7.4)
Varying metric tensor g , we have:
) (
∫ (
∫(
) (
)
√
)
√
(7.5)
Thus, we get the following well known equation of motion for electromagnetic field under
gravity:
(
)
(7.6)
Putting back c, G and 0, we have:
(
)
(7.7)
Varying electromagnetic four-potential A , we have:
∫
√
∫
(
√
)(
)
∫
(
)(
)√
(7.8)
Thus, we get the following well-known Maxwell equations (7.2) of motion for electromagnetic
field under the new understanding of self-gravity in the source-free vacuum:
Putting back c and 0, we have:
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1086
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
(7.9)
where
(
)
(7.10)
Due to a recent result by Loinger and Marsico [25], it turns out that the above equation (7.6) or
(7.7) for describing the gravitational field of electromagnetic field also implies Maxwell
equations (7.1) or (7.2) which describe self-gravity (self-interactions) of E and iB.
Therefore, in the case of electromagnetic field (photons), the unification of quantum self-gravity,
quantum gravity and general relativity is successfully and consistently realized under the new
understandings of gravity and self-gravity. In this case, the Ricci scalar R and metric tensor g
are originated from and determined by the collective internal and external wave functions E and
iB of the electromagnetic fields.
General Relativity of Fermion, Massive Boson, Dark Matter and Dark Energy
Transitions from quantum gravity and self-gravity of fermions and massive bosons to general
relativity, quantifications of dark matter and dark energy, and possible connections to other
scholarly work are currently under investigations and formulations. New results will be reported
in due course.
8. Some Related Work by Other Authors
Besides other authors’ work already referenced in this article, we briefly list here some more
related works by other authors. However, the list is undoubtedly incomplete.
Pope and Osborne [26] argued for the instantaneousness of gravity. Gibbs [27] explored quantum
gravity based on the principle of event-symmetric space-time. Arcos and Pereira [28] attempted
to connect Kerr-Newman solution to Dirac particle. Pitkanen [29] explored a TGD-based theory
of gravitation. Fiscaletti and Amrit [30] explored gravitation in a timeless quantum space.
Kyriakos [31] explored a Lorentz-invariant theory of gravitation based on the nonlinear theory of
elementary particles. Kaufman [32] explored gravitation based on relational-matrix model.
Crowell [33] explored gravitation based on unitarity, locality and spacetime geometry. Campbell
[34] explored gravitation based on cosmic order.
In a series of articles stretching more than a decade, Loinger [35] argued against the existence of
gravitational wave and the common explanation of binary pulsar PSR1913+16 (Hulse–Taylor
binary pulsar)’s decaying orbit. Dalton [36] showed that Einstein’s gravitational field has zero
energy, momentum, and stress. Recently, Pusey et al [37] have argued that quantum state is
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1087
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
physically real and Hehl [38] argued that nonlocal gravity simulates dark matter both of which
support the herein authors’ earlier propositions [3-6]. Kowall [39] explored quantum gravity
based on the holographic principle.
9. Conclusions
In this article, the natures of quantum gravity and graviton have been reviewed and explored
from the non-mainstream perspectives. It turns out that quantum gravity is likely manifestation
of quantum entanglement and mediated by wave-functions of elementary particles as nonlocal
objects. Thus, each elementary particle has its corresponding gravitons comprised of its external
and internal wave-functions as nonlocal objects. This new understanding allows one to reconcile
quantum mechanics with general relativity and explain dark matter and dark energy as nonlocal
effects on the cosmic scales.
To make the transition from quantum gravity to general relativity, it is theorized that: (1) Ricci
scalar R and metric tensor g are originated from and determined by the collective internal and
external wave functions of the matter present; (2) in the absence of nonlocal effect of remote
matter through quantum entanglement, R and g are only correlated to momentum-energy tensor
of the local matter; (3) in the presence of nonlocal effect of remote matter through quantum
entanglement, R and g are also influenced by the nonlocal effect of the remote matter currently
interpreted or seen as dark matter and/or dark energy.
Some of the important consequences of the above theory are the following: (1) gravitational
fields (gravitons as nonlocal objects comprised of internal and external wave functions) may not
carry localized or directly detectable momentum and energy; and (2) there may be no
gravitational wave since gravity is nonlocal and instantaneous.
References
1. Carlip, S. (2001), Quantum Gravity: a Progress Report. http://arxiv.org/abs/gr-qc/0108040v1
2. Carlip, S. (2008), Is Quantum Gravity Necessary? http://arxiv.org/abs/0803.3456v1
3. Hu, H. & Wu, M. (2006), Thinking outside the box II: The origin, implications and applications of
gravity and its role in consciousness. http://cogprints.org/5259/; NeuroQuantology, 2007; 5(2): 190196 ( http://neuroquantology.com/index.php/journal/article/view/126 ).
4. Hu, H. & Wu (2006), M., Evidence of Non-local Chemical, Thermal and Gravitational Effects.
http://cogprints.org/5613/; http://arxiv.org/abs/quant-ph/0208068v4; NeuroQuantology, 2006; 4: 291306 ( http://neuroquantology.com/index.php/journal/article/view/108 ); Progress in Physics 2007; v2:
17-24 ( http://ptep-online.com/index_files/2007/PP-09-03.PDF ).
5. Hu, H. & Wu, M. (2007), On Dark Chemistry: What’s Dark Matter and How Mind Influences Brain
Through Proactive Spin, http://cogprints.org/5614/; NeuroQuantology, 2007; 5(2): 205-213
(http://neuroquantology.com/index.php/journal/article/view/128 ).
6. Hu, H. & Wu, M. (2010), Prespacetime Model of Elementary Particles, Four Forces & Consciousness.
Prespacetime Journal, 1(1): 77-146 (Also see http://vixra.org/abs/1001.0011 ); and Hu, H. & Wu, M.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1088
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
(2011), Prespacetime Model II: Genesis of Self-Referential Matrix Law, & the Ontology &
Mathematics of Ether. Prespacetime Journal, 1(10): 1477-1507 (also see http://vixra.org/abs/1012.0043 ).
7. Hu, H. & Wu, M. (2003), Spin as Primordial Self-referential Process Driving Quantum Mechanics,
Spacetime Dynamics and Consciousness. http://cogprints.org/2827/; NeuroQuantology (2004); 2:4149 ( http://neuroquantology.com/index.php/journal/article/view/35 ).
8. Newton, I., The Principia: Mathematical Principles of Natural Philosophy. Translated by I.Bernard
Cohen and Anne Whitman. Preceded by A Guide to Newton's Principia, by I.Bernard Cohen.
University of California Press ISBN 0-520-08816-6 ISBN 0-520-08817-4 1999 (Source: Wikipedia).
9. Mach, E., The Science of Mechanics; a Critical and Historical Account of its Development. LaSalle,
IL: Open Court Pub. Co. LCCN 60010179 1960 (Source: Wikipedia).
10. Einstein, A. (1915), Die Feldgleichungun der Gravitation. Sitzungsberichte der Preussischen
Akademie der Wissenschaften zu Berlin Nov.; 844-847.
11. Einstein, A., Podolsky, B. & Rosen, N. (1935), Can quantum-mechanical description of physical
reality be considered complete? Phys. Rev.; 47: 777-780.
12. Julsgaard, B., Kozhekin, A. & Polzik, E. S. (2001), Experimentally long-lived entanglement of two
macroscopic objects. Nature; 413, 400–403.
13. Dirac, P. A. M. (1928), The quantum theory of the electron. Proc. R. Soc.; A 117: 610-624.
14. Penrose, R. A. (1960), Spinor approach to general relativity. Ann. Phys.; 10: 171.
15. Penrose, R. (1967), Twistor algebra. J. Math. Phys.; 8: 345.
16. Bohm, D. and Hiley, B. J. (1984), Generalisation of the twistor to Clifford algebras as a basis for
geometry. Revista Brasilera de Fisica; Vol. Especial Os 70, anos de Mario Schonberg, pp. 1-26.
17. Smolin, L. (2002), Three Roads to Quantum Gravity. New York: Basic Books.
18. Newman, T. E. (2002), On a classical, geometric origin of magnetic moments, spin-angular
momentum and the Dirac gyromagnetic ratio. Phys. Rev.; 65D:104005.
19. Sidharth, B. G. (2001), Issues and ramifications in quantized fractal space-time: an interface with
quantum superstrings. Chaos Solitons Fractals; 12: 1449-1457.
20. Sidharth, B. G. (2001), Chaotic Universe. New York : Nova Science.
21. Burinskii, A. (2006), Kerr’s gravity as a quantum gravity on the Compton level. http://arxiv.org/abs/grqc/0606035
22. Makhlin, A. (2004), The Dirac field and the possible origin of gravity. http://arxiv.org/abs/hepph/0408105
23. Bohm, D. and Hiley, B. J. (1993), The Undivided Universe. London: Routledge.
24. Hu, H. & Wu (2006), M., Photon induced non-local effects of general anesthetics on the brain.
http://cogprints.org/4783/; http://arxiv.org/abs/quant-ph/0208068v3; NeuroQuantology, 2006; 4 (1):
17-31 (http://neuroquantology.com/index.php/journal/article/view/86 ); Progress in Physics 2006, v.3,
20-26 ( http://ptep-online.com/index_files/2006/PP-06-04.PDF ).
25. Loinger, A. & Marsico, T., On the gravitational fields created by the electromagnetic waves.
http://arxiv.org/abs/1106.2210v1
26. Pope, N. V. & Osborne, A. D. (1996), Instantaneous and gravitational and inertial action-at-adistance, Phys. Essay; 8: 184-197.
27. Gibbes, P. E. (1996), The Cyclotron Note Books. http://www.weburbia.com/pg/theories.htm (also see:
http://prespacetime.com/index.php/pst/article/view/104).
28. Arcos, H. I. & Pereira, J. G. (2002), Kerr-Newman solution as a Dirac particle, http://arxiv.org/abs/hepth/0210103
29. Pitkanen, M. (2006), The relationship between TGD and GRT. http://tgdtheory.fi/ (Also see:
http://prespacetime.com/index.php/pst/issue/view/4).
30. Fiscaletti, D. & Sorli, A. S. (2010), Gravitation in a timeless quantum space. Prespacetime Journal,
1(8): 1192-1217 (http://prespacetime.com/index.php/pst/article/view/103).
31. Kyriakos, A. G. (2012), On Lorentz-invariant Theory of Gravitation Part 1: Review. Prespacetime
Journal, 3(6): 542-573 (http://prespacetime.com/index.php/pst/article/view/374).
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
1089
Journal of Consciousness Exploration & Research | December 2013 | Vol. 4 | Issue 10 | pp. 1066-1089
Hu, H. & Wu, M., On the Natures of Quantum Gravity & Graviton
32. Kaufman, S. E. (2011), Application of the Relational-Matrix Model to Spacetime and Physical
Reality. Prespacetime Journal, 2(7): 1013-1092 (http://prespacetime.com/index.php/pst/article/view/225).
33. Crowell, L. B. (2012), Unitarity, Locality and Spacetime Geometry: Foundations that Are Not
Foundations. Prespacetime Journal, 3(12): 1110-1119 (http://prespacetime.com/index.php/pst/article/view/441).
34. Campbell R. (2008), Gravity, Quantum Relativity & System 3. http://www.cosmic-mindreach.com/Gravity.html
(also see http://prespacetime.com/index.php/pst/article/view/570)
35. Loinger, A. (1998-2013), http://arxiv.org/find/all/1/all:+AND+Loinger+A/0/1/0/all/0/1
36. Dalton K. (1998), Einstein’s Energy-Free Gravitational Field. http://arxiv.org/abs/gr-qc/9512008v3
37. Pusey,M. F., Barrett, J. and Rudolph, T., On the reality of the quantum state. http://arxiv.org/abs/1111.3328v3
38. Hehl, F. W. (2008), Nonlocal Gravity Simulates Dark Matter. http://arxiv.org/abs/0812.1059v3
39. Kowall, J. (2012), What is Reality in a Holographic World? Prespacetime Journal, 2(13): 2086-2199
(http://prespacetime.com/index.php/pst/article/view/325).
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com |
Physics of the Brain-Schizophrenia
Probabilistic approach to consciousness and
Hallucination
OMID REZANIA
1,2
1
York University, Department of Physics and
Astronomy, Toronto, Canada
2
Douglas Mental Health University Hospital,
Aging Center, Montreal, Canada
Correspondence: OMID REZANIA
(omico80@yorku.ca)
Schizophrenic patients suffer from hallucination
which its causality is not yet fully understood. This
paper attempts to approach this mystery from the
perspective of quantum mechanical theories. A
novel approach has been adopted to demonstrate
the hallucination as a time evolution of percepts
basis states in the Hilbertian consciousness which
are desynchronised from the time in real world.
The method also extends his approach to predict
mind and brain modulation through the
correlation and coupling of consciousness and it
reaches a clinically hypothetical outcome of
inducing consciousness into a brain which is not
conscious.
Key words: Schizophrenia, Brain modulation,
Hilbertian consciousness, sub-Hilbertian
consciousness, Percepts basis vector states,
consciousness induction
Schizophrenia is a complex neuropsychiatric
disorder which is characterized by delusions,
hallucinations, passivity phenomena, disordered
thought process, disorganized behavior and
progressive cognitive deficits. [1,5]
However, after many years of studying
schizophrenia, the causality of this psychiatric
disorder has not yet been fully understood.
There has been numerous publication to explain
the causality of schizophrenia as the perturbation
of consciousness from the quantum mechanical
perspective, but no attempts have been made to
address the causality of schizophrenia by
exploiting the core nature of the consciousness,
itself. [6.7].
The approach which has been proposed at this
research
has
fundamentally
addressed
consciousness itself from a very novel perspective
which not only explains the bizarre phenomena
such as hallucinations but also provides a
methodology which is capable to make predictions
for future observations.
Consciousness regardless of its definition from any
discipline can be represented as an infinite
dimensional Hilbert space, where this novel
approach to consciousness would play a significant
role in explaining and predicting many yet
unresolved mysteries in related scientific fields.
In quantum physics, Hilbert space is an abstract
system where the rigorous mathematical
formulation of dynamism of quantum systems is
formulated. [8]
By this assumption, then we can liberally refer to
consciousness as Hilbertian consciousness, where
any percept can form a vector with unit length
residing in that space, which would be referred to
later as percepts basis vector inhabitant of the
Hilbertian consciousness. These percepts now
inhabitant of the Hilbertian consciousness
following Dirac representation for quantum states:
[8]
|𝑝𝑒𝑟𝑐𝑒𝑝𝑡 >
However, every percept made by the individual at
the same time forms and constructs a dual
consciousness which is referred to as adjoint
Hilbertian consciousness, represented similarly by
the following notation:
< 𝑝𝑒𝑟𝑐𝑒𝑝𝑡|
It can be well perceived that for any conscious or
unconscious percept, both the percept basis state
and its adjoint basis state are present
simultaneously as a vector in the consciousness of
individual, in other words any percepts
Page | 1
represented as a basis vector in Hilbertian
consciousness cannot exist individually without the
coexistence of its adjoint in the adjoint Hilbertian
consciousness.
In quantum mechanics, any quantum state
represented as a vector in the Hilbert space can
mathematically pair with an adjoint quantum state,
not necessarily its own corresponding adjoint to
extract a complex valued figure which has an
important interpretation as a “probability
amplitude”. To extract that all important
probability amplitude, basis vector states should
mathematically satisfy orthogonality principle in
the Hilbert space, which mathematically can be
represented as 𝛿 − 𝑓𝑢𝑛𝑐𝑡𝑖𝑜𝑛 which its value
assumes either to be one or zero, and nothing else.
[8]
However, when applied to quantum basis states, it
essentially represents the functioning of an adjoint
basis states on the quantum states to extract a
probability amplitude (concept of probability
amplitude is different from probability which
would be hinted later). Quantum representation of
orthogonality can be constructed in Dirac notation
as [8]:
< 𝑛 | 𝑚 > = 𝛿(𝑛, 𝑚)
𝑤ℎ𝑒𝑟𝑒 𝛿 (𝑛, 𝑚) = 1 𝑖𝑓 𝑛 = 𝑚
𝛿(𝑛, 𝑚) = 0 𝑖𝑓 𝑛 ≠ 𝑚
Above 𝑚 𝑎𝑛𝑑 𝑛 both represents any arbitrary
quantum states which their inner product yields
the probability amplitude of either one or zero, or
simply states that the desired outcome would
either happens 100% or it would never ever
happen, and there is no other possibility in
between.
In parallel, this approach assumes that when an
individual
consciously
or
unconsciously
experiences a cognition, it stores that as percept
which is represented as a vector basis state in his
Hilbertian consciousness. Any percepts now an
inhabitant of that complex space, couples with
other percepts basis states but follows rigorously
the orthogonality principle in analogous to Hilbert
space inner products of two vectors.
As an example, the percept formed by smelling a
flower and another percept similarly formed by
seeing a picture of a cat, both form a basis vector
and then they can couple by constructing an inner
product in the Hilbertian consciousness of the
individual who underwent those experiences.
Later the mechanism of coupling of the percepts
basis states between two different individuals are
discussed and evaluated in detail.
According to the orthogonality principle outlined
above these two percepts when couple and
construct the inner product
< 𝑆𝑚𝑒𝑙𝑙 𝑜𝑓 𝑡ℎ𝑒 𝑓𝑙𝑜𝑤𝑒𝑟|𝑃𝑖𝑐𝑡𝑢𝑟𝑒 𝑜𝑓 𝑎 𝑐𝑎𝑡 >
=0
Produces the probability of zero.
The realisation of our outside universe is a matter
of orthogonality of our percepts basis states already
in our Hilbertian consciousness with the newly
acquired percepts evolved in time.
This happens as an example in learning process.
When an individual learn a French word such as
𝐵𝑜𝑛𝑛𝑒 𝐽𝑜𝑢𝑟𝑛𝑒𝑒 for the first time, he forms that as
a percept basis state on his Hilbertian
consciousness, which mathematically can be
represented as | 𝐵𝑜𝑛𝑛𝑒 𝐽𝑜𝑢𝑟𝑛𝑒𝑒 > alongside its
simultaneous adjoint basis state formed in the
adjoint Hilbertian state as < 𝐵𝑜𝑛𝑛𝑒 𝐽𝑜𝑢𝑟𝑛𝑒𝑒 | ,
then upon future hearing of that phrase , the only
and only recognition happens when the newly
heard of the phrase forming a new percept basis
state on the Hilbertian consciousness, provided
that the coupling or inner product of the trigger
with the already formed adjoint basis state of the
phrase be orthogonal as :
< 𝐵𝑜𝑛𝑛𝑒 𝐽𝑜𝑢𝑟𝑛𝑒𝑒|𝐵𝑜𝑛𝑛𝑒 𝐽𝑜𝑢𝑟𝑛𝑒𝑒 > = 1
It is obvious that the coupling of this basis state
with a trigger which forms a newly vector upon
hearing the same phrase in German yields zero
due to the orthogonality of those basis vector in the
Hilbertian consciousness
Page | 2
< 𝐵𝑜𝑛𝑛𝑒 𝐽𝑜𝑢𝑟𝑛𝑒|𝐺𝑢𝑡𝑒𝑟 𝑇𝑎𝑔 > = 0
Which zero probability amplitude of the above
two basis states implies lack of recognition at the
moment, but as German phrase already forms a
permanent basis vector state on the individual`s
Hilbertian consciousness and upon future hearing
and due to the orthogonality, which yield one, the
individual forms a recognition and memory
shapes.
As it was implied then the formation of the
memory can be interpreted as the complete sets of
percepts formed as basis vector in the Hilbertian
consciousness of the individual.
The picture which has been presented so far
provides a static picture of the perception and
cognition, which is defined only as coupling
between two percepts formed as basis vector in the
human Hilbertian consciousness and the element
of the time which provides all crucial aspect of the
temporality of the proposal has to be incorporated
into the model.
The incorporation of time in this model sets the
stage for an all-important boundary between
hallucination and reality.
It is evident that outside universe is not static and
it constantly evolves through the time, then our
percepts basis states should also evolve in time to
makes perception matches with outside events
with respect to time.
But how temporal dimension of the Hilbertian
consciousness can be incorporated with real
experience events?
To visualise this scenario, a Clock can be imagined
which is installed on your Hilbertian
consciousness which measures the time for the
evolution of the percepts basis states and a clock
on the wall of your room.
For any percept formed due to an external event
to be experienced in real-time, the two clocks,
should be synchronised. This synchronisation
manifest itself to experience real life events in realtime sequences.
Interestingly, if the time experience in the
Hilbertian consciousness does not synchronise
with the real-time events, then as a result the
percepts basis vector states already inhabitant of
Hilbertian consciousness evolve in time
desynchronised with the real time. The result of
these desynchronised time evolved percepts basis
states in your Hilbertian consciousness is nothing
but the hallucination which can be either
experienced as dream or any symptoms of
neurological or neuropsychiatric disorders such as
schizophrenia or dementia with Lewy bodies.
However, this probabilistic approach to
perception and cognition, can well be utilized from
the quantum mechanical perspective to explain the
memory and cognition impairment in other
neurological disorders such as Alzheimer`s
disease where the percepts basis vector states in the
Hilbertian consciousness fails to correlate with the
correct adjoint percept basis states in the
Hilbertian consciousness of the patient , which in
essence results in zero probability amplitude.
Mind modulation through
consciousness coupling
However, as any physics ‘formulation should not
only explain the physical phenomena, but also
should be able to make some predictions about
future applications. The model which has been
presented here to explain the hallucination, a
marked syndrome of schizophrenic patients can
also be extended to predict the direct impact of
Hilbertian consciousness of an individual on any
other individual who they share some vector basis
on their Hilbertian consciousness, which they
correlate in the temporal dimension during which
the basis vectors are constructed in their Hilbertian
consciousness.
In this case, everyone if regarded in isolation in his
Hilbertian consciousness has a complete
superposition of all those cognitive experiences
which they all exist with the same probability
amplitude to occur at the same time before the
triggering of an external occurrence which
collapses the superposition only to one state which
is your response.
Page | 3
Here, a completely new concept which is uniquely
applicable to quantum mechanics is borrowed,
probability amplitude 𝑎 , which it relates to
probability 𝑃 as 𝑃 = |𝑎| ∗ |𝑎∗ | which 𝑎∗is the
conjugate of 𝑎.[8]
The percepts basis states can be completely
different or similar but for the sake of reaching a
sound conclusion we assume that some percepts
are similar:
𝑛
In the simplest scenario, when an individual is
exposed to some external stimuli, like smelling a
flower or watching an accident or any other
cognitive experience from external environment
during a time interval which can span arbitrarily
from 10 am to 11 am, we can consider the
formation of a sub-Hilbertian consciousness
where it can be constructed as a group formed by
each cognitive experience which he has
experienced limited to the time interval.
This sub-Hilbertian consciousness itself is an
element of the Hilbertian consciousness of the
individual.
For demonstration, the percept formed in the subHilbertian consciousness would be represented as
below, but due to limitation for graphical
representation, I do represent each percept by a
geometrical figure, in which case | ∎ > may
represent a percept formed by watching a picture
of a cat now a basis vector in the sub-Hilbertian
space, in its totality, then the complete sets of
percept amplitude can form the following
superposition in my consciousness:
|𝐵 > = ∑ 𝑏1|∢ > +𝑏2|∎ > +𝑏3|⊾ > +𝑏4|⊿
1
> + ⋯ + 𝑏𝑛| ∤>
Which is similarly the complete superposition of
percepts states in the sub-Hilbertian consciousness
of the other individual.
The implication of the proposed model here
comes with the idea of each participant`s
consciousness which acts to collapse the complete
superposition of percept basis states of the other
participant in the pair, in other words each
participant`s consciousness acts as if to measure
the probability amplitude of the percepts of the
other participant with respect to itself by forming
the inner product as:
<𝐵|𝐴>
Which this product should conform to the
orthogonality principle; [8]
𝑛
< 𝐵 | 𝐴 > = (∑ 𝑏1∗ < ∡| + 𝑏2∗ < ∎| + 𝑏3∗
1
< ⊾|+𝑏4∗ < ⊿| + ⋯ + 𝑏𝑛∗ <
𝑛
𝑛
|𝐴 >= ∑ 𝑎1|∎ > +𝑎2| ∴> +𝑎3|⊿ > +𝑎4| ⊥
1
> + ⋯ + 𝑎𝑛| ∦>
Where 𝑎1, 𝑎2, 𝑎3 , … , 𝑎𝑛 all refer to the
probability amplitude of each percept basis states
in the superposition constructed by them.
The individual superposition of percepts with
equal probability amplitude formed during the
time interval which is synchronised with other
individual which is exposed to the same external
stimuli during the same interval pairing with the
other participant.
∤ | )(∑ 𝑎1|∎ > +𝑎2| ∴
1
> +𝑎3|⊿ > +𝑎4| ⊥
> + ⋯ + 𝑎𝑛| ∦>)
Which can be summarized as:
𝑏1∗ 𝑎1 < ∡|∎ > +𝑏1∗ 𝑎2 < ∡| ∴> +𝑏1∗ 𝑎3
< ∡|⊿ > +𝑏1∗ 𝑎4 < ∡| ⊥
> + ⋯ + 𝑏1∗ 𝑎𝑛 < ∡| ∦
> + ⋯ + 𝑏4∗ 𝑎1 < ⊿|∎
> +𝑏4∗ 𝑎2 < ⊿| ∴> +𝑏4∗ 𝑎3
< ⊿|⊿ > +𝑏4∗ 𝑎4 < ⊿| ⊥>
Due to the orthogonality principle then the
consciousness to consciousness modality of a pair
Page | 4
of individuals lead to the modulation of their mind
with the following probability amplitude:
< 𝐵 | 𝐴 > = 𝑏2∗ 𝑎1 + 𝑏4∗ 𝑎3 + 𝜇
Where 𝜇 takes value from zero to any positive
value depending on the similarity of mutual
percepts of each individual.
Nonetheless, then the probability of finding the
correlation and modulation of each brain to the
brain of the other participants through the mutual
consciousness correlation forming in the subHilbertian space is:
𝑃 = ( 𝑏2∗ 𝑎1 + 𝑏4∗ 𝑎3
+ 𝜇)(𝑏2∗ 𝑎1 + 𝑏4∗ 𝑎3 + 𝜇)∗
= (𝑏2∗ 𝑎1 + 𝑏4∗ 𝑎3
+ 𝜇)(𝑏2𝑎1∗ + 𝑏4𝑎3∗ + 𝜇∗ )
Which the probability with respect to the initial
assumption with non-vanishing probability
amplitudes for each percept basis states formed in
the sub-Hilbertian consciousness of individual will
never go to zero, which is an implication of the
existence of the brain modulation through the
correlation of the consciousness.
This provides a concrete analysis and a
mathematical framework within the context of the
quantum mechanics of the correlation of the
consciousness between individuals who shares
some percepts on their Hilbertian consciousness.
This can be interpreted also as a brain modulation
due to its consciousness correlation with others`
due to the non-vanishing of the probability
amplitudes of those percepts which formed a
superposition state in Hilbertian consciousness.
But whether this method can be clinically adopted
to induce consciousness to a patient who has lost
consciousness leaves to be exploited further.
COCLUSION
In this novel approach to consciousness,
consciousness was regarded as an infinite
dimension Hilbert space, referred to as Hilbertian
consciousness where each conscious and
unconscious experience and percept formed an
inhabitant unit vector in that space. By carefully
adhering to the orthogonality principle, cognition
was interpreted as the time evolution of the
percepts basis states triggered by the presence of
the external stimuli. Hallucination as a
characteristic symptom of schizophrenia then
could be regraded as time evolution of the percept
basis states which are not synchronised with real
life temporal dimension, of all those conscious
bases states which has been formed and
constructed in the Hilbertian consciousness since
the birth of the individual.
This approach has been adopted to make
predictions which included the brain modulation
through the correlation of the consciousness of the
individuals who share some, although negligible
percept basis vector states in their sub-Hilbertian
consciousness. The approach was solely relied
heavily on the principles of the probability
amplitudes whose mod square produces the
probability in its conventional scientific sense. It
was shown that regardless of technical difficulties
for realization of his approach, the brain
modulation through correlation of the
consciousness provides the probability which can
never vanishes to zero.
ACKNOWLEDMENTS
This research did not receive any specific grant
from funding agencies in the public, commercial,
or not-for-profit sectors.
REFERENCES
[1].
van
Os
J,
Kapur
S.
Schizophrenia. Lancet. 2009; 374:635–645. doi:
10.1016/S0140-6736(09)60995-8.
[2]. Northoff G. Resting state activity and the
“stream of consciousness” in schizophrenianeurophenomenal
hypotheses. Schizophr
Bull. 2015;
41:280–290.
doi:
10.1093/schbul/sbu116.
Page | 5
[3]. Howes OD, Murray RM. Schizophrenia: an
integrated
socio-developmental-cognitive
model. Lancet. 2014;
383:1677–1687.
doi:
10.1016/S0140-6736(13)62036-X
[4]. Harrison PJ, Weinberger DR. Schizophrenia
genes, gene expression, and neuropathology: on
the
matter
of
their
convergence. Mol
Psychiatry. 2005;
10:40–68.
doi:
10.1038/sj.mp.4001558.
[5].
Insel
TR.
Rethinking
schizophrenia. Nature. 2010; 468:187–193. doi:
10.1038/nature09552.
[6]. Sass LA, Parnas J. Schizophrenia,
consciousness, and the self. Schizophr Bull. 2003;
29:427–444.
doi:
10.1093/oxfordjournals.schbul.a007017.
[7]. Vogeley K, Kupke C. Disturbances of time
consciousness from a phenomenological and a
neuroscientific perspective. Schizophr Bull. 2007;
33:157–165. doi: 10.1093/schbul/sbl056.
[8] The principles of quantum mechanics book by
Paul Dirac
Page | 6 |
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
458
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
Article
The Experiential Basis of Maya:
How the Limitations Inherent in the Individual's Creation of
Experience Function to Conceal the Nature of Reality (Part I)
Steven E. Kaufman*
ABSTRACT
Maya, as the phenomenon that conceals from the Individual both its own Nature as well as the
Nature of the universe as being composed of Consciousness-Existence, is a result of the
unavoidable and inviolable functioning of two experiential limitations. These two experiential
limitations are themselves an unavoidable result of the way experience is always created as the
product of some relation of Existence to Itself, in which relation the Individual point of Existence
that is apprehending the experience must always be involved, and in which relation the
Individual point of Existence that is apprehending the experience must also always occupy a
particular perspective. One experiential limitation is negatively restrictive while the other is
positively restrictive, making impossible the creation of some experiences while making only
possible the creation of other experiences, with the experiences that an Individual both cannot
and can only create in any one moment limited by the relations in which the Individual must
already be involved in order to create what they are already, in that moment, from their
Individual perspective, apprehending as experience.
What will be shown is that the two experiential limitations that, operating individually, produce
the phenomena of wave-particle duality, quantum uncertainty, and quantum non-locality, are the
same two experiential limitations that, operating in concert, produce the phenomenon referred to
as maya, whereby Existence, at the level of the Individual, as a result of how the Individual is
choosing to conceive of reality, becomes locked into a mode of experiential creation that serves
to both hide and disguise Existence from Itself, thereby preventing the Individual from
apprehending its own Nature as well as the Nature of the universe as being composed of
Consciousness-Existence, while at the same time perpetuating the misconception necessary for
maya to function, which misconception is the idea that what we apprehend as physical reality is
what is actually there.
Part I of this two-part article contains: 1. Introduction; 2. Maya as Process and Illusion; 3. The
Actual Nature and Limitations of Experience; and 4. The Seeming Nature of Experience.
Key Words: Consciousness, Existence, experiential basis, Maya, experiential reality, physical
reality, experiential limitation, negatively restrictive, positively restrictive, wave-particle duality,
quantum uncertainty, quantum entanglement.
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
459
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
When one is in ignorance, he sees the phenomenon and does not see God. When he sees God,
this universe vanishes entirely for him. Ignorance or Mâyâ, as it is called, is the cause of all this
phenomenon — the Absolute, the Unchangeable, being taken as this manifested universe. This
Maya is not absolute zero, nor non-existence. It is defined as neither existence nor nonexistence. It is not existence, because that can be said only of the Absolute, the Unchangeable,
and in this sense, Maya is non-existence. Again, it cannot be said it is non-existence; for if it
were, it could never produce phenomenon. So it is something which is neither; and in the
Vedanta philosophy it is called Anirvachaniya or inexpressible. - Swami Vivekananda1
1. Introduction
The question often posed is: What is the nature of reality? However, this is really a trick question
because reality as a whole consists of two completely different and yet related realities, and the
overall nature of reality can only be understood in the context of these two realities and their
relation to each other. Thus, the nature of reality is that there are two realities; the reality of
experience and the Reality that both creates and apprehends experiential reality. And although
these two realities are completely different in nature, in as much as one is created whereas the
other is uncreated, they are nonetheless inseparable, like a mirror and the reflection contained
within it.
The uncreated Reality that, through relation to Itself, both creates and apprehends experiential
reality, will be referred to in this work using various terms, depending on the context. Those
terms include; Existence, Consciousness, the Absolute, Underlying Actuality, God, Self,
Relational Structure, Individual, More Fundamental Individuality, Nature, What Is Actually
There, and Reality. Basically, any capitalized word that is not capitalized simply because it is at
the beginning of a sentence is a word that indicates a concept that points toward That which,
through relation to Itself, both creates and apprehends experiential reality, and yet is Itself never
an experience, because experience is of a different nature, as a reflection is of a different nature
than the mirror in which it resides. The same is true for any capitalized phrase. Similarly, to
avoid confusion, other words that are normally capitalized are not capitalized if those words refer
to what Reality is apprehending as an experiential reality, e.g., the earth and the universe.
As we look at the universe around us it appears to be composed of objects, of things, of physical
realities. However, as explained in both Unified Reality Theory2 and Existential Mechanics,3 the
universe is not actually composed of any experiential reality, physical or otherwise. Rather, what
the universe is actually composed of is the Reality that both creates and apprehends experiential
reality. More specifically, what the universe is actually composed of is the Reality that both
creates and apprehends experiential reality, as that Reality is being iteratively and progressively
in relation to Itself, and in so doing, having evolved Itself into, and continuing to evolve Itself
into, a Relational Structure composed of the Underlying Actuality of Consciousness-Existence as
that Reality has become and is becoming structured and configured in relation to Itself, while
simultaneously creating, as a product of those same iterative and progressive relations, the
reflections of Itself it apprehends as experiential reality. This overall process is depicted in
Figure 1.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
460
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
Absolute Existence - Consciousness - Reality
3rd level of
Existential
Self-Relaion
physical experience - physical reality
3rd level relative existence
Relational
Structure
Absolute Existence - Consciousness - Reality
mental experience - mental reality
2nd level relative existence
2nd level of
Existential
Self-Relaion
Absolute Existence - Consciousness - Reality
1st level of
Existential
Self-Relaion
emotional experience - emotional reality
1st levelrelative existence
Absolute Existence - Consciousness - Reality
Figure 1. This drawing depicts in a concise way the iterative and progressive relations of
Existence to Itself that simultaneously create the Relational Structure of Reality, composed of
Existence as it is being in relation to Itself, (represented by the dashed lines) as well as the
relative existences that the Existence involved in those relations apprehends as experiential
reality, (represented by the solid lines) with the specific type of experiential reality created and
apprehended, i.e., emotional, mental, or physical, dependent upon the specific level of
Existential Self-Relation at which the relative existence being apprehended by the Individual
Existence involved in that relation is being produced.
Thus, although the universe appears to be composed of what are experiential realities, it is
actually composed of the Reality that, through relation to Itself, both creates and apprehends
experience or experiential reality. Thus, there is Reality and reality, i.e., the Reality of
Consciousness-Existence and the reality which that Reality, through relation to Itself, both
creates and apprehends as experiential reality. However, what has happened is that our
conception of these two realities has become inverted, in as much as we conceive of the
subordinate or secondary reality as the primary reality, and we conceive of the primary Reality,
when we conceive of it at all, as the subordinate or secondary reality. Thus, What Is Actually
There has become both hidden and disguised; hidden because when we look for What Is
Actually There we cannot find it, as it lies hidden behind the veil of physical-experiential reality,
and disguised because when we do come across it, it appears as something other than What Is
Actually There. And when What Is Actually There becomes hidden and disguised, What We
Actually Are also becomes hidden and disguised, i.e., we lose sight of our Nature, because What
We Actually Are is not different or other than What Is Actually There.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
461
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
This reality duality between what we experience as reality and the Reality or Underlying
Actuality that underlies what we experience as reality, as both its Creator and Apprehender, was
clearly recognized by the ninth-century Hindu philosopher Adi Shankara, for whom Reality or
the Underlying Actuality was represented or indicated by the term Brahman or the Absolute.
Shankara's Advaita philosophy centers on the recognition of the ultimate identity between the
Atman and Brahman, which terms correspond to what I refer to as the Individual and the More
Fundamental Individuality, respectively. In the Vedanta philosophy, this situation, wherein the
universe appears to be composed of what are experiential realities when it is actually composed
of That Which Apprehends Experience, is often indicated by the example of seeing a snake
where there is only a rope. This situation is also analogous to looking toward a calm body of
water and seeing the reflection that lies on its surface as being what is actually there, in which
case what is actually there underlying the reflection becomes hidden. However, the recognition
of this reality duality along with the recognition of the identity between the Individual and God,
if you will, brings with it the following questions: If the universe is actually composed of the
Absolute then why do we not know it as That? Further, if we as Individuals, as points of
Consciousness apprehending experience, are not other than That, not other than That of which
the universe is actually composed, then why do we not know ourselves as That? That is, why do
we see a snake where there is actually a rope? Or, more directly, why do we apprehend only
experiential reality if What Is Actually There is the Reality that is the Creator and Apprehender
of experience, i.e., Consciousness-Existence?
In order to explain this situation Shankara refined the ancient concept of maya. The refined
concept of maya was essentially put forth as a way of explaining how Absolute Existence
becomes effectively hidden from Itself by appearing to Itself as the phenomenal universe, a.k.a.,
physical-experiential reality. However, the Vedantic concept of maya only holds that this
situation exists, and that reason is maya. That is, the Vedantic concept of maya does not itself
explain how maya operates, as the functioning of maya is considered by the Vedantists to be
inexpressible. That is, although the Vedantists have recognized that there is something that
causes What Is Actually There to be apprehended as the material or manifested universe, thereby
hiding What Is Actually There, and they call that something maya, that is as far as they go, for
they consider the inner workings of maya, i.e., the way that maya actually functions to cause
What Is Actually There to appear as the manifested universe and so hide from view What Is
Actually There, to be inexpressible, i.e., not able to be expressed and therefore not able to be
explained. Thus, in terms of the snake and rope analogy, the doctrine of maya holds that
although What Is Actually There is a rope, when we look at it we see a snake, and the reason that
this happens is the result or working of an inexpressible phenomenon called maya, as shown in
figure 2.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
462
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
Absolute Existence - Consciousness - Reality
the Rope
What Is Actually There
Absolute Existence - Consciousness - Reality
What Is Actually There
maya
Absolute Existence - Consciousness - Reality
The More Fundamental Individuality - Brahman
the Rope
What Is Actually There
physical experience - physical reality - what seems to be there
the snake
Absolute Existence - Consciousness - Reality
The Individual - Atman
What Is Actually There
Figure 2. Although What Is Actually There is Absolute Existence, through the functioning of
what the Vedantists refer to as maya, physical reality appears or seems to be what is there,
thereby hiding from the Individual the Nature of the universe as well as their own Nature,
indicated in the drawing by the shading of What Is Actually There, which situation is compared
to seeing a snake where there is actually a rope.
Thus, the Vedantic concept of maya is not so much an explanation of the situation as it is a
recognition of the situation along with the recognition that, if this is the case, then there must be
a reason for it, and that reason is indicated by the concept of maya. Thus, the famous Vedantist
Vivekananda stated that "…the Maya of the Vedanta, in its last developed form, is neither
Idealism nor Realism, nor is it a theory. It is a simple statement of facts — what we are and what
we see around us,"4 as well as, "Maya is not a theory; it is simply a statement of facts about the
universe as it exists…"5 In other words, the idea that the universe is actually composed of one
thing while appearing to be composed of something else is, from the perspective of a Vedantist,
not a theory, but a fact. Recognizing this fact, Shankara also recognized that in order for the
Absolute to fool Itself into thinking that the universe was composed of experiential reality rather
than Itself, the Absolute had to be performing some sort of magic trick or slight of hand, as it
were, and he called that trick maya. However, although he identified that there must be some sort
of trick being performed in order for the Absolute to become hidden from Itself behind the veil
of experiential reality, he apparently did not feel that it was possible to describe how the trick is
done.
That having been said, it is nonetheless the purpose of this work to explain how the trick is done.
That is, it is the purpose of this work to explain how the Absolute, at the level of the Individual,
appears to Itself as this manifested, physical-experiential universe, and in so doing loses sight of
both the Nature of the universe as well as its own Nature. And it has become possible to describe
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
463
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
the mechanics of this trick because information is now available that Shankara did not have.
Specifically, I have the benefit and advantage of being able to analyze the reality duality, and the
questions it brings with it, from a perspective made possible by the discovery of wave-particle
duality and quantum uncertainty, which phenomena, in revealing one of the limitations inherent
in the Individual's creation of experience, also revealed the nature of experiential reality, thereby
making it possible to understand how the Absolute, through relation to Itself, creates experiential
reality. In other words, thanks to the discovery of wave-particle duality and quantum uncertainty,
I now know how the snake is created by the Rope, which in turn has made it possible for me to
identify the conditions under which the Rope can mistake Itself for the snake and in so doing,
become blind to its own Nature.
Thus, it is the purpose of this work to continue the work of Shankara by expressing what the
Vedantists have heretofore considered inexpressible, i.e., the mechanism underlying the
phenomenon of maya, the mechanism underlying how the Absolute, through its creation and
apprehension of experiential reality at the level of the Individual, becomes blind to the actual
Nature of the universe, and so blind to its own Nature. Ultimately what will be shown is that the
same limitations of experience responsible for the physically paradoxical phenomena of waveparticle duality, quantum uncertainty, and quantum non-locality are the same limitations of
experience that underlie the metaphysical paradox that is maya, i.e., the metaphysical paradox
that involves Existence concealing Itself from Itself. That is, the solution to one of the great
metaphysical questions will be shown to be identical to the solution to several of the great
physical questions, as all find their solution in understanding the unavoidable and inviolable
limitations inherent in the Individual's creation of experience. In essence, what is going to be
explained is how the Magician pulls off the trick whereby She both hides Herself from Herself,
as well as disguises Herself so that She cannot recognize Herself, using the veil of experiential
reality. It is quite a trick, and for now all that will be said is that, as already alluded to, it does
involve the use of mirrors.
2. Maya as Process and Illusion
The term maya, as it has been used historically, has two related meanings. One meaning is as the
illusion that hides Existence from Itself, and the other meaning is in reference to the overall
process by which Existence creates the illusion whereby it becomes hidden from Itself. When the
term maya is used in to indicate the illusion that hides Existence from Itself, it is then said that
the universe is maya, and in this context the universe as it appears to us is considered to be an
illusion. However, this use of the term maya has a very limited validity and is not the meaning
ascribed to that term by Shankara or the Vedantists. Rather, for a Vedantist, the term maya is
used to indicate the overall process by which Existence creates the illusion whereby it becomes
hidden from Itself, which process the Vedantists consider to be inexpressible.
Regardless of which of these two meanings one implies by using the term maya, implicit in the
concept of maya is the idea that the world, as we apprehend it as being composed of physical
reality, is an illusion of some sort. That is, the concept of maya, in both meanings or usages,
involves something appearing to be there that is different or other than What Is Actually There.
Again, the example is used of seeing a snake where there is actually only a rope. When the term
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
464
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
maya is used in the limited non-Vedantic sense to indicate the illusion that hides Existence from
Itself, maya then indicates just the snake, and the snake is analogous to physical reality.
However, when the term maya is used in the more subtle and refined Vedantic sense to indicate
the overall process by which Existence creates the illusion whereby it becomes hidden from
Itself, the term maya then indicates far more than just the snake, as it is then being used to
indicate the heretofore inexpressible process whereby a snake can appear where there is actually
only a rope.
Thus, although the term maya has two related meanings, the goal of this work is to describe that
term in accord with the more subtle and refined meaning ascribed to it by the Vedantists, which
is as an overall process whereby an illusion is created. However, before we get into that it will be
helpful to first define the nature of the illusion itself, which illusion is not itself maya, but rather
is a result of the functioning of maya.
Again, maya as a process that creates an illusion has often been described using the analogy of
seeing a snake where there is actually only a rope. However, in order to explain the nature of this
illusion, as opposed to the mechanics of how the illusion is created, which explanation will come
later, I prefer the analogy of looking at a calm body of water or into a mirror and mistaking the
reflection for what is actually there, in which case the reflective substance itself becomes hidden.
I prefer this analogy because it gets more directly at the nature of the illusion since, as will be
described, all experience is ultimately a reflection of Existence, and it is through the Individual's
creation of experience that maya operates, which is to say, it is the Individual's creation of
experience that makes possible the creation of an illusion that serves to obscure or hide from the
Individual the Nature of the universe, as well as their own Nature, as being composed of nonexperiential Consciousness-Existence.
However, to say that the world as we apprehend it is an illusion and leave it at that means
nothing, and if anything, fosters confusion. This is because physical experience, and so physical
reality, is not, in and of itself, an illusion. Rather, physical experience only functions as an
illusion when it is taken by an Individual as being what is actually there. Is a reflection in and of
itself an illusion? No. A reflection understood as reflection is not an illusion. It is only when a
reflection is taken for what is actually there that the reflection is then functioning as an illusion,
appearing as something that it is not, i.e., as what is actually there, which functioning then causes
it to obscure from view what is actually there, much like the appearance of a snake where there is
actually only a rope, hence the analogy. And just as it is possible to look into a mirror and remain
cognizant that what you are seeing is a reflection and not what is actually there, in which case
what is actually there does not become hidden, so to is it possible to look out at the world, out at
manifested reality, at physical reality, and understand that what you are seeing is a reflection, in
which case What Is Actually There as one's Nature doesn't become concealed, but is instead
revealed.
What this means is that physical experience, physical reality, manifested reality, is not in and of
itself an illusion, is not in and of itself maya, in the limited non-Vedantic use of the term. Rather,
physical experience only functions as an illusion when it is taken by an Individual as being what
is actually there, which is to say, is mistaken for being what is actually there by an Individual.
For this reason, blanket statements that the world is an illusion are meaningless, because they
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
465
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
imply that experiential reality is inherently illusory, when it is not. Experiential reality is no more
inherently illusory than a reflection in a mirror is inherently an illusion. Experiential reality
provides the basis for the creation of an illusion in the same way a reflection provides the basis
for the creation of an illusion, in that each provides the opportunity for what is actually there to
be obscured from view, as a reflection on the surface of a pond makes it possible, but not
inevitable, for an Individual to take the reflection that lies on its surface for what is actually
there, which, if done, and for as long as it is done, must obscure from that Individual's view what
is, in the physical sense, actually there.
As explained in my previous work,6 Existence, because it Exists, cannot help but create and
apprehend experience. Thus, all Existence is creating experience, but not all Existence is
mistaking experience for What Is Actually There, not all Existence is mistaking the reflection for
What Is Actually There, and so not all Existence has lost sight of the Reflective Substance that is
actually there, which Reflective Substance is not other than the Consciousness that apprehends
experience. That is, maya is not a function of experience alone, rather, it is a function of the
Individual, as the Creator and Apprehender of experience, in some way or another taking
experience for what is actually there, i.e., mistaking experience for What Is Actually There, and
in so doing seeing a snake where there is only a rope, which is to say, taking experiential reality
for what is actually there when What Is Actually There is the more fundamental Reality of
Consciousness-Existence. Thus, to reiterate, although maya is often considered as the illusion
that hides Existence from Itself, this is a limited meaning. Again, the deeper and more refined
meaning of maya is that of the overall process by which the illusion is created and maintained,
which process, as will be described, requires for its functioning the Individual's active
participation in the creation of the illusion.
All that having been said, the vast majority of humanity does consider physical reality to be what
is actually there, and so for the vast majority of humanity physical experience does function as
an illusion, and in so functioning does serve to hide from the Individual's view the Reflective
Substance that is actually there, which Reflective Substance is not different or other than the
Individual's own Nature. And in this context, and in this context alone, i.e., in the context of
understanding that for the vast majority of humanity physical experience functions as an illusion,
stating that the world is an illusion has some meaning, and yet is still too broad of a statement,
since it still implies that physical experience is always an illusion, that it always functions as an
illusion, when the determination of whether or not physical experience functions as an illusion is
not a foregone conclusion, but rather is a function of a choice each Individual is making in each
moment as they choose the relations with Existence in which they become involved, which
relations serve to create what they then, as Individual's, apprehend as experiential reality.
Now here it is important to make clear that even when an Individual understands and recognizes
the reflection-like nature of physical experience and so of physical reality, in which case physical
experience does not function as an illusion and so does not serve to hide from the Individual their
Nature, this does not mean that that Individual then experiences their Nature directly, as it is,
because the nature of experience is different than the Nature of the Individual, different than the
Nature of Existence, different than the Nature of Consciousness.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
466
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
No one in all of history has ever or will ever see their own face directly, as it is. In order to see
one's own face one has to use a reflective surface, in which case what one is seeing is a reflection
of their face, and not their face directly, as it is. And just as it is not possible for someone to see
their own face directly, as it is, it is not possible for Existence to know Itself directly, as it is,
because knowledge of any sort is always experiential in nature, always a reflection, and so is
always of a different nature than the Nature of the Individual, always of a different nature than
the Nature of That which, through relation to Itself, creates and apprehends experience.
So, in order to see your face you have to use a mirror, and what you see as a result is not your
face directly. Perfectly understandable. No problem. And for Existence to know Itself it too has
to use a Mirror, and what it then knows as a result is not Itself directly, but is a reflection of
Itself. And as will be described, it is the necessity and unavoidability of Existence's use of a
Mirror to know Itself, to see Itself, to experience Itself, that makes possible, but not unavoidable
nor inevitable, the functioning of maya, because a process that, on the one hand, makes it
possible for Existence to create an accurate reflection of Itself, by which means it can reveal
Itself to Itself, must, on the other hand, also make it possible for Existence to create an inaccurate
reflection of Itself, by which means it is then able to conceal Itself from Itself.
As will be described, the process of maya is intimately related to the experiential process, i.e. to
the process whereby Existence, at the level of the Individual, creates what it apprehends as
experience. Put another way, the process whereby Existence becomes both hidden from Itself, as
well as disguised so that it is not able to recognize Itself, to recognize its own reflection, cannot
be separated from the process whereby Existence, at the level of the Individual, creates
experiential reality. Therefore, in order to understand how maya functions to both hide Existence
from Itself, as well as disguise Existence so that it is not able to recognize Itself, it is necessary to
understand the experiential process, necessary to understand how Existence, at the level of the
Individual, creates and apprehends experience, in order that the limitations inherent in the
Individual's creation of experience can be understood, because, as will be shown, the functioning
of maya is ultimately the unavoidable and inviolable functioning of those limitations.
3. The Actual Nature and Limitations of Experience
The concept of maya can only have meaning in the context of a recognition that there is some
difference between what we experience as reality and the Reality that is actually there where
experience seems to be. And as the Reality that is actually there where experience seems to be is
also the Reality that, through relation to Itself, both creates and apprehends experience, that
context is provided by understanding how experience is created.
As described in my previous works,7 all experience is created as the result of some relation of
Existence to Itself. Specifically, when Existence is in relation to Itself a relative existence is
created where Existence is being in relation to Itself, which relative existence the Individual
Existence involved in that relation apprehends, from its perspective within that relation, as an
experiential reality. Different Existential relations create different relative existences that are
apprehended as different experiential realities. Thus, for an Individual to apprehend any specific
experience requires the involvement of that Individual in a specific relation with Existence. Put
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
467
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
another way, what any Individual experiences as reality, be it an experience of the emotional,
mental, or physical variety, is the product of a relation in which the Individual that is
apprehending the experience must themself be involved, as is shown in figure 3.
Individual
(Experiencer Reality)
Relational Structure
(Experienced Reality)
Relational Structure
Experiencer is penetrated by
Experienced Reality
Experiencer
Reality
Reality
Existence
Consciousness
mutually exclusive relations creating
complementary experiences of reality
Individual
(Experiencer Reality)
Relational Structure
(Experienced
Reality)
Relational
Structure
Reality
Existence
Consciousness
particle
experience
Experienced
Reality
created relative
existence
apprehended as
experience
mutually exclusive relations creating
complementary experiences of reality
Experiencer
Reality
wave
experience
Experienced
Reality
created relative
existence
apprehended as
experience
Experiencer penetrates
Experienced Reality
Figure 3. Depicted in these drawings are two different relations of Existence to Itself, each of
which creates what Existence apprehends as a different experiential reality. On the left the two
different relations of Existence to Itself are shown as a relation occurring between two different
Relational Structures, representing the Experiencer and the Experienced Realities. On the right
the two different relations of Existence to Itself are shown in close up, depicting the relative
existence created as the product of each of those relations, which relative existence is what is
apprehended from the perspective of the Individual, i.e., the Experiencer Reality, as an
experience or experiential reality. The two different Existential relations shown in this drawing
are, with respect to a single Individual and a single Experienced Reality, mutually exclusive in a
given moment, because each requires the involvement of the Individual in a relation that makes
impossible the simultaneous involvement of that Individual in the other, mutually exclusive
relation. Mutually exclusive relations always create opposite or complementary experiences,
depicted here as the creation of the opposite or complementary experiences of wave and
particle.
As already stated, the product of the relation of Existence to Itself that is ultimately apprehended
as an experience by the Individual is referred to as a relative existence. That product is referred
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
468
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
to as a relative existence because it only exists as a product of, and in the context of, the relation
of Existence to Itself that creates it. Thus, the relative existence created by the relation of
Existence to Itself exists, but it does not exist in the same way that Existence Exists, because as a
relative existence its existence, such as it is, is dependent on a relation, whereas the Existence of
Existence is not dependent on any relation. Existence is in relation to Itself because it Exists,
whereas relative existences only exist because there is some relation of Existence to Itself
occurring. Thus, the nature of experience is completely different and other than the Nature of the
Existence that, through relation to Itself, both creates and apprehends experience.
The relative existence created by any relation of Existence to Itself is like a boundary or
reflection that arises where Existence is being in relation to Itself, and what an Individual point
of Existence, or simply an Individual Existence, apprehends as experience is that boundary or
reflection as it appears or is apprehended from the side of the relation composed of that
Individual Existence. Thus, what an Individual apprehends as experience is not What Is Actually
There, but rather is the apprehension of the boundary, the relative existence, the reflection, that is
created where the Existence That Is Actually There as the Individual is in relation to the
Existence That Is Actually There, i.e., the Underlying Actuality, where the created experience
seems to be, as that boundary is apprehended from the Individual's side of the relation.
Thus, the created relative existence is not apprehended as an experience in its totality, but rather
is apprehended as an experience as it appears or presents itself to the Existence that composes
only one side of the relation that creates it, which Existence we call the Individual. For this
reason, experience is not just the product of a relation, but it is also the product of a perspective
within a relation. Put another way, experience is not just the product of a relation of Existence to
Itself, but it is also the product of the perspective of the Individual Existence that is involved in
that relation. Understanding this point regarding the role the Individual's perspective plays in
determining what an Individual apprehends as experience is of vital importance, since it is the
necessity of the Individual's perspective in the creation and apprehension of any experience that
is central to both the duality inherent in all experience, as well as the limitations inherent in the
Individual's creation of experience.
Specifically, the duality inherent in all experience has as its basis two factors. The first factor is
that the created relative existence that is ultimately apprehended by the Individual as experience
is the product of a relation and thus always has two sides. The second factor is that what an
Individual apprehends as experience is that relative existence as it appears from only one side of
the relation that creates it or brings it into relative existence. Thus, every experience has as its
basis a created relative existence of which only one side is apprehended by any one Individual as
an experience. And for every side of every relative existence that is apprehended as an
experience, there is an opposite or complementary side which, if it were to be apprehended
instead, would be apprehended as the opposite or complementary experience. It is for these
reasons that all experiences come in pairs of opposites or complements; e.g., up/down, hot/cold,
good/bad, positive/negative, wave/particle, position/momentum, light/dark, etc., etc., etc.,
because anything that we experience is our apprehension of only one side of what is always a
two-sided reality. Thus, what we experience is not What Is Actually There, but rather is our
apprehension of something that is created according to a relation in which we, as Individuals, are
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
469
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
involved, and which created something then, by its nature, has two opposing sides and so two
potentially opposite ways of being apprehended as an experience.
However, we do not, as Individuals, create a relative existence through our involvement in some
relation with Existence and then choose our perspective upon the created relative existence, in
which case we would then be choosing which of the two opposite or complementary experiences
we would apprehend as a result of our involvement in that particular relation. Rather, it is our
involvement in the relation as the relative existence is created that also determines our
perspective upon that created relative existence, which perspective then determines which one of
the two opposite or complementary experiences we apprehend as a result of our involvement in
that particular relation. Put another way, we do not get to be involved in some relation with
Existence and then choose whether we will apprehend the created relative existence as this or
that experience. Rather, it is how we choose to be involved in any relation with Existence that
itself determines whether we will apprehend the relative existence created as a result of that
relation as this or that experience. Thus, to change what we experience from this to that we have
to change our perspective, and to change our perspective we have to change our involvement in
the relation that is creating the experience. This is a subtle distinction, but it is a vital distinction
if one is to understand the unavoidable and inviolable limitations upon the Individual's creation
of experience that are central to the functioning of maya.
3.1 The negative and positive experiential limitations
As was shown in figure 3, opposite or complementary experiences are produced by an
Individual's involvement in opposite relations. The importance of this is that opposite relations
are, for a single Individual in a single moment, mutually exclusive, meaning that if the Individual
is involved in one relation then they are also, by definition, not involved in the opposite relation.
For example, if you are looking north then you are also, by definition, not looking south. What
this means is that, for a single Individual, being involved in a relation with an Underlying
Actuality that creates a relative existence that is apprehended from the Individual's perspective
within that relation as a particular experience makes it impossible for that same Individual, in
that same moment, to be involved in the opposite relation with that same Underlying Actuality
necessary for that Individual to create and apprehend the opposite or complementary experience.
Therefore, with respect to a single Underlying Actuality, it is not possible for an Individual to
simultaneously apprehend opposite or complementary experiences, because it is not possible for
an Individual to be simultaneously involved in the mutually exclusive relations necessary for
their creation.
Further, if it is not possible for an Individual to become involved in a relation that is mutually
exclusive of a relation in which they are already involved, and in which they continue to be
involved, then the corollary to this limitation is that, with respect to a single Underlying
Actuality, it is only possible for an Individual to become involved in relations that are mutually
inclusive of whatever relations in which they are already involved, and in which they continue to
be involved. In terms of experience, if it is not possible for an Individual to create and apprehend
an experience that would require their involvement in a relation that is mutually exclusive of a
relation in which they are already involved, then it is only possible for an Individual to create and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
470
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
apprehend experiences that require their involvement in relations that are mutually inclusive of
relations in which they are already involved.
Thus, in describing experience as being the product of a relation in which the Individual that is
apprehending the experience must themself be involved, which description makes clear the basis
of the duality inherent in all experience, what has also been uncovered are two unavoidable
limitations inherent in the Individual's creation of experience. These two experiential limitations
restrict what it is possible for an Individual to create and apprehend as experience in any moment
as a result of the limitations upon the relations in which an Individual can become involved in
that moment according to the relations in which that Individual must already be involved in that
moment in order to create what they are already, in that moment, apprehending as experience.
The first experiential limitation is a limitation with regard to what it is not possible for an
Individual to create and apprehend as experience in any one moment with respect to a particular
Underlying Actuality, and the second experiential limitation is a limitation regarding what it is
only possible for an Individual to create and apprehend as experience in any one moment with
respect to a particular Underlying Actuality. Thus, these two experiential limitations limit what it
is possible for an Individual to create and apprehend as experience in any moment by limiting the
relations in which an Individual can become involved in a negative and a positive way, i.e., in a
way that is negatively restrictive and in a way that is positively restrictive.
The experiential limitation that is negatively restrictive regarding what it is possible for an
Individual to create and apprehend as experience in any one moment exists because it is not
possible for an Individual to be simultaneously involved in the mutually exclusive relations
necessary to create opposite or complementary experiences. Thus, the negative experiential
limitation limits what an Individual can experience according to what they are already
experiencing by making it impossible for an Individual to become involved in the mutually
exclusive relations necessary for them to create and apprehend whatever experiences are the
opposite of those they are already, in that moment, creating and apprehending. Thus, the negative
experiential limitation dictates what it is not possible for an Individual to create and apprehend as
experience according to what that Individual is already creating and apprehending as experience.
In essence, what the negative experiential limitation means is that for every relation in which an
Individual is involved, which relation creates something that Individual apprehends as
experience, there is a mutually exclusive relation in which that Individual cannot, in that same
moment, be involved. Thus, for everything an Individual experiences there is an opposite
experience which that Individual cannot, under any circumstance, apprehend as an experience in
that same moment, because apprehending that opposite experience would require that the
Individual be in the impossible position of being simultaneously involved in mutually exclusive
relations, e.g., facing north and south at the same time.
The experiential limitation that is positively restrictive regarding what it is possible for an
Individual to create and apprehend as experience in any moment also exists because it is not
possible for an Individual to be simultaneously involved in the mutually exclusive relations
necessary to create opposite or complementary experiences. And because it is not possible for an
Individual to be simultaneously involved in mutually exclusive relations, it is only possible for
an Individual to be simultaneously involved in mutually inclusive relations, meaning that it is
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
471
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
only possible for an Individual to create experiences that require their involvement in relations
that are mutually inclusive of relations in which they are already involved. Thus, while the
negative experiential limitation dictates what an Individual cannot experience according to what
they are already experiencing, the positive experiential limitation dictates what an Individual
must experience according to what they are already experiencing, because anything and
everything that an Individual apprehends as an experience requires the involvement of that
Individual in a relation, and the involvement of an Individual in any relation makes their
simultaneous involvement in certain other relations impossible, while also making their
simultaneous involvement in certain other relations unavoidable.
Thus, one experiential limitation has as its basis the impossibility of an Individual's simultaneous
involvement in mutually exclusive relations while creating experience, while the other has as its
basis the necessity of the Individual's simultaneous involvement in mutually inclusive relations
while creating experience. In essence, one experiential limitation restricts what an Individual can
know according to what they are already knowing, while the other experiential limitation dictates
what an Individual must know according to what they are already knowing.
It is the negative experiential limitation that is responsible for the phenomena of wave-particle
duality and quantum uncertainty, in which situations what can be known is being limited by what
is already being known, as what is already being known is the product of a relation that makes
impossible the Individual's simultaneous involvement in the mutually exclusive relation
necessary to create the opposite knowing, i.e., the opposite experience. Thus, the Actualities
underlying what are apprehended as quantum realities appear as either waves or particles, and
the extent to which one aspect of quantum reality is known limits the extent to which the
opposite aspect of that quantum reality can be known, e.g., position and momentum, because
what is known is always the product of a relation and not What Is Actually There, and so what
can be known is always limited by the Individual's inability to be simultaneously involved in the
mutually exclusive relations with an Underlying Actuality necessary to create the opposite or
complementary experiences that are apprehended as the opposite or complementary
characteristics or properties of a quantum reality.
On the other hand, it is the positive experiential limitation that is responsible for the phenomenon
of quantum non-locality, in which situations what can be known is being dictated by what is
already being known. For example, if one wants to measure the spin state of two electrons that
are entangled, i.e., which have interacted in a way such that "each resulting member of a pair is
properly described by the same quantum mechanical description (state), which is indefinite in
terms of important factors such as position, momentum, spin, polarization, etc.,"8 before any
measurement of either is made it is not possible to predict the spin state of either. However, once
the spin state of one electron has been observed or created as an experience, the observed or
created spin state of the other becomes completely predictable, as it is always found to be in the
opposite state. Further, this correlation between the observed spin states occurs regardless of the
distance between the two electrons and occurs faster than light can travel between them,
implying what is referred to as a non-local effect or what Einstein referred to as spooky action at
a distance. Quantum non-locality, like wave-particle duality and quantum uncertainty, is purely
an experiential phenomenon, i.e., a phenomenon that has as its basis the limitations inherent in
the Individual's creation of experience. Specifically, when a system is entangled that system
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
472
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
functions as a single Underlying Actuality, and any relation in which an Individual becomes
involved with that system, owing to the positive experiential limitation, limits other relations in
which that Individual can become involved with that same system to those relations that are
mutually inclusive of their previously established relation, thereby dictating the nature of that
Individual's subsequent relations with that system, which in turn dictates the experiences it is
possible for that Individual to create and apprehend through involvement in a subsequent
relation with that system.
Thus, when an Individual is involved in a relation with an entangled system that creates the
experience of one electron as having a clockwise spin, that Individual, owing to the positive
experiential limitation, no longer has two possible ways of being in relation to that system in a
way that will create the experience of electron spin direction, and so no longer can create,
through relation to that system, the unpredictable experience of the other electron having either
clockwise or counterclockwise spin, since the Individual's prior involvement in a relation with
that system limits their subsequent involvement in a relation with that system to a relation that is
mutually inclusive of the prior relation and so limits their subsequent involvement in a relation
with that system to just one of the two previously possible relations, and specifically limits their
subsequent involvement to the relation that is mutually inclusive of their already established
relation with that system, thereby limiting their subsequent involvement in a relation with that
system to one that has a predictable experiential outcome, since experience is always the product
of a relation. That is, since experience is always the product of a relation in which the Individual
that is apprehending the experience must be involved, dictating the Individual's involvement in a
subsequent relation based upon their prior involvement in a relation is the same as dictating the
subsequent experience that Individual creates and apprehends based upon the experience that
Individual previously created and apprehended. And as it is the positive experiential limitation
that, with respect to a unitary or entangled quantum system, dictates an Individual's involvement
in subsequent relations based upon their involvement in prior relations by only allowing the
Individual to become involved in subsequent relations that are mutually inclusive of previously
established relations, it is therefore the positive experiential limitation that is the basis of the
phenomenon of quantum non-locality displayed by entangled systems, i.e., systems that are
functioning as a single Underlying Actuality.
And both of these experiential limitations, i.e., the negative and the positive, have as their basis
the necessity of the Individual's involvement in a particular relation in order to create what that
Individual apprehends as a particular experience, which involvement in a particular relation
imposes negative and positive restrictions with regard to other particular relations in which that
Individual can become simultaneously involved, making some relations impossible and others
unavoidable, and so making some experiences impossible to create and apprehend, thereby
producing the phenomena of wave-particle duality and quantum uncertainty, while making
others impossible not to create and apprehend if they are to be created and apprehended at all,
thereby producing the phenomena of quantum non-locality.
However, these experiential limitations do not operate at the quantum level alone. Rather, these
experiential limitations operate at all levels of experience, in the creation of everything we
apprehend as experience, be it an experience of the emotional, mental, or physical variety. It is
just that we do not recognize the operation of the experiential limitations at these levels as their
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
473
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
functioning is so integral to and so interwoven into the fabric of our Individual experiential
realities that their results, and so the limitations themselves, go completely unnoticed. Unnoticed
that is, until one realizes that they exist and then looks for evidence of their operation, in which
case such evidence is found lying about all over the place.
One example of the functioning of the experiential limitations in our everyday creation of
experience is found in how we experience emotions, in that it is the negative experiential
limitation, functioning at the level of Existential Self-Relation that creates what we apprehend as
emotional experience, that causes us to feel either good or bad, but not both simultaneously, i.e.,
create and apprehend in any moment either a wanted or unwanted emotional experience, because
while involved in the relation in which we create and apprehend one emotional experience, we
cannot be involved in the mutually exclusive relation necessary to create the opposite emotional
experience.
Another example of the functioning of the experiential limitations in our everyday creation of
experience is found in how we experience conceptual reality, in that it is the negative
experiential limitation, functioning at the level of Existential Self-Relation that creates what we
apprehend as mental experience, that results in the situation that for everything you know there is
an opposite idea, thought or concept that you cannot know in that same moment, because in
order to know that opposite concept you would have to be involved in a relation that is mutually
exclusive of the relation in which you must already be involved in order to know what you
already know. For example, you cannot know that the earth is round while knowing it to be flat,
and you cannot believe in evolution while believing that the universe was created in six days,
and you cannot know Consciousness-Existence to be What Is Actually There while knowing
physical reality as what is actually there.
It is also the functioning of the negative experiential limitation that is the basis of most, if not all,
interpersonal conflict, because most, if not all, interpersonal conflict has as its basis the complete
inability and utter impossibility of each Individual involved in the conflict to see the other's side,
to experience what the other is experiencing as reality, as long as each is unwilling to let go of
their own reality. Because as long as each Individual involved in the conflict clings to their
reality, they are each obligated to remain involved in the relation that is creating that experience
as their reality, in which case it is simply not possible for either of them to become involved in
the opposite, mutually exclusive relation in which they must be involved if they are to apprehend
what the other Individual is apprehending as reality. And because almost no one understands
this, and even if they do they can quite easily lose sight of it, each Individual involved in the
conflict cannot understand how the other Individual can be so blind as to not see what is to them
so very clear and simple. But what they do not know, and what almost no one knows, is that
because experience does not just already exist waiting for us to happen across it, but rather is
created by us according to a relation in which we, as Individuals, must be involved, it is simply
not possible for two Individuals that are actively involved in creating opposite experiences to
apprehend as real, i.e., realize, what the other considers to be their reality.
The practical effect of the negative experiential limitation is that it creates, for each and every
Individual, for each and every point of Consciousness, regardless of scale, an experiential blind
spot consisting of whatever experiences are the opposite of those that the Individual is presently
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
474
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
involved in creating and apprehending. Again, what this experiential limitation means is that for
everything you experience there is an opposite experience, an opposite experiential reality, that
you cannot, in that same moment, create and apprehend, in which case then the particular
experiences you cannot create are not, for you, realities, and so for you are not real. And yet, for
another Individual that is involved in the opposite relations and so creating and apprehending the
opposite experiences, those opposite experiences are their reality, and for them are quite real, in
which case, from their perspective, it is your experiences that are not a reality, your experiences
that are unreal.
And while it is the negative experiential limitation that creates the experiential blind spot, it is
the positive experiential limitation that fills in that blind spot, allowing us to remain unaware that
there even is an experiential blind spot, which is what a blind spot is, which is a place you cannot
see but do not know you cannot see because you think you are seeing what is there. For
example, while conceiving of the earth as being flat it is not possible to conceive of the earth as
being round. Thus, the idea of a round earth is, in this case, what lies in the experiential blind
spot. However, while conceiving of the earth as being flat it is possible, owing to the positive
experiential limitation, to conceive of the falseness of the idea of the earth as being round,
thereby filling in the blind spot with an experience that contains the opposite conception, yet
remains mutually inclusive of the primary or more proximal conception of the earth as being flat.
Thus, almost no one ever realizes that they cannot experience the opposite of what they are
already experiencing, because the experiential blind spots created by the negative experiential
limitation are filled in by seemingly opposite experiences that are, owing to the functioning of
the positive experiential limitation. actually mutually inclusive of the experiences that one is
already creating and apprehending.
It is the positive experiential limitation that keeps our experiences consistent, regardless of
whether or not those experiences accurately or inaccurately reflect What Is Actually There, so
that when up is seen as down, down, if it is to be seen at all, must be seen as up, and when effect
is seen as cause, cause, if it is to be seen at all, must be seen as effect. It is the positive
experiential limitation that causes Individuals who identify themselves as members of a group,
e.g.., political, religious, or national, and who further identify their group as "good" and "right,"
to invariably see opposing groups, as well as their members, as "bad" and "wrong." And so while
the negative experiential limitation lays the foundation for interpersonal conflict by blinding an
Individual to any opposing reality as long as they cling firmly to their reality, i.e., as long as they
remain involved in the relation that is creating that experience as their reality, it is the positive
experiential limitation that fuels those conflicts by causing Individuals to label other Individuals
they perceive as being in opposition to them in a way that is the opposite of the way they label
themselves, which labels then serve to justify actions which, if performed on a member of one's
own group, would be perceived as bad and wrong, but when performed on a member of an
opposing group are able to be perceived as good and right.
So it is that these two experiential limitations are interwoven into each of our experiential
realities, influencing the patterns we each weave as we each create our own unique experiential
reality according to the relations in which we, as Individuals, are involved, by limiting our
involvement in some relations, thereby preventing the creation of some experiences, and
requiring our involvement in other relations, thereby dictating the creation of other experiences.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
475
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
And as will be described, the functioning of maya is ultimately nothing more than the
unavoidable functioning of these two experiential limitations, operating in concert, to first hide
from us our Nature, through the functioning of the negative experiential limitation, once we
mistake physical-experiential reality for what is actually there, followed by the disguising of our
Nature, through the related functioning of the positive experiential limitation, so that even when
we apprehend that which accurately reflects our Nature it appears as something other than our
Nature. Thus, what will be shown is that maya, as the phenomenon that that hides from the
Individual both the Nature of the universe as well as their own Nature, is a result of the
unavoidable and inviolable functioning of the two experiential limitations, which two
experiential limitations are themselves an unavoidable result of the way experience is always
created as the product of an Existential relation in which the Individual that is apprehending the
experience must always be involved and must always occupy a particular perspective.
However, became the functioning of maya hinges upon an Individual conceiving of physical
reality, or some more subtle experiential reality, as being what is actually there, which
conception itself hinges upon the Individual conceiving of physical reality or experiential reality
as being Experiencer independent, i.e., existent as it is experienced to exist in the absence of the
Individuals experience of it as such, before moving on to describe in more detail how these
experiential limitations function in concert to create the phenomenon referred to as maya, it will
be helpful to understand why it is that, although experience is actually Experiencer dependent,
and so has inherent limitations in its creation with respect to a single Individual in a single
moment, it nonetheless appears to be Experiencer independent. For this reason, what will be
explained in the next section is why experience can, up to a point, present us with the illusion
that it is Experiencer independent, with the illusion that what we experience to exist exists as
that, i.e., as an experience, whether we are experiencing it or not, and so presents us with the
illusion that physical experience is what is actually there, which illusion is necessary for the
functioning of maya, i.e., for the experiential limitations to function in concert to conceal from
the Individual both their own Nature as well as the Nature of the universe.
4. The Seeming Nature of Experience
In this section what will be explained is why even though experience is always actually
Experiencer dependent, it nonetheless appears to us as being Experiencer independent. The
purpose of explaining this is like the purpose of explaining to someone the hidden mechanics of
how a magic trick is done, which is to offer an alternative explanation of how the rabbit came to
be pulled out of the hat, because in the absence of that explanation one is left to believe that the
rabbit did actually materialize out of thin air. Likewise, in the absence of understanding the
slights of hand that cause experience to appear to be Experiencer independent, one is left with
the impression that experience is truly Experiencer independent. And owing to the negative
experiential limitation, conceiving of experience as being Experiencer independent makes it
impossible for one to conceive of experience as being Experiencer dependent, as being
something that the Individual that is apprehending the experience always has a hand in creating,
which conception is necessary if one is to understand how maya functions to conceal from the
Individual the Nature of Reality.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
476
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
Conceiving of experience as being Experiencer independent is not unreasonable, given the way
in which physical experience presents itself to us. However, no matter how much it seems that
experience is Experiencer independent, no matter how much it seems that things exist as they are
experienced to exist even in the absence of their being experienced as such, no matter how much
it seems that what we experience as physical reality is what is actually there, none of this is the
case. In the same way, at one time it was not unreasonable to conceive of the earth as being flat,
because from a limited perspective that is how the earth presented itself or appeared, and we
know how that turned out. Likewise, idea of experience as being Experiencer independent is the
flat earth idea of our time, because even though there is irrefutable evidence to the contrary in the
form of the phenomena of wave-particle duality, quantum uncertainty, and quantum non-locality,
that evidence goes both unnoticed and is misinterpreted, i.e., is both hidden and disguised,
because it does not fit into the presently held conceptual framework of experience as being
Experiencer independent, which framework is derived from what appears or seems to be the case
with regard to gross physical experience.
Because the seeming Experiencer independence of experience derives from its nature as both the
product of a relation, as well as the product of a perspective within that relation, it was necessary
to first explain why experience is actually Experiencer dependent in order to now be able to
explain why experience seems to be Experiencer independent. Put another way, it is the actual
Experiencer dependent nature of experience that is the basis of its seeming Experiencer
independence. Specifically, the reason experience seems Experiencer independent is because
consistent Existential relations occurring at different times for the same Individual, or at the
same time for different Individuals, create consistent relative existences that are then
apprehended by the Individual or Individuals from consistent perspectives as consistent and
seemingly identical experiences, thereby creating the illusion that what we experience as
physical reality exists as that, i.e., as a physical reality, whether we are experiencing it or not.
That is, it is the consistency and seeming identicalness of experience occurring at different times
for the same Individual that allows us to extrapolate between experiences and imagine there to be
an existent experience where there actually is none. For example, every time you walk into a
room you see what appears to be the same chair. You see, i.e., visually experience, what appears
to be the same chair, not because it actually is the same experience, but because the Underlying
Actualities or Relational Structures composed of Existence that are involved in the relation, i.e.,
the Experiencer and Experienced Realities, are in essentially the same configuration and relation
to each other as they were before, and therefore the relation between them produces a nearly
identical relative existence, which is then apprehended by the Individual from the same general
perspective within that relation as what seems to be the same experience, when in actuality it is a
new and unique experience created by the Existential relation that is happening now, in the
present moment. It may seem or appear to be the same experience, but that is an illusion, as the
prior experience was the result of a relation that was occurring in a prior moment. In the same
way, one may jump repeatedly off the same dock into what they consider to be the same river,
but the river into which they jump now is different than the river into which they jumped before,
because the river, like the Existence that underlies experience, is flowing. For this reason, no two
Existential relations in any two moments are, for a single Individual, ever truly identical, and so
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
477
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
no two experiences, which are the products of those two relations, can themselves ever be truly
identical.
What creates the illusion of our having the same experience is our ability to imagine that the
experience was there the whole time, even when we were not experiencing it, i.e., even when we
were not involved in the relation that was creating it as an experience. For example, if you stand
in front of a mirror and view your reflection and then step away, you do not consider the mirror
to still contain your reflection once you have stepped away, because you understand that the
reflection is the product of a relation between yourself and the mirror, and so you do not imagine
the reflection to still be there once the relation that creates it is no longer operant. And so when
you step in front of the mirror again and create another reflection, even though the reflections
may seem identical, you recognize this as a new and different reflection, because you understand
that in the moment before there was no reflection. On the other hand, because people do not
generally recognize experience as being the product of a relation, they imagine that the
experience is still there even when the relation that creates the experience is no longer operant,
and so when they create, in a later or subsequent now, in a different moment, a very similar and
seemingly identical experience, they are able to create the illusion for themselves that it is the
same experience because they imagine a continuity of experience between the experience then
and now that does not actually exist.
And this illusion of the continuity and Experiencer independence of gross physical experience is
reinforced by other Individuals, who assure us that they are experiencing the same object that we
are experiencing, and who also inform us that even when we are not in the room that there is still
a chair in the room. However, the reason it seems that different Individuals are having the same
experience at the same time, or at different times, is for the same reason that it seems that the
same Individual is having the same experience at different times, which is owing to the
consistency of the Existential relations and perspectives that create the relative existences being
apprehended by different Individuals as different, yet seemingly identical, experiences.
Specifically, when two or more Individuals of the human variety are being in relation to the same
Underlying Actuality, in relation to the same Relational Structure, those Individuals are each
forming their relations to that Underlying Actuality using nearly identical Relational Structures
of their own, which Relational Structures we apprehend and refer to as the physical senses, i.e.,
the specific sensory devices that allow us to be in relation to Existence around us in a way that
creates the physical experiential realties of sight, sound, smell, taste, and touch. What we
experience as physical reality in general is the product of the relation of those sensors, which are
themselves Relational Structures, to the Relational Structure that is actually there where the
physical experience seems to be. What we experience as physical reality in particular is the
product of the relation of those sensors, which again are themselves Relational Structures, to the
specific Relational Structure that is actually there, as that product, that relative existence, is
apprehended from our side of the relation, i.e., from our perspective within the relation that
creates the relative existence we apprehend as a specific physical experience. And so when we,
or any other human Individual or Individuals, are creating a physical experience as a result of
being in relation to the same underlying Relational Structure, we are each actually creating and
apprehending our own unique experience as a product of our own unique, though nearly
identical, relation to What Is Actually There. And because the relations that create the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
478
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
experiences are nearly identical, as are the general perspectives, the created relative existences
are apprehended by different Individuals as a very similar or nearly identical experience, and so
are assumed by those Individuals to be the same experience, thereby reinforcing the illusion of
the seemingly Experiencer independent nature of experience in general and physical reality in
particular.
However, it is only because we are each, in the case of the creation of a particular physical
experience or reality, using almost identical Relational Structures to be in relation to the same
underlying Relational Structure or Underlying Actuality from the same Existential perspective
that the relative existences created as the product of those different relations are very similar and
so are apprehended by different Individuals as what are assumed to be the same physical
experience, even though each Individual is actually creating and apprehending their own unique
experience created as a product of their own unique relation to the Underlying Actuality. For
example, if there are fifty people in a room looking at what seems to be the same chair, there are
really fifty different experiential chair realities being created and apprehended in that moment.
This is somewhat analogous to what would happen if there were fifty people standing around the
perimeter of a very large room unknowingly facing a large reflective pillar at the center, in as
much as each person would then see a person reflected in the mirror, in which case they could
then tell each other that what they saw as they looked toward the middle of the room was a
person, in which case they might assume they were all seeing the same person, when what each
would actually be seeing is their own reflection created by their own unique relation to the
reflective surface.
Experience is the Individual's apprehension of the relative existence created as the product of the
relation between What Is Actually There where they are and What Is Actually There where the
experience seems to be, as that relative existence is apprehended from the side of the relation
occupied by the Individual, i.e., from the Individual's perspective, and that relative existence is
unique to each Individual in each moment, in each now. That relative existence is unique to the
Individual that is apprehending the experience because that relative existence only exists, as it
were, owing to the Individual's involvement in the relation that creates it. Therefore, in the
absence of the Individual's involvement in a particular relation there is no created relative
existence for that Individual to apprehend as a particular experience. There may be another
Individual creating a relative existence which that other Individual apprehends as an experience,
but that created relative existence is only apprehended as an experience by the Individual that is
themself involved in the relation that creates it. Put another way, no Individual apprehends as an
experience the relative existence created by another Individual's involvement in a relation,
because relative existences only exist, and so are only real, in the context of some relation of
Existence to Itself. Therefore, in the absence of an Individual's involvement in a particular
relation, there is, for that Individual point of Existence, no particular relative existence created
and so nothing for that Individual to apprehend as a particular experience.
Again, whatever we apprehend as experience we ourselves create according to whatever
relations in which we, as Existence, as Individuals, are involved with the rest of Existence. Thus,
that we are each, as different Individuals, ever having what is actually the same physical
experience is an illusion, fostered by the similarity of the experiences that we each create when
in relation to the same Underlying Actuality from the same general perspective. And so it is that
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
479
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
the similarity and nearly identicalness of physical experience for a single Individual at different
times, and for different Individuals at the same time, help create the illusion that experience is
Experiencer independent, which is to say, the illusion that experience exists as we experience it
to exist even when we are not experiencing it, the illusion that experience exists as we
experience it to exist even when we are not involved in the particular relation necessary to create
the particular relative existence that, from a perspective within that relation, is apprehend as a
particular experience.
4.1 Why the seeming nature of experience breaks down in the creation of quantum
experience
Although the illusion of experience as Experiencer independent is generally upheld in the
creation of gross physical experience, that illusion breaks down in the creation of quantum
experience, i.e., in the creation of physical experience at the sub-microscopic level, revealing
experience to be Experiencer dependent. However, owing to the unavoidable functioning of the
experiential limitations, even when the curtain is pulled aside, as it is by the phenomena of waveparticle duality, quantum uncertainty, and quantum non-locality, thereby revealing experience to
be Experiencer dependent, it is still not possible to comprehend what is being revealed as long as
one continues to hold fast to the notion of experience as being in some way Experiencer
independent, i.e., as having some sort of truly objective existence.
The reason that the illusion of experience as being Experiencer independent breaks down at the
quantum level was explained in detail in my paper The Experiential Basis of Wave-particle
Duality and The Uncertainty Principle.9 In short, the reason experiences created at the quantum
level reveal the Experiencer dependent nature of experience is because in relations occurring at
that level, unlike relations occurring at the gross physical sensory level, the Individual that is
creating and apprehending the experience, i.e., the experimental result, is able to adopt opposite
perspectives at different times with respect to the Underlying Actuality they are being in relation
to in order to create the relative existence they are apprehending as an experience, i.e., as an
experimental result, and so can, at different times, create opposite experiences, e.g., wave and
particle, as a result of their involvement in those opposite and therefore mutually exclusive
relations. However, owing to the negative experiential limitation, which precludes an Individual
from being involved simultaneously in opposite and therefore mutually exclusive relations with
the same Underlying Actuality, an Individual can only adopt one perspective at a time with
respect to any one Underlying Actuality and so can create, in any one moment, as the result of
any one relation, only one of the two opposite and complementary experiences, or some portion
of each, that it is possible to create through relation to that Underlying Actuality, e.g., wave or
particle, or complete knowledge of position and no knowledge of momentum, or partial
knowledge of both position and momentum.
And the reason that, at the quantum level, an Individual can adopt different perspectives at
different times with respect to the Underlying Actuality that they are being in relation to in order
to create the relative existences they then apprehend as different experiences, i.e., as different
experimental results, is because, at the quantum level, the Individual must use intermediary
sensory devices, rather than just the physical senses, in order to be in relation to the Underlying
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
480
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
Actuality in a way that creates what that Individual then apprehends as those quantum
experiences or quantum experimental results. And it is the necessary use of those intermediary
sensory devices that allows the Individual a degree of freedom that is not afforded by the
physical senses with regard to how they can approach or be in relation to an Underlying
Actuality, which additional degree of freedom makes it possible for an Individual that is creating
experience using intermediary sensory devices to, in different moments, be involved in opposite
and so otherwise mutually exclusive relations with an Underlying Actuality and so, in different
moments, be in relation to that Underlying Actuality from opposite perspectives, thereby creating
opposite or complementary experiences as a result of their involvement in those opposite
relations with that Underlying Actuality, as was shown in figure 2.
Conversely, when using our physical senses, or devices that are direct extensions of those senses,
e.g., a microscope, our relation to the Underlying Actuality always occurs from the same
perspective and so always produces a relative existence apprehended as the same general
experience. For example, when using our senses to be in relation to the Underlying Actuality or
Relational Structure that we apprehend as a rock, the rock is always experienced as being hard,
because the relation of its Relational Structure to our Relational Structure is always the same, in
that the Underlying Actuality or Relational Structure that is there where we apprehend the rock is
always more rigid than the Underlying Actuality or Relational Structure that is here where we
are. Likewise, when using our senses to be in relation to the Underlying Actuality that we
apprehend as water, the water is always experienced as being soft, because the relation of its
Relational Structure to our Relational Structure is always the same, in that the Underlying
Actuality that is there where we apprehend water, at least in the liquid form, is less rigid than the
Underlying Actuality that is here where we are.
However, if the Underlying Actuality or Relational Structure where we are was somehow more
rigid than the Underlying Actuality or Relational Structure where a rock is apprehended as being,
or less rigid than the Underlying Actuality or Relational Structure where water is apprehended as
being, then our perspective within those relations would be reversed, or the opposite of the norm,
in which case the experiences we would then create and apprehend as a result of our relations to
those Underlying Actualities would themselves be the opposite of the norm, i.e., the rock would
seem soft and the water, in liquid form, would seem hard. However, these reversals of relation
and perspective, and so of created experience, do not occur in everyday sensory experience, but
they are able to occur in the creation of quantum experience, i.e., in the creation of quantum
experimental results, owing to the Individual's unavoidable use of intermediary devices to
become involved in the relations that create what that Individual ultimately apprehends as
quantum experience or quantum reality.
The reasons just presented explaining why the illusion of experience as being Experiencer
independent is reinforced at the gross physical level, while that same illusion breaks down at the
quantum level, are fully consistent with the description of experience as always being both the
product of a relation in which the Individual that is apprehending the experience must themself
be involved, as well as a product of the Individual's perspective within that relation, and so
provide further evidence regarding the accuracy of the description of experience that is being
presented here, which description holds that experience is always Experiencer dependent. Thus,
no matter how much it may seem or appear that experience is Experiencer independent,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2013 | Volume 4 | Issue 5 | pp. 458-481
481
Kaufman, S. E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of Experience Function
to Conceal the Nature of Reality (Part I)
experience of every sort, i.e., emotional, mental, and physical, is always actually Experiencer
dependent. Put another way, no matter how much it may seem or appear that experience is
Experiencer independent, experience does not exist in the absence of the Individual's
apprehension of it as such, i.e., as an experience. Put yet another way, experience does not exist
in the absence of the Individual's involvement in, as well as perspective within, a relation that
creates what that Individual apprehends as experience.
(Continued in Part II)
References
1
(2003) The Complete Works of Swami Vivekananda (Advaita Ashrama) Vol 1 pp. 363-364
Kaufman, S. E. (2001) Unified Reality Theory: The Evolution of Existence Into Experience. (Destiny
Toad Press, Milwaukee)
3
Kaufman, S. E. (2011) Introduction to Existential Mechanics: How the Relations of Existence to Itself
Create the Structure of Reality and What We Experience as Reality. Journal of Consciousness
Exploration and Research, 2(9), pp. 1299-1314
4
(2003) The Complete Works of Swami Vivekananda (Advaita Ashrama) Vol 2 p. 89
5
Ibid., p. 105
6
Ibid. 3
7
Ibid. 2, 3
8
Wikipedia: Quantum Entanglement
9
Kaufman, S. E. (2011) The Experiential basis of Wave-particle Duality and The Uncertainty Principle.
Prespacetime Journal, 2(4) pp.544-573
2
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
This is a preprint submitted to the symposium on the meta-problem of
consciousness in the Journal of Consciousness Studies announced in mid-2018 at
https://www.imprint.co.uk/call-for-paper-the-meta-problem-of-consciousness/
The meta-problem and the transfer of
knowledge between theories of
consciousness: a software engineer’s take
Marcel Kvassay
Institute of Informatics, Slovak Academy of Sciences,
Dúbravská cesta 9, 845 07 Bratislava 45, Slovak Republic
marcel.kvassay@savba.sk
Abstract
This contribution examines two radically different explanations of our phenomenal intuitions,
one reductive and one strongly non-reductive, and identifies two germane ideas that could
benefit many other theories of consciousness. Firstly, the ability of sophisticated agent
architectures with a purely physical implementation to support certain functional forms of
qualia or proto-qualia appears to entail the possibility of machine consciousness with qualia,
not only for reductive theories but also for the nonreductive ones that regard consciousness as
ubiquitous in Nature. Secondly, analysis of introspective psychological material seems to hint
that, under the threshold of our ordinary waking awareness, there exist further ‘submerged’ or
‘subliminal’ layers of consciousness which constitute a hidden foundation and support and
another source of our phenomenal intuitions. These ‘submerged’ layers might help explain
certain puzzling phenomena concerning subliminal perception, such as the apparently
‘unconscious’ multisensory integration and learning of subliminal stimuli.
As a researcher in intelligent technologies, I have long been interested in scholarly debates
about consciousness. Nevertheless, my lack of formal training in philosophy would have kept
me away from the arena were it not for encouragement from unexpected quarters. In this
contribution, I examine two radically different explanations of our phenomenal intuitions and
identify some opportunities for the transfer of knowledge between various theories. The
possibility of such a mutually beneficial interaction seems to be one of the reasons David
Chalmers chose the meta-problem as the focus of this symposium.
-1-
1. Reductive explanation
My ‘reductive’ choice is Virtual machines and consciousness (Sloman and Chrisley 2003),
which is the source of all quotations in this section.
Its authors maintain that ‘although the word ‘consciousness’ has no well-defined meaning, it
is used to refer to aspects of human and animal information-processing.’ They believe that a
study of extant ‘biological information-processing architectures’ would help us supplant our
vague pre-theoretical notions of consciousness with more precise and empirically tractable
ones. In effect, they adopt a ‘designer stance’, which leads them to virtual machine
functionalism (VMF).
VMF dispenses with the notion of atomic states and clean transitions between them, which
shields it from ‘a number of standard objections.’ In VMF, a modelled entity can have several
coexisting, independently-varying, and interacting states which need not start or end at the
same time. VMF can thus easily accommodate the way we normally view our own mental
states, such as our conflicting desires or attitudes.
The authors’ first tangible result was the ‘CogAff’ (Cognitive-Affective) architecture schema
(a ‘grammar’ for agent architectures) with three layers: reactive, deliberative and reflective.
The reactive layer consists of the oldest and simplest mechanisms, lacking the ability to
explicitly represent and compare alternatives in a symbolic form. Consequently, it cannot
‘reason about nonexistent or unperceived phenomena (e.g., future possible actions or hidden
objects)’, which is the core ability of the second, deliberative layer. The third, reflective layer
(also called meta-management) contains reflective and self-reflective mechanisms, whose
main task is to monitor deliberative processes and, should they get stuck, interrupt them and
redirect the processing to more promising alternatives.
On this basis, the authors formulate their ‘human-like architecture for cognition and affect’
(‘H-CogAff’), which they think sufficient (in principle) for the construction of robots with
human-like common sense and consciousness. Their claim rests on an ‘unrestricted’ form of
VMF, in which states and processes need not be causally connected to the rest of the system
or its inputs and outputs. They maintain that unrestricted VMF can explain even notoriously
elusive features of human psychology such as qualia. They tried to demonstrate this through a
graded series of examples, which culminated in a special case of a semi-detached process in
the reflective layer that monitors and evaluates other processes:
This internal self-observation process might have no causal links to external motors, so that its
information cannot be externally reported. If it also modifies the processes it observes … then it
may have external effects. However it could be the case that the internal monitoring states are
too complex and change too rapidly to be fully reflected in any externally detectable behaviour:
a bandwidth limitation. For such a system experience might be partly ineffable. (p. 151)
The authors seem to imply that partial ineffability in the reflective layer amounts to a kind of
proto-qualia, or elementary qualia, instantiated in a machine. They bolster their argument
through a discussion of concept formation in self-organising systems, which, as they show,
provide scope for more advanced forms of qualia. To that end, they draw a distinction
between ‘architecture-based’ and ‘architecture-driven’ concepts. While the architecture-based
concepts are defined ‘in terms of what components of the architecture can do’, and refer to
their states and processes as if ‘from outside’, the architecture-driven ones are inherently
private, especially if they form during the unique developmental histories of such systems
without any reference to an external world. Such concepts then acquire ‘causal indexicality’
(see Campbell 1994):
-2-
If such a concept C is applied by A to one of its internal states, then the only way C can have
meaning for A is in relation to the set of concepts of which it is a member, which in turn derives
only from the history of the self-organising process in A.... This can be contrasted with what
happens when A interacts with other agents in such a way as to develop a common language
for referring to features of external objects. Thus A could use ‘red’ either as expressing a
private, causally indexical, concept referring to features of A’s own virtual-machine states, or as
expressing a shared concept referring to a visible property of the surfaces of objects. (p. 165)
Considering two agents, A and B, of this type,
then if A uses its causally indexical concept Ca, to think the thought ‘I am having experience Ca’,
and B uses its causally indexical concept Cb, to think the thought ‘I am having experience Cb’,
the two thoughts are intrinsically private and incommunicable, even if A and B actually have
exactly the same architecture and have had identical histories leading to the formation of
structurally identical sets of concepts. A can wonder: ‘Does B have an experience described by a
concept related to B as my concept Ca is related to me?’ But A cannot wonder ‘Does B have
experiences of type Ca’, for it makes no sense for the concept Ca to be applied outside the
context for which it was developed, namely one in which A’s internal sensors classify internal
states. They cannot classify states of B. (p. 165)
Such self-referential architecture-driven concepts, the authors claim,
are strictly non-comparable: not only can you not know whether your concepts are the same as
mine, the question is incoherent. If we use the word ‘qualia’ to refer to the virtual machine
states or entities to which these concepts are applied, then asking whether the qualia in two
experiencers are the same would be analogous to asking whether two spatial locations in
different frames of reference are the same, when the frames are moving relative to each other.
But it is hard to convince some people that this makes no sense, because the question is
grammatically well-formed. Sometimes real nonsense is not obvious nonsense. (p. 166)
The authors thus explain the spontaneous emergence of ‘phenomenal intuitions’ about qualia
in conscious creatures of the requisite sophistication by their internal structure: ‘Some robots
with our information processing architecture,’ they conclude, ‘will discover qualia and be
puzzled about them. The more intelligent ones should accept our explanation of how that
happens.’
In a sequel (Chrisley & Sloman 2016), they classify themselves as ‘qualia revisionists’ and
admit that qualia do (or might) exist, with the important proviso that they may not be as they
seem. This differentiates them from both qualia eliminativists, like Daniel Dennett, and ‘naive
qualia realists’, who hold that qualia exist and are truly as they seem: unmediated, private,
intrinsic, and ineffable.
Although I subscribe to strongly nonreductive views on consciousness, the authors have
convinced me that intelligent machines could possess qualia. More precisely, I feel we should
rather speak of proto-qualia, structural and functional preconditions leading to qualia in the
presence of some form of irreducible consciousness. Such a possibility for machines is
inherent e.g. in Chalmers’ minimalistic ‘nonreductive functionalism’ (Chalmers 1995). In
principle, therefore, its proponents could directly incorporate Sloman’s and Chrisley’s
conceptions into their theories, thereby strengthening the case for the feasibility of human-like
machine consciousness. (For a more detailed comparison of Chalmers with Sloman and
Chrisley see Kvassay 2012). However, it might still turn out that there are kinds of qualia that
only humans can have but that would not detract from the value of demonstrating the viability
-3-
of machine consciousness with qualia on a nonreductive basis, given that people with strongly
nonreductive views tend to resist its very idea.
2. Nonreductive explanation
Chalmers’ nonreductive functionalism represents an intermediate position between
physicalism and strongly nonreductive views, which is an ideal vantage-point for initiating a
meaningful dialogue between them. Chalmers himself tentatively explores the potential of
idealism to solve the mind-body problem in Idealism and the Mind-Body Problem
(forthcoming). In doing so, he differentiates its numerous varieties, but there is one important
distinction that he omits: the one between purely speculative systems and those associated
with psychological practices such as concentration and meditation, which also attempt to
experience the higher or deeper states of consciousness postulated by these systems. I believe
that their accumulated psychological material could help explain many aspects of the problem
of consciousness and the meta-problem, if approached from the right angle and with an
adequate explanatory framework. Naturally, to develop such a framework would not be easy
because each system tends to cast its psychological experiences into a form congruent with its
underlying philosophy. Many are openly theistic, though some are non-theistic or even
atheistic (see, e.g. Heehs 2014, 2018). Nevertheless, a competent multidisciplinary team
might still achieve worthwhile results.
In order to illustrate the idea, I will now review some salient observations by the Indian
thinker Sri Aurobindo (1872-1950), whose main philosophical work The Life Divine
(Aurobindo 2005) can be regarded as one such attempt. In this tome, he developed his own
position (‘a universal Realism’) and contrasted it with Materialism and ‘spiritual Illusionism’.
In the process, he reflected on the rich experiential material drawn mainly from Indian
Vedanta and revaluated it in the light of modern knowledge and his own spiritual experiences.
I will try to show that the result is highly relevant for the contemporary philosophy of mind,
including the meta-problem. (All quotations in this section are from The Life Divine.)
Arguably the most pertinent are his remarks on the function and constitution of the human
mind, particularly in Book Two, chapters 8-11 (pp. 519-85). Many are philosophically neutral
but are embedded in his idealistic metaphysics, from which they have to be extricated. Thus,
for example, he notes that ‘Ordinarily, we speak of a subconscious existence and include in
this term all that is not on the waking surface.’ We are inclined to think of it as something
devoid of consciousness and inferior to our waking mind. To him, this is an error. He calls
that large submerged part of us our ‘subliminal’ self and distinguishes in it four distinct
layers: (1) the subconscious, (2) the submental, (3) the inner or subliminal proper and (4) the
superconscient or supramental. Of these, only the first two are really inferior, although still
not completely devoid of consciousness; the third is qualitatively similar, yet much more
capable than our waking mind; and the last is so much superior that it is practically
inaccessible to all but the most advanced spiritual practitioners. In their totality, they represent
‘our real or whole being, of which the outer [waking consciousness] is a part and a
phenomenon, a selective formation for a surface use’ (p. 576).
Our submental self corresponds to ‘a vitality working in [our] bodily form and structure as in
the plant or lower animal.’ Because it is mostly subconscious to us, we tend to think that ‘this
vital-physical part of us also is not conscious of its own operations’ and ‘becomes conscious
only so far as it is enlightened by mind and observable by intelligence.’ But this is a mistake,
he writes,
-4-
due to our identification of consciousness with mentality and mental awareness. Mind
identifies itself to a certain extent with the movements proper to physical life and body and
annexes them to its mentality, so that all consciousness seems to us to be mental. But if we
draw back, if we separate the mind as witness from these parts of us, we can discover that life
and body... have a consciousness of their own, a consciousness proper to an obscurer vital and
to a bodily being, even such an elemental awareness as primitive animal forms may have, but
in us partly taken up by the mind and to that extent mentalised. (p. 579)
He admits that it “has not, in its independent motion, the mental awareness which we enjoy’
because ‘there is no organised self-consciousness,’ yet ‘it has its own separate reactions to
contacts and is sensitive to them in its own power of feeling; it does not depend for that on the
mind’s perception and response.’ The true subconscious, he explains next,
is other than this vital or physical substratum; it is the Inconscient vibrating on the borders of
consciousness, sending up its motions to be changed into conscious stuff, swallowing into its
depths impressions of past experience as seeds of unconscious habit and returning them
constantly but often chaotically to the surface consciousness... in dream, in mechanical
repetitions of all kinds, in untraceable impulsions and motives,... in dumb automatic necessities
of our obscurest parts of nature. (pp. 579-80)
Our inner self (the subliminal proper) is qualitatively different from both because
it is in full possession of a mind, a life-force, a clear subtle-physical sense of things. It has the
same capacities as our waking being... [but] wider, more developed, more sovereign.... [I]t
exceeds the physical mind and physical organs although it is aware of them and their works
and is, indeed, in a large degree their cause or creator. It is only subconscious in the sense of
not bringing all or most of itself to the surface. (p. 580)
The extraordinary capabilities of this inner self underpin such apparently ‘miraculous’
phenomena as hypnotic analgesia and anaesthesia (p. 115). They can also manifest
spontaneously in a special type of dreams, which sometimes bring us solutions to problems
that we could not solve in our waking state (pp. 440-41).
The superconscient represents a yet higher level of ‘extraordinariness.’ It is usually associated
with deeply spiritual and religious experiences, but it does have one ‘secular’ manifestation,
too: the phenomena of genius. In the genius, though, there is a certain veiling element,
because the light of the superior consciousness not only acts within narrow limits, usually in a
special field,... but also in entering the mind it subdues and adapts itself to mind substance so
that it is only a modified or diminished dynamis that reaches us, not all the original divine
luminosity of what might be called the overhead consciousness beyond us. (p. 289)
In most people, however, the superconscient acts rarely and indirectly through their
subliminal proper.
With respect to these four different components, our waking consciousness appears as a
makeshift construction in a permanent state of flux, an amalgam of disparate materials and
influences rising from them to our waking surface. This gives our subjective existence a very
complicated (and partly chaotic) character and explains, among other things, why our
attempts at rational self-control are never entirely or permanently successful. It also leads to
several classes of phenomena that could be considered phenomenal intuitions.
-5-
The simplest type rests on the inability of our waking mind (a weakness shared by its
subliminal counterpart) to directly perceive the indivisible unity of all existence, including
matter and consciousness. In Aurobindo’s system, such a unitary perception is the prerogative
of the superconscient and, until our mind is ‘transformed’ by its direct contact and influence,
our ordinary perception will continue to render matter and consciousness, as well as other
pairs of dualities like pleasure/pain, personality/impersonality, activity/passivity,
truth/falsehood, good/evil, etc., as irreconcilable opposites, irrespective of whether we
intellectually adhere to some form of philosophical monism or dualism.
The second type builds on the first and adds a vague valuation: consciousness may be
perceived as the worthier of the two because we tend to regard matter as mere inert stuff, but
consciousness seems to be both the essence of ourselves and the seat of our precious capacity
to fashion that material creatively in innumerable ways.
Finally, intuitions and intimations of the third type (usually mediated by our subliminal
proper) make us aware of, and dissatisfied with, our present imperfect condition. They spur us
on towards continual self-exceeding in the never-ending quest for a more integrated inner life
and an ever-expanding fullness of being. In spiritually inclined people, this often takes the
form of regular spiritual practice, but in the secularly minded, it may manifest as a thirst for
knowledge, a search for the meaning of life, a self-dedication to the betterment of humanity or
some other similar ideal.
Aurobindo’s philosophical magnum opus was in fact meant for people in the third category,
who felt moved by ‘the impulse towards perfection, the search after pure Truth and unmixed
Bliss, the sense of a secret immortality’ (p. 3). Today we might prefer to put it differently but,
verbal differences aside, do we not still continue to dream of perfect knowledge, unlimited
happiness, unshakable health, and perhaps even of the conquest of death through the
‘miracles’ of science and technology?
Of course, in materialist theories, all the above types of phenomenal intuitions would be
replaced by their ‘computational’ or ‘functional’ equivalents, with appropriate evolutionary
justifications. Thus, for example, the need to differentiate between pleasant and painful,
beneficent and maleficent is a clear precondition for survival. Aurobindo actually admits this
when he calls pain a ‘device of Nature’ (p. 115), but he still needs a better alternative
compatible with unitary consciousness. Analogously, the second type might simply be a
clever trick of Nature, reinforcing our instinct of self-preservation; and the third, a similar
device, predisposing us towards change instead of being attached to one static optimum
(which might turn into an evolutionary liability). I will not attempt to adjudicate these issues
here, nor will I, for reasons of space limitations, discuss in further detail Aurobindo’s
philosophy or his acute introspective insights. A handy summary of the former can be found
in Odin (1981), and of the latter in Kvassay (2011).
To summarise, although Aurobindo’s idealistic metaphysics is unlikely to find many takers
among contemporary philosophers, his concept of several ‘subliminal’ layers of
consciousness might have a broader appeal. In fact, something similar seems to be implied by
Sloman’s and Chrisley’s CogAff schema, because each of its layers can be construed as a
distinct and independently operating type of consciousness. For example, if we grant purely
reactive species like termites a rudimentary awareness (‘submental’ in Aurobindo’s
terminology), then this type of awareness might survive in a ‘submerged’ form (perhaps with
some loss of priority and importance), even as new conscious layers (deliberative and
reflective) are added to that reactive foundation in its evolutionary descendants and inheritors.
Moreover, Sloman himself speaks of ‘two co-occurrent forms of consciousness, one
performing a task and succeeding or failing, the other observing modal aspects of task e.g.
-6-
necessity or impossibility’ (personal communication). I believe this ‘confluence’ of views
testifies to the value of the idea. It might also help to explain certain puzzling phenomena
regarding subliminal perception. In a recent study in which Chrisley himself participated
(Scott et al. 2018), associative learning occurred between pairs of subliminal stimuli presented
in different sensory modalities, thus challenging theories of consciousness based on the
‘conscious access hypothesis’ (CAH). The theoretical admission of a concurrently active
submental layer of consciousness in the experiment participants (of which they would not
have been directly aware) could explain the results without completely undermining the CAH,
although its revision would probably still be needed.
Conclusion
In this paper, I have examined two different approaches to consciousness which, for various
reasons, seem to have stayed largely beneath the radar of most professional philosophers of
mind. Sloman’s and Chrisley’s pragmatic approach, perhaps a bit too technical and empirical
at first sight, may yet be essential for the success of the more abstract philosophical
enterprise; first, by helping it to clarify inherently vague concepts like ‘consciousness’ and,
second, by practically demonstrating the capabilities of sophisticated agent architectures, such
as their support for certain functional forms of qualia or proto-qualia. As a software engineer,
I am in full sympathy with their ‘designer stance’ and hope to see more practical results
coming out of their continual explorations of new territories, such as learning mechanisms in
‘altricial’ versus ‘precocial’ animals, the role of mathematical intuition versus mathematical
ingenuity, or the need for chemistry-based forms of computation (Sloman 2013, 2018).
Aurobindo’s ideas seem to have been neglected for opposite reasons. First, they are part of an
unabashedly idealistic system with a strong Vedantic colouring, which runs counter to the
broadly analytical tenor of the contemporary philosophy of mind. Second, he often employs a
demanding style in which, to quote his biographer, ‘clause follows clause follows clause, until
sometimes the point of the statement is lost in a maze of qualifications’ (Heehs 2008, p. 328).
But whatever the merits and demerits of his philosophy and style, his incisive introspective
insights remain universally relevant. Probably the most pertinent of these is his claim, broadly
compatible with Sloman’s and Chrisley’s architectural notions, that, under the threshold of
our waking mind, there exist several distinct and concurrently active layers of ‘submerged’ or
‘subliminal’ consciousness. These constitute an independent source of our phenomenal
intuitions and factoring them into extant theories of consciousness could open the way to
solving several conundrums presently facing them, such as the apparently ‘unconscious’
multisensory integration and learning of subliminal stimuli.
Acknowledgments
This work was supported in part by the Slovak Research and Development Agency under
contract No. APVV-17-0619 and by the VEGA project No. 2/0167/16. I am grateful to Aaron
Sloman for comments on an earlier draft of this manuscript.
-7-
References
Aurobindo, Sri. (2005) The Life Divine (Volumes 21–22 of The Complete Works of Sri
Aurobindo), Pondicherry: Sri Aurobindo Ashram.
https://www.sriaurobindoashram.org/sriaurobindo/writings.php
Campbell, J. (1994) Past, Space, and Self. Cambridge/London: The MIT Press.
Chalmers, D. J. (1995) Facing up to the problem of consciousness, Journal of Consciousness
Studies 2(3), pp. 200-219.
http://consc.net/papers/facing.html
Chalmers, D. J. (forthcoming). Idealism and the mind-body problem. Forthcoming in W.
Seager, ed., The Routledge Handbook of Panpsychism.
http://consc.net/papers/idealism.pdf
Chrisley, R., & Sloman, A. (2016) Functionalism, revisionism, and qualia, APA Newsletter on
Philosophy and Computers, 16(1), pp. 2-13.
http://sro.sussex.ac.uk/64774/1/FunctionalismRevisionismandQualiav5rev.pdf
Heehs, P. (2008) The Lives of Sri Aurobindo. Columbia University Press.
Heehs, P. (2014) Practices of Non-Theistic Spirituality. Gandhi Marg 36, 2&3, pp. 251-68.
Reprinted in A.K. Giri, ed., Practical Spirituality and Human Development (Palgrave
Macmillan, 2018), pp. 63-80.
http://www.academia.edu/28775868/Practices_of_Non-Theistic_Spirituality
Heehs, P. (2018) Spirituality without God: A Global History of Thought and Practice.
Bloomsbury Publishing.
Kvassay, M. (2011) Psychological Foundations of Sri Aurobindo’s Philosophy and His
Approach to the Problem of Evil. [Online]
http://marcelkvassay.net/article.php?id=psychological [23 Jan 2019]
Kvassay, M. (2012) Machines, Intelligence, Consciousness. [Online]
http://marcelkvassay.net/article.php?id=machine [4 Feb 2019]
Odin, S. (1981) Sri Aurobindo and Hegel on the involution-evolution of Absolute Spirit.
Philosophy East and West, 31(2), 179-191.
Scott, R. B., Samaha, J., Chrisley, R., & Dienes, Z. (2018) Prevailing theories of
consciousness are challenged by novel cross-modal associations acquired between subliminal
stimuli. Cognition, 175, 169-185.
Sloman, A. (2013) Virtual Machine Functionalism. [Online]
http://www.cs.bham.ac.uk/research/projects/cogaff/misc/vm-functionalism.html [2 Feb 2019]
Sloman, A. (2018) Alan Turing's 1938 thoughts on intuition vs ingenuity in mathematical
reasoning. [Online]
http://www.cs.bham.ac.uk/research/projects/cogaff/misc/turing-intuition.html [2 Feb 2019]
Sloman, A. & Chrisley, R. (2003) Virtual machines and consciousness. Journal of
consciousness studies, 10(4-5), pp.133-172.
http://www.cs.bham.ac.uk/research/projects/cogaff/sloman-chrisley-jcs.pdf
-8- |
467
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
Article
Phenomenological Convergence between Major Paradigms of
Classic Parapsychology and Cross-Cultural Practices:
An Exploration of Paranthropology
Joey M. Caswell1, *, Jack Hunter1, 2, *, & Lucas W. E. Tessaro1
1
2
Transnational Anomalies Research, Sudbury, Ontario, Canada
Department of Archaeology & Anthropology, University of Bristol, UK
Abstract
A new generation of researchers have begun to contribute to the emerging transdisciplinary
endeavours of paranthropology. This intriguing area of research unifies methodologies and
theoretical perspectives of both parapsychology and anthropology to enhance understanding of
anomalous phenomena related to consciousness. Furthermore, by employing a
paranthropological perspective, a number of cross-cultural convergences between disciplines are
revealed. We begin by summarizing a number of major paradigms typically observed in classic
parapsychology, followed by a brief historical overview of the development of paranthropology
and its implications for subsequent research. Finally, phenomenological convergences between
parapsychology and anthropology are discussed, before a final summary of general conclusions
are entertained.
Key Words: Consciousness, psi, mediumship, culture, shamanism, magico-religious practices,
parapsychology, paranthropology, altered states of consciousness, field research, anomalies.
1. Introduction
The emerging paradigm of paranthropology seeks to unite the fields of parapsychology and
anthropology, treating them as non-mutually exclusive entities despite decades of academic
isolation from each other. Paranthropology examines claims of “paranormal” experience by
individuals and groups in cross-cultural settings, particularly with regard to shamanism and other
magico-religious practices [1-3]. While many practitioners may regard these fields of
investigation as incompatible, there are a number of clear convergences of phenomenological
experience between these disciplines which may have simply received varying labels by those
who study them in differing experimental contexts [4-5].
*Corresponding authors: J. M. Caswell & J. Hunter. Emails: neuraljc@gmail.com; discarnates@googlemail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
468
Experiences which modern science may typically deem “anomalous” are not only culturally
universal [6], but these experiences are not generally considered anomalous by the indigenous
cultures which have integrated these various magico-religious practices into their respective
traditions and belief systems [7].
Mind-Matter Interaction
Contemporary research in the area of physical anomalies associated with consciousness also
bears striking similarities to many cross-cultural practices, including the general area of “psi”
phenomena [5]. Outgoing psi processes may include apparent mind-matter interactions,
otherwise referred to as psychokinesis (PK) or, to use the more modern terminology,
consciousness-correlated collapse (3C). Within the realm of the 3C phenomenon, human
operators attempt to influence the outcome of an external random physical system by means of
cognitive intention alone [8].
Remote Viewing and Precognition
Similarly, incoming psi processes typically examined include the seemingly related phenomena
of remote viewing and precognition. While both of these anomalous processes appear to
represent some form of extrasensory perception of non-local information external to the
individual, the actual role of the observer varies between these processes. Remote viewing
involves an active role by the individual, as they attempt to mentally access information about a
distant target image of which they have no previous knowledge [9-10] simply by means of
intention. While precognition also involves conscious access to external information [11-12], the
observer plays a more passive role in this process, as precognitive premonitions in the general
population typically occur without an individual’s intention to do so. Furthermore, this
phenomenon is often associated with reception of information regarding future events [13-14],
while remote viewing is generally concerned with accessing information about the present.
Poltergeists and Haunts
While the more esoteric parapsychological fields of poltergeist and haunt activities may appear
at greater odds with the proposed cross-cultural convergences found in this area of study, these
phenomena also possess marked consistency between subjective labels across research fields.
While both poltergeist and haunt reports are typically associated with similar physical
manifestations and strong thematic-links [15], there are distinct differences that have been
revealed between these areas of investigation. Poltergeist cases, for example, are typically
associated with an individual or group of individuals as the focus or source of the phenomenon
[16-17], which may include unexplained movement of objects, odd behaviour, and reports of
“seeing” or “hearing” things. While the overall physical manifestations of haunt cases are
consistent with occurrences of anomalous sensory reports, haunt activity is typically associated
with a specific environment or location [18-19].
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
469
Altered States of Consciousness
Finally, the more general area of altered states of consciousness (ASC) has also been considered
in both empirical and cultural-experiential contexts [5], which again display striking similarities
between subjective experiences across both fields of study [20]. While cross-cultural spiritual
practitioners may ingest hallucinogenic substances and/or engage in ritual activity in order to
induce ASCs [21], many studies have also demonstrated the potential for weak-intensity
physiologically-patterned electromagnetic fields (EMF) to induce altered states [22-23]. Many
experiences reported by participants in these studies appear consistent with those found in
indigenous practices around the world, including out-of-body experiences (OOBE), and the
“sensed-presence” phenomenon, where the individual feels as though “someone else” is in the
room with them.
2. A Brief History of Paranthropology
The term “paranthropology,” referring to an anthropological approach to the paranormal, and a
shortened form of the more cumbersome “parapsychological anthropology,” was first coined by
the linguist Roger W. Wescott in Joseph K. Long’s ground-breaking book Extrasensory Ecology:
Parapsychology and Anthropology [24]. However, the origins of an anthropological approach to
the paranormal go back much further into the discipline’s history.
Early anthropologist and folklorist Andrew Lang, for instance, sought to develop what he called
“comparative psychical research.” In spite of the clear parallels between accounts of paranormal
experiences across cultures, however, Lang was dismayed to find that most anthropologists of
his day were unwilling to take seriously the data from psychical research, and the psychical
researchers were similarly unwilling to examine more thoroughly the accounts of paranormal
experiences and phenomena documented in the ethnographic literature. This impasse continued
until 1953, when John R. Swanton published his “Letter to Anthropologists” in the Journal of
Parapsychology [25], which called for anthropologists to take seriously the data of
parapsychology and psychical research.
Later, Francis Huxley [26] wrote a paper specifically concerned with anthropology and
extrasensory perception (ESP), in which he highlighted the tendency of anthropological accounts
of witchcraft, magic, divination and shamanism to ignore the possibility that ESP might be a
genuine phenomenon. Huxley also observed that a cross-cultural survey of divinatory techniques
revealed an underlying fundamental characteristic: “a profound dissociation has to be provoked,
during which the normal connections between consciousness and physical activity are severed”
[26]. In other words, the crucial role of altered states of consciousness in the mediation of psi
experiences was recognized. It was further suggested that ethnographic observation of practices
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
470
such as shamanism and spirit mediumship may reveal other fundamental process associated with
apparent ESP [26].
The Italian philosopher and anthropologist Ernesto de Martino’s work [27] discussed how
laboratory investigations of ostensible psi phenomena frequently involve a complete reduction of
the emotional and environmental contexts within which psi experiences naturally occur. Such an
approach does, of course, yield significant benefits to the experimentalist, but it also ignores the
natural complexity of psi as experienced in the “real world.” It is precisely at this juncture that
the ethnographic methodology of anthropology provides insight into the nature of the paranormal
through documenting and describing its occurrence in the midst of the social drama that allows
psi to manifest in its most elaborate forms, whether spontaneously in the field [28], or as part of a
ritual process [29-30].
Joseph K. Long [31] emphasized the role of culture in mediating the experience and expression
of psi, a notion that was later echoed by Robert Van de Castle [32], who suggested that
ethnographic fieldwork might provide for parapsychology what Darwin’s Galapagos Island
expedition gave to biology. In other words, an anthropological approach to parapsychology
might enable researchers to investigate how the environment and culture shape various psi
processes. In this way the over-emphasis of parapsychologists on manifestations of psi in the
Western laboratory context was criticized, along with the prejudices of anthropologists in
considering non-Western magical beliefs and practices as irrational and primitive.
Subsequent researchers also sought to improve the one-sided approaches of both parapsychology
and anthropology. The potential for a fruitful application of parapsychological insights into the
nature of psi to the interpretation of the anthropology of magic and religion was suggested, and it
has been argued that parapsychology has generally failed to employ the rich and diverse insights
provided by ethnographic and cross-cultural investigations [33]. This general perspective calls
for a process-oriented approach to psi, an approach that takes into account the many ecological
variables (e.g., the ethnographic facts), that correlate with the occurrence of psi phenomena in
the field [33].
More recently, Roger Wescott’s term paranthropology has been revived and expanded by a new
generation of anthropologists and parapsychologists with an interest in ethnographic
investigations of the ostensibly paranormal [34]. Social anthropologist Fabian Graham, for
example, has sought to differentiate paranthropology from the more traditional approaches of the
anthropology of religion by highlighting paranthropology’s emphasis on the objects of
supernatural belief, rather than on belief:
[...] paranthropology [defines] itself in relation to the phenomena themselves, and not (in
relation) to the belief systems, scientific or religious, that have evolved to support the
phenomena [35].
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
471
Paranthropology, therefore, takes a bold step in attempting to interpret systems of supernatural
belief from the perspective of those who subscribe to them, that is, not as beliefs but as
ontological realities. In studies of spirit mediumship, for example, a paranthropologist will take
seriously their informants beliefs about, and experiences of, spirits as ontologically real entities
[36-37]. Further to this, the paranthropologist will attempt to participate, as far as possible, in the
rites, rituals and performances under study in order to develop an “insider” perspective [38-39].
A truly rounded study of spirit possession, for instance, cannot be complete without an
appreciation of the experiential component, which certainly plays a central role in the
development of traditions of practice and belief [40]. Such an approach might also come under
the heading of what parapsychologist David Luke calls “first-person parapsychology” [41].
In conclusion to this brief overview of the development of paranthropology, four key areas of
focus are apparent for paranthropological research:
1.
Cross-cultural comparison of the phenomenology of psi
2.
A naturalistic approach to psi, exploring its psychological, sociological and
cultural contexts
3.
An emphasis on participation and first-hand experience
4.
Parapsychological experimentation in the field
3. Examples of Cross-Cultural Parapsychological-Convergence
Given the major areas of classic parapsychology previously discussed, along with the overall
objectives of paranthropology as a newly emerging paradigm, the following transdisciplinary
thematic and/or phenomenological convergences are proposed for further experimental field
research:
Ritual Healing
First, the recurring experimental phenomenon of mind-matter interactions (MMI; psychokinesis
or consciousness-correlated collapse), which has been a continual area of interest for
parapsychologists, has revealed many fundamental similarities with cross-cultural practices,
particularly regarding shamanic traditions. While decades of persistent research have
demonstrated the potential for human operators to seemingly affect the outcome of an external
random system [42-43], many traditional and spiritual practices have demonstrated similar
effects related to statistical shifts in random physical processes. Previous research in this area has
examined potential MMI-like effects associated with both a shamanic healing ritual [44] and
group meditation [45]. Similarly, previous theories have suggested the potential enhancement of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
472
this phenomenon in a normal population through the induction of neuroelectrical variations
associated with altered states of consciousness [5, 8, 46].
The second major component of cross-cultural-MMI convergence is the importance of conscious
intention within specific contexts of this phenomenon. While human “intention” has been
correlated with statistical deviations in random event variations [8, 42], the role of this cognitive
process has also been examined in relation to cross-cultural spiritual practitioners and their
apparent abilities to exert mental influence on various facets of the external environment [47].
Finally, the role of MMI-like effects associated with traditional healing practices may be even
more evident than the preceding convergences. A wide range of cultural traditions focus on using
what are essentially forms of cognitive intention to heal the body, including Qigong [48] and
Reiki [49]. In various traditions of non-local or “energy” healing, the practitioner employs their
mind in order to affect positive changes in another biological system or individual [50]. While
the theoretical consistency is remarkably persuasive, further field studies of veteran spiritual
practitioners should be examined with the objective of assessing any equivalence between
laboratory MMI effects and traditional healing practices with regard to both overall experimental
effects, and potential biophysical or physiological factors.
Shamanic Journeying and Visions
The alternate area of psi research which focuses on various forms of apparently non-local
information access includes the previously discussed phenomena of remote viewing practices
and precognitive experience. Again, remote viewing typically involves an individual actively
intending to access information about a distant object or event, while precognitive predictions
may be voluntary or involuntary and are often associated with information about future events
[14]. These forms of “incoming” psi may be among the more overtly cross-cultural
consciousness-anomaly equivalences.
While individuals located in the West who appear capable of actively accessing external
information or passively receiving information about future events have been revealed in the
parapsychological literature [9, 51], one of the primary roles of the shaman and other crosscultural spiritual practitioners is also to access and engage information that is not otherwise
available to the rest of the immediate population [20, 52]. A range of cross-cultural spiritual
practices, particularly in the specific context of shamanism, include mental imagery as an
important aspect of communicating with the “spirit world” [53-54], or mental journeying with
the objective of acquiring information not otherwise available. The role of this form of “imagery
journeying” and the experience of mental visions in general [55] is markedly consistent with the
parapsychological phenomena of incoming non-local information (e.g., remote viewing and
precognition).
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
473
In comparison to the area of mind-matter interactions, cross-cultural practices associated with
shamanism have more often been directly applied in the laboratory with regard to incoming psi
information [56-57], and have suggested an enhanced propensity to engage in anomalous psi
processes during shamanic-like states compared to other classic parapsychology testing protocols
[58]. While the application of indigenous cultural practices in the context of laboratory testing is
certainly a step in the right direction with regard to experimental paranthropology, there remains
a requirement to investigate these apparent abilities of both Western and non-Western
practitioners in a naturalistic field setting. The same benefits previously suggested could be
attained, such as further support for a phenomenological convergence between parapsychology
and anthropological research, and also to help determine potential physiological and biophysical
factors which may be involved.
Spirit Possession
The peculiar area of alleged poltergeists and haunt activity reported in previous parapsychology
research has similarly proven to be consistent with anthropological reports regarding spirit
possession, sacred sites, and other similar phenomena. The ethnographic literature is particularly
rich in data about spirit possession, which has been a subject of constant fascination for
anthropologists since the discipline’s earliest days [59]. Anthropologist Janice Boddy provides a
fairly broad definition of spirit possession as the purported “[...] hold over a human being by
external forces or entities more powerful than she. These forces may be ancestors or divinities,
ghosts of foreign origin, or entities both ontologically and ethnically alien [...]” [60].
Belief in the possibility that the physical body may be temporarily occupied by non-physical
beings is near-universal. Spirit possession is usually associated with some form of dissociative
altered state of consciousness [61], or “trance state.” Possession may be either spontaneous or
deliberately induced. Spontaneous possession is usually associated with illness, while deliberate
incorporation of spirits may lead to enhanced social status for the possessed. Pathological spirit
possessions are frequently treated with ritual exorcism to rid the afflicted of the intruding spirit,
while deliberate spirit possession may be induced for a variety of social reasons, including
healing [62], the acquisition of knowledge, and for political insight [63].
In spite of the huge amount of parapsychological research conducted with spirit mediums in the
Western world [64-65], there has been very little in the way of experimental parapsychological
research conducted with mediums from different cultural traditions. One notable exception is
Giesler [66], who conducted standard extrasensory perception (ESP) tests with Umbanda
mediums with preliminary results suggestive of significant effects. Other forms of experimental
work have been conducted with non-Western mediums, such as electroencephalograph (EEG)
studies with Balinese mediums performing traditional ritual dances [67], which are suggestive of
the involvement of interesting psychophysiological processes in traditional spirit possession
practices.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
474
These cases reveal a particularly salient experiential consistency between cross-cultural
traditional beliefs and the parapsychological phenomenon of poltergeist activity, where a
“possessed” individual may display odd behaviour associated with other anomalous physical
manifestations. Further research into the parapsychological and neurophysiological aspects of
traditional spirit possession practices is required to clarify and expand on these exploratory
convergences.
Mystical States
A central biochemical agent employed by shamans and other spiritual practitioners is ayahuasca,
a drink brewed by many indigenous cultures throughout the Upper Amazon. The spread of its
use for healing and spiritual ceremonies also extends into Ecuador, Colombia and Peru [68]. The
ingestion of ayahuasca is integral to the spiritual practices of many indigenous cultures in the
Amazon region for inducing altered states of consciousness (ASC), in addition to being central to
myths, cosmologies, and other cultural aspects of life [69]. The drink itself is a concoction of two
plants, the root of the ayahuasca vine Banisteriopsis caapi and leaves of the perennial shrub
Psychotria viridis, which contain psychotropic compounds such as harmala alkaloids and
dimethyltryptamine (DMT) [69]. DMT specifically is a known hallucinogenic compound whose
dissociative properties are mediated through the 5-HT2A serotonin receptor, with recent studies
determining that DMT is a naturally occurring substance within the mammalian nervous system
[70].
Contemporary investigation of ayahuasca practices in Brazil have revealed that the adoption and
use of the admixture was developed relatively early, and can be traced back to the earliest
inhabitants of the region [71]. It is a commonly held belief among these peoples that the
ingestion of the “vine of the dead” (Quecha meaning ayahuasca), permits the soul to leave the
physical body. A freed soul takes on the ability to communicate with dead ancestors and other
magical experiences associated with alternate forms of reality and ASCs [71]. Ethnographic
studies of the region have illustrated common themes and experiences among indigenous
ayahuasca users, such as spirit visions of animals and of distant persons or places, which could
be related to out-of-body experiences (OOBE) [71-73]. Some preliminary field experiments have
been conducted to test drinkers of the brew for psi [74-75]. Survey research also shows that the
majority of people using ayahuasca also report a variety of paranormal experiences, such as the
encounter with discarnate entities [76-77].
Additionally, ayahuasca use can lead to the elicitation of entoptic imagery – geometrical visual
patterns, zig-zags, grids, and simple shapes [78]. Indeed, archaeological evidence suggests that
cultures around the world ritualistically engaged in hallucinatory experiences, as evidenced by
the appearance of entopic images in sacred cave paintings [79-81]. That ASCs and other mystical
subjective experiences can be elicited through the application of transcerebrally applied
physiologically-patterned electromagnetic fields is particularly relevant given the general
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
475
thematic overlap of reported experiences [22-23]. These studies have shown the temporal lobes
of the brain to be the optimal locus for the development of religious experiences, religiosity, and
other mystical experiences similar to those which have been described in ayahuasca states [8284].
Given that the synthesis and release of naturally occurring DMT has been demonstrated, Hill &
Persinger [85] hypothesized that the application of these weak-intensity complex magnetic fields
in the order of 1 to 5 μT could increase blood levels of DMT, corresponding with the similarities
observed between experimentally-induced altered states and those encountered in the field.
4. Conclusions
Based on a number of previous theoretical approaches [1, 4-5], along with the preceding
discussions presented here, there is a clear relevance and transdisciplinary convergence between
the realms of parapsychology and anthropological investigation of cross-cultural spiritual
practices, particularly with regard to magico-religious activities. The briefly defined overlap
present throughout these disciplines suggests something more fundamental to the subjective
human experience throughout history with regard to seemingly anomalous or mystical
phenomena.
By integrating methods and theories across disciplines, a greater understanding of notoriously
difficult to interpret psi processes could be gleaned, and this is especially relevant to furthering
an overall ecological understanding of physical consciousness-related anomalies and other
“paranormal” activities. Furthermore, an increased focus on psi and other consciousness research
with indigenous practitioners may help support the suggestion of paranthropological equivalence
between cross-disciplinary phenomenology encountered in parapsychology and anthropological
field studies. Ethnographic study within the field of anthropology may also benefit from this
emerging paradigm shift. As Stanley Krippner [52] has previously noted, “Western
interpretations of [magico-religious practices] often reveal more about the observer than they do
about the observed.” In this regard, many anthropologists and other Western field researchers
who are fortunate enough to observe a traditional spiritual practice may tend to describe these
activities as products of a particularly robust cultural belief system [5], or as little more than
fraudulent performances. However, by applying theoretical components of parapsychology, a
more accurate understanding may be obtained which could be more reflective of the
practitioners’ values and beliefs, while simultaneously enhancing our understanding of the
phenomenon itself.
While some researchers have begun to apply theoretical approaches derived from cross-cultural
studies in the context of experimental psi and consciousness research [8, 56-57], a concerted
effort to conduct field research employing parapsychological methodologies remains in a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
476
preliminary phase of investigation [15, 44, 47, 86]. Ecological studies of psi employing both
parapsychological and ethnographic methods seem likely to be able to shed light not only on the
fundamental nature of psi, but also on the role and function that psi phenomena may perform in
the wider contexts of culture and personal experience. Much is left to be revealed regarding these
transdisciplinary relationships, although research efforts are ongoing around the world in order to
bridge the gap between parapsychology and anthropology.
Acknowledgments: The authors would like to thank Transnational Anomalies Research team members
Nicolas Rouleau for internal review, and Dr. David Luke for useful comments on this paper.
References
1) Hunter, J. (ed.). (2012a). Paranthropology: Anthropological Approaches to the Paranormal. Bristol:
Paranthropology.
2) Hunter, J. (2014). Paranthropology: Towards a Parapsychological Anthropology. Anomaly: Journal of
Research into the Paranormal, 47, 102-112.
3) Miller, I. (2012). A transdisciplinary look at paranthropology: An emerging field of exploration.
Journal of Consciousness Exploration & Research, 3(8), 1018-1031.
4) Luke, D. (2010). Anthropology and parapsychology: Still hostile sisters in science? Time and Mind:
The Journal of Archaeology, Consciousness and Culture, 3(3), 245-266.
5) Caswell, J. M. (2014). Consciousness, cross-cultural anomalies and a call for experimental research in
paranthropology. Journal of Consciousness Exploration & Research, 5(4), 331-340.
6) Saroglou, V. (2011). Believing, bonding, behaving, and belonging to the big four religious dimensions
and cultural variation. Journal of Cross-Cultural Psychology, 42.8, 1320-1340.
7) Hunter, J. (2012c). Why People Believe in Spirits, God and Magic. David & Charles.
8) Caswell, J. M., Collins, M. W. G., Vares, D. A. E., Juden-Kelly, L. M., & Persinger, M. A. (2013).
Gravitational and experimental electromagnetic contributions to cerebral effects upon deviations from
random number variations generated by electron tunneling. International Letters of Chemistry, Physics
and Astronomy, 11, 72-85.
9) Persinger, M. A., Roll, W. G., Tiller, S. G., Koren, S. A., & Cook, C. M. (2002). Remote viewing with
the artist Ingo Swann: Neuropsychological profile, electroencephalographic correlates, magnetic
resonance imaging (MRI), and possible mechanisms. Perceptual and Motor Skills, 94, 927-949.
10) Scott, M. A., & Persinger, M. A. (2013). Cerebral activity and source profiles accompanying the
process of non-locality. NeuroQuantology, 11(3).
477
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
11) Radin, D. I. (2004). Electrodermal presentiments of future emotions. Journal of Scientific
Exploration, 18(2), 254-273.
12) Bem, D. J. (2011). Feeling the future: Experimental evidence for anomalous retroactive influences on
cognition and affect. Journal of Personality and Social Psychology, 100(3), 407-425.
13) Dotta, B. T., & Persinger, M. A. (2009). Dreams, time distortion and the experience of future events:
A relativistic, neuroquantal perspective. Sleep and Hypnosis, 11(2), 29-39.
14) Gaona, J. M., Colinas, F. Rouleau, N., Tessaro, L. W. E., & Caswell, J. M. (2014). Premonitions:
A global online statistical tracking study of precognitive predictions. Journal of Consciousness
Exploration & Research, 5(4), 341-350.
15) Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A. (2014a). Transnational
FieldREG exploration II: Investigating the FieldREG phenomenon in a range of novel settings.
Journal of Consciousness Exploration & Research, 5(4), 309-330.
16) Lange, R., Houran, J., Harte, T. M., & Havens, R. A. (1996). Contextual mediation of perceptions in
hauntings and poltergeist-like experiences. Perceptual and Motor Skills, 82, 755-762.
17) Roll, W. G., Saroka, K. S., Mulligan, B. P., Hunter, M. D., Dotta, B. T., Gang, N., Scott, M. A., StPierre, L. S., & Persinger, M. A. (2012). Case report: A prototypical experience of 'poltergeist'
activity, conspicuous quantitative electroencephalographic patterns, and sLORETA profiles suggestions for intervention. Neurocase, 18(6).
18) Houran, J., Wiseman, R., & Thalbourne, M. A. (2002). Perceptual-personality characteristics
associated with naturalistic haunt experiences. European Journal of Parapsychology, 17, 17-44.
19) Braithwaite, J. J. (2004). Magnetic variances associated with 'haunt-type' experiences: A comparison
using time-synchronised baseline measurements. European Journal of Parapsychology, 19, 3-28.
20) Luke, D. (2011). Anomalous phenomena, psi and altered consciousness. In E. Cardeña, and
Winkelman, M. (Eds.), Altering consciousness: A multidisciplinary perspective, vol 2 –Biological and
psychological perspectives. (pp.355-374). Westport, CT: Praeger.
21) Krippner, S. (2000). The epistemology and technologies of shamanic states of consciousness. Journal
of Consciousness Studies, 7(11-12), 93-118.
22) Cook, C. M., & Persinger, M. A. (1997). Experimental induction of the 'sensed presence' in
subjects and an exceptional subject. Perceptual and Motor Skills, 85, 683-693.
normal
23) Persinger, M. A., Saroka, K., Koren, S. A., & St-Pierre, L. S. (2010). The electromagnetic induction
of mystical and altered states within the laboratory. Journal of Consciousness Exploration &
Research, 1(7).
24) Long, J. K. (ed.) (1977). Extrasensory Ecology: Parapsychology and Anthropology. Metuchen:
Scarecrow Press.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
478
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
25) Swanton, J.R. (1953). A letter to anthropologists. Journal of Parapsychology, 17, 144-152.
26) Huxley, F. (1967). Anthropology and ESP. In Science and ESP. New York: Humanitarian
Press.
27) de Martino, E. (1968 [1972]). Magic: Primitive and Modern. London: Tom Stacey.
28) Evans-Pritchard, E.E. (1937 [1976]). Witchcraft, Oracles and Magic Among the Azande. Oxford:
Clarendon Press.
29) Grindal, B. T. (1983). Into the heart of Sisala experience: Witnessing death divination. Journal of
Anthropological Research, 39(1), 60-80.
30) Turner, E. (1998). Experiencing Ritual: A New Interpretation of African Healing. Philadelphia:
University of Pennsylvania Press.
31) Long, J. K. (ed.) (1977). Extrasensory Ecology: Parapsychology and Anthropology. Metuchen:
Scarecrow Press.
32) Van de Castle, R. L. (1976). Some possible anthropological contributions to the study of
parapsychology.' In. G. Schmeidler (ed.) (1976). Parapsychology: Its Relation to Physics, Biology,
Psychology and Psychiatry. Metuchen: Scarecrow Press, Inc. (pp. 151-161).
33) Giesler, P. V. (1984a). Parapsychological anthropology I: Multi-method approaches to the study of
psi in the field setting. Journal of the American Society for Psychical Research, 78(4), 289-330.
34) Hunter, J. (2009). Anthropology & the paranormal: Approaches to the investigation of paranormal
beliefs and practices. Anomaly: Journal of Research Into the Paranormal, 46, 24-36.
35) Graham, F. (2011). Commentary on “Reflecting on paranthropology.” Paranthropology: Journal of
Anthropological Approaches to the Paranormal, 2(3), 20 – 21.
36) Blanes, R., & Espirito Santo, D. (2013). The Social Life of Spirits. Chicago: University of Chicago
Press.
37) Hunter, J., & Luke, D. (2014). Talking with the Spirits: Ethnographies from Between the Worlds.
Brisbane: Daily Grail.
38) Laughlin, C. D. (2012). Transpersonal anthropology: What is it, and what are the problems we face in
doing it? In B. Alden Cox, J. M. Chevalier, & V. Blundell (eds.) A Different Drummer: Readings in
Anthropology with a Canadian Perspective. McGill-Queen’s Press.
39) Bowie, F. (2013). Building bridges, dissolving boundaries: Towards a methodology for the
ethnographic study of the afterlife, mediumship and spiritual beings. Journal of the American
Academy of Religion, 81(3), 698-733.
40) Hunter, J. (2012c). Talking with Spirits: Personhood, Performance and Altered States of
Consciousness in a Contemporary Spiritualist Home-Circle. Unpublished MLitt Dissertation,
University of Bristol.
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
479
41) Luke, D. (2012). Experiential reclamation and first-person parapsychology.’ In J. Hunter (ed.) (2012).
Paranthropology: Anthropological Approaches to the Paranormal. Bristol: Paranthropology.
42) Jahn, R. G., Dunne, B. J., Nelson, R. D., Dobyns, Y. H., & Bradish, G. J. (1997). Correlations of
random binary sequences with pre-stated operator intention: A review of a 12-year program. Journal
of Scientific Exploration, 11(3), 345-367.
43) Radin, D. I., & Nelson, R. D. (2003). Meta-analysis of mind-matter interaction experiments: 19592000. In Healing, Intention, and Energy Medicine (pp. 39-48). London: Harcourt Health Sciences.
44) Nelson, R. D., Jahn, R. G., Dunne, B. J., Dobyns, Y. H., & Bradish, G. J. (1998). FieldREG II:
Consciousness field effects: Replications and explorations. Journal of Scientific Exploration, 12(3),
425-454.
45) Mason, L. I., Patterson, R. P., & Radin, D. I. (2007). Exploratory study: The random number
generator and group meditation. Journal of Scientific Exploration, 21(2), 295-317.
46) Bajpai, R., Burke, R., Carniello, T., Caswell, J., DeGracia, D. J., Dossey, L., Dotta, B., Juden Kelly,
L., Kokubo, H., Millar, B., Persinger, M. A., Pitkanen, M., Rouleau, N., Saroka, K., Scott, M. A.,
Sidorov, L., St.-Pierre, L., Tessaro, L., Tressoldi, P., & Vares, D. (2013). Tinkering with the
unbearable lightness of being: Meditation, mind-body medicine and placebo in the quantum biology
age. Journal of Nonlocality, 2(2).
47) Saklani, A. (1988). Preliminary tests for psi-ability in shamans of Garhwal Himalaya. Journal of the
Society for Psychical Research, 55(811), 60-70.
48) Pippa, L., Manzoli, L., Corti, I., Congedo, G., Romanazzi, L., & Parruti, G. Functional capacity after
traditional Chinese medicine (qi gong) training in patients with chronic atrial fibrillation: A
randomized controlled trial. Preventive Cardiology, 2007; 10(1): 22-25.
49) Dressen, L. J., & Singg, S. Effects of Reiki on pain and selected affective and personality variables of
chronically ill patients. Subtle Energies & Energy Medicine, 1998; 9(1): 51-82.
50) Ventura, A. C., Saroka, K. S., & Persinger, M. A. (2014). Non-locality changes in intercerebral theta
band coherence between practitioners and sujects during distant Reiki procedures. Journal of
Nonlocality, 3(1).
51) Persinger, M. A., & Saroka, K. S. (2012). Protracted parahippocampal activity associated with Sean
Harribance. International Journal of Yoga, 5(2), 140-145.
52) Krippner, S. C. (2002). Conflicting perspectives on shamans and shamanism: Points and
counterpoints. American Psychologist, 57(11), 962-977.
53) Desjarlais, R. R. (1989). Healing through images: The magical flight and healing geography of Nepali
shamans. Ethos, 17(3), 289-307.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
480
54) Glass-Coffin, B. (2010). Anthropology, shamanism, and alternate ways of knowing-being in the
world: One anthropologist's journey of discovery and transformation. Anthropology and Humanism,
35(2), 204-217.
55) Noll, R. (1985). Mental imagery cultivation as a cultural phenomenon: The role of visions in
shamanism. Current Anthropology, 26(4), 443-461.
56) Storm, L., & Rock, A. J. (2009a). Shamanic-like journeying and psi: I. Imagery cultivation,
paranormal belief, and the picture-identification task. Australian Journal of Parapsychology, 9(2),
165-192.
57) Rock, A. J., & Storm, L. (2010). Shamanic-like journeying and psi: II. Mental boundaries,
phenomenology, and the picture-identification task. Australian Journal of Parapsychology, 10(1), 4168.
58) Storm, L., & Rock, A. J. (2009). Imagery cultivation vs. noise reduction: Shamanic-like journeying as
a psi-conducive alternative to the Ganzfeld protocol. Australian Journal of Parapsychology, 9(1), 531.
59) Frazer, J.G. (1890 [1993]). The Golden Bough: A Study in Magic and Religion. Hertfordshire:
Wordsworth Editions.
60) Boddy, J. (1988). Spirits and selves in Northern Sudan: The cultural therapeutics of possession and
trance. American Ethnologist, 15(1), 4-27.
61) Bourguignon, E. (1973). Religion, Altered States of Consciousness, and Social Change. The Ohio
State University Press.
62) Greenfield, S.M. (2008). Spirits with Scalpels. Walnut Creek: Left Coast Press.
63) Bubandt, N. (2009). Interview with an ancestor: Spirits as informants and the politics of possession in
North Maluku. Ethnography, 10(3), 291-316.
64) Gauld, A. (1982). Mediumship and Survival: A Century of Investigations. London: Granada
Publishing Ltd.
65) Rock, A.J. (2014). The Survival Hypothesis: Essays on Mediumship. Jefferson: McFarland
Publishing.
66) Giesler, P.V. (1985). Parapsychological Anthropology: II. A multi-method study of psi and psirelated processes in the Umbanda ritual trance consultation. Journal of the
American Society for
Psychical Research
67) Oohashi, T., Kawai, N., Honda, M., Nakamura, S., Morimoto, M., Nishina, E., Maekawa, T. (2002).
Electroencephalographic measurement of possession trance in the field. Clinical Neurophysiology,
11(3), 435-445.
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
481
68) Luna, L. E. (2003). Ayahuasca shamanism shared across cultures. Cultural Survival Quarterly,
27(2), 20-23.
69) Tupper, K. W. (2009). Ayahuasca healing beyond the Amazon: The globalization of a traditional
indigenous entheogenic practice. Global Networks, 9(1), 117-136.
70) Nichols, D. E. (2004). Hallucinogens. Pharmacology & Therapeutics, 101(2), 131-181.
71) Grob, C. S., McKenna, D. J., Callaway, J. C., Brito, G. S., Neves, E. S., Oberlaender, G., Saide, O. L.,
Labigalini, E., Tacla, C., Miranda, C. T., Strassman, R. J., & Boone, K. B. (1996). Human
psychopharmacology of hoasca, a plant hallucinogen used in ritual context in Brazil. The Journal of
Nervous and Mental Disease, 184(2), 86-94.
72) Harner, M. J. (1973). Common themes in South American Indian yagé experiences. Hallucinogens
and Shamanism, 155-175.
73) Luke, D. P. (2012). Psychoactive substances and paranormal phenomena: A comprehensive review.
International Journal of Transpersonal Studies, 31, 97-156.
74) Luke, D. P. (2009, September). Telepathine (ayahuasca) and psychic ability: Field research in South
America. Abstracts of the British Psychological Society, Transpersonal. Psychology Section 13th
Annual Conference, Scarborough, p.10.
75) Luke, D. P. (2012). Psychoactive substances and paranormal phenomena: A comprehensive review.
International Journal of Transpersonal Studies, 31, 97-156.
76) Luke, D. P., & Kittenis, M. (2005). A preliminary survey of paranormal experiences with
psychoactive drugs. Journal of Parapsychology, 69 (2), 305-327.
77) Luke, D. (2011). Discarnate entities and dimethyltryptamine (DMT): Psychopharmacology,
phenomenology and ontology. Journal of the Society for Psychical Research, 75, 26-42.
78) Lewis-Williams, J. D. (2004). Neuropsychology and Upper Palaeolithic art: Observations on the
progress of altered states of consciousness. Cambridge Archaeological Journal, 14(1), 107-111.
79) Bednarik, R. G. (1990). On neuropsychology and shamanism in rock art. Current Anthropology,
31(1), 77-84.
80) Whitley, D. S. (1998). Cognitive neuroscience, shamanism and the rock art of native California.
Anthropology of Consciousness, 9(1), 22-37.
81) Lewis-Williams, J. D., & Lewis-Williams, J. D. (2002). The Mind in the Cave: Consciousness and the
Origins of Art. Thames & Hudson: London.
82) Persinger, M. A. (1983). Religious and mystical experiences as artifacts of temporal lobe function: A
general hypothesis. Perceptual and Motor Skills, 57(3f), 1255-1262.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 467-482
Caswell, J. M., Hunter, J. & Tessaro, L. W. E., Phenomenological Convergence between Major Paradigms of Classic
Parapsychology and Cross-Cultural Practices: An Exploration of Paranthropology
482
83) Meli, S. C., & Persinger, M. A. (2009). Red light facilitates the sensed presence elicited by
application of weak, burst-firing magnetic fields over the temporal lobes. International Journal of
Neuroscience, 119(1), 68-75.
84) Saroka, K., Mulligan, B. P., Murphy, T. R., & Persinger, M. A. (2010). Experimental elicitation of an
out of body experience and concomitant cross-hemispheric electroencephalographic coherence.
NeuroQuantology, 8(4).
85) Hill, D. R., & Persinger, M. A. (2003). Application of transcerebral, weak (1 microT) complex
magnetic fields and mystical experiences: Are they generated by field induced dimethyltryptamine
release from the pineal organ? Perceptual and Motor Skills, 97(3f), 1049-1050.
86) Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C., & Tessaro, L. W. E.
(2014b). The potential effects of human group emotion and subjective novelty on the statistical
behaviour of a random event generator: Exploratory study. Journal of Consciousness Exploration &
Research, 5(3), 195-214. |
On the independence between phenomenal
consciousness and computational intelligence
Eduardo C. Garrido Merchán, Sara Lumbreras
arXiv:2208.02187v1 [cs.AI] 3 Aug 2022
1
Universidad Pontificia de Comillas, Madrid, Spain ecgarrido@icade.comillas.edu
2
Universidad Pontificia de Comillas, Madrid, Spain slumbreras@comillas.edu
Abstract. Consciousness and intelligence are properties commonly understood as dependent by folk psychology and society in general. The
term artificial intelligence and the kind of problems that it managed to
solve in the recent years has been shown as an argument to establish
that machines experience some sort of consciousness. Following Russell’s
analogy, if a machine is able to do what a conscious human being does,
the likelihood that the machine is conscious increases. However, the social implications of this analogy are catastrophic. Concretely, if rights are
given to entities that can solve the kind of problems that a neurotypical
person can, does the machine have potentially more rights that a person that has a disability? For example, the autistic syndrome disorder
spectrum can make a person unable to solve the kind of problems that
a machine solves. We believe that the obvious answer is no, as problem
solving does not imply consciousness. Consequently, we will argue in this
paper how phenomenal consciousness and, at least, computational intelligence are independent and why machines do not possess phenomenal
consciousness, although they can potentially develop a higher computational intelligence that human beings. In order to do so, we try to
formulate an objective measure of computational intelligence and study
how it presents in human beings, animals and machines. Analogously,
we study phenomenal consciousness as a dichotomous variable and how
it is distributed in humans, animals and machines. As phenomenal consciousness and computational intelligence are independent, this fact has
critical implications for society that we also analyze in this work.
Keywords: Computational Intelligence, Phenomenal Consciousness
1
Introduction
The concept of consciousness has always been difficult to define, as it is a
property that can not be directly measured by any method coming from
our current scientific method [56]. In particular, it is an ontologically subjective phenomenon, and a measure in the sense of the scientific method
applies to an epistemologically objective phenomenon [60]. However, we
can split the consciousness concept into several phenomenons associated
with the term to make it easier to work with this phenomenon. Specifically, the philosophy of mind literature splits consciousness into phenomenal consciousness, also referred as vigilance according to neuroscience
2
Eduardo C. Garrido Merchán, Sara Lumbreras
[9]) and that basically refers to the subjective and private to the observer
sensations that human beings feel (also called awareness) and access consciousness, [5], that refers to the ability to put attention to a particular
feeling. Last, another type of consciousness is self-consciousness, that is
basically the model of our identity that we build based on our experience and abilities [49]. In other words, we differentiate between subjective
phenomenona, the relative to the observer experience of something that
the observer is paying attention to, and the objective phenomena, that
can be simulated in a computer even if it is related to consciousness [40].
For example, we can manipulate colours with computers but we cannot
simulate qualia. We can even simulate the bottleneck of consciousness
[18] but cannot simulate the perceived experience of the result.
Whereas access and self-consciousness can arguably, and in our opinion, be simulated by a computer successfully, for example with attention
mechanisms [64] and a computational ontology of a person based on historical records [6], how to implement or simulate phenomenal consciousness, that is going to be the target of this paper, remains a complete
mystery. In particular, we can not simulate the experience of the perception of qualia, such as the redness of the red colour. Philosophy of
mindexplains this impossibility with the example of Mary, a blind girl
that is an expert in vision. Although being an expert, Mary is unable
to know what is the difference in the perception of red or black, as this
information comes from qualia and is subjective, that is, cannot be represented in an objective manner such as in a book description [36]. This is
known as the knowledge argument: and it rests on the idea that someone
who has a complete objective knowledge, from the point of view of the
scientific method and our epistemological scope, about another conscious
being might yet lack knowledge about how it feels to have the experiences of that being [44]. A common belief shared by many people of the
computer science community, and concretely in the machine consciousness community [17] and even in the philosophy of mind community and
more concretely shared by the connectionism community [2], is that if
an artificial general intelligence [20] is modelled (supposedly via some
meta-learning [63] or transfer learning methodology [62] applied to high
capacity deep learning models [30] and huge datasets), due to emergence,
phenomenal consciousness may arise. Hence, this group of people believe,
assuming the multiple realizability philosophy of mind assumption [24],
that an intelligent enough system is the cause of phenomenal consciousness, that phenomenal consciousness arises as an epiphenomenon [41], or
that intelligence is the cause of phenomenal consciousness or viceversa,
that is, that they are dependent variables.
In order to continue analyzing the potential statistical, or even metaphysical, causal relation between phenomenal consciousness and intelligence, it is important to also briefly describe intelligence, which is another controversial concept that has been in focus since the times of
ancient philosophers. Coming from the psychology community, and in a
broad sense, intelligence is a very general mental capability that, among
other things, involves the ability to reason, plan, solve problems, think
abstractly, comprehend complex ideas, learn quickly and learn from experience [21]. If these problems are computational, we can reduce and
On the independence between consciousness and intelligence
quantify intelligence as an analytical expression [7], as we will see in
further sections, giving rise to the concept of computational intelligence.
From an ontological objective point of view, independent of the observer,
the described definition of intelligence shown by a system or living being
would be epistemologically subjective, as it is relative to the observer
and its knowledge, culture and beliefs. Consequently, we can not directly
measure it without observing the external behaviour of the person. As
a result, the observer could be really more intelligent that he appears
to be according to its behaviour. However, it is the only measure that
we can express quantitatively and to study its relation with phenomenal
consciousness, although it is based on the behaviour of the subject. As
we will further see, as in the case of Asperger and Autism syndrome
subjects, the person may be really more intelligent according to Stern’s
intelligence quotient or some measures of intelligence that we will show
than its behaviour shows, which is very problematic. In other words,
we argue that computational intelligence would be an ontological objective continuous numerical latent variable whose observation is noisy and
obscured by a series of factors such as the personality or mood of the person being measured. As phenomenal consciousness is also an ontological
dichotomous property, it only has sense to use this definition of computational intelligence, and not a epistemological subjective definition, to
study its independence with phenomenal consciousness.
If these computational problems can be solved by a computer, either traditional or a quantum computer, we find the concept of artificial or machine intelligence [31]. Concretely, it is important to remark that the artificial intelligence models implemented in quantum, traditional or other
computing paradigms such as biological computation mechanisms, solve
the same space of problems, in particular, those solvable by an universal
Turing machine. However, artificial intelligence does not involve concepts
as understanding [19], as understanding requires an entity being aware of
the learned concept. Nevertheless, computational intelligence does not require understanding. For example, a model can beat any human at chess,
displaying a bigger estimation of computational intelligence than aware
beings, while being unaware. It wins chess by having learned complex
patterns of previous data with statistical models or performing search
algorithms that humans can not perform but it does not understand the
meaning of chess as it is not aware of the experience of playing chess.
Consequently, it is merely following a sequence of instructions that maximizes the probability of winning chess based on previous data. Hence,
we find that computational intelligence, which is a subset of intelligence,
is independent in this example from phenomenal consciousness, which is
the focus of this paper and we will further continue to provide examples
such as this one. General intelligence [69] involves other types of intelligence such as emotional intelligence [53] or multiple intelligences [29].
These intelligences can also be measured in human beings with measures such as the Stern’s intelligence quotient [57], or more sophisticated
metrics, and may be simulated in machines if they do not require understanding nor qualia experience. All the other aspects of intelligence
coming from the psychology community definition such as learning from
experience, thinking abstractly or planning can be simulated with ma-
3
4
Eduardo C. Garrido Merchán, Sara Lumbreras
chines, as for example The Generalized Agent (GATO) from DeepMind
empirically shows. Citing the paper explicity:
”The agent, which we refer to as Gato, works as a multi-modal,
multi-task, multi-embodiment generalist policy. The same network with
the same weights can play Atari, caption images, chat, stack blocks with
a real robot arm and much more, deciding based on its context whether
to output text, joint torques, button presses, or other tokens.”
We will provide arguments to theoretically support the claim that computational intelligence is not related to phenomenal consciousness and
that machines do not possess phenomenal consciousness. Therefore, as
we will illustrate in detail in further sections, we justify and claim that
rights must belong to people and ethical decisions must be taken by people, not just by, for example, machine learning systems. Moreover, we
must not judge a person for its intelligence but because it is a human
being with the potential of being conscious. Not doing it so implies a discrimination of a conscious being because of its measurable computational
intelligence.
In this paper, we will provide solid arguments coming from computer
science, neuroscience, physics, psychology and philosophy of mind to reject the hypothesis that phenomenal consciousness computational intelligence are dependent variables. We find that the root of this belief is
explicitly formulated in the ”Analogy” paper written by Bertrand Russell [51]. Hence, all the argumentation that will be shown in this paper
tries to show that the Analogy of Russell, that very briefly states that
as the observable degree of computational intelligence of an individual
increases then it becomes more probable that the individual possesses
phenomenal consciousness, is a fallacy.
The organization of the paper is the following.First, we illustrate the
Analogy of Russell and formalize it from a Bayesian point of view. Then,
we provide some simple counter-examples of it that show empirical evidence of how unlikely is that hypothesis to be true. In an additional
section, we study the concept of intelligence and provide a new definition
of computational intelligence to more formally reject the mentioned hypothesis. With that definition, modelling computational intelligence with
a numerical variable and phenomenal consciousness with a dichotomous
variable, we study the potential causal relation of phenomenal consciousness and computational intelligence and theoretically provide an argument that shows how these properties are independent, formally and
with an exhaustive list of counter-arguments. Afterwards, we formalize
how phenomenal consciousness and computational intelligence are independent and the consequences that this fact have in our society. Finally,
we finish the paper with a section of conclusions and further work.
2
Russell’s analogy of consciousness
In this section, we will present the analogy postulated bn y Russell about
intelligence and consciousness [51]. Broadly speaking, he states that it
On the independence between consciousness and intelligence
is highly probable that consciousness is the only cause of the intelligent
behaviour that humans exhibit. It does so by supposing that if the behaviour of people is similar to our own, then, by observation, we can
establish a causal relation that the other people possess consciousness as
we do. Literally, from the Analogy of Russell, we have that:
”We are convinced that other people have thoughts and feeling that are
qualitatively fairly similar to our own...it is clear that we must appeal to
something that may be vaguely called analogy. The behavior of other
people is in many ways analogous to our own, and we suppose that is
must have analogous causes. What people say is what we should say if
we had certain thoughts, and so we infer that they probably have these
thoughts... As it is clear to me that the causal laws governing my
behavior have to do with thoughts... how do you know that the
gramophone does not think? ... it is probably impossible to refute
materialism by external observation alone. If we are to believe that
there are thoughts and feelings other than our own, that must be in
virtue of some inference in which our own thoughts and feelings are
relevant... establish a rational connection between belief and data...From
subjective observation I know that A, which is a thought or feeling,
causes B, which is a bodily act, whatever B is an act of my own body, A
is its cause. I now observe an act of the kind B in a body not my own,
and I am having no thought or feeling of the kind A. But I still believe
on the basis of self-observation, that only A can cause B. I therefore
infer that there was an A which caused B, though it was not an A that I
could observe.”
Consquently, at least probabilistically, we can infer from the text that
behaviour is a cause of consciousness, although we can not observe consciousness. As behaviour is a cause of intelligence, we can infer that
intelligence is an effect of consciousness, being a causal relation. However, the previous reasoning is a fallacy, as it deals with the assumption
that the intelligent behaviour of any agent shares the same causes as
our behaviour, which as he writes in multiple times in the text, is the
mind. For instance, the DALLE-2 model generates artistic images but
if we assume that the multiple realizability postulate is false, then, it is
not conscious, so consciousness is not the cause of its behavior. In other
words, it seems that the analogy reasoning involves more correlation that
causality. Here the confounder would be that both my behaviour and the
behaviour of the DALLE-2 model are both the result of a human intent.
From a classical logic point of view, he states that every living being
produces intelligent behavior, applying modus ponens. However, applying modus tollens if a being does not exhibit intelligent behavior outside,
then it would be no conscious, at least, from a probabilistic point of view,
probably. This fact that is a consequence of applying the analogy reasoning has dramatic consequences that will be analyzed in further sections.
Moreover, he states that a rational connection between belief, consciousness, and data, behaviour, must be set. Therefore, consciousness would
5
6
Eduardo C. Garrido Merchán, Sara Lumbreras
be the cause of intelligence, at least from a computational point of view.
Also, we cannot establish a causal relation by performing such an experiment based on analogy alone. In that particular experiment, we observe
that a subject is intelligent and we infer that he is conscious. First, we
do not have any control group in this experiment, being what is known
in science and in a plethora of disciplines such as psychology or econometrics a pre-experiment, an experiment where we are not able to infer
a causal relation between the dependent variable, being conscious, and
the independent variable, showing an intelligent behaviour.
In addition, we have several other problems, as we will detail in this
work. First, dealing with several syndromes and illnessess. Let us examine
a person suffering from severe autism, this person may not show an
intelligent behaviour, hence, following the argument of Russell, there is,
at least, a high likelihood that this person is not conscious. We believe
and will add theoretical evidence that this is not true, showing clear
empirical cases where a phenomenal conscious human being does not
exhibit an intelligent behaviour. Moreover, the same happens with other
syndromes such as Down.
Having shown that there are phenomenally conscious human beings that
do not exhibit intelligent behaviour according to several estimates or that
its computational intelligence can not be compared to the ones of computers, we provide another counter-example to the analogy, coming from
the field of artificial intelligence [52]. In particular, we have seen how, in
recent years, due to methodological advantages such as deep learning [30]
and the rise of computational power, intelligent systems have surpassed
human abilities in a series of complex games. Some examples include AlphaGo winning at the Go game to the world champion [66], IBM Watson
winning at Jeopardy [15] and discovering new unknown chess strategies
with deep learning [39]. General intelligence is a broad property, in the
ontological sense, but we can reduce its meaning and provide a definition for a subset of it. In particular, we can epistemologically measure
it as a function of the proportion of the computational problems that a
system can solve from the set of all computational problems. Following
this lower bound of general intelligence, a system implementing all the
known machine learning models and meta models of them able to solve
any task with sufficient data will, for sure, outperform the performance
of human beings in a broad series of problems and even solve problems
that we do not know how to solve, like the protein folding problem [28].
As a consequence, following the analogy of Russell, it would be highly
likely that a system that implements these algorithms would be conscious. It would be even more probable that such a system is conscious
that any other human being. However, as we will further show, providing
multi-disciplinary arguments, the likelihood that a Turing machine, that
is essentially any known software being executed by a computer, is conscious is almost zero. Hence, the evidence given by the data shows that
the hypothesis that there is a causal relation between intelligence and
consciousness is fallacious. Finally, as an extreme argument, if we measure the computational intelligence of a severe autistic person with respect to a system implementing several methodologies such as AlphaGo,
the difference in intelligence, measured for example with the intelligence
On the independence between consciousness and intelligence
quotient would be even higher, however, and also with theoretical and
empirical evidence coming from the global workspace theory [9], the severe autistic person is conscious and the system is not. If we follow this
argument, we discover that it is more probable that intelligence and consciousness are just independent variables. In this paper, we will slowly
give arguments that support this claim.
Bayesian modelling of the analogy. The correlation between intelligence
and phenomenal consciousness is positive and strong, near to 1. That
is, the conditional probability (C) that an entity possesses consciousness
given that is intelligent (I) is close to 1 p(C/I) ≈ 1. [8].
Implies a measure of consciousness and intelligence. [54]
Consciousness cannot be measured with the current scientific method.
(Include citations)
Moreover, can we measure, or even define, intelligence? At least, can we
even define different types of intelligence? [68]
3
Defining intelligence
Intelligence is a widely known concept that has been assimilated by the
computer science community to coin the term artificial intelligence. However, artificial intelligence is a misleading term, as it requires a proper
definition of intelligence as a property that can be modelled with a set
of numerical variables.
In particular, multiple definitions of intelligence have been proposed by
different communities but all of them seem to be a reduction of the
general meaning of intelligence. For example, if we include as intelligence
the ability to understand and empathize with another person, this ability
requires to feel the situation that is having the other person. From a
theoretical, relative to the observer and internal point of view, it will
not be enough to appear to understand or feel by simulation methods
based on quantitative measures, it would need to recieve the qualia of
the feeling or the idea being understood.
Hence, feeling requires awareness, or phenomenal consciousness, of the
person that is having a conversation. As a consequence, as we will argue,
this ability can not be reduced to a a simple set of numerical variables
nor be implemented in a machine.
Consequently, the term artificial intelligence is a reduction of the intelligence of conscious beings and the term intelligence is really hard to
define. In this paper we make a review of the different definitions of
intelligence, we will technically argue why artificial intelligence is a reduction of biological intelligence and propose a new definition of general
intelligence that can not be reduced to a set of numerical variables nor,
as we will show, be implemented in machines.
Definitions of intelligence [68]: machine [31], technical or computational
(related to artificial intelligence) [7] general [69] emotional [53] multiple
[29], natural [68].
3.1
Artificial intelligence and deep learning
Artificial intelligence [52] has another controversial definition. Generally,
it is the science and engineering of making intelligent machines [38].
7
8
Eduardo C. Garrido Merchán, Sara Lumbreras
But, if we want to define the intelligence of machines, that definition is
circular, hence invalid. We prefer to define it as an objective quantitative
measure that is determined by the scope of problems that an artificial
system is able to solve.
In the recent years, due to the significant advances of computational
power, it has been possible to implement high-capacity machine-learning
models [42] like deep neural networks, what is usually referred as deep
learning [30]. As we have illustrated in the introduction, these models,
whose capacity includes having more than 500 billions of parameters
[50], are able to solve complex problems like the protein folding problem
[28], go and chess [66], write philosophy articles in a newspaper mocking
the type of writings that were usually only attributed to human beings
[16] mastering natural language processing and common sense tasks and
generating art [67]. In essence, deep learning methodologies are able to
fitting complex probability distributions being able to generalize their
behaviour to tasks that we only supposed to be solved by humans, making
their behaviour indistinguishable from the one of humans [13].
However, deep neural networks are software programs that are executed
using computer hardware in a CPU (Central Processing Unit), GPU
(Graphical Processing Unit) or TPU (Tensorial Processing Unit). Concretely, these hardware units are a part of a Von Neumann architecture,
that is essentially a Turing machine, making deep neural networks algorithms that can be executed by a Von Neumann architecture, hence a
Turing machine. Consequently, as we will further provide arguments for
this claim, they lack awareness or phenomenal consciousness. As a result,
they are unable to understand nor experience the scope of problems that
they are solving and merely solve computations involving pattern recognition, independently of their complexity. Hence, artificial intelligence
systems only posses computational intelligence [31] [7], lacking understanding as it requires the qualia of the problem being solved. However,
a virtue of computational intelligence is that it can be quantified, as
it solves objective problems belonging to the set of all possible computational problems. In contrast, general human intelligence, as we will
further see, is a subjective and relative to the observer measure, requiring
the qualia generated by understanding, feelings or empathy and hence
being impossible to fully quantify without incurring in a reductionist
measure.
There are several propositions to quantify the computational intelligence
that a system or an entity possess. Let π be an entity, for example a human being, that in every instant t is able to perform a set of actions A
to solve a given problem. An intelligent agent π would decide, for every
instant t, the optimum action a⋆ ∈ A to solve the problem. The branch
of computer science that studies how to train intelligent agents in this
framework is called reinforcement learning [58], and can be directly extrapolated to the reality. For example, if we want to say the optimum
phrase to win a negotiation, in every instant t we receive the sentence
of the person that we are negotiating with, its word frequency, mood
state and more information and as a function of all that information we
choose to answer a certain phrase in a particular mood state. As we can
see, the reinforcement learning can be applied to a plethora of computa-
On the independence between consciousness and intelligence
tional intelligence problems. In fact, reinforcement learning systems are
implemented in robots for planning. Dealing with these systems, that
can perfectly be humans, the universal intelligence function Υ of a data
structure resembling an agent π is given by the following measure [32]:
X −K(µ) π
2
(1)
Vµ .
Υ (π) =
µ∈E
where µ is a data structure representing an environment from the set E
of all computable reward bounded
environments, K(·) is the Kolmogorov
P
complexity, and Vµπ := E( ∞
R
)
is the expected sum of future rewards
i
i=1
Ri when agent π interacts with environment µ. That is, the previous expression is a weighted average of how many problems µ ∈ E does an
agent π solve weighted by their difficulty 2−K(µ) Vµπ and the capabilities
of the agent. In particular, this is the reason why Vµπ includes π. Several things are interesting dealing with this expression. First, the set of
all computable reward bounded environments, i.e., generalizing this set
would be the set of all computational problems, is countably infinite,
having as an axiom that it exists a particular simple problem that can
not be decomposed in more single parts. Hence, the intelligence Υ of an
agent is not upper bounded. If we transform the set E to a set where
the area of a problem µ is given as a function of its difficulty S(µ), being more area given to more difficulty with respect to a particular agent
π, the previous measure can be transformed in this abstract, general
measure:
Z
Υ (π) =
δ(µ|π)S(µ)dµ .
(2)
E
where S(µ) is a oracle function that gives the objective area of a problem µ and δ(µ|π) is a delta function representing whether the particular
problem is solved or not by the agent π. Recall that the delta function
outputs 1 if the problem is solved and 0 otherwise. As the set is potentially countably infinite, a problem can be decomposed according to the
progress on it in different problems until a simple base problem, each one
with different area to measure the progress of an agent in the progress of
a particular problem. Interestingly, the integral over the set E gives the
area of computational problems being solved, and this area is infinite.
Moreover, an oracle giving the particular objective unbiased measure of
difficulty for every problem would be needed. Depending on the features
of the system, a problem may be more difficult than other, specially for
non-computable problems requiring qualia to be solved. These objections
make such a measure impossible to be unbiasedly implemented in practice, but may be a lower bound of the computational intelligence of a
system, animal or human being.
Another example of an intelligence measure of a system represented by
IS for a scope of tasks sampled from Pscope is now described. We have
generalized from the measure proposed by Chollet, taking into account
not only a scope of particular task that are numerable into a set but all
the possible tasks that can be done in our universe, which is potentially
infinite and the one that we believe that should be taken into account.
Recall that we want to provide an ontologically objective general measure
9
10
Eduardo C. Garrido Merchán, Sara Lumbreras
of computational intelligence [7], as we want to study its independence
with an ontologically objective dichotomous property, that is whether
an agent is aware of its phenomenal consciousness. Consequently, any
measure that excludes a single property or is noisy or biased, such as
the intelligence quotient, can not be compared with phenomenal consciousness without being also the results biased or noisy. Summarizing
the main components of the expression, let PIS,T + EIS,T,C (priors plus
experience) represent the total exposure of the system to information
about the problem, including the information it starts with at the beginning of training represented by C, the curriculum. Let ωT · θT be the
subjective value we place on achieving sufficient skill at T and let GD
be the generalization difficulty for agent IS of solving task T given its
curriculum or specific properties of the agent C:
θT
= EPscope [ωT · θT
IIS,P
scope
X
[PC ·
θ
C∈CurTT
θT
GDIS,T,C
θT
θT
PIS,T
+ EIS,T,C
]].
(3)
The formula is basically a generalization of Υ that takes into account
the previous knowledge, modelled by the curriculum and the priors, to
solve a particular task T . The difficulty of the task is now modelled by
the generalization difficulty and solving a potentially infinite scope is
given the computing the expectation over Pscope . However, although this
measure takes into account whether an entity is able to generalize from
prior knowledge as a measure of intelligence, we find the same problems
than in the previous measure.
In both measures of intelligence, as the set of potential problems is potentially infinite and not-numerable, any entity would really have a measure
of general intelligence of approximately 0, as it would fail to solve a potentially infinite set of problems. Moreover, both measures require having an oracle to determine the difficulty of the task. Consequently, they
would both be biased although an objective oracle was able to provide
this quantity.
Any measure of intelligence giving any other score rather than zero, although practical, would be just a lower bound of the true intelligence
of the entity, better approximated with these measures than with the
intelligence quotient measure. Hence, it can be useful for health situations but never to classify an individual as more intelligent than another
individual or, as we will further see, to say that a being is susceptible of
having more or less likelihood of having phenomenal consciousness as a
result of scoring more degree of intelligence according to a measure, as it
is only a lower bound on the true intelligence, that cannot be measured in
practice as we can only approximate it based on a subset of problems and
by the external behaviour of the subject as in the case of the intelligence
quotient. However, recall that it is critical to provide an abstract definition of computational intelligence because of two main reasons: first,
in order to study its independence with an ontological property such as
being aware of phenomenal consciousness, it needs to possess the same
properties as phenomenal consciousness, that is, being ontological, general and not biased. As an analogy, in statistical terms, it needs to be
defined as the parameter, from a frequentist point of view. Second, it
On the independence between consciousness and intelligence
can be useful to provide such a definition of intelligence to shed light to
the psychology community to provide less biased estimators to it. Once
again, this definition corresponds to the parameter and measures such
as the intelligence quotient correspond to the estimator.
3.2
Intelligence quotient and similar approaches
Human intelligence includes a series of skills that are able to solve different types of problems. The set of problems that human intelligence
can solve intersects with the set of computational problems but is not
contained on it.
Some examples of these kind of problems include discriminating which
is the most beautiful color for a particular observer in terms of our perception of the colours, which is the best action that we should do in a
complex personal conflict involving human relationships, how do a person change its state of mood or which is the true notion of a metaphysical
phenomenon. The common feature of all these problems is that they involve qualia, an information about our universe that Turing machines
lack. In particular, we consider qualia as semantic information, in the
sense that the observer perceives the quale of a color in a particular way,
the redness of red, and not in another one. Consequently, this perception
can be considered a property that may be codified and that is actually
transmited to the observer by the brain. Although this information is
subjective and relative to the observer, it is still information that can
be represented in a qualia space such as in the integrated information
theory and is transmitted to the phenomenal consciousness observer.
Consequently, from our point of view, we can only measure the intelligence that a human being shows externally and that is associated to
these problems in terms of correlations, that are a reduction of its true
scope but are the only way of being objective. Since ancient times, human intelligence has been measured with features. For example, in the
ancient Greece memory was very valuable, then the Roman society paid
special attention to rhetoric. In the past century, abstract reasoning was
very appreciated and become a critical feature of Stern’s intelligence quotient [57]. Stern’s intelligence quotient assigns a mental age to a person
based on her performance on a series of tests including reasoning, logic,
language and more. In particular, he divides the scored mental age with
the chronological age to obtain a simple ratio.
However, several features that are independent of intelligence may affect Stern’s measure. For example, the subject can be in a sad mood,
be an introvert or have some special condition as autism. Due to these
conditions, the intelligence shown externally by the subject does not
correspond to its true intelligence, in other words, the true human intelligence would be a latent variable contaminated by noise or any approach
that measures human intelligence as the Stern’s intelligence quotient is
an approximation to the underlying intelligence of the subject.
Moreover, as Stern’s test and similar ones include only a subset of all the
subjective problems that a human being is able to solve, the intelligence
measured by these tests is a lower bound of the true intelligence of the
human being. Consequently, we believe that these approximations are
11
12
Eduardo C. Garrido Merchán, Sara Lumbreras
very naive, poor, unreliable, culturally biased and noisy. From a statistical point of view, the intelligence quotient would be a poor estimator
of human intelligence: biased because it does not test all the areas of intelligence and it is influenced by western culture and with high variance
as its measurement contains noise because individuals may be nervous,
be shy, have a special condition or simply do not wish to score high.
Hence, as we can only obtain a measure of intelligence via a test analogous as the one of Stern, as the quality of the approximation is poor, the
value of this random variable cannot be used in a causal relation with
the value of the phenomenal consciousness dichotomous variable. Recall
that these tests are only able to reduce the true underlying intelligence
of a human being, or even a system, as an approximate lower bound.
Consequently, this quantity can not be established as the cause nor the
effect of phenomenal consciousness.
We can illustrate several examples of this statement. First, we would assume that Russell is correct and consciousness is an effect, or an epiphenomenon, of intelligence. Firstly, a comatose person is, according to neuroscience, phenomenally conscious [1] but would score a 0 according to
Stern’s test or similar ones. Hence, it would not be probable that this
person is conscious if there is a causal relation between consciousness and
intelligence and by analogy with respect to other human beings as Russell
describes in his text. However, it can be [1]. Another example includes
a natural language generative transformer like GPT-3. This algorithm is
very close to passing the Turing test [13] and performs greatly in intelligence quotient tests, however, as we will see in the further section, the
system does not possess awareness. Finally, a Down-syndrome person
would score less points in average than a neurotypical person but both
possess consciousness. These three examples show how, at least computational intelligence and phenomenal consciousness are not related, so the
Russell’s analogy is false. An even more convincing case than the rest is
this one: In the science-fiction book The Three Body Problem [33] an
enormous plethora of people was displayed in a planet like a CPU. Each
person acts as a transistor, creating a huge Von Neumann architecture.
Most critically, observe that there does not exist a physical connection
between the people acting as transistors. Consequently, according to consciousness theories such as information integration theory, that requires
physical connections [61], or the Pribram-Bohm holoflux theory of consciousness [27], this people CPU would be non-conscious as a whole.
However, it is able to solve the same problems that a high capacity deep
learning model is able to solve, as the people CPU can execute a program that implements the deep learning model. This is the most obvious
case where we can see that any algorithm, independently on the degree
of intelligence that we can measure with respect to its behaviour, does
not have phenomenal consciousness and that phenomenal consciousness
is independent from intelligence. In the following section we will argue
how non-computational intelligence may be correlated by consciousness,
but that it remains a mystery and we can not say objectively if they are
dependent or not.
On the independence between consciousness and intelligence
4
Intelligence is not a measure of consciousness
If we accept, as an absurd, that are dependent, we find some problems.
Use in all the section Bayes theorem to model the two hypotheses, entities
having or not phenomenal consciousness.
4.1
Machine consciousness
The computer science community that studies the potential for consciousness in machines is called machine consciousness [17]. In particular, the machine consciousness community, inherits the assumptions of
functionalism, like multiple realizability, and connectionism to especulate
that systems or robots may develop qualia through the implementation
of expert systems, machine learning models, hybrid methodologies or
other variants of information processing systems that, in any case, they
can be emulated using Turing machines [17]. However, as we have illustrated in the previous section with the people CPU, the computational
intelligence shown by algorithms, independently of its complexity, is not
the cause of phenomenal consciousness. Moreover, as we will illustrate
in the following section, there are more philosophical arguments that
provide evidence on the highly remote hypothesis that computational
intelligence is the cause of phenomenal consciousness.
4.2
Strong artificial intelligence counter-arguments
Our argumentation depends on the assumption that artificial intelligence
systems, like high-capacity deep learning models, are not aware of themselves. As currently an ensemble of systems would have greater computational intelligence than human beings and they do not have phenomenal
consciousness, this example is a great counter-argument to the hypothesis that phenomenal consciousness is an epiphenomenon of computational intelligence or that they are simply dependent variables. Hence, in
this section, we will describe the main counter arguments to the strong
artificial intelligence hypothesis, i.e., the one saying that complex machines implementing high capacity models and reasoning systems may
arise consciousness by emergence.
The nobel laureate Roger Penrose, defending its controversial Orch-Or
theory that states that phenomenal consciousness arises at the quantum
level inside neurons [47], gives a plethora of strong artificial intelligence
counter-arguments in its books.
First, we find the famous Searle chinese room [55]. This experiment basically denotes the difference between pattern recognition and understanding. Generalizing the argument, suppose that an entity is hidden
in a room where a text written in an unknown language is read by the
entity. The entity has a dictionary, or a mapping function, with the correct answers to the questions written in that language. From the point of
view of an observer located outside of the room, the entity that resides in
the room appears to understand the language, however, the entity does
not understand nothing, as it lacks an understanding of the language.
13
14
Eduardo C. Garrido Merchán, Sara Lumbreras
From our point of view, understanding a language requires an additional
mapping that the observer that lies inside of the room lacks. A mapping
of every word of the language and the qualia that the words refer to.
Qualia is necessary for understanding, and phenomenal consciousness is
necessary for qualia. Hence, as the machines lack phenomenal consciousness, they are unable to understand a language and consequently all that
they do perform is pattern recognition, in other words, solving complex
correlations creating a function whose input is a sentence of a language
and its output is another sentence of that language.
Recall from previous sections, where we provide the example of the people CPU that appears in the science fiction book The Three Body Problem [33] that was able to perform complex computations and run algorithms to predict a planetary disaster without using computers, that
performing complex pattern recognition tasks due to the information processing done by high capacity deep learning or other statistical models
is not enough to arise phenomenal consciousness by emergence. Concretely, not only in science fiction we have found an example of a person
CPU, in a real experiment available on Youtube [65] and that has been
implemented in a code that is available on Github, we have found how
people were organized smartly in a field emulating a brain to perform
an algorithmic task. If that experiment had more people available, they
could solve any kind of problem that a Turing machine is able to solve. In
other words, the Stilwell brain is also a Turing machine, as quantum or
classical computers, that does not posses phenomenal consciousness. If
an external observer does not know whether the Stilwell brain is a code,
as the one hosted on Github, or people being organized in a smart way, it
could argue that is intelligence, hence following Russell’s analogy potentially phenomenally conscious, however, according also, without loss of
generality, to the integrated information theory of consciousness and the
Pribram-Bohm holoflux theory of consciousness, the Stilwell brain or any
other brain created by independent entities is an excellent example that
shows how phenomenal consciousness and intelligence are independent.
It is also important to consider that all the algorithms that can be executed in a computer can be solved by Turing machines [25]. Quantum
computers are not an exception, both classical computers and quantum
computers are universal Turing machines and, hence, solve the same kind
of problems only with different computational complexity [11]. Nevertheless, humans are able to feel, that requires being able to perceive
the qualia of the feeling and, we have said before, having the phenomenal consciousness required to feel, phenomenon that is not able for a
Turing machine and that we can not measure objectively [48]. If quantum computers are not able to possess the characteristics and abilities of
phenomenal consciousness, hence, the idea of the brain being a quantum
computer or arising phenomenal consciousness by means of a quantumlike procedure is, at least, a reductionist one, as, in principle, phenomenal
consciousness is independent of this procedure.
Finally, because of the qualia that we experience, we can gain an intuition
about problems that do not have an algorithmic solutions. It is specially
relevant that this intuition, the experience of being able to understand
these problems, can not be sensed by a computer, as it can not perceive
On the independence between consciousness and intelligence
qualia. Some examples of these problems are the following ones. First, the
halting problem, that is, being able to determine, from a random computer program description and an input, whether the program will finish
executing the problem, or continue to run forever [35]. Second, Hilbert’s
tenth problem dealing with Diophantine equations, that are equations
involving only sums, products, and powers in which all the constants are
integers and the only solutions of interest are integers. In particular, the
Hilbert’s problem, proved to be undecidable, is described as being able to
find an algorithm that decides whether a random Diophantine equation
has an integral solution [37].
4.3
Disability and comatose states
Having seen that solving a wide variety of tasks inside the set of all computational problems, even more than the ones of human beings, does
not require that the computationally intelligent system has phenomenal
consciousness we will now study another causal relation that, according
to Russell’s analogy, would incur in a low likelihood for the entity to
be conscious. It is the one dealing with people suffering different syndromes as Down [14] or severe Autism [34] that would make them score
low in Stern’s intelligence quotient test and that, however, are phenomenally conscious. Once again, we find another counter-example to the
Russell’s analogy dealing computational intelligence. Moreover, autism
is a curious case, as it is highly correlated with special abilities such as
the one of Daniel Tammett [59] that is able to memorize and say the
first 22514 digits of number pi in only 5 hours, or speak 11 languages.
According to intelligence quotient tests the abilities of Tammett would
not be quantified, hence being the tests a lower bound on intelligence
and being intelligence a variable that is not correlated with phenomenal consciousness, as other social abilities are hard for ASD people like
Tammett.
The extreme case would be the one dealing with a comatose person. Concretely, there is empirical evidence coming from neuroscience that shows
how comatose people have neural correlates of consciousness, what has
been called as islands of consciousness [1], conscious states that are neither shaped by sensory input nor able to be expressed by motor output.
Technically, people suffering a comatose state would be phenomenally
conscious but unable to perform any kind of movement nor reaction to
any external stimuli. Consequently, the score that they would perform in
any kind of test similar to the one of Stern’s intelligence quotient would
be 0. Nevertheless, the neuroscience community shows evidence to support the claim that they are phenomenally conscious or just aware but
unable to report any stimuli.
4.4
Consciousness in the animal kingdom
Neurobiology gives us evidence that animal brains share features with
our brains dealing with the neural correlates of consciousness [23]. Concretely, this evidence does not only reduce to the most similar animals
15
16
Eduardo C. Garrido Merchán, Sara Lumbreras
to us, like primates, but these neural correlates are found, up to some
degree, in other mammals, birds, and at least some cephalopod molluscs,
like octopuses, squid or cuttlefish [3].
Following Rusell analogy, concerning intelligence, we can say that the
neuroscience community gives evidence to suggest that animals, young
infants and adult humans possess a biologically determined, domainspecific representation of number and of elementary arithmetic operations [10]. However, we have seen that computational intelligence seems
to be independent with phenomenal consciousness. Nonetheless, phenomenal consciousness is a prerequisite to experiment the qualia of subjective phenomena such as being aware of feelings. Precisely, concerning
the qualia of feelings, neurobiological evidence shows how animal brains
perform similarly to us dealing with the elaboration of the primary emotions, which include the foraging-expectancy system, the anger-rage system, the fear-anxiety system, the separation-distress-panic system and
social-play circuitry [45]. Consequently, it seems very plausible that, although animals would score very badly in an Stern’s like intelligence
quotient test, they may have phenomenal consciousness, as their neural correlates of consciousness, i.e., their emotion processing, seem to be
similar to ours.
Ironically, as we have said, Stern’s intelligence quotient is culturally biased, but according to our proposed general intelligence metric, the size
of the computational set of problems is infinite. Hence, if an animal has,
for example, better memory that us, in average, we could argument that
a lower bound intelligence quotient biased to memory would make them
score better score than us. Dealing with different aspects of intelligence,
animals score better than us, in average. Some examples are birds in spatial memory [46], dogs in smell [26], ants in visual [22] and even bats in
abities that are unique to them [43] and that human beings would score
a zero. Consequently, following Russell’s analogy, the likelihood of them
having phenomenal consciousness would be greater than us. However, although it is very probable that they are phenomenally conscious due to
neurobiological evidence based on the neural correlates of consciousness
[3], it is not as evident as in the case of human beings. Hence, again,
Russell’s analogy fails in this case.
5 Phenomenal consciousness is independent of
computational intelligence
We will now formalize Russell’s analogy from a Bayesian point of view.
The latent, unobservable measure would be whether an entity possess
phenomenal consciousness or not. We assume here, as we isolate the
observer of phenomenal consciousness, in the sense of the defined term
awareness by Dehaene, from all the different features of consciousness
such as access consciousness, that phenomenal consciousness is a dichotomous variable C. Recall that phenomenal consciousness is not being
aware of more or less phenomena, as the complexity of the integrated information theory qualia space φ can model. Phenomenal consciousness,
from our definition, is being an observer of the qualia space generated
On the independence between consciousness and intelligence
by a living being. Consequently, you can only be aware of the qualia
space, an observer of the qualia space, or not. Hence, following our assumptions that phenomenal consciousness is not an epiphenomenon or
intrinsically related to the qualia space but a property of beings to be
aware of their qualia space, we define phenomenal consciousness as a
dichotomous variable of perceive or not the qualia space that a being
generates.
Let I be the computational intelligence of an entity as have defined it
in previous sections, denoted by the continuous numerical variable I. A
subject S may possess or not phenomenal consciousness, but with the
current state of science, we are only able to determine whether it is conscious by looking at the neural correlates of consciousness. If the system
does not have a biological brain nor nervous system, science is unable to
provide any clue about the consciousness of S. Then p(C|S) would be the
conditional probability that a subject S has phenomenal consciousness
such that p(C = 1|S) + P (C = 0|S) = 1 and p(I|S) is the conditional
probability of the computational intelligence of the subject. Concretely,
an intelligence quotient test would not determine the intelligence of S as
a point estimation but the only thing that it would do is to reduce the
entropy of the p(I|S) distribution.
In order to carry out this analysis we use some concepts from probability
theory that we now review. The first one is the amount of information
needed to encode a probability distribution, also known as entropy. The
entropy H(·) can be viewed as a measure of information for a probability distribution P associated with a random variable X. That is, its
self-information. It can be used as a measure of uncertainty of a random variable X. When the random variable is continuous, we refer to
the entropy as differential entropy. The entropy of an uni-dimensional
continuous random variable X with a probability density function p(x),
or differential entropy H[p(X)], is given by the following expression:
Z
H[p(X)] = −
p(x) log p(x)dx .
(4)
S
Where S is the support of the random variable X, that is, the space
where p(x) is defined. The entropy H(·) is useful to model the following
relation: If we have a random variable X with high entropy H(·), that
means that we have low information about the values that it may take.
On the other hand, if we consider a random variable X with low entropy
H(·), it is a sign that we have high information about the potential values that the variable X can take. In other words, higher knowledge of a
random variable implies lower entropy and viceversa. Another interesting concept regarding information theory, that we use in this work, is the
mutual information I(X; Y ) of two random variables X and Y . Mutual
information is defined as the amount of information that a random variable X contains about another random variable Y . It is the reduction in
the uncertainty of one random variable X due to the knowledge of the
other. Mutual information is a symmetric function. Consider two random variables X and Y with a joint probability density function p(x, y)
and marginal probability density functions p(x) and p(y). The mutual
information I(X; Y ) is the relative entropy between the joint distribution
17
18
Eduardo C. Garrido Merchán, Sara Lumbreras
p(x, y) and the marginal distributions p(x) and p(y):
I(X; Y ) =
XX
x
y
p(x, y) log
p(x, y)
.
p(x)p(y)
(5)
Concretely, we define as information gain the amount of information that
we gain for a certain random variable knowing the value of the other one.
According to Russell, we know that human beings are likely to be are
conscious, so we denote the being a human being as the dichotomous
random variable B. Then, p(C = 1|B = 1) = 1 independently on the
degree on intelligence. More technically, the information gain of the intelligence degree I over consciousness given that the entity is a human
being is 0.
IG(C, I|B = 1) = 0.
(6)
In other words, the entropy H(·) of the conditional probability distribution of consciousness being also conditioned to the degree of computational intelligence of subject S, which is also a random variable as we
do not have direct access to it, is the same one. Then, in our case we
can illustrate that the entropy on the consciousness random variable for
humans H(C|B = 1) is equal to the conditional entropy on the consciousness for a certain computational intelligence level I.
H(C|B = 1, I) = H(C|B = 1).
(7)
As p(C = 1|B = 1) = 1, there is not need to show that H(I|B = 1, C =
1) = H(I|B = 1), as it is obvious. Hence, we have formally shown how,
for the case of human beings, the computational intelligence degree is independent from the phenomenal consciousness variable. However, until
now we have only performed the analysis of computational intelligence
and phenomenal consciousness in the case that the subject is a human
being. Nevertheless, important implications of this analysis need to be
taken into account. For example, we now know that a low measure of
computational intelligence according to the intelligent quotient of Stern
does not condition the subject from being conscious. Let p(I) << denote
a probability distribution over the computational intelligence for a subject S having its density concentrated over a low value. Concretely, we
know that p(C = 1|p(I) <<) = 1. We put here p(I) and not I = k being
k a real number as we have denote that current measures of intelligence
are a noisy lower bound over the true value of intelligence of subject
S, that is a random variable. Importantly, we now know with complete
certainty that, in the case of disabilities or certain comatose states, a
subject has phenomenal consciousness.
Next, we analyze and compare the probability distributions p(C|I) and
p(C). Science gives us evidence that if the entity shares features with
the human being biologically talking, concretely the neural correlates of
consciousness, the subject may be conscious. We denote with N ∈ [0, 1]
a continuous numerical variable that represents the degree of biological
similarity of the brain of the subject with the brain of the human being.
Concretely, current AI systems, denoted with the dichotomous variable
On the independence between consciousness and intelligence
A, have A = 0, as deep neural networks or meta-learning methodologies
are just sequences of instructions sequentially computable by Turing machines as we have shown before, although the name may be misleading.
We found a real analogy with P (C) and P (C|N ). Concretely, these variables are, according to evidence found in neurobiology, linearly correlated, i.e., r(C, N ) ≈ 1 being r the correlation coefficient. However, a
bird, elephant, dolphin, monkey or cephalopod, for example, may score
a low computational value p(I) <<. However, and again, we find that
conditioning the variable p(I) << to the conditional distribution P (C|N )
does not change the entropy of the distribution:
H(C|N, p(I) <<) = H(C|N ).
(8)
Finally, we use the example of a meta-learning system to show how
the degree of computational intelligence is not correlated to phenomenal consciousness. Concretely, a meta-learning system with N = 0 has
the biggest computational intelligence known as it is able to solve a potentially infinite set of computational problems that humans or animals
are not able to solve up-to-date as we have seen in previous sections. We
denote that such a system has a computational intelligence probability
distribution p(I) >>. However, we know that: p(C = 0|N = 0) = 1, independently on its degree of computational intelligence. In other words,
if we condition the probability to p(I) >>, for all the set of artificial
intelligence systems, we have that p(C = 0|N = 0) = p(C = 0|N =
0, p(I) >>) = 1. Hence, the degree of intelligence does not generate
phenomenal consciousness as an epiphenomenon or by emergence. Concretely, it is the anatomy of the biological brain, or even less probably
the nervous system or body, where supposedly we find, at least, neural correlates of consciousness. Given all the information and evidence
that we have provided, we could formalize that the information gain of
the computational intelligence random variable given that we know the
phenomenal consciousness variable if we marginalize the kind of entity
that may have phenomenal consciousness is 0, i.e., they are independent
random variables independently on the intelligence degree.
IG(C, I) = 0.
(9)
From a Bayesian point of view, this information could be formalized as
follows. Concerning artificial intelligence systems, let p(C = 1|I, N = 0)
be an a priori distribution representing the probability of the system
being conscious, our previous beliefs coming from the Russell’s analogy.
Following this analogy, this probability was high as the system is intelligent and the complementary probability, p(C = 0|I, N = 0), is low. We
have provided empirical and theoretical evidence showing that this is not
true that we formalize in the likelihood p(E|C = 1, I, N = 0), being E
the evidence that we have illustrated in previous sections. Let p(E) be
the marginal likelihood representing the probability of our evidence being
true, which is high due to the fact that it comes from highly cited papers
of various research communities like neurobiology, psychiatry or philosophy of mind. Lastly, let p(C = 1/E, I, N = 0) be our posterior beliefs
of the hypothesis that artificial intelligence systems are conscious. As
19
20
Eduardo C. Garrido Merchán, Sara Lumbreras
the probability rectifier coefficient is very low, that is p(E|C = 1, I, N =
0)/p(E), despite having an a priori belief supporting the hypothesis of
conscious artificial intelligence systems, now the posterior belief clearly
shows that p(C = 0/E, I, N = 0) > p(C = 1/E, I, N = 0) significantly.
Mainly because computational intelligence is independent from phenomenal consciousness.
6
Repercusions in society
Given that deep learning and related models, which are a simplification
of reality, do not have phenomenal consciousness, that is, they are not
aware of themselves, they do not have an identity. Consequently, as they
do not have an identity, they can not have the intention nor perceive the
idea of inventing nothing, as they are not aware of anything. As a result,
a machine can not have the intellectual property of an invention, since
it is only the tool of the inventor, as aware of the invention as a pencil
or wrench can be. Hence, we can not attribute an invention or discovery
to them, as they are not aware of the action of inventing nor discovering. For example, suppose that an economist discovers, using machine
learning models or econometrics, that a certain consuming behaviour in
the population is correlated with their income. This discovery cannot
be attributed to the model, but to the scientist that has formulated the
research question and formulated the necessary methodology to obtain
significant empirical evidence to support its claim. Similarly, if an architect designs a house and draws it in a paper, we can not attribute the
creation of the house to the pencil but to the architect. Consequently, if
a deep learning system discovers the solution to the protein folding problem [28] its discovery can not be attributed to the deep learning system
but to the scientists team that configured the deep learning system and
gathered the data used to fit it.
Hence, we can not attribute a patent to an artificial system, independently on its degree of computational intelligence. Basically because a
prerequisite for an entity to have a patent would be that the entity is
aware of itself. And, as we have seen in previous sections, artificial intelligence current systems are not aware of itself. Consequently, patents
would belong to the team of scientists that build the model or configured
the artificial intelligence system.
Artificial intelligence models are a simplification of reality. ”All models
are wrong, but some of them are useful” [4]. Concretely, they are useful
for an aware human being to help him to decide what to do in a complex
decision such as a clinical decision, a business problem or discriminating
which physical hypothesis is true within a set of plausible ones. We believe that a decision that is potentially harmful for an aware entity, being
human or animal, must be at the end executed by an aware entity that is
able to comprehend the decision that is being taken. That is, the entity
is required to have phenomenal consciousness and a computational intelligence level enough to comprehend the reasoning of the decision. The
only entity able to be the responsible for such a decision is the human
being. However, the human being can use as a tool a computationally
On the independence between consciousness and intelligence
more intelligent system that it for advice. Concretely, explainable machine learning and artificial intelligence [12] are models and algorithms
that are able to justify its decision using a logic that is understandable
for humans and would be the best methodology for this scenario.
Finally, we also consider than in an ethical situation where the integrity
of entities is in danger, and some of them can survive and others not,
an artificial system can never be priorized over an aware being. Our axiom for the decision is that we should always priorize the survival of the
entity that is aware of itself, since phenomenal consciousness cannot be
replicated artificially but any kind of artificial device can be replicated.
In other words, the value of phenomenal consciousness is much higher
than any artificial system. As a corollary, for example, if an artificial
intelligence system can be damaged versus an animal or human being
damaged, the artificial intelligence system would necessarily be, independently of its complexity, the one damaged. Most critically, our main
conclusion is that the priority would be to save the aware entity, and as
the artificial intelligence system is not aware of itself, the integrity of the
aware entity must be prioritized independently on its computational intelligence degree because its value is higher than any artificial system as,
independently on its cost, we can not replicate the exact aware system
but we can replicate any artificial machine created by humans. This is a
corollary of our assumed axiom, that is priorizing potentially aware entities to non-conscious entities and that conscious beings are not replicable
by humans.
7
Conclusions and further work
Phenomenal consciousness is defined as the awareness of an individual to
internal and external estimuli, of the information processed by the brain,
in the form of qualia. In this work, we have analyzed and show how the
Russell’s analogy of consciousness, that basically states that awareness
and intelligence are correlated with high probability, is a fallacy at least
for computational intelligence. In order to do so, first, we defined what
is phenomenal consciousness and give an objective measure of computational intelligence. Then, we provided a set of counter-arguments to
Russell’s analogy with evidences coming from neurobiology, psychiatry
or philosophy of mind, where we can see how phenomenal consciousness
and computational intelligence are independent. Consequently, we include a formalism with probability and information theory to represent
this independence. Finally, we conclude with the social impacts of this
fact, mainly that aware beings must be prioritized from non-conscious
machines independently of the degree of intelligence, that as machines
do not have identity they can not possess patents and that they should
not be responsible of decisions that could harm an aware being, mainly
because as they do are not aware they can not be responsible of a decision.
21
22
Eduardo C. Garrido Merchán, Sara Lumbreras
References
1. Bayne, T., Seth, A. K., and Massimini, M. Are there islands of
awareness? Trends in Neurosciences 43, 1 (2020), 6–16.
2. Bechtel, W. Connectionism and the philosophy of mind: an
overview. Connectionism and the Philosophy of Mind (1991), 30–
59.
3. Birch, J., Schnell, A. K., and Clayton, N. S. Dimensions of
animal consciousness. Trends in cognitive sciences (2020).
4. Box, G. All models are wrong, but some are useful. Robustness in
Statistics 202, 1979 (1979), 549.
5. Chalmers, D. J. Philosophy of mind: Classical and contemporary
readings.
6. Chandrasekaran, B., Josephson, J. R., and Benjamins, V. R.
What are ontologies, and why do we need them? IEEE Intelligent
Systems and their applications 14, 1 (1999), 20–26.
7. Chollet, F. On the measure of intelligence. arXiv preprint
arXiv:1911.01547 (2019).
8. DeGroot, M. H. Probability and statistics. Pearson, 2012.
9. Dehaene, S. Consciousness and the brain: Deciphering how the
brain codes our thoughts. Penguin, 2014.
10. Dehaene, S., Dehaene-Lambertz, G., and Cohen, L. Abstract
representations of numbers in the animal and human brain. Trends
in neurosciences 21, 8 (1998), 355–361.
11. Deutsch, D. Quantum theory, the church–turing principle and the
universal quantum computer. Proceedings of the Royal Society of
London. A. Mathematical and Physical Sciences 400, 1818 (1985),
97–117.
12. Došilović, F. K., Brčić, M., and Hlupić, N. Explainable artificial intelligence: A survey. In 2018 41st International convention on
information and communication technology, electronics and microelectronics (MIPRO) (2018), IEEE, pp. 0210–0215.
13. Elkins, K., and Chun, J. Can gpt-3 pass a writer’s turing test?
Journal of Cultural Analytics 5, 2 (2020), 17212.
14. Epstein, C. J. Down syndrome. In Abnormal States of Brain and
Mind. Springer, 1989, pp. 43–44.
15. Ferrucci, D. A. Introduction to “this is watson”. IBM Journal of
Research and Development 56, 3.4 (2012), 1–1.
16. Floridi, L., and Chiriatti, M. Gpt-3: Its nature, scope, limits,
and consequences. Minds and Machines 30, 4 (2020), 681–694.
17. Gamez, D. Human and machine consciousness. Open Book Publishers, 2018.
18. Garrido-Mercháin, E. C., Molina, M., and Mendoza-Soto,
F. M. A global workspace model implementation and its relations
with philosophy of mind. Journal of Artificial Intelligence and Consciousness 9, 01 (2022), 1–28.
19. Garrido-Merchán, E. C., and Blanco, C. Do artificial intelligence systems understand? arXiv e-prints (2022), arXiv–2207.
20. Goertzel, B., and Pennachin, C. Artificial general intelligence,
vol. 2. Springer, 2007.
On the independence between consciousness and intelligence
21. Gottfredson, L. S. Mainstream science on intelligence: An editorial with 52 signatories, history, and bibliography, 1997.
22. Graham, P., and Philippides, A. Vision for navigation: what
can we learn from ants? Arthropod Structure & Development 46, 5
(2017), 718–722.
23. Griffin, D. R., and Speck, G. B. New evidence of animal consciousness. Animal cognition 7, 1 (2004), 5–18.
24. Heil, J. Multiple realizability. American Philosophical Quarterly
36, 3 (1999), 189–208.
25. Hopcroft, J. E. Turing machines. Scientific American 250, 5
(1984), 86–E9.
26. Horowitz, A. Inside of a dog: What dogs see, smell, and know.
Simon and Schuster, 2010.
27. Joye, S. R. The Pribram-Bohm holoflux theory of consciousness:
An integral interpretation of the theories of Karl Pribram, David
Bohm, and Pierre Teilhard de Chardin. California Institute of Integral Studies, 2016.
28. Jumper, J., Evans, R., Pritzel, A., Green, T., Figurnov, M.,
Ronneberger, O., Tunyasuvunakool, K., Bates, R., Žı́dek,
A., Potapenko, A., et al. Highly accurate protein structure prediction with alphafold. Nature 596, 7873 (2021), 583–589.
29. Kagan, L., and Kagan, S. Multiple intelligences. Kagan cooperative learning, 2000.
30. LeCun, Y., Bengio, Y., and Hinton, G. Deep learning. nature
521, 7553 (2015), 436–444.
31. Legg, S., and Hutter, M. Universal intelligence: A definition of
machine intelligence. Minds and machines 17, 4 (2007), 391–444.
32. Legg, S., and Veness, J. An approximation of the universal intelligence measure. In Algorithmic Probability and Friends. Bayesian
Prediction and Artificial Intelligence. Springer, 2013, pp. 236–249.
33. Liu, C. The three-body problem, vol. 1. Macmillan, 2014.
34. Lord, C., Cook, E. H., Leventhal, B. L., and Amaral, D. G.
Autism spectrum disorders. Neuron 28, 2 (2000), 355–363.
35. Lucas, S. The origins of the halting problem. Journal of Logical
and Algebraic Methods in Programming 121 (2021), 100687.
36. Ludlow, P., Nagasawa, Y., and Stoljar, D. There’s something
about Mary: essays on phenomenal consciousness and Frank Jackson’s knowledge argument. MIT press, 2004.
37. Matilasevich, Iuri, V., Matijasevič, J. V., Matiâsevič, Û. V.,
Matiyasevich, Y. V., Matiyasevich, Y. V., Garey, M. R., and
Meyer, A. Hilbert’s tenth problem. MIT press, 1993.
38. McCarthy, J. What is artificial intelligence.
39. McGrath, T., Kapishnikov, A., Tomašev, N., Pearce, A.,
Hassabis, D., Kim, B., Paquet, U., and Kramnik, V. Acquisition
of chess knowledge in alphazero. arXiv preprint arXiv:2111.09259
(2021).
40. Merchán, E. C. G., and Molina, M. A machine consciousness
architecture based on deep learning and gaussian processes. In International Conference on Hybrid Artificial Intelligence Systems (2020),
Springer, pp. 350–361.
23
24
Eduardo C. Garrido Merchán, Sara Lumbreras
41. Morgado-Bernal, I. Is consciousness an epiphenomenon? In
Mario Bunge: A Centenary Festschrift. Springer, 2019, pp. 377–385.
42. Murphy, K. P. Machine learning: a probabilistic perspective. MIT
press, 2012.
43. Nagel, T. What is it like to be a bat. Readings in philosophy of
psychology 1 (1974), 159–168.
44. Nida-Rümelin, M., and O Conaill, D. Qualia: The knowledge
argument.
45. Panksepp, J. The neurobiology of emotions: Of animal brains and
human feelings.
46. Payne, H., Lynch, G., and Aronov, D. Neural representations of
space in the hippocampus of a food-caching bird. Science 373, 6552
(2021), 343–348.
47. Penrose, R. The emperor’s new mind. RSA Journal 139, 5420
(1991), 506–514.
48. Penrose, R. Shadows of the Mind, vol. 4. Oxford University Press
Oxford, 1994.
49. Ravenscroft, I. Philosophy of mind: A beginner’s guide. Oxford
University Press, USA, 2005.
50. Ren, J., Rajbhandari, S., Aminabadi, R. Y., Ruwase, O., Yang,
S., Zhang, M., Li, D., and He, Y. Zero-offload: Democratizing billion-scale model training. arXiv preprint arXiv:2101.06840
(2021).
51. Russell, B. Human knowledge: its scope and limits. Essays on
other minds (1948), 3–8.
52. Russell, S., and Norvig, P. Artificial intelligence: a modern approach.
53. Salovey, P., and Mayer, J. D. Emotional intelligence. Imagination, cognition and personality 9, 3 (1990), 185–211.
54. Searle, J. Reductionism and the irreducibility of consciousness. Emergence: Contemporary readings in philosophy and science
(2008), 69–80.
55. Searle, J. Chinese room argument. Scholarpedia 4, 8 (2009), 3100.
56. Searle, J. R. The mystery of consciousness. The New York Review
(1995).
57. Stern, W. The psychological methods of testing intelligence. No. 13.
Warwick & York, 1914.
58. Sutton, R. S., and Barto, A. G. Reinforcement learning: An
introduction. MIT press, 2018.
59. Tammet, D. Born on a blue day: Inside the extraordinary mind of
an autistic savant. Simon and Schuster, 2007.
60. Timmermans, B., and Cleeremans, A. How can we measure
awareness? an overview of current methods, 2015.
61. Tononi, G. Consciousness as integrated information: a provisional
manifesto. The Biological Bulletin 215, 3 (2008), 216–242.
62. Torrey, L., and Shavlik, J. Transfer learning. In Handbook of
research on machine learning applications and trends: algorithms,
methods, and techniques. IGI global, 2010, pp. 242–264.
63. Vanschoren, J. Meta-learning. In Automated Machine Learning.
Springer, Cham, 2019, pp. 35–61.
On the independence between consciousness and intelligence
25
64. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones,
L., Gomez, A. N., Kaiser, L., and Polosukhin, I. Attention is
all you need. In Advances in neural information processing systems
(2017), pp. 5998–6008.
65. Vsauce. The stilwell brain. https://www.youtube.com/watch?v=rA5qnZUXcqo,
2018.
66. Wang, F.-Y., Zhang, J. J., Zheng, X., Wang, X., Yuan, Y.,
Dai, X., Zhang, J., and Yang, L. Where does alphago go: From
church-turing thesis to alphago thesis and beyond. IEEE/CAA Journal of Automatica Sinica 3, 2 (2016), 113–120.
67. Wang, X., Oxholm, G., Zhang, D., and Wang, Y.-F. Multimodal transfer: A hierarchical deep convolutional neural network for
fast artistic style transfer. In Proceedings of the IEEE Conference on
Computer Vision and Pattern Recognition (2017), pp. 5239–5247.
68. Wang, Y. On abstract intelligence: Toward a unifying theory of natural, artificial, machinable, and computational intelligence. International Journal of Software Science and Computational Intelligence
(IJSSCI) 1, 1 (2009), 1–17.
69. Wheaton, K. J., and Beerbower, M. T. Towards a new definition of intelligence. Stan. L. & Pol’y Rev. 17 (2006), 319.
This figure "eduardo.png" is available in "png" format from:
http://arxiv.org/ps/2208.02187v1
This figure "logo_unirv.png" is available in "png" format from:
http://arxiv.org/ps/2208.02187v1 |
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
1
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
Article
The Nature of Quantum Reality: What the Phenomena at the Heart
of Quantum Theory Reveal About the Nature of Reality (Part I)
Steven E. Kaufman*
ABSTRACT
What quantum theory has revealed about the nature of reality has remained hidden in plain sight
for almost one-hundred years because what quantum theory has revealed about the nature of
reality cannot be comprehended in the context of the materialist model and conception of reality
in which science presently operates, which materialist model places physical reality at the center
of reality and Consciousness at the periphery, as a secondary or derivative reality. What this
work will demonstrate, by explaining the heretofore inexplicable basis of the phenomena that lie
at the heart of quantum theory, is that it is Consciousness rather than physical reality that lies at
the center of reality, and that it is physical reality rather than Consciousness that is a secondary
or derivative reality. Specifically, wave-particle duality, quantum uncertainty, quantum nonlocality, the probabilistic nature of the wavefunction, and the collapse of the wavefunction, will
all be shown to be phenomena that have as their basis the way in which the fundamental Reality
of Consciousness, through relation to Itself, creates what it apprehends as physical reality.
One of the most important things the phenomena that lie at the heart of quantum theory will be
shown to reveal about the nature of reality is that the nature of physical reality is like that of a
reflection, and like a reflection, physical reality is able to obscure from view what is actually
there, as long as it is mistaken for what is actually there. Thus, in revealing the reflection-like
nature of physical reality, the phenomena that lie at the heart of quantum theory indirectly reveal
that what is actually there, underlying the reflection that is physical reality, is the non-physical,
non-experiential Reality of Consciousness that is, through relation to Itself, both creating and
apprehending experiential reality in general and physical reality in particular. Ultimately,
understanding the reflection-like nature of physical reality should make it possible for
Individuals to understand that what actually Exists directly where they are, where their physical
bodies appear to be, is not different in Nature than what actually Exists everywhere else as well,
where the rest of physical reality appears to be, thereby disabusing them of the notion that what
they are is a physical reality, while at the same time revealing to them their true Nature as
Consciousness, which, through relation to that which is also Consciousness, creates what they, as
Individual points of Consciousness, apprehend as experiential reality in general and physical
reality in particular.
Part I of this series of three articles includes: Background; Introduction; and 1. Building a new
model of reality.
Key Words: Nature, quantum reality, quantum physics, Consciousness, materialist model.
*Correspondence: Steven E. Kaufman, Indep. Researcher. http://www.unifiedreality.com E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
2
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
"There was a time when the newspapers said that only twelve men understood the theory of
relativity. I do not believe there ever was such a time. There might have been a time when only
one man did, because he was the only guy who caught on, before he wrote his paper. But after
people read the paper a lot of people understood the theory of relativity in some way or other,
certainly more than twelve. On the other hand, I think I can safely say that nobody understands
quantum mechanics." - Richard P. Feynman, 1964, MIT1
Background
There is a pattern in the progression of humanity's understanding of the Universe in which we
reside. That pattern is that each time humanity takes a large step forward in understanding the
nature of the Universe, which large step is always accomplished by throwing off the shackles of
the present conception of reality and adopting a new conception of reality, we think that we have
it all figured out, and all that remains is to fill in the details.
This was certainly the case with regard to the philosophy of materialism, the essence of which is
depicted in figure 1, which at one time held the position that if one knew all of the physical laws
that governed the interactions between physical objects, as well as the variable characteristics of
all the physical objects, such as mass, position and momentum, then it would be theoretically
possible to predict with complete accuracy all future events from that point onward, like
calculating an almost infinitely complex pool shot.
Materialism
physical
laws
physical
laws
etc.
physical
laws
physical
laws
higher order
physical reality
even higher
order physical
reality
fundamental
physical reality
etc.
macroscopic
physical reality
and assumed
emergence of
Sentience or
Consciousuness
that apprehends
physical reality
Figure 1 The philosophy of materialism has as its basis the idea that physical reality is essentially a
mindless or non-sentient mechanism composed of some sort of fundamental physical building block that
interacts with and comes together with other fundamental physical building blocks according to a set of
physical laws to form higher order physical building blocks, which higher order physical building blocks
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
3
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
then come together to form still higher order physical building blocks, and so on, with the ultimate
outcome of this progression thought to result in both the construction of what we apprehend as
macroscopic material reality, as well as the creation and emergence at some point of the Sentience or nonmaterial Consciousness that apprehends material reality.
However, for physicists working to determine the structure of the atom, this deterministic aspect
of the materialist conception of reality was shattered nearly one-hundred years ago with the
discovery of quantum uncertainty, which imposes a limit upon what it is possible to know
regarding the variable characteristics of a physical object, e.g., the more one knows about the
position of an object the less one can know about that same objects' momentum, thereby
eliminating even the theoretical possibility of predicting with complete accuracy the future
interactions of material objects. Instead, what they found at these very small levels of physical
reality, i.e., at the level of quantum reality, could only be accurately expressed by what is termed
the wavefunction, which is a mathematical expression that expresses the physical state of
quantum realities in terms of probability, which is to say, in terms of the probability of observing
a particular quantum reality to be in this or that physical state if it is observed. Thus, as physicists
dug deep into physical reality, instead of finding very tiny physical realities, what they found
instead were realities that were decidedly non-physical in their behavior, as shown in figure 2.
deconstruction and observation of physical reality
wave-particle duality
becomes unavoidable
wave-particle duality re mains hidden
quantum uncertainty
becomes unavoidable
quantum uncertainty rema ins hidden
????
wavefunction
????
wavefunction
????
wavefunction
molecu le
????
wavefunction
atom
electron
indeterminate quantum
realities
seemingly determinate physical rea lit ies
Figure 2 Scientists working to uncover the interior structure of the atom, i.e., working to determine the
nature of the building blocks of physical reality, found to their surprise and great dismay that electrons did
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
4
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
not behave in the way that they were used to physical realities behaving, in as much as they could be
observed to behave as either a wave or as a particle in any one moment, but never as both at once. The
dual and yet mutually exclusive nature of reality uncovered at this level introduced uncertainty, such that
the determination of one physical characteristic made impossible the determination of the complementary
physical characteristic, leaving scientists to express what they found at these very small levels of physical
reality not as physical realties with definite physical characteristics, but rather as quantum realities with
indeterminate physical characteristics expressed as a mathematical statement of probability referred to as
the wavefunction.
Another aspect of the materialist philosophy that was undercut by scientists probing into the
quantum level of reality was the discovery, prior to the discovery of quantum uncertainty, that
light could be observed to behave as either a wave or as a particle, depending upon the
experimental setup used to observe it. Soon thereafter it was also determined that other larger
quantum realities, such as electrons, displayed the same wave-particle duality. The fact that
quantum realities could, in different moments, be observed to be in two completely different and
mutually exclusive states made it no longer possible to assume that the Observer played no part
in shaping the character of what was observed as a physical reality, at least at the quantum level.
That is, the phenomenon of wave-particle duality introduced the notion that the Observer, i.e.,
the Sentience or Consciousness that was apprehending the physical reality, rather than just
passively apprehending what was already there as a particular physical reality, instead played
some active role in shaping what was being apprehended as a particular physical reality.
And so, even though some of the earliest discoveries made regarding the nature of physical
reality at very small scales undercut two of the basic premises of materialism, i.e., that there is
some fundamental determinate physical reality or building block out of which the rest of
physical-material reality is constructed, and that what we apprehend as physical reality is already
there as it is apprehended to exist regardless of whether it is being apprehended or not, the
philosophy of materialism did not die nearly one-hundred years ago with the discoveries of
wave-particle duality and quantum uncertainty, although it should have. Rather, it was poisoned
and has been dying a slow death ever since, while still continuing to struggle to remain the
dominant philosophy underlying science's and therefore humanity's conception of reality, even
though it is science itself, in the form of quantum physics, that has administered the poison that
has made its demise inevitable.
One of the reasons the materialist philosophy and conception of reality has been so slow to go
away, even though its situation is indeed terminal, is because there has been no acceptable or
satisfactory alternate conception of reality with which to replace it. To some degree, science's
situation with materialism is like being stuck in an unhappy relationship, in as much as people
tend not to leave their partner, no matter how badly things are going, until they find someone
else to replace them. And so, even though materialism is not really working for humanity or
science any more as a philosophy that can answer the big questions the Universe poses, humanity
and science stick with it because they have yet to find a suitable replacement. That materialism is
no longer working for humanity or science as a philosophy that can answer the big questions the
Universe poses is evidenced by the fact that nearly one-hundred years after the discovery of
wave-particle duality, quantum uncertainty, and the wavefunction, what quantum theory says
about the nature of reality remains as much of a mystery to science and humanity now as was the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
5
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
case when these phenomena were first discovered, owing to science's ongoing determination to
cram these phenomena into a materialist conception of reality into which they can never be fit.
The source of the difficulty in finding a replacement for the philosophy of materialism that is
consistent with the findings of quantum physics regarding the behavior of physical reality at very
small scales is that there is a significant difference between the pending advancement in human
understanding regarding the nature of reality that has been made possible by the discoveries of
quantum physics and prior advancements in human understanding regarding the nature of reality.
And that significant difference is that those prior advancements took place within the conceptual
context of an intact physical reality and were essentially modifications of some physical or
material model of reality, as shown in figure 3, whereas the pending advancement in human
understanding regarding the nature of reality, which has been made possible by the discoveries
of quantum physics, does not take place in the context of an intact physical reality and so cannot
be expressed through a modification of some physical or material model of reality, but requires
instead the annihilation of our present conception of physical reality, and specifically requires
that we let go of our conception of physical reality as being what is actually there where it
appears to be.
broader
perspective
Ea rth
Ea rth and other celestial bodies
Sun, stars, rest of Universe
Ea rth
Ea rth
broader
perspective
Ptolemaic system
mistaken conception of reality
Sun
Copernic an system
more accurate conception of reality
Figure 3 The idea that the Earth is round rather than flat, and that the Earth orbits the Sun rather than the
other way around, are different ways of viewing or picturing a physical object or set of physical objects,
respectively. Thus, these prior advancements in human understanding regarding the nature of reality, i.e.,
the shape of the Earth and the relation of the Earth to other celestial bodies, while involving some
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
6
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
rearrangement of physical reality, do not bring into question the assumed nature of physical reality as
being what is actually there where it appears to be.
Our present situation with regard to our idea or conception of physical reality as being what is
actually there where it appears to be, i.e., our idea that what is actually there where we apprehend
a physical reality is actually a physical reality, which idea or conception is at the heart of
materialism, is directly analogous to the historical situation wherein humanity thought that the
Earth was at the center of the Universe, with the rest of the Universe revolving around the Earth.
That is, just as a portion of humanity at one time placed the Earth at the center of the Universe,
with everything else revolving around it, because from the common perspective that is how it
appeared or seemed to be, materialism is a philosophy that places physical reality at the center of
reality, with all other realities orbiting around it or extending from it, because from our common
perspective that is how it appears or seems to be. And just as the findings of Copernicus brought
humanity a new perspective from which to view the Universe, thereby requiring a new model of
the Universe to fit that new perspective, so to do the findings of quantum physics bring to
humanity a new perspective from which to view physical reality, thereby requiring a new model
of reality to fit that new perspective, as shown in general terms in figure 4.
everything else, i.e., e motional
expe rience, mental e xperience, and
Consciousness
physical
reality
expe rientia l reality, i.e.,
emotional, mental, and physical e xperience
broader
perspective
of quantum
physics
Materi alism
inaccurate conception of reality
ExistenceConsciousness,
i.e., Reality
Ide alism
more accurate conception of reality
Figure 4 Just as at one time the common perspective left at least a portion of humanity with the mistaken
idea that the Earth was at the center of the Universe, with other celestial bodies occupying a peripheral
position relative to the Earth, our common perspective leaves us with the mistaken impression that
physical reality is at the center of reality, with other realities revolving around physical reality, i.e.,
occupying a secondary or peripheral position relative to physical reality, as shown in the drawing on the
left. However, quantum physics has brought to humanity a new perspective from which to view reality,
one that requires a reorganization of how we see the different realities in relation to each other if
humanity is to ever understand what it is that quantum theory says about the nature of reality.
Specifically, understanding what quantum theory says about the nature of reality requires a reorganization
with respect to how we view the relation between physical reality and the non-physical Reality of
Consciousness, in as much as the nature of quantum reality can only be described and understood in the
context of a model and description of reality that places the non-physical Reality of Consciousness at the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
7
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
center of reality, with the rest of reality, i.e., experiential reality, including physical reality, occupying a
secondary or peripheral position relative to that central Reality, as shown in the drawing on the right.
Owing to the new perspective upon physical reality afforded by the findings of quantum
physics, any new model of reality that incorporates the perspective of quantum physics, as any
model must for it to be considered to have any validity whatsoever, cannot be a model of reality
that simply represents some modification of the still accepted and yet already discredited
materialist model, and so cannot be a model that simply represents some rearrangement of the
chairs on the deck of the sinking ship that is the philosophy of materialism, i.e., it cannot be a
model that assumes both that physical reality is what is actually there where it appears to be and
that physical reality is at the center of reality, simply because that is how it appears to us from
our common and general perspective, but must instead be a model of reality that takes into
account the fact that the Consciousness that apprehends physical reality plays some role in
shaping what is apprehended as physical reality.
Therefore, the pending advancement in human understanding regarding the nature of reality
made possible by the discoveries of quantum physics represents an advancement of far greater
significance and scope than any that has come before, because understanding the nature of
quantum reality does not require just another conceptual rearrangement of physical reality, but
requires instead a conceptual rearrangement of all that can be called reality, both experiential and
non-experiential. Specifically, understanding the nature of quantum reality will require that one
cease to recognize physical reality as "the" reality, i.e., as the central or source reality that in
some magical and mysterious way gives rise to all the other realities, including the Reality of
Consciousness. Instead, understanding the nature of quantum reality will require one to
recognize that physical reality is but one type of experiential reality, and that all experiential
realities have as their basis the non-physical, non-experiential Reality of Existence or
Consciousness. Additionally, understanding the nature of quantum reality will also require one to
recognize that physical reality is not what is actually there where it appears to be, in the same
way that one can recognize that a reflection in a mirror, or on the surface of a body of water, is
not what is actually there where it appears to be, even though such reflections can present the
appearance of being what is actually there.
It is the requirement of ceasing to place physical reality at the center of reality, of ceasing to treat
it as "the" reality, and accepting that what we apprehend as physical reality is not what is actually
there where it appears to be, and science's refusal to do so on both counts, that has so far, for
almost one-hundred years, kept science, and therefore humanity, from understanding what its
own endeavors and experiments in the quantum realm have discovered and uncovered regarding
the overall nature of reality. Nor will science in a thousand years be any closer to understanding
the nature of reality as revealed by quantum physics if it is still, at that time, trying to fit quantum
reality into some increasingly twisted, distorted, and contorted materialist conception of reality,
because the conceptual assumptions that lie at the heart of materialism have no more validity
with respect to being reflective of the nature of reality than the idea of a flat Earth is reflective of
the actual shape of the Earth. The Catholic church did not want to give up the idea of the Earth as
being at the center of the Universe and science does not want to give up its related ideas
regarding the primacy, centrality, and objectivity of physical reality. Dogma always dies hard
and with great struggle.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
8
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
That having been said, the philosophy of materialism was not a mistake. Materialism was a step
forward, and it has also provided the opportunity for an even larger step forward with regard to
increasing humanities' understanding of the nature of reality. And while materialism was not a
mistake, it becomes a mistake when it becomes the barrier that keeps science and so humanity
from taking the next step forward. Put another way, materialism was not a mistake, but it has
become a mistake to the extent that it has become that which is keeping humanity from
understanding what the discoveries of quantum physics reveal about the nature of reality. And as
will be demonstrated, one of the things that the discoveries of quantum physics reveal about the
nature of reality is that what we experience as physical reality is the product of a relation, much
like a reflection in a mirror, making physical reality not what is actually there where it appears to
be. And the importance of realizing that physical reality is not what is actually there where it
appears to be is that, as long as one thinks that physical reality is what is actually there where it
appears to be, then What Is Actually There must remain hidden from view, the same way that a
body of water remains hidden as long as one takes the reflection that lies on its surface for what
is actually there.
And What Is Actually There, and so that which has been hidden from view, or hidden in plain
sight really, as a result of our mistaking the reflection that is physical reality for what is actually
there, is that which we refer to as our Consciousness. As one might come across a block of wood
and a tree, and somehow become confused with regard to their actual relation and so set themself
the impossible task of figuring out how the tree comes from the block of wood, so it is that
humanity has, by and large, become confused with regard to the actual relation between physical
reality and Consciousness, and so has left science with the impossible task of figuring out how
physical reality produces the non-physical, non-experiential Reality referred to as Consciousness.
And the task of figuring out how physical reality produces Consciousness is impossible because,
as the phenomena that lie at the heart of quantum theory will reveal once their basis is
understood, it is actually Consciousness that produces physical reality.
Consciousness is the means by which all experiential reality, including physical reality, is
apprehended, and in the absence of which physical reality could not even be known to exist. The
logical slight of hand through which materialism has been able to get away with making physical
reality the creator of the Reality, i.e., Consciousness, without which it could not even be known
to exist, requires the assumption of realism, which is the assumption that physical realities exist
at some level independent of their observation as such, and so independent of Consciousness.
Basically, what the philosophy of materialism requires one to imagine or assume is that there is
an objectively existent physical reality that mindlessly evolved to a point where Consciousness
somehow came into being, at which point Consciousness then, having been poofed into being
through some as yet unknown physical mechanism, just takes in and observes what is already
there as the objectively existent physical reality that is considered to be its source. However, as
demonstrated by a group of physicists, the findings of quantum physics are in conflict with the
assumption of realism, as pointed out in the following passages taken from their paper:
Physical realism suggests that the results of observations are a consequence of properties
carried by physical systems. It remains surprising that this tenet is very little challenged,
as its significance goes far beyond science. Quantum physics, however, questions this
concept in a very deep way.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
9
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
Most working scientists hold fast to the concept of 'realism' - a viewpoint according to
which an external reality exists independent of observation. But quantum physics has
shattered some of our cornerstone beliefs. … Our result suggests that giving up the
concept of locality is not sufficient to be consistent with quantum experiments, unless
certain intuitive features of realism are abandoned.2
Thus, the findings of quantum physics directly contradict and undercut the assumption of realism
that rests at the heart of the materialist philosophy, which philosophy still guides and constrains
the vast majority of scientific thought. So it is that we have one branch of science that has,
through some of the most rigorous experiments ever conducted, determined that the assumption
of realism is almost certainly false, while the rest of science continues to move merrily along,
blissfully ignorant of this fact, or at least ignoring this fact, still assuming realism to be the case
and so still maintaining and upholding an already discredited materialist philosophy that places
physical reality at the center of reality and Consciousness at the periphery of reality, as a reality
somehow created by the machinations of an objectively existent physical reality that quantum
physics has demonstrated, in all likelihood, does not exist. These are indeed strange times.
But as they say, the times, they are a-changin', for as Graham Smetham points out in his many
excellent works, only three of the most recent of which are referenced, more and more physicists
are recognizing that the findings of quantum physics are incompatible with the assumption of
realism, i.e., that physical reality exists independent of observation, and so are rethinking their
positions with regard to the relation between Consciousness and physical reality. 3,4,5 Thus, it is
no longer just idle metaphysical speculation, nor eastern philosophic tradition, that grants to
Consciousness a place in the hierarchy of reality far more important and central than that
ascribed to it by any materialist philosophy, and by extension, most of modern science. To the
contrary, it is the branch of science that has delved the deepest into physical reality that has
taken, or at least is beginning to take, however tepidly, the position that Consciousness and
physical reality are inseparably linked in some way, since what that branch of science has found
is that there is no such thing as a physical reality absent its observation as such. And as
observation implies the presence of Consciousness, since in the absence of an apprehending
Consciousness there is no observation, there is therefore no such thing as a physical reality
absent some Consciousness that apprehends, i.e., observes, that physical reality. This finding
completely undercuts the materialist notion that the machinations of physical reality somehow
create Consciousness, since how can physical reality be the creator of the Reality upon which its
very existence, such as it is, rests, and therefore in the absence of which it cannot even be said to
exist? It cannot and so is not.
If one had somehow been raised with the notion and spent their life believing that trees come
from blocks of wood, it would seem very strange and unbelievable at first to hear that blocks of
wood actually come from trees. Likewise, having been raised in a cultural environment wherein
physical reality is assumed to be the central reality that produces all other realities, including
Consciousness, it is no doubt strange to hear that it is actually the other way around, i.e., that
Consciousness produces physical reality. Understand though that the strangeness does not arise
from any actual strangeness, but only appears as strange in relation to the opposite materialist
position or conception of reality that one most likely presently holds, since materialism is the
conception of reality that has been, and still remains, for the time being, the most dominant. Put
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
10
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
another way, the idea that Consciousness could give rise to physical reality only seems strange
and unbelievable from within a materialist perspective and framework, which by its nature holds
the opposite view. In the absence of an attachment to either philosophy, i.e., materialism or
idealism, these are simply opposite possibilities, one no more strange than the other, i.e., physical
reality produces Consciousness or Consciousness produces physical reality, respectively. The
only question is, which position more accurately reflects the actual nature of reality, since it
cannot be both.
The strange is only strange in the context of considering its opposite to be normal. But what are
we to do when what we consider to be normal is itself an illusion, thereby making what is
actually the normal state of affairs seem strange by comparison? We can either see through the
illusion and so realize what is actually the normal state of affairs, or we can cling to the illusion,
in which case what is actually the normal state of affairs remains hidden from view, as a body of
water remains hidden as long as one takes the reflection that only lies on its surface for what is
actually there. If one had somehow been raised with the notion and spent their life believing that
trees come from blocks of wood, and then be told that it is actually the other way around, one
might find it hard to believe, until they were taken to a lumber mill, at which point seeing the
process by which trees are turned into boards or blocks of wood one would be hard pressed to
maintain their erroneous belief in the relation between trees and blocks of wood. Likewise, most
who are reading this have spent their life believing that Consciousness is produced by physical
reality, and therefore probably find it hard to believe that it is actually the other way around.
Therefore, one purpose of this work is to take the reader to the quantum lumber mill, so to speak,
to demonstrate exactly how physical reality is produced by Consciousness, by using the actual
relationship between Consciousness and physical reality to explain the heretofore inexplicable
behavior and nature of quantum reality as expressed by the phenomena that lie at the heart of
quantum theory.
As this work will demonstrate, it is possible to describe how the non-physical, non-experiential
Reality of Consciousness gives rise to physical reality in a way that is both consistent with, as
well as explanatory of, the nature of quantum reality as put forth and described by quantum
theory, because that is what actually happens. Conversely, it will never be possible to describe
how physical reality gives rise to Consciousness, because that is not what actually happens, but
is only what appears to happen. The idea that physical reality produces Consciousness is a
dogmatic assumption for which science has no actual proof whatsoever. All science has is what
has been assumed based on common perspective, which is the same sort of perspective that at
one time had humanity believing that the Earth was flat and that the Sun orbited the Earth. In
fact, as stated previously, what science has proven is that physical reality cannot produce
Consciousness, because physical reality cannot be said to exist in the absence of its observation,
which is to say, in the absence of its apprehension as such by an Individual Consciousness.
It is time for humanity to continue to move forward in its conception of reality by freeing itself
from the shackles of a conception of reality that has become a hindrance rather than a help with
regard to furthering its understanding of the nature of reality. With that in mind, it is my
intention in this work to function as a modern day Copernicus with regard to the whole of reality,
by making the heretofore incomprehensible behavior and nature of quantum reality
comprehensible by explaining its behavior and nature in the context of a model of reality that
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
11
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
places the non-physical and non-experiential Reality of Consciousness at the center of reality,
with the rest of reality, including physical reality, revolving around or extending from That.
Introduction
As will be described, there is far less going on than meets the eye, and things are nowhere near
as complex as they appear to be. In short, What Is Actually There, i.e., the Reality that underlies
the reflection that is physical reality, forms a relation with Itself, and as a result of that relation
something is produced that is apprehended by What Is Actually There. It is the innate, intrinsic,
and inherent ability of What Is Actually There to apprehend the product created as a result of its
relation to Itself that allows What Is Actually There to function as Consciousness, and it is that
created product, as it is apprehended by What Is Actually There, now functioning as
Consciousness, that is experience or experiential reality. Put another way, all experience,
including physical experience and so physical reality, is nothing more than What Is Actually
There apprehending the products of its relations to Itself.
In this work, the terms Existence, Consciousness, and Reality are all used to point toward or
indicate What Is Actually There where physical reality appears to be, and so are for the most part
interchangeable. Nonetheless, when discussing that which apprehends experience, What Is
Actually There will most often be referred to as Consciousness, and when talking about that
which through relation to Itself creates what is apprehended as experience, What Is Actually
There will most often be referred to as Existence. And when referring in general to What Is
Actually There, it will most often be referred to as Reality. Further, any word that is capitalized
that is not at the beginning of a sentence is also a word that is being used to indicate or point
toward What Is Actually There where physical reality appears to be. Also, owing to the use of
this convention to indicate What Is Actually There, from this point onward words that are usually
capitalized are not capitalized if they are not being used to point toward What Is Actually There.
In order to understand the nature of quantum reality, one needs to understand the nature of reality
as a whole. The reason the nature of quantum reality remains a mystery is because, as has just
been described, science has been stuck with a conception of reality, i.e., materialism, that bears
little to no resemblance to the actual nature of reality. This has made it impossible to fit quantum
reality, which is reflective of the actual nature of reality, into that conception of reality. In
essence, quantum reality represents a section of the puzzle that is the whole of reality, and up
until now humanity has been attempting to fit that section of the puzzle into a materialistic
puzzle that is thought to depict the whole of reality, and the results have been as one would
expect when trying to fit a section of a puzzle into what is the wrong puzzle, i.e., it does not fit.
The statement that the nature of quantum reality remains a mystery means that no one who deals
with quantum theory knows what makes quantum reality behave the way it behaves and appear
the way it appears, which is what Feynman meant when he stated that "nobody understands
quantum mechanics." To a limited degree, quantum physicists are like the technicians in charge
of a large machine, the inner workings of which remain a complete mystery. They know which
buttons to push to make this or that come out, to produce this or that result, i.e., they know the
equations, but they really know little to nothing of the machine itself that produces those results,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
12
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
i.e., they do not know what the equations and the results of those equations actually represent.
And again, the reason they do not understand the nature and inner workings of the machine with
which they are dealing is because they were handed the wrong instruction manual in the form of
the philosophy of materialism, leaving them to try and understand the why and how of the
workings of quantum theory by looking to an instruction manual that really has nothing to do
with the machine or mechanism with which they are dealing.
As a conception of reality materialism is very understandable, it just does not accurately reflect
the nature of reality. The behavior of quantum reality is what it is. Quantum reality remains
unknown and not understood because it cannot be fit into what we do know, which is the
materialist model. Therefore, as the goal of this work is to allow the reader to understand why
quantum reality appears and behaves as it does, the approach in this work toward that end will be
to first build a new and different puzzle or model of reality, to write a different instruction
manual, that represents the whole of reality, after which quantum reality will be fit into that new
model by showing how the phenomena that lie at the heart of quantum theory can be explained
and understood in the context of that model. This new model, which will be referred to as the
iterative Existential self-relation model of Reality and reality, will be one that is also
understandable, but will also have the added advantage of being accurately reflective of the
nature of reality. Once this new model of reality has been built, the section of the puzzle that is
quantum reality will be fit into that new model, thereby converting quantum reality from an
unknown to a known reality, from a mystery to something that can be understood, because it will
be seen in its proper context and place within the overall scheme and structure of reality, as
shown in general terms in figure 5 below.
If one finds a strange object lying on the ground and that object is part of a larger mechanism,
that object remains a mystery unless and until one discovers and understands the larger
mechanism of which the strange object is a part, at which point the object ceases to be strange
and mysterious. That is where humanity stands at present with respect to quantum reality and
quantum theory, i.e., it has discovered this strange object called quantum reality, which strange
object is described by quantum theory, but it has no explanation for that object because the larger
mechanism of which it is a part remains hidden, and as a consequence the object continues to be
strange and mysterious. For this reason, as already mentioned, the first part of this work will deal
with developing a model of reality that describes the larger mechanism of which quantum reality
is but a part.
And also as already mentioned, the model of reality that will be developed, and into which
quantum reality will be shown to fit and thereby be rendered understandable, will be referred to
as the iterative Existential self-relation model of Reality and reality. The reason for the
cumbersome name will become clear as the model is developed, including why the name of the
model contains both the words Reality and reality. And do not let the seeming complexity of the
name fool you, because understanding the iterative Existential self-relation model of Reality and
reality is as simple as understanding what happens to a rubber band that is twisted repeatedly
upon itself. And so, if you are able to understand what happens to a rubber band that is twisted
repeatedly upon itself then you will be able to understand the nature of reality as a whole, and if
you can understand that, then you will be able to understand the nature of quantum reality. It
really is that simple.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
13
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
quantum
reality
something that is
incomprehensible
and so is not understood
Materi alistic
model o f rea lity
assumption
of physical
realism
quantum
reality
something that
remains incompre hensible
and so rema ins not understood
something that is
comprehensible
and so can be understood
quantum
reality
Ide alistic
model o f rea lity
iterative Existential self-relation
model of Reality and reality
something that is
incomprehensible
and so is not understood
physical
realism
abandoned
quantum
reality
something that is
now c omprehensi ble
and so is now understood
something that is
comprehensible
and so can be understood
Figure 5 This drawing depicts, in a general way, the purpose of this work, which is to covert quantum
reality from an incomprehensible to a comprehensible reality by fitting it into a comprehensible model of
reality. As depicted at the top, although materialism presents a very comprehensible model of reality, the
inability to fit quantum reality into the materialistic model, illustrated here as the attempt to fit a round
peg into a square hole, has caused quantum reality to remain mysterious and incomprehensible. Quantum
reality cannot be fit into a materialistic model because the materialistic model does not accurately reflect
the actual nature of physical reality, in as much as a central tenet of materialism is physical realism, i.e.,
that what we apprehend as physical reality exists independent of observation and is what is actually there
where it appears to be. However, as shown at the bottom, once quantum reality is fit into a
comprehensible model of reality that reflects what the phenomena that lie at the heart of quantum theory
say about the nature of physical reality, i.e., that physical reality does not exist independent of observation
and is not what is actually there where it appears to be, then quantum reality will be converted from
something that is both incomprehensible and not understood to something that is both comprehensible
and understood.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
14
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
1. Building a new model of reality
1.1 The evolution of Existence
As stated previously, in order to understand the nature of quantum reality it will be necessary to
understand the nature of reality as a whole, and in order to understand the nature of reality as a
whole it will be necessary to understand three things:
1. That the whole of reality consists of two completely different and yet related realities;
experiential reality and the Reality of Existence that, through relation to Itself, both
creates and apprehends experiential reality.
2. That Existence evolves through a process of iterative and progressive self-relation, and
produces as a result of those self-relations both Relational Structures that are composed
of Existence as It has become configured in relation to Itself, as well as experiential
realities that are not composed of Existence.
3. That both Reality and reality are stratified owing to the process through which
Existence evolves.
However, in order to understand the three things necessary to understand reality as a whole it
will only be necessary to understand the second item listed above, i.e., how the Reality of
Existence evolves through a process of iterative self-relation. Iterative processes are processes
where something is produced as a result of a process, with that result then fed back into that
same process, producing another result that is then fed back into that same process, producing
still another result that is then fed back into that same process and on and on ad infinitum. The
geometric structures referred to as fractals are generated through iterative processes. Physical
reality, including organic reality, appears fractal because underlying what we apprehend as
physical reality are Relational Structures composed of Existence that has become configured in
relation to Itself as the result of an iterative process. Put another way, underlying what we
apprehend as physical reality is Existence that has become configured into a fractal Relational
Structure as a result of subjecting Itself to the process of iterative self-relation.
As already stated, the iterative process whereby Existence evolves into the progressive and
stratified Relational Structures that underlie what we apprehend as physical reality is one of
iterative self-relation. Specifically, that process is one in which Existence forms a relation with
Itself, thereby Existing as a Relational Structure composed of Itself as It is being in relation to
Itself, and then while Existing as that Relational Structure It forms yet another relation with
Itself, thereby Existing as a new Relational Structure composed of Itself as It is being in relation
to Itself, and then while Existing as the new Relational Structure It forms yet another relation
with Itself, and on and on and on until here we are, taking part in that ongoing process while
looking out upon and into a universe that has evolved and continues to evolve through that
process. However, it is important to note here that what we apprehend as the physical or material
universe is not itself the overall Relational Structure composed of Existence that has evolved
through a process of iterative self-relation. Rather, what we apprehend as the physical or material
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
15
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
universe is only an etching of that Structure, a point which will become clear once the nature of
experiential reality has been described.
And as perhaps daunting and abstract as all of the above may sound, the process of iterative
Existential self-relation whereby Existence evolves into a progressive and so stratified Relational
Structure, while producing at the same time, as a result of those same relations, what Existence
apprehends as experiential reality, can all be explained by examining what happens to a rubber
band that is twisted repeatedly upon itself. As previously stated, in order to understand reality as
a whole, i.e., the nature of Reality and reality, as well as the relation of each to the other, one
need only understand how Existence evolves into the progressive and hence stratified Relational
Structure that is the basis of and underlies what we apprehend as experiential reality in general
and physical reality in particular, and in order to understand that one need only understand what
happens to a rubber band that is repeatedly twisted upon itself, i.e., subjected to the force of
iterative self-relation.
1.2 The evolution of Existence into a progressive Relational Structure
Since I first began writing about the nature of reality as a whole and the evolution of Existence
through the process of iterative and progressive self-relation, I have stated that what happens to a
rubber band that is repeatedly twisted upon itself is analogous to what happens to Existence as It
subjects Itself to the force of iterative self-relation. However, it has occurred to me recently that
what happens to a rubber band that is repeatedly twisted upon itself is not just analogous to what
happens to Existence as it subjects Itself to the force of iterative self-relation, but is in fact
Existence being subjected to the force of iterative self-relation, albeit externally rather than
internally, and as a result doing what Existence does when subjected to that force, which is form
into a progressive Relational Structure. And so, what happens to a rubber band as it is twisted
upon itself not only provides an example of the process of iterative Existential self-relation, but
is itself evidence that when the force of iterative self-relation is applied to Existence, the result is
that Existence becomes configured into a progressive Relational Structure. And even though
what we apprehend as the physical object-reality referred to as a rubber band is not what is there
directly, but is an etching of what is there, that etching nonetheless reveals in some measure what
is taking place with respect to the Reality that underlies what we experience as the physical
object-reality.
To be clear, we do not and cannot experience or see the Relational Structure that is actually there
where the rubber band appears to be, because the Existence of which that Relational Structure is
composed is of a completely different Nature than the nature of experience, a fact which will be
made clear shortly. However, what we do experience as the physical reality of the rubber band is
an etching of the Relational Structure composed of Existence that is actually there, which is
another fact which will be made clear shortly. That is, what we experience as physical reality is
never what is actually there where the physical reality appears to be, because what is actually
there is always Existence that has become configured, through the process of iterative selfrelation, into a Relational Structure. However, what we experience as physical reality does bear
some relation to what is actually there, the same way the appearance of an etching bears some
relation to whatever it was that was etched.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
16
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
Therefore, what we apprehend as a rubber band is not what is actually there where the rubber
band appears to be. What is actually there where the rubber band appears to be, even before it is
twisted upon itself, is Existence that has been configured into a specific Relational Structure
composed of a specific set of Existential relations which, when apprehended, appears as the
physical object-experience-reality we call a rubber band. And when the Existence-Reality, i.e.,
the Existence configured into a Relational Structure, that is actually there is subjected to the
force of iterative self-relation, which is accomplished by twisting the rubber band repeatedly
upon itself, the Existence-Reality that is there becomes configured into a progressively higher
order Relational Structure composed of additional Existential self-relations, which progressively
higher order relational structuring we apprehend as the rubber band becoming increasingly
twisted upon and configured in relation to itself, as shown in figures 6-8.
Figure 6 Depicted in this photo is a rubber band that has been repeatedly twisted upon itself, i.e.,
subjected to the force of iterative self-relation, and as a result has become configured into a first level of
relational structuring consisting of a single set of relations of the rubber band to itself. The repeated
twisting of a rubber band upon itself subjects the rubber band, and so the Existence-Reality that is actually
there, to the force of iterative self-relation, which is the same force that is responsible for the evolution of
Existence into the progressive and stratified Relational Structure that underlies what we apprehend as
experiential reality in general and physical reality in particular.
It is important to note that the force of iterative self-relation being applied to the rubber band,
and hence to Existence-Reality, in order to cause the rubber band to become configured into a
relational structure, is being applied externally, i.e., from the outside in, or coming from outside
the Existence-Reality that is actually there where the rubber band appears to be, whereas the
force of iterative self-relation that is responsible for the evolution of Existence into the
progressive and stratified Relational Structure that underlies what we apprehend as physical
reality is one that is applied internally, i.e., from the inside out, or coming from inside Existence,
as that force is intrinsic to Existence. That intrinsic force is what we refer to as the force of will,
and is not different or other than the force by which we ourselves chose to think a thought or
move our hand in a certain direction. That is, the force by which we choose to think a thought or
move ourselves about is not different or other than the force that Existence uses to become
involved in the progressive relations with Itself that cause it to become configured into the
Relational Structures that underlie what we apprehend as physical-material reality. Put another
way, it is possible to identify the force by which Existence becomes involved in relations with
Itself as the same force by which we become involved in relations with the world around us and
within us, because, as will be described, what actually Exists directly where we are is of the same
Nature as what actually Exists directly where the rubber band, or any other physical reality,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
17
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
appears to be. That is, the only difference between what actually Exists here and what actually
Exists there is not in the Nature of what actually Exists here or there, but is only a difference in
the way in which that singular Nature has become arranged and configured in relation to Itself,
through iterative relation to Itself, both here and there.
Nonetheless, regardless of whether the force of iterative self-relation is being applied to
Existence from the inside out or from the outside in, the result is that Existence becomes
configured into a Relational Structure. The relational structuring of the rubber band shown in
figure 6 represents a first level of relational structuring relative to the untwisted rubber band i.e.,
relative to the rubber band to which no external force of iterative self-relation has yet been
applied. As such, the relational structuring of the rubber band shown in figure 6 is analogous to
what will be described as the first level of Reality, i.e., the first level of Relational Structure or
Existential Self-Relation.
And as shown in figure 7, as the rubber band continues to be subjected to the force of iterative
self-relation it becomes configured into a higher order relational structure, i.e., a second level of
relational structure. This second level of relational structuring arises as the first level of relational
structuring becomes complex enough, i.e., has undergone enough iterations, that it is then able to
form a relation with itself, creating a second level of relational structuring, both of which levels
of relational structuring are composed of the single rubber band configured in relation to itself as
a result of its being subjected to the force of iterative self-relation.
Figure 7 Depicted in this photo is a rubber band that has continued to be repeatedly twisted upon itself,
i.e., continued to be subjected to the force of iterative self-relation, and as a result has become configured
into a first and second level of relational structuring consisting of two sets of relations of the rubber band
to itself. The second level of relational structuring occurs as the rubber band, already configured into a
first level of relational structuring, continues to be subjected to the force of iterative self-relation,
eventually causing the first level of relational structure to form a relation with itself, thereby creating a
second level of relational structuring that is composed of the first level of relational structure configured
in relation to itself.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
18
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
The second level of relational structuring of the rubber band, shown in figure 7, is analogous to
what will be described as the second level of Reality, i.e., the second level of Relational
Structure or Existential Self-Relation. And as shown in figure 8, as the rubber band continues to
be subjected to the force of iterative self-relation, it becomes configured into a third level of
relational structuring. And following the same pattern, this third level of relational structuring
arises as the second level of relational structuring becomes complex enough, i.e., has undergone
enough iterations, that the second level relational structure is able to form a relation with itself,
creating a third level of relational structuring, all of which levels are composed of the single
rubber band configured in relation to itself through the force of iterative self-relation. And like
the first and second levels of rubber band relational structuring of which it is composed, this
third level of relational structuring of the rubber band is analogous to what will be described as
the third level of Reality, i.e., the third level of Relational Structure or Existential Self-Relation.
Figure 8 Depicted in this photo is a rubber band that has continued to be repeatedly twisted upon itself,
i.e., subjected to the force of iterative self-relation, and as a result has become configured into a first,
second, and third level of relational structuring, consisting of three sets of relations of the rubber band to
itself. The third level of relational structuring occurs as the rubber band, already configured into first and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
19
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
second levels of relational structuring, continues to be subjected to the force of iterative self-relation,
eventually causing the second level of relational structure to form a relation with itself, thereby creating a
third level of relational structuring that is composed of the second level of relational structure configured
in relation to itself.
As stated previously, the process whereby Existence evolves into the progressive and stratified
Relational Structure that underlies what we apprehend as physical reality is, like the process that
causes the rubber band in figures 6-8 to become configured into a progressive relational
structure, one of iterative self-relation. Also as stated previously, the geometric structures
referred to as fractals are generated through iterative processes. Therefore, the progressive
Relational Structure that underlies what we apprehend as physical reality is Itself a fractal
Structure, since it is a Structure that has been generated as the result of an iterative process. One
of the properties of fractals is that they exhibit the property of self-similarity, which is the
repetition of structural patterns at different levels of iteration within a particular fractal structure.
This property can be seen in the fractal referred to as the mandelbrot set shown in figure 9.
Figure 9 Shown here are images of the fractal structure known as the mandelbrot set, captured at
increasingly iterated levels, progressing in clockwise rotation from the upper left. Within the first three
images is a white box that shows the area that is expanded and depicted in the following image. What
these images demonstrate is the property of self-similarity, i.e., the repetition of structural patterning at
different levels of iteration, inherent in fractal structures, which is to say, inherent in structures that are
created as the product of an iterative process, such as that which is responsible for a rubber band
becoming configured into a progressive relational structure, or such as that which is responsible for the
evolution of Existence into the progressive Relational Structure that underlies what we apprehend as
physical reality.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
20
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
The purpose of pointing out this property of fractals, i.e., self-similarity, or the repetition of
pattern within pattern, is to explain why it is possible to use a rubber band to describe in general
the way in which Existence evolves into a progressive Relational Structure through the process
of iterative self-relation. As stated previously, what is actually there where the rubber band
appears to be is Existence that is already configured into a Relational Structure. And as the force
of iterative self-relation is applied to that Structure, i.e., to Existence configured as that Structure,
which force is applied by twisting the rubber band repeatedly upon itself, the fractal Relational
Structure that is actually there exhibits the property of self-similarity by repeating, at a higher
level of iteration, the pattern of progressive relational structuring already intrinsic to it, by
becoming visibly configured into progressive levels of relational structuring, as was depicted in
figures 6-8.
The three levels of rubber band relational structure that have just been described and depicted
form the basis of what one needs to understand in order to understand the Nature of Reality,
because the Reality that underlies what we apprehend as physical reality consists of Existence
that has, through the process of iterative self-relation, become configured into three progressive
levels of Reality or Relational Structuring. The three progressive and so stratified levels of
Relational Structure into which Existence has become configured or arranged have been
described extensively in my various writings prior to this, and will be summarized below.6,7
The three progressive levels of Relational Structure composed of Existence that underlie what
we apprehend as physical reality evolve in the same way that the relational structure of the
rubber band evolves. Specifically, as Existence subjects Itself to the force of iterative selfrelation it becomes configured into a first level of Relational Structuring. And once that first
level of Relational Structuring has reached a sufficient level of complexity, the ongoing
application of the force of iterative self-relation causes that first level of Relational Structuring to
form a relation with Itself, thereby producing a second level of Relational Structuring. And once
that second level of Relational Structuring has reached a sufficient level of complexity, the
ongoing application of the force of iterative self-relation causes that second level of Relational
Structuring to form a relation with Itself, thereby producing a third level of Relational
Structuring.
Each of these three different levels of Relational Structuring are each composed of Existence as
it has become configured and arranged in relation to Itself owing to the force of iterative selfrelation, and each corresponds to our apprehension of a different sort of physical reality. Again,
physical reality is not What Is Actually There, but it is a sort of etching of What Is Actually
There, and as such there is correspondence and correlation between the differences in what we
apprehend as being there physically and differences in the way What Is Actually There is
configured and arranged in relation to Itself.
Specifically, what we apprehend as the physical reality of space corresponds to the first level of
Existential Relational Structuring, and what we apprehend as inorganic matter and energy
corresponds to the second level of Existential Relational Structuring, and finally, what we
apprehend as organic reality corresponds to the third level of Existential Relational Structuring.
Put another way, What Is Actually There, i.e., Existence, forms relations with Itself and as a
result becomes configured into a first level Relational Structure that is the basis of the physical
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
21
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
reality we apprehend as space. That first level Relational Structure then forms relations with
Itself and as a result becomes configured into the second level Relational Structures that are the
basis of what we apprehend as material reality. Those second level Relational Structures then
form relations with each other and as a result become configured into the third level Relational
Structures that are the basis of what we apprehend as organic reality. This progression is
summarized in figure 10.
Organic
Processes Relational
Structures
underlying
organic
matter
3rd level relat ion and
Relat ional Structure
3rd level of Reality
force of iterative
self-relation
force of iterative
self-relation
Distortion
Processes Relational
Structures
underlying
inorganic
matter and
energy
2nd level re lation and
Relat ional Structure
2nd level of Reality
force of iterative
self-relation
force of iterative
self-relation
Relational
Matrix Relational
Structure
underlying
space
1st level re lation and
Relat ional Structure
1st level of Reality
force of iterative
self-relation
rubber band
force of iterative
self-relation
Existence
Figure 10 On the left is depicted the progressive relational structuring of a rubber band into three
successive levels of rubber band reality as it is subjected to the force of iterative self-relation, and on the
right is depicted the progressive Relational Structuring of Existence into three successive levels of Reality
as it subjects Itself to the force of iterative self-relation. Each successive level of rubber band reality or
relational structuring is composed of a different set of relations of the rubber band to itself only made
possible by the relations of the rubber band to itself that compose the preceding or prior levels of rubber
band reality. Likewise, each successive level of Reality or Existential Relational Structuring is composed
of a different set of relations of Existence to Itself only made possible by the relations of Existence to
Itself that compose the preceding or prior levels of Reality.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
22
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
As shown in figure 10, the first level of Reality or Existential Relational Structuring is referred to
as the Relational Matrix. That is, the Relational Matrix is the name I have given to the first level
Relational Structure composed of Existence configured in relation to Itself that underlies and is
the basis of what we apprehend as the physical reality of space or space-time. The credit for
discovering the structure of space, or more accurately, the Structure underlying what we
apprehend as the emptiness of space, must go to Buckminster Fuller. Fuller was interested in the
way force was distributed in space, and found that forces in space followed the vectors described
by a particular cubic-closepacking arrangement of spheres.8 And whether Fuller knew it or not,
what he was describing with his arrangement of spheres was the static aspect of the first level of
Relational Structuring into which Existence arranges Itself as a result of subjecting Itself to the
force of iterative self-relation. Further evidence pointing toward the spherical Structuring of the
first level of Reality can be found in the cellular structure of Organic Processes, which exhibit
the fractal property of self-similarity by repeating, at a more iterated level of Reality, i.e., at the
third level of Reality, the spherical or cellular pattern of Relational Structuring found at the first
level of Reality.
Also as shown in figure 10, when Existence, already configured into a first level of Relational
Structuring owing to the force of iterative self-relation, continues to subject Itself to the force of
iterative self-relation, that first level Relational Structure forms a relation with Itself, thereby
creating a second level of Relational Structuring composed of Existence configured in relation to
Itself in a new way, only made possible by the relations that compose the previous level of
Relational Structuring. Thus, the second level of Reality or Relational Structuring is composed
of the first level, i.e., the Relational Matrix, being in relation to Itself. I refer to these second
level Realities or Relational Structures as Distortion Processes, and it is these second level
Relational Structures that underlie and are the basis of what are apprehend as the physical
realities of electromagnetic energy and, in their more iterated form, matter. Einstein clearly
understood that what we apprehend as matter is an accumulation and configuration of what we
apprehend as energy, as expressed by his famous equation, e = mc2. However, what Einstein also
clearly understood was that what we apprehend as matter, and therefore what we apprehend as
energy, extend from what we apprehend as space, as evidenced by the following quote:
I wished to show that space-time isn’t necessarily something to which one can ascribe a
separate existence, independently of the actual objects of physical reality. Physical objects
are not in space, but these objects are spatially extended. In this way the concept of "empty
space” loses its meaning.9
In other words, what we apprehend as physical objects do not exist in empty space; rather,
physical objects are structures that are themselves extensions of, or which extend from, an
underlying spatial structure.
Finally, as shown in figure 10, when Existence, already configured into first and second level
Relational Structures owing to the force of iterative self-relation, continues to subject Itself to the
force of iterative self-relation, those second level Relational Structures are able to form a new
type of relation with each other, and as a result become configured into a third level of Relational
Structuring. I refer to these third level Realities or Relational Structures as Organic Processes,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
23
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
since it is these third level Relational Structures that underlie and are the basis of what we
apprehend as organic physical reality.
As just described, each of the three different levels of Reality are composed of Existence that is
configured and arranged in relation to Itself in a different way. Thus, the relations of Existence to
Itself by which Existence becomes configured into the first level of Reality or Relational
Structuring, i.e., the Relational Matrix, are different than the relations of Existence to Itself by
which Existence becomes configured into the second level of Reality or Relational Structuring,
i.e., Distortion Processes, and the relations of Existence to Itself by which Existence becomes
configured into the third level of Reality or Relational Structuring, i.e., Organic Processes, are
different than the relations of Existence to Itself by which Existence becomes configured into
both the first and second levels of Reality.
The importance of understanding that each of the three different levels of Reality is constructed
of Existence being in relation to Itself in a different way is that this will allow for an
understanding of why there are three different types of experiential realities that we each, as
Consciousness, are able to apprehend, once it is understood that what we apprehend as an
experiential reality of any sort, i.e., emotional, mental, or physical, is the product of a particular
type of relation of Existence to Itself occurring at a particular level of Reality or Existential selfrelation. Also, understanding that each of the three different levels of Reality is constructed of
Existence being in relation to Itself in a different way will also allow for an understanding of the
stratified structure of experience that goes along with the stratified Structure of Reality, which
will be of benefit in understanding just what it is that scientists are poking their noses into when
they probe into quantum reality.
That having been said, it is now time to describe the nature of experiential reality, as well as the
relation of experiential reality to Reality, i.e., the relation of experiential reality, and especially
physical reality, to the Relational Structures composed of Existence being in relation to Itself that
underlie what we apprehend as physical reality. And the way the nature of experiential reality
will be described is by explaining how experiential reality is created as a result of the same
Existential relations by which Existence becomes configured into a progressive and stratified
Relational Structure.
1.3 The nature and creation of experiential reality
So far all that has been accomplished is a brief description of how what the universe is actually
composed of, i.e., Existence, becomes configured into a tri-level Relational Structure. Not much
has been said so far regarding the nature of experience in general, or regarding the nature of
physical reality in particular, other than to point out that experience is always the product of
some relation of Existence to Itself, and that what we apprehend as physical reality is not what is
actually there.
As previously stated, reality as a whole consists of both Reality and reality, i.e., a progressive
Relational Structure composed of Existence configured in relation to Itself, and what we
apprehend as experiential reality, which is not composed of Existence, but rather is produced as a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
24
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
sort of by-product of the relations of Existence to Itself through which Existence becomes
configured into a progressive and stratified Relational Structure. That is, the same relations of
Existence to Itself that cause Existence to become configured into a progressive Relational
Structure also produce what the Existence involved in those relations apprehends as experiential
reality. And in order to explain both how this occurs as well as how experience is created, which
explanation will allow one to understand the relation of experience to Existence, we will return
to the rubber band model.
When using the rubber band model to explain how Existence becomes configured into a
progressive and stratified Relational Structure as a result of the process of iterative self-relation,
the focus was upon the overall structure into which the rubber band became configured as a
result of those iterative and progressive self-relations. However, in discussing the nature of
experience and how experience is created as a product of those same relations, the focus will be
upon a different aspect of that structure, which different aspect is the boundary that is created
where the rubber band comes to be in relation to itself, and so becomes defined in relation to
itself, as it simultaneously becomes configured in relation to itself.
As will be described, as well as demonstrated through direct correlation to quantum experience
and phenomena, what we apprehend as experiential reality is analogous to the boundaries that
are created where the rubber band comes to be in relation to itself as a result of its being
subjected to the process of iterative self-relation, as shown in figure 11. That is, what will be
shown is that what we apprehend as experiential realities in general, and physical realities in
particular, have as their basis boundaries that are created where Existence becomes defined in
relation to Itself as a result of being in relation to Itself, with the specific type of boundary that is
created and so experience that is apprehended, i.e., emotional, mental, or physical, dependent
upon the specific type of relation in which the Existence that is apprehending the experience is
involved.
force of iterative
self-relation
1st, 2nd, and 3rd level boundaries that arise where the rubber
band becomes defined in relation to itself through iterative and
progressive relation to itself at a first, second, and third level of
relational structuring.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
25
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
Figure 11 As shown in this photo, as the rubber band is subjected to the force of iterative self-relation and
so becomes configured into a progressive relational structure, boundaries are created where the rubber
band becomes defined in relation to itself through relation to itself. These boundaries, some of which are
highlighted by black, red, and blue lines, are not what is actually there, but are created as a by-product of
the relations occurring between what is actually there, which in this case is the rubber band. Likewise, as
Existence subjects Itself to the force of iterative self-relation and so becomes configured into a Relational
Structure, boundaries are created where Existence becomes defined in relation to Itself through relation to
Itself. Such boundaries, which will be referred to as experiential boundaries, are also not what is actually
there, but are created as a by-product of the relations occurring between What Is Actually There, which in
this case is Existence, and it is such boundaries that are what the Existence-Consciousness that is involved
in a relation that creates such a boundary apprehends as an experiential reality, with the particular type of
experience apprehended, i.e., emotional, mental, or physical, dependent on the type and so level of
Existential relation that produces the boundary.
As can be seen in figure 11, the nature of the boundary that arises where the rubber band
becomes defined in relation to itself through relation to itself is different than the nature of the
rubber band itself. The boundaries only exist as long as there is some relation of the rubber band
to itself, whereas the rubber band continues to exist even when the relations that create those
boundaries no longer exist. Likewise, the nature of what we apprehend as experience is different
than the Nature of That which, through relation to Itself, both creates and apprehends experience,
since what we apprehend as experience only exists, as it were, as the product of some relation of
Existence to Itself, whereas Existence Exists regardless of whether or not it is involved in any
particular relation. Thus, although they are related, inasmuch as Existence both creates and
apprehends experience, Existence and experience are completely different in nature, which is
why it is not possible to experience Existence, i.e., not possible that Existence Itself be an
experience, not possible to experience What Is Actually There, because if it is an experience then
it cannot be Existence, since the nature of experience is different than the Nature of Existence.
Existence is that which can only be known through relation to Itself, and even then what is
known is not Existence Itself, but rather is only the apprehension of the boundary that is created
where Existence, as a result of some relation to Itself, has become defined in relation to Itself.
As previously stated, reality as a whole consists of both Reality and reality. The meaning of this
statement should now be more clear, as it should now be possible to understand and comprehend
the difference between Reality and reality, i.e., the difference between the Reality of What Is
Actually There as Existence configured into a progressive Relational Structure through the
process of iterative self-relation, and the realities that are created as by-products of those selfrelations, which created realities are what the Existence that is involved in those relations
apprehends as various experiential realities, simply by recognizing the difference between a
rubber band that is twisted upon itself and the boundaries that arise and are created where the
rubber band becomes defined in relation to itself as a result of its being twisted upon itself, i.e.,
as a result of its being subjected to the force of iterative self-relation.
In summary, when Existence subjects Itself to the force of iterative self-relation and so comes to
be in relation to Itself, two things are created, one of which is composed of Existence and the
other of which is not composed of Existence. That which is created that is composed of
Existence, composed of What Is Actually There, is a Relational Structure composed of Existence
as it has become configured and arranged in relation to Itself as a result of its participation in the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
26
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
process of iterative self-relation. That which is created that is not composed of Existence, not
composed of What is Actually There, are the experiential boundaries that arise where Existence
becomes defined in relation to Itself as a result of its participation in the process of iterative selfrelation. And it is the experiential boundaries that arise where Existence becomes defined in
relation to Itself that are apprehended as experiential realities by the Existence-Consciousness
that is taking part in the relations that create those experiential boundaries. Thus, there is Reality
and reality, i.e., there is Existence-Consciousness, which is What Is Actually There, and there is
experience, which, like a reflection, can present the appearance of being what is actually there.
Also as previously stated, Reality, i.e., the progressive and stratified Relational Structure
composed of Existence configured in relation to Itself that underlies what we apprehend as
physical reality, consists of three related and yet different levels of Reality or Relational
Structuring, and each different level of Reality or Relational Structuring is composed of
Existence being in relation to Itself in a different way. And as experience is always the product
of some relation of Existence to Itself, it follows that different types of experience must be the
products of different types of Existential relations. And as there are only three different types of
experience or experiential realities, i.e., emotional, mental, and physical, it then also follows that
there must then be three different levels of Relational Structuring, each composed of Existence
being in relation to Itself, and so configured in relation to Itself, in a different way. Coming at it
from another direction, if there are three different levels of Reality, three different levels of
Relational Structuring composed of Existence being in relation to Itself in three different ways,
then each level of Reality should produce its own unique type of experiential boundary as a
result of the Existential relations that are unique to that level of Reality, which unique type of
experiential boundary would then be apprehended as a unique type of experience by the
Existence-Consciousness involved in the relations that create that particular level of Reality. And
indeed this is what is found to be the case and is in fact why there are only three different types
of experiential realities that we are able to apprehend, i.e., emotional, mental, and physical,
because each of these different types of experiential reality is the apprehension of the product of
a different type of Existential relation occurring at a different level of Reality or Relational
Structuring. This is also why experiential reality is stratified along with the stratification of the
Relational Structure of Reality, as shown in figure 12.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
27
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
Organic
Processes impactive
relation
3rd level relat ion,
Relat ional Structure
and boundary
physical
experience
created
(form and
tangibility)
3rd level of Reality
force of iterative
self-relation
force of iterative
self-relation
Distortion
Processes interactive
relations
2nd level re lation,
Relat ional Structure,
and boundary
mental
experience
created
(form)
2nd level of Reality
force of iterative
self-relation
force of iterative
self-relation
Relational
Matrix relations of flow
1st level re lation,
Relat ional Structure,
and boundary
emotional
experience
created
(formless)
1st level of Reality
force of iterative
self-relation
rubber band
force of iterative
self-relation
Existence
Figure 12 On the left is depicted the progressive relational structuring of a rubber band into three
successive levels of rubber band reality as it is subjected to the force of iterative self-relation, and on the
right is depicted the progressive Relational Structuring of Existence into three successive levels of Reality
as it subjects Itself to the force of iterative self-relation. Each level is composed of what is there, i.e., the
rubber band or Existence, involved in a type of relation that is unique to that level. And as the relations
occurring to create each level of Reality are unique, the type of experiential boundary created and so
experience apprehended at each level of Reality is also unique. Thus, the unique relations of Existence to
Itself that occur in the construction of the first level of Reality produce an experiential boundary that the
Existence-Consciousness involved in those relations apprehends as emotional experience, while the
unique relations of Existence to Itself that occur in the construction of the second level of Reality produce
an experiential boundary that the Existence-Consciousness involved in those relations apprehends as
mental experience. And finally, the unique relations of Existence to Itself that occur in the construction of
the third level of Reality produce an experiential boundary that the Existence-Consciousness involved in
those relations apprehends as physical experience.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
28
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
However, it should be noted that the nature of the stratification of the Relational Structure of
Reality is not like the stratification we are used to, in as much as when we think of stratification
we tend to think of progressive layers that are stacked on top of each other. That is, in the types
of stratification we are used to, such as the stratification of the earth's layers or the rings of a tree,
there is spatial distance between the different stratified layers. And while this conceptualization
of the stratification of the Relational Structure of Reality has some validity, since in the
progressive construction of the Structure of Reality successive levels are built upon prior levels,
it is not accurately reflective of the actual nature of that stratification, as there is no spatial
distance between the different and so stratified layers or levels of Reality. That is, in physical
stratification, what exists in one layer is distinct from what exists in another layer, be it a more
proximal or distal layer, whereas in Existential stratification, what Exists in one layer or level of
Reality is not distinct from what Exists in the other layers or levels, since the more peripheral or
distal levels are actually composed of the more central or proximal levels. Specifically, the
second level of Reality is composed of the first level of Reality being in relation to Itself, while
the third level of Reality is composed of the second level of Reality, which also includes the first
level of Reality, being in relation to Itself.
Thus, the overall Relational Structure of Reality is stratified in a way that can be referred to as
single-point stratification, where the term "point" does not refer to a point in space, or a point
"in" anything, but rather refers to a point of Existence, i.e., a point of What Is Actually There. It
is owing to this single-point stratification of Reality that, although we ourselves are third level
Relational Structures, i.e., Organic Processes, composed of Existence that is being relation to
Itself in way that is unique to that level of Reality, we are also, at the same point of Existence,
both second and first level Relational Structures, and so are also composed of Existence that is
being relation to Itself in the ways that are unique to those levels of Reality. And it is for this
reason that we are able to create and apprehend all three types of experiential realities
simultaneously, i.e., emotional, mental, and physical, because we are, at the same point of
Existence, composed of and so simultaneously involved in all three levels of Existential selfrelation. And as the explanation of the basis of the phenomena that lie at the heart of quantum
theory will demonstrate, it is the relations of Existence to Itself that create what Existence,
functioning as Consciousness, apprehends as experiential reality in general and physical reality
in particular.
As shown in figure 12, the relations of Existence to Itself that occur in the construction of the
first level of Reality are termed relations of Existential flow, while the relations of Existence to
Itself that occur in the construction of the second level of Reality are termed interactive
relations, and finally, the relations of Existence to Itself that occur in the construction of third
level of Reality are termed impactive relations. It is the impactive relations occurring at the third
level of Reality, as second level Realities or Relational Structures become involved in a higher
order or more iterated relation, that create the experiential boundaries that the ExistenceConsciousness involved in those relations apprehends as physical experience or physical reality.
Therefore, it is these third level impactive relations and their experiential products that will now
be examined in detail in order to explain the nature of quantum reality, which is to say, explain
the behavior of physical reality at the quantum level, by using the model of Reality and reality
just described to explain the basis of wave-particle duality, quantum uncertainty, quantum nonlocality, the probabilistic nature of the wavefunction, and the collapse of the wavefunction, and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 01-29
29
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part I)
in so doing demonstrate that it is Consciousness that, through relation to Itself, creates physical
reality, and not the other way around.
1
http://bouman.chem.georgetown.edu/general/feynman.html
Gröblacher, S., Zeilinger, A. et al., An experimental test of non-local realism, Nature 446, 871-875 (19 April 2007)
3
Smetham, G. P., Consciousness as a Fundamental Dimension of Reality, Journal of Consciousness Exploration &
Research| July 2013 | Volume 4 | Issue 7 | pp. 743-779
4
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter Journal of
Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
5
Smetham, G. P., Quantum Entanglement, Consciousness & Evolution, Scientific GOD Journal | October 2013
Volume 4 | Issue 8 | pp. 576-599
6
Kaufman, S. E. Unified Reality Theory: The Evolution of Existence into Experience, Destiny Toad Press, 2001,
republished as series of four articles in Journal of Consciousness Exploration & Research| April 2011 | Vol. 2 |
Issue 3 | pp. 220-544
7
Kaufman, S. E. Existential Mechanics: How the Relations of Existence to Itself Create the Structure of Reality and
What We Experience as Reality, published as series of four articles in Journal of Consciousness Exploration &
Research| November 2011 |Vol. 2 | Issue 9 | pp. 1299-1384
8
Edmondson, A., A Fuller Explanation: The Synergetic Geometry of R Buckminster Fuller, EmergentWorld, 2009
9
Einstein, A., June 9, 1952, Note to the 15th edition of Relativity
2
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Comment on the paper “Quantum mechanics needs no consciousness”, by Yu
and Nikolic (2011)
Catherine M Reason
Correspondence: CMRneuro@Gmail.com
This is a brief comment on the paper "Quantum mechanics needs no consciousness"
by Shan Yu and Danko Nikolic [1]. Yu and Nikolic argue that the "consciousness
causes collapse hypothesis" interpretation of quantum mechanics, or CCCH, can be
falsified by a particular experimental setup. This claim is incorrect and the cause of
the error appears to be a confusion over where and when a collapse can be assumed to
occur.
The apparatus described by Yu and Nikolic is a stripped down modification of the
Delayed Choice Quantum Eraser experiment designed by Kim et al [2]. In the Yu and
Nikolic setup the interferometer arrangement on the idler side of the DCQE apparatus
is removed, with the resulting setup as follows. Single photons from a laser pass
through a double slit and are put into a superposition of paths. Each path hits a
particular region on a non-linear BBO crystal and produces an entangled pair of
photons by parametric down conversion. One photon from each pair, the signal
photon, is directed through a lens to a detector D0 which moves through the focal
plane of the lens. The other photon from each pair, the idler photon, is either detected
independently by a detector whose position is correlated with slit position, or allowed
to disappear into the distance. (For a fuller explanation and diagram of the
experimental setup, please consult [1].)
It is clear that under such circumstances the rules of quantum mechanics predict that
no interference pattern will be found at the signal detector site D0, and this the authors
acknowledge. Nonetheless the authors also claim the CCCH predicts that an
interference pattern should be found at D0, and the absence of such interference is
claimed to falsify the CCCH. Yu and Nikolic are not entirely clear in their paper
what sort of interference they expect; De Barros and Oas [3] point out that the DCQE
apparatus is a fourth-order interference setup, which requires coincidence counting
between the idler and signal detections to detect interference They also point out that
the particular setup proposed by Yu and Nikolic does not actually produce fourthorder interference. Correspondence with Dr Yu has confirmed to me that the
interference pattern he and Dr Nikolic are referring to is however a second-order
interference pattern ( or "standard Young's double-slit interference") which would be
detectable without coincidence-counting between idler and signal detections.
This is all rather puzzling and I have recently undertaken a somewhat extensive
correspondence with Dr Shan Yu to try and clarify the matter. In particular, why are
the authors claiming that the CCCH should predict something so at odds with the
basic rules of quantum mechanics? The crux of the problem seems to be Dr Yu's
belief that the very existence of "which-path" information in a quantum system, and
the concomitant lack of interference, is itself a definitive indicator of wavefunction
collapse (personal communication). In what follows I hope to show that this belief is
erroneous for quite simple and straightforward reasons.
In order to do so it is necessary to look a little more closely at the role played by
wavefunction collapse in those interpretations of quantum mechanics which
incorporate it. Yu and Nikolic correctly point out that the wavefunction collapse is
postulated in order to reduce a physical state which can be represented as a
superposition of eigenstates in some basis to a single eigenstate. Empirically,
however, it is not always so easy to distinguish between pure states and statistical
mixtures -- that is to say, between physical states which are quantum superpositions
on the one hand, and physical states which are mixtures of well-defined classical
states on the other. In practice, one tends to distinguish between the two by the
presence or absence of interference effects. If we denote the two photons in the
Yu/Nikolic setup by a and b, and the two slit-positions by L and R, then the
wavefunction of the two-photon system can be written in terms of:
|aL>|bL> + |aR>|bR>
If the system is fully entangled (as it is in the Yu and Nikolic setup) then the terms in
the superposition are clearly orthogonal, and hence there will be no second-order
interference at D0. However the system remains technically a superposition, since the
wavefunction will itself be an eigenstate of some observable which could, in
principle, be measured [4]; and such a measurement would reveal an interference
effect.
The first point to note here is that the second-order interference pattern disappears at
D0 whether or not one assumes a collapse has taken place, since the basic unitary
evolution of the wavefunction is sufficient by itself to eliminate the interference --
wavefunction collapse is not necessary to do this. The second point to make is that,
even if one endorses an interpretation of quantum mechanics which incorporates
wavefunction collapse, there is still no reason to assume that wavefunction collapse
has occurred at this point in the evolution of the system, since the particular
measurement which would distinguish between a pure state and a statistical mixture
has not yet been made (and indeed, such a measurement will become impractical once
the wavefunction has become entangled with the environment to such an extent that it
cannot be reproduced). Therefore it cannot be true to say, as Dr Yu has said to me
(personal communication) that the absence of second-order interference at D0 is the
definitive indicator of wavefunction collapse. The collapse, if it occurs at all, could
take place at any time prior to the conscious perception of some observable of the
entire system by some observer; and that entire system would include the two
photons, any measuring instruments, and possibly also the brains of the observers.
(This is because it is only the conscious perception of a single determinate state which
provides any evidence that a collapse has occurred at all.) The claims made by Yu
and Nikolic, that the CCCH predicts a second-order interference pattern at D0
whenever "which-path" information is available but not consciously observed, are
therefore unfounded. Their claim to have falsified the CCCH is therefore incorrect.
References
[1] S. Yu and D. Nikolic, Ann. Phys. (Berlin) 523 (11), 931-938 (2011).
[2] Y. Kim, R. Yu, S. P. Kulik, Y. Shih and M. O. Scully, Phys. Rev. Lett. 84, 1-5
(2000).
[3] J. A. de Barros and G. Oas (2017), Can we Falsify the Consciousness-CausesCollapse Hypothesis in Quantum Mechanics? forthcoming in Foundations of Physics.
Preprint at arXiv:1609.00614
[4] J. A. Barrett, Quantum Mechanics of Minds and Worlds, (Oxford Univ. Press,
Oxford,
(1999). |
arXiv:2209.02414v3 [cs.AI] 1 Mar 2023
F ROM S MART S ENSING TO C ONSCIOUSNESS : A N
INFO - STRUCTURAL MODEL OF COMPUTATIONAL
CONSCIOUSNESS FOR NON - INTERACTING AGENTS
Gerardo Iovane
Department of Computer Science
University of Salerno
Fisciano, Italy
giovane@unisa.it
Riccardo Emanuele Landi
Rigenera S.r.l.
Rome, Italy
riccardo.landi@rigenera2020.it
A BSTRACT
This study proposes a model of computational consciousness for non-interacting agents. The phenomenon of interest was assumed as sequentially dependent on the cognitive tasks of sensation,
perception, emotion, affection, attention, awareness, and consciousness. Starting from the Smart
Sensing prodromal study, the cognitive layers associated with the processes of attention, awareness,
and consciousness were formally defined and tested together with the other processes concerning
sensation, perception, emotion, and affection. The output of the model consists of an index that
synthesizes the energetic and entropic contributions of consciousness from a computationally moral
perspective. Attention was modeled through a bottom-up approach, while awareness and consciousness by distinguishing environment from subjective cognitive processes. By testing the solution on
visual stimuli eliciting the emotions of happiness, anger, fear, surprise, contempt, sadness, disgust,
and the neutral state, it was found that the proposed model is concordant with the scientific evidence
concerning covert attention. Comparable results were also obtained regarding studies investigating
awareness as a consequence of visual stimuli repetition, as well as those investigating moral judgments to visual stimuli eliciting disgust and sadness. The solution represents a novel approach for
defining computational consciousness through artificial emotional activity and morality.
Keywords artificial consciousness · attention · awareness · consciousness · decision support systems · cognitive
systems · artificial intelligence
1
Introduction
Artificial Consciousness (AC) is a branch of Artificial Intelligence that aims to build computational models inspired by
the functioning of human consciousness. In particular, rather than artificially reproducing the above phenomenon, the
goal is to constitute, or at least identify, consciousness-like processing to the machine. The related field of research is
mainly associated with computer science, but the modeling of human cognition permits enhancing the multidisciplinarity
of the results. AC is particularly important for designing novel methodologies and algorithms in the field of Artificial
Intelligence since the study of human cognition is significant for defining increasingly sophisticated cognitive systems.
Social robots or virtual agents need to reach suitable flexibility in interacting with human beings, both from an emotional
and behavioral point of view. In the context of human-machine interaction, the deployment of software solutions which
guarantee perceptual and emotional adaptation to the environment allows achieving significant results in terms of user
satisfaction [1, 2, 3].
The phenomenon of consciousness has never been defined precisely. Some scholars distinguish consciousness from
awareness, while others conceive the two concepts as synonyms; others, instead, describe the phenomenon in terms of
perception, emotion, and morality. Further difficulties arise from the fact that only a part of consciousness seems to
result in an objective functioning; most of what is conceived as “conscious experience” appear somehow subjective, i.e.,
dependent on personal judgments, feelings, or comparisons with others. The above observation requires constructing
computational models of consciousness that possibly lack generality since there seems to be the necessity of introducing
the element of subjectivity in the machine. The reproduction of the good and evil conception, i.e., the translation of
morality to the machine, represents one of the closest horizons towards which Artificial Intelligence is planning to
go beyond, but the vision of AC as “artificial morality,” to our knowledge, has not been explored sufficiently. This
is probably because research has been focused on proving the objective, rather than the subjective, functioning of
consciousness. Furthermore, while a lot of studies focus on the correlates between brain and consciousness, no suitable
investigation has been performed concerning the correlates between emotions and consciousness. For this reason,
the present study was intended to provide an interpretation for studying consciousness, rather than just proposing a
computational model. There is no intention, in any way, of trying to demonstrate the functioning of consciousness; the
present study should be considered as one of the admissible models which reductively explain certain mechanisms of
the phenomenon of interest. As it can be verified in the experimental Section of the present work, certain evidence
corresponded with the analyzes performed on human beings, while others did not.
The present study focuses on the definition and experimentation of a computational model of consciousness for noninteracting agents, i.e., for agents which merely observe, without carrying out actions towards the environment, with a
particular focus on subjectivity. It was decided to develop a model considering human cognitive tasks as a hierarchy
of layers involving the concepts of sensation, perception, emotion, affection, attention, awareness, and consciousness.
The model was founded on a previously conducted work [4], in which the authors indicated the research path and
modeled the first four cognitive layers (i.e., those associated with the concepts of sensation, perception, emotion, and
affection). Re-executing the prodromal solution, it was decided to model the cognitive layers associated with the
concepts of attention, awareness, and consciousness. The proposed model of computational consciousness was defined
with reference on the following assumptions: i) attention depends on sensations, perceptions, emotions, and affections,
and acts as a modulating factor for awareness to happen (i.e., without a suitable layer of attention, no awareness can
happen); ii) awareness is not the same concept as consciousness, since the former is implied in acquiring experiences,
while the latter in connecting and associating experiences with moral semantics; iii) consciousness depends on the
awareness and associates experiences with semantics through personal and social morality, which in turn depends on
the emotional activity.
The study is structured as follows. Section 2 presents a theoretical background on the studies concerning the phenomenon
of consciousness, highlighting which, to our opinion, are the most important studies, definitions, and horizons in the
research scenario, as well as the key concepts deployed for commenting on our modeling choices and experimental
results. In Section 3 the latest advancements in AC are mentioned and the context in which it was intended to provide our
contributions is indicated, while in Section 4 the prodromal study based on which the proposed model of computational
consciousness was developed and experimented is described. Section 5 is reserved for the formal definition of the
proposed solution concerning the cognitive tasks of attention, awareness, and consciousness, while Section 6 describes
the results obtained by experimenting the solution through a dataset of visual stimuli. Finally, in Section 7 the achieved
results are discussed and compared with the scientific evidence in the studies of consciousness, while in Section 8 the
conclusions are drawn and future work is indicated.
2
Consciousness: a theoretical background
Consciousness is a complex phenomenon addressed for years, from a multidisciplinary point of view, by many branches
of research, such as, e.g., Phenomenology, Philosophy of mind, Neuroscience, and Psychology. An exhaustive synthesis
of the scientific debate on the subject of consciousness is difficult to provide and is out of the purpose of the present
study. The dissertation is limited to mentioning the theories that, to our knowledge, enhance the most important aspects
of the phenomenon. Further hints on scientific evidence are supplied in Sections 5 and 7, in which the proposed model
of computational consciousness is defined and its results are compared with those identified by further studies involving
human beings, respectively.
Consciousness is often dyadically declined as objective and subjective: the first indicates states of awareness related
to objective stimuli, i.e., instances of the reality acquired consciously and not affected by subjective factors, such as
judgments or feelings; the second may be intended as awareness of objective stimuli from a subjective point of view,
e.g., associating perceived stimuli to personal judgments or feelings. A different categorization is that concerning
phenomenal and access consciousness [5]: the first refers to the cognition reserved for raw experiences of the body,
such as sensations, movements, and emotions, also called qualia; the second indicates the processing of information
acquired from the environment through language, reasoning, and personal evaluation.
In Neuroscience, studies concerning the correlates of brain activity with a subject’s reported experiences, also called
the neural correlates of consciousness, play a fundamental role. The aforementioned investigations mainly employ
EEG (Electroencephalography) and fMRI (Functional Magnetic Resonance Imaging) to analyze the subject’s brain
2
activity. The correlation of physical and mental processes, which investigation was often called “the hard problem
of consciousness,” [6] has not been proved yet. Neuroscience tries to explain the functioning of consciousness in
terms of neuronal effects, but exhaustive evidence is still missing; for instance, the issue of binding neural activity
to the experience of consciousness has not been solved yet [7]. Graziano and Kastner [8] supported the thesis for
which consciousness would function through the mechanisms of social perception. They consider the phenomenon of
consciousness as the perception of the awareness of an external subject to a stimulus; this process, rather than taking
place outside, would take place inside the mind. However, the correlation between consciousness and the areas of
the brain associated with social perception considered by the authors, i.e., superior temporal polysensory area and
temporoparietal junction, is still debated as an exhaustive explanation of the phenomenon. Other discussed theories are
those of the holonomic brain [9] and Orch-OR [10] theories, which try to explain consciousness in terms of quantum
neuronal effects.
A theory for describing consciousness in terms of quantity and quality was provided by Tononi [11]. With the
Information Integration Theory, the author proposed to describe consciousness as the capacity of a system to integrate
information. In particular, the author defined the quantity of consciousness as the information integration φ, i.e., the
effective information of the minimum information bipartition of a complex. In this context, the complex represents
a subset characterized by φ > 0 that is not part of a subset characterized by higher φ. The quality of consciousness,
instead, was modeled as the informational relationships among the elements of a complex, i.e., the related effective
information matrix. Starting from phenomenological analysis, Tononi provided evidence for the theory by comparing
the related model with neuroscientific results.
Psychological studies provided evidence in the general mechanisms of consciousness by employing experimental
methodologies, such as response priming and verbal reports. Unfortunately, experimental approaches which try to
find the general functioning of the phenomenon failed in explaining the subjective effects. Explaining consciousness
exclusively through general effects in the species can lead to the description of a philosophical zombie, rather than of
a human being. Evidence for this thesis was provided by Haggard [12], who found that human beings often report
experiences that do not correspond to their actual behavior or brain activity.
In Medicine, the phenomenon is often associated with the concept of attention, as a measure of the subject’s responsiveness, by giving to consciousness the general meaning of measuring cognitive abilities. In the present study,
stimuli altering states of consciousness were not considered, since it was intended to investigate, from a computational
perspective, the essential characteristics of the phenomenon.
To propose a model of computational consciousness, the concepts of objective/subjective and phenomenal/access
consciousness seem fundamental, as they categorize the features of the phenomenon, even though at a high layer, with
suitable consistency. Even though Neuroscience provides important insights regarding the neural activity of cognition,
psychological studies focus on acquiring human experiences, describing consciousness with suitable abstraction
from the brain. Therefore, the present study was intended to focus on the attempt of mathematical modeling some
psychological mechanisms of the phenomenon, accepting the categories of objective/subjective and phenomenal/access
consciousness, as well as the perspective proposed by Graziano and Kastner [8], which conceive the process in terms of
social perception. Concerning the assumption of consciousness as information integration, the present work considers
Tononi’s theory as consistent with the proposed model. In fact, as it can be evaluated in Section 4, the present work
conceives consciousness as the capacity of a system to connect a given experience with all the other previously acquired
experiences, by employing, to make a comparison with the Integration Information Theory, a sort of integration.
3
Related work
One of the most relevant consciousness-inspired computational models of cognition is LIDA (Learning Intelligent
Decision Agent) [13, 14]. The system is based on the Global Workspace Theory (GWT) [15], which is a theory
of consciousness considering a working memory of perceptual, evaluative, and attentional contents for activating
computational conscious and unconscious processes. Unconscious cognition competes to access a Global Workspace
for entering consciousness; then, the relevant information is broadcast to motor systems to perform actions. At a given
instant, the event the agent attends is processed in parallel by specialized modules; conscious information is globally
available by the whole set of cognitive functions.
The GWT framework was recently adopted by Huang, Chella, and Cangelosi [16], which proposed a general model of
computational consciousness based on top-down and bottom-up attention mechanisms (see Section 5.1) as criteria to
access the Global Workspace. The authors assumed that not all the specialized modules of cognition are necessary
for achieving consciousness, proposing a subdivision of the Global Workspace into separated nodes. By adopting
convolutional neural networks for the visual and auditory stimuli acquisition and recurrent neural networks for action
generation, they provided evidence for the machine to reproduce the attentional shift [17] and blinking [18] effects,
3
together with the lag-1 sparing [19]. The experiments were conducted on simple visual and auditory stimuli, accounting
for the above three fundamental phenomena of objective consciousness. The authors proposed their solution as a
starting point for building further cognitive processes concerning subjective mechanisms of consciousness, such as
emotional activity and short-term memory.
Lewis [20] focused the modeling of computational consciousness on the concept of morality, proposing a mathematical
tool based on the rough set theory and the Riemannian covariance matrix. It revealed possible to acquire data for
extracting classifiers across many dimensions involving human moral behavior. As described by the author, an
example of space involving significant dimensions is the plane in which the axes are moral act and loving environment,
representing the covariance between positive and negative actions to environments. The relationship between positive
and negative semantics of human behavior can be studied through rough set dimensions concerning the consciousness
of a person or community.
The above solutions provided significant results for developing machine consciousness, but, to our knowledge, no
suitable investigation has been conducted in AC concerning the functioning of consciousness as dependent on the
relationship between emotional activity and morality. In the present study, emotions were considered fundamental
for modeling consciousness; thus, important subjective mechanisms of machine consciousness can be obtained by
introducing artificial emotional activity. As in the work conducted by Huang et al. [16], attention is assumed as a
significant modulating factor for consciousness to happen. Similar to LIDA, the present study focuses on the integration
of different parts of human cognition, but the correspondence between sensory stimuli acquisition and consciousness is
assumed sequential, rather than parallel, i.e. cognitive tasks are executed sequentially.
4
Background and assumptions
The present study is based on a computational model of artificial cognition, mainly focused on the artificial reproduction
of human emotional activity, which is called Smart Sensing [4]. The model was built by empirically assuming that
human intelligence can be mathematically modeled as a hierarchy of cognitive layers concerning the concepts of
sensation, perception, emotion, affection, attention, awareness, and consciousness. Figure 2 shows a qualitative
representation of the reference model in which the arrow symbol indicates a direct dependence between two cognitive
layers. In the prodromal study [4], the authors specified a linguistic distinction between the concept of human cognitive
layer and its relative artificial representation using mention with the initial capital letter (e.g., calling sensation the
human sensation, while Sensation its modeled version); in the present study, it was decided to deploy the same linguistic
artifice to keep the discussion clearer.
Smart Sensing includes the modeling of the cognitive layers of Sensation, Perception, Emotion, and Affection, proposing
the cognitive layers of Attention, Awareness, and Consciousness as future developments. The model acquires visual
stimuli in the form of images through a convolutional neural network to produce, at each discrete time instant n, the
cognitive instances r1,n , r2,n , r3,n , and r4,n associated with the cognitive layers of Sensation, Perception, Emotion, and
Affection, respectively.
The Sensation cognitive instance r1,n ∈ R1×k is defined as
T1
t−n
e− n − e− n
r1,n = D1 (n, m1,n , xn , t) = k1,n α1 thrH (xn )
+
β
m
1 1,n ,
T1
1 − e− n
tb < n =⇒ D1 (n, m1,n , xn , tb ) = 0
tb > n + T1 =⇒ D1 (n, m1,n , xn , tb ) = 0
D1 (nf , m1,nf , xnf , n)
..
.
m1,n = D1 (ng , m1,ng , xng , n)
..
.
D1 (nh , m1,nh , xnh , n)
n ∈ N,
n ∈ N,
(1)
(2)
(3)
nf < ng < nh < n ∈ N,
(4)
where xn ∈ R1×k is the input at the instant n, while T1 > 0, α1 ∈ R1×k , and β1 ∈ R1×l are the removal period, the
weights of the current input, and the weights of the memory m1,n ∈ Rl×1 of the Sensation cognitive layer, respectively,
4
with k the input dimensions and l = nh − nf + 1 the number of elements in the memory. The function D1 represents
the trend through which the cognitive instances decay exponentially with the time t. The thrH (·) function sets to zero
all the components of the input xn that are lower than the threshold H. Finally, it holds that k1,n = r2,n−1 r5,n−1 ,
where r2,n−1 ∈ R1×k and r5,n−1 ∈ R1×k represent the Perception and Attention cognitive instances at the instant
n − 1, respectively.
The Perception, Emotion, and Affection cognitive instances, i.e., the instances ri,n ∈ R1×k , with i ∈ {2, 3, 4}, are
defined as
ri,n = Di (n, mi,n , xn , t) = ki,n Ai
αi xn
βi mi,n
−
t
+
0i ,
t
t2
(5)
αi xn + βi mi,n
Ai = α x
,
βi mi,n
i n
− t0i
t +
t2
(6)
αi xn
βi mi,n
,
+
t + Ti
(t + Ti )2
(7)
t0i =
Di (nf , mi,nf , xnf , n)
..
.
mi,n = Di (ng , mi,ng , xng , n)
..
.
Di (nh , mi,nh , xnh , n)
nf < ng < nh < n ∈ N,
(8)
where xn is the input at the instant n, while Ti > 0, αi ∈ R1×k , and βi ∈ R1×l , are the removal period, the weights of
the current input, and the weights of the memory mi,n ∈ Rl×1 of the i-th cognitive layer, respectively, with i ∈ {2, 3, 4},
k the input dimensions, and l = nh − nf + 1 the number of elements in the i-th memory. The function Di represents
the trend through which the cognitive instances decay polynomially with the time instance n. Finally, it holds that
k2,n = k4,n = j, with j ∈ R1×k representing a unitary vector, while k3,n = r4,n−1 , where r4,n−1 ∈ R1×k is the
Affection cognitive instance at the instant n − 1.
Each i-th cognitive layer, with i ∈ {1, 2, 3, 4}, computes the instances by considering its own memory mi,n , called
the cognitive memory. Sensation’s cognitive memory m1,n is characterized by an exponential decay function, while
the memories m2,n , m3,n , and m4,n associated with the cognitive layers of Perception, Emotion, and Affection are
described polynomially. These memories consist in time windows storing decaying cognitive instances to reproduce the
concept of short-term memory artificially. Each cognitive instance decreases in its relevance in the function of the time
n to a predefined removal period Ti , i.e., with respect to the time interval in which a cognitive instance is stored in the
relative memory.
To associate the cognitive instances provided by the Emotion with the classes of happiness, anger, fear, surprise,
contempt, sadness, disgust, and the neutral state, the authors trained a learner on three different episodes depicting
visual scenes eliciting happiness (i.e., “beautiful woman” and “own home”), anger (i.e., “murder of animal”), fear (i.e.,
“war,” “man pointing weapon,” and “terrorism”), surprise (i.e., “crazy sportsman”), contempt (i.e., “politician” and
“parking car”), sadness (i.e., “someone’s death or sick” and “car accident”), disgust (i.e., “injury” and “autopsy”), and
the neutral state (i.e., “landscape”).
For the training of the learner, the authors associated the Emotion cognitive instance at the discrete time n with a
pre-defined emotional class in the dataset. For instance, in the case the stimuli at the time instants n − 2, n − 1, and n
are “murder of animal” (labeled with anger), “war” (labeled with fear), and “crazy sportsman” (labeled with surprise),
respectively, the emotional class associated with the instant n will be the surprise. However, the above orientation
of the model is not mandatory and it depends on the emotional history it was intended to provide to the agent. The
classification of Emotion cognitive instances introduces an element of emotional subjectivity in the model.
During experimentation, by adopting VGG16 [21] pre-trained on ImageNet [22] for feature extraction and XGBoost
[23] as the learner for associating Emotion cognitive instances to the emotional classes and the neutral state, the authors
achieved 85% accuracy on a custom dataset composed of 612 images, of which the 80% was employed for the training
phase. To provide some instances of the above dataset, Figure 1 shows some of the images employed for training the
learner.
5
Figure 1: Some of the images employed in the custom dataset for training the learner.
Subsequently, by evaluating the model on different episodes (the process of emotional activity, as called by the authors),
they found a lowering in the accuracy score as the α3 weights of the Emotion cognitive instance increased in magnitude
[4]. The same evaluation provided an increase in the accuracy score as the α3 weights decreased towards zero. The
above test proved that Smart Sensing reproduces certain phenomena of human emotional activity, artificially. Similar to
a human being, the agent evaluates an emotional history, i.e., a series of stimulus-emotion associations which leverage
emotional activity concerning different episodes of stimuli. The model represents an extreme reduction of human
cognition, but it allows to reach, as described in the prodromal study, a coherent approximation of the evidence found in
the area of Cognitive Psychology and Neuroscience. In their work, the authors compared the functioning of the model
with the related experimental evidence involving human beings.
The present study continues the development of the above proposed model of computational consciousness by reevaluating the Smart Sensing and modeling the cognitive layers of Attention, Awareness, and Consciousness.
5
Proposed model of computational consciousness
The proposed model acquires sensory stimuli by sampling occurrences from the environment as a consequence of
evaluating the visual artificial channel. As shown in Figure 2, the feature vector fn ∈ R1×k , with k the input dimensions,
is processed through a hierarchy of seven cognitive layers, i.e., Sensation, Perception, Emotion, Affection, Attention,
Awareness, and Consciousness, which compute cognitive instances and pass temporary results to other cognitive layers.
The dependencies concerning cognitive layers can be listed as follows.
• Sensation depends on Attention and Perception: as the cognitive instances of Attention increase in magnitude,
the model acquires sensory occurrences more intensely; as the cognitive instances of Perception increase in
magnitude, the model provides higher significance to the acquired stimuli.
• Perception depends on Sensation: to produce cognitive instances, Perception acquires temporary results from
the Sensation cognitive layer.
• Emotion depends on Perception and Affection: to produce cognitive instances, Emotion acquires temporary
results from Perception and provides higher significance to the produced cognitive instances as Affection
increases in magnitude.
• Affection depends on Emotion: to produce cognitive instances, Affection acquires temporary results from the
Emotion cognitive layer.
• Attention depends on Sensation, Perception, Emotion, and Affection: to produce cognitive instances, Attention
acquires temporary results from the Sensation, Perception, and Affection cognitive layers, while the probability
vector en ∈ [0, 1]1×Ce related to the classification of the current Emotion cognitive instance from a learner,
with Ce the quantity of considered emotional classes.
6
Encoder
fn
1
r1,n
r2,n
2
r1,n
Sensation
Perception
r2,n
r2,n
3
r3,n
Emotion
r3,n
r4,n
r5,n
4
Learner
Affection
en
r4,n
5
Attention
r5,n
6
Awareness
r6,n
7
Consciousness
r7,n
Figure 2: A qualitative representation of the proposed model of computational consciousness.
• Awareness depends on Attention and observes Sensation, Perception, Emotion, and Affection cognitive
instances: to produce cognitive instances, Awareness acquires temporary results from Attention and state
representations of Sensation, Perception, Emotion, and Affection cognitive layers.
• Consciousness depends on Awareness and connects Sensation, Perception, Emotion, and Affection cognitive
instances: to produce cognitive instances, Consciousness acquires temporary results from Awareness and
connects state representations of Sensation, Perception, Emotion, and Affection through semantics produced
from classifications of Emotion cognitive instances provided by a learner.
As explained in Section 5.1, the Attention cognitive layer was assumed as dependent directly on Sensation, Perception,
and Affection, since it processes cognitive instances, while it depends on Emotion through the classifications of cognitive
instances provided by the deployed learner.
Awareness was assumed as dependent directly on the Attention to represent the feature suggested by Huang et al.
[16], for which the process of awareness depends on attention, while not dependent directly on Sensation, Perception,
Emotion, and Affection. Awareness does not process cognitive instances but states representations concerning the
whole set of cognitive layers preceding Attention. As it can be verified in Section 5.2, the representation above is the
information fusion of probability, plausibility, credibility, and possibility scores associated with the current processing
stimuli. This feature was introduced to highlight the value of the intuition provided by Graziano and Kastner [8], which
assume the awareness as the perception of an entity which is, in turn, aware of stimuli acquired from the environment
and body. To make a comparison with our proposal of a computational model of consciousness, the Awareness cognitive
layer processes a stimulus by objectifying the Sensation, Perception, Emotion, and Affection cognitive instances, i.e.,
by perceiving them as external, through the evaluation of state representations.
Finally, Consciousness was assumed as dependent directly on Awareness but indirectly on Sensation, Perception,
Emotion, and Affection. This cognitive layer connects the state representations provided by the Awareness and
associates them with moral semantics which depend on the classifications of Emotion cognitive instances provided
by the deployed learner. As it can be verified in Section 5.3, the connection of states representations provided by the
Awareness cognitive layer, together with the related semantics associations, was modeled through the adjacency matrix
of a graph.
7
Under the above assumptions, the following Sections describe the part of the model concerning cognitive layers of
Attention, Awareness, and Consciousness.
5.1
Attention
Through sensations, the human being confronts reality with the continuous perception of stimuli, which are subjected
to selection based on their importance. In particular, when listening to an interesting lesson, the visual and auditory
systems focus on capturing the information that comes from the outside, making the understanding of the proposed
contents easier. The above process is called attention, which can be defined as the cognitive process of selecting the
stimuli received through the five senses, or as the ability to focus on specific information coming from the environment
or the body. Attention is often intended as the efficient management of cognitive resources, as the brain would be
characterized by a limited capacity to process all the information at a given time. This definition is not far from the
concept of inattentional blindness related to visual attention, which considers the physical inability to process all the
information coming from the environment. In fact, at any time, the human being misses a substantial part of the visual
world [24].
Visual attention can be declined into covert and overt. The first refers to the act of processing a given stimulus without
moving the eyes, while the second concerns the action of selectively focusing on a particular position of interest [25].
In overt attention, the distinction between reflexive and controlled eye movements is significant: reflexive attention is
characterized by the involuntary focus following a stimulus of particular relevance, while controlled attention employs
the voluntary selection of a visual stimulus. More generally, an attention process affected exclusively by external factors
is often called bottom-up attention, while that determined by internal factors, intended as prior acquired knowledge, is
often called top-down attention [26]. Similar to the definition of overt attention is the selective attention, which consists
of focusing on a part, while neglecting the rest, of a stimulus of interest. This definition is also used in association with
the sensory sources different than the visual channel, such as the auditory perception [27]. The attention involves all the
senses, including touch [28], taste, and smell [29]; the overall attention of a subject can be considered as a combination
of focuses on different sensory channels.
The above cognitive process was proved to be dependent on emotions, as it depends on the affective reaction elicited by
a stimulus [30, 31]. Attention was found also dependent on the culture, as proved by Chavajay and Rogoff [32], but the
present study wanted to focus on the general characteristics only.
Focusing on the visual sensation, Attention can be considered as a mind cognitive process that allows to select or
ignore environmental stimuli. Therefore, the related cognitive instance r5,n ∈ [0, 1]1×1 is dependent on time and on the
cognitive matrix Acn ∈ [0, 1]4×k . Formally,
r5,n = ten(Acn ),
(9)
with
s̊n
a11n
p̊n a21n
Acn = =
Es
a31n
a41n
ån
...
...
...
...
s̊n =
r1,n
,
Sb
p̊n =
r2,n
,
Pb
a1kn
a2kn
,
a3kn
a4kn
ån =
max { max {aijn }} +
j∈{1,...,k} i∈{1,...,4}
ten(Acn ) =
2
(10)
r4,n
,
Ab
Pk
i=1
j=1 aijn
Hc =1
(11)
P4
,
(12)
where ten(·) is called the tension function. The vector Es ∈ [0, 1]1×k contains the probability vector en provided by
the learner, i.e., the relative probabilities associated with the classification of the Emotion cognitive instance at the
discrete time n, zero-padded with k − Ce elements. Vectorss̊n , p̊n , and ån are the normalized versions of the Sensation,
Perception, and Affection cognitive instances. Quantities Sb , Pb , and Ab are the upper bounds that the components
of the Sensation, Perception, and Affection cognitive instances can reach, respectively. Finally, the Hc parameter
represents a saturation threshold; since Acn is a matrix defined in [0, 1]4×k , the bound Hc = 1 was chosen.
The cognitive layer of Attention processes the normalized distributions of cognitive instances to provide the related
tension. For instance, in the case the agent receives a sensory impulse, i.e., when the cognitive matrix provides, except
8
for a single component close to 1, all equally distributed, and close to zero, occurrences, the magnitude of the Attention
cognitive instance increases accordingly. The above model can be compared with the category of bottom-up attention.
5.2
Awareness
Awareness represents that layer of cognition through which a human being acquires experience of him/herself and the
surrounding environment. Many use the term “awareness” as a synonym for consciousness, intending awareness as
“becoming conscious” of something. However, the present study considers the above assumption is not necessarily true,
as consciousness would represent the process that associates awareness to moral semantics. One can be aware of an
event, such as the breaking of a glass or the sound of the breath, without attributing meanings to these stimuli. In the
present study, it was assumed that acquired stimuli become associated with semantics only through consciousness. The
phenomenon of awareness can be conceived as the acquisition of experiences that come from the outside, such as the
perception of a sensation, or the inside, as an emotion [33]. Awareness seems to be a sort of cognitive relevance of a
human’s sensory, perceptive, emotional, and affective experience. Consciousness, on the other hand, would consist in
the association of the aforementioned experiences with positive, negative, or neutral moral semantics.
Awareness can be conceived as the cognitive reaction to the occurrence of certain conditions or given events. It was
assumed as a function of time and the Attention cognitive layer. In the case the stimuli are exclusively internal, the
awareness is regarded as “self-awareness” or “subjective awareness” since, for instance, a subject can be aware of
something under subconscious perspective, i.e., gaining awareness through internal states, visceral sensations, or
sensory perceptions related to the external events. The above faculty seems to be related to the comprehension of
environmental and subjective events in terms of intensity. The Environment Awareness can be conceived under the
statement “I know,” while the Subjective Awareness with the statement “I am.” Consciousness, instead, seems to be a
“deeper” layer of awareness enriched by the semantics of social and personal morality. The Environment Consciousness
can be synthesized with the statement “I evaluate,” while the Subjective Consciousness with the statement “I am me.”
Awareness was modeled as the cognitive layer that provides the agent with objective knowledge about external and
subjective events. Consciousness was assumed to be activated after the processing of the above pool of knowledge to
enrich the Awareness cognitive instances with critical evaluations. Under the above hypotheses, it was possible to base
the modeling of Awareness and Consciousness by adopting the following scheme:
I know
=⇒
I am
=⇒
Environment Awareness
Subjective Awareness
I evaluate
Environment Consciousness
I am me
.
Subjective Consciousness
In the proposed model, Environment Awareness was associated with the knowledge, analysis, and inference concerning
the occurrence of external events; more specifically, Sensation and Perception cognitive instances represent the
knowledge acquired by the agent. Subjective Awareness, instead, was associated with the knowledge related to
subjective events; in this case, Emotion and Affection cognitive instances represent the knowledge acquired by the
agent.
The theory of decision and reasoning in info-incompleteness conditions [34] was adopted for modeling the influence
of others (humans or agents) on personal opinions or experiences. It was possible to describe the Awareness in terms
of probability, plausibility, credibility, and possibility associated with Sensation, Perception, Emotion, and Affection
cognitive instances. This approach introduces into the model the awareness that the agent can reach as a consequence
of an external suggestion, i.e., awareness that does not depend on direct experience (plausibility, credibility, and
possibility scores, in the model). For instance, the artificial agent can acquire awareness either by directly processing
the occurrences of a given event or by extracting information from the experiences of other agents or human beings.
Additional Sensation, Perception, Emotion, and Affection cognitive instances, together with the relative plausibility,
credibility, and possibility scores can be acquired by the agent as a consequence of the interaction with the environment.
Hence, at the instant n, for each cognitive instance ri,n , with i ∈ {1, 2, 3, 4}, the agent computes the distributions
P r(ri,n ) : R1×k → [0, 1],
(13)
P l(ri,n ) : R1×k → [0, 1],
(14)
Cr(ri,n ) : R1×k → [0, 1],
(15)
9
P o(ri,n ) : R1×k → [0, 1],
(16)
where P r(ri,n ), P l(ri,n ), Cr(ri,n ) and P o(ri,n ) are, respectively, the probability, plausibility, credibility, and possibility related to a given cognitive instance ri,n at the discrete instant n.
The information fusion of the above distributions provides the expectation function
P r(ri,n ) if 0.05 ≤ P r(ri,n ) ≤ 1.00,
(P r(ri,n ) + w1,i P l(ri,n ))/2 if 0.01 < P r(ri,n ) ≤ 0.05,
Oi (n) =
(P r(ri,n ) + w1,i P l(ri,n ) + w2,i Cr(ri,n ))/3 if 0.005 < P r(ri,n ) ≤ 0.01,
(P r(ri,n ) + w1,i P l(ri,n ) + w2,i Cr(ri,n ) + w3,i P o(ri,n ))/4 if P r(ri,n ) < 0.005,
(17)
where wj,i ∈ [0, 1], with j = {1, 2, 3}, are the weights related, respectively, to the plausibility, credibility, and
possibility associated with the i-th cognitive layer.
Cognitive instances probabilities are computed through a frequentist approach, i.e., by counting the occurrences of a
given instance in the function of time. Since similar sensory stimuli can result in non-stackable cognitive instances, it
was useful to support the above process by means of similarity measures. At each step, for each cognitive layer of the
Smart Sensing, the Awareness computes the Euclidean distance between the current acquired cognitive instance and all
the previously captured occurrences. Then, the counter associated with the current cognitive instance is incremented
only in the case the above distance results greater than or equal to a predefined threshold R. Formally,
C(ri,n ) = C(ri,m ) + 1 ↔ ∃ ri,m ∈ Mi,n−1 : 0 ≤ d(ri,n , ri,m ) ≤ R,
C(ri,n ) = 1 otherwise,
(18)
where
P r(ri,n ) =
C(ri,n )
,
Cn
(19)
with m < n ∈ N, R > 0 the reference distance threshold, Cn the count of the cognitive instances at the instant n, and
Mi,n−1 the set of the reference cognitive instances acquired up to the instant n − 1, i.e., all the instances which counters
are greater than or equal to 1. The terms C(ri,n ) and C(ri,m ) are the counters related to the current and reference
cognitive instances, respectively. Finally, the term d(ri,n , ri,m ) represents the Euclidean distance between the above
instances.
Theoretically, cognitive instances plausibility was defined to be determined by experts’ opinions, credibility by
affectively relevant identities opinions, and possibility by sentiment analysis results. With this approach, the agent can
enrich its cognition even when it does not directly experience sensory stimuli or when the number of occurrences is not
suitably high.
Under the above hypotheses, the Awareness cognitive instance r6,n ∈ R1×1 was defined as the sum of the Environmental
and Subjective Awareness. Formally,
r6,n = k6,n (φ1 O1 (n) + φ2 O2 (n) + φ3 O3 (n) + φ4 O4 (n)),
{z
} |
{z
}
|
Environment Awareness
(20)
Subjective Awareness
where O1 (n), O2 (n), O3 (n), and O4 (n) are the Sensation, Perception, Emotion, and Affection expectation functions
and φ1 , φ2 , φ3 , and φ4 their related weights, all defined in R1×1 , respectively.
Awareness is supported by a geometrical model, in which the distribution of cognitive instances, as shown in Figure 3, is
encapsulated into hyperspheres, with ray R, in which the centres are the reference instances ri,m ∈ Mi,n−1 . Formally,
V̂ri,m = {ri,n ∈ AHi : 0 ≤ d(ri,n , ri,m ) ≤ R},
(21)
where AHi ∈ Rk is the Awareness Hyperspace associated with the i-th cognitive layer, with k the dimensions of
cognitive instances.
10
Awareness
Hypersphere 1
Awareness
Hypersphere 3
Awareness
Hypersphere 2
Lattice
Reference instance
Instance
Distance
Awareness
Hyperspace
Awareness
Hyperspace
Figure 3: On the left, a qualitative 2D representation of the Awareness Hyperspace; the centers of the hyperspheres
represent the reference cognitive instances ri,m ∈ Mi,n−1 and dotted lines their relative distances. On the right, a
qualitative 3D representation in the form of a lattice.
By assuming the hyperspheres as non-intersecting, it is possible to conceive the Awareness as similar to an amorphous
crystalline lattice in which the molecules are the hyperspheres themselves. In the proposed model, the intensity of
Awareness related to a given reference cognitive instance is considered at its maximum when the hypersphere becomes
completely, i.e., infinitely, full of instances.
5.3
Consciousness
In the present study, the phenomenon of consciousness was considered as the semantic processing of awareness.
Awareness was conceived as a cognitive process in which the experiences are acquired and distinguished, but not
connected and not associated with semantics; Consciousness links the acquired experiences and associates them with
semantics. Consciousness was not assumed as a process exclusively related to the acquisition of a stimulus, but
conceived also as a process connecting a stimulus with the other previously acquired stimuli. For simplicity, the
semantics of experiences, which in the present model were modeled as Awareness cognitive instances, can be interpreted
as positive, negative, and neutral. The semantics related to the environment are hypothesized as affected by the social
morality, i.e., the semantics that an agent learns from the external context; the semantics related to subjectivity are
assumed as affected by the personal morality, which in the present study are obtained from the emotional activity (e.g.,
when an experience elicits a negative emotion, like fear, the relative subjective semantic associated with that experience
is negative).
Consciousness was modeled as the sum of contributions concerning the entropy and energy of an undirected graph, called
the Consciousness Graph, in which the nodes are associated with semantics. Two types of graphs were conceived: the
first considers the Environment Awareness by deploying the hyperspheres in the Sensation and Perception Hyperspaces
as nodes; the second considers the Subjective Awareness by deploying the hyperspheres in the Emotion and Affection
Hyperspaces as nodes. Each hypersphere is represented through the relative reference instance, which union with a
semantic provides a social morality instance for the Environment Awareness, while a personal morality instance for
the Subjective Awareness. Entropy and energy represent two metrics of the complexity of information present in the
graphs, in terms of connections among reference cognitive instances and positivity, negativity, and neutrality of the
relative semantics. This approach permitted to model the consciousness of an experience as a relationship with other
experiences. Furthermore, the data structure of the graph permits also to find paths from a reference cognitive instance
to all the other reference cognitive instances.
Figure 4 shows a qualitative example of the above two types of graphs. As it can be seen, the environment semantics,
which are associated with the Sensation and Perception Consciousness Graphs can be different from the subjective
semantics, which are associated with the Emotion and Affection Consciousness Graphs.
The Consciousness Graph Gi is associated with an adjacency matrix Ji,n ∈ Rm×m , with m the quantity of reference
cognitive instances, i.e., the centers of hyperspheres, of generic element
gl,h =
Sl + Sh
d(ri,l , ri,h ),
2
11
(22)
Emotion/Affection
Consciousness Graph
Sensation/Perception
Consciousness Graph
PS
NE
PE
NeE
PS
NS
PS
PE
Reference instance
NeE
Environment semantics
NeS
NE
Subjective semantics
Social morality instance
NeS
Personal morality instance
Figure 4: A qualitative representation of the Sensation, Perception, Emotion, and Affection Consciousness Graphs.
NE , PE , and N eE represent the negative, positive, and neutral environment semantics, while NS , PS , and N eS the
negative, positive, and neutral subjective semantics.
where l and h are the indexes of the reference instances ri,l , ri,h ∈ Mi,n−1 concerning two adjacent nodes, with
Sl , Sh ∈ {−1, 0, 1} the related semantics. The term d(ri,l , ri,h ) in the equation represents the Euclidean distance
between two reference instances.
The Consciousness cognitive instance r7,n ∈ R1×1 depends directly on the Awareness and was defined as the sum of
the Environmental and Subjective Consciousness. Formally,
r7,n = k7,n (ψ1 Y1 (n) + ψ2 Y2 (n) + ψ3 Y3 (n) + ψ4 Y4 (n)),
|
{z
} |
{z
}
(23)
Yi (n) = d(Ai (0), Ai (n)),
(24)
Ai (n) = (H(Ji,n ), E(Ji,n )),
(25)
Ai (0) = (H(Ji,0 ), E(Ji,0 )),
(26)
Environment Consciousness
Subjective Consciousness
with
where Y1 (n), Y2 (n), Y3 (n), and Y4 (n) are the Sensation, Perception, Emotion, and Affection Consciousness intensities
and ψ1 , ψ2 , ψ3 , and ψ4 their related weights, all defined in R1×1 , respectively. The Consciousness intensity Yi (n)
of the i-th cognitive layer is computed through the Euclidean distance between the point Ai (n) and the origin of the
entropy-energy plane associated with the adjacency matrix Ji,n .
The Consciousness energy of the i-th cognitive layer was defined as
E(Ji,n ) =
X
|ḡl,h |,
(27)
l,h
where ḡl,h is the generic element of the normalized version of the adjacency matrix Ji,n . This quantity increases
proportionally to the distance between two reference instances and the positivity of their semantics in the related
hyperspace.
12
Table 1: Performance in classifying Emotion cognitive instances through FCNN.
Confusion matrix of Emotion cognitive instances classification
Neutral
Happiness
Anger
Fear
Surprise
Contempt
Sadness
Disgust
Neutral
Happiness
Anger
Fear
Surprise
Contempt
Sadness
Disgust
18
1
0
1
0
0
0
0
0
7
0
0
0
0
0
0
0
0
10
0
0
0
0
0
0
0
1
17
0
1
0
0
0
0
0
1
7
0
0
0
0
0
0
0
0
6
2
0
0
1
0
0
0
0
5
0
0
0
0
0
2
0
0
12
The Consciousness entropy of the i-th cognitive layer was defined as
H(Ji,n ) = −
X
ḡl,h log(ḡl,h ),
(28)
l,h
where ḡl,h is the generic element of the normalized version of the adjacency matrix Ji,n . This quantity decreases as
the graph increases its homogeneity in the distances between reference instances and in the discrepancy of the relative
semantics. The entropy also increases proportionally to the occurrences of neutral semantics, as stimuli eliciting neutral
emotions were considered as non-polarizing towards positivity or negativity.
The defined energy is a measure of how much the artificial agent is “conscious” of stimuli associated with positive
semantics, i.e., a measure of how the agent’s experiences are polarized towards positivity. The defined entropy, instead,
is a measure of how much the artificial agent is “conscious” of stimuli heterogeneously associated with different
semantics, i.e., a measure of how agent experiences are not polarized towards a specific semantic.
6
Experiments with visual stimuli
Cognitive layers of Attention, Awareness, and Consciousness were tested together with the Smart Sensing, i.e., with
the cognitive layers of Sensation, Perception, Emotion, and Affection. The custom dataset employed for the present
experimentation is the same adopted in the prodromal study. The Smart Sensing was re-executed by deploying, instead
of XGBoost, a Fully Connected Neural Network (FCNN) as the learner, coupled with the VGG16 [21] convolutional
network for feature extraction. A total of 611 and 92 images were considered for training and testing the proposed model
of computational consciousness. Regarding the Emotion cognitive layer, the new learner reached 89.13% accuracy
by considering the classes of anger, fear, happiness, surprise, contempt, sadness, disgust, and the neutral state, while
94.57% accuracy by considering the positive, negative, and neutral classes only (surprise and happiness were considered
as belonging to the set of positive emotions).
Table 1 summarizes the results achieved by deploying the FCNN as the learner for generating the emotional spectrum
Es at each time instant n. The network consisted of four dense layers of 64, 32, 16, and 8 units with ReLU activation,
coupled with dropouts set to a percentage of 30%. Optimization was performed through Adam at the learning rate of
10−3 , with a batch size of 64 samples per epoch. The percentages of emotions in the considered dataset are: 11% for
happiness, 11% for anger, 18% for fear, 11% for surprise, 6% for contempt, 6% for sadness, 16% for disgust, and 21%
for the neutral state.
Emotion cognitive instances were well classified, except for what regards the emotions of surprise and sadness,
which were misclassified four times. The suitability of the performance allowed us to test Attention, Awareness, and
Consciousness with better performance of the Smart Sensing (4.13% more accuracy, compared to the prodromal study).
Table 2 shows the values adopted for the plausibility, credibility, and possibility scores (i.e., the support in infoincompleteness) associated with the stimuli provided to the model. The values were chosen randomly, as a multi-agent
experimentation of the proposed model was not intended as an objective of the present study. Even though a simulation
of the model with support info-incompleteness was performed, the present study focuses on the definition and
experimentation of a model of computational consciousness for non-interacting agents.
13
Table 2: The plausibility, credibility, and possibility scores adopted for each stimulus in the experimentation concerning
the support in info-incompleteness.
Adopted scores for the support in info-incompleteness conditions
Stimulus
Plausibility (P l(ri,n ))
Credibility (Cr(ri,n ))
Possibility (P o(ri,n ))
Beautiful woman
Own home
Murder of animal
War
Man pointing weapon
Terrorism
Crazy sportsman
Politician
Parking car
Someone’s death or sick
Car accident
Injury
Autopsy
Landscape
0.2
0.9
0.8
0.3
0.6
0.1
0.7
0.9
0.9
0.2
0.5
0.9
0.1
0.9
0.6
0.8
0.6
0.9
0.8
0.8
0.2
0.9
0.8
0.4
0.8
0.7
0.3
0.9
0.4
0.5
0.8
0.2
0.5
0.5
0.9
0.9
0.9
0.6
0.7
0.4
0.6
0.8
Significance testing concerning the achieved results was performed through one-way ANOVA, of which 95% confidence
intervals, specified through mean and standard deviation (i.e., M (SD)), are shown in the tables; salient evidence is
highlighted in the text by specifying the F -score and p-value.
The Attention, Awareness, and Consciousness cognitive layers were experimented both on the training and test sets of
emotional episodes. The average of the components in cognitive instances r5,n and the percentage of Attention obtained
for each stimulus and emotional class were computed.
The Awareness cognitive layer was experimented with optimal R = 2007 both on the training and test sets regarding
the provided emotional episodes. Figure 5 shows a visual representation of the reference cognitive instances r1,m ,
r2,m , r3,m , r4,m , belonging to the sets M1,n−1 , M2,n−1 , M3,n−1 , M4,n−1 , in the Sensation, Perception, Emotion,
and Affection Awareness Hyperspaces, respectively. To provide a 2D representation of the results, the two principal
components describing the most of the variance were generated by employing PCA (Principal Component Analysis)
dimensionality reduction [35]. Each point in the Figure represents a reference instance ri,m , which relative probability
was highlighted through the size of the points themselves. For instance, the biggest point shown in the plots is associated
with the Awareness cognitive instance concerning the “landscape” stimulus.
Regarding Consciousness, social and personal morality instances were computed by evaluating the emotional classification of the learner to positive, negative, and neutral classes. In particular, Sensation, Perception, Emotion, and Affection
cognitive instances acquired at a time instant in which the learner provided the emotions of anger, fear, contempt,
sadness, and disgust are associated with a negative semantic, while associated with a positive semantic for the emotions
of happiness and surprise and with a neutral semantic for the neutral state. In principle, social and personal morality
instances should be different, since a subject can express disagreement in the semantics related to cognitive instances;
for instance, a terrorist can subjectively associate the “terrorism” stimulus with happiness, which, under the assumptions
considered in the present study, is associated with a positive semantic, while being aware that for the society the same
stimulus is associated with the emotion of fear, which, under the same aforementioned assumptions, is associated with a
negative semantic. Instead, the present experimentation considers artificial agents which agree on the Environment and
Subjective semantics.
Figure 6 shows the plots concerning cognitive instances of Attention, Awareness, and Consciousness, together with
the related energy and entropy, in the function of the time instants associated with the provided visual stimuli for
the experiments. The Attention results do not change with support in info-incompleteness, while Awareness and
Consciousness trends result more positive when considering the plausibility, credibility, and possibility scores associated
with the stimuli. As it can be seen from the Figure, Awareness, and Consciousness upper bounds do not change,
while their lower bounds significantly increase, when providing support in info-incompleteness to the artificial agent.
Significant higher Awareness and Consciousness are achieved for poorly experienced cognitive instances, i.e., instances
characterized by low probability P r(ri,n ), when considering plausibility, credibility, and possibility scores.
It is also noticeable that the initial Awareness cognitive instance provided a maximum peak. This state indicates the
moment of agent’s activation, i.e., the acquisition of the first Awareness cognitive instance. The proposed model
14
Figure 5: Reference instances r1,m , r2,m , r3,m , r4,m , belonging to the sets M1,n−1 , M2,n−1 , M3,n−1 , M4,n−1 ,
associated with the Sensation, Perception, Emotion, and Affection cognitive layers, respectively, in their related
Awareness Hyperspaces. The cognitive instances are plotted with size proportional to the P r(ri,m ) values.
provided maximum probability to the first stimulus received since the ratio between experience and lifetime reached an
upper bound in that instant. The Awareness cognitive layer with support in info-incompleteness presented significant
higher magnitude since the uncertainty concerning the acquired cognitive instances decreased substantially.
Tables 3 and 4 show the statistics of the experiments concerning the proposed model of computational consciousness
performed without and with support in info-incompleteness.
The results show that the Attention cognitive instances assume the highest magnitude for the stimuli related to the
emotions of happiness, anger, fear, surprise, contempt, and the neutral state, while a decrease was found concerning
those associated with sadness and disgust. The stimuli for which the artificial agent provided significant high Attention
are “beautiful woman,” “own home,” and “crazy sportsman” (F (13, 597) = 434.16, p < 0.001), which all belong to
the set of positive emotions. The stimuli for which the artificial agent provided significant low Attention are “autopsy”
and “injury” (F (13, 597) = 434.16, p < 0.001), belonging to the set of disgust, while “someone’s death or sick,” and
“car accident” (F (13, 597) = 434.16, p < 0.001), belonging to the set of sadness. The emotion for which the agent
provided the highest Attention was happiness (F (13, 597) = 3101.39, p < 0.001); contrarily, the most significant
decrease was found during disgust and sadness (F (13, 597) = 3101.39, p < 0.001).
In the experiments conducted without support in info-incompleteness, the Awareness and Consciousness cognitive
instances are proportional to the probability score, i.e., to the frequency of the related stimuli. In particular, anger
and surprise, which were characterized by the same percentage of occurrences, did not provide significant differences
in the Awareness. However, the Awareness also depends on the number of cognitive instances encapsulated into
15
r5,n
r6,n
r6,n
r7,n
r7,n
En
Hn
Figure 6: Trends of cognitive instances r5,m , r6,m , r7,m , associated with the Attention, Awareness, and Consciousness
cognitive layers, respectively, together with the related trends of energy and entropy. The plots concerning Awareness
and Consciousness are compared with their version involving support in info-incompleteness.
hyperspheres and the number of hyperspheres associated with a given stimulus. Significant high Awareness was found
for the emotion of contempt, which was characterized by the lowest percentage of occurrences (F (13, 597) = 31.87,
p < 0.001). Compared to the stimuli associated with the emotion of disgust, which were significantly more frequent in
the occurrences, the stimuli related to the contempt resulted in a lower number of hyperspheres. The stimuli associated
with the contempt presented less visual variance compared with those eliciting disgust. The artificial agent provided the
highest and lowest Awareness during the neutral state and the emotion of disgust (F (13, 597) = 31.87, p < 0.001),
respectively; the stimuli for which the agent provided the highest and lowest Awareness are “own home” and “injury,”
respectively (F (13, 597) = 20.10, p < 0.001). Regarding Consciousness, the artificial agent provided the highest
magnitude for the emotion of contempt and the neutral state (for which no significant differences were found with each
16
Table 3: Statistics concerning experiments involving no support in info-incompleteness.
Experiments’ statistics (no support in info-incompleteness)
CIs of Attention, Awareness, and Consciousness for each emotional class
Stimulus
Attention (r5,n )
Awareness (r6,n )
Consciousness (r7,n )
Neutral
Happiness
Anger
Fear
Surprise
Contempt
Sadness
Disgust
1.00 (0.00)
0.99 (0.01)
0.99 (0.01)
0.98 (0.01)
0.99 (0.01)
0.99 (0.01)
0.51 (0.00)
0.51 (0.00)
3.12 (0.07)
2.43 (0.32)
2.02 (0.30)
2.69 (0.21)
2.01 (0.32)
2.78 (0.34)
1.46 (0.15)
1.33 (0.11)
1621.07 (218.71)
1349.92 (310.43)
1334.17 (308.65)
1391.34 (246.13)
922.63 (255.16)
1636.38 (451.75)
835.06 (234.18)
674.83 (130.65)
CIs of Attention, Awareness, and Consciousness for each stimulus
Stimulus
Attention (r5,n )
Awareness (r6,n )
Consciousness (r7,n )
Parking car
Man pointing weapon
Someone’s death or sick
Autopsy
Injury
Car accident
Terrorism
Beautiful woman
War
Politician
Landscape
Murder of animal
Own home
Crazy sportsman
0.97 (0.04)
0.99 (0.01)
0.57 (0.07)
0.52 (0.02)
0.51 (0.00)
0.58 (0.13)
0.98 (0.01)
1.00 (0.00)
1.00 (0.01)
1.00 (0.01)
0.99 (0.01)
0.99 (0.01)
1.00 (0.00)
1.00 (0.00)
3.08 (0.12)
2.44 (0.61)
1.76 (0.21)
1.40 (0.14)
1.29 (0.25)
1.26 (0.81)
2.78 (0.26)
2.33 (0.36)
2.83 (0.30)
2.53 (0.57)
3.09 (0.08)
1.75 (0.36)
3.18 (0.03)
1.81 (0.36)
1710.26 (699.78)
1083.63 (559.24)
1304.62 (357.60)
732.16 (159.09)
738.83 (329.58)
297.52 (316.78)
1805.56 (412.10)
1125.61 (302.58)
1448.59 (340.52)
1737.19 (639.30)
1634.10 (218.24)
979.75 (315.08)
2113.64 (907.05)
729.98 (234.38)
other). The lowest Consciousness, instead, was found during the emotion of disgust (F (13, 597) = 7.46, p < 0.001).
Regarding the stimuli eliciting happiness and anger, no differences in the Consciousness cognitive instances were found.
The stimuli for which the agent provided the highest and lowest Consciousness are “own home” and “car accident,”
respectively (F (13, 597) = 6.50, p < 0.001). Regarding the same cognitive layer, no significant differences were found
concerning the stimuli of “autopsy,” “injury,” and “crazy sportsman;” the same holds for “parking car” and “politician.”
Regarding Consciousness entropy, the Sensation cognitive layer provided lower magnitude compared with Emotion
(F (1, 609) = 3.86, p = 0.04), while Perception was found to be comparable with Sensation and Emotion. The
Affection cognitive layer, instead, provided significant high entropy (F (3, 607) = 8.13, p < 0.001). Significant low
Consciousness energy was found concerning the Sensation (F (3, 607) = 36.59, p < 0.001), while no significant
differences were found in the Perception and Emotion cognitive layers. Finally, the Affection provided the highest
Consciousness energy.
7
Discussion
The results concerning Attention are concordant with the scientific evidence regarding covert attention in human beings.
In particular, a decrease in the attention associated with the emotion of disgust was found by Van Hooff et al. [30],
which investigated the effects of disgust-, fear-, and neutral-related stimuli on covert attention. They proposed an
experiment, called covert orienting task, by employing the IAPS (International Affective Picture System) dataset [36]
for studying participants’ reactions to images. The process consisted of the task of targeting a picture, shown on a
screen, eliciting one of the above emotions (i.e., disgust, fear, or the neutral state) in participants. The results provided
significantly less accurate identifications and longer reaction times in targeting disgust-evoking pictures. An extension
of the above study [31] revealed a significant lowering in the attention concerning disgust-evoking pictures compared
to the emotion of happiness. No further studies were found concerning the same experimental method applied to
the emotions of surprise, contempt, and sadness. Experimentation employing the covert orienting task for analyzing
17
Table 4: Statistics concerning experiments involving support in info-incompleteness.
Experiments’ statistics (support in info-incompleteness)
CIs of Attention, Awareness, and Consciousness for each emotional class
Stimulus
Attention (r5,n )
Awareness (r6,n )
Consciousness (r7,n )
Neutral
Happiness
Anger
Fear
Surprise
Contempt
Sadness
Disgust
1.00 (0.00)
0.99 (0.01)
0.99 (0.01)
0.98 (0.01)
0.99 (0.01)
0.99 (0.01)
0.51 (0.00)
0.51 (0.00)
3.18 (0.02)
2.58 (0.25)
2.71 (0.13)
2.87 (0.13)
2.56 (0.16)
3.04 (0.11)
1.53 (0.09)
1.45 (0.07)
1648.65 (216.64)
1407.96 (303.01)
1714.93 (270.05)
1493.18 (233.96)
1270.04 (236.94)
1815.69 (429.59)
855.59 (233.31)
710.58 (126.20)
CIs of Attention, Awareness, and Consciousness for each stimulus
Stimulus
Attention (r5,n )
Awareness (r6,n )
Consciousness (r7,n )
Parking car
Man pointing weapon
Someone’s death or sick
Autopsy
Injury
Car accident
Terrorism
Beautiful woman
War
Politician
Landscape
Murder of animal
Own home
Crazy sportsman
0.97 (0.04)
0.99 (0.01)
0.57 (0.07)
0.52 (0.02)
0.51 (0.00)
0.58 (0.13)
0.98 (0.01)
1.00 (0.00)
1.00 (0.01)
1.00 (0.01)
0.99 (0.01)
0.99 (0.01)
1.00 (0.00)
1.00 (0.00)
3.08 (0.12)
2.84 (0.27)
1.78 (0.21)
1.47 (0.11)
1.50 (0.10)
1.56 (0.54)
2.90 (0.17)
2.50 (0.29)
2.94 (0.20)
2.98 (0.19)
3.14 (0.04)
2.61 (0.15)
3.18 (0.03)
2.48 (0.19)
1710.26 (699.78)
1263.25 (518.29)
1331.66 (366.26)
764.44 (154.03)
769.57 (323.26)
383.81 (308.66)
1928.73 (389.03)
1186.06 (297.64)
1490.57 (326.12)
2046.74 (568.30)
1660.33 (216.32)
1441.64 (280.87)
2113.64 (907.05)
1145.50 (223.75)
attention during the elicitation of the above emotions could confirm the relative results obtained in the present work. For
instance, finding a lowering in the covert attention during the emotion of sadness would provide further evidence that
the proposed attention model consistently describes the phenomenon. Adopting another experimental method, called
the flanker task, Bellaera and von Mühlenen [37] found that participants showed significant narrowing of the selective
attention in conditions of sadness. Selective attention may be considered as the opposite of covert attention; thus, an
experiment employing the covert orienting task may provide evidence for the decrease in the identification accuracy
and longer reaction times. Research on the covert and selective attention often present conflicting results: Finucane [38]
proved that response times are significantly faster in anger and fear conditions than in the neutral state by employing the
flanker task, while Van Hooff et al. [30] found no significant differences in the covert attention for the emotions of
anger, fear, and the neutral state.
A comparison of the Awareness cognitive layer with the scientific evidence is difficult. However, the results seem
coherent with the evidence provided by Atas et al. [39], in which a gradual increase in the awareness of a visual stimulus
was found by augmenting the repetitions. The experiment conducted by the authors was the visual masking [40], which
consists in proposing the repetition of masked visual stimuli to participants. Visual masking represents one of the most
employed methods for the study of consciousness, especially as regards the differentiation between conscious and
unconscious processes. To our knowledge, no experiments concerning the study of awareness in the function of the
experiences of other subjects have been conducted yet. However, the modeling of the cognitive differentiation between
one’s personal experience and that of other subjects, i.e., the evaluation of the probability score as concurrent with the
plausibility, credibility, and possibility scores introduced the element of self-awareness in the Awareness cognitive
layer. Scientific evidence considers the mirror test as one of the most relevant experimental methods for identifying
self-awareness in species. Regarding the human being, the experimentation consists in verifying the capability of
distinguishing one’s image reflected in the mirror to the visualization of other targets. Since the above test was passed
by humans, the proposed model of computational consciousness may introduce interesting perspectives of research,
since the differentiation of probability, plausibility, credibility, and possibility scores may reveal, from the “experiential”
point of view, a sort of self-awareness in the machine.
18
The experiments revealed that the probability associated with a given reference cognitive instance represents a measure
of the “quantity” of Awareness, intended as “artificial experience,” concerning a given event. In the proposed model, the
magnitude of the Awareness cognitive instance r6,n increases proportionally to the number of occurrences acquired at a
distance lower than or equal to R from the relative reference instance ri,m (i.e., as the population of cognitive instances
grows within a hypersphere). As defined in Section 5.2, the Awareness cognitive layer also integrates the contribution
provided by non-direct experience. The awareness of a subject concerning a given stimulus was assumed as affected
also by the interaction with other subjects; in fact, the acquisition of information associated with a given event can
significantly influence the awareness of a subject. For instance, an external opinion regarding the content of a bi-stable
image can be essential to the awareness of that visual stimulus. In the present model, while the probability-based model
allows increasing the magnitude of Awareness cognitive instances directly, the characterization based on plausibility,
credibility, and possibility was theoretically associated with the results obtained from external models or humans. In the
case the agent reached not suitable P r(ri,n ), the values P l(ri,n ), Cr(ri,n ), and P o(ri,n ) can be acquired from external
sources. For instance, these scores can be obtained by interacting with another agent, with a human, or by extracting
data from the web.
The experiments revealed that Consciousness is higher during the processing of stimuli eliciting the emotions of
contempt and the neutral state, while lower during disgust. The results highlight that the agent’s experiences are
more polarized towards positive semantics during contempt and the neutral state, while towards negative semantics
during disgust. The model valued the comparison with positive experiences during the processing of stimuli such as
“politician,” “parking car,” and “landscape,” while significantly comparing “autopsy” and “injury” stimuli with negative
experiences. This process of comparison is affected by the contribution of the Consciousness energy, which provides a
metric of semantic polarization in the Consciousness Graphs. By providing visual stimuli to participants, Schnall et al.
[41] provided evidence for increasing judgments of wrongness for occurrences eliciting disgust, compared with those
eliciting sadness. Similarly, the present study found a lower Consciousness magnitude during sadness than disgust,
revealing less negative orientation of personal morality instances towards stimuli eliciting sadness, such as “someone’s
death or sick” and “car accident.” However, the authors also found that participants provided less severe judgments
towards visual stimuli concerning sadness, compared with those concerning the neutral state. This last result was found
as opposed to the outcomes of our experiments, in which Consciousness energy revealed higher positiveness during the
processing of stimuli related to the neutral state.
The analysis of entropy and energy revealed that Consciousness increases as cognition approaches deeper cognitive
layers. Sensation Consciousness was found to be weaker than Affection Consciousness, in terms of entropy and energy.
The results reveal that the experimented artificial agent acquires higher Consciousness for the personal, as opposed to
the social, morality since the Affection cognitive layer provided the increasing positive orientation of personal morality
instances. These results encourage a scientific investigation of consciousness in the function of sensations, perceptions,
emotions, and affections through the metrics of entropy and energy.
In general, the proposed model of computational consciousness approximates several human cognitive tasks, such
as covert attention, the awareness related to a repetition of stimuli through both direct and indirect experiences, and
consciousness as the semantic connection of environment and subjective experiences. The mechanisms conceived
in Section 2 as “objective” and “phenomenal,” in our model were represented by the Environment and Subjective
Awareness; those conceived as “subjective” and “access,” in the proposed model were represented by the Environment
and Subjective Consciousness.
8
Conclusions and future work
In the present study, a novel model of computational consciousness for non-interacting agents was proposed. By analyzing the latest advancements in the field of AC and the Smart Sensing prodromal solution, an info-structural hierarchy
of cognitive layers concerning the cognitive tasks of sensation, perception, emotion, affection, attention, awareness,
and consciousness was defined and experimented on visual stimuli. In doing so, the theoretical background regarding
the studies of consciousness was evaluated and several theories, definitions, and scientific evidence were considered
for operating the mathematical modeling. Consciousness was assumed as the moral evaluation of environment and
subjective experiences, which depend on the emotional activity.
Attention was deployed computationally through a bottom-up approach and adopted as the fundamental modulating
factor for awareness to happen; its mathematical representation was conceived with a matrix acquiring artificial
sensation, perception, emotion, and affection stimuli. Emotions were represented through the classes of anger, fear,
happiness, surprise, contempt, disgust, and the neutral state. Adopting the theory of decision and reasoning in uncertainty
and info-incompleteness conditions, Awareness was modeled as the information fusion of probability, plausibility,
credibility, and possibility scores concerning the acquired sensation, perception, emotion, and affection related artificial
19
experiences. In our solution, the probability was deployed to represent the agent’s direct experience of stimuli, while
plausibility, credibility, and possibility represent the agent’s indirect experience. Our model of awareness was supported
by the geometry of hyperspheres, which allow representing information in the Euclidean space. Finally, consciousness
was modeled by connecting and associating the above artificial experiences with semantics related to the sets of social
and personal morality employing graph structures. The final result consisted of an index obtained by computing the
sum of contributions related to the analysis of the above graph structures in terms of energy and entropy.
The results showed that, from our comparative analysis, the proposed model of attention is concordant with the scientific
evidence concerning covert attention in human beings. Regarding our models of awareness and consciousness, a direct
comparison with scientific studies was difficult, but strong similarities were found concerning experiments involving
the repetition of visual stimuli and the relative moral judgments. In particular, the proposed model resulted comparable
with scientific evidence regarding increasing judgments of wrongness concerning the occurrences of visual stimuli
eliciting disgust, compared with those eliciting sadness.
The present model of computational consciousness provides contributions to AC by proposing an approach to implement
artificial subjectivity in the machine, as well as by investigating the sequential, rather than the parallel, execution of
cognitive tasks. Furthermore, a model enhancing the functioning of consciousness in terms of emotional activity and
morality has been defined and experimented with visual stimuli. The unique part of the system involving the training of
a learner is the model deployed for artificial emotion, which allows running the solution on specific emotional history.
From a scientific point of view, the results obtained in the present study encourage investigations on the subjective
nature of consciousness through emotional, moral, energetic, and entropic perspectives.
A future study concerning the proposed model consists in the introduction of causality by associating the arcs of
Consciousness Graphs to the actions performed by the agent towards the environment. This approach permits to
adopt the paradigm of reinforcement learning to find the optimal policy for reaching the best reward in never-explored
environments. Such a model could be deployed in social robots with the aim of studying computational consciousness in
human-robot interaction. A further future study regards the acquisition of plausibility, credibility, and possibility scores
for the proposed model of awareness directly from the interacting environment or from other sources of information,
such as the internet.
References
[1] H. Ritschel and E. André. Real-time robot personality adaptation based on reinforcement learning and social
signals. In Proceedings of the Companion of the 2017 ACM/IEEE International Conference on Human-Robot
Interaction, pages 265–266, 2017.
[2] A. Paiva, I. Leite, H. Boukricha, and I. Wachsmuth. Empathy in virtual agents and robots: A survey. ACM
Transactions on Interactive Intelligent Systems (TiiS), 7(3):1–40, 2017.
[3] A. Bonarini, S. Boriero, and E. L. S. de Oliveira. Robot player adaptation to human opponents in physical, competitive robogames. In 2020 29th IEEE International Conference on Robot and Human Interactive Communication
(RO-MAN), pages 851–856. IEEE, 2020.
[4] Gerardo Iovane, Iana Fominska, Riccardo Emanuele Landi, and Francesco Terrone. Smart sensing: An infostructural model of cognition for non-interacting agents. Electronics, 9(10):1692, 2020.
[5] N. Block. On a confusion about a function of consciousness. Behavioral and Brain Sciences, 18(2):227–247,
1995.
[6] D. J. Chalmers. The conscious mind: In search of a fundamental theory. Oxford Paperbacks, 1996.
[7] W. Singer. Consciousness and the binding problem. Annals of the New York Academy of Sciences, 929(1):123–146,
2001.
[8] M. S. A. Graziano and S. Kastner. Human consciousness and its relationship to social neuroscience: A novel
hypothesis. Cognitive Neuroscience, 2(2):98–113, 2011.
[9] K. H. Pribram and E. H. Carlton. Holonomic brain theory in imaging and object perception. Acta Psychologica,
63(2):175–210, 1986.
[10] S. Hameroff and R. Penrose. Consciousness in the universe: A review of the ‘orch or’ theory. Physics of Life
Reviews, 11(1):39–78, 2014.
[11] G. Tononi. An information integration theory of consciousness. BMC Neuroscience, 5:1–22, 2004.
[12] P. Haggard. Human volition: towards a neuroscience of will. Nature Reviews Neuroscience, 9(12):934–946, 2008.
20
[13] S. Franklin, T. Madl, S. D’Mello, and J. Snaider. Lida: A systems-level architecture for cognition, emotion, and
learning. IEEE Transactions on Autonomous Mental Development, 6(1):19–41, 2013.
[14] S. Kugele and S. Franklin. Learning in lida. Cognitive Systems Research, 66:176–200, 2021.
[15] B. J. Baars. A cognitive theory of consciousness. In Cambridge University Press, volume 174, 1988.
[16] W. Huang, A. Chella, and A. Cangelosi. A design of global workspace model with attention: Simulations of
attentional blink and lag-1 sparing. Journal of Artificial Intelligence and Consciousness, 9(01):29–57, 2022.
[17] W. Sato, T. Kochiyama, S. Uono, and M. Toichi. Neural mechanisms underlying conscious and unconscious
attentional shifts triggered by eye gaze. NeuroImage, 124:118–126, 2016.
[18] J. E. Raymond, K. L. Shapiro, and K. M. Arnell. Temporary suppression of visual processing in an rsvp task: An
attentional blink? Journal of Experimental Psychology: Human Perception and Performance, 18(3):849, 1992.
[19] B. Hommel and E. G. Akyürek. Lag-1 sparing in the attentional blink: Benefits and costs of integrating two events
into a single episode. The Quarterly Journal of Experimental Psychology Section A, 58(8):1415–1433, 2005.
[20] R. Lewis. Rough set & riemannian covariance matrix theory for mining the multidimensionality of artificial
consciousness. In Proceedings of the 10th International Conference on Web Intelligence, Mining and Semantics,
pages 248–251, 2020.
[21] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv
preprint arXiv:1409.1556, 2014.
[22] Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image
database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255. Ieee, 2009.
[23] T. Chen and C. Guestrin. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD
International Conference on Knowledge Discovery and Data Mining, pages 785–794, 2016.
[24] A. Mack. Inattentional blindness: Looking without seeing. Current Directions in Psychological Science,
12(5):180–184, 2003.
[25] J. M. et al. Findlay. Active vision: The psychology of looking and seeing. Number 37. Oxford University Press,
2003.
[26] F. Katsuki and C. Constantinidis. Bottom-up and top-down attention: different processes and overlapping neural
systems. The Neuroscientist, 20(5):509–521, 2014.
[27] Y. Ouchi, K. Meguro, K. Akanuma, Y. Kato, and S. Yamaguchi. Normal hearing ability but impaired auditory
selective attention associated with prediction of response to donepezil in patients with alzheimer’s disease.
Behavioural Neurology, 2015.
[28] C. Spence and A. Gallace. Recent developments in the study of tactile attention. Canadian Journal of Experimental
Psychology/Revue canadienne de psychologie expérimentale, 61(3):196, 2007.
[29] M. G. Veldhuizen and D. M. Small. Modality-specific neural effects of selective attention to taste and odor.
Chemical Senses, 36(8):747–760, 2011.
[30] J. C. Van Hooff, C. Devue, P. E. Vieweg, and J. Theeuwes. Disgust-and not fear-evoking images hold our attention.
Acta Psychologica, 143(1):1–6, 2013.
[31] J. C. Van Hooff, M. van Buuringen, I. El M’rabet, M. de Gier, and L: van Zalingen. Disgust-specific modulation
of early attention processes. Acta Psychologica, 152:149–157, 2014.
[32] P. Chavajay and B. Rogoff. Cultural variation in management of attention by children and their caregivers.
Developmental Psychology, 35(4):1079, 1999.
[33] A. Hussain, I. Aleksander, L. S. Smith, A. K. Barros, R. Chrisley, and V. Cutsuridis. Brain inspired cognitive
systems, volume 657. Springer Science & Business Media, 2009.
[34] Gerardo Iovane, Patrizia Di Gironimo, Marta Chinnici, and Antonio Rapuano. Decision and reasoning in
incompleteness or uncertainty conditions. IEEE Access, 8:115109–115122, 2020.
[35] I. Jolliffe. Principal component analysis. Encyclopedia of Statistics in Behavioral Science, 2005.
[36] P. J. Lang. International affective picture system (iaps): Affective ratings of pictures and instruction manual.
Technical Report, 2005.
[37] L. Bellaera and A. von Mühlenen. The effect of induced sadness and moderate depression on attention networks.
Cognition and Emotion, 31(6):1140–1152, 2017.
[38] A. M. Finucane. The effect of fear and anger on selective attention. Emotion, 11(4):970, 2011.
21
[39] A. Atas, A. Vermeiren, and A. Cleeremans. Repeating a strongly masked stimulus increases priming and awareness.
Consciousness and cognition, 22(4):1422–1430, 2013.
[40] B. Breitmeyer, H. Ogmen, H. Öğmen, et al. Visual masking: Time slices through conscious and unconscious
vision. Oxford University Press, 2006.
[41] Simone Schnall, Jonathan Haidt, Gerald L Clore, and Alexander H Jordan. Disgust as embodied moral judgment.
Personality and Social Psychology Bulletin, 34(8):1096–1109, 2008.
22 |
341
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
Article
Premonitions: A Global Online Statistical Tracking Study of
Precognitive Predictions
J. Miguel Gaona1, 2, 3, *, Francisco Colinas1, Nicolas Rouleau1,
Lucas W. E. Tessaro1, and Joey M. Caswell1,*
1
Transnational Anomalies Research, Sudbury, Ontario, Canada
Centro Europeo Neurosalus, Madrid, Spain
3
Faculty of Medicine, Universidad Rey Juan Carlos, Madrid Spain
2
Abstract
A number of interesting and testable theories of precognitive information transfer have been
posited, and focus on the potential role of both ultraweak photon emissions and the geomagnetic
field. While many experiments examining this anomalous phenomenon have been previously
conducted, a precognitive study of a magnitude similar to the Premonitions project
(ThePremonitions.com) has not yet been undertaken to our knowledge. By using an internetbased study to statistically examine this intriguing occurrence, the main objective of
Premonitions is to acquire data from a large population of participants from across the globe.
Furthermore, if some individuals are truly capable of receiving or accessing this apparently nonlocal information for accurate prediction of future events, a significant increase in the available
sample size should increase the “signal resolution” for the detection of global non-local
information.
Key Words: Consciousness, premonitions, extrasensory perception, precognition, internet study,
anomalies, psi, non-local, geomagnetic field, dreams.
1. Introduction
Premonitions are examples of precognition which involve the prediction of future events without
inferential reasoning or a priori knowledge [1]. Although premonitions are typically transient,
the ability to readily acquire information about an event before it occurs would have marked
implications on individuals and societies. As a transient experience, precognition within the
whole of a given group would be expected to have a higher frequency of occurrence than in any
one individual within that same group. It is therefore a practical approach, in pursuit of an
understanding and application of precognitive phenomena, to probe large groups over long
periods of time for information relevant to future events. Large-scale statistical analyses upon
aggregated precognitive event data would allow for an identification of potential unanticipated
details which could predict geopolitical or perhaps natural events before their occurrence. In this
*Corresponding authors: J. M. Caswell & J. M. Gaona E-mail: neuraljc@gmail.com, drgaona@neurosalus.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
342
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
sense, each member of the global community would represent a sensor for precognitive
information where, as the participants increase, so does the resolution of the signal.
Modern internet culture represents a medium in which a large scale premonition project is
possible. Automated tests which make use of email messaging have already seen application in
psychical research [2]. Whereas it was once difficult to maintain longitudinal studies involving
participants situated in distant geographical locations, the internet provides a medium in which
large quantities of data can be collected non-invasively without expending many resources.
Apparent precognitive events also appear to display a propensity to occur during dreaming [3-4]
which makes an online initiative of this nature even more attractive, given that potential
participants who experience this phenomenon during sleep can easily and, more importantly,
immediately report their experience.
Cognition refers to the mental processing of information which is associated with neural
activations along myriad pathways within the brain. Classically, subjective experiences
associated with objective events follow the events themselves, proceeding along a linear
unidirectional model of subjective time. Precognition refers to the subjective experience of a
later confirmed objective event and is typically observed on the same day of the event [5]. These
experiences violate the assumption of unidirectional subjective time and, if objectively relevant,
represent hitherto untapped sources of information.
A meta-analysis of 309 forced-choice experiments involving over 50,000 subjects demonstrated
that effect sizes associated with studies of precognition remained constant despite high
variability in research quality over time [1]. This suggests a reliability of the phenomenon and
has since motivated further quantitative investigation. Physiological predictors of precognition
have been reported from the experimental literature which has included heart rate [6] as well as
pupillary dilation and spontaneous blinking [7]. Environmental variables which predict
precognitive events have also been reported. Lewicki et al. [5] demonstrated that global
geomagnetic activity on the day of the subjective experience moderately correlated with
geomagnetic activity which would occur during the two days preceding the objective event. The
study indicated that the electromagnetic environment on the day of the precognitive experience
and that of the objective event were fundamentally related. In addition, recent quantitative work
indicates that all human brains could access shared information while immersed in the same
geomagnetic environment [8]. Together, these findings support the claim that there are subtle
shifts in variables intrinsic and extrinsic to the human body which predict objective events that,
when phenomenologically accessible as subjective experiences preceding the events, are
accessible as explicit forms of information which can be self-reported and subject to predictive
analysis.
The acquisition of precognitive information has often been linked with sleep or, more
specifically, to dreams and dream-like altered states of consciousness [3-4, 9]. During periods of
dream-sleep, it has been demonstrated that the right hemisphere shows characteristics of cerebral
dominance, in addition to responding conspicuously to exogenous geomagnetic activity [10-11].
That geomagnetic activity can be correlated with right hemispheric activity bears particular
importance in regard to Bókkon’s theories [12-13]. Given the requirement of electromagnetic
(EM) activation of visual neurons, the fact that dreams incorporate visual imagery suggests these
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
343
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
photic stimuli are produced from within the brain itself; e.g., they are the result of endogenous
biophoton emission [12-13].
In a series of studies, Dotta et al. [14-15] have demonstrated that conscious thought and
imagination can lead to increased ultraweak photon emission (UPE) from the cerebrum localized
to the right hemisphere. Given that photons are individual packets of information, it therefore
stands to reason that certain forms of hypnogogic imagery may be the result of UPE interactions
with visual receptors. However, we submit the following question: if dreams and hypnogogic
imagery can be the result of biophoton emission, can that information be transferred to another
individual?
Previous experiments have also demonstrated that subjects in isolation from one another during
application of the same circumcerebrally applied magnetic field pattern show a correlation in
cerebral activity when only one subject received a stimulus, such as a flash of light [16]. These
cerebral events were localized to the right parietal region. Given subsequent studies by Dotta et
al. [17] demonstrating the “doubling” of UPE from cell cultures exposed to identical magnetic
field configurations, it follows that biophotons may be the mode of transport for non-local
information [17-18].
For example, one individual who has proven himself reliable and consistent in the phenomenon
of acquiring information at a distance is Sean Harribance [19]. Countless studies have verified
the veracity of his claims, which have also shown increased activity in the right temporoparietal
region during his intuitive-state [20-21]. Recent studies have established that Mr. Harribance’s
cerebral activity is also correlated with cerebral UPE, again localized within the right
hemisphere, which would support the hypothesis of biophotons carrying information which can
be read by such individuals [22-23].
Indeed, the possibility for photon emissions from non-biological sources carrying non-locally
available information about future events can be posited from studies on the Earth’s background
photon emissions and subsequent earthquake activity. In a series of studies, Persinger et al. [24]
have shown that protracted background photon emission increases frequently precede major
(magnitude M > 8.0) earthquakes. This phenomenon has been observed in interactions with
Random Event Generator (REG) devices, where it has been shown that significant deviations in
REG output can be predicted using photon emissions occurring two days prior [25].
Furthermore, Caswell et al. [26] previously illustrated a number of interesting relationships
between human UPE and significant deviations in REG output.
These studies taken together suggest a possible mechanism by which Bókkon’s dream-biophoton
emission can be related to real life precognitive events. Given that both earthquake and REG
output can be predicted by photon emission, it is therefore plausible that this same photon
emission could be the carrier of precognitive information at the individual level, as exemplified
by Mr. Harribance.
In addition to the photon emission hypotheses related to the non-local access of information and
prediction of future events, Persinger [8, 27] has consistently demonstrated relevant convergent
dimensional analyses which suggest that the geomagnetic field could hold “information” of
every thought from every human being who has lived, with an enormous amount of residual
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
344
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
energy available. With this fascinating and quantified theory in mind, the fact that every human
on the planet is immersed in the same planetary magnetic conditions, and that electromagnetic
configurations have been shown to produce non-local excess correlations or ”entanglement” [1617], it is possible that the geomagnetic field could allow transfer of and access to this “stored”
information associated with human thought.
To further this proposition in the context of premonitory predictions and non-local information
access, numerous studies have previously demonstrated that precognitive phenomena typically
occur during periods of quiet geomagnetic activity [28], which could suggest a reduction in
environmental “noise” might enhance the “signal” by which the acquisition of exogenous
information is accomplished. Furthermore, this relationship has also been observed in association
with the similar parapsychological phenomenon of remote viewing [29-30], whereby an
individual remotely accesses information about an unknown distant target image.
2. About the Premonitions Project
Premonitions (ThePremonitions.com) is a web-based service designed for the purpose of
conducting longitudinal, mixed-design online tracking studies of precognitive phenomena. Users
from around the world are able to submit and track precognitive predictions, which are then
analyzed by the system.
While the project is currently in a preliminary phase, a number of additional features have been
proposed and entered various stages of development. The following overall objectives will be
reached in future consecutive phases.
2.1. Overview and Objective
The platform consists of a database which is accessed through a simple and friendly web
interface, programmed in php, JavaScript and HTML, where the user can input a priori
predictions of future events, detailing its contents, and labeling them according to a classification
of possible scenarios. The main objectives are:
i. Establish a server for safe storage of such a priori predictions of the occurrence of each
event.
ii. Evaluate premonitions post-event involving accuracy indicators weighted accordingly.
iii. Perform a statistical treatment of the data input for the generation of graphical categories,
tags, etc., and their evolution over time.
2.2. Database
i. A database (MySQL type) hosted on multiple servers is used to contain all data on system
performance. The database, therefore, will be duplicated in order for an external institution
or agency, attesting to the veracity of the protocol followed by the system, and externally to
ensure no targeted manipulation of premonitions and entered data.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
345
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
ii. Periodically, backups will be done to ensure consistency and data security for any
eventual downfall and/or cyber-attack to the servers where the system is hosted.
2.3. Registry
The data needed for user registration are:
- A user nickname.
- A password that will be encrypted in the database.
- A contact email to allow access.
- Various demographics such as age, gender, etc.
At all times, the privacy of such data is guaranteed under the Terms and Conditions of Use of the
platform.
2.4. Interaction with the Platform
There are two types of interaction: registered and unregistered.
i. Unregistered Users:
Can tell the system that "something" is going to happen, and may categorize a number of
user-contributed tags. With this information we generate real-time graphics with a focus on
temporal properties.
ii. Registered Users:
In this case, the user can access the system through a login, and enter fully and in detail the
content of their prediction. They may also view the history of previous predictions made, but
cannot alter or modify the contents thereof.
2.5. Entering Premonitions
The user must fill in all or part of the following fields:
i. Expected date of event if known. Can be completely filled, partially filled, or left blank if
the deadline of the prediction is unknown. Users may also state whether the intended date of
the event is given precisely or approximately.
ii. Category and sub-category, selecting from a set of possibilities to classify the content of
the prediction.
iii. "Strength" of perceived premonition (high, medium or low).
iv. Content of prediction, with the best possible detail of the content.
v. Tags or keywords related to the content provided for statistical purposes.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
346
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
2.6. Viewing Premonitions Made
The user can view the premonitions, made to appear as a table, temporarily (Newest First)
ordered. Users may not, under any circumstances, modify any of the fields filled out when the
premonition was introduced. If the premonition is fulfilled, the user will receive information that
may inform the outcome of that particular prediction, detailing the incident which has generated
such compliance, and may provide supporting documentation where appropriate.
For fulfilled premonitions, users may also consult the system evaluation that was conducted
according to certain indicators.
2.7. Viewing Premonitions of Others
A further feature is the ability to view premonitions made by other users. Here, you can see
premonitions made by users that have already been fulfilled and evaluated. The reason for not
allowing access to the premonitions of other users yet unfulfilled is to avoid creating a "trend of
opinion" that may influence the premonitions of other users, and to avoid the phenomenon of
self-fulfilling prophecy of a set of individuals. However, implementation of this option is
currently being considered.
2.8. Statistics
Apart from the main objective of the system, which is the study of the existence of premonitions
as an aspect of the phenomena of extrasensory perception, the entered data undergoes a statistical
treatment which is held by the system. Conclusions will be obtained about the most common
type(s) of predictions in a sample of users of the system by gender, age, and other demographic
characteristics.
Given the strong temporal component of the phenomenon under study, the temporal evolution of
the premonitions are discussed in relation to the total amount of reports or forecasts, and in terms
of the categories and/or subcategories most frequently given over a specific period of time.
Another aspect to consider is that of the most commonly used tags for premonitions and the
corresponding quantitative, statistical analyses which will be performed over time.
2.9. Evaluation of Premonitions
There are two processes which may prompt evaluation of predictions:
- User prompt.
- Expiration of its deadline.
In either case, the system will be notified and it shall assess the accuracy of the predictions made
in each case by quantifying the degree of compliance with the actual event. For calculation of the
evaluation, a series of weighted indicators, such as the risk of the prediction made (that is, the
likelihood that an event of this kind happens), the setting, and detail that is provided are used, as
well as the degree of overall precision if the user has provided a deadline for the event.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
347
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
2.10. Conclusions
This initiative is a project whose long-term evaluation of results depends on the volume of
premonitions introduced by users.
Although initially set to have a version in Castilian and English, we will try to include as many
languages as possible, thus maximizing the size of the population sample both qualitatively
(countries, cultures, societies, etc.) and quantitatively.
3. Discussion
There are approximately 7·109 humans on planet Earth, roughly 2.8·109 of which could be
described as internet users (~40% of global population). Given that a “thought” is associated
with a discrete, coherent activation of approximately 106 neurons [31], and the upper limit for
neurons within the cerebral cortex is ~2·1010 [32], the maximum number of discrete processing
clusters available to the Premonitions endeavor when accounting for all internet users is 5.6·1013.
Suppose an internet-based project as described here can reach 0.0035% or ~100,000 individuals
within the world’s internet using population. The total number of thought-processing units
available to the project would be 2·109 or within the lower range of neurons which comprise a
single human neocortex [32]. This global brain, spread out across the Earth’s surface (5.1·108
km2) represents a sensor area density of 3.9 sensor units per km2. However, only 30% of the
Earth’s surface area is land, which gives a true sensor area density of 13.07 sensors per km2 for
the available surface area. Of course, the actual distribution will be clustered within discrete
geographical locations where the appropriate infrastructure is present. These values describe the
receptive field within which extracerebral sources of information might be sequestered. As
discussed previously, the geomagnetic field is one potential source for this extracerebral
information. Once data has been collected, analyses will attempt to isolate geophysical
perturbations which might affect the quantity or quality of the information.
An assembly of self-reported thought patterns, largely uninformative in isolation, could represent
collective information indicative of future events. The provision of accurate data on the possible
existence of extrasensory perception as premonitions will allow for further exploration into the
possibilities of group initiatives such as these and the emergent functions of interconnected
brains. The Premonitions project (ThePremonitions.com) is an initiative which aims to explore
these properties of interconnectedness and derive applied solutions for predicting events relevant
to cultures, societies, and all life on the planet.
Acknowledgments: The authors would like to thank Transnational Anomalies Research team member
David A. E. Vares for internal review.
References
1) Honorton, C., & Ferrari, D. C. (1989). Future telling: A meta-analysis of forced-choice precognition
experiments, 1935–1987. Journal of Parapsychology, 53(28) 1-308.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
348
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
2) Sheldrake, R., & Avraamides, L. (2009). An automated test for telepathy in connection with emails.
Journal of Scientific Exploration, 23(1).
3) Krippner, S. (1993). The Maimonides ESP-dream studies. Journal of Parapsychology, 57(1), 39-54.
4) Dotta, B. T. & Persinger, M. A. (2009). Dreams, time distortion and the experience of future events: A
relativistic, neuroquantal perspective. Sleep and Hypnosis, 11(2), 29-39.
5) Lewicki, D. R., Schaut, G. H., & Persinger, M. A. (1987). Geophysical variables and behavior: XLIV.
Days of subjective precognitive experiences and the days before the actual events display correlated
geomagnetic activity. Perceptual and Motor Skills, 65(1), 173-174.
6) Sartori, L., Massacessi, S., Martinelli, M., & Tressoldi, P. E. (2004). Physiological correlates of ESP:
Heart rate differences between targets and nontargets. Journal of Parapsychology, 68(2).
7) Radin, D., & Borges, A. (2009). Intuition through time: What does the seer see?. Explore: The Journal
of Science and Healing, 5(4), 200-211.
8) Persinger, M. A. (2013). Billions of human brains immersed within a shared geomagnetic field:
Quantitative solutions and implications for future adaptations. Open Biology Journal, 6, 8-13.
9) Hearne, K. M. (1987). A dream-telepathy study using a home 'dream machine'. Journal of the Society
for Psychical Research, 54(807).
10) Babayev, E. S. & Allahverdiyeva, A. A. (2007). Effects of geomagnetic activity variations on the
physiological and psychological state of functionally healthy humans: Some results of Azerbaijani
studies. Advances in Space Research, 40(12), 1941-1951.
11) Saroka, K. S., Caswell, J. M., Lapointe, A., & Persinger, M. A. (2014). Greater
electroencephalographic coherence between left and right temporal lobe structures during increased
geomagnetic activity. Neuroscience Letters, 560, 126-130.
12) Bókkon, I. (2005). Dreams and neuroholography: An interdisciplinary interpretation of development
of homeotherm state in evolution. Sleep and Hypnosis, 7(2), 61-76.
13) Bókkon, I. (2008). Phosphene phenomenon: A new concept. BioSystems, 92(2), 168-174.
14) Dotta, B. T. & Persinger, M. A. (2011). Increased photon emissions from the right but not the left
hemisphere while imagining white light in the dark: The potential connection between consciousness and
cerebral light. Journal of Consciousness Exploration & Research, 2(10).
15) Dotta, B., Saroka, K. & Persinger, M. A. (2012). Increased photon emission from the head while
imagining light in the dark is correlated with changes in electroencephalographic power: Support for
Bókkon's Biophoton Hypothesis. Neuroscience Letters, 513(2), 151-154.
16) Persinger, M. A. & Lavallee, C. F. (2010). Theoretical and experimental evidence of macroscopic
entanglement between human brain activity and photon emissions: implications for quantum
consciousness and future applications. Journal of Consciousness Exploration & Research, 1(7).
17) Dotta, B. T., Buckner, C. A., Lafrenie, R. M., & Persinger, M. A. (2011). Photon emissions from
human brain and cell culture exposed to distally rotating magnetic fields shared by separate lightstimulated brains and cells. Brain Research, 1388, 77-88.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
349
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
18) Dotta, B. T. & Persinger, M. A. (2012). “Doubling” of local photon emissions when two
simultaneous, spatially-separated, chemiluminescent reactions share the same magnetic field
configurations. Journal of Biophysical Chemistry, 3(1).
19) Harribance, C. C. (1994). Sean Harribance: A Psychic Predicts the Future. Sean Harribance Institute
of Parapsychology Foundation.
20) Roll, W., Persinger, M., Webster, D., Tiller, S., & Cook, C. (2002). Neurobehavioral and
neurometabolic (SPECT) correlates of paranormal information: involvement of the right hemisphere and
its sensitivity to weak complex magnetic fields. International Journal of Neuroscience, 112(2), 197-224.
21) Hunter, M. D., Mulligan, B. P., Dotta, B. T., Saroka, K. S., Lavallee, C. F., Koren, S. A. & Persinger,
M. A. (2010). Cerebral dynamics and discrete energy changes in the personal physical environment
during intuitive-like states and perceptions. Journal of Consciousness Exploration & Research, 1(9),
1179-1197.
22) Persinger, M. A. & Saroka, K. S. (2012). Protracted parahippocampal activity associated with Sean
Harribance. International Journal of Yoga, 5(2), 140.
23) Saroka, K. S., Dotta, B. T., & Persinger, M. A. (2013). Concurrent photon emission, changes in
quantitative brain activity over the right hemisphere, and alterations in the proximal geomagnetic field
while imagining white light. International Journal of Life Sciences and Medical Research, 3(1), 30-34.
24) Persinger, M. A., Lafreniere, G. F., & Dotta, B. T. (2012). Marked increases in background photon
emissions in Sudbury Ontario more than one week before the magnitude> 8.0 earthquakes in Japan and
Chile. International Journal of Geosciences, 3(3).
25) Vares, D. E. & Persinger, M. (2013). Predicting Quantum Random Events from Background Photon
Density Two Days Previously: Implications for Virtual-to-Matter Determinism and Changing the Future.
Journal of Nonlocality, 2(2).
26) Caswell, J. M., Dotta, B. T., & Persinger, M. A. (2014). Cerebral biophoton emission as a potential
factor in non-local human-machine interaction. NeuroQuantology, 12(1), 1-11.
27) Persinger, M.A. (2008). On the possible representation of the electromagnetic equivalents of all
human memory within the Earth’s magnetic field: Implications for theoretical biology. Theoretical
Biology Insights, 1, 3-11.
28) Krippner, S. & Persinger, M. (1996). Evidence for enhanced congruence between dreams and distant
target material during periods of decreased geomagnetic activity. Journal of Scientific Exploration, 10(4),
487-493.
29) Makare, K. & Persinger, M. A. (1987). Geophysical variables and behavior: XLIII. Negative
correlation between accuracy of card-guessing and geomagnetic activity: A case study. Perceptual and
Motor Skills, 65, 105-106.
30) Scott, M. A. & Persinger, M. A. (2013). Quantitative convergence for cerebral processing of
information within the geomagnetic environment. Journal of Signal and Information Processing, 4(3),
282-287.
31) Levy, I., Hasson, U. & Malach, R. (2004). One picture is worth at least a million neurons. Current
Biology, 14(11), 996-1001.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 341-350
350
Gaona, J. M., Colinas, F., Rouleau, N., Tessaro, L. W. E., & Caswell, J. M., Premonitions: A Global Online Statistical Tracking Study
of Precognitive Predictions
32) Pakkenberg, B. & Gundersen, H. J. G. (1997). Neocortical neuron number in humans: Effect of sex
and age. Journal of Comparative Neurology, 384(2), 312-320.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
551
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 551-555
Barušs, I., A Vision for the Society for Consciousness Studies
Guest Editorial
A Vision for the Society for Consciousness Studies
Imants Barušs*
Department of Psychology, King’s University College at The University of Western Ontario
ABSTRACT
This editorial is based on a presentation given by the author at the inaugural meeting of the Society
for Consciousness Studies at The California Institute of Integral Studies on May 31, 2014. The
author discusses the hegemony of materialism and some of the deleterious consequences of its
entrenchment in the academy. In particular, research into the nature of consciousness is curtailed,
those with demonstrated psychic abilities are oppressed, and little gets done to find effective
interventions for resolving existential anxiety. The author’s vision for the Society for
Consciousness Studies is that: (1) it is a society that values open inquiry into the nature of
consciousness; (2) its members can regard themselves as leaders who are guiding the direction of
consciousness studies; (3) practical projects can be undertaken to advance the open study of
consciousness; (4) the society can cultivate support for the discussion of existential issues,
self-transformation, and transcendent states of consciousness; and (5) the founding of the Society
for Consciousness Studies can be a turning point in the history of the study of consciousness.
Key Words: Society for Consciousness Studies, consciousness, materialism, existential anxiety,
anomalous phenomena.
There was an article in the Toronto Star newspaper on Sunday morning, March 16, 2014. “Mental
health services are strained as a growing number of teens show up at emergency rooms across
Canada with self-inflicted injuries and suicidal thoughts, say pediatric psychiatrists.” This is also a
trend in the United States. Yet these teenagers do not have the “hallmarks of a psychiatric disorder.
. . . Instead they seem to be suffering an existential crisis that is sort of ‘I’m empty, I don’t know
who I am, I don’t know where I’m going, I don’t have any grounding and I don’t know how to
manage my negative feelings’” (Auld & Bailey, 2014, p. A3). So, we have some of our youth
trying to cut, burn, and bruise their way out of an existential vacuum. And how do we, their
mentors, respond to their anguish?
The structures of Western society — our governments, financial institutions, industry, health care
systems, academic institutions, and so on — are based on a materialist doctrine. Materialist in both
of the usual senses, namely, that our activity while alive is to pursue material well-being and the
notion that all of reality can be entirely explained in terms of matter. The second of these, scientific
materialism, assures us that reality is a meaningless, incidental, mechanistic, collocation of
improbable events. So, one might as well get as many goodies as one can before being overtaken
by senescence, chronic disease, and death. And if that is all too depressing to tolerate, then there
are drugs that we can take to make us feel better. But is materialism a correct interpretation of the
nature of reality?
* Correspondence: Professor Imants Barušs, Department of Psychology, King’s University College, 266 Epworth Ave., London,
Ontario, Canada N6A 2M3. E-Mail: baruss@uwo.ca
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
552
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 551-555
Barušs, I., A Vision for the Society for Consciousness Studies
This is not the place to sort through the various definitions of materialism or the nuances of the
debate which I have previously presented in various books and papers (Barušs, 1993; 2007; 2010).
Let me just say that Pierre Gassendi, in the first half of the 17th century, reintroduced Greek
atomism into early modern thought with the notion that matter is made up of continuously existent,
indivisible atoms located within an absolute space and time (Fischer, 2014). In the 350 years since
then, the infrastructure for mounting that sort of materialist interpretation of reality has collapsed.
We now know that space is not fixed but is expanding at the rate of the Hubble flow. Determinism
has disappeared since quantum events are stochastic in nature. Time is no longer a fixed linear
stream, given that effects can temporally precede their causes in the case of delayed choice and
presentience experiments. Elementary particles do not have continuous existence. In fact, particles
do not have set positions in space until such time as one decides to look for their positions or those
positions change depending upon what else one chooses to measure (Barušs, 2010; Kochen &
Specker, 1967). These are not the kinds of properties of matter that lend themselves to a materialist
ideology. So, materialism cannot explain matter. Materialism also cannot explain the existence of
existential qualia, i.e., the sense of existence that people have for themselves. Materialism cannot
explain anomalous phenomena such as the non-local properties of consciousness. Pierre Gassendi
was an innovative Catholic priest who dared to challenge the received wisdom of his time, but this
is no longer 1650. So why are we stuck with a medieval theory of reality?
The answer is the institutionalization of materialism in the academy and other bureaucratic
structures in society. The academy is supposed to support open inquiry, critical thinking, and, in
the sciences, dependence on empirical investigation. So why do logical reasoning and objective
evidence frequently go out the window as soon as materialism is challenged? In fact, there is so
much corruption in the academy that it is difficult to do research that does not conform to the
prevailing dogma. In particular, those who dare to challenge materialism are frequently ridiculed,
bullied, and extruded from the academy (Barušs, 2010; Jahn, 2001; Tart, 2009).
This persecution has led to a culture of fear. In my experience, students are afraid that if they
choose to study anomalous phenomena for an undergraduate thesis, then they will not get accepted
to graduate school. Professors are afraid that if they discuss the evidence for the survival
hypothesis in class, then they will be censured in spite of their right to academic freedom.
Researchers are afraid that if they appear to be challenging materialism then they will not receive
funding for their research and their papers will not get published in mainstream academic journals.
And these are not just paranoid fears. And this is just the short list of the ways in which the
oppression manifests itself.
The hegemony of materialism held in place by intimidation has a number of deleterious
consequences. One problem is that it impedes research into the nature of consciousness. For
instance, if a researcher has to keep proving to granting agencies, journal and book editors, and
university administrators that good mediums produce correct information, something that has been
empirically well-established (Beischel, 2013; Braude, 2003; Schwartz, Russek, Nelson, &
Barentsen, 2001), then she cannot move on to the next step of trying to determine whether or not
dead people are the source of that information. The normal processes of science and critical
inquiry need to be able to proceed uninhibited in the exploration of the nature of consciousness
(Cardeña, 2014).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
553
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 551-555
Barušs, I., A Vision for the Society for Consciousness Studies
A second problem is that those who have demonstrated psychic abilities need to conceal those
abilities, particularly from mental health professionals. Even belief in psychic abilities is formally
a symptom of schizotypal personality disorder (American Psychiatric Association, 2013). There is
still a widespread tendency to regard anyone who manifests or claims to have such abilities as
lying, cheating, and as being mentally ill. The problem is that these abilities can be erratic,
confusing, and frightening, particularly if they begin to manifest suddenly, as they sometimes do
after near-death experiences, and the person for whom they occur is in need of some guidance for
integrating them (Barušs, 2003; Atwater, 2011).
A third problem brings us back to the opening discussion about the occurrence of existential angst
among teenagers. This is something that I understand from my own experience. I was in my
second year of Engineering Science at the University of Toronto when I became so overwhelmed
with existential questions that I simply could no longer sustain sufficient interest in engineering to
continue with it. I switched to the New Program at the University of Toronto, which allowed me to
take any course in any discipline that I wanted to take. So I took courses in philosophy,
psychology, religious studies, and anything else that I could think of that could practically help me
to answer my questions about the meaning of human existence. And, except for a course in
existential philosophy and a course in Taoism, I found nothing that deepened my understanding of
existential matters. I came to the conclusion that universities were a waste of time for anyone
interested in learning anything meaningful about the big questions concerning life and, upon
graduation, went to work for a friend of mine as a roofer.
I was halfway up the front of a roof one morning in a new subdivision in Calgary, when I put down
my hatchet, climbed down the ladder, got in my van, and drove to the University of Calgary. I
walked into the office of the graduate student advisor in the Department of Mathematics, and
asked him if they would take me. I had decided that I needed to go back inside the educational
system in order to try to make a difference. However, the only subject that I could stomach at that
time was mathematics. So, I spent four years studying mathematics and writing a thesis in
advanced logic (Barušs & Woodrow, 2013). Then I spent six months at the California Institute of
Integral Studies. Then I decided to become an expert in consciousness and spent four years at the
University of Regina getting a psychology degree. And then, for the past 27 years, in my
consciousness courses at King’s University College, I have been teaching students what I wanted
to learn in the first place.
I have found that there is such a thirst on the part of students for information about existential
issues, self-transformation, altered states of consciousness, life after death, and various types of
anomalous experiences. I frequently get comments such as “This course changed my life,” “This
is the best course that I took in my four years at Western,” “Every student should be required to
take this course,” “Don’t change a thing,” and so on. Students who have had anomalous
experiences of various sorts are afraid to talk about them for fear of being regarded as being crazy.
But in my classes, they often find a context to frame such experiences and a safe forum for their
discussion. And students who regard themselves as skeptics and say that they have never thought
about these sorts of things previously, frequently appreciate the opportunity to have their minds
stretched.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
554
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 551-555
Barušs, I., A Vision for the Society for Consciousness Studies
But it is not just students who crave an open forum for the discussion of existential issues,
anomalous phenomena, self-transformation, and so on. Robert Moore and I conducted a survey at
the second Toward a Science of Consciousness Conference in Tucson in 1996. Of the 1000
participants who received the questionnaire, 212 completed it. We found that about one third
believed that the world is a physical place and that strange things do not happen. One third
believed that strange things happen but that they could in principle be explained in physical terms.
And one third believed not only that strange things happen, but also that consciousness is
ontologically primitive (Barušs, & Moore, 1998). Where are the two thirds of consciousness
researchers who believe that strange things happen represented in the academy? Where is the one
third of consciousness researchers who think that consciousness is primary represented in the
academy? Is it just that everyone is afraid to speak up for fear of punishment?
My vision for the Society for Consciousness Studies is, first, that it is a society that values open
inquiry into the nature of consciousness without automatic deference to a materialist ideology. I
would like to see everyone empowered to conduct research into the nature of consciousness in an
atmosphere of mutual respect.
Second, rather than being marginalized in the academy, my vision is that we should see ourselves
as leaders who are guiding the direction of consciousness studies. And rather than retreating from
repressive institutions we should seek to transform them from within by asserting, as much as
possible, our right to be part of them.
Third, there are practical things that we can do to support the open study of consciousness. By our
numbers we can seek to protect those whose academic freedom is violated because they have
chosen to challenge conventional ways of thinking about consciousness. We can provide resources
for those who wish to teach courses about consciousness. We can create an endowment fund to
financially support research into consciousness. We can create annual awards that recognize
outstanding contributions to the study of consciousness. We can create a publications office to
publish academic books and journals. We can create a communications office to disseminate
information about consciousness to the public as well as to solicit financial resources for an
endowment fund. We can actively network with other organizations that support our goals. And
we can assist other academics and professionals who become interested in consciousness.
Fourth, because consciousness is closely tied to questions about the meaning of life, my vision is
that we cultivate support for the discussion of existential issues, self-transformation, and
transcendent states of consciousness that can have soteriological effects. Let us give something
practical back to today’s youth so that they not only find it unnecessary to end up in hospital
emergency wards, but offer an inspiration to the rest of us with their wisdom, compassion, and
existential equanimity. And, of course, this does not just apply to our youth. We can all use a
healthier understanding of what it means to be human.
Fifth, my vision is that at the annual convention of the Society for Consciousness Studies 100
years from now, whoever is giving the keynote talk will say that the turning point in the history of
the study of consciousness occurred as a result of the founding of the Society for Consciousness
Studies.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
555
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 551-555
Barušs, I., A Vision for the Society for Consciousness Studies
References
American Psychiatric Association. (2013). Diagnostic and statistical manual of mental disorders (5th ed.).
Arlington, Virginia: American Psychiatric Association.
Atwater, P. M. H. (2013). Near-death experiences: The rest of the story: What they teach us about living,
dying, and our true purpose. Charlottesville, VA: Hampton Roads.
Auld, A. & Bailey, S. (March 16, 2014). Psychiatrists see increase in suicidal teenagers. Toronto Star, p.
A3.
Barušs, I. (1993). Can we consider matter as ultimate reality? Some fundamental problems with a
materialist interpretation of reality. Ultimate Reality and Meaning: Interdisciplinary Studies in the
Philosophy of Understanding, 16(3–4), 245–254.
Barušs, I. (2003). Alterations of consciousness: An empirical analysis for social scientists. Washington,
DC: American Psychological Association.
Barušs, I. (2007). Science as a spiritual practice. Exeter, UK: Imprint Academic.
Barušs, I. (2010). Beyond scientific materialism: Toward a transcendent theory of consciousness. Journal
of Consciousness Studies, Controversies in Science & the Humanities, 17(7-8), 213–231.
Barušs, I. & Moore, R. J. (1998). Beliefs about consciousness and reality of participants at ‘Tucson II’.
Journal of Consciousness Studies: Controversies in Science & the Humanities, 5(4), 483–496.
Barušs, I., & Woodrow, R. (2013). A reduction theorem for the Kripke-Joyal semantics: Forcing over an
arbitrary category can always be replaced by forcing over a complete Heyting algebra. Logica
Universalis 7(3), 323–334. (DOI: 10.1007/s11787-013-0084-y)
Beischel, J. (2013). Among mediums: A scientist’s quest for answers. Tucson, Arizona: The Windbridge
Institute.
Braude, S. E. (2003). Immortal remains: The evidence for life after death. Lanham, MD: Rowman &
Littlefield.
Cardeña, E. (2014). A call for an open, informed study of all aspects of consciousness. Frontiers in Human
Neuroscience, 8, (Article 17), 1–4. (DOI: 10.3389/fnhum.2014.00017)
Fisher, S. (2014). Pierre Gassendi, The Stanford Encyclopedia of Philosophy E. N. Zalta (Ed.). URL =
http://plato.stanford.edu/archives/spr2014/entries/gassendi/
Jahn, R. G. (2001). 20th and 21st century science: Reflections and projections. Journal of Scientific
Exploration, 15(1), 21–31.
Kochen, S. & Specker, E. P. (1967). The problem of hidden variables in quantum mechanics. Journal of
Mathematics and Mechanics, 17(1), 59–87.
Schwartz, G. E. R., Russek, L. G. S., Nelson, L. A., & Barentsen, C. (2001). Accuracy and replicability of
anomalous after-death communication across highly skilled mediums. Journal of the Society for
Psychical Research, 65.1(862), 1–25.
Tart, C. T. (2009). The end of materialism: How evidence of the paranormal is bringing science and spirit
together. Oakland, CA: New Harbinger.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
arXiv:quant-ph/0508100v1 13 Aug 2005
Notes on Quantum Mechanics and
Consciousness
Elemér E Rosinger
Department of Mathematics
University of Pretoria
Pretoria, 0002 South Africa
e-mail : eerosinger@hotmail.com
Abstract
There have lately been a variety of attempts to connect, or even explain, if not in fact, reduce human consciousness to quantum mechanical processes. Such attempts tend to draw a sharp and fundamental
distinction between the role of consciousness in classical mechanics,
and on the other hand, in quantum mechanics, with an insistence on
the assumed exceptional character of the latter. What is strangely
missed, however, is the role of human consciousness as such in the
very discovery or creation of both of these physical theories. And this
a priori role is far more important than all the possible a posteriori
interplays between consciousness and the mentioned two theories of
physics, interplays which may happen during one or another specific
experiment, measurement, and so on. In this regard it is suggested
that the specific features human consciousness may exhibit during interactions with quantum mechanical systems may as well have other
explanations which do not appear to be less plausible, or less well
founded.
1. Introduction
Since the literature on the relationship between consciousness and
quantum processes is rather considerable, here for the sake of brevity,
we shall refer specifically to one rather typical sample presented by
the recent paper of Stapp.
1
For a start, let us for a moment take one or more steps back, and
from the respective perspective, note a few features which may be
relevant not only to the way one deals with the relationship between
consciousness and quantum processes, but possibly as well to the venture of quantum mechanics itself.
A deficiency, which tends to amount to a rather regrettable feature of
studies in quantum mechanics, is manifested in the fact that, subsequent to the times of John von Neumann ended in the 1950s, the main
players prove, intentionally or not, to have a manifest disregard not
only for the latest conquests of pure mathematics, but also of applied
mathematics. What pure mathematics is concerned, this means a near
unanimous limitation to concepts introduced and developed prior to
World War II, such as Hilbert spaces, C*-algebras, and the like, and
of course, to the near exclusive use of the much earlier known scalars
given by the usual real or complex numbers. On the other hand, when
it comes to applied mathematics, one cannot but note with regret that
by now classical, well established and massively used concepts are not
employed according to their full relevance and power. For instance, we
can mention in this regard linear and finite dimensional control theory,
with concepts such as ”state-space”, ”observability”, ”controlability”,
”reachability”, ”stability”, and so on, celebrated ever since the 1960s
with their successes, among others, in the Kalman-Bucy filters.
It may appear to be a first natural reaction on the part of those involved in the cutting edge pursuit of quantum mechanics to disregard
much of everything else in science. After all, it has always been a
widely accepted assumption that, according to our best present knowledge and understanding, the quantum level is underlying all else in
nature. Not to mention that quantum phenomena are so much different from whatever else we have known earlier.
However, two objections may nevertheless arise.
First, to the extent that in the study of quantum processes one goes
outside of them and deals, for instance, with consciousness, mind,
brain, or for that matter, with any other relevantly related macroscopic phenomenon, one may do well to be familiar with and make
use of the state-of-the-art concepts in these non-quantum realms.
2
Second, scientific thinking can only benefit from what in more simple
terms can be called cross-fertilization of concepts across a number of
different ventures in science, often so different as at first not to appear
being related in any relevant manner.
Another feature, ever since the 1920s, of the approaches of most of
those involved in the cutting edge pursuit of quantum mechanics has
been the relentless insistence on, and rather enthusiastic highlightening of what appeared as being the extraordinary and completely
unprecedented difference between that theory, and on the other hand,
all other earlier known theories of physics.
Such and other possibly questionable features in quantum mechanical studies have quite likely had their less than fortunate consequences.
Here in this paper we shall mean by quantum mechanics the theory
of non-relativistic quantum systems of finitely many particles.
2. Are States of Quantum Systems of Any Relevance ?
In control theory, or more at large, in general systems theory, any
given system S that is not supposed to be fixed in time is assigned a
so called ”state-space” XS which contains the set of all its different
possible relevant manifestations.
In von Neumann’s first model of quantum mechanics, Rosinger [1,
pp. 9-13], such a ”state-space” is given by the vectors ψ of a suitable Hilbert space H, vectors which are called ”wave functions”, and
which are supposed to be normalized, that is, satisfy the condition
|| ψ || = 1. Further, in this model there is also the concept of ”observable”, and it is given by self-adjoint operators A : H −→ H. Here
however one should note a certain difference, when compared with
the sense control theory uses the similarly named concept. Indeed, in
quantum mechanics by ”observable” one rather means a specific kind
of ”observation” or measurement of the quantum system, while in control theory, the term ”observable” describes an important property of
the system as a whole, and not of any of its particular observation or
3
measurement. One can recall in this regard the celebrated theorem of
Kalman, according to which a finite dimensional linear system which
is observable will also be stable, if and only if it is controllable.
Similarly, the concept of ”state-space”, and that of ”observable”, in its
quantum specific sense, are present in von Neumann’s second model,
Rosinger [1, pp. 9-13].
On the other hand, in spite of such a presence of the concept of ”statespace”, one finds as a pillar of the Copenhagen Interpretation statements such as :
”The conception of objective reality of the elementary particles has thus evaporated not into the cloud of some obscure new reality concept but into the transparent clarity of
a mathematics that represents no longer the behaviour of
the particles but rather our knowledge of this behaviour”,
Heisenberg.
In other words, the ”state-space” is no longer supposed to incorporate anything at all related to the set of all different possible relevant
manifestations of the quantum system which is under consideration.
Instead, all that the ”state-space” does - and is alleged to be able to
do - is to incorporate but the different possible relevant manifestations
of our knowledge of that quantum system.
Such a view obviously is a most remarkable - and in science, unprecedented - total renunciation of any possible ontological relation on our
part to quantum systems, and implies the total resignation to a mere
epistemological connection.
Nevertheless, the Copenhagen Interpretation does not deny that quantum system exists as such as physical entities, and that they may go
through a variety of different physically relevant manifestations, and
do so either all on their own, or in conjunction with their observation
or measurement.
Those who may find such a total renunciation + total resignation hard
to accept, among them Einstein, Schrödinger, or Bohm, may simply
ask :
4
Are physicists, and for that matter, the theories of physics,
ever to deal with the ”state-spaces” of quantum systems
in the physical sense of this concept, that is, as it is understood in all the other branches of physics, namely, ontologically ?
And if not, then who else is supposed to do it ?
And what kind of other possible scientific theories may be
able to do so ?
The Copenhagen Interpretation, instead of having a constructive approach to such questions, seems to take a special pride in the mentioned total renunciation + total resignation, and appears to do so
under the pretext of, and in direct proportion to the truly unprecedented novelty in the whole of modern science of such a controversial
position.
Naturally, scientists evermore and most eagerly aim at bringing forth
truly unprecedented novelties. The Copenhagen Interpretation is obviously not a stranger to such an attitude. What is strange and unprecedented in science, however, about that interpretation is the eagerness to pay such a considerable price renunciation and resignation
for trying to make sense out of the remarkable novelties of quantum
phenomena.
3. What Aspect of Conscious Involvement Is More
Important ?
As far as we all know, humankind got to know about classical and
quantum mechanics not as a gift from somewhere outside of itself, but
as the discovery or creation of some of its own members. And needless
to say, the respective processes of creation or discovery were acts of
human consciousness.
By the way, lest we may overlook it, it is useful to recall that classical
mechanics is by no means a closed or exhausted subject. Indeed, issues such as for instance turbulence in fluid flow, or even the existence
of regular enough solutions of the Navier-Stokes equations, are still
widely open and highly nontrivial problems.
5
In view of that one may consider that the involvement of human consciousness in classical or quantum mechanics not only starts with the
discovery or creation of the respective physical theories, and keeps
going on with their further development, but that such an ”a priori”
involvement is a far more deep and relevant manifestation of human
consciousness within the realms of physics, than any other ”a posteriori” conscious involvement during one or another specific physical
experiment.
In a manifest contradistinction to the above, a great accent is often
placed in the literature dealing with the relationship between consciousness and quantum processes on the significant difference the
consciousness of the human observer plays in classical, as opposed
to quantum mechanics.
It is for instance stated that in classical mechanics ”... all physically described properties become completely determined by physically described properties alone, with consciousness a causally inert,
or causally superfluous bystander. Correlations between the physically and psychologically described properties can be described within
a classical physics based framework, but the psychologically described
aspects will remain essentially epiphenomenal byproducts of brain activity”, Stapp.
When encountering such or similar views, and especially coming from
partial or total supporters of the Copenhagen Interpretation, the following comment is hard to avoid :
The fact that classical mechanics, as correctly described in the above
citation, is ”causally complete” only shows that at the ”a priori” stage
of involvement in it of human consciousness - namely, of those who
created or discovered it - a rather perfect job was accomplished. Consequently, in the ”a posteriori” stages of involvement of consciousness,
such as happens in the process of various experiments, human consciousness can have it so much easier, in particular, as a mere witness.
On the other hand, when it comes to quantum mechanics, if one starts
with the mentioned total renunciation + total resignation promulgated
by the Copenhagen Interpretation, and among others, replaces the
6
ontological ”state-space” with a mere epistemological one, one clearly
risks various forms ”incompleteness” in the respective theory. After
all, even the Copenhagen Interpretation does not go so far as to deny
the physical existence of quantum system as ontological entities which
go through a variety of different physically relevant manifestations.
But then, by denying the very possibility of ever reaching in any theory that physical ontology, the risk is taken for ”incompleteness”.
In this way, one may note that the attempts within the Copenhagen
Interpretation which try to connect human consciousness with the dynamics of quantum systems are to a good extent trying to support
themselves through a self-fabricated entrapment within the epistemic.
Namely
• one first denies the very possibility of an ontological theory,
• then one ends up with incompleteness, and finally
• one has a chance to introduce some active, causal role for human consciousness during certain experimental processes, in an
attempt to explain the whole range of dynamics of quantum
systems.
4. About Relative Clumsiness
When one observes, for instance, the Moon from the Earth and does
so with the naked eye, it is very hard to assume that one can cause
by that any relevant disturbance in the motion of the Moon. In other
words, such an experiment performed relating to the dynamics of the
Moon can quite safely be considered as perfectly non-invasive in terms
of that dynamics.
On the other hand, as it is well known, when we implement various
experiments in genetic engineering, many of our actions end up being
not only invasive, but simply destructive, even if they were not meant
to be so.
7
The difference between the above two situations, both of them rather
within the realms of classical mechanics, can be seen as a simple manifestation of ”relative clumsiness” on our part, having much to do with
the significant differences in the relative sizes we humans have, when
compared with the respective objects of our interest.
Compared with the typical scales in the quantum realms, the relative
difference between them and those of our human scales are far larger
than when we compare ourselves with the realms of genes.
Consequently, it does not appear too far fetched to consider the possibility that various so far disregarded invasive effects may accompany
many of the measurement and observation processes which, as usual,
bring together in interaction macroscopic devices with quantum systems. And one of the consequences of such invasiveness may possibly
be what goes under the name of the ”collapse of the wave function”,
which puts an instant end to the free dynamics of a quantum system as
described by the Schrödinger equation, and switches it to some other
state.
5. Is the Quantum World so Boringly Repetitive ?
One of the arguments brought by the Copenhagen Interpretation in
support of the impossibility of an ontological quantum theory is what
appears to be the inherent randomness of a variety of quantum phenomena, such as for instance, the radioactive decay.
As we know from a large variety of situations, randomness experienced
on a certain level when dealing with a given physical process may not
necessarily be the sign of an inherent essential aspect of the respective
process. Indeed, sometime, like in the case of statistical mechanics,
it may be the effect of an insufficient knowledge on our part of the
precise initial state of the process. Or it may be a deeper ignorance,
namely, of important aspects of the laws of dynamics of that physical
process.
In the case of quantum systems, in addition to some consideration of
8
the possible effects of the above mentioned ”clumsiness”, one should
not disregard the eventuality that, because of the same reasons of immense discrepancies of the scales involved, we may miss on certain
relevant features of quantum entities, thus exposing ourselves to what
appear as random manifestations when seen on our level.
It is indeed most surprising to note the following rather dramatic discrepancy.
On our human scales, and higher up, till the cosmic ones, it is very
hard, if not in fact impossible, to encounter among all the immensity
of the number of objects we can observe two perfectly identical ones.
On the other hand, on the atomic and on the quantum scales we make
the assumption that, say, every two electrons are absolutely the same
from whatever point of view relevant to physics.
Well, existence on the quantum or atomic scales must therefore be
just about ... infinitely boring ...
Or perhaps, not ...
In which case the various entities of the quantum realms may actually
have features relevant physically, yet so far not known to us, and thus
not taken into account.
Therefore, one possible way to see the randomness in a variety of quantum phenomena is as an effect of the combination of the ”operative
clumsiness”, mentioned in section 4, with the ”conceptual clumsiness”
pointed to above, a clumsiness manifested in our present view of seeing existence on the quantum scales so endlessly boring due to the
immense number of entities which are assumed to be perfectly identical from whatever physically relevant point of view ...
Indeed, once the ”conceptual clumsiness” of that ”boringly repetitive”
structure of the quantum realms is set aside, it is conceivable that, say
for instance, electrons or photons do in fact spread across a considerable spectrum with respect to a number of yet not known physical
features. And then, the randomness we may observe with respect to
them may be the result of the statistical distribution of such features,
features which in ways not yet known make electrons, photons, and so
9
on, behave somewhat differently during our operatively and conceptually clumsy present kind of experiments.
6. Let Us Have Some Mixture ...
In Stapp, several recent proposals relating to a quantum theory of consciousness are mentioned. One of them is due to Hameroff & Penrose,
in which three of the presently fascinating ideas are mixed together
in a somewhat ad-hoc manner, in the hope of producing an effect in
which the resulting whole may be larger than the sum of its parts.
The respective parts are the celebrated Gödel incompleteness result
of the early 1930s, the recent discovery of the microtubular structure
of the neurons, and some ideas from the ongoing and still far from
conclusive research related to quantum gravity.
A problem with such mixes of ideas is that, so often, they do not really
fit together in order to form a more organic whole. What Hameroff &
Penrose use in the hope of constituting a more genuine whole are some
suggested estimates of typical time scales of the action of gravitation
within the brain which, being of the order of tenth of a second, seem
to correlate with those associated with conscious processes.
The validity and relevance of such estimates is, however, an open
question, given that the possible actions of gravity on brain, mind,
neurological processes, or thinking, let alone the respective more precise ways of manifestation, are still highly hypothetical.
7. The Alleged Dualism of Descartes
It is fashionable to label Descartes a ”dualist”, or even ”substance
dualist”, Stapp. What is missed is a more thorough understanding of
the world-views of thinkers in Europe of those times. To mention a
few of them, Copernicus, Kepler, Galileo, Pascal, Descartes, Newton,
Leibniz, or Spinoza were deeply religious men in the Judaeo-Christian
tradition. Consequently, none of them - and this includes Descartes
as well - could possibly be anything else but fervent ”monists”.
10
As for ”dualism”, or for that matter, ”substance dualism”, chemistry
is practicing it without any objections from any quarter, and it does so
in a most successful manner, when it divides itself into its ”inorganic”
and ”organic” branches.
Biology proceeds in a yet more dramatic manner, when it makes an essential differentiation between ”living organisms” and all other forms
of matter. And such a differentiation is by no means arbitrary or
superficial. For instance, only plants are able to turn through their
metabolism inorganic, thus clearly non-living matter, into living one.
And by far most of the plants only use inorganic matter in their
metabolic processes. Animals, on the other hand, must use in their
metabolism mostly plants or other animals, since they cannot live only
on inorganic intake.
As for Descartes, his division in ”res cogitans” and ”res extensa” was
in his own view but of course about the two branches of a unique tree,
two branches which grow out from the same one and only, universal
and all encompassing, eternal grace of God’s act of creation. In this
way, what is labelled as mere ”dualism” is in the case of Descartes
but about the two surface aspects of manifestation of the fundamental ”monism” underlying, creating, and for evermore sustaining them.
In this regard, unless seen in ways similar with Descartes and his famous fellow thinkers of those older times, the so called ”mind-body”
or ”brain-mind” problems are but problems of relating together two
branches cut off a living tree, and with the tree lost, forgotten, or
denied to exist, or even to have ever existed ...
But as at the beginning of section 1, let us stop again for a moment,
and take one or more steps back, in order to gain some perspective.
Indeed, we can use that typically human ability of consciousness which
allows it to be self-referential.
And then we can ask the question :
When one thinks about solving a duality, like for instance,
that of the ”brain-mind” problem, is it not that such a
11
thinking happens under the aim of non-dualism, happens
under the sign of an intended monism ?
Therefore, either that unique tree from which the two terms of duality branched out has ever existed or not, we, by trying to solve the
problem of that duality do in fact plant a tree, a unique tree in our
own thinking, hoping that the two terms of duality may somehow be
grafted into it in an organic manner ...
This is, indeed, what we in fact do - consciously or not - when trying
to go beyond any duality ...
Here however, there seems to be quite some discrepancy between what
the ”... right hand and the left hand ...” end up doing.
For instance, Stapp lists as the first main objection to dualism its failure to provide some understanding about the ways the two dual, and
so essentially different, terms do interact. The second main objection,
Stapp, is that, in the case of the ”mind-body” problem, for instance,
the physical description already gives a causally and deterministically
complete account of what is going on. Thus the mental element of
the duality is only left as a sort of ”ghost in the machine”, with the
physical side being perfectly able to get along all on its own.
The suggested solution, Stapp, of ”quantum interactive dualism” is
claimed to evade neatly both of these major objections. Namely, the
interaction between the mental and physical is claimed to be given
by the celebrated von Neumann account of the measurement process.
The second main objection above is done away with due to the major and essential difference between classical, and on the other hand,
quantum physical processes. Indeed, the latter ones - according to the
Copenhagen Interpretation - are not causally complete, when taken
all alone and only within themselves. And then it is precisely the
mental processes which are alleged to come and complete the causal
structure, and on top of that, they also underlie the structural relationship between the elements in our streams of conscious experiences.
What is missed in such and other similar arguments is that, before
everything else, it is the unique, consistent, and persistent ”tree” of
12
the thinking of the respective physicist concerned with such a duality
which does hopefully bring together in an organic manner the two essentially different ”branches”. And the ”seed” of that ”tree” is there
- and must be there - already in the physicist’s thinking before one
or another claimed method, such as for instance von Neumann’s measurement theory, is brought in to overcome duality.
Unfortunately however, to the extent that we may not be sufficiently
aware of the typically human ability of self-referentiality of consciousness, we easily tend to miss on that ”tree” in us ... And we may also
miss, Rosinger [2], on a far more fundamental ”tree” ...
References
[1] Hameroff, S R & Penrose, R : Orchestrated reduction of quantum
coherence in brain microtubules : a model for consciousness. J.
Consciousness Studies, Vol. 3, 1996, 36-53
[2] Heisenberg, W : The representation of nature in contemporary
physics. Daedalus, Vol. 87, 1958, 95-108
[3] Rosinger, E E [1] : What is wrong with von Neumann’s theorem
on ”no hidden variables”. arXiv:quant-ph/0408191 v2
[4] Rosinger, E E [2] : Where and how does it happen ?
arXiv:physics/0505041 v2
[5] Stapp, H : Quantum mechanical theories of consciousness (to appear in ”Balckwell Companion to Cnsciousness”, 2005/6)
13 |
A temporal access code to consciousness?
Birgitta Dresp-Langley
CNRS UMR 7357
Strasbourg, FRANCE
Short title: A brain code to consciousness
Keywords: Conscious States – Biophysical Time – Resonant Brain Learning – Temporal
Activity Patterns – Time-Bin Coding
2
Abstract
While questions of a functional localization of consciousness in the brain have been the
subject of myriad studies, the idea of a temporal access code as a specific brain mechanism
for consciousness has remained a neglected possibility. Dresp-Langley and Durup (2009;
2012) proposed a theoretical approach in terms of a temporal access mechanism for
consciousness based on its two universally recognized properties. Consciousness is limited in
processing capacity and described by a unique processing stream across a single dimension:
time. The time ordering function of conscious states is highlighted and neurobiological
theories of the temporal brain activities likely to underlie such function are reviewed.
Arguments for a purely temporal access code for conscious states are discussed, including
Ramachandran’s ‘Remapping Hypothesis’, research on the ‘Coherence Index’ and
coincidence detectors, and theoretical models of adaptive resonant matching of bottom-up and
top-down representations. We conclude that a purely temporal resonance mechanism provides
the most parsimonious neurobiological explanation of consciousness and propose a ‘time-bin
resonance model’, where temporal messages for conscious state access are generated on the
basis of signal reverberation in dedicated neural circuits. When above a certain threshold,
such reverberation produces meaningful biophysical time bins in terms of specific temporal
patterns which trigger, maintain and terminate a conscious brain state. Spatial information
would be integrated into provisory topological maps at non-conscious levels through adaptive
resonant matching, but not form part of the temporal access code as such. The latter, decorrelated from the spatial code, would operate without any need for firing synchrony on the
sole basis of temporal coincidence probabilities in dedicated resonant circuits through the
progressively non-arbitrary selection of specific temporal activity patterns in the continuously
developing brain.
1. What is phenomenal consciousness?
The many different definitions of phenomenal consciousness proposed in the literature
(e.g. Kihlstrom, 1987; Natsoulas; 1983; Dennett; 1991; Posner, 1994; Block, 1995; Revonsuo,
2000; Zeman, 2001; Dietrich, 2003) disappointingly reveal that a truly operational definition
of the phenomenon as such, indispensable to its scientific investigation, has not been found,
yet. The major problem here is that to define phenomenal consciousness, we refer to
introspective considerations, as pointed out almost two centuries ago by William James
(1890). In the first book (part 4, section 6) of the Treatise of Human Nature (1740), the
3
Scottish Philosopher David Hume compared phenomenal consciousness to a theatre, a scene
of complex events where various different sensations and perceptions make their successive
appearance in the course of time:
“The mind is a kind of theatre, where several perceptions successively make their
appearance; pass, repass, glide away, and mingle in an infinite variety of postures and
sensations. There is properly neither simplicity in it at one time, nor identity in
different, whatever natural propension we may have to imagine that simplicity and
identity. The comparison of the theatre must not mislead us. They are the successive
perceptions only, that constitute the mind; nor have we the most distant notion of the
places where these scenes are represented, or of the materials of which it is
composed.”
Hume’s phenomenal description of successive perceptions appearing as sequences in time is
embedded in some contemporary views of consciousness. Less than ten years ago, the
neurobiologist Ramachandran discussed the concept of ‘self’ in relation with the concept of
‘consciousness’, and emphasized that phenomenal consciousness encompasses hardly more
than sequences of many distinct perceptions and sensations (Ramachandran, 1998). This
difficulty we seem to have in science to actually get a hold on what we call phenomenal
consciousness compromises our attempts to work out a scientifically operational definition. A
number of authors suggested that such attempts may be doomed in advance, or that we do not
dispose of enough experimental data, yet (e.g. Searle; 1998, Crick & Koch, 2000; Humphrey,
2000). Dehaene and colleagues (Dehaene, Changeux, Naccache, Sackur, & Sergent, 2006)
proposed a supposedly operational taxonomy for the scientific investigation of consciousness
based on a distinction between subliminal, preconscious and conscious processing. While
there is nothing new about this taxonomy as such, given that Kihlstrom (1987) already
proposed exactly the same three-level model twenty years ago, Dehaene et al’s distinction
between vigilant states and what they call ‘conscious report’ highlights the somewhat
sobering fact that the only means scientists have of knowing whether their human subjects are
phenomenally conscious instead of merely being in a vigilant or wakeful state is when some
event is reliably reported. This consideration may point towards a potentially operational
definition of consciousness in terms of ‘access of information to conscious report’, already
embedded in Block’s more general concept of access consciousness (e.g. 1995), but it still
poses a major problem. The immediate data of phenomenal consciousness may consist of
multiple, rapidly succeeding events that are often not coherent enough (see Hume’s argument
4
given above) to be reported as accurately as the carefully controlled events in behavioural
studies. More importantly, the contents of our consciousness are often totally disconnected
from external events or stimuli otherwise there would be no such thing as imagination or
creative thinking.
2. Where is phenomenal consciousness produced in the brain?
In the fourteenth century, well before the dawn of the Age of Enlightenment, some
physicians were trying to find the locus of the human soul in the body. With the advent of
modern functional imaging techniques, the localization of consciousness in the brain has
become the pet subject of a small industry in contemporary science. Rapid technological
progress promoting the development of imaging and electrophysiological techniques has
made it possible to correlate cognitive function with increasingly precisely located neural
activities and interactions in specific brain areas. The observation that various aspects of
conscious information processing are correlated with local or global activities in the brain is
anything but surprising, but such correlations neither explain phenomenal consciousness, nor
do they help us explain or understand how the brain achieves to render non-conscious
representations in long-term memory conscious at a given moment in time. Interestingly,
Dehaene et al. (2006) claim that considerable progress has been achieved by contrasting brain
activation images leading to conscious perception or not, some indicating that conscious
activity appears to correlate with occipital neural activity, others pointing toward a correlation
with late parieto-frontal activity (see Rees et al., 2002, for a review). At the same, the authors
conclude that the results of such studies appear inconsistent and that no coherent picture has
emerged from them. While they agree that it is important to design paradigms in which
conscious perception is not confounded with changes in behaviour, in other words the
observable stimulus-response system, their own approach does not avoid this trap. In the
experimental work of Dehaene’s group, consciousness is conceived as the result of stimulusdriven processing based on what neuroscientists refer to as ‘attentional selection’. But is
attention necessary for the brain to generate a conscious state? When we dream, i.e. in the
total absence of external stimulation, we are not wakeful and therefore not attentive to
anything, but we are phenomenally conscious of many things. Sometimes we may even be
able to access and report these phenomenal data several hours later by recounting our dreams
over breakfast.
5
Approaching the still missing link between the conscious mind and the human brain
may require some renewal in our scientific minds. Maybe some new form of theoretically
guided analysis of functional characteristics of neural activity (e.g. Buszaki, 2007) triggering
a radical shift in our ways of thinking about consciousness is just what is needed now to
produce a proper theory of how consciousness arises from the brain. For the time being,
unequivocal evidence supporting any theory that claims to link phenomenal consciousness to
the ways in which the brain works is still missing, and we have to make do with only pieces
of the puzzle that constitutes our current knowledge of functional aspects of information
processing by the brain.
3. Functional aspects of conscious and non-conscious information processing
The greatest part of the information processed by the brain is not made available to
phenomenal consciousness (e.g. Gray, 2002). Velmans (1991) even suggests that almost all
mental processes are of a non-conscious or pre-conscious nature and that consciousness is
nothing more than a by-product. An even stronger claim comes from Pockett (2004), who
argues that consciousness may only be epiphenomenal, which is somewhat reminiscent of
Lashley's (1956) now famous statement that "no activity of mind is ever conscious". Other
views consider that any mental process may operate either consciously or non-consciously,
depending on prior knowledge, experience, or practice (e.g. Schneider & Shiffrin; 1977,
Shiffrin & Schneider, 1977; Frith & Dolan, 1996; Baars, 1997; Ramsey et al, 2004).
Kihlstrom (1987) emphasized that consciousness must not be identified with any particular
perceptual-cognitive function such as stimulus discrimination, perception, memory, or the
higher mental processes involved in judgment or problem-solving. Rather, consciousness
would be an experiential quality that may accompany any of these functions. Some of them
involve what is called ‘rationality’, a process or property of the mind that is not necessarily
experienced consciously and would, according to Churchland (2002), have a skill-based
nature. In fact, conscious processing mainly seems to consist of arranging the elements of
knowledge retrieved at a given moment in time into a temporal sequence of “input” and
“output” transfers necessary to execute thoughts or actions. The periods of pure thought in
such a process may, according to Crick & Koch (2000), not be directly accessible to
consciousness, as is frequently the case in the perception of specific properties of so-called
illusory figures (e.g. Dresp & Fischer, 2000).
6
From a strictly functional point of view, there are not more than two properties of
consciousness that would be consistent with most of the experimental evidence available and
that most authors would probably agree upon: its rather limited information processing
capacity, and its expression in terms of a unique, continuously refreshed and updated stream
of processing within a limited temporal window (e.g. Duncan, 1980; Mangan, 2003; LeDoux,
2002; Dietrich, 2003). In terms of brain processing, conscious activity relies mainly on serial
processing, which allows for only a very limited amount of information to be dealt with in a
given time span. Most people cannot consciously follow two ideas at the same time, or
consciously execute two even simple, simultaneous tasks (e.g. Cherry, 1953; Baars, 1998).
This “conscious seriality” (Seth & Baars, 2005; Edelman, 2003) undeniably constrains any
possible theory of consciousness. Non-conscious activity, on the other hand, is largely based
on massively parallel processing and can therefore handle a lot more information (e.g.
Mesulam, 1990; Hochstein & Ahissar, 2002; Mangan, 2003; Dietrich, 2003). The function of
serialization in terms of an ordered list of conscious events (e.g. Page & Norris, 1998; Seth et
al, 2006), discussed already half a century ago by Lashley (1951), is linked to the hypothesis
that an event or piece of information, once made conscious, would become selectively
available to other processes involved in producing thought and speech. This function of
making non-conscious information accessible to the mind is an important achievement of
brain evolution; the limited capacity of conscious processing, on the other hand, represents a
major functional constraint, as highlighted by numerous psychophysical data which include
the observations by Triesch, Ballard, Hayhoe & Sullivan (2003) showing that observers see
sudden changes in visual scenes only and “just in time” when they need the information to
solve a specific problem.
The limited capacity of conscious processing entails that it must entirely rely on
working memory, which can handle the ‘magic’ number of about 7 representations (e.g.
Vogel, Woodman, & Luck, 2001). Such a limitation severely constrains the top-down
processes that can effectively operate within the temporal window of a conscious experience.
As proposed earlier by Mangan (2003), the pre-conscious processes at the fringe of
consciousness may provide some kind of buffer, which both compensates for and regulates
the limited conscious capacity. The processing capacity of the non-conscious, in contrast, may
be estimated within a range of at least 107 bits, knowing that the optical nerve transfers 108
bits per second (Koch, 1997), which is infinitely more than working memory can deal with,
i.e. the well-known 7±2 items demonstrated by Oberly (1928), Miller (1956), and more
recently by Parkin (1999). Treisman (1998) argued that there are too few neurons to
7
individually encode the combinatorial explosion of arbitrary conjunctions that we are capable
of processing consciously, taking as example that of a "purple giraffe with wings". This
implies that ‘purple giraffe with wings’ is coded holistically once its representation has been
internally validated, i.e. accepted by the mind as a ‘thing that makes some kind of sense’ to an
individual. Also, we believe that whenever the brain builds a complex representation, it is
inevitably matched to some past, present, or future event by a specific and purely temporal
brain mechanism. How such temporal matching could be achieved will be explained later
herein. In the course of time, a given match will either come up frequently and be
consolidated (imagine, for example, an artist becoming obsessed by purple giraffes with
wings), or it will eventually fade out. The limitations of conscious processing are defined in
terms of the representational content “authorized” to invade the conscious workspace at a
given time. Most of it would be concerned with complex objects or object relations and
transformations. This complex material is retrieved from non-conscious long-term memory,
where each integrated representation is ‘tagged’ by a specific temporal activity pattern.
Temporary retrieval of a given ‘tag’ produces what we will as of now refer to as a ‘conscious
state’.
The notion of a conscious state as a potentially operational concept for the study of
consciousness was successfully defended by Tononi & Edelman (1998) and encompasses the
earlier definition by von der Malsburg (1997) in terms of a continuous process with a limited
duration. A conscious state is not to be confounded with a state of awareness or vigilance (see
also Nielsen & Stentstrom, 2005; Dehaene et a., 2006). Although conscious states may
involve cognitive processes such as memory (e.g. Cowan, Elliott, Saults, Morey, Mattox,
Hismjatullina, & Conway, 2005), attention (e.g. Raz & Buhle, 2006), conscious report (e.g.
Crick & Koch, 2000), or volition (Grossberg, 1999; Dehaene et al., 2006), such implications
will not be discussed here. Instead, we will focus on experimental data and theoretical
arguments that further the conscious state notion as a scientifically operational concept. On
the basis of this concept, we will bring to the fore how the pieces of the puzzle may eventually
fit together and reveal a clearer picture of how brain mechanisms may trigger temporarily
available conscious representations; these sequences of unique, successive events in time or,
expressed in Humes’ or Ramachandran’s terms, ‘successive perceptions’, within a dynamic
range of relatively brief durations.
4. Temporal brain mechanisms and conscious states
8
The limits of conscious states in terms of processing capacity and duration suggest,
and may even impose, a temporal mechanism as the most parsimonious explanation for their
genesis. The Lisman-Idiart-Jensen model has been the first to make an attempt in this
direction (Lisman & Idiart, 1995, Jensen et al, 1996, Jensen & Lisman, 1996, Lisman, 1998,
Jensen & Lisman, 1998, Jensen, 2005). It postulates that a temporal pattern code only is
required to trigger and maintain a conscious state. While the conscious state may exploit
spatial or topological information linked to the representations made available, these spatial
contents remain encoded or ‘tagged’ at non-conscious levels.
Taking into account some of the experimental data and theoretical arguments
discussed above, the Lisman-Idiart-Jensen model is composed of a working memory with a
maximum processing capacity of 7±2 items. Each such item is represented by the firing of a
specific cell assembly (the so-called ‘coding assembly’) during one gamma period, the whole
phenomenon occurring in a theta period composed of approximately 7 gamma cycles.
Detailed model accounts, for the slope of the Sternberg curve (38 ms per item), for example,
were developed on the basis of this approach (Jensen & Lisman, 1998; 2005). Similarly,
Başar (1998) and Başar et al (2000) considered cognitive transfer activities to be based on
oscillations at alpha, gamma, theta, delta and other temporal frequencies which would be
‘combined like the letters of an alphabet’ to deliver a temporal code reflected through EEG
and event-related potentials (ERP), analyzed in terms of wavelets.
Whether conscious states can be approached topologically, i.e. whether they occupy a
precise and functionally delimited area in the brain like a particular prefrontal region, for
example, or whether they involve long-range interactions between areas of the brain has been
subject to debate (e.g. Dehaene & Naccache, 2001; Dehaene et al, 2003, Feinstein et al, 2004;
Dehaene et al., 2006). The heuristic value and merit of Lisman, Idiart & Jensen’s model relies
on the postulate that a conscious state can be triggered by a critical temporal activity pattern
anywhere in the brain at any given moment in time. This is a radically different way of
thinking about the brain genesis of consciousness because the latter is conceived in terms of a
firing pattern independent of the functional identity of the cells that fire. A code for conscious
state access thus would consist of a truly unique temporal pattern of activity retrieved for an
individual conscious event, and regenerated whenever required by the same set of cells
without any need for synchronous activity. Models developed by Helekar (1999) and John
(2001) have provided theoretical and empirical arguments in favour of temporal codes for
conscious state access.
9
These temporal codes are closely linked to the duration of a conscious state, or socalled ‘psychological moment’ (Pöppel & Logothetis, 1986; von der Malsburg, 1999; Tononi
& Edelman, 1998), with variations in the limited dynamic range of a few hundreds of
milliseconds. This has been established on the basis of a considerable body of psychophysical
and neurobiological data (e.g. Lehmann et al, 1987; Lestienne & Strehler, 1988; Thorpe &
Imbert, 1989; Crick & Koch, 1990; Potter, 1993; Strik & Lehmann, 1993; Gray, 1995;
Pascual-Marqui et al, 1995; Taylor, 1996; Koenig & Lehmann, 1996; Lehmann et al, 1998;
von der Malsburg, 1999; Bressler & Kelso, 2001; Chun & Marois, 2002). The work of Libet
(1993; 2003; 2004), for example, has shown that a time minimum of about 500 ms is required
for a near-threshold stimulus to produce a conscious perceptual experience. From an
evolutionary viewpoint, the upper limit of a conscious state would correspond to some
temporal duration beyond which a newly triggered conscious state, making representations
potentially relevant to survival available, would be likely to come too late. In order to analyze
neural patterns in terms of the temporal codes they deliver, the duration of a conscious state is
to be divided into critical time windows, or 'bins', the length of which would be limited by the
accuracy of neuronal timing, or the lower limit of biophysics. Such a time window, or ‘bin’,
has been expressed by the parameter t which would, in principle, represent the sum of
standard deviations for the time delay of synaptic transmission including the duration of the
refractory period. An average estimate of 6 ms for this parameter appears reasonable in light
of the data available (Bair, 1999). Helekar (1999) based his calculations of a temporal code on
an average duration of 3 ms for t, operating under the hypothesis of an average estimate of
only 30 ms for a state duration, expressed in terms of the parameter t. An average value of 6
ms for t would be consistent with ‘bin’ durations proposed by Shastri & Ajjanagadde
(1993), Moore & King (1999), or Rieke et al (1997). Yoshioka & Shiino (1998) suggested 10
ms and Singer (2000) times no longer than 10 ms. Interspike intervals and integration times of
cortical neurons are within a similar dynamic range (Eggermont, 1998).
Under the simple assumption that within each ‘bin’ there is either a signal or no signal,
derived from McCullough & Pitts’ (1943) germinal work on information transmission in
neural networks, the information content of each bin is 1 bit. On the basis of an average
duration of 300 ms for a given conscious state, which seems more realistic than the 30 ms
state duration suggested by Helekar, a 6 ms duration for a critical time window or ‘bin’ within
that state, and with a deterministic signal being generated during each ‘bin’, the information
content of such a conscious state would be 300/6 = 50 bits. A similar computation of the
10
maximum quantity of information conveyed by a duration t with a number of temporal
windows identified by a given t was proposed by MacKay & McCulloch (1952).
Considering there are equal probabilities for activity (signal) and non-activity (no signal)
within each ‘bin’, a conscious state of a duration of 300 ms would then generate 61 bits of
content (for t = 6 ms). This theoretical approach is detailed in Rieke et al (1997), who also
point out that actual neuronal systems approach the assumed theoretical limit of information
transmission. The figures given above may be compared with estimates of the number of
visual prototypes held in memory, given by Tsotsos (1990), which correspond to information
contents of 17 to 23 bits. Similar time-based coding schemes were suggested later by Thorpe
et al (2001) and VanRullen et al (2005). The biophysical code for conscious state access is
defined in terms of critical temporal activity patterns that trigger and maintain conscious
states. This code has the considerable advantage of operating independently from the
functional identity of the neurons delivering it or the spatial ‘tags’ contained in the
subjectively experienced events. The dynamic analysis of correlated oscillations in cortical
areas at various frequencies (e.g. Bassett et al, 2006) and the study of functional interactions
between gamma and theta oscillations in various structures of the brain (e.g. Axmacher et al,
2006) represent promising approaches here.
None of the existing neural models of cognition proposes a clear division between the
functioning mode of processors or circuits generating conscious brain data from that of
processors generating non-conscious events. In the light of the evidence considered above, we
have serious doubts that any plausible functional account for human consciousness can be
expected from a spatial model. If all the complex spatial brain data we may experience when
in a conscious state were, indeed, part of the code for conscious states, then how would they
be organized and reliably deciphered? A unifying, purely temporal code provides a ready and
perfectly plausible answer here. The mechanisms for the generation of such a temporal code
for conscious state access would be based on the functional characteristics of reverberating
brain activity. Reverberation (Abeles et al, 1993; Edelman, 1993; Crick, 1994; Grossberg,
1999; Constantinidis et al, 2002; Lau & Bi, 2005; Dehaene et al., 2006) would, among other
things, explain how the immense variety of afferent input triggering a multitude of brain
signals eventually leads to the critical temporal patterns for conscious state access.
Reverberant neural activity has been studied in thalamo-cortical (Llinás et al, 1998; Llinás &
Ribary, 2001; VanRullen & Koch, 2003) and in cortico-cortical pathways (Steriade, 1997;
Pollen, 1999; Lamme, 2004; 2006). Reverberation is a temporal process that generates feedback loops in the brain, described by various authors in terms of ‘re-entrant circuits’
11
(Edelman, 1989; 1993, Tononi et al, 1992; 1998, Tononi & Edelman, 1998; 2000, Edelman &
Tononi, 2000; Fuster, 2000; Prinz, 2000; Di Lollo et al, 2000; Klimesch et al, 2001; Edelman,
2003; Robertson, 2003; Crick & Koch, 2003; 2005), and successfully implemented in fractal
neural network models of the brain (e.g. Bieberich, 2002). Reverberation readily explains how
the brain copes with situations where two or more representations with similar or identical
probabilistic weights are trying to invade the conscious workspace at one and the same
moment in time. Without reverberation, the conscious execution of focussed action would be
difficult, if not impossible (e.g. Lamme, 2006). Two successive conscious states need to be
separated by at least the time the brain needs to inactivate the current temporal access code
and to generate the new one. If not separated from each other in time, the different sustained
neural activities producing the critical temporal patterns would inevitably interfere with each
other, like representations in short-term memory are annihilated by new input if they are not
maintained through rehearsal (Potter, 1993).
5. Arguments for a temporal access code to consciousness
The idea of a purely temporal access code for consciousness as the most parsimonious
link between brain and mind (Dresp-Langley & Durup, 2009; 2012) is compelling in the light
of several theoretical arguments. If spatial coding took place within consciousness, the brain
would have to integrate so many signals from multi-channel cross-talk that a reliable and
unifying coding scheme seems almost inconceivable. We suggest that, for generating access
to capacity-limited spatial and temporal representations within consciousness, the temporal
code is de-correlated from the spatial code. De-correlation is an important notion in neural
network theory and systems theory in general. It describes a mechanism that reduces crosstalk
between multi-channel signals in a system (like the brain) but preserves other critical signal
properties. As a reminder, we should like to emphasize that the term ‘code’ originally stems
from information theory and may stand for both 1) an entire system of information
transmission or communication (like the brain) where symbols are assigned definite meanings
and 2) a set of symbols for the content of a given message (like a temporal activity pattern)
within that system. One of the major arguments in favour of a purely temporal access code for
conscious brain states would be its undeniable adaptive advantage.
5. 1 Adaptive advantage and epigenetic plausibility
12
Many authors have insisted on the important adaptive function of consciousness
(Gray, 1971, 1995; Crick & Koch, 1995, Koch & Crick, 2000, de Charms & Zador, 2000). In
line with their considerations and arguments, Helekar (1999) proposed a genetically
programmed code for consciousness arising from non-arbitrary linkages between temporal
firing patterns and subjective experience in a similar way as the genetic code arises from nonarbitrary linkage of anticodons and their cognate codons. Helekar was the first to fully realize
that encoding conscious states by a single, unifying parameter would represent a considerable
adaptive advantage compared with spatio-temporal codes, which would be far too complex
and definitely more costly in terms of allocation of neural resources. Whether evolution has
produced genes that drive conscious state generation, or whether this capacity would rather be
a consequence of epigenetic development is subject to debate.
If there is such a thing as a genetic code for conscious states, then why did evolution
not push the processing capacity of conscious states? Baars (1993) and Newman and Baars
(1993) argued that nature would have calculated the trade-off between the benefits and the
costs of increasing the processing capacity of consciousness, with the result that such an
increase would have been too costly a process to justify its, assumedly minor, advantage.
Such reasoning was countered by Pockett (2004), who argued that conscious capacity
compared with the immense resources of non-conscious processes would represent only about
1/100.000 of brain capacity available, and that an increase in conscious capacity through
evolution would not have been costly at all. We believe that, under the hypothesis of a purely
temporal mechanism for conscious state access within a limited dynamic range of durations,
not increasing the processing capacity of conscious brain states represents a sound strategy of
evolution. For the sake of economic resource allocation, evolution has made a smart choice by
only pushing non-conscious resources, i.e. the capacity of the brain to generate and integrate
increasingly complex non-conscious representations. Making these fully integrated
representations then available to consciousness remains the sole task of the temporal access
code, with no need to increase conscious processing capacity any further. Also, during
ontogenetic brain development representations remain largely non-conscious for a long time
before some of them eventually become the subjectively and holistically experienced data of a
human being’s phenomenal consciousness, at the age of two or three. Sensory,
somatosensory, and proprioceptive signals may instantly be perceived as the immediate data
of a conscious state, eliciting what psychophysicists call sensations, but these are
continuously integrated into representations by non-conscious mechanisms. This, among other
things, explains the striking similarities between descriptions of objects resulting from direct
13
perception and from pure imagination (Kosslyn, 1994; 1999; Kosslyn et al, 2001). Because of
their considerable adaptive advantage as well as the adaptive properties of the brain
mechanism underlying their genesis, which we will discuss later, we suggest that the origin of
the temporal activity patterns for conscious state access is epigenetic.
5.2 Functional plasticity and Ramachandran’s spatial ‘re-mapping hypothesis’
The integration of signals originating from the different sensory modalities into
topologically coded representations has to be sufficiently adaptable and it has to display a
certain functional plasticity to enable the continuous updating of these representations as a
function of changes in contents. Such changes are imposed on our brains day by day by new
situations and experiences. Yet, to be made available to consciousness, there has to be some
permanently reliable, unifying “tag” for these continuously updated, re-integrated
representations to ensure a stable access over time irrespective of changes in contents.
Grossberg (1999) referred to this problem as the “plasticity-versus-stability dilemma” and
proposed resonant brain learning mechanisms as a potential solution. While these latter
satisfactorily resolve the dilemma at the level of non-conscious information processing, they
fail to explain how non-conscious representations would become available to consciousness.
By the vague claim that not all resonant brain mechanisms generate conscious representations,
but that all conscious representations would be based on resonant mechanisms, without
specifying the functional characteristics that would generate the passage from one to the
other, Grossberg re-introduces the plasticity-versus-stability dilemma at the level of the
functional transition between non-conscious and conscious states. This particular point will be
discussed further in our chapter on ‘Adaptive resonance and Grossberg’s dilemma’.
Some compelling observations which reveal the extraordinary plasticity of spatial and
topological coding in the brain have been reviewed by Ramachandran (1998). These include
the author’s own experimental work on so-called ‘phantom limbs’ (e.g. Ramachandran,
Rogers-Ramachandran, & Cobb, 1995), a phenomenon first described in 1872 and repeatedly
observed in hundreds of case studies since. After arm amputations, patients often experience
sensations of pain in the limb that is no longer there, and experimental data show that a third
of such patients systematically refer stimulations of the face to the phantom limb, with a
topographically organized map for the individual fingers of a hand. On the basis of similar
evidence for massive changes in somatotopic maps after digit amputation, and other
experimental data showing that several years after dorsal rhizotomy in adult monkeys, the
14
region corresponding to the hand in the cortical somatotopic map of the primate’s brain is
activated by stimuli delivered to the face (Merzenich et al, 1984), Ramachandran and his
colleagues proposed their ‘remapping hypothesis’ (e.g. Ramachandran, RogersRamachandran & Stewart, 1992). The latter clarifies how spatial and topological
representations are referred to other loci in the brain through massive cortical re-organization.
The findings reported by Ramachandran and others deliver compelling elements of proof that,
despite dramatic changes in non-conscious topology, representations remain available to
conscious state access and may still experienced in terms of sensations such as pain, cold,
digging or rubbing. This phantom-like persistence of conscious representation in time but not
in space is possibly one of the strongest arguments for conscious state access through a
temporal code independent of, or de-correlated from, the spatial code.
5.3 The temporal ‘coherence index’ and coincidence detection
In his ‘neurophysics of consciousness’, John (2001, 2002) suggests that a conscious
state may be identified with a brain state where information is represented by levels of
coherence among multiple brain regions, revealed through coherent temporal firing patterns
that deviate significantly from random fluctuations. This assumption is consistent with the
idea of a reliable temporal code for conscious state access despite spatial remapping through
cortical re-organization. Empirical support for John’s theory comes from evidence for a tight
link between electroencephalographic activity in the gamma range defined by temporal firing
rates between 40 and 80 Hz (i.e. the so-called ‘40-Hz’ or ‘phase-locked’ gamma oscillations)
and conscious states (e.g. Engel et al, 1992). This ‘coherence index’, with its characteristic
phase-locking at 40 Hz, was recently found to change with increasing sedation in anaesthesia,
independent of the type of anaesthetic used (Stockmanns et al, 2000), with decreasing
temporal frequencies when doses of a given anaesthetic were increased. Moreover, the
characteristic phase-locking at 40 Hz displays coherence not only across brain regions during
focussed arousal, but also during REM sleep, when the subject is dreaming (Llinás & Ribary,
1993). Coherence disappears during dreamless, deep slow-wave sleep, which is consistent
with the findings reported on deeply anesthetized patients referred to above. The fact that the
temporal coherence index of a conscious state is produced during focussed arousal as well as
in dream states is completely consistent with the view that dreams, imaginations, or
daydreams represent genuine conscious states in the absence of wakefulness and external
trigger stimuli.
15
The phase-locking at the critical temporal frequency would be achieved through intracortical reverberation, enabled by a digital event within a hybrid system, according to John’s
terminology (John, 2001, 2002). This hybrid system, the brain, establishes non-random
departures from different loci or topological maps. These latter may undergo functional reorganization, yet, the temporal code for conscious state access remains coherent. This would
lead to cortico-thalamic feedback loops, or resonance loops which generate the temporal
access codes for conscious states through probability-based detection of memory events
coinciding in time. The mechanisms which would explain how memory events are read out
and compared in the brain were discussed by Grossberg in his Adaptive Resonance Theory
(1975; 1999).
5.4 Adaptive resonance in the continuously learning brain
Originally, Adaptive Resonance Theory (ART) was conceived as a theory of brain
learning to explain how the brain generates and updates representations of continuously
changing physical environments (Grossberg, 1975). More recently, ART was extended to
account for related phenomena such as attention and intention or volition. According to
Grossberg (1999), the link between these three could be described by the fact that intentions
would lead to focus attention on potentially relevant internal or external events. These foci of
attention would lead to new representations when the system (the brain) is able to validate and
integrate them into resonant states, which would include, according to Grossberg, the
conscious states of the brain. According to the theory, all conscious states would be resonant
states, triggered either by external or internal events and mediated by either attention or
volition. Thisnas such, however, does not explain how non-conscious representations would
become available to ongoing consciousness. In our analysis, this is a direct consequence of
the fact that the theory fails to separate spatial from temporal coding and thereby fails to
resolve Grossberg’s stability-versus-plasticity dilemma at the level of the transition from nonconscious representation to conscious state access (see chapter 6.2 above). Adaptive
resonance theory nonetheless plausibly explains how the brain ensures the continuous
updating of non-conscious representations through a mechanism termed top-down matching,
which produces the so-called resonant brain states.
A resonant brain state would be achieved through the repeated matching of external or
internal events in short-term or working memory to internal events activating top-down
representations. According to the theory, the brain is continuously confronted with ongoing
16
internal or external representations (bottom-up) and therefore has to continuously generate
probabilistic hypotheses to determine what all these transitory events are most likely to be and
whether they are relevant. This involves matching the ongoing representations to
representations stored in long-term memory (top-down). Coincidence of bottom-up
representations and top-down representations (top-down-matches) would produce so-called
matching signals, or coincidence signals which, when repeatedly generated, lead to resonant
states in the brain. The representations generated through top-down matching of brain signals
would be, according to Grossberg, coded topologically in the ‘What’ and ‘Where’ processing
streams of the brain (see Grossberg, 1999 for an extensive review of relevant physiological
data), and what he calls “the resonant code” is therefore tightly linked to functional
topological organization. The question how non-consciously encoded topological information
would be made available to consciousness is left unanswered. We propose that the resonance
states corresponding to conscious states arise from temporal integration only, given that only
non-conscious states would dispose of enough capacity to integrate signals across both time
and space. How reverberation of temporal signals, probabilistic signal coincidence detection
and adaptive resonance in dedicated neural circuits would produce what we call the temporal
access code for conscious states is explained in the following chapter, which introduces our
own model.
6. The ‘time-bin’ code
While there is no empirically based description of resonators receiving, amplifying
and transmitting time-patterned messages in the brain, it is nevertheless certain that a large
number of physical and biophysical phenomena can be plausibly and parsimoniously
explained on the basis of resonance principles or mechanisms. We believe it makes good
sense that evolution (see 6.1 above) would have produced brains capable of generating
conscious states on the basis of resonance mechanisms. How this may work, is shown in our
model here.
6.1 Underlying assumptions
It is likely that biological resonators, in contrast to “ordinary” resonance devices
designed by humans, would almost certainly have highly sophisticated operating principles,
given that hundreds of functionally different kinds of cells exist in the brain. On the other
17
hand, there is no reason why resonators in the brain would have to function with a high level
of precision, provided they operate according to some redundancy principle and the whole
ensemble of cells producing a conscious resonance state behaves in a statistically predictable
way. Our model conception of temporal signal sequences forming a specific biophysical
‘time-bin’ pattern that activates, maintains, and inactivates a conscious state is certainly and
inevitably a simplification of reality. Such a simplification does, however, not affect the
internal validity of the model arguments presented here. The principal aim of our model is to
explain how a ‘time bin resonance system’ would generate conscious brain states on the basis
of a relatively limited amount of neural resources.
Given the known temporal properties of conscious information processing, we
suppose that conscious states may generate messages corresponding to variable contents in
terms of bit sequences corresponding to variable durations. Any of these conscious states
would be identified by a unique sequence of 1s and 0s. Thus, in the same way as bar codes
provide the key to an almost infinite variety of things, such temporal sequences provide the
key to consciously experienced brain events. A given temporal code would be generated
spontaneously at a given moment in early brain development and would then eventually be
reproduced and consolidated during brain learning (see Figure 2). Consolidation would be a
result of repeated reverberation in cortical memory circuits, leading to resonance states which
correspond to more or less specific conscious states. Once a resonance circuit has been
consolidated for a given temporal sequence, a resonant state is automatically activated
whenever there is a statistically significant temporal coincidence between representations at a
given moment in time. As long as the threshold of statistically significant coincidence is not
attained, representations in the resonance circuit remain non-conscious or pre-conscious.
Counting from a first signal, or spike, in biophysical time, the resulting temporal
sequence of 1s and 0s may be described as a succession of intervals (q) between 1's. Let us
imagine a network of brain cells, or a resonator, with a functional architecture or connectivity
described by the shapes of closed polygons (see Figure 1 for an illustration), with a variable
number q of apices and the same number of edges. Each apex of such a polygon would
correspond to a neuron which can receive or emit input or output signals from and to
processors anywhere in the brain as well as along the specific tracks of the resonant circuit
that was primed during brain development for a specific temporal pattern tagging a conscious
state. Here, we refer to the apices of our network model in terms of dedicated principal
resonant neurons. Each edge of a polygon would represent a delay path which transmits
signals from a given apex to the next, with a characteristic delay corresponding to some
18
multiple of the elementary ‘bin’ unit (t, as defined earlier by others in other models
discussed earlier here). The distribution of these delays should fit the proportion of 1's and 0's
in typical ‘time-bin’ messages: if, for example, 1's are as likely to occur in a code as 0's, then
the proportions of various delays t, 2t, ..., nt would be predictable. The delay paths as
such would correspond to local neural architectures in the brain. Whatever the effective
operational structure of such a resonance circuit, its specific temporal characteristics would be
experience-dependent and consolidated during development.
A brain or system operating on the basis of purely temporal resonance principles
would work as follows. All principal resonant neurons would have been primed during brain
development to preferentially process statistically significant signals. Thus activated, principal
resonant neurons would send signals along all delay paths originating from them, and all those
receiving a signal coinciding with the next input signal would remain activated. The
connections between principal resonant neurons of the circuit would thereby be potentiated, as
in the classical Hebbian model. Simultaneously, signals travelling from initially activated
neurons to connected cells with too long delay paths would be cancelled. Thus, once a given
polygon of a resonant network is potentiated along all of its edges, it would reverberate
temporally coinciding signals while amplifying more and more the potentiation of the
resonant connections. Now, let us consider the example of a simple sensorimotor task, which
can be performed either consciously or non-consciously. Obviously, the message sent by the
sensory system has to be decoded by the motor system. This would happen via non-conscious
signal exchanges between functionally specialized neuronal assemblies. A conscious state,
where the content of the representations activated by these signal exchanges between
functionally specialized systems in the brain becomes subjectively experienced data of
consciousness, is only triggered if the temporal coincidence between signals reverberating
within resonant circuitry generates levels of potentiation beyond a given statistical threshold.
How neuronal circuits would be able to learn statistical temporal information embedded in
distributed patterns of activity was recently discussed by Gutig & Sompolinski (2006).
A network model of dedicated temporal resonance circuitry with a polygone shaped
architecture may also generate quantitative predictions, as could be demonstrated by
numerical simulations. If we consider, for example, a model structure with only 10 000
principal resonant neurons, each connected to only 5 others, numerical simulations would
show that we then would have a resonant circuit that is able to reverberate signals, contents,
or messages coding for biophysical time spans up to 50 bin. Whether a resonant circuitry
reverberating bin codes for conscious state access would be localized or distributed all over
19
the brain becomes irrelevant in regard to the probabilistic temporal coincidence hypothesis. It
seems plausible, and likely to us, that inter-connected resonant circuits would develop all over
the cortex during lifespan brain learning.
6. 2 Developmental selection of non-arbitrary temporal activity patterns
Like time-bin resonance itself, the selection of the critical temporal firing patterns that
constitute the access code for conscious states use purely statistical criteria leading to fewer
and fewer consolidated patterns for increasingly complex and integrated signal coincidences
as our brain learns and develops. When we are born, all brain activity is more or less random.
During brain development, temporal activity patterns elicited by events in biophysical time (t)
ranging from 30 to approximately 500 ms (as explained above) will be linked to particular
conscious experiences in a decreasingly arbitrary manner as frequently occurring, highly
likely (‘relevant’) codes are progressively consolidated through a process called
‘developmental selection’. This is illustrated in Figure 2, which is our adaptation of Figure 6
from Helekar’s (1999) original paper. The model approach we propose here thereby resolves
a critical problem in Helekar’s model by explaining how non-arbitrary linkage of codes and
contents is put into place progressively by developmental processes within dedicated resonant
circuits of the brain. These developmental processes would operate on the basis of selective
matching with a statistic temporal coincidence criterion, as explained above. In fact, once a
given temporal code has been arbitrarily linked to a conscious state, it would remain
potentially available as a ‘brain hypothesis’, which may then be repeatedly confirmed and
consolidated or not. Once consolidated, the linkage of a code to content is non-arbitrary, or
deterministic.
6.3 From temporal activity patterns to dynamic resonant coding
In his model, Helekar proposes a one-to-one non-arbitrary linkage between elements
of subjective experience and specific temporal activities of neuronal assemblies. Nonarbitrary linkage would be, according to Helekar, innate and genetically driven. The
mechanisms that execute these non-arbitrary operations are, as pointed out by Helekar
himself, unknown. Once again, we find ourselves confronted with theoretical reasoning in
terms of some kind of obscure superstructure. To overcome this problem with Helekar’s
model, we propose a selection mechanism that would operate on the basis of probabilistic
20
learning in the memory circuits of the brain during lifespan development, progressively
leading to deterministic and non-arbitrary temporal activity patterns for conscious state
access. Helekar’s “elementary experience-coding temporal activity patterns” were conceived
in terms of a subset of neural firing patterns belonging to the set of all possible temporal
patterns that can be generated by the brain. The original hypothesis states that only those
patterns that are members of the subset would give rise to elementary subjective experiences,
or conscious states, upon their repeated occurrence; repeated occurrence of so-called noncoding patterns would not give rise to conscious states. The problem with this approach is that
the contents we may subjectively, or consciously, experience are also represented nonconsciously in the brain. Helekar suggested that it would be the subjective nature of
phenomenal consciousness per se that is genetically determined, which brings us right back to
the “old” question, pointed out by Hume centuries ago and cited above: what is phenomenal
consciousness? To avoid this old trap, our model proposes that conscious state access is based
on ‘time-bin’ patterns corresponding to a temporally deterministic resonance state in
dedicated circuits. How such states are consolidated outside consciousness through the
repeated matching of current representations to representations in long-term memory is
explained in Grossberg’s theory (1999), discussed earlier here.
6.4 From dynamic resonant coding to biophysical eigenstates
What distinguishes a conscious state from a non-conscious state in our model would
solely depend on a probabilistic criterion. A brain mechanism achieving coincidence
computation would lead to the activation of a given temporal resonance code at a given time
on the basis of a statistical coincidence criterion, or coincidence threshold. While Helekar
(1999) suggested that the subjective nature of the conscious experience per se would
determine an innate and genetically pre-wired temporal code, we propose a brain mechanism
that would produce such a code through resonant learning in terms of temporal matches
independent of the subjective nature of phenomenal consciousness. A conscious state would
arise from a temporarily retrieved resonance state, tagged by a specific temporal pattern and
generated within reverberating neural circuits which are updated outside consciousness during
lifespan brain development. In fact, what is called “experience” in common language is recoded in the brain in terms of temporal signal sequences in purely biophysical time.
The statistical coincidence of specific temporal sequences would activate, maintain,
and inactivate conscious states in the brain like a bar code activates, maintains, or inactivates
21
the electronic locks of a safe. Given the almost infinite number of signal sequences that are
possible in such a code, there is no reason why there should not be a unique temporal pattern
for a unique conscious state. In terms of quantum physics analogy, the time-bin resonance
model suggests that non-conscious states are described by temporal wavefunctions which do
not have a well-defined period. While a non-conscious state may be a combination of many
non-specific eigenstates, resonant activity beyond the probabilistic coincidence threshold
produces the well-defined temporal activity pattern or wavefunction of a single specific
eigenstate, the ‘conscious eigenstate’.
7. Conclusions
A large part of the recent theoretical and empirical work devoted to the question of
consciousness has consisted of trying to correlate conscious mental representations with
neural activity in specific regions of the brain. Questions about a mechanism for the brain
genesis of conscious activity have been neglected and there still is an immense explanatory
gap between subjective conscious experience and brain functions. The problem at the root of
this explanatory gap has become quite clear: the immediate data of phenomenal consciousness
are too complex and often totally disconnected from any external stimuli or events to provide
the basis for a scientifically operational definition of consciousness. In this article, we present
an analysis that focuses on functional constraints of so-called conscious states, in line with
definitions proposed earlier by others (e.g. Tononi & Edelman, 1998). We then show how the
limited processing capacity and the unique stream of information processing in time that
universally describe conscious states lead the way to a scientifically operational definition,
which encompasses what we refer to as ‘the time ordering function’ of conscious states,
where complex past, present and future events are represented in one and the same moment of
conscious time. On the basis of a selective and thorough review of relevant experimental and
theoretical data on temporal characteristics of conscious states, we propose a theory of
conscious state access based on an epigenetic, biophysical code. The latter would be
composed of resonant temporal activity patterns in the brain, generating time bins of several
milliseconds each, with a few hundreds of milliseconds for a given conscious state. The
probabilistic coincidence of resonance signals in time only provides the unique brain activity
patterns that trigger, maintain, and terminate a conscious state like a bar code activates,
maintains, or inactivates the electronic locks of a safe. The specific temporal patterns for
conscious state access would be consolidated during brain development.
22
This suggests that our conscious brains become connected with the physical world in
the course of their development, which is to be conceived in terms of a lifelong process. In a
way similar to that of sonar systems which connect to the outside by acquiring some form of
knowledge of a physical environment, conscious states are encoded in our brains in terms of
some critical temporal base frequency as through scanning or pulsing. Although a conscious
state may be experienced in any form of psychological space or time, the associated
biophysical periods in the brain ‘scale’ this experience through a completely self-sufficient
code. This explains how the inner clocks of consciousness can operate independently from
spatial, verbal or any other form of cognitive or emotional experience. The brain does not care
about the “exciting”, “creative”, “active”, “boring”, or “passive” subjective nature of
conscious experience, which may lead to variations in subjectively experienced time later
recalled as “time was flying by” or “time was standing still” (see Figure 4), it contents itself
with scaling the signals produced by such events in its own, biophysical time.
The temporal code model addresses the mind-body problem at its very root. Some
time ago, Nagel (1974) insisted that, in order to understand the hypothesis that a mental event
is a physical event, we require more than the understanding of the word ‘is’, and that what we
need most would be some plausible idea of how a mental and a physical term might refer to
one and the same thing. Here, we have proposed such an idea and taken the risk of
simplifying the question of consciousness at a moment where neuroscientists are struggling
with a mass of evidence for complex correlates between consciously reported perceptions and
spatio-temporal firing activity in functionally specialized cortical areas. In the ever thickening
forest of facts and conjectures, a few will eventually stand out and become landmarks on the
path of the science of consciousness. The fascinating experiments by Ramachandran and
colleagues (e.g. Ramachandran, 1998), revealing the independence of conscious sensation
from constraints imposed by topological cortical organization, supports the idea that
conscious state access is not generated by any spatio-temporal code. The recent theoretical
work by Lazar, Pipa, & Triesch (2007) on interactions between spike timing dependent and
intrinsic synaptic plasticity in recurrent neural networks for the dynamic genesis of specific
sequences or series of temporal activity patterns points towards future developments that may
further our understanding of the functional characteristics of temporal brain codes. As for
now, a temporal access code de-correlated from topological functional organization seems the
most parsimonious explanation of how consciousness arises from brain function on the basis
of mechanistic principles that take into account what we believe to have learnt about the
brain.
23
References
Abeles, M., Bergman, H., Margalit, E., & Vaadia, E. (1993). Spatiotemporal firing patterns in
the frontal cortex of behaving monkeys. Journal of
Neurophysiology, 70, 1629-1638.
Axmacher, N., Mormann, F., Fernandez, G., Elger, C.E., & Fell, J. (2006). Memory formation
by neuronal synchronization. Brain Research Reviews, 52, 170182.
Baars, B.J. (1993). How does a serial, integrated and very limited stream of consciousness
emerge from a nervous system that is mostly unconscious, distributed,
parallel and of enormous capacity ? In: Experimental and theoretical studies of consciousness
(Ciba Foundation Symposium 174), pp 282-303. Chichester, NY: Wiley.
Baars, B.J. (1997). In the Theater of Consciousness. New York and Oxford: Oxford
University Press.
Baars, B.J. (1998). Metaphors of consciousness and attention in the brain. Trends
inNeurosciences, 21, 58-62.
Bair, W. (1999). Spike timing in the mammalian visual system. Current Opinion in
Neurobiology, 9, 447-453.
Bassett, D.S., Meyer-Underberg, A., Achard, S., Duke, T., & Bullmore, E. (2006). Adaptive
reconfiguration of fractal small-world human brain functional
networks. Proceedings of the National Academy of Sciences of the USA, 103, 19518-19523.
Başar, E. (1998). Brain functions and oscillations, I. Brain oscillations: Principles and
approaches. Berlin: Springer.
Başar, E., Başar-Eroglu, C., Karakaş, S., & Schürmann, M. (2000). Brain oscillations in
perception and memory. International Journal of Psychophysiology,
35, 95-124.
Bieberich, E. (2002). Recurrent fractal neural networks: a strategy for the exchange of local
and global information processing in the brain. BioSystems, 66, 145164.
Block, N. (1995). On a confusion about a function of consciousness. Behavioral and Brain
Sciences, 18, 227-287.
Bressler, S.L., & Kelso, J.A.S. (2001). Cortical coordination dynamics and cognition. Trends
in Cognitive Sciences, 5, 26-36.
24
Bullock, T.H., Bennett, M.V.L., Johnston, D., Josephson, R., Marder, E., & Fields, R.D.
(2005). The neuron doctrine, redux. Science, 310, 791-793.
Buzsaki, G. (2007). The structure of consciousness. Nature, 446, 267.
Cherry, E.C. (1953). Some experiments on the recognition of speech, with one and two ears.
Journal of the Acoustical Society of America, 25, 975-979.
Chun, M.M., & Marois, R. (2002). The dark side of visual attention. Current Opinion in
Neurobiology, 12, 184-189.
Churchland, P.S. (2002). Brain-Wise. Studies in Neurophilosophy. Cambridge, MA: MIT
Press.
Constantinidis, C., Williams, G.V., & Goldman-Rakic, P.S. (2002). A role for inhibition in
shaping the temporal flow of information in prefrontal cortex. Nature
Neuroscience, 5, 175-180.
Cowan, N., Elliott, E.M., Saults, J.S., Morey, C.C., Mattox, S., Hismjatullina, A., & Conway,
A.R.A. (2005). On the capacity of attention: Its estimation and its
role in working memory and cognitive aptitudes. Cognitive Psychology, 51, 42-100.
Crick, F. (1994). The astonishing hypothesis: the scientific search for the soul. New York:
Simon and Schuster.
Crick, F., & Koch, C. (1990). Towards a neurobiological theory of consciousness. Seminars
in Neuroscience, 2, 263-275.
Crick, F., & Koch, C. (1995). Are we aware of neural activity in primary visual cortex?
Nature, 375, 121-123.
Crick, F., & Koch, C. (2000). The unconscious homunculus. Neuro-psychoanalysis, 2, 3-11.
Crick, F., & Koch, C. (2003). A framework for consciousness. Nature Neuroscience, 6, 119126.
De Charms, R.C., & Zador, A. (2000). Neural representations and the cortical code. Annual
Review of Neuroscience, 23, 613-647.
Dehaene, S., & Naccache, L. (2001). Towards a cognitive neuroscience of consciousness:
basic evidence and a workspace framework. Cognition, 79, 1-37.
Dehaene, S., Sergent, C., & Changeux, J.P. (2003). A neuronal network model linking
subjective reports and objective physiological data during conscious
perception. Proceedings of the National Academy of Sciences of the USA, 100, 8520-8525.
Dehaene, S., Changeux, J. P., Naccache, L., Sackur, J., & Sergent C. (2006). Conscious,
preconscious and subliminal processing: a testable taxonomy. Trends in
Cognitive Science, 10, 204-211.
25
Delorme, A., Rousselet, G. A., Mace, M. J., & Fabre-Thorpe, M. (2004) Interaction of topdown and bottom-up processing in the fast visual analysis of natural
scenes. Cognitive Brain Research, 19, 103-113.
Dennett, D.C. (1991). Consciousness explained. Brown: Little.
Dennett, D. (2001). Are we explaining consciousness yet? Cognition, 79, 221-237.
Dietrich, A. (2003). Functional neuroanatomy of altered states of consciousness: the transient
hypofrontality hypothesis. Consciousness and Cognition, 12, 231256.
Di Lollo, V., Enns, J.T., & Rensink, R.A. (2000). Competition for consciousness among
visual events: The psychophysics of re-entrant visual processes. Journal of Experimental
Psychology: General, 129, 481-507.
Dresp, B., & Fischer, S. (2001). Asymmetrical contrast effects induced by luminance and
color configurations. Perception & Psychophysics, 63, 1262–1270.
Dresp-Langley, B. & Durup, J. (2009). A plastic temporal brain code for conscious state
generation. Neural Plasticity, 482696. doi: 10.1155/2009/482696.
Dresp-Langley, B. & Durup, J (2012). Does consciousness exist independently of present
time and present time independently of consciousness? Open Journal of Philosophy, 2, 45-49.
doi: 10.4236/ojpp.2012.21007.
Duncan, J. (1980). The locus of interference in the perception of simultaneous stimuli.
Psychological Review, 87, 272-300.
Edelman, D.B., Baars, B.J., & Seth, A.K. (2005). Identifying hallmarks of consciousness in
non-mammalian species. Consciousness and Cognition, 14, 169-187.
Edelman, G.M. (1989). The Remembered Present. New York: Basic Books.
Edelman, G.M. (1993). Neural Darwinism: selection of re-entrant signalling in higher brain
function. Neuron, 10, 115-125.
Edelman, G.M. (2003). Naturalizing consciousness: a theoretical framework. Proceedings of
the National Academy of Sciences of the USA, 100, 5520-5524.
Edelman, G.M., & Tononi, G. (2000). Re-entry and the dynamic core: neural correlates of
conscious experience. In: Neural Correlates of Consciousness: Empirical and Conceptual
Questions, T. Metzinger (ed.), pp 139-151. Cambridge, MA: MIT Press.
Eggermont, J.J. (1998). Is there a neural code? Neuroscience and Biobehavioral Reviews, 22,
355-370.
26
Engel, A., Konig, P., Kreiter, A., Schillen, T., & Singer, W. (1992). Temporal coding in the
visual cortex: new vistas on integration in the nervous system. Trends in Neurosciences, 15,
218-226.
Feinstein, J.S., Stein, M.B., Castillo, G.N., & Paulus, M.P. (2004). From sensory processes to
conscious perception. Consciousness and Cognition, 13, 323-335.
Fellin, T., & Carmignoto, G. (2004). Neurone-to-astrocyte signalling in the brain represents a
distinct multifunctional unit. Journal of Physiology, 559, 3-15.
Fields, R.D. (2004). The other half of the brain. Scientific American, 290 (4), 54-61.
Frith, C., & Dolan, R. (1996). The role of the prefrontal cortex in higher cognitive functions.
Cognitive Brain Research, 5, 175-181.
Fuster, J.M. (2000). Cortical dynamics of memory. International Journal of
Psychophysiology, 35, 155-164.
Gray, J.A. (1971). The mind-brain identity theory as a scientific hypothesis. Philosophical
Quarterly, 21, 247-252.
Gray, J.A. (1995). Consciousness and its (dis)contents. Behavioral and Brain Sciences, 18,
703-722.
Gray, J.A. (2002). To thine own synapses be true? Nature Neuroscience, 5, 1115.
Gross, C.G., & Sergent, J. (1992). Face recognition. Current Opinion in Neurobiology, 2,
156-161.
Grossberg, S. (1975) A neural model of attention, reinforcement and discrimination learning.
International Review of Neurobiology, 18, 263-327.
Grossberg, S. (1999). The link between brain learning, attention, and consciousness.
Consciousness & Cognition, 8, 1-44.
Gutig, R., & Sompolinski, H. (2006). The tempotron: a neuron that learns spike timing-based
decisions. Nature Neuroscience, 9, 420-428.
Guttman, S.E., Gilroy, L.A., & Blake, R. (2007). Spatial grouping in human vision: Temporal
structure trumps temporal synchrony. Vision Research, 47, 219-230.
Helekar, S.A. (1999). On the possibility of universal neural coding of subjective experience.
Consciousness and Cognition, 8, 423-446.
Herrmann, C.S., Munk, M.H., & Engel, A.K. (2004). Cognitive functions of gamma-band
activity: memory match and utilisation. Trends in Cognitive Sciences, 8, 347-355.
Hochstein, S., & Ahissar, M. (2002). View from the top: hierarchies and reverse hierarchies in
the visual system. Neuron, 36, 791-804.
27
Holmgren, C., Harkang, T., Svennenfors, B., & Zilberter, Y. (2003). Pyramidal cell
communication within local networks in layer 2/3 of rat neocortex. Journal of
Physiology, 551, 139-153.
Hume, D. (1740). A Treatise of Human Nature. Oxford: Oxford University Press.
Humphrey, N. (2000). How to solve the mind-body problem. Journal of Consciousness
Studies, 7 (4), 5-112.
James, W. (1890). Principles of Psychology. New York: Holt.
Jensen, O., Idiart, M.A.P., & Lisman, J.E. (1996). Physiologically realistic formation of
autoassociative memory in networks with theta/gamma oscillations - role of fast NMDA
channels. Learning and Memory, 3, 243-256.
Jensen, O., & Lisman, J.E. (1996a). Novel tests of 7±2 known items can be reliably stored in
on oscillatory short-term memory network: interaction with long-term memory. Learning and
Memory, 3, 257-263.
Jensen, O., & Lisman, J.E. (1996b). Theta/gamma networks with slow NMDA channels learn
sequences and encode episodic memory: Role of NMDA channels in recall. Learning and
Memory, 3, 264-278.
Jensen, O., & Lisman, J.E. (1996c). Hippocampal region CA3 predicts memory sequences:
accounting for the phase precession of place cells. Learning and Memory, 3, 279-287.
Jensen, O., & Lisman, J.E. (1998). An oscillatory short-term memory model can account for
data on the Sternberg task. Journal of Neuroscience, 18, 10688-10699.
Jensen, O. (2005). Reading the hippocampal code by theta phase-locking. Trends in Cognitive
Sciences, 9, 551-553.
Jensen, O., & Lisman, J.E. (2005). Hippocampal sequence-encoding driven by a cortical
multi-item working memory buffer. Trends in Neuroscience, 28, 67-72.
John, E.R. (2001). A field theory of consciousness. Consciousness and Cognition, 10, 184258.
John, E.R. (2002). The neurophysics of consciousness. Brain Research Reviews, 39, 1-28.
Kihlstrom, J.F. (1987). The cognitive unconscious. Science, 237, 1445-1452.
Klausberger, T., Magill, P.J., Marton, L.F., Roberts, J.D.B., Cobden, P.M., Buzsaki, G., &
Somogyi, P. (2003). Brain-state- and cell-type-specific firing of hippocampal interneurons in
vivo. Nature, 421, 844-848.
Klimesch, W., Doppelmayr, M., Yonelinas, A., Kroll, N.E.A., Lazzara, M., Röhm, D., &
Koch, C. (1997). Computation and the single neuron. Nature, 385, 207-210.
28
Koch, C., & Crick, F. (2000). Some thoughts on consciousness and neuroscience. In: The New
Cognition Neurosciences, 2nd edn., M.S. Gazzaniga (ed.), pp 1285-1294. Cambridge, MA:
MIT Press.
Koenig, T., & Lehmann, D. (1996). Microstates in language-related brain potential maps
show noun-verb differences. Brain and Language, 53, 169-182.
Kosslyn, S.M. (1994). Image and brain: the resolution of the imagery debate. Cambridge,
MA: MIT Press.
Kosslyn, S.M. (1999). If neuroimaging is the answer, what is the question? Philosophical
Transactions of the Royal Society of London B, 354, 1283-1294.
Kosslyn, S.M., Ganis, G., & Thompson, W.L. (2001). Neural foundations of imagery. Nature
Reviews Neuroscience, 2, 635-642.
Lamme, V.A.F. (2004). Separate neural definitions of visual consciousness and visual
attention: a case for phenomenal awareness. Neural Networks, 17, 861-872.
Lamme, V.A.F. (2006). Towards a true neural stance in consciousness. Trends in Cognitive
Sciences, 10, 494-501.
Lamme, V.A., & Roelfsema, P.R. (2000). The distinct modes of vision offered by
feedforward and recurrent processing. Trends in Neurosciences, 23, 571-579.
Lashley, K. (1951). The problem of serial order in behavior. In: Cerebral Mechanisms in
Behavior, L.A. Jeffress (ed.), pp 112-136. New York: Wiley.
Lashley, K.S. (1956). Cerebral organisation and behavior. In: The Brain and Human
Behavior. Proceedings of the Association for Nervous and Mental Diseases, pp 1-18. New
York: Hafner.
Lau, P.-M., & Bi, G.-Q. (2005). Synaptic mechanisms of persistent reverbatory activity in
neuronal networks. Proceedings of the National Academy of Sciences of the USA, 102,
10333-10338.
Lazar, A., Pipa, G., & Treisch, J. (2007) Fading memory and time series prediction in
recurrent networks with different forms of plasticity. Neural Networks, 20, 312-322.
LeDoux, J. (2002). Synaptic self. How our brains become who we are. New York: Macmillan.
Lehmann, D., Ozaki, H., & Pal, I. (1987). EEG alpha map series: brain microstates by space
oriented adaptive segmentation. Electroencephalography and Clinical Neurophysiology, 67,
271-288.
Lehmann, D., Strik, W.K., Henggeler, B., Koenig, T., & Koukkou, M. (1998). Brain electric
microstates and momentary conscious mind states as building blocks of spontaneous thinking.
I. Visual imagery and abstract thoughts. International Journal of Psychophysiology, 29, 1-11.
29
Lennie, P. (2003). The cost of cortical computation. Current Biology, 13, 493-497.
Lestienne, R., & Strehler, B.L. (1988). Differences between monkey visual cortex cells in
triplet and ghost doublets informational symbol relationships. Biological Cybernetics, 59,
337-352.
Libet, B. (1993). The neural time factor in conscious and unconscious events. In:
Experimental and theoretical studies of consciousness, pp 282-303. Chichester, NY: Wiley.
Libet, B. (2003). Timing of conscious experience. Consciousness and Cognition, 12, 321-331.
Libet, B. (2004). Mind time. Cambridge, MA.: Harvard University Press.
Lin, L., Osan, R., & Tsien, J.Z. (2006). Organizing principles of real-time memory encoding:
neural clique assemblies and universal neural codes. Trends in Neuroscience, 29, 48-57.
Lisman, J.E. (1998). What makes the brain's tickers tock? Nature, 394, 132-133.
Lisman, J.E., & Idiart, M.A.P. (1995). Storage of 7±2 short-term memories in oscillatory
subcycles. Science, 267, 1512-1515.
Llinás, R., & Ribary, U. (1993). Coherent 40-Hz oscillation characterizes dream states in
humans. Proceedings of the National Academy of Science USA, 90, 2078-2081.
Llinás, R., Ribary, U., Contreras, D., & Pedroarena, C. (1998). The neuronal basis for
consciousness. Philosophical Transactions of the Royal Society of London B, 353, 1841-1849.
Llinás, R., & Ribary, U. (2001). Consciousness and the brain: the thalamocortical dialogue in
health and disease. Annals of the New York Academy of Sciences, 929, 166-175.
Maccaferri, G., & Lacaille, J.-C. (2003). Interneuron diversity series: Hippocampal interaction
classification - making things as simple as possible, not simpler. Trends in Neurosciences, 26,
564-571.
Machens, C.K., Romo, R., & Brody, C.D. (2005). Flexible control of mutual inhibition: a
neural model of two-interval discrimination. Science, 307, 1121-1124.
MacKay, D.M., & McCulloch, W.S. (1952). The limiting information capacity of a neuronal
link. Bulletin of Mathematical Biophysics, 14, 127-135.
Malsburg, C. von der (1997). The coherence definition of consciousness. In: Cognition,
Computation and Consciousness, M. Ito, Y. Miyashita, & E.T. Rolls (eds.), pp 193-204.
Oxford: Oxford University Press.
Malsburg, C. von der (1999). The what and why of binding: the modeler's perspective.
Neuron, 24, 95-104.
Mangan, B. (2003). The conscious "fringe": bringing William James up to date. In: Essential
Sources in the Scientific Study of Consciousness, B.J. Baars, W.P. Banks, & J.B. Newman
(eds.), pp 741-759. Cambridge, MA: MIT Press.
30
McCullough, W., & Pitts, W. (1943) A logical calculus of ideas imminent in nervous activity.
Bulletin of Mathematical Biophysics, 5, 115-133.
Merzenich, M. M., Nelson, R. J., Stryker, M. S., Cyander, M. S., Schoppmann, A., & Zook,
J. M. (1984). Somatosensory cortical map changes following digit amputation in adult
monkeys. Journal of Comparative Neurology, 224, 591-605.
Mesulam, M.M. (1990). Large-scale neuro-cognitive networks and distributed processing for
attention, language, and memory. Annals of Neurology, 28, 597-613.
Miller, G.A. (1956). The magic number seven, plus or minus two: some limits on our capacity
for processing information. Psychological Review, 63, 81-97.
Milner, A.D. (1995). Cerebral correlates of visual awareness. Neuropsychologia, 33, 11171130.
Moore, D.R., & King, A.J. (1999). Auditory perception: the near and far of sound
localization. Current Biology, 9, 361-363.
Nagel, T. (1974). What is it like to be a bat? The Philosophical Review, 83, 435-450.
Natsoulas, T. (1983) Concepts of consciousness. Journal of Mind and Behavior, 4, 13-59.
Nedergaard, M., Ransom, B., & Goldman, S.A. (2003). New roles for astrocytes: Redefining
the functional architecture of the brain. Trends in Neurosciences, 26, 523-530.
Nelson, S.B. (2002). Cortical microcircuits: diverse or canonical. Neuron, 36, 19-27.
Newman, J., & Baars, B.J. (1993). A neural attentional model for access to consciousness: a
global workspace perspective. Concepts in Neuroscience, 4, 255-290.
Nielsen, T.A., & Stenstrom, P. (2005). What are the memory sources of dreaming? Nature,
437, 1286-1289.
Oberly, H.S. (1928). A comparison of the spans of attention and memory. American Journal
of Psychology, 40, 295-302.
Page, M.P.A., & Norris, D. (1998). The primacy model: a new model of immediate serial
recall. Psychological Review, 105, 761-781.
Parkin, A.J. (1999). Human memory. Current Biology, 9, 582-585.
Pascual-Marqui, R.D., Michel, C.M., & Lehmann, D. (1995). Segmentation of brain electrical
activity into microstates: model estimation and validation. IEEE Transactions on Biomedical
Engineering, 42, 658-665.
Pockett, S. (1999). Anesthesia and the electrophysiology of auditory consciousness.
Consciousness & Cognition, 8, 45-61.
Pockett, S. (2004). Does consciousness cause behaviour? Journal of Consciousness Studies,
11 (2), 3-4.
31
Pollen, D. (1999). On the neural correlates of visual perception. Cerebral Cortex, 9, 4-19.
Pöppel, E., & Logothetis, N. (1986). Neuronal oscillations in the human brain.
Naturwissenschaften, 73, 267-268.
Posner, M.I. (1994). Attention: the mechanisms of consciousness. Proceedings of the
National Academy of Sciences of the USA, 91, 7398-7403.
Potter, M.C. (1993). Very short-term conceptual memory. Memory & Cognition, 21, 156-161.
Prinz, J. (2000). A neurofunctional theory of visual consciousness. Consciousness and
Cognition, 9, 243-259.
Ramachandran, V. S. (1998) Consciousness and body image: lessons from phantom limbs,
Capgras Syndrome and pain asymbolia. Philosophical Transactions of the Royal Society of
London B, 353, 1851-1859.
Ramachandran, V. S., Rogers-Ramachandran, D., & Stewart, M. (1992) Perceptual correlates
of massive cortical reorganization. Science, 258, 1159-1160.
Ramachandran, V. S., Rogers-Ramachandran, D., & Cobb, S. (1995) Touching the phantom
limb. Nature, 377, 489-490.
Ramsey, N.F., Jansma, J.M., Jager, G., Van Raalten, T., & Kahn, R.S. (2004).
Neurophysiological functions in human information processing capacity. Brain, 127, 517-525.
Ransom, B., Behar, T., & Nedergaard, M. (2003). New roles for astrocytes (stars at last).
Trends in Neurosciences, 26, 520-522.
Raz, A., & Buhle, J. (2006). Typologies of attentional networks. Nature Reviews
Neuroscience, 7, 367-379.
Rees, G., Wojciulik, E., Clarke, K., Husain, M., Frith, C., & Driver, J. (2002). Neural
correlates of conscious and unconscious vision in parietal extinction. Neurocase, 8, 387-393.
Revonsuo, A. (2000). Prospects for a scientific research program on consciousness. In: Neural
Correlates of Consciousness: Empirical and Conceptual Questions, T. Metzinger (ed), pp 5775. Cambridge, MA: MIT Press.
Ridderinkhof, K.R., & van den Wildenberg, W.P.M. (2005). Adaptive coding. Science, 307,
1059-1060.
Rieke, F., Warland, D., de Ruyter van Steveninck, R., & Bialek, W. (1997). Spikes: exploring
the neural code. Cambridge, MA: MIT Press.
Robertson, L.C. (2003). Binding, spatial attention and perceptual awareness. Nature Reviews
Neuroscience, 4, 93-102.
Rosenthal, D.M. (1986). Two concepts of consciousness. Philosophical Studies, 49, 329-359.
32
Rosenthal, D.M. (2002). How many kinds of consciousness? Consciousness and Cognition,
11, 653-665.
Roth, G. (2000). The evolution and ontogeny of consciousness. In: Neural Correlates of
Consciousness: Empirical and Conceptual Questions, T. Metzinger (ed.), pp 77-97.
Cambridge, MA: MIT Press.
Schneider, W., & Shiffrin, R. M. (1977). Controlled and automatic human information
processing: 1. Detection, search, and attention. Psychological Review, 84, 1-66.
Schwartz, S. (2003). Are life episodes replayed during dreaming? Trends in Cognitive
Sciences, 7, 325-327.
Seth, A.K., & Baars, B.J. (2005). Neural Darwinism and consciousness. Consciousness and
Cognition, 14, 140-168.
Seth, A.K., Izhkevich, E., Reeke, G.N., & Edelman, G.M. (2006). Theories of measures of
consciousness: An extended framework. Proceedings of the National Academy of Sciences of
the USA, 103, 10799-10804.
Shastri, L., & Ajjanagadde, V. (1993). From simple association to systematic reasoning: A
connectionist representation of rules, variables, and dynamic bindings using temporal
synchrony. Behavioral and Brain Sciences, 16, 417-494.
Sheinberg, D.L., & Logothetis, N.K. (1997). The role of temporal cortical areas in perceptual
organization. Proceedings of the National Academy of Sciences of the USA, 94, 3408-3413.
Shiffrin, R. M., & Schneider, W. (1977). Controlled and automatic human information
processing: 2. Perceptual learning, automatic attending, and a general theory. Psychological
Review, 84, 127-190.
Shiffrin, R.M. (2003). Attention, automatism, and consciousness. In: Essential Sources in the
Scientific Study of Consciousness, B.J. Baars, W.P. Banks, & J.B. Newman (eds.), pp 631642. Cambridge, MA: MIT Press.
Silberberg, G., Gupta, A., & Markram, H. (2002). Stereotypy in neocortical microcircuits.
Trends in Neurosciences, 25, 227-230.
Singer, W. (2000). Phenomenal awareness and consciousness from a neurobiological
perspective. In: Neural Correlates of Consciousness: Empirical and Conceptual Questions, T.
Metzinger (ed.), pp 121-137. Cambridge, MA: MIT Press.
Steriade, M. (1997). Synchronized activities of coupled oscillators in the cerebral cortex and
thalamus at different levels of vigilance. Cerebral Cortex, 7, 583-604.
Stockmanns, G., Kochs, E., Nahm, W., Thornton, C., & Kalkmann, C.J. (2000). Automatic
analysis of auditory evoked potentials by means of wavelet analysis. In: Memory and
33
Awareness in Anaesthesia IV, D.C. Jordan, D.J.A. Vaughan and D.E.F. Newton (eds.), pp.
117-131. London: Imperial College Press.
Taylor, J.G. (2002). Paying attention to consciousness. Trends in Cognitive Sciences, 6, 206210.
Thorpe, S.J., & Imbert, M. (1989). Biological constraints on connectionist models. In:
Connectionism in Perspective, R. Pfeifer, Z. Schreter, & F. Fogelman-Soulié (eds.), pp 63-92.
Amsterdam: Elsevier.
Thorpe, S., Delorme, A., & Van Rullen, R. (2001). Spike-based strategies for rapid
processing. Neural Networks, 14, 715-725.
Tononi, G., Sporns, O., & Edelman, G.M. (1992). Re-entry and the problem of integrating
multiple cortical areas: simulation of dynamic integration in the visual system. Cerebral
Cortex, 2, 310-335.
Tononi, G., & Edelman, G.M. (1998). Consciousness and complexity. Science, 282, 18461851.
Treisman, A. (1998). Feature binding, attention and object perception. Philosophical
Transactions of the Royal Society of London B, 353, 1295-1306.
Triesch, J., Ballard, D. H., Hayhoe, M. M., & Sullivan, B. T. (2003). What you see is what
you need. Journal of Vision, 3, 86-94.
Tsotsos, J.K. (1990). Analyzing vision at the complexity level. Behavioral and Brain
Sciences, 13, 423-445.
Van Rullen, R., & Thorpe, S.J. (2001). Rate coding versus temporal order coding: what the
retinal ganglion cells tell the visual cortex. Neural Computation, 13, 1255-1283.
VanRullen, R., & Koch, C. (2003). Is perception discrete or continuous? Trends in Cognitive
Sciences, 7, 207-213.
VanRullen, R., Guyonneau, R., & Thorpe, S.J. (2005). Spike times make sense. Trends in
Neurosciences, 28, 1-4.
Velmans, M. (1991). Is human information processing conscious ? Behavioral and Brain
Sciences, 14, 651-669.
Vogel, E.K., Woodman, G.F., & Luck, S.J. (2001). Storage of features, conjunctions, and
objects in visual working memory. Journal of Experimental Psychology: Human Perception
and Performance, 27, 92-114.
Volterra, A., & Meldolesi, J. (2005). Astrocytes, from brain glue to communication elements:
The revolution continues. Nature Reviews Neuroscience, 6, 626-640.
34
Yamazaki, Y., Hozumi, Y., Kaneko, K., Li, J., Fujii, S., Miyakawa, H., Kudo, Y., & Kato, H.
(2005). Direct evidence for mutual interactions between perineuronal astrocytes and
interneurons in the CA1 region of the rat hippocampus. Neuroscience, 134, 791-802.
Zeman, A. (2001). Consciousness. Brain, 124, 1263-1289.
35
Figure 1: Genesis of resonance states in a dedicated circuit with five principal resonant
neurons acting as ‘coincidence detectors’
a)
b)
36
Figure 2: Developmental selection of temporal activity patterns coding for conscious state
access
brain
circuitry
temporal activity patterns
randomly generated in the brain
activity-dependent
plasticity and brain
development
dedicated
resonant
circuitry
selected temporal activity
patterns generated in dedicated
resonant circuitry
37
Figure 3: “Top-down matching” (after Grossberg, 1997, 1999) generates resonant brain
activity for non-conscious memory representation at a given moment in time
long-term
memory
top-down
resonance layer
bottom-up
short-term
or working
memory
38
Figure 4: The conscious eigenstate (after Dresp-Langley and Durup, 2009) as a function of
biophysical and subjectively recalled time
conscious eigenstates
brain state vector
temporal activity patterns
resonant code patterns
biophysical time T
subjectively
recalled time
‘non-conscious’
or ‘pre-conscious’
brain states
‘conscious’ states
« excitement »
« boredom »
39
Figure captions
Figure 1
Figure 1a illustrates how a dedicated resonant circuit with five principal resonant neurons
acting as coincidence detectors may be formed. Each apex of a given polygon would
correspond to a principal resonant neuron which can receive or emit input or output signals
from and to processors anywhere in the brain as well as along the specific tracks of the
resonant circuit that has been primed in the course of brain development for a specific
temporal pattern signalling for a conscious state. Unidirectional priming only is shown here,
for illustration. Each edge of a polygon would represent a delay path which would transmit
signals from a given apex to the next, with a characteristic delay that would correspond to
some multiple of the elementary ‘bin’ unit (t, as explained in section 5.3). All principal
resonant neurons would have been primed throughout lifespan brain development to
preferentially process input which carries statistically ‘strong’ signals. Thus activated,
principal resonant neurons would send signals along all delay paths originating from them,
and all those receiving a signal coinciding with the next input signal would remain activated.
The connections between principal resonant neurons of such a model would be thereby
potentiated, like in the classic Hebbian model. Figure 1b shows some of the many possible
excitation patterns within a dedicated resonance circuit with only five principal neurons.
Figure 2
Figure 2 illustrates schematically how the critical temporal activity patterns for conscious
state access would be progressively selected through activity dependent plasticity during
lifespan brain development. At birth, a potentially infinite number of temporal activity
patterns would be generated more or less randomly in the neural circuits of the brain. As brain
learning progresses, repeated bottom-up-top-down matches (see Figure 3) of current brain
events to learnt memory representations would generate resonant states in reverberating
circuits which then progressively become dedicated resonant circuits. Whenever the firing
patterns produced by these dedicated resonance circuits reach a statistical temporal
coincidence threshold, the temporal firing pattern generated then would activate a conscious
brain state. Thus, the temporal code of our ‘time bin resonance’ model would unlock the door
to consciousness in a similar way as some bar code would unlock the door of an electronically
protected safe.
40
Figure 3
Figure 3 illustrates schematically how Grossberg’s Adaptive Resonance Theory (1999)
accounts for the matching of bottom-up signals generated by current events to top-down
signals generated by representations activated in long-term memory. This matching process is
termed “top-down matching” and explains how non-conscious representations may be
updated at any given moment in time via resonant circuitry in the brain.
Figure 4
Figure 4 illustrates how a conscious eigenstate of the brain may be conceived as part of a state
vector as a function of biophysical time (T) and subjectively recalled time (). In our model,
the duration of a conscious eigenstate would correspond to a given number of biophysical
‘time bins’. Biophysical time (t) is independent of the subjectively recalled duration of a given
experience by a human individual, and would correspond to the duration of the critical
temporal activity pattern produced by dedicated resonant circuits (Figure 1) to activate,
maintain and inactivate a conscious eigenstate. Our ‘time bin model’ thus explains how the
inner clocks of consciousness can operate independently from subjective experience, where
variations from “interesting” to “dull” may produce variable, subjectively recalled durations
of events. |
434
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
Article
Effect of Yoga & Meditation on Consciousness & Mindfulness
Sona Ahuja*
Dayalbagh Educational Institute, India
Abstract
The effect of yoga and meditation on consciousness and mindfulness were examined comparing
beginners, intermediate, advanced meditators and a group of non-meditators. The three
experimental groups improved from pre-test to post-test compared to control group, highlighting
the benefits of yoga and meditation on consciousness and mindfulness. Consciousness of
advanced meditators was highest in comparison to other groups at pre-test. Consciousness and
mindfulness of beginners increased at a faster rate over time. Further, the effect of intervention
was examined on physical, emotional, cognitive, social, spiritual and self-consciousness. There
was significant increase in social and self-consciousness after 11 weeks of intervention whereas
physical and emotional consciousness increased significantly post intervention which was for 20
weeks. Although there was increase in cognitive and spiritual consciousness but it was not
significant. A longer duration of practice may prove helpful for betterment of these faculties.
Key Words: Yoga, meditation, physical consciousness, emotional consciousness, mental
consciousness, social consciousness, self-consciousness, spiritual consciousness.
Introduction
Consciousness has been discussed in the last century from varied perspectives ranging from
general to domain specific viz. self-consciousness, spiritual consciousness, emotional
consciousness, etc. It has become a significant topic of research by neuro-scientists and cognitive
scientists in recent years. While the science of consciousness in ancient India as given in Vedas
and Upanishads dates back to second millennia B.C.; it is over the past 50 years or so there has
been considerable interest in the modern science in the West, in terms of cognitive psychology
and neuro-science (neuro-physiology or neuro-medicine) in studying the consciousness
(Satsangi, 2010). Neuro-scientists relate consciousness to the brain whereas in modern scientific
psychology, the mind is largely equated with consciousness. There is also scientific and
philosophical research into the nature and basis of consciousness (Baars, Banks& Newman,2003;
Chalmers, 1996; Crick, 1984; Dennett, 1992). Philosophers sometimes use the technical term
‘qualia’ to refer to the subjective texture of experience (Dennett, 1988; Chalmers, 1996).
Psychologists also claim that consciousness is a subjective experience (Brazdau& Mihai, 2011;
Charlton, 2000).
In the past decades, attempts have been made to psychological theorizing of this concept,
identifying research methods to define and assess consciousness and to apply statistical methods
*
Correspondence:Sona Ahuja, PhD, Dayalbagh Educational Institute,India. sonaahujadei@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
435
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
to quantify it. The subjective knowledge of human sentient entities, if based on facts and correct
application of indicative reasoning, should not, even in the abstract, be, relegated to the category
of illusions(Satsangi, 2013).The conscious processes can be operationally defined and it has been
proved that consciousness can be researched as a variable (Baars, Banks, Newman, 2003;
Brazdau& Mihai, 2011). The present scenario of research in consciousness reflects attempts to
find the neural and psychological correlates of consciousness.The factors influencing
consciousness and factors influenced by consciousness are being studied. In laboratory settings,
neuro-scientists are also making efforts to study consciousness of meditators.Meditation holds an
important place in experimental framework of consciousness research as it is believed to trigger
altered states of consciousness (Lutz, Dunne, & Davidson, 2007;Thompson, 2006; Varela,
Thompson, &Rosch, 1999).Scientific interest in meditation also reflect a recent shift in cognitive
science toward viewing the integration of consciousness and first-person experience as a
valuable object of scientific investigation(Braboszcz, Hahusseau, Delorme, 2010). When
meditative awareness deepens—with aid of meditation and other practices (Goleman, 1988)—
altered states and psychic phenomena become more common (Wade,1996).There are different
types of meditative practices but self-regulation of attention is the most common among all of
them. In the West, the word meditation means a concentrated state of mind in serious
reflection.In the East, however, meditation does not mean thinking at all but fixing the mind in a
spiritual ideal, to be one with it, or the thought-process dissolving in the consciousness of it. The
effect of various meditational practices including transcendental meditation, mindfulness,
focused attention, loving kindness meditation, etc. is studied on different domains.
In eastern philosophy, yoga is associated with meditation for spiritual practices.Yoga is a
commonly known generic term for physical, mental, and spiritual disciplines which originated in
ancient India.In a national survey, long-term yoga practitioners in the United States reported
musculo–skeletal and mental health improvements (Birdee, Legedza, Saper, Bertisch, Eisenberg,
and Philips,2008). By practicing yoga, a person is supposed to reach a state of mental
equanimity, where responses to favorable or unfavorable external events are well under the
individual’s control, and responses are moderate in intensity. The science of yoga is a powerful
stream of knowledge, which enables the practitioners to achieve radiant physical health, serene
mind, continues spiritual uplift, and creates the ability for harmonious social living
(Telles,Nagrathna&Nagendra, 1998).Cognitive behavioural therapy and yoga is reported to
significantly reduce the stress levels (Granath, Ingvarsson, von Thiele & Lundberg 2006; Smith,
Shelley, Dalen, Wiggins, Tooley, and Bernard 2008).Yoga can effectively improve memory after
6 months of practice, along with psychophysiological measurements related to anxiety,
depression and stress in healthy subjects (Rocha, Ribeiro, Rocha, Sousa, Albuquerque, Ribeiro,
Silva, 2012).Dunn, Hartigan andMikulas (1999) compared OM and Focused Attention practices
with a relaxation control: each produced ‘unique frequency patterns,’ suggesting that they
represent different forms of consciousness, not simply degrees of relaxation.
There have been a number of studies focused on reduction in stress levels, increased processing
capacity of visual system, attention regulation and other beneficial effects of yoga and
meditation. None of these studies look specifically at the effect these practices have on
consciousness, with experimental control.Consciousness may also be influenced by yoga and
meditation. This hypothesis is tested in the present study.With the advancement of research in
psychology and consciousness studies, consciousness of meditators can be studied using
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
436
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
psychometric tools.Brazdau(2008) introduced Consciousness Quotient (CQ) Theory and
developed Consciousness Quotient Inventory (Brazdau, 2009). This is a new concept in
researching consciousness as a variable. The psychometric properties of this inventory (CQ-i)
was further established (Brazdau, 2012). Consciousness Quotient, along with a psychological
and anthropological perspective allows the measurement of consciousness quotient(Brazdau,
2008).
Satsangi (2012) proposed HOT Consciousness – SCANE correlates, where HOT stands not for
Higher Order Thought (Gennaro, 2012) but Hierarchical Order Theory of Consciousness and
SCANE stand for Spiritual-Cognitive and Neural-Environmental Correlates. This theory is based
on spiritual system modeling in cosmology which is generalization to physical system theory
(Satsangi, 2006). These theoretical model predictions are scientifically verified using Fuzzy
Analytical Hierarchy Process (AHP) and Interpretive Structural Model (ISM) (Satsangi & Sahni,
2012). It is consistent with the modern science. The meditational practices of oriental philosophy
of Saints or cosmology of Radhasoami Faith is based on this systemic analytic framework for
hierarchization of consciousness.
The present study examined whether the experimental intervention of yoga and meditation based
on Hierarchical Order Theory of Consciousness, increased consciousness. To further assess the
impact of intervention, it was examined whether the intervention had any effect on self-reported
mindfulness. This approach allows the additional investigation of relation between mindfulness
and consciousness.
Method
Participants
Sixty participants took part in the experiment. The participants were applicants of yoga and
meditation program offered for twenty weeks. Consent was sought from the applicants for the
intervention. The age-range of the participants was 17 to 70 years (M=38.82, SD=11.64)Four
groups of 20 each were formed including, 3 experimental groups and one control. The groups did
not differ with respect to gender (11males and 9females in each group).Experimental group had
three set of subjects as stratified samples viz., pre-initiates(beginners) - those who were not
trained for any meditational practices prior to experiment, first initiates (intermediate meditators)
- those who were trained for contemplation of divine form at the seat of spirit(between two eyes),
second initiates (advanced meditators) - those who were trained for sound practice which
consists in concentrating attention at the seat of the spirit and establishing contact with the
current of Sabda or mystic word.
Intervention
The experiment was in the form of practice of yoga and meditation for 20 weeks. The practice
sessions (one hour) were held on weekdays in the evening for three days a week under the
guidance of experienced practitioner. These were conducted by yoga instructor with 10 years of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
437
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
experience and a facilitator with 30 years of experience in teaching meditation. Each day, the
programme commenced with a brief 15 minutes lecture covering different topics to reinforce the
subjects for meditation. The topics included body, mind, spirit and consciousness; cosmology;
spiritual awakening; nerve centres, chakras, kamals and padmas; attunement with spiritual
sounds; main object of meditation and ways to establish contact with the source of spirituality.
This was followed by yoga. Seven yogasanas were included in the intervention programme for
relaxation Siddhasan, Sarvangasan, Bhujangasan, Paschimottanasan, Padahastasan,
Ardhamatsyendrasan and Shavasan. These asanas were selected for relaxation and preparation of
body for meditation. After yogasana, the practice of meditation was modeled on practices of
oriental philosophy of Saints (Radhasoami Faith). These meditational practices are based on
Hierarchical Order Theory of Consciousness(Satsangi, 2013).
Materials and Procedure
The multiple measure design was used as detailed in Table 1. Consciousness Quotient Inventory
(CQ-i) was administered in pre-test, mid test and post-test. The CQ-i (Brazdau, 2012) evaluates
the global consciousness level of an individual. The construct of CQ-i is based on 6 factors:
Physical Consciousness Emotional Consciousness, Cognitive Consciousness, Spiritual
Consciousness, Social – Relational Consciousness, Self-Consciousness; and also provides a
general consciousness quotient. The secondary factors of CQ-i are internal state awareness, selfreflectiveness, mindfulness, autonomy, personal growth, positive relations with others, purpose
in life, verbal expression, and openness toward new experiences. The inventory has 62 items,
with the responses evaluated on a six point equal appearing type Likert Scale ranging from
1(strongly disagree) to 6(strongly agree). It has 8 reverse items. The reliability analysis of tool,
has a more than satisfactory internal consistency (N=62, Cronbach’s Alpha =.920). CQ-i does
not measure consciousness directly, but through inference from behaviours and applied life
principles that are indicators for conscious awareness experience (Brazdau, 2013).
The Frieburg Mindfulness Inventory (FMI) was used to assess mindfulness of participants.
FMIis a 14-item inventory that measures the experience of mindfulness (Walach, Bucheld,
Buttenmuller, Kleinknecht, & Schmidt, 2006).It is a psychometricallyvalid instrument with high
internal consistency, Cronbach alpha = .93 (Baer, Smith, Hopkins, Krietemeyer, & Toney, 2007).
Each item is rated on a four-point scale ranging from 1(rarely) to 4(always). Higher scores on
FMI indicate a greater degree of mindfulness. FMI was administered at the end of Phase I and
Phase II as mentioned in Table 1.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
438
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
Table 1. Overview of Procedure
Stage of the Study
Activity
Pre-intervention
Pre-test measure
(CQ-i)
Phase I
Phase II
Post-intervention
Timing
Practice of Yoga and
Meditation/ control
condition
Mid test measures
(CQ-i, FMI)
Practice of Yoga and
Meditation/control
condition
Post test measure
(CQ-i, FMI)
After seeking consent from participants to
participate in the study
Three days a week
(one hour each day - for 11 weeks)
After 11 weeks of Practice of Yoga and
Meditation
Three days a week
(one hour each day)
for 9 weeks
After 20 weeks of intervention
Results
Data was analyzed using Statistical Package for Social Sciences, Version16.0.The p values are
reported for all effects and effect sizes are reported as d, r calculated from t, z values respectively
and eta-squared for F-value (Fritz, Morris and Richler, 2012).
Consciousness Quotient Inventory
The consciousness scores over three measures are presented in Table 2. The analysis of scores on
baseline measure shows there were no differences between experimental and control group
(t=1.07, p=.28). A major purpose of this study was to examine the effect of yoga and meditation
on consciousness over time. There was effect of experiment over time, F(2, 36) = 3.37, p = .038,
= .06 and no change in control group, F<1.
The experimental group improved from pre-test to mid-test (t=3.400, p=.002, d= 0.55). The
improvement in this group was also observed in post-test (t = 3.135, p=.003, d = 0.51) from the
baseline measure (Fig. 1). The control group showed no significant difference from initial scores
to mid-test measure (t= 0.58, p=.567) and to post-test measure (t=.021, p=.983).
Group
Control
Experimental
ISSN: 2153-8212
Table 2.Consciousness scores over repeated measures
Pre-test
Mid-test
Post-test
M
SD
M
SD
M
SD
270.30 24.99
272.90 23.22
270.20 27.96
261.11 34.39
278.93 30.13
278.64 33.69
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
439
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
Experimental Group
290
Mean Consciousness Scores
285
*
#
Pre-test
Mid-test
Control Group
280
275
270
265
260
255
250
245
240
Post-test
Figure 1.Consciousness scores of experimental and control group over repeated
measures. The error bars represent standard errors. * p = .002 and # p = .003
compared to baseline measure.
For experimental group, the participants’ meditation training before intervention could
potentially affect results. Hence stratified random assignment was done to control this variable.
The mean scores of these groups are presented in Table3. The strata-wise gain in scores over
time is reflected in fig. 2. The analysis shows that post intervention there is significant increase
in consciousness of pre-initiates (z = 2.04, p = .041, r = .58) and first initiates (z=2.35, p = .01,
r = .71). Although there is increase in mean consciousness scores of second initiates but the
difference is not significant, z = 1.42, p = .15.
Table 3.Strata-wise Means (standard deviations) of consciousness scores over repeated measures
Pre-test
Mid-test
Post-test
Pre-initiates
241.75 (39.59)
267.75 (29.02)
264.25 (29.13)
First initiates
262.62 (26.30)
278.46 (27.49)
279.62 (26.05)
Second initiates
280.45 (26.87)
289.82 (32.73)
293.18 (41.73)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
440
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
350
Pre-Initiates
First Initiates
Second Initiates
325
300
#
275
Gain
#
250
225
200
175
150
Pre-test
Mid-test
Post-test
Figure 2. Gain in consciousness scores over pre-test, mid-test and post test of preinitiates, first initiates and second Initiates. Error bars reflect the standard errors.
#
p <.05 compared to baseline measure.
In order to find the change in specific dimension of consciousness as a result of experiment, the
scores were analyzed dimension-wise (Table 4).There is significant increase in consciousness
scores for some dimensions from pre-test to post-test (Fig. 3). The difference in mean
consciousness score in pre-test and post test is not significant for mental consciousness (t= 0.76,
p=.45) and spiritual consciousness (t=0.63, p=.52). There is significant increase in scores of
social consciousness (t=3.53, p=.001, r =.73) and self consciousness (t=2.56, p=.015, d = .47)
from pretest to mid-test. Also, the difference in scores is significant from pretest to posttest for
social consciousness(t=4.56, p=.000, d = .80) and self consciousness (t=3.11, p=.004, d =
.61).The difference in pretest and mid-test scores is not significant for physical consciousness
(t=1.87, p=.070) and emotional consciousness (t=1.88, p=.070). There is significant gain in the
scores of physical consciousness (t=2.28, p=.029, d = .43) and emotional consciousness (t=2.57,
p=.015, d = .36) from pre-test to post-test.
Table 4.Means (standard deviations) of consciousness scores for different dimensions
Dimensions of
Pre-test
Mid-test
Post-test
Consciousness
M (SD)
M (SD)
M (SD)
Physical
33.44 (5.68)
35.78 (6.54)
35.97 (6.00)
Emotional
42.08 (6.18)
44.08 (5.22)
44.36 (6.28)
Mental
37.50 (6.07)
39.67 (6.43)
38.69 (8.65)
Spiritual
57.81 (9.58)
59.44 (9.32)
58.69 (10.13)
Social
38.89 (6.47)
43.78 (6.85)
44.19 (6.67)
Self
51.39 (9.90)
55.61 (7.79)
56.72 (7.23)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
441
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
Pre-test
90
80
Mid-test
Post-test
*
#
#
Mean Consciousness Scores
70
60
50
40
30
20
10
0
Physical
Consciousness
Emotional
Consciousness
Mental
Consciousness
Spiritual
Consciousness
Social
Self Consciousness
Consciousness
Figure 3. Dimension-wise mean consciousness scores of experimental group in pre-test,
mid-test and post test. Error bars reflect the standard errors. * p<.001 compared to
baseline measure. # p<.05 compared to baseline measure.
The analysis of scores on FMI in two phases is presented in Table 5. The first phase was 11
weeks of yoga and meditation practice and second phase was 20 weeks of intervention.
The difference in mean scores on FMI of control group in phase I and phase II is not significant
(t= 0.72, p=.48). There is significant difference in mindfulness scores of experimental group in
Phase I and Phase II (t = 2.41, p=.021, d = 0.35). Fig.4 reveals that there is effect of experiment
on mindfulness (t= 2.16, p =.036, d = 0.59).
Group
Control
Experimental
ISSN: 2153-8212
Table 5.Mindfulness scores of participants
Phase I
Phase II
M
SD
M
SD
39.05
4.66
39.65
4.44
40.44
6.687
42.56
5.43
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
442
Mean Scores on FMI
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
45
44
43
42
41
40
39
38
37
36
35
Phase I
Phase II
#
*
Experimental Group
Control Group
Figure 4.Mean scores of experimental and control Group on Freiburg’s Mindfulness
Inventory (FMI). Error bars reflect the standard errors. * p<.05 compared to phase I.
#
p<.05 compared to control group.
Table 6 presents strata-wise mindfulness scores. There is significant difference in the scores on
FMI of pre-initiates in Phase I and Phase II (z=1.99, p = .046, r = .29).The difference in
mindfulness scores of first and second initiates is not statistically significant.Fig.5 reveals that
although there was notable difference in mindfulness of pre-initiates from first and second
initiates in phase I of experiment, but in phase II this difference has reduced to a considerable
extent.
Table 6.Strata-wise Means (standard deviations) of mindfulness scores
Group
Phase I
Phase II
M (SD)
M (SD)
Pre-Initiates
37.91 (6.00)
41.09 (4.39)
First Initiates
39.67 (7.18)
42.07 (5.44)
Second Initiates
44.40 (5.21)
44.90 (6.19)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
443
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
50
Phase I
Phase II
Mean Scores on FMI
45
40
*
#
35
30
25
20
Pre-Initiates
First Initiates
Second Initiates
Figure 5.Mean scores on FMI of pre-Initiates, first initiates and second initiates in
phase I and phase II of experiment. Error bars reflect standard errors. * p<.05 as
compared to phase I. # p<.05 compared to second initiates.
Further, to examine the relationship between mindfulness and consciousness a correlational
approach was employed. The analysis reveals that mindfulness scores are positively correlated to
all dimensions of consciousness. There is significant correlation of mindfulness scores with
mental consciousness (r= 0.43, p = .009), social consciousness (r = 0.39, p = .019), self
consciousness (r= 0.35, p = .040) and spiritual consciousness (r= 0.34, p = .045). The correlation
of mindfulness scores with physical consciousness (r = 0.15, p = .393) and emotional
consciousness (r = 0.26, p = .125) is not significant. The overall scores of mindfulness and
consciousness have significant correlation (r = 0.44, p = .036).
Discussion
In summary, the results of the study indicate that the practice of yoga and meditation increased
the consciousness and mindfulness of individuals. Importantly, the practice has considerable
effect on all dimensions of consciousness over time. The impact is more and relatively
immediate on social and self-consciousness. Thus, an individual becomes more aware about self
as a person and is able to connect oneself with others. Also, initially after ten weeks of practice,
the practitioners did not show significant change in physical and emotional consciousness but
there was significant increase in these dimensions of consciousness after 20 weeks of practice of
yoga and meditation. Though the difference in mental and spiritual consciousness was not
significant even after 20 weeks, but there was increase in these dimensions also. A longer
duration of practice may have significant effect on mental and spiritual consciousness. Further,
the naïve practitioners showed significant gain in consciousness scores after practice of 20 weeks
in comparison to those who had exposure to the practice of yoga and meditation. It may be
possible that for more gain in consciousness scores, regular practice at length is required. The
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
444
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
study highlights that the practice of yoga and meditation is more effective for pre-initiates who
are not trained for any meditational practice. The consciousness of experienced practitioners also
increased considerably with the regular practice of yoga and meditation.
These findings corroborate the results of previous studies that report meditation promotes both
physical and mental wellbeing and contributes to the development of positive emotional traits
(Brown & Ryan, 2003). The regular yoga practice is reported to improve aspects of cognition
and quality of life for healthy individuals (Rocha, et al., 2012). The workers reported feeling
happier, with a renewed sense of enthusiasm for their life and work after eight weeks of
meditation training and practice (Davidson & Lutz, 2008). Meditation effects are conceptualized
as a function of the cognitive-attentional processes that are engaged (Austin, 2006; Bishop et al.,
2004). Also, in line with the results of present study, it has been reported that experienced
meditators generally score higher than novices on most attention measures, including selective
(Hodgins and Adair, 2010), executive (Moore and Malinowski, 2009) and sustained attention
(Jha, Krompinger and Baime, 2007). Researchers looking at individuals engaging in Focussed
Attention meditation found that expert practitioners with an average of 19,000 practice hours
displayed more activation in the brain regions than novices, while those with 44 000 hours of
practice showed less (Brefczynski-Lewis, Lutz, Schaefer, Levinson & Davidson, 2007).
Further, the correlational analysis indicate that high levels of mental, spiritual, social and selfconsciousness are correlated to high level of mindfulness. These results support the hypothesis
that mindfulness would correlate positively with consciousness. Mindfulness is inherently a state
of consciousness(Brown and Ryan, 2003).
Conclusion
The objective of the study was to examine the effect of yoga and meditation on six dimensions of
consciousness of naïve and experienced practitioners in comparison to non-practitioners.The
improvement in different dimensions of consciousness showed in this study and effect of yoga
and meditation as reported in other researches account for amelioration in cognitive functions
and consciousness as a whole. The findings are very optimistic in that meditation practice can
alter an individual’s social, self, physical and emotional consciousness setting towards the
positive, which may then become default state. Although the further investigation is required
separating out the effect of both the practices on consciousness and mindfulness.
Acknowledgements: I am highly grateful to Prof. P.S.Satsangi, Chairman, Academic Committee on
Education, Dayalbagh Educational Institute, for his incessant guidance throughout this research. I present
my gratitude to Coordinator, Centre for Consciousness Studies for his co-operation to conduct this
research and to Prof. P.Sriramamurti, Advisor, Centre for Consciousness Studies for co-ordinating the
intervention.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
445
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
References
Austin, J.H. (2006). Zen-brain reflections: reviewing recent developments in meditation and states of
consciousness. Cambridge, Mass: MIT Press.
Baars, B. J., Banks, W. P., &Newman, J. B. (2003). Essential sources in the scientific study of
consciousness. Cambridge: MIT Press/Bradford Books.
Baer, R., Smith, G., Hopkins, J., Krietemeyer, J., & Toney, L. (2007).Using self report assessment
methods to explore facets of mindfulness. Assessment, 13,27–45. doi:10.1177/1073191105283504.
Birdee, G. S., Legedza, A. T., Saper, R. B., Bertisch, S. M., Eisenberg, D. M. & Philips, R.
S.(2008).Characteristics of yoga users: results of a national survey.Journal of General Internal
Medicine,23(10), 1653-1658.
Bishop, S. R., Lau, M., Shapiro, S., Carlson, L., Anderson, N.D., Carmody, J., et al. (2004). Mindfulness:
A proposed operational definition. Clinical Psychology: Science andPractice 11(3), 230-241.
Braboszcz, C., Hahusseau, S.,& Delorme, A. (2010). Meditation and Neuroscience: from basic research to
clinical practice. In R. Carlsdett (Ed.), Integrative Clinical Psychology Psychiatry and Behavioral
Medicine: Perspectives, Practices and Research (pp. 755-778), Springer Publishing.
Brazdau, O. (2008). Research on the consciousness experience.The Consciousness Quotient and CQ
Inventory.Doctoral dissertation, Romanian Academy of Science, Bucharest, Romania.
http://www.consciousness-quotient.com/docs/Consciousness_Quotient_Doctoral_
Dissertation_Ovidiu_Brazdau_dec2009%28excerpt%29.pdf
Brazdau, O (2009, June). The Conscious Experience: Consciousness Quotient (CQ) and the CQ
Inventory. Paper presented at Toward a Science of Consciousness Conference, Hong Kong,
China.http://www.consciousness.arizona.edu/TSCHongKong09ProgramUpdated.htm
Brazdau, O. & Mihai, C. (2011). The consciousness quotient: a new predictor of the students’academic
performance,Procedia Social and Behavioral Sciences, 11, 245–250.
Brazdau, O., Constantinescu, P.M., Constantinescu, I., Butucescu, A., &Sbircea, R. (2012).
Consciousness Quotient Inventory Improvement: Qualitative Study Using Cognitive Interviewing
Approach, Procedia-Social and Behavioural Sciences, 78, 425-530.
Brazdau, O. (2013). The consciousness quotient: introducing the consciousness experience as a research
variable in psychological assessment. Retrieved from http://www.consciousness-quotient.com/theconsciousness-quotient-introducing-the-consciousness-experience-as-a-research-variable-inpsychological-assessment
Brefczynski-Lewis, J. A., Lutz, A., Schaefer, H. S., Levinson, D. B., & Davidson, R. J. (2007). Neural
correlates of attentional expertise in long-term meditation practitioners. Proceedings of the National
Academy of Sciences, 104, 11483-11488.
Brown, K. W., & Ryan, R. M. (2003). The benefits of being present: Mindfulness and its role in
psychological well-being. Journal of Personality and Social Psychology, 84(4), 822–848.
Charlton, B. (2000).Psychiatry and Human
Condition.http://www.hedweb.com/bgcharlton/awconlang.html
Chalmers, D. J. (1996).The conscious mind: In search of a fundamental theory. Oxford: Oxford
University Press.
Crick, F. (1984). Function of the thalamic reticular complex: The searchlight hypothesis. Proceedings of
the National Academy of Sciences,81, 4586–4590.
Davidson, R.J &Lutz , A. (2008). Buddha‘s Brain: Neuroplasticity and Meditation. Signal Processing
Magazine, IEEE, 25(1),176-174.
Dennett, D.C. (1988). Quining qualia. In: Marcel AJ, Bisiach E, (Eds.). Consciousness in contemporary
science (pp. 42-77). Oxford: Clarendon Press.
Dennett, D. C. (1992).Consciousness explained. New York: Basic Books.
Dunn, B. R., Hartigan, J. A.&Mikulas, W. L. (1999). Concentration and mindfulness meditations: Unique
forms of consciousness? Applied Psychophysiology and Biofeedback24(3), 147-165.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
446
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
Fritz, C.O., Morris, P. E. & Richler, J.F. (2012). Effect size estimates: current use, calculations and
interpretations. Journal of Experimental Psychology: General, 141(1), 2-18.
Gennaro, R.J., (2012). The Consciousness Paradox:Consciousness, Concepts, and Higher-order
Thoughts.Cambridge, MA: MIT Press.
Goleman, D. (1995). Emotional intelligence. New York: Bantam Books.
Granath, J., Ingvarsson, S., von Thiele, U., & Lundberg, U. (2006). Stress management: A randomized
study of cognitive behavioural therapy and yoga. Cognitive Behavioural Therapy, 35, 3-10.
Hodgins, H. S.& Adair, K. C. (2010).Attentional processes and meditation.Consciousness and
Cognition,19(4), 872-878.
Jha, A. P., Krompinger, J.&Baime, M. J. (2007). Mindfulness training modifies subsystems of attention.
Cognitive, Affective and Behavioral Neuroscience,7, 109-119.
Lutz, A., Dunne, J. D., & Davidson, R. J. (2007).Meditation and the neuroscience of consciousness.In P.
Zelazo, M. Moscovitch, & E. Thompson (Eds.), Cambridge handbook of consciousness (pp. 480551). New York: Cambridge University Press.
Moore A and Malinowski P (2009) Meditation, mindfulness and cognitive flexibility.Consciousness and
Cognition,18(1), 176-186.
Nagendra H.R. &Nagarathna R. (2000).New perspective in stress management. Bangalore, India:
Vivekananda Kendra Parkashana.
Patil, S.P &Telles, S. (2006). Cyclic meditation – a moving meditation –reduces energy expenditure more
than supine rest.Journal of Indian Psychology, 24(2), 44-51.
Rocha, K.K., Ribeiro, A.M., Rocha, K.C., Sousa, M.B., Albuquerque, F.S., Ribeiro, S. & Silva, R.H.
(2012). Improvement in physiological and psychological parameters after 6 months of yoga
practice.Journal of Consciousness and Cognition, 21,843-850.
Satsangi, P.S. (2006). Generalizing physical systems through applied systems research from “real”
physical systems through “conceptual” socio-economic-environmental systems to “ complete”
(physical-mental-spiritual) creational systems”. International Journal of General Systems, 35(2), 127167.
Satsangi, P.S. (2010).Expositions on Truth, Ultimate Reality and Supreme Being. Agra, India
:RadhasoamiSatsang Sabha.
Satsangi, P.S. (2012).Neuro-environmental Cognitive Spiritual Phenomenology.
http://www.dayalbagh.org.in/specialTalks/visionTalkQANSAS2012.htm
Satsangi, P.S. &Sahni, V. (2012, April). Cosmic Consciousness Hierarchization: Analytic, Experimental
and Experiential. Paper presented at Toward a Science of Consciousness, Tucson, Arizona.
http://www.consciousness.arizona.edu/documents/TSC2012CCS_
BookofAbstracts_forweb2012.pdf
Satsangi, P. S. (2013).Cosmology from the Twin Vantage Points of Radhasoami Faith and Systems
Science. In P.Sriramamurti, P.Prashant & A. Mohan (Eds.),Spiritual Consciousness (pp. 21 – 38 ).
New Delhi, India: DK Agencies.
Smith, B., Shelley, B.M., Dalen, J., Wiggins, K., Tooley, E., & Bernard, J. (2008).A pilot study
comparing the effects of mindfulness-based and cognitive-behavioral stress reduction.The Journal of
Alternative and Complementary Medicine, 14, 251-258.
Thompson, E. (2006). Neurophenomenology and contemplative experience.In P. Clayton (Ed.), The
Oxford handbook of science and religion(pp. 226-235). New York: Oxford University Press.
Telles, S. &Desiraju, T. (1993). Recording of auditory middle latency evoked potentials during the
practice of meditation with the syllable ‗OM. Indian Journal of Medical Research, 98, 237-239.
Telles, S., Nagarathna, R. and Nagendra, H.R. (1998) Autonomic changes while mentally repeating two
syllables – one meaningful and the other neutral. Indian Journal of Physiology and Pharmacology,
42(1), 57-63.
Telles, S., Reddy S.K., &Nagendra H.R. (2000).Oxygen consumption and respiration following two yoga
relaxation techniques.ApplPsychophysiol Biofeedback, 25(4), 221–7.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
447
Journal of Consciousness Exploration & Research| June 2014 | Volume 5 | Issue 5 | pp. 434-447
Ahuja, S., Effect of Yoga & Meditation on Consciousness & Mindfulness
Vaitl, D., Birbaumer, N., Gruzelier, J., Jamieson, G. A., Kotchoubey, B. &Kubler, A. (2005)
Psychobiology of altered states of consciousness. Psychological Bulletin, 131, 98–127.
Varela, F. J., Thompson, E., &Rosch, E. (1991).The embodied mind:Cognitive science and human
experience. Cambridge, MA: MIT Press.
Wade, J. (1996). Changes of mind: A holonomic theory of the evolution of consciousness. Albany, NY:
State University of New York Press.
Walach, T., Buchheld, N., Buttenmuller, V., Kleinknecht, N., & Schmidt, S. (2006). Measuring
mindfulness: The Freiburg Mindfulness Inventory (FMI). Personality and Individual Differences,
40(8), 1543–1555. doi:10.1016/j.paid.2005.11.025.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
561
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
Article
The Cosmology of Conscious Mental States (Part I)
Chris King*
ABSTRACT
We explore the diversity of mental states, and examine to what extent these are both a product of
specific known brain processes and yet may access a complementary aspect of existence to the
cosmology of the physical universe and its natural biosystems, potentially giving mental states an
existential cosmological status. The case is made that the cosmology of mental states reflect a
deeper physical principle connecting quantum entanglement with the brain wave processing
evolved in higher organisms to solve the computational intractability of open environmental
dilemmas, which go beyond Bayesian statistics and causal prediction, into multiple nested
Schrödinger cat paradoxes, hinting at a meta-evolutionary paradigm of conscious cosmological
integration.
Part I of this two-part article contains: A Natural Classification of Mental States; The Physiology
of Mental States; & Subjective Consciousness – What are Mental States For?
Key Words: cosmology, conscious, mental state, brain process, existence, physical universe,
biosystem, quantum entanglement, brain wave processing, computational intractability, Bayesian
statistics, causal prediction, Schrodinger’s Cat.
Fig 1: A representative spectrum of prominent mental states
* Correspondence: Chris King http://www.dhushara.com E-Mail: dhushara@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
562
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
A Natural Classification of Mental States
Human conscious experience involves a spectrum of mental states surrounding the everyday
waking condition. Some of these are biological, associated with essential processes, including
reflection, reminiscence and daydreaming associated with the so-called default network (see fig
2), the dreams and nightmares of REM sleep, and ‘out of the body’ (OBE) experiences
associated with hypnagogic states. Others are culturally-based associated with devotional
practices, including meditation, prayer, religious vision and spiritual contemplation. Still others
are pharmaceutical, associated with changes of subjective consciousness induced by
psychotropic substances, such as psychedelics and dissociatives, either synthetic molecules, or
associated with certain plants or fungi. Finally we have a number of pathological states involving
extreme medical conditions, from schizophrenia and dementia to epileptic seizures, particularly
in the temporal lobes, and the near death experiences (NDE) associated with heart attacks,
drowning, and severe trauma, such as traffic accidents.
While some have a natural origin in circadian rhythms, and others a cultural origin, others still a
chemical origin and yet others a medical origin, all of them arise from specific brain states
physiologically, which, despite their different origins, fall into a natural classification.
However this doesn’t mean brain physiology is all there is to mental states. Indeed our
description of reality and the physical world is founded first and foremost on our subjective
conscious mental states, whose actual basis remains the most confounding and unfathomed
question facing the scientific description of the natural world. We may thus find in the diversity
of mental states clues to the existential cosmology of the conscious universe - hence the title of
this article.
The Physiology of Mental States
All mental states, from natural to cultural, are accompanied by specific physiological changes to
the brain, which are signature of the state concerned. This applies equally to drug-induced states
and states which people may associate with higher spiritual practices or religious experiences,
showing these too can be seen to have a biological origin.
The transition from wakefulness to the onset of light and deep non-dreaming (non-REM) sleep,
interspersed with phases of dreaming or REM sleep, occurs naturally in waves over the night’s
slumber. While the electrical activity of the EEG of non-REM sleep shows theta spindles and
deep slow delta waves, different from the high frequency, low amplitude, beta activity of waking
attention, the beta EEG of dreaming sleep is remarkably similar to the waking brain. Dreaming
phases lasting up to 30 minutes indicate phases of dreaming experience last a similar time to
their subjective experience. Brain scans of the metabolic activity of the dreaming brain using
PET and fMRI show an active brain with increased activity in visual areas and reduced executive
control in frontal areas, consistent with the rich visual experiences and lack of full voluntary
control over the events in dreams.
These changes are driven by major ascending neural pathways from the brain stem to the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
563
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
cerebral cortex, and other descending pathways, which together mediate major changes in
alertness and attention, facilitated by specific neurotransmitters and receptors. The reticular
activating system contains pathways mediating full arousal. In the waking condition, both the
cholinergic acetylcholine and adrenergic norepinephrine pathways are active. In non-REM sleep,
norepinepherine and serotonin ascending pathways are active. At the onset of dreaming these go
silent and acetylcholine pathways in the pons become active, having the effect of shutting down
brain stem centers facilitating motor activity, putting the dreaming subject into a state of atonia,
or sleep paralysis, preventing them acting out their dreaming experiences, except for the rapid
eye movements for which REM is named. This also has the effect of making the dreamer often
feel transfixed in their dream, while at other times feeling they are floating or flying. The exotic,
intensely perceived and bizarre mental states accompanying dreams and nightmares are thus
clearly related to fundamental physiological changes orchestrated by brain stem centers in
interaction with the entire cerebral cortex.
Fig 2: Physiological underpinnings of a variety of brain states. (a,b) fMRI and PET scans of REM
(dreaming) sleep show increased occipital (visual) activity and reduced prefrontal (executive) function,
with an EEG similar to the waking brain (Braun). (c) Sleep phases of REM and non-REM sleep alternate
in waves. The EEGs are on a time scale of seconds, the sleep waves in hours. (d) Sleep phases are driven
by ascending serotonin and nor epinephrine pathways from the Raphe nucleus and Locus coeruleus. (e)
The default network associated with worry and recollection of events to prepare for the future shows
depression of activity during task performance and increase during rest (Raichle et al, Raichle & Snyder,
Mason et al, Fox D, Horovitz et al, Buckner et al, Marshall). (f) There are believed to be two attention
systems in the human brain (Fox et al.) a bilateral dorsal attention system (blue) involved in top-down
orienting of attention and a right-lateralized ventral attention system (red) involved in reorienting
attention in response to salient sensory stimuli. (g) Zen meditation studies (Pagnoni et al, Ritskes et al) in
which subjects are asked to switch from a verbal task to contemplation show transient activity consistent
with the default network which is more quickly suppressed by experienced meditators more effectively
inhibiting verbal thought. (h) Carmelite nuns entering oneness with God show fMRI activations in areas
in specific frontal, parietal, temporal and basal areas consistent with directed control (Beauregard &
Paquette). (i) Tibetan Buddhists performing compassion meditation for other people’s suffering show
specific activation in limbic regions including cingulate cortex and insula, consistent with an empathic
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
564
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
response to another’s pain (Lutz et al 2008). (j) PET study of psilocybin taken orally shows frontal
activation by comparison with a resting state (Vollenweider et al). (k) fMRI study during the 12 minutes
after intravenous administration of psilocybin shows reduced activity in medial frontal cortex (mPFC),
posterior cingulate cortex (PCC) and other areas (Carhart-Harris et al 2012a, Lee & Roth) suggesting
suppression of the default network as the effects come on. (l) Increases in activity associated with
autobiographical memories on psilocybin right over placebo (left) (Carhart-Harris et al. 2012b). (m)
Increases in fMRI in frontal and paralimbic brain regions in an ayahuasca session (Riba et al 2006). (n)
Above ketamine induces a decrease in ventromedial frontal cortex (blue) and increased activity in midposterior cingulate, thalamus and temporal cortical regions (yellow-red) consistent with its dissociative
effects. Below inhibition of ketamine activity by lamotrigine, a sodium channel blocker that decreases
glutamate release (Deakin et al).
While many theories have been proposed for the function of dreams, particularly in relation to
the reencoding of hippocampal memories into compactified strategically effective forms in the
cortex, the extreme variation of REM and of sleep duration in different mammal species and the
ambiguity of studies of sleep deprivation leave the purpose and existential status of dreaming
still awaiting a full explanation.
Key psychotropic agents also act on specific neuroreceptors, inducing physiological changes in
brain dynamics by altering the receptor-mediated activation of excitatory or inhibitory neurons.
For example, psychedelics, are believed to act as super-agonists of the 5HT2a serotonin receptor,
setting off a different form of activation from serotonin itself, in which a push-pull coupling with
a second receptor mGluR2, for the principal excitatory neurotransmitter glutamate, alters the
stability of excitation in such a way as to evoke the ‘fractal’ instabilities associated with the
kaleidoscopic visions of the psychedelic state. Both of these receptors are slow acting G-proteinlinked ‘metabotropic’ receptors whose changes in dynamics are measured in hours – the life of
the drug effect. They do not directly cause changes in ion flow, but trigger a protein cascade
altering long term dynamics. Other psychotropics, from cannabinoids to datura-containing
deleriants such as scopolamine, are positive agonists, or negative antagonists, of other key
receptors, respectively the anandamide CB1 cannabinoid receptor and the muscarinic
acetylcholine receptor.
By contrast, ketamine acts to block the pore in a fast acting glutamate NMDA ionotropic
receptor, directly altering ion flow and excitability in target neurons, resulting in global changes
in excitability which appear to dissociate the subject from their bodily sensations, so that, while
remaining technically conscious, they become relatively oblivious to an operation being
performed on them and at the same time experience dislocated out of the body experiences, some
of which have profound impressions, similar to classic near death reports.
In fact the situation is vastly more complicated than this description. Psychedelics, for instance,
activate a broad spectrum of many serotonin (5HT), norepinephrine and other receptors, to
varying degrees, in a manner similar to pressing a large number of keys on a polyphonic
keyboard, resulting in a variety of simultaneous effects, from sensory hallucinations to anxiety
reactions. Paradoxically agonism of the 5HT1a receptor in the psychedelic tryptamines silences
the Raphe nucleus responsible for serotonin innervation of the cortex (Braden, Nichols 2011), as
occurs in REM sleep, resulting in a close parallel with the dreaming state. In addition, a given
receptor type can have differing actions depending whether it is on an excitatory e.g. pyramidal
cell, or an inhibitory interneuron, so a psychotropic agent may have simultaneous excitatory and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
565
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
inhibitory effects on different cells, or on distinct brain regions.
Still other psychotropics such as the releasing agents methamphetamine and MDMA and
reuptake inhibitors such as fluoxetine (prozac), principally affect the transporters that carry
neurotransmitters to the synapse and remove any excess after release, inhibiting re-uptake or
causing reverse dumping, rather than activating or de-activating receptors directly, as agonists
and antagonists do.
Nevertheless psychotropic drugs and sacramental species act on brain dynamics broadly through
the same receptors and some of the same pathways we saw driving natural changes in the sleep
wakefulness cycle. This involvement of sappy neurotransmitter molecules in what would
otherwise be electro-chemical neurodynamics is very ancient, and key neurotransmitters, from
serotonin to cyclic-AMP, trace their evolutionary origin right back to chemical signaling in
single celled eucaryotes and have similar or parallel function in diverse animal groups, from
arthropods to vertebrates, acting on major modes to keep neurodynamic function biologically
attuned to the survival of the organism.
Many spiritual practitioners and religious believers consider their experiences to be states of
attainment far beyond mere physiology, requiring devoted concentration and higher forms of
consciousness, as different from lowly dissipated drug experiences as gold is to lead. However
research exploring states of meditation and religious devotion show that these states fall into a
physiological spectrum as clearly as natural and pharmaceutically induced states do.
When it comes to the investigation of mental states associated with spiritual and religious
practice using brain scans, we find clear physiological indicators related to the particular practice
engaged by the subject. By contrast with the rich and bizarre nature of dreaming, mental states
associated with prayer and meditation tend to involve focused control and suppression of the
wandering mind through limiting the verbal thought process, or one-pointed concentration.
While these mental states are highly varied, they share common features of intentional control of
the mental process. Zen meditators in fMRI studies show more rapid and complete suppression
of the mind-wandering of the default network (Pagnoni et al), with increased activity in the
prefrontal cortex and basal ganglia and decreased activity in the occipital (visual) cortex and
anterior cingulate processing emotion (Ritskes et al). In EEG studies they showed a significant
increase in frontal alpha and occipital beta power, whereas an average increase of theta power
was observed in controls, indicating loss of concentration (Huang et al). Consistent with onepointed concentration, Zen meditators recalled more subliminal messages than controls (Strick et
al).
Tibetan Buddhist meditators in PET and fMRI studies have increased blood flow in the
cingulate, inferior and orbital frontal cortex, dorsolateral prefrontal cortex and thalamus
(Newberg et al 2001, Hanky). EEG studies show greater activation in attentional regions,
including fronto-parietal, cerebellar, temporal, para- hippocampal, and posterior occipital,
possibly due to the attended spot (Brefczynski-Lewis et al). They have also been found to enter
high-amplitude gamma-band oscillations with high phase-synchrony during meditation,
consistent with a one-pointed concentration with heightened attention (Lutz et al 2004). By
contrast, compassion meditators under PET show similar activations to a person feeling empathy
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
566
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
for a person in pain (Lutz et al 2008). In a more recent fMRI study contrasting “focus-based” and
“breath-based” practice, in the first, blood flow increased in the medial prefrontal cortex and left
caudate, but decreased in parietal and occipital regions. The second induced activation in several
limbic structures and the left superior temporal cortex (Wang et al).
Investigation of Transcendental meditators by PET (Newberg et al 2006b) also found bilateral
prefrontal activation associated with relaxed attention on the mantra, other increases in frontal,
occipital and parietal areas and a decrease in the thalamus and hippocampus. An fMRI study
centered on the capacity of the relaxed state to be helpful in dealing with an induced painful
stimulus saw reductions in the prefrontal cortex, anterior cingulate cortex, and thalamus (OrmeJohnson et al), and has been suggested to be linked to hormonally induced increases in the
inhibitory neurotransmitter GABA (Elias et al). Catholics observing a Marian image saw
increases in the ventrolateral prefrontal cortex and brain stem leading up to the thalamus (Wiech
et al).
Brain studies of Carmelite (Beauregard & Paquette) and Franciscan nuns (Bielo) in professed
‘union with god’, which they admitted was difficult to achieve in a noisy MRI tunnel, show
different structured activations, with increased activity in the caudate nucleus associated with
learning, memory and falling in love, the insula processing body sensations and social emotions,
the inferior parietal processing spatial awareness in contradiction to the Zen studies, the medial
orbito-frontal and prefrontal cortices dealing with emotional and executive decision-making, and
the middle of the temporal lobe. Most prevalent brain waves were long, slow alpha waves such
as those produced by sleep, consistent with a relaxed state.
By contrast with the prefrontal control evidenced in Buddhist meditation, during speaking in
tongues, by Christian women who had practiced glossolalia for more than 5 years, there was a
decreased blood flow in the frontal lobes bilaterally and in the left caudate, indicating relaxation
of executive controls (Newberg et al. 2006a).
In comparing these highly varied and contradictory results, one can conclude that claimed states
of higher spirituality are varied products of different forms of concentration, which share the
feature of overall focused control, but otherwise look like distinct humanly-generated states of
mind, rather than convergence on the ‘divine’. One thus needs to consider the possibility that the
profound transformations of the cortical dynamic induced both by dreaming and by psychotropic
entheogens may give rise to every bit as deep a potential for exploratory existential processes,
which might nevertheless be enhanced by contemplative repose.
Moreover, certain pathological states, such as temporal epilepsy, are associated with states of
religious fervor bordering on the mystical and become experiences which the patient, while
suffering from the effects of such seizures, regards as having overwhelming significance, which
they are reluctant to part from. In one subject’s description “Triple halos appeared around the
sun. Suddenly the sunlight became intense. I experienced a revelation of God and of all creation
glittering under the sun. The sun became bigger and engulfed me. My mind, my whole being was
pervaded by a feeling of delight” (Naito and Matsui). The incidence of these states caused the
neuroscientist Vilayanur Ramachandran to coin the term the ‘god spot’ for the region of the
temporal lobe bordering on the limbic emotional system amygdala, suggesting that stimulation of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
567
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
this region could cause both the intense significance and meaning of temporal excitation and the
ecstatic fulfillment of positive centers in the amygdala, whose function is to do with orienting to
intense emotional conditions, from flight and fight to peak fulfillment. Neuroimaging studies of
individuals suffering from schizophrenia with religious delusions similarly found over-activation
of the left temporal lobe during religious delusions (Puri et al).
Religious conservatism may also be a product of social evolution, as the moral deity reinforces a
situation of inhibiting intra-social conflict through fear of an omniscient god’s punishment,
combined with repression of the infidels, resulting in inter-social dominance, permitting larger
human groups to remain stable and to become dominant over their neighbors - a not entirely holy
outcome!
On a slightly different tack, several researchers have drawn attention to the idea that genetic
differences in neurotransmitter dynamics could underpin human religiosity, in particular the
generalized monoamine transporter VMAT2, which is essential for carrying dopamine and
serotonin to the synapse. Dean Hamer in “The God Gene” suggested that genes expressing
higher levels of the transporter resulted in spiritual individuals favored by natural selection
because they are provided with an innate sense of optimism, the latter producing positive effects
at either a physical or psychological level. The dopamine receptor DRD4 (Comings et al) and
various other receptors have likewise been cited as enhancing a measure of spirituality called
‘self transcendence’.
Intriguingly removal of tumors from two brain regions, the left inferior parietal lobe and the right
angular gyrus, was also associated with immediate increases in self-transcendence (Weaver).
Significantly these regions are involved in processing one’s body image, so the loss of function
could well evoke feelings of spiritual merging. The questionnaire tapped into three main
components of self-transcendence: losing yourself in the moment, feeling connected to other
people and nature, and believing in a higher power. Examples include: "I often become so
fascinated with what I'm doing that I get lost in the moment - like I'm detached from time and
place" and "I sometimes feel so connected to nature that everything seems to be part of one
living organism."
Out of body experiences or OBEs also have direct physiological correlates. Many of the reported
experiences appear to arise from hypnagogic states, when a person is on the borderline of sleep
or partially awakening from REM sleep, but are still in a state of sleep paralysis, leading to the
impression of floating, while perceiving they are able to witness their body from a distance.
My most classic OBE was practicing for lucid dreaming by trying to look at the backs of my
hands in a dream. Many times I had awakened realizing I had seen my hands in a dream, for
example climbing ladders, and not registered. Eventually one night I looked at my hands in a
dream and made the connection. This set off an immediate and powerful reaction. I found my
consciousness split in three, one self was lucid dreaming, but lost in the dream universe. I looked
up at the deep blue sky and realized it was not the ordinary sky of the waking world and no
galaxy out there was the one I had come from. I became desperate to find my way back to life. I
was standing in bright daylight on a promenade by the ocean. I saw a woman with dark eyes
staring at me. I walked up to her, grabbed her by both shoulders and stared down deep into her
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
568
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
dilated pupils, silently begging to know how to find the way back, but she just stepped back and
shook her head smiling. No way back to Ixtlan! At the same moment a blast of sea breeze hit me.
I was wearing a light Indian shirt and I could feel every one of the droplets of spray that hit me
lucidly with crystal clarity. At the same time the gust was a force like a levitating tornado
sending me shooting up faster and faster in some other space. However again at the same time, I
realized I was bumping on the ceiling of my bedroom, reassuringly witnessing my body asleep in
the bed below, saying to myself silently "It's all okay! You are down there sleeping peacefully on
the bed!" Afterwards I realized all these experiences had started simultaneously and ended
simultaneously. I had been in three places at once!
The brain is richly endowed with mirror neurons which are essential in our social function and
cause us for example to get shivers down our spine when we see someone else get injured.
Several studies, including under MRI brain scans, have confirmed that the temporo-parietal
junction, one of several regions involved in helping to integrate visual, tactile and proprioceptive
senses with the signals from the inner ear that give us our sense of balance and spatial orientation
has altered function when experiments are performed to simulate out of body experiences which
are perceived to result in a full or partial OBE by the subject. Various forms of experiment where
the subject receives tactile stroking while watching a mannequin which has camera-mounted
eyes relayed to goggles worn by the subject can cause such brain areas to integrate these
perceptions into an OBE (Ananthaswamy 2013).
We finally come to the physiology of NDEs or near death experiences. Many people undergoing
cardiac arrest, suffering extreme trauma, such as a car accident, in which they have become
comatose, or in drowning, report experiences involving one or more of a spiraling tunnel, often
with light at the end, a sense of ‘telepathic’ communication with a higher conscious being, who
may at the same time be themselves, a sense of leaving their body and perhaps seeing departed
friends or relatives or seeing their own body being resuscitated, and a sense of being drawn back
to life rather than departing to the realm of death, before coming back to consciousness. These
experiences are often reported as life-changing and have become the subject of intense debate
between people who believe it is evidence of a conscious afterlife and skeptics who see it as an
hallucinatory physiological phenomenon. Some people have even reported seeing objects like
shoes in inaccessible places which later proved to be there, stoking ideas that such experiences
possess super-natural powers, however events of this type such as Maria’s NDE are so rare that
there remain only a handful of such accounts. British psychiatrist Peter Fenwick who set up
messages in inaccessible places to test this hypothesis in such patients has found no confirmation
of the effect (Ebbern et al), nor has a review of research studies into NDEs (Mobbs and Watt).
Beauregard (2012) describes an iconic account concerning a woman who was operated on for a
brain stem aneurism by being chilled to the point of cardiac arrest, her blood drained from her
body to avoid a hemorrage, and her EEG going into flat line for a full hour. She recalls floating
out of the operating room and traveling down a tunnel with a light. She saw deceased relatives
and friends, including her long-dead grandmother, waiting at the end of this tunnel. She entered
the presence of a brilliant, wonderfully warm and loving light, and sensed that her soul was part
of God and that everything in existence was created from the light (the breathing of God). But
this extraordinary experience ended abruptly, as Reynolds’s deceased uncle led her back to her
body—a feeling she described as “plunging into a pool of ice.”
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
569
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
The difficulty with assessing NDE reports is that they only come to light after the person regains
consciousness, so we don’t really know exactly when they occurred or whether they occurred in
the deepest phases of coma or in the transition zone back to consciousness. Under cardiac arrest
the loss of blood rapidly causes the EEG to fall to a flat line. If consciousness is simply
suspended at this point the subject might experience a continuous transition from the onset phase
to the recovery phase accompanied by the NDE experience in transition, a little like the rebirth
process in the Bardo Thodol or Tibetan Book of the Dead.
Significantly, both psychedelics and dissociatives induce experiences sharing many common key
features with NDEs, including the tunnel, experience of clear light communion, out of body
perceptions and a sense of transformative meaning. The work of Griffiths et al shows the
spiritual rejuvenation experienced by ordinary people under psilocybin is lasting and beneficial.
Similar improvements have been found in the terminally ill. The fact that so many of the key
elements are shared strongly indicates the NDE is a natural physiological manifestation of the
way the brain processes consciousness under the kinds of close encounters with death we are
dealing with, including any or all of deprivation of oxygen, or glucose, changes in
neurotransmitters such as norepinephrine (Mobbs and Watt), and other stresses including those
resulting in neuronal hyper-excitation.
My most recent sacred mushroom experience came on with a symphony of shrilling vibrations
that, as they overtake me, spiral me into the visions. It is a synesthesia, which is sensitive to my
mental awareness, listening and looking, so I can enter the existential kaleidoscope and fall into
the ‘other’ reality beyond. Visions come and go of impossible experiences I know I have had and
witnessed first-hand yet know I could never have happened. As Maria Sabina says: "And you
also see our past and our future, which are there together as a single thing already achieved,
already happened . . . I saw stolen horses and buried cities, the existence of which was unknown,
and they are going to be brought to light." Mushrooms have given me extraordinary visions
whose significance I still ponder to this day. I had a horrific vision that my firstborn daughter
would be doomed to an obstruction to her fertility. Then years later, her first offspring was born
with Downs syndrome. My impression from inside these experiences is that all conscious life is
interconnected across space-time and that the sacred mushroom brings us closer to unraveling
the bundle of life that locks us into our personal egos, so that for a minute, or an hour or two, we
can see, through the disembodied eye, the way the universe perceives disincarnately and evercompassionately of the mortal coil. It is a feeling that gives great reassurance to the travails of
life. At the peak I feel as if I am suspended in a state of light-induced electrocution, searingly
high and at the same time utterly pure. As I sit breathless in the living room, non-ordinary reality
comes bursting out of my sub-conscious and across my peripheral vision so I feel as if I am
simultaneously in about five places at once. Next morning I am fresh and clear in the sparkling
sunshine. A new man in a world reborn with the youthful freshness of a new day, my creativity
and sense of emergence rekindled. "But I, I am lord of two ways. I am master of up and down. I
am as a man who is a new man, with new limbs and life, and the light of the Morning Star in his
eyes." D H Laurence The Plumed Serpent.
After the first few minutes of my ketamine experience struggling not to swallow the bitter
insufflated substance for fear of nausea, I realize I am entering a state of peace. The anesthetic
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
570
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
effect is taking me deep into a reverie through what has become a kind of yogic breathing. I fall
deeper into the dissociated state and I realize that it is an experience of simply awesome depth. A
depth so inscrutable, you are touched by it, swept into silent awestruck oblivion - but still
conscious - still there - still aware - somewhere in the aether, as the void breathes its delicate
structured emptiness. I continue to recognize the depth and mystery of what I am witnessing. But
then things take a more sinister turn. My mind is becoming memory-less. It's as if all my brain
and memory circuits are reprogramming themselves and all the needles are beginning to point
every which way. I know it's going to be alright, but it sure feels as if I am going to be stark
staring mad forever. So I decide just to ride with the experience and then suddenly its as if the
dials have connected to the master index of all my life experiences, and here they are, flashing
before my eyes, just as they say about someone who is drowning, but its not just my life
experiences, but the very peak experiences, like the chain of the Himalayas. I realize I am
looking back down on them in the same way Moses might look down on his life and the life of
everyone from the mountain top, and that all the experiences of my life are coming into one
cosmic focus of meaning and destiny. At this point I suddenly realize that everything I have ever
done and everything I will ever do has been brought to this very moment of truth and this very
experience, and it is 'God', and my destiny coming to its true destination at this point, which is
beyond time and space, coming from the very beginning, and for ever. I have this overpowering
feeling of having been taken so far it is the full age of the universe and I have so far to get back
to the land of the living. It is the same thing I have read about where one feels one is uniting with
the universal self and could go with it or return to the incarnate world of individuals. But at the
same time it is the universal mind coming to know and understand itself. At this point it seemed
almost as if my life was now over. I had made the connection which gave my life its central
meaning and though I might in future do nothing else and maybe I would never be able to come
to this point again, my life had meaning in giving ultimate meaning to the totality witnessing and
knowing itself.
Even though NDEs may be physiological, this does not mean these experiences are just
hallucinatory, or in any sense unreal. On the contrary, dreaming experiences, and many
psychedelic and dissociative experiences, as well as NDEs, share a fundamental feature that the
subject experiences them as veridical realities that they have actually seen in the same way as a
waking person experiences the real world around them. They are not imagined, but perceived
with the full integrity of perception of existential reality and occasionally do subsequently appear
to correspond to physical events and realities.
We thus need to come to terms with a fundamental question: “What is the existential nature of
conscious experience?” Is it merely an internal model of reality constructed by the brain, having
no status above an epiphenomenon, a mere shadow constructed by a biological brain, or is it a
fundamental component of the cosmology of the conscious universe?
Subjective Consciousness – What are Mental States For?
Subjective consciousness poses the deepest dilemma for the scientific description of reality.
While we have discovered the Higgs boson and are tantalizingly close to decoding the theory of
everything orchestrating both large-scale cosmology and the fundamental forces of nature and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
571
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
have decoded the human genome and the molecular basis of biological organisms, we still have
no idea of how the brain generates subjective consciousness, or even how or why such an elusive
phenomenon can come about from the physiology of brain dynamics.
The problem is absolutely fundamental because, from birth to death, the sum total of all our
observations of the physical world and all our notions about it come exclusively through our
subjective conscious experiences. Although neuroscience has produced many new exciting
techniques for visualizing brain function, from EEG and MEG to PET and fMRI scans, which
show a deep parallel relationship between mental states and specific modalities of brain
processes, these go no way in themselves to solving the so-called ‘hard problem of
consciousness research’ – how these purely objective physiological processes give rise to the
subjective effects of our conscious experiences. Philosopher Jerry Fodor famously complained
that: “Nobody has the slightest idea how anything material could be conscious. Nobody even
knows what it would be like to have the slightest idea about how anything material could be
conscious” (Deacon).
Fig 3: Existential reality presents as a complementary
paradox. While we acknowledge our subjective
consciousness is somehow a product of our biological brain,
which is in turn a fragile product of physical forces on a
cosmological scale, all our experiences of reality, including
our perceptions of the physical world, as well as dreams
memories and reflections, come exclusively and totally from
our subjective consciousness. This suggests that existential
cosmology is a complementarity between subjective
consciousness and the physical universe, in which both are
fundamental.
Although, from a commonsense point of view, we
are forced to acknowledge that our conscious life
is dependent on or fragile biological brain and that
we will pass out and lose consciousness if we are
struck on the head or sever our blood supply, really all our experiences of the physical world
come as consensual subjective conscious experiences of the world shared by sentient beings.
Indian philosophy declares that consciousness is more fundamental than the grosser
accumulations of physical matter, essentially because it is only through subjective consciousness
that the physical universe becomes manifest.
This leads to another critical question: “Why did nervous systems evolve subjective
consciousness?” If nervous systems are able to fully provide adaptive solutions simply as
heuristic computers, there is no role for extraneous brain functions that simply add a subjective
shadow reality with no adaptive function and presumably a physiological cost. A digital
computer is a purely functional entity, even when processing probabilistic optimizations, so has
no role for a subjective aspect, no matter how complex it becomes.
The fact that animals share physiological properties, which, in humans, are accompanied by
subjective consciousness, implies that subjectivity is a critical survival attribute, which has been
reinforced by natural selection. Its key role has to be anticipating threats to survival and key
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
572
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
strategic advantages. Problems of strategic decision-making in the open environment are
notorious for being computationally intractable because of super-exponential runaway in
calculation times, as exemplified in the traveling salesman problem, whose calculation time
grows with the factorial of the number of cities involved.
All animal nervous systems appear to work on a common basis of edge-of-chaos excitation that
arose in excitable single cells before multi-celled organisms evolved Vertebrate brains have a
common mechanism of massive parallel processing using wave phase coherence to distinguish
ground noise from attended signal, accompanied by transitions from the edge of chaos to an
ordered outcome, in diametric opposition to the ordered serial and digital processing of classical
computers.
Fig 4: In the veridical way existential reality
is generated, subjective experience is
primary. In the consensual overlap of our
subjective experiences we gain a common
experience of the physical world, which we
then interpret as containing biological brains,
which may also be able to have subjective
experiences.
However,
attempted
construction of reality from the physical
universe and its brains remains incomplete
because there is no explanation of how the
brains can also have subjective conscious
experiences – the hard problem of
consciousness research.
The organization of the cerebral
cortex and its underlying structures,
consist of a series of microcolumns
acting as parallel processing units for an envelope of featural characteristics, from the focal line
orientation and binocular dominance of visual processing and tonotopic processing of sounds
through somato-sensory and emotional representations, including those of the body, to abstract
spatial, temporal and semantic features, leading to the strategic executive modules of the
prefrontal cortex and our life aims and thought processes. Attempts to find the functional locus
of subjective consciousness in brain regions have arrived at the conclusion that active conscious
experiences are not generated in a specific cortical region but are a product of integrated
coherent activity of global cortical dynamics, in which the cortical modules we see activated in
brain scans correspond to the salient features of conscious experience we witness subjectively.
This implies that the so called Cartesian theatre of consciousness is a product of the entire active
cortex and that the particular form of phase coherent, edge-of-chaos processing adopted by the
mammalian brain is responsible for the manifestation of subjective experience. This allows for a
theory of consciousness in which preconscious processing e.g. of sensory information can occur
in specific brain areas which then reaches the conscious only when these enter into a wave
synchronous neuronal activity integrating the processing. Three regions associated with global
workspace have been identified as key participants in these higher integrative functions, the
thalamus which is a critical set of relay centres underlying all cortical areas and possibly driving
the active EEG, the lateral prefrontal and the posterior parietal (Bor).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
573
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
Baars’ global workspace approach (1997, 2001) suggests that consciousness is associated with
the whole brain in integrated correlated activity and is thus a property of the brain as a whole
functioning entity rather than a product of some specific area, or system, such as the
supplementary motor cortex (Eccles, Fried et al, Haggard). Furthermore, the approach rather
neatly identifies the distinction between unconscious processing and conscious experience in
terms of whether the dynamic is confined to local or regional activity or is part of an integrated
coherent global response. It is also consistent with there being broadly only one dominant stream
of conscious thought and experience at a given time, as diverse forms of local processing gives
way to an integrated global response. A series of experiments, many by teams working with
Stanislas Dehaene, involving perceptual masking of brief stimuli to inhibit their entry into
conscious perception (Sergent et al, Sigman and Dehaene 2005, 2006, Dehaene and
Changeux,De Cul et al 2007, 2009, Gaillard et al), studies of pathological conditions such as
multiple sclerosis (Reuter et al, Schnakers), and brief episodes in which direct cortical electrodes
are being used during operations for intractable epilepsy (Quiroga et al) have tended to confirm
the overall features of Baars’ model of consciousness based on the global work space
(Ananthaswamy 2009, 2010). EEG studies also show that under diverse anesthetics, as
consciousness fades, there is a loss of synchrony between different areas of the cortex (Alkire et
al). The theory also tallies with Tononi’s idea of phi, a function of integrated complexity used as
a measure of consciousness (Barras, Pagel).
Fig 5: Common regions involved in the self, the
default network and alert consciousness. Above:
regions in the self network (Zimmer). Lower right:
the default network (Fox). Lower left disruptions of
active consciousness (Bor). (a, a2) Medial/Lateral
prefrontal (b,b2) Precuneus/ Posterior cingulate (c)
Anterior insula (d,d2) Lateral/Posterior parietal
running to the temporo-parietal junction (e)
Thalamus.
Although subjective consciousness involves
the entire cortex in coherent activation, brain
scans highlight certain areas of pivotal
importance, whose disruption can impede
active consciousness. These include
prefrontal cortex executive functions, spatial
integration in the parietal, and the central
information pathways of the thalamus.
When we turn to self-consciousness, and the
ongoing notion of ‘self’, which is the
shadowy actor-agent behind all the
manifestations of conscious states, we find a
close association between the default circuit
activated in idle periods, believed to be adaptively envisaging future challenges, and brain
regions involved in our sense of self.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
574
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
These include the medial prefrontal cortex and the cingulate cortex and neighbouring precuneus.
The default network encompasses posterior-cingulate/precuneus, anterior cingulate/mesiofrontal
cortex and temporo-parietal junctions, several of which have key integrating functions.
The ventral medial prefrontal (Macrae et al.) is implicated in processing risk and fear. It also
plays a role in the inhibition of emotional responses, and in the process of decision-making. It
has been shown to be active when experimental subjects are shown experiences which they think
apply to themselves. The changes in Phineas Gage when a tamping iron destroyed his left
prefrontal lobe (O’Driscoll & Leach), leading to him becoming a side-show attraction, show how
such damage can lead to subtle changes of personality and difficulty in making constructive life
decisions, even when localized prefrontal damage does not significantly affect classical IQ tests.
The precuneus (Cavanna & Trimble) is involved with episodic memory, visuospatial processing,
reflections upon self, and aspects of consciousness. Adolescents have the same activations as
adults in the medial prefrontal when they think about themselves, but less in the precuneus than
if they were thinking about a third party, suggesting their theory of mind/self is active but still
under development (Zimmer).
The insulae are also believed to be involved in consciousness and play a role in diverse functions
usually linked to emotion and the regulation of the body's homeostasis, including perception,
motor control, self-awareness, cognitive functioning, and interpersonal experience. The anterior
insula is activated in subjects who are shown pictures of their own faces, or who are identifying
their own memories, and uniquely in a woman subject who experiences watching other people
being touched, as if she herself is being touched, suggesting it plays a critical role in the sense of
self. The temporo-parietal junction is known to play a crucial role in self-other distinction and
theory of mind. Damage to this area, or electrical stimulation of it, has been implicated in
producing OBEs.
The mind is naturally partitioned between features we usually assign to be external, such as
visual and auditory, and those that usually function as part of our bodily sensations and reactions,
such as somatosensory, emotional and motor – those we associate with ‘self’. Self also has a
specific relationship with voluntary motor activity. All intentional actions lead both to direct
motor outputs and to systems that monitor these actions so we have an integrated sensory-motor
experience of action.
Nevertheless the relationship of ‘self’ and our body image can become dissociated in bizarre and
disquieting ways, which show us that the ‘self’ is very much a dynamic representation in the
brain. Amputees sometimes suffer a phantom limb, feeling a limb is still sometimes painfully
present, possibly due to new circuits invading the brain areas that previously served the limb.
Conversely, people with body integrity identity disorder and xenomelia seek to cut their limbs
off because of the oppressive feeling that one or more limbs of one's body do not belong to one's
self. Again this may have a physiological basis in cerebral anomalies in the body image map. An
even more convoluted form of ‘self’ dissociation, apotemnophilia, involves sexual arousal based
on the fantasy of becoming an amputee. Schizophrenics likewise can become catatonic and
refuse to move, believing their limbs are under the control of unseen forces and people with
certain forms of cortical injury suffering hemispatial neglect refuse to recognize that one side of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
575
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
their body is their own and, depending on the extent of damage, may completely neglect the lefthand side of their entire sensory and attentional left field without even recognizing half of reality
is missing.
Fig 6: Top right: Activation of left frontal and right parietal areas involving mirror neuron activity (Iacoboni). A set
of brain areas to do with both empathy and one's reactions and behavior in relation to others associated with 'reading
the minds' of others (Motluk) has been discovered in the form of 'mirror neurons' which, although they may be in
areas we usually associate with motor function, intentional action or even the expression of language, contain a
population of neurons which react in the same way when the same action is being performed by another individual.
Lower right: Response to an unpleasant experience, in the amygdala, differs between men, who respond in the right
amygdala and are drawn to central features, and women who respond in the left amygdala and remember more of
the context (Cahill). Left: Forms of hemispatial neglect.
We have seen already that OBEs are a function of changes in the way we integrate experiences,
and that OBEs can be induced by tricking the brain into perceiving an external sensation as being
part of ‘self’, e.g. through combining visual experience of another person being touched with
somatosensory impressions of being stroked.
In a more general way we can see that the nature of ‘self’ and hence of self-consciousness is both
a function of social interactions with others (Bond), and is also a ‘sense’ we attribute to others,
both in terms of our mirror neurons, which provide direct sensations of what others might be
feeling, and in terms of our intuitive assessment of others ‘self’-assumptions. Social emotions
such as admiration or compassion, which result from a focus on the behaviour of others, tend to
activate the posteromedial cortices, important in constructing our sense of self (Immordino-Yang
et al.), something Antonio Damasio calls the “social self”. One can thus see that our personal
idea of self is part of a larger adaptive strategy – an intuitive ‘theory of mind’ to understand selforganized behavior in others, something essential for our social survival. People can sustain up to
five or six successive layers of indirected attribution of mind - “I think that he believed she was
intending to go to the movies with him” - similar to their digit span.
This social idea of ‘self’ also shows differences across cultures (Brealey). Researchers
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
576
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
examining autobiographical memory, have found Chinese people's recollections are more likely
to focus on moments of social or historical significance, whereas people in Western countries
focus on personal interest and achievement. This is similar to the sex differences in response to
an unpleasant experience in the amygdala, which differs between men, who respond in the right
amygdala and are drawn to central features, and women who respond in the left amygdala and
remember more of the context (Cahill). Both these show us that the 'geography of the self' varies
from culture to culture just as it does between the sexes. Intriguingly, babies as young as seven to
fifteen months appear to be able to intuitively sense false beliefs in others, suggesting this kind
of circuitry has an innate basis (Onishi & Baillargeon, Kovács et al.).
Research is now beginning to suggest there may be two forms of ‘theory of mind’, one fast and
intuitive, developing almost from birth, and the other more complex and based on using
experiences in life to provide more finely attuned adaptive responses (Weir). People diagnosed
with Asperger's syndrome, a high-functioning form of autism, show they have the explicit
system, yet they fail at non-verbal tests of the kind that reveal implicit theory of mind (Senju et
al.). Evidence for a social theory of mind is also reflected in the relationship between social
network size, orbital-prefrontal cortex volume and theory of mind performance (Powell et al.).
Studies using transcranial magnetic stimulation implicate the right temporo-parietal junction in
enabling mental states perceived in others to participate in making moral judgments (Young et
al.). A study of people with right parietal damage likewise found them to have enhanced
spirituality consistent with a cortical lateralization notion of the right parietal dealing with ‘self’
and the left with ‘other’, with decreased right function leading to ‘self-transcendence’ (Johnstone
& Bodling).
We thus come full circle to the dual problems of space-time anticipation and the notion of ‘freewill’ – can subjective conscious experiences actually lead to changes in physical outcomes by
affecting the outcome of our biological brain states?
Many scientists tend to a classical view of physics and a reductionistic assumption that all human
activity must be a product of brain function alone and that any notion of free will, in which
subjective consciousness can act to induce a change in outcomes of objective brain states is
delusory. This flies in direct contradiction to our subjective feelings that we are autonomous
beings with voluntary control over our fates. To claim otherwise in all honesty leads to a
catatonic outcome where no purely conscious volition can lead in any way to an active brain
state of any form of behavior. It also contradicts the assumptions of legal accountability, where
we assume a person of sound mind is responsible for the consequences of their consciously
intentional actions.
The classical way around this impasse is then to claim that the subjective impression of
voluntary autonomy is a kind of delusion necessary for an organism to maintain an active life in
adaptive survival, but this itself is a contradiction, because it assumes subjective consciousness
does have an adaptive advantage of some kind.
Many physicists, from Arthur Eddington’s citation of the uncertainty of position of a synaptic
vesicle in relation to the thickness of the membrane on, have drawn attention to the fact that the
quantum universe is not deterministic in the manner of classical Laplacian causality and that
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
577
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
quantum uncertainty provides a causal loophole, which might make it possible for free will to
coexist in the quantum universe. This in turn has led to opposing pleas from classical
reductionists that the law of mass action would condemn any fluctuations at the quantum level to
become swamped and that no quantum effects can possibly interfere in the cellular level
processes of neurodynamics. This position is obtuse and incorrect.
Biology is full of phenomena at the quantum level, which, far from being swamped by mass
action, are essential to biological function. Enzymes invoke quantum tunneling to enable
transitions through their activation barrier. Protein folding is likewise an effective manifestation
of quantum computation intractable by classical computing. When a photosynthetic active centre
absorbs a photon, the wave function of the excitation is able to perform a quantum computation,
which enables the excitation to travel down the most efficient route to reach the chemical
reaction site (McAlpine, Hildne et al). Quantum entanglement is believed to be behind the way
some birds navigate in the magnetic field. Light excites two electrons on one molecule and
shunts one of them onto a second molecule. Their spins are linked through quantum
entanglement. Before they relax into a decoherent state the, Earth's magnetic field can alter the
relative alignment of the electrons' spins, which in turn alters the chemical properties of the
molecules involved (Amit, Courtland). Quantum coherence is an established technique in tissue
imaging, demonstrating an example of quantum entanglement in biological tissues at the
molecular level (Samuel, Warren).
Although many processes in the brain need to be resilient to quantum noise, in the event of a
critically poised dynamic in which there is no stable determining outcome, known brain
processes, from chaotic sensitivity, through and the amplifying effects of chandelier cells, to
stochastic resonance are able to amplify fluctuations at the quantum-molecular level to the
neuronal and ultimately to a global change in the dynamics (King). Hence a change of a single
ion channel can lead to threshold activation of a hippocampal neuron and in turn to a change in
global brain activity.
Karl Pribram the founder of the idea of the holographic brain has drawn attention to the
suggestive similarity between phase coherence processing of brain waves in the gamma
frequency range believed to be responsible for cognitive processes and the wave amplitude basis
of quantum uncertainty in reduction of the wave packet and quantum measurements based on the
uncertainty relation Et h , where the relation is determined by the number of phase fronts to
be counted (see fig 8). This raises an interesting spectre, that the evolution of nervous systems
has arrived at a neurodynamic process forming a model of the quantum processes at the
foundation of physics, suggesting that quantum entanglement in brain states may be a basis for
active biological anticipation of immediate threats to survival through the forms of subjective
consciousness the brain generates.
To get an idea of what this advantage might be, we need to examine more closely the kinds of
survival situation that are pivotal to organisms in the open environment and the sorts of
computational dilemmas involved in decision-making processes on which survival depends.
Several researchers have highlighted various aspects of consciousness in an attempt to
understand how it evolved (Wilson). For example higher integrative processing associated with
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
578
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
global workspace has been extended to a few other animals such as apes and dolphins. Another
strand suggests that making integrative decisions socially would have aided better environmental
decision-making concerning hard to discern situations involving the combined senses (Bahrami
et al). However both these ideas pertain to integrative capacities of brain processing and don’t
provide any direct explanation of why consciousness also evokes the Cartesian theatre of
subjective experience. We need to try to unravel the much harder problem of why subjective
experience occurs at all, even in a parallel integrative brain.
Open environment problems of survival are intractable not just because they involve superexponentiating contingent factors which would leave a digital antelope stranded at the crossroads
until pounced upon by a predator, but because they are prone to irresolvable structural
instabilities, which defy a stable probabilistic outcome.
Fig 7: Decision-making in the open environment
involves computationally intractable problems,
which cannot necessarily be solved by
probabilities alone. Which path should we take
to the water hole today? There could be a tiger
on the shady path or a lion on the stony path.
Both of these animals are also trying to outmanoeuvre us by changing their decisionmaking.
Suppose a gazelle is trying to get to the
waterhole along various paths. On a
probability basis it is bound to choose
the path, which, from its past
experience, it perceives to be the least
likely to have a predator, i.e. the
‘safest’. But the predator is likewise
going to make a probabilistic calculation
to choose the path that the prey is most
likely to be on i.e. the same one.
Ultimately this is an unstable problem
that has no consistent computational
solution.
There is a deeper issue in these types of situation. Probabilistic calculations, both in the real
world and in quantum mechanics, require the context to be repeated to build up a statistical
distribution. In an interference experiment we get the bands of light and dark color representing
the wave amplitudes as probability distributions of photons on the photographic plate only when
a significant number have passed through the apparatus in the same configuration (see fig 8). The
same is true for estimating a probabilistically most viable route to the waterhole. But real life
problems are plagued by the fact that both living organisms and evolution itself are processes in
which the context is endlessly being changed by the decision-making processes. Repetition
occurs only in the most abstract sense, which is one reason why the massively parallel brains we
have are so good at such problems.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
579
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
Finally, in many real life situations, there is not one optimal outcome but a whole series of
possible choices any or all of which could lead either to death or survival and reproduction. A
central enigma of quantum reality is the Schrodinger cat paradox, in which a cat set to be killed
by a radioactive scintillation in quantum reality is both alive and dead with differing
probabilities, but in our subjective experience, when we open the box the cat is either alive or
dead with certainty. This is the renowned problem of the causality-violating reduction of the
wave packet.
Come back for a minute to the animal tracing a path to the waterhole. Animals and even people
are quite lousy computers with a digit span of only six or seven and a calculation capacity little
better than a pocket calculator. We all know what we do and what conscious animals do in this
situation. They look at the paths forward. If they have had a bad experience on one they will
probably avoid it, but otherwise they will try to assess how risky each looks and make a decision
on intuitive hunch to follow one or the other, depending on how thirsty and desperate, or
distractedly oblivious they have become by the sunlight and green shoots in the glade.
In a sense, all their previous life experience is being neatly summed up in their parallel
processing awareness and their semantic and episodic memory, but the real role of consciousness
is to keep watch on the unfolding living environment, to be paranoid to hair-trigger sensitivity
for any hint of a movement or the signs or sound of a pouncing predator. The absolutely critical
point here is that their consciousness is providing something completely different from a
computational algorithm, it is a form of real time anticipation of threats and survival that is
sensitively dependent on environmental perturbation and attuned to be anticipatory in real time
just sufficiently to jump out of the way and bolt for it and survive. So the key role of subjective
consciousness is an integrated ‘holographic’ form of space-time anticipation.
How could this come about? One way is by quantum entanglement. In quantum mechanics, not
only are all probability paths traced in the wave function, but past and future are interconnected
in a time-symmetric hand-shaking relationship, so that the final states of an entangled pair on
absorption are determining boundary conditions for the interaction just as the initial states that
created them are. Thus when an entangled pair are created, each knows instantaneously the state
of the other and if one is found to be in a given state, the other is immediately in the
complementary state no matter how far away it is in space-time. This is the ‘spooky action at a
distance’, which Einstein feared because it violates local Einsteinian causality. The transactional
interpretation of quantum mechanics expresses this relationship nicely in terms of offer waves
from the past emitter and confirmation waves from the eventual absorbers, whose wave
interference becomes the single or entangled particles passing between.
The brain explores ongoing situations which have no deductive solution, by evoking an edge-ofchaos global entangled state which, when it does collapse, results in the ‘aha’ of insight learning,
but otherwise remains sensitively tuned for anticipating any signs of danger. This is pretty much
how we do experience waking consciousness.
The key thing about quantum entanglement is that it cannot be used to make classical causal
predictions, which would formally anticipate a future event, so the hand-shaking is only good so
long as we maintain an entangled state. This suggests that the brain may use its brain waves and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
580
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
phase coherence to evoke entangled states that carry quantum encrypted information about
immediate future states of expereince as well as immediately past states, in a kind of quantum
‘present’ which we witness as subjective experience encoded through the parallel feature
envelope of the cerebral cortex. The idea then is that his provides an intuitive form of
anticipation which cannot however be crystallized into a fully causal classical prediction
algorithm because it would collapse the entanglement to do so.
Fig 8: (1) Schrodinger cat experiment has
a cat in a box with a radioactive
scintillation counter, which works by
quantum tunneling out of the nucleus
triggering a hammer to smash a cyanide
flask pronouncing a cat alive and dead
with differing probabilities according to
the tunneling wave function of the nucleus
potential well. However we find the cat is
either alive or dead with certainty. (2) The
uncertainty relation Et h is derived
directly from the counting of wave
coherence beats, since energy is related to
frequency by E h and t 1 / .
(3) Quantum interference experiment
shows wave-particle complementarity and
reduction of the wave packet occurs
statistically (centre) according to the
amplitude of the wave function (right)
although the wave-particle reduction of
individual quanta (left) is unpredictable.
(4) Wheeler delayed choice shows time
reversed boundary condition. A cosmic
scale version of the interference
experiment using galactic gravitational
lensing can be adjusted at the detector
after the photons have traversed space to
either sample a particle going one way
round, or a wave interference going both
ways. (5) The transactional interpretation
visualizes an exchanged particle wave
function as the interference of a retarded
usual time direction offer wave and a
time-reversed advanced confirmation
wave. (6) Time symmetric interactions
also occur in quantum field theories where
special relativity allows both advanced
and retarded solutions because of the energy relation E p m . (a,b) Virtual photons and elecctron2
2
positron pairs deflecting an electron in quantum electrodynamics. Since the photon is its own anti-particle, a
negative energy photon traveling backwards in time is precisely a positive energy one traveling forwards. (c) weak
force exchange (d) An electron scattering backwards in time is the same as positron creation-annihilation.
But there is more to this cat paradox situation. In the quantum universe we have multiverses.
Quantum mechanics appears to preserve all the conceivable outcomes in parallel so that, not only
is Schrodinger’s cat both alive and dead, but Napoleon has both won and lost the battle of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
581
Journal of Consciousness Exploration & Research | July 2013 | Volume 4 | Issue 6 | pp. 561-581
King, C., The Cosmology of Conscious Mental States (Part I)
Waterloo. Many of these strategic outcomes, indeed all the accidents of history, depend on
uncertainties that go in principle right down to the quantum level.
There is continuing debate among physicists about how and where in the causal chain, reduction
of the wave packet actually occurs. While decoherence theories suggest this may occur simply
through interaction of single or entangled states with other particles. e.g. in the experimental
apparatus, in a fundamental sense the wave function of the entire universe appears to one single
multi-particle entangled state and so the whole notion of a single line of history unfolding seems
to be something only our conscious awareness is able to determine. Several of the founding
quantum physicists adhered to this view. John von Neumann suggested that quantum observation
is the action of a conscious mind. That argument relies on the view that there is something
special about consciousness, especially human consciousness. Von Neumann argued that
everything in the universe that is subject to the laws of quantum physics creates one vast
quantum superposition. But the conscious mind is somehow different. It is thus able to select out
one of the quantum possibilities on offer, making it real - to that mind, at least. Max Planck, the
founder of quantum theory, said in 1931, "I regard consciousness as fundamental. I regard matter
as derivative from consciousness." Werner Heisenberg also maintained that wave function
collapse—the destruction of quantum superposition—occurs when the result of a measurement is
registered in the mind of an observer. In Henry Stapp’s words we are "participating observers"
whose minds cause the collapse of superpositions. “Before human consciousness appeared, there
existed a multiverse of potential universes. The emergence of a conscious mind in one of these
potential universes, ours, gives it a special status: reality” (Brooks). This is effectively a
complement to the anthropic principle of physical cosmology in which conscious observers are
selective boundary conditions on the laws of nature in the universe (Barrow and Tipler).
Thus another idea of the role of subjective consciousness is that it is a way the universe can solve
the super-abundance of multiverses to bring about a natural universe in which some things do
happen and other things don’t. One of the most central experiences of our transient mortal lives
is that there is a line of actual history in which each of us, however small and insignificant our
lives, are participating in bringing the world into actual being, albeit sometimes somewhat
diabolically in times of selfishness and exploitation, but with some reflection on our own
transience, perhaps reaching towards a more enlightened existence, in which the passage of the
generations is able to reach towards a blessed state where the universe comes to consciously
understand itself ever more deeply and completely.
This brings us to a nub question: “Can consciousness anticipate physical reality, let alone
influence it through will?”
(Continued on Part II which also contains the references)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
103
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
Article
Mind Over Matter: Investigation of Materialization of Intentions
Pradeep B. Deshpande*1, Sanjeev A. Aroskar2, S. N. Bhavsar3, and B. D. Kulkarni4
1
Professor Emeritus of Chemical Engineering, University of Louisville, & Six Sigma & Advanced Controls,
Inc. P.O. Box 22664, Louisville, KY 40252 USA
2
Ganesh Computers, Survey No. 143, Sneha Building, Opp. Lokmat Office Singhad Road, Vadgaon Dhayari,
Pune-411 041, India
3
Spacetime Research Institute, 29, Vrindavan Society No. 2, Pashan, Pune-411008, India
4
Chemical Engineering Division, CSIR-National Chemical Laboratory, Homi J. Bhabha Road, Pune, India 411008.
Abstract
In this article, we present our investigation of materialization of intentions using the input-output
data based Six Sigma methodology for problem solving. The investigation is inspired by our
respective Gurus, the wisdom of present and past seers, and the works of several scientists. We
present two examples of materialization of intentions (change of pH and levitation). The pH
example is preliminary requiring additional experimentation. We believe that the evidence
presented is very supportive of the hypothesis of materialization of intentions. We hope this
paper will contribute towards the unfolding of a Copernican-like revolution which will have
profound positive impact on humanity.
Keywords: Aristotle, Copernicus, Galileo, Six Sigma, Internal Excellence, External Excellence,
Consciousness, Intentions, Emotions, Materialization of Intentions, Meditation.
Prayojanam anudishya na mandopi pravartate
(Without intentions, there can be no materialization). Well-known aphorism
Kriyasiddhi satve bhavati mahatam nopakarane
(The secret of success in materialization of intentions lies in the Sattva
- S component - and not in the instruments and devices). Kalidasa – Raghu Vansha
Experiences of Vedic seers and experiments of scientists will lead the world. Shri Arubindo
Introduction
The Late Maharishi Mahesh Yogi had the vision of transforming this world into a more peaceful
world. Materialization of intentions was a key element of that vision. Numerous scientists
investigating his program over several decades had found it to be credible and numerous
scientific papers on his program have appeared in reputed international journals (see e. g., 23).
*
Correspondence: Prof. Pradeep B. Deshpande, Six Sigma & advanced Controls, Inc. P.O. Box 22664, Louisville,
KY 40252-0664, http://www.sixsigmaquality.com E-mail: pradeep@sixsigmaquality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
104
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
In the Aristotle era (Born 384 BCE) lasting some two thousand years, it was widely believed that
the planet Earth was at the center of our solar system. That began to change when Copernicus
discovered in the 15th Century that the Sun was at the center. Galileo was put under house arrest
in the 16th Century for subscribing to the Copernican model. The widespread acceptance of the
heliocentric model of the solar system ushered in the first Copernican revolution of thought (22).
That revolution enabled tremendous strides in science over the course of the ensuing five
hundred or so years to the present time. However, throughout this period, scientists have
steadfastly maintained that consciousness, intentions, and emotions cannot possibly influence
physical reality. To understand this further, consider Equation (1) we refer as the Tiller
hypothesis (22):
(1)
QT QP1 QP2
In Equation (1) QT is the total measurement, Qp1 is the current reality, α is an activity coefficient
(0 < α < 1), and Qp2 is psycho-energetic component. Ordinarily α = 0 and therefore the total
measurement is reflective of the current reality. However, when becomes nonzero, the total
measurement will reflect the intended new reality.
The extent to which the new reality materializes increases with the increasing values of α. Now,
if multiple experiments are conducted to test the Tiller hypothesis, many will likely fail and
herein lies a problem for science. Science demands that for a hypothesis to be acceptable, it must
be possible to repeat the experiment and obtain the same results regardless of who conducts the
experiment, how many times, and where, and that is the way it should be. The problem is not
with the Tiller hypothesis but that the activity coefficient is a function of the level of
consciousness of the tester among other unknown and uncontrollable causes. That is to say, the
access to the intended new reality may be possible only when the level of consciousness of the
experimenter is sufficiently high. Thus, science is not the proper framework to examine the Tiller
hypothesis, six-sigma is. We have coined the name “The Brahma Uncertainty Principle” for this
type of uncertainty in measurements (8).
Six Sigma is a systemic methodology for problem solving that is based solely on input-output
data. Fundamental mechanistic approaches to problem solving should always be preferred but
when sufficiently-detailed knowledge of the system under scrutiny is unavailable, Six Sigma is
the appropriate tool to use. Such is the case with human beings. We all are multivariable,
nonlinear, self-regulating, and evolving. Unlike science which demands that the results of every
experiment be repeatable and reproducible, Six Sigma posits that there will always be a certain
amount of inherent and inevitable variation in the outcomes of a process or transaction due to
uncontrollable and unknown causes.
Statisticians refer to these as common causes. In human beings, the common cause variability
arises for two reasons: One source is what we inherit from our ancestors (Prarabdha Karma) and
the other is what we accumulate by our own actions from the time of birth to the present age
(Agama Karma). Thus, common cause variability precludes zero defects ad infinitum. That is, if
a sufficiently large random sample of aspirants were to undertake the program of materialization
on intentions, no matter how well it is designed, understood, and practiced, not all will succeed.
The goal of Six Sigma is to uncover all discoverable sources of variation so that maximum
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
105
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
number of aspirants will achieve their goal. In the light of these observations, we propose the
following modification to the Tiller hypothesis:
QT QP1 ( LOC )QP2
(2)
Where LOC is parameter associated with the Level of Consciousness.
Tiller realizes the functional dependence but it may be better to state it explicitly. Materialization
of intentions may be seen as the pursuit to render nonzero. Tiller has shown that an intention
can not only be materialized but it can also be imprinted on an electrical device he calls Intention
Host Device (IHD) for use elsewhere (www.tiller.org). The intention is imprinted on the device
by a meditative practice. As an example, Tiller has presented a case study involving the raising
or lowering the pH of water by 1 unit by intention alone without the addition of any chemicals.
Figure 1 is a plot from their study for the intention of increasing the pH by 1 unit. The pH is seen
to decrease over the first twenty-four hours as the water equilibrates with the surrounding air and
then rises over time to reach the intended +1 unit change in pH. The accuracy of the pH system is
reported to be +0.02. According to Tiller, these results have been reproduced at ten different
laboratories in the US and Europe but always imprinting the device at their home-base in
Arizona for use in these ten laboratories. The notion of Brahma Uncertainty Principle and the
need for Six Sigma analysis can be readily realized in this example. If a number of laboratories
were to try to reproduce these results by imprinting the device at their own end, not all will
succeed!
CO2
Figure 1. Raising of pH by Intention Alone (Source: www.tiller.org)
Two coauthors of this paper are chemical engineers and we debated if the change in the
hydrogen and hydroxyl ion concentration reported in the Tiller experiment violates the
conservation of mass principle since no chemicals were added. In the example soon to be
presented involving meditators lifting of the ground we encountered a similar dilemma. Were the
meditators defying the Newton’s Law of Gravity? Our current understanding is that the laws of
nature can never be violated although in some cases we may not fully understand them.
However, intentions may manipulate the system delivering the intended results without ever
violating the fundamental laws of nature. Thus, in the context of the Tiller example, it is possible
that the intention has caused the output of the pH measuring system to undergo the desired
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
106
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
change but the pH of water itself had not changed. Similarly, in the levitation example,
meditators have made themselves sufficiently light to lift of the ground and not that they
remained heavy and still lifted of the ground.
During September – October 2013, the first author conducted an experiment to reproduce the
Tiller results with the cooperation of Dr. Mahendra Sunkara, Interim Director, Conn Center for
Renewable Energy Research and Professor of Chemical Engineering, University of Louisville,
and his doctoral scholar, Swathi Sunkara. The intention host device was procured from the Tiller
organization. Figure 2 shows a photograph of Rebecca Martin, Ph. D. in Psychology, and her
meditators who imprinted the intention of raising the pH by 1 unit using the Tiller procedure
(www.tiller.org). Figure 3 depicts the response of pH over time.
Figure 2. Dr. Rebecca Martin’s Meditation Group
Figure 3. The Response of pH in Our Experiment
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
107
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
In our investigation, the initial reduction in pH occurred over a much longer period of time. Our
measurement system consisted of a Eutech Instruments Oakton pH Testr 2.0 while Tiller’s is a
computer-based system described in Tiller and Dibble (23). Our data on pH measurement is
preliminary and more experiments need to be carried out. It is possible that here too what has
changed is the measurement of pH and not the pH itself. Other sources of variability between the
Tiller results and ours include: (1) Calibration issues at our end, and (2) Tiller used purified
water from a vendor of scientific supplies while we used distilled water from the supermarket.
These observations lead us to suggest that we may have succeeded in our intention of raising the
pH at least in the qualitative sense. There is nothing in traditional chemistry and physics that
allows for the type of a change depicted to occur. Later in the paper we will learn Patanjali’s
explanation of the state required for the materialization of intentions.
We were also inspired by the daily discourses of Baba Shivanandji (www.shivyog.com) in India
on Z-TV where he regularly speaks of the wherewithal for the materialization of intentions using
Durga Saptashati – 700 shlokas of Durga (21). The life-story of the Buddha and how he evolved
from being a prince to the Buddha, my (first author) conversations with Guruji Paranjothiyar
together with the citing of my mother during Japamala mantra meditation (108 beads rosary
mantra meditation) in a levitated state by my older sister and her two children have also served
as motivating factors.
To continue, Larry King asked the Late Maharishi Mahesh Yogi in a CNN TV interview on May
12, 2002, what is transcendental meditation? Maharishi replied:
Transcendental meditation is a means to do what one wants to do in a better way, in the
right way for maximum results. It's a program in which the mind begins to experience
its own finer impressions, finer thoughts, and then finally transcends the finest thought
to the level called self-referral consciousness, the ultimate reality of life. This is pure
intelligence from where the creation emerges, from where the administration of life is
maintained, and from where the physical expression of the universe has its basis.
Transcendental meditation brings about transcendental consciousness, which is selfreferral consciousness, the source of all intelligence.
Later in the interview, Larry Asked, What is Yogic Flying? Maharishi responded:
It is that level of creative intelligence in the self-referral consciousness that will
materialize the intentions. Whatever the intentions, materialize the intentions.
Larry King appeared to remain puzzled throughout the interview. The interview is available on
YouTube at (http://www.youtube.com/watch?v=0icNZnUxYo0&feature=relmfu). The reader is
also encouraged to view the video at http://www.youtube.com/watch?v=k1cwMc4Myvg.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
108
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
Six Sigma Project for Materialization of Intentions
In the following paragraphs, we present the contours of a Six Sigma project for the
materialization of intentions. We have coined the name Sankalpa Siddhi Sadhana for the
program. In Sanskrit, Sankalpa refers to intention(s), siddhi to realization, and Sadhana is
meditation. The name resonated with us as the scientific framework for external excellence, Six
Sigma, also has s as the first letter in each of the two words. Thus, the 2s’s for external
excellence plus the 3s’s for internal excellence equates to 5s’s for total excellence.
Central Premise: An intention imprinted in the deepest recesses of our consciousness
materializes.
Program Objective: Design, implement, and assess the performance of a process for testing the
hypothesis of materialization of intentions with Six Sigma principles.
Outcomes: The outcome measures (intentions) of general interest are improvement in health &
wellbeing, relationships, exemplary performance in all aspects of life, creativity and
innovativeness, less discord, better decision making.
Tools for investigating the hypothesis: The principal tools available appear to be: (i)
Meditation practices as gleaned from the Sanskrit Yoga Sutras of Patanjali and Tamil
Tirumantiram of Tirumular (18); (ii) Mantras as gleaned from Mantra Shastra (e. g., see Sutra
4.1 in Patanjali’s Yoga Sutras (18); (iii) What on the surface may appear as religious practices in
Durga Saptashati (21) program of Baba Shivanandji. In our line of thinking, there is really no
difference between spirituality, religion, and science. We may use whichever resonates with us.
The parameters to be optimized are: (1) Stepwise process, (2) Chronology, and (3) Duration.
In his book The Divine Matrix, Gregg Braden presents the results of several scientific
experiments of European, American, and Russian scientists showing that we all remain
connected at some level with a field of energy via what in Mahayana Buddhism is called the
Indra’s Net, just as everything was at the time of the Big Bang. This energy field has enormous
intelligence in that it responds to the power of human emotions. Therefore, we may tap into this
field using emotions as the language of communication. Even temporary access to this field
appears to bring about enormous benefits. Connecting to the “Net” would appear important if our
pursuit of materializing intentions is to succeed.
A topic related to connecting to the Net is the notion of Purusha and Prakriti of the Samkhya
philosophy. Patanjali begins with the verse, Atha Yoganushasanam (I am exposing you
henceforth to the science of Yoga). Patanjali appears to assume that the reader is familiar with
the concept of Purusha and Prakriti. To briefly explain, there are two basic principles from which
the universe is deemed to be manifested. Purusha - characterized by cosmic consciousness
through which he, Purusha, observes, witnesses, and supervises Prakriti. At the cosmic level,
whatever has been created is nothing but Prakriti. At the level of a living being, there is also a
purusha and prakriti that are microcosmic parts of the cosmic Purusha and cosmic Prakriti,
respectively. Without purusha, prakriti can do nothing. Our prakriti includes the five senses, five
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
109
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
sense organs, five sense faculties, and five different types of sense objects (panch mahaboot five creative elements - Earth/matter, water/liquid, fire/heat, air, and Ether/space).
Purusha is ever present, unchanging, and above and beyond the pairs of opposites (e. g.,
happiness/sadness) and defects of any kind. Individual purusha being a microcosm of the cosmic
Purusha, the potential for purusha to acquire the attributes of Purusha exist. The obstacles to
progress are our mind, intellect, and ego. Because of this, these three control our prakriti rather
than our purusha. The meditative practices are intended to remove this obstacle. When this
obstacle is removed, the individual consciousness gets connected to the cosmic consciousness.
Patanjali’s Yoga Sutras (Vedic Sanskrit tradition) and Tirumular’s Tirumantiram (Old Tamil
tradition) suggest that meditating on a specific sutra will materialize the associated intentions
(see e.g., sutra 4.1 (18). It may therefore be reasonable to include in our practices the intention of
removing the obstacles and endowing us with the understanding of Purusha and Prakriti. Prakriti
cannot exist without Purusha and therefore the intention must include both. Connection to the
Net is synonymous to connecting our consciousness with the cosmic consciousness.
Having opted for the Yoga Sutras to investigate the phenomenon of materialization of intentions,
there is an immediate problem. There are 195 sutras - aphorisms - (In the case of Durga
Saptashati there are 700 verses). The question is how many of them should be included in the
meditative practices and which ones. Each of them has associated with it one or more specific
thought/intention/emotion and therefore, the selection of the correct ones could conceivably spell
the difference between success and failure. The chronology and duration too are likely major
impact factors. We have selected some twenty sutras for this Six Sigma project. We leave it to
the readers to select their own set of sutras and carry out the investigation and evaluate the
efficacy of their selection. We site several sutras taken from Govindan (18) for illustrative
purposes:
A sutra on Purusha and Prakriti is:
Sva-svami-saktyoh sva-rupa-upalabdhi-hetuh samyogah
2.33
Translation:
The union (coming together) of the owner (purusha) and the owned (prakriti) leads
to the recognition of the essence and power of them both.
In sutra 2.17, Patanjali says, the reason for suffering is that we confuse the Seer (purusha) with
the Seen, the constituent forces of nature (prakriti), and this suffering leads to fluctuations of our
consciousness which is an obstacle to progress.
A couple of sutras outlining the obstacles to progress are:
Vyadhi-styana-samasya-pramada-alasya-avirati-bhranti-darsana-bhumikatva-anavasthitvatvani
citta-viksepas-te’ntarayah
1.30
Translation:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
110
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
Disease, dullness, doubt, carelessness, lethargy, absence of detachment,
false perception, inability to reach firm ground, and instability
cause fluctuations of consciousness and become obstacles.
And
Drg-darsana-saktyor-eka-atmata-iva-asmita
2.6
Personal ego identifies the power of the Seer (Purusha) with
that of the instrument of Seeing (body-mind).
Sutras 1.32 and 2.11 provide the path forward for progress.
Tat-pratisedha-artham-eka-tatva-abhyasah
1.32
Translation:
The practice of concentration on a single object is the best way
to overcome the obstacles.
and
Dhyana-heyas-tad-vritayah
2.11
Translation:
These fluctuations of our consciousness are discarded by meditation.
Next, suppose you have become aware of the increasing body of evidence suggesting a strong
link between positive emotions (unconditional love, compassion, kindness, empathy, etc.),
reduced fluctuations in and rising levels of consciousness, internal excellence, health & wellness,
and exemplary business performance and you wish to include them in your meditative practices.
Patanjali narrates the path forward for progress:
Maitry-adisu balani
3.23
By communion [samyama: Dharana (concentration), Dhyana (meditation), Samadhi
(contemplation)] on friendliness and other such qualities, the power to transmit them is attained.
There are other sutras related to positive emotions; one is:
Vitarka-badhane pratipaksa-bhavanam
2.33
Translation:
When bound by negative thoughts, their opposites (positive ones)
should be cultivated. This is pratipaksha bhavanam.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
111
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
The importance of cultivating positive emotions is further explained in the next sutra:
Vitarka: himsa-adayah krta-karita-anumodita lobha-krodha-moha-purvaka
Mrdu-madhya-ahimatra dukha-ajnana-ananta-phalaiti pratipaksha-bhavanam
2.34
Negative thoughts or acts such as violence, etc., done by us or by someone else on our behalf, or
endorsed by us, whether incited by greed, anger, or infatuation, whether indulged in with mild,
moderate, or strong intentions result in endless ignorance and unhappiness. Hence, the need for
the cultivation of opposite thoughts (pratipaksha bhavanam).
Materialization of intentions giving the desired outcomes could take time measured in months or
even years. Levitation may serve as a valuable intermediate observation indicative of progress
with our meditative practices. If we succeed, we may also surmise that this depth of
consciousness is that state sufficient enough to materialize the intention of levitation. This is
important because in the absence of an intermediate result, we may discover too late why we did
not succeed. It is important to remember that levitation happens; we do not try to levitate.
Patanjali’s yoga sutras related to levitation are 3.39 and 3.42: The sutra 3.42 is:
kaya-akasayo Sambandha-samyamat laghu-talasampatteh ca akasa-gamanam
3.42
Translation:
When we concentrate (sanyama) upon the gap between the skin of our body and the adjoining
space, lightness of objects such as cotton and the capacity to travel across space are acquired.
In an earlier paper, we provided a scientific explanation of levitation during meditation using
principles of fluidization widely known in chemical engineering (10). The practices render an
aspirant light as cotton and so he lifts up from the ground, not that he remains heavy and still
levitates. The phenomenon of levitation does not violate the basic laws of physics.
The Practice
Patanjali suggests that the issues related to physical health, stresses and strains are also obstacles
to progress. To address these issues Asanas (yoga postures) and Pranayam (breathing exercises)
are suggested. Each sutra is studied on a regular basis until its meaning and significance are
internalized. An operative word or a small group of words reflective of the meaning of the sutra
are selected for meditation. Then, whenever the selected word(s) are chanted, the meaning of the
entire sutra will fill our consciousness. This type of meditation is based on mantras and therefore,
sound assumes importance. There are said to be four types of sound depicted in Figure 4 (3). It is
suggested that that at the minimum, mantras should be chanted in Madyama, preferably near the
upper boundary of Pashyanti. With practice, this should be possible.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
112
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
Figure 4. Sounds and Mantras
For ready reference, the program may be summarized as follows:
1. Select the outcomes desirous of materialization.
2. Study the Patanjali’s yoga sutras, Tirumular’s Tirumantiram, or Durga Saptashati and
identify a reasonable number of sutras/mantras to include in the meditation program.
3. Internalize the meaning of these sutras/mantras so when the sutra/mantra is chanted, the
consciousness knows its meaning.
4. Select one or two operative words from each sutra/mantra which when chanted will cause the
associated meaning to be filled in the deepest recesses of our consciousness.
5. Select the chronology, power (see Figure 4), and duration of each sutra/mantra, and duration
of the program.
6. Select the physical exercises and breathing exercises to do for removing stresses and strains
to ready the body for meditation.
7. Practice the program for the duration of the program.
8. Evaluate the program efficacy; remember it may take some time whose magnitude cannot be
ascertained at this time before the intended outcomes are materialized. Six Sigma principles
need to be adhered to in all aspects of the program except during the meditative practice.
Rational thinking may be an obstacle to success during the actual practice of meditation.
9. Be sure to secure the approval of your healthcare professional and physician. Soft seating
such as mattresses needs to be in place; landing on hard surfaces could cause serious injury.
10. Remember, You Are Undertaking the Investigation entirely at Your Own Risk!
Results
The second author gathered a group of seven participants in Pune, India for the investigation.
They practiced their meditation program for nearly four months culminating in the final set of
sessions on January 25 – 27, 2014. The first author had come from the United States to Pune in
November 2013 for interactions with the participants. The first author shot a video of the session
and the screenshots of five participants lifting off of the ground to a varying degree are shown in
Figure 5.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
113
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
Of the seven participants, six had lifted off the ground on 25 - 26 January 2014 to a varying
degree ranging from a couple of inches to several feet. This is simply not possible unless the
intention of lifting of the ground had materialized. None of the participants remained still in the
air unlike my mother who was seen in a stationary state some six to nine inches from the ground
Figure 5. Five of the Participants Lifting from the Ground while in Meditation
by my older sister Vijaya Bhalerao in Pune when she was a teenager. Vijaya holds a B. A. from
the University of Poona. Her daughter, Poornima Talwalker of Mumbai who has a Master’s
degree in psychology and her son Sanjeev Bhalerao, an advertising executive in New Delhi with
an MBA and a degree in Law told me that they too had witnessed my mother in a levitated state
as young children. None of us know what mantras my mother was silently chanting but my
family believes that my mother had a pretty high S component. She died in 1997 at the age of 95
and for over seven decades she would complete tens of thousands of Japamala rounds on a daily
basis. The participants in this investigation on the other hand are decent folks but subject to
many more stresses and strains of daily life. It is a challenge to maintain a high S component
under such circumstances. These examples give us a tantalizing clue about the connection of the
S, R, T level of consciousness and the defect rates.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
114
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
The bioenergy of participants was measured with Korotkov’s GDV device (4, 19). The stress
levels, energy levels, and physical-emotional balance as well as chakra energies of participants
halfway into the program on 11/23/13 and at the conclusion of the program on 01/25/2014 are
shown in Table I and II. In Table I, a significant improvement in energy levels is evident. Stress
and balance before and after are similar. Table II shows a substantial increase in the energy of
chakras (average for all participants has increased from 4.82 to 6.1 while the standard deviation
has reduced somewhat from 0.51 to 0.49).
Table I. Bioenergy Data of Participants
Name
Stress
Starting Ending
3.38
3.24
3.34
3.34
2.91
2.96
2.26
2.81
2.49
2.80
2.75
2.32
2.22
2.25
SK
SS
SA
SG
RK
RS
AK
Energy, Joules
Starting
Ending
61.59
71.56
63.40
70.50
62.87
72.13
55.62
72.07
53.77
66.56
62.19
71.12
53.94
61.95
Balance, %
Starting Ending
96.75
99.46
95.52
97.55
98.96
99.62
98.29
98.99
97.92
96.74
96.16
95.16
96.29
97.61
Table II. Chakra Energy, Joules, Before and After
Chakra
SK-Start SK-End SS-Start SS-End SA-Start SA-End SG-Start SG-End RK-Start RK-End RS-Start RS-End AK-Start AK-End
Muladhara
Swadhishthana
Manipura
Anahata
Vishuddha
Ajna
Sahasrara
6.18
5.67
5.65
6.48
5.00
4.15
4.42
6.99
6.62
6.78
7.2
6.8
5.7
5.28
6.44
5.69
5.68
5.74
5.78
4.56
5.09
7.71
6.43
6.59
7.03
5.69
5.78
5.99
5.96
5.2
5.44
5.19
5.09
4.52
4.21
7.29
6.71
6.68
6.76
6.79
5.26
5.57
4.62
4.29
4.66
4.79
4.57
4.6
4.39
6.16
6.08
6.55
7.14
6.97
5.59
6.06
5.36
4.37
4.58
4.37
4.68
3.82
4.14
6.58
5.68
6.15
5.88
5.88
5.03
5.26
4.41
3.62
3.77
4.7
3.79
4.76
5.15
5.98
5.61
5.55
6.20
6.57
5.82
6.50
4.52
4.05
4.64
4.19
4.30
4.54
4.43
4.65
4.8
5.58
5.03
5.27
5.42
5.39
Average
5.36
6.48
5.57
6.46
5.09
6.44
4.56
6.36
4.47
5.78
4.31
6.03
4.38
5.16
We have presented two examples (change of pH and levitation) of materialization of intentions
by at least two groups. We believe that the evidence presented is very supportive of the
hypothesis of materialization of intentions. We hope this paper will contribute towards the
unfolding of a Copernican-like revolution which will have profound positive impact on
humanity.
The first author conducted interviews of the participants on January 25th at the concluding
session to learn of their experiences and their responses are summarized in Note 1. Readers may
find the comments on the link of this work to the previously mentioned S, R, T level of
consciousness in Note 2 interesting.
Acknowledgments: This paper is written with the implied blessings on my guru (first author’s), Guruji
Paranjothiyar (www.univrsalpeacefoundation.org). The authors also thank Mr. Nitin Chitre of Pune, B. E. (Gold
Medalist) College of Engineering, Pune and M. E., University of Birmingham, UK for the valuable explanation of
the sounds of Mantras leading to Figure 4. Sanjeev S. Aroskar holds a bachelor’s degree in Electronics and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
115
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
Computers from the Indian Institute of Technology Mumbai. Dr. S. N. Bhavsar holds a Ph. D. in linguistics
(Etymology of Brahmanas) from the University of Poona. Additionally, Dr. Bhavsar is a Sanskrit and Ayurvedic
scholar.
Note 1: Interview with Participants
The response of Dr. Rajiv Shelar, MBBS, MS (Orthopedics) in his own words:
I have experienced total happiness in my entire self. Usually, we experience happiness at the
level of the mind but the body doesn’t feel it or we have a bodily happy experience but the mind
doesn’t feel it. Now, the experience is in unison and I notice that my entire being is like a child
bubbling with joy. After completion of the program I felt that I am dancing like I used to dance
in my childhood. These are the changes in happiness, perception, understanding, exercise, and
fitness level.
One participant said, “My confidence level and positivity have improved. I felt like crying but not out of
sorrow and then I felt peace afterwards.” Another commented, “I realize improvement in myself, there is
peace in my family. My friends ask, what are you doing different?” A third comment was “My creativity
has increased.” Additionally, everyone reported feeling better.
Note 2: Some Comments on this Work, and S, R, T Level of Consciousness
Over the past few years the first author has published several papers on a scientific framework for internal
and external excellence for personal, organizational, national, and global transformation (4 – 14). Six
Sigma has been presented as the wherewithal for the excellence of the external while Maharishi’s ideas fit
in the scientific framework for the excellence of the internal which contains the wherewithal for raising
one’s level of consciousness. We have also shown that the excellence of the external and the excellence of
the internal are intricately linked. In the absence of internal excellence, Six Sigma programs will lead to
suboptimal results and vice-versa (6). Both components of excellence are essential for emerging as one’s
best and for world transformation.
In a recent article, the first author presented strong evidence of the link of internal excellence to
performance based on a very large sample running into millions (6). Condon, et al., and DeSteno
presented a case study showing how meditation directly leads to higher compassion (15). Profits at
compassionate companies are being reported to be much higher than that at others. During the November
2013 – February 2014 visit, the first author came across substantial evidence involving certain
communities in India running into tens of million revealing a strong link between intention, compassion,
internal excellence, and exemplary business performance. It is expected that the program outlined if
embraced will lead to exemplary business performance.
Finally, Maharishi’s group had conducted multitude of investigations successfully delivering the
intermediate results of levitation they call yogic flying based on their own method involving hundreds of
thousands
of
participants
(see
for
example
the
YouTube
video
at
http://www.youtube.com/watch?v=jlw8CxTkyxA). Among the followers of Maharishi are numerous
scientists such as physicist, John Hagelin, PhD, neurophysiologist Dr. R. Keith Wallace, Ph. D., and
neuroscientist, Tony Nader, MD, PhD, and some celebrities such as the Beatles, film maker David Lynch,
comedian Jerry Seinfeld, and others. Scientific papers on meditation have appeared in numerous
prestigious journals such as Science and well-known media publications such as the New York Times.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
116
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 103-116
Deshpande, P. B., Aroskar, S. A., Bhavsar, S. N. & Kulkarni, B. D., Mind Over Matter: Investigation of Materialization of Intentions
References
[1]
[2]
[3]
[4]
[5]
[6]
[7]
[8]
[9]
[10]
[11]
[12]
[13]
[14]
[15]
[16]
[17]
[18]
[19]
[20]
[21]
[22]
[23]
[24]
Belak, Tony and Curtin, J-R, Planned New U of L-Spalding Institute will Examine How
Compassion Can Boost Business Performance, The Lane Report, August 5, 2013.
Boyers, J., Why Empathy is the Force that Moves a Business Forward, Forbes, May 30, 2013.
Chitre, Nitin, Private Communication, Pune, 10 January 2014.
Deshpande, P. B., Can the excellence of the Internal be Measured, Journal of Consciousness
Exploration and Research, 4, 11, November 2013.
Deshpande, P. B., Scientific Framework for Individual, Organizational, National, and Global
Transformation, 17th Annual Conference on Science, Information, and Consciousness, St.
Petersburg, Russia, July 6 – 8, 2013.
Deshpande, P. B., Compassion, Performance, and Programs of Excellence, Journal of
Consciousness Exploration and Research, 4, 4, April 2013.
Deshpande, P. B., Science of Compassion, Journal of Consciousness Exploration and Research, 3,
9, October 2012.
Deshpande, P. B. and Kulkarni, B. D., The Brahma Uncertainty Principle, Journal of
Consciousness Exploration and Research, 3, 2, February 2012.
Deshpande, P. B., Science of Enlightenment, Journal of Consciousness Exploration and Research,
3, 2, February 2012.
Deshpande, P. B., and Kulkarni, B. D., and Aroskar S. S., and Bhavsar S. N., Levitation during
Meditation: A Scientific Investigation, Journal of Consciousness Exploration and Research, 2, 4,
June 2011.
http://2012daily.com/?q=node/17 (Pradeep B. Deshpande’s Message for World Transformation,
September 30, 2011).
Deshpande, P. B., Six Sigma for Karma Capitalism, Six Sigma and Advanced Controls, Inc., 2011.
Deshpande, P. B., A Small Step for Man: Zero to Infinity with Six Sigma, Six Sigma and
Advanced Controls Inc., 2008.
Deshpande, P. B. and Christopher, P. M., On The Cyclical Nature of Excellence, reflections, Vol.
1, No. 1, 1993.
DeSteno, David, The Morality of Meditation, OpEd Column, NY Times, July 5, 2013 (Condon,
Paul, et al., J Psychological Science, 21 August 2013). This paper shows how meditation directly
leads to more compassion
Fryer, B., The Rise of Compassionate Management (Finally), Harvard Business School Blog
Network, September 18, 2013.
George Bill, Compassion makes you a Better Leader, Harvard Professor George’s Blog, 2013.
Govindan, Marshall, Kriya Yoga Sutras of Patanjali and the Siddhas, Babaji’s Kriya Yoga Order of
Acharyas Trust, Bangalore, India.
Korotkov K.G., Energy fields Eletrophotonic analysis in humans and nature, 2012. 240 p. e-book:
Amazon.com.
Mannikar, T. G., Samkhyakarika of Isvarakrsna, Oriental Book Agency, Poona, 2nd Printing 1972.
Thakur, Nanda and Thakur Jitendranath, Sarth Shridurgasaptashati 5th Ed., Dharmic Publication
House, Mumbai 2013.
Tiller, W. A., Psychoenergetic Science: Second Copernican Revolution, www.amazon.com, 2007.
Tiller, W. A. and Dibble, W. E., White Paper II: Steps for Moving Psychoenergetic Science into
the Hands of General Public Researchers, 2009 (www.tiller.org).
Wallace, R. K., Physiological Effects of Transcendental Meditation, Science, Vol. 167, No. 3926,
1970.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
MATHEMATICAL MODELS OF CONSCIOUSNESS
JOHANNES KLEINER†
arXiv:1907.03223v2 [q-bio.NC] 20 Apr 2020
†
Munich Center for Mathematical Philosophy
Ludwig Maximilian University of Munich
Abstract. In recent years, promising mathematical models have been suggested
which aim to describe conscious experience and its relation to the physical domain.
Whereas the axioms and metaphysical ideas of these theories have been carefully
motivated, their mathematical formalism has not. In this article we aim to remedy
this situation. We give an account of what warrants mathematical representation of
phenomenal experience, derive a general mathematical framework which takes into
account consciousness’ epistemic context and study which mathematical structures
some of the key characteristics of conscious experience imply, showing precisely where
mathematical approaches allow to go beyond what the standard methodology can
do. The result is a general mathematical framework for models of consciousness that
can be employed in the theory-building process.
Keywords: Models of Consciousness, Experience Space, Phenomenal Space, Mathematical
Approaches in Consciousness Science, Mathematical Phenomenology, Theories of Consciousness,
Phenomenal Consciousness, Epistemic Asymmetry, Non-collatability
Contents
1. Introduction
2. Summary of Results
3. Basic Definitions
3.1. Conscious Experience and Qualia
3.2. Formal Representation of Experience
3.3. References to Qualia
3.4. A Phenomenological Grounding of the Scientific Study of Consciousness
3.5. Examples
4. Explanatory Gap
5. The Mathematical Structure of Models of Consciousness
5.1. Mathematical Structure of Scientific Theories
5.2. Models of Consciousness
5.3. Notation
6. Taking Characteristic Features of Conscious Experience into account
6.1. Non-Collatability implies Symmetry
6.2. The Mathematical Structure of Models of Consciousness
6.3. Comparison with Direct Reference
7. Closure of the Physical
8. Examples
8.1. Integrated Information Theory
8.2. Global Neuronal Workspace Theory
1
2
5
10
10
13
16
19
19
26
27
27
29
30
31
31
33
35
37
38
38
41
2
J. KLEINER
8.3. Conscious Agent Networks
8.4. Expected Float Entropy Minimisation
9. Conclusion & Outlook
Appendix A. Chalmers’ Grounding of the Scientific Study of Consciousness
Appendix B. Conceptual Problems of Chalmers’ Grounding
References
43
45
48
49
51
58
1. Introduction
Conscious experience and its relation to the physical domain has been studied by
philosophers, theologians and scientists over many centuries [Faw14]. In the previous
three decades, there has been a resurgence of scientific investigations. Groundbreaking
developments in neuroscience, cognitive psychology and analytic philosophy lead to the
emergence of a dedicated science of cosnciousness, whose aim is to develop a scientific
account of conscious experience and its relation to the physical domain (e.g. brain
processes).
A model of consciousness is a hypothetical theory about how conscious experience
and the physical domain relate [Set07]. Examples include Global Workspace Theories [DKC98, Baa05], Multiple Draft Theory [Den93], Higher Order Thought Theories [Car16] or Integrated Information Theory [OAT14], among many others. Models
of consciousness complement metaphysical theories of consciousness, such as the various forms of functionalism, identity theories, interactive dualisms or neutral monisms.
These theories are concerned primarily with ontological questions and address the
general type of relation between consciousness and the physical domain.
The rising importance of mathematics in consciousness studies. In recent
years, many models of consciousness have been proposed which are mathematical
in nature. Primary examples in neuroscience are the recent versions of Integrated
Information Theory [OAT14, MMA+ 18, HT19], which aim to determine the quality and quantity of a system’s conscious experience using a complex mathematical
algorithm [KT20, TK20], or Predictive Processing Theory [MW], which can be interpreted as specifying the content of conscious experience of a system using an advanced minimization principle [DD20]. But promising models have been proposed by
other disciplines as well, including philosophy [CM21], physics [Ken18, Ken19], mathematics [Pen94, KR15a, Mas16] or psychology [HP14], all based on various different
metaphysical ideas about consciousness.
These developments point at an increasing relevance of mathematical tools and
methods in the scientific study of consciousness, much like in other scientific disciplines
throughout the last century, with promising new insights on the horizon. However,
mathematization on its own does not have unique scientific merit. Valuable progress
can only be made if the mathematization is based on and integrates previous theoretical, empirical and conceptual work.
What makes consciousness a problem. Consciousness is a phenomenon unlike
any other studied by natural science. It is unique as an object of investigation both in
its characteristic features and in its epistemic context. This is true in particular for its
most relevant and mysterious connotation, which much of the science of consciousness
and also this article is concerned with, namely phenomenal consciousness. Phenomenal
MATHEMATICAL MODELS OF CONSCIOUSNESS
3
consciousness refers to the way in which the world appears to us, i.e. the way in
which we experience the world. This can roughly be paraphrased as “pure subjective
experience” [Met95b].
Much of philosophy of mind is concerned with analysing in detail just what the
characteristic features of phenomenal consciousness are and how precisely they relate
to metaphysical ideas and efforts of scientific investigation. The arguably most crucial
features attributed to phenomenal experience are its essential subjective nature, which
sometimes is taken to mean that phenomenal consciousness embodies a particular point
of view [Nag74], but also that some of its parts or properties seem ineffable [Lew29],
private, or unavailable to cognitive and linguistic processing or communication [Met07].
Basic properties or simple constituents of phenomenal consciousness are called qualia,
but this term is being used with many different connotations to date. Qualia are
variously claimed to be intrinsic and non-relational or to have a qualitative and nonquantifiable nature. Phenomenal consciousness is also claimed to be directly or immediately apprehensible, to be transparent in the sense that it appears as if we are
in direct contact with the content of our conscious experience or to be homogeneous
[Met95b]. Various different connotations of all of these notions exist, and different
philosophers endorse various combinations thereof.
Complementing these characteristic features of consciousness is its unique epistemic
context, which comes about from the fact that phenomenal consciousness per se is
accessible only to the experiencing system itself. Thus in any scientific approach there
are two fundamentally different methodological approaches that allow one to gather
information, a first person perspective and a third person perspective. This is referred
to as the epistemic asymmetry of consciousness [Met95a].
The need for a mathematical foundation. Any scientific analysis which strives
to address and explain phenomenal consciousness needs to take these features of consciousness into account, at the very least as providing epistemic restrictions which
constrain and shape the empirical access to conscious experience. Failing to do so at
all amounts to ignoring what makes consciousness a problem in the first place, which
no serious scientific investigation can afford.
To date, almost none of the existing formal models take any of these properties
of consciousness into account. While mathematical structures are quickly associated
with terms like ‘qualia’, ‘subjective experience’ or ‘act of consciousness’, contemporary
models fall short of actually considering the conceptual meaning of these philosophical
concepts.
What is necessary to mend this is a thorough foundation of mathematical models of
consciousness that analyses which implications the various characteristics of conscious
experience have on the mathematical structure of these models and which provides
a precise account of how the concepts developed in philosophy of mind relate to the
mathematical structure of models of consciousness.
The goal of the work presented in this article is to provide this foundation for the case
of ineffability, privateness and cognitive, linguistic and communicative unavailability.
A framework for formulating models of consciousness. The result of this work
is a general mathematical framework in which models of consciousness can be formulated. Much like Lagrangian mechanics in theoretical physics, it does not provide any
particular law or equation which constitutes a model of consciousness, but rather a
4
J. KLEINER
general formal machinery. What this machinery achieves is to properly take into account that conscious experience has ineffable, private or inaccessible aspects and that
it exhibits an epistemic asymmetry. This framework provides a first mathematical
foundation for models of consciousness, and needs to be expanded in future work to
take other key characteristics into account.
Crucially, the framework is independent of whether one considers any of these characteristic features to be ontological in origin or simply due to a system’s particular
design or cognitive functions [Den93]. What matters, from the perspective of this
framework, are only the epistemic restrictions that arise from these features of conscious experience, i.e. that access to some parts of conscious experience is limited by
consciousness’ subjective nature and by ineffability, privateness and inaccessibility in
any type of experimental situation.
Thus this framework can be dubbed operational. Much like Quantum Theory in its
conventional formulation, it takes as its starting point the prototypical experimental
situation in which a theory (of consciousness) is being tested, used or inferred, and
then adds the particular epistemic context of consciousness, so as to arrive at a general
operational description. Great care has been taken to keep the mathematical structure
of this formalism as general as possible, and to provide operational justifications of all
essential definitions, so as to ensure that the framework is compatible with all types
of mathematical structure one would want to use in modelling consciousness, including category theory [TK20, TTS16], information theory [Ton08] or complex system
approaches [Atm16], among many others.
An axiomatic conceptual underpinning. In order to translate any concept into
formalism, the concept itself needs to be rigorously defined. To date, neither the term
qualia, nor the concepts of ineffability, privateness and inaccessibility are defined in a
rigorous enough manner to warrant thorough formalization.
Thus in order to achieve our goal, it was necessary to represent the underlying
philosophical concepts in an axiomatic form that is suitable for formalization. Since
this whole programme is operational in nature, it suffices in fact to provide an axiomatic definition of the operational consequences of these characteristic features of
consciousness.
For the case of ineffability, privateness and inaccessibility this is possible at once by
introducing the concept of non-collatability: A part, property or feature of conscious
experience is non-collatable if there do not exist any reasonable means to identify
this part, property or feature over several experiencing subjects in an experimental
trail. Non-collatability is entailed by ineffability, privateness and inaccessibility and
arguably also by consciousness’ subjective nature. As shown in detail throughout this
work, it is precisely non-collatability which generates much of the epistemic difficulty
in investigating conscious experience, and which has substantial consequences for any
empirically adequate model of consciousness.
The conceptual definitions we have derived in order to found the mathematical
structure of models of consciousness give rise to an axiomatic grounding of the scientific study of consciousness that is an alternative to and further development of the
grounding that derives from David Chalmers’ work. While our grounding was primarily intended to constitute an intermediate construction which links philosophical
concepts and mathematical formalism, it may also have some conceptual worth in its
MATHEMATICAL MODELS OF CONSCIOUSNESS
5
own, providing an interim way to conceive of the task and methodology of the scientific
study of consciousness from a more formal perspective.
A new way of consciousness science. In summary, this article can be understood
as taking seriously a new way of doing consciousness science that has been pioneered
in eminent works such as [OAT14], [HP14] or [Res18]. Its central idea is to represent
phenomenal consciousness in terms mathematical spaces, and to use these spaces to
build theories of how conscious experience might relate to the physical domain. This
facilitates a much richer and refined way of addressing conscious experience and offers promising tools to resolve of some of the key issues that permeate contemporary
consciousness studies.
What this article adds to this new methodology is the requirement that the essential
features of conscious experience, studied in detail by philosophy of mind, are taken
into account when building this mathematical representation. Doing so requires an
account of how precisely mathematical spaces can be grounded in the phenomenology of experience and of which mathematical implication consciousness’ fundamental
epistemological context has. Answers to all of these questions are proposed here. The
hope is that these considerations might provide a useful basis for further development
of formal models of consciousness.
The structure of this article. This article is structured as follows. In order to make
it accessible to readers without formal background, we first summarize the results in
Section 2, keeping mathematical details to a minimum. In this section, we also explain
in detail the rationale and motivation of this work.
All subsequent sections aim for a concise presentation of definitions, explanations
and examples. In Section 3, we give the conceptual definitions on which our framework rests, making as few assumptions as necessary. This gives rise to an axiomatic
grounding of the scientific study of consciousness. In Section 4, we show that there
is an explanatory gap between qualia as defined here and natural science. Section 5
is devoted to deriving a general mathematical framework for formal models of consciousness, making use of a minimal set of ingredients of any formal theory and of
consciousness’ epistemic asymmetry. In Section 6, finally, we show how consciousness’
characteristic features can be taken into account. We conclude this paper with a brief
remark on a metaphysical question in Section 7 and various examples in Section 8.
In Appendix A, we review the grounding of the scientific study of consciousness that
derives from David Chalmers’ work in [Cha96, Cha10], emphasizing the logical relations
among its parts. In Appendix B, we discuss problems that arise if one attempts to
apply this grounding in a model-building process.
2. Summary of Results
Any research activity directed at conscious experience presupposes a conception
of the phenomenon that is to be studied and a conception of a methodology that is
suitable to do so. We call this a grounding of the scientific study of consciousness.
Definition 2.1. A grounding of the scientific study of consciousness contains at least
- an explicit definition of what is to be studied.
- an explicit outline of the methodology.1
1Here “methodology” refers to “a collection of methods, practices, procedures and rules used by
those who work in some field” [Wik18b], “a system of methods used in a particular area of study or
6
J. KLEINER
Much of the research devoted to consciousness in the previous two decades has been
guided by a grounding that derives from David Chalmers’ work [Cha96]. This grounding has played a pivotal role in the creation and consolidation of the field. However,
it also exhibits several severe problems when being applied (Appendix B). In the first
part of this paper, we introduce an alternative to Chalmers’ grounding of the scientific
study of consciousness. This alternative is built on a thoroughly operational perspective,
which means that we define all notions relative to prototypical experimental investigations.
Any experimental situation devoted to study conscious experience presupposes a
preliminary choice of organisms that are considered to be conscious, and whose conscious experience and physical state is probed during the experiment in order to gain
information about how consciousness relates to the physical domain. We denote any
such class of organisms by C and call them experiencing subjects. Taking the operational perspective seriously, we consider C to be a primitive notion. While it may
be guided by theoretical insights and changed over the course of time, at any particular time a class C provides the basis for both inference and tests of theories about
consciousness.
Having chosen our primitive notion, we can define experience relative to it. A
promising choice is to use somewhat phenomenological terminology in defining the term
conscious experience, referring to the totality of how experience ‘reveals itself’ to an
experiencing subject, how the experiencing subject finds itself experiencing, or how the
‘the world’ appears to it. While this is what we have in mind, we have opted for more
approachable terminology and define the term conscious experience to denote totality
of impressions, feelings, thoughts, perceptions, etc. which an experiencing subject
lives through at a particular instant of time (Definition 3.1). Experience so defined
has various different aspects, where we define the term ‘aspect’ to be a placeholder for
any conception like ‘part’, ‘property’ or ‘element of’ (Definition 3.2).
The key notion on which our grounding is built is that of non-collatability. An
aspect of experience is non-collatable if there is no reasonable method to identify
whether two or more experiencing subjects in an experiment experience this very
aspect of experience. In other words, if the identity of this aspect over several different
experiencing subjects in C cannot be determined (Definition 3.5).
The distinction between collatable and non-collatable aspects of experience is what
replaces the distinction between phenomenological and psychological concepts of mind
in [Cha96]. Whereas the latter distinction is defined in terms causal roles and spatiotemporal structure (cf. Appendix A), our distinction is defined axiomatically in
terms of phenomenological or operational notions.
What is crucial is that non-collatability is implied by various essential characteristic
features of conscious experience. E.g., any aspect which appears to be ineffable (i.e.
which is experienced as ineffable) is also non-collatable in the above sense. The same is
true for aspects of experience which are experienced as private or which are not available to cognitive or linguistic processing. All of these characteristic features destroy the
possibility to identify an aspect under consideration over several experiencing subjects.
Non-collatability is a necessary operational consequence of all of these characteristic
features.
activity” [Oxf18]. In particular, the methodology includes the specification of what constitutes an
experiment. The term ‘grounding’ is one of several translations of the German word “Grundlegung”.
MATHEMATICAL MODELS OF CONSCIOUSNESS
7
The same may be true of subjectivity of conscious experience, if taken to warrant the
claim that “there are facts that do not consist in the truth of propositions expressible
in a human language” [Nag74, p. 441]. In fact, one of the main claims in [Nag74] is that
there is at present no conception that allows one to establish the identity of a ‘what it
is like’ aspect of experience with a physical state. Our starting point, non-collatability,
is closely related to this claim and may even be implied by it in reasonable cases.
Building on non-collatability, we define qualia as follows.2
Definition 3.9 We define the term qualia to refer to all non-collatable aspects of
experience of an experiencing subject within the class C.
This definition is warranted since it includes the paradigmatic examples of what
qualia are claimed to be (Example 3.10), as well as aspects of experience referenced
by the Nagelian ‘what it is like’ conception (Example 3.11). It is furthermore axiomatic and replaces the concept of phenomenal consciousness as defined in Chalmers’
grounding.3
The aspects of experience which satisfy Definition 3.9 are of special interest because
the non-collatability induces a fundamental difficulty in any scientific approach: It
implies that these aspects cannot be referenced intersubjectively, which in turn implies
that they cannot be referenced in a scientific model or empirical analysis. There is
a fundamental explanatory gap (Section 4). The goal of this paper, when put in
these terms, is to develop a mathematical framework that allows us to address both
collatable and non-collatable aspects of experience, providing a formal methodology
suitable to address this explanatory gap.
Next, we make use of the central idea that underlies many contemporary mathematical models of consciousness: To represent phenomenal consciousness as a mathematical space. In order to provide an accurate method to do so, we make use of two
phenomenological axioms.
First, we make use of the fact that both collatable and non-collatable aspects of
experience can be recognized to a certain extent (Phenomenological Axiom 3.12). Another way to say this is that aspects of experience may be experienced as identical.
Following our operational perspective, this warrants the introduction of labels for both
qualia and collatable aspects of experience, i.e. names relative to an experiencing
subject.
Second, we make use of the fact that there are collatable relations between aspects
of experience (Phenomenological Axiom 3.14). This might be considered obvious in
the case of collatable aspects of experience. With respect to non-collatable aspects of
experience, it corresponds to the observation that “structural features of perception
might be more accessible to objective description, even though something would be
left out” [Nag74, p. 449], or that “even if experiences are in some sense ‘ineffable,’
relations between experiences are not; we have no trouble discussing these relations,
whether they be relations of similarity and difference, geometric relations, relations of
intensity, and so on. As Schlick [Sch38] pointed out, the form of experience seems to be
2 Note that the numbering of this and all following definitions is chosen according to the main body
of this article.
3We remark that for this and all other definitions, it does not matter whether non-collatability or
any of the characteristic features which imply it are considered to be fundamental or merely the result
of a system’s architecture. All that matters is that experience appears as such.
8
J. KLEINER
straightforwardly communicable, even if the content (intrinsic quality) is not” [Cha96,
p. 224].
Together, these two phenomenological observations allow us to define a mathematical space that represents conscious experience, which we call experience space E. The
elements of this space are not experiences themselves but labels that an experiencing
subject may give for his/her aspects of experience, and the mathematical structure
on this set of labels is induced by the collatable relations between aspects of experience. To conceive of E as space of labels, rather than as a space of experiences, is
of advantage because it prevents from the very beginning any implicit assumption of
well-defined reference to aspects of experience. In contrast, working with a space whose
elements are intended to express experiences themselves requires the introduction of
a map which describes how these experiences can be inferred from reports (labels),
e.g. as in [KH20]. The details of our introduction of experience space are explained in
Section 3.2, and various examples are given in Section 3.5.
We remark that whereas our constructions are guided by conceiving of labels as
something that an experiencing subject can express, which requires C to comprise
humans, this is not necessary. This is to because the various principles that are used
in experiments to date to infer the state of consciousness of some subject (e.g. button
presses or behavioural indicators) are, in our terminology, in fact means to infer labels
of aspects of experience. Whether a label is a recorded word or some other type of
report, such as a particular movement, does not matter for our purposes. What is
crucial about the terminology of labels is that one avoids from the very beginning any
implicit assumption that there is an empirically well-defined method to refer to qualia
of an experiencing subject.
Non-collatability implies limitations on how aspects of experience can be referenced
in a theory or empirical investigation. Whereas labels of collatable aspects of experience can be synchronized over all experiencing subjects in the class C (because
collatability holds iff there exist means to identify), labels of qualia cannot. In virtue
of non-collatability, the definition of qualia implies that any label which one experiencing subject uses to denote a quale may denote another quale in a different experiencing
subject. Any scientific investigation which aims to address qualia needs to take the
resulting ambiguity into account. Ignoring it will lead to errors, such as the study of
the wrong “information pathway” or confounding neural correlates of external signals
with neural correlates of qualia.
In the next step of our construction, we quantify this ambiguity precisely. To this
end, we make use of the mathematical representation E of experience constructed
previously. As we explained in detail in Section 3.3, the conceptual and mathematical
definitions imply that the ambiguity of any reference to aspects of experience can be
stated concisely in terms of the automorphism group Aut(E) of E, i.e. the group of
all transformations of E which change labels in such a way that the mathematical
structure of E is left invariant.
We find that any statement about conscious experience that uses an individual
label e could, in light of non-collatability, have equally well be formulated in terms of
any label e′ that is part of a subset [e] of labels. This subset [e] is called the equivalence
class of the label e with respect to the automorphism group Aut(E).
The crucial insight here is that these equivalence classes describe what is intersubjectively accessible or, in our terminology, empirically well-defined. Taken together,
MATHEMATICAL MODELS OF CONSCIOUSNESS
9
these equivalence classes describe what is amenable to the usual scientific methodology. Depending on the mathematical structure of E, this may well include some of
the non-collatable aspects of experience.
This second step in our constructions may be sufficient for many investigations once
experimental tools become advanced enough to proceed to the study of individual
aspects of experience. It enables experimentalists to use structural features of phenomenal experience, as represented in E, to push the boundary of ineffability and all
the other characteristic features that imply non-collatability back a little bit. However,
as long as there are equivalence classes [e] which contain more than one label, there
are questions that evade the reach of the standard scientific methodology: Why the
subject had one of the corresponding experience rather than the other. Even though
this cannot be expressed by intersubjective means, there is a fact to the matter for
the experiencing subject, and hence a priori an open scientific question. The goal of
the remaining part of the article is to develop tools that allow us to address this open
question.
To develop these tools, we have to go beyond the mathematical representation of
experience, and in fact consider formal hypotheses about how conscious experience
relates to the physical domain, i.e. formal models of consciousness. In order to remain
as general as possible, as a first step in answering this question, we ask what the most
general mathematical structure is that a model of consciousness needs to address.
In order to answer this question, we first give an account of the minimally sufficient
formal structure of any scientific theory (Section 5.1). A theory needs to specify
some dynamical variables d that describe what the theory intends to address, may
contain some formal background structure, needs to have a parameter such as time
that facilitates description of variations of the dynamical variables and, finally, needs
to contain some laws that pick out some variations of d from all possible variations.
In order to further fix the dynamical variables d, we make use of the epistemic
asymmetry of conscious experience (Section 5.2). The epistemic asymmetry states
that there are two fundamentally different ways of gathering knowledge about conscious experience, the first-person perspective and the third-person perspective. Thus
there are two epistemically different notions of state in any experimental situation,
one that corresponds to first-person access, and one that corresponds to third-person
access. While any metaphysical theory of consciousness can ignore one of these states,
a scientific model of consciousness cannot. The difference between a coherent idea and
a scientific model of consciousness is precisely that the latter addresses both types of
states, while the former need not.
Since the states that are accessible in the third-person perspective are in fact physical
states (neural states, brain states, or similar) and the states that are accessible in the
first-person perspective are aspects of experience (with ‘aspect’ suitably defined, cf.
above), this implies that the dynamical variables of a formal model of consciousness
are in fact a subset of
d=E×P ,
where E denotes the mathematical representation of conscious experience we have
introduced above and where P denotes the state space of some physical theory TP .
Combining the above gives a general framework in which models of consciousness
(Definition 5.3) can be formulated. It provides a reference to which models of consciousness need to refer in light of consciousness’ epistemic context, independently
10
J. KLEINER
of how they are primarily defined and independently of which ontological ideas they
express.
This general framework finally puts us into a position to investigate the implications of non-collatability in Section 6. First, in Section 6.1, we prove that in light of
non-collatability, models of consciousness are only well-defined if they carry a particular symmetry. This is comparable to physical theories. Much like general relativity
carries a particular symmetry that ensures that the theory is well-defined with respect to changes of coordinates, our results show that models of consciousness need
to carry a particular symmetry that ensures that they are well-defined with respect
to changes of labels. The changes of labels in question are precisely those transformation which keep the equivalence classes [e] introduced above constant, but transform
individual members of these equivalence classes. The corresponding symmetry group
is the automorphism group Aut(E) introduced above.
What is crucial in our results of Section 6.1 is that the symmetry required to exist is
not fixed uniquely. There is a freedom in its form which depends on the laws of a model
of consciousness. This freedom describes how the transformations of labels relate to
transformations of physical states. Sections 6.2 and 6.3 are devoted to proving that
this remaining freedom is what allows formal models of consciousness to go beyond
what the standard methodology can do.
In a nutshell, this is so because the standard methodology can only utilize intersubjectively well-defined references. Mathematically, this means that the standard
methodology can only reference aspects of experience once it has imposed the group
Aut(E) in order to construct equivalence classes [e]. Formal models of consciousness,
on the other hand, allow one to reverse this order. They allow one to relate individual
elements of E and P prior to imposing the symmetry which ensures well-definedness.
Since all our arguments, proofs and derivations hold true also in the limiting cases
where all aspects of experience are either collatable or non-collatable, we summarize
all insights in a concise definition of what a model of consciousness is (Definition 6.4).
This is the main result of our project.
“Many scientific discoveries have been delayed over the
centuries for the lack of a mathematical language
that can amplify ideas and let scientists
communicate results.” [Pea09, p. 427]
3. Basic Definitions
In this section, we provide the basic definitions that underlie our constructions. In
Section 3.1, we specify the notion of experience we consider, introduce some fundamental terminology and give a definition of qualia in these terms. Subsequently, in
Section 3.2, we discuss the mathematical representation of experience. In Section 3.3,
we explain the implications of the defining characteristic of qualia for any reference to
consciousness in an experiment or theory. As mentioned above, altogether this can be
taken to provide a grounding of the scientific study of consciousness, and Section 3.4
is devoted to summarize the resulting picture. In Section 3.5, finally, we give several
examples for the mathematical structure introduced in Sections 3.2 and 3.3.
3.1. Conscious Experience and Qualia. The starting point of every scientific activity related to consciousness is a preliminary choice of a class C of experiencing
subjects that are available for experimental investigations and which are targeted by
MATHEMATICAL MODELS OF CONSCIOUSNESS
11
theoretical models. The object of investigation of any empirical study, and what informs any model-building process, is experience of these experiencing subjects in the
following sense.
Definition 3.1. We use the term ‘conscious experience’ (‘experience’ for short) to
denote the totality of impressions, feelings, thoughts, perceptions, etc. which an experiencing subject lives through at a particular instant of time.4
The general idea underlying any conception of the scientific study of consciousness is
to study experience and its relation to the physical domain by scientific means. Mostly,
some part or feature of experience is under consideration. In order to emphasise that
this part or feature may not be strictly separable from other parts of features, we use
the term ‘aspects of experience’:
Definition 3.2. Aspects of experience denote specific or general features, parts, properties or elements of a particular experience or of a set of experiences.
According to this definition, ‘aspect’ is thus merely a placeholder for ‘feature’, ‘part’,
‘property’ or ‘element of’. Which of these notions is relevant is part of the specification
of a model of consciousness.
Example 3.3. Aspects of experience range from individual visual, auditory or tactile experiences to general characteristics, such as the experience of a first person perspective, the unity
of the conscious scene [Set07], or the structure and composition of experience [OAT14].
♦
A priori, every experiencing subject only has access to his/her own experience. However, systematic investigations of which aspects of experience are invariant over a large
class of experiencing subjects are possible and have been carried out as part of the
philosophical discipline of phenomenology.
Definition 3.4. A phenomenological axiom is a statement about aspects of experience
which holds for all experiencing subjects in a class C.5
Phenomenological axioms serve as a starting point for any investigation in the scientific study of consciousness. In empirical studies, they are what can be correlated with
physical states, e.g. to construct neural correlates of consciousness. When building
models of consciousness, they are what informs the choice of mathematical structure.
In simple terms, phenomenological axioms are statements about how experiencing subjects find themselves experiencing, or how ‘the world’ appears to them. One could also
say that they express invariant facts of ‘what experience is like’ or of how experience
‘reveals itself’.
4No special focus on subjectivity is intended when using the term ‘experiencing subject’. Alterna-
tively, one could use the term ‘experiencer’. We also remark that the meaning of ‘instant’ is to be fixed
during the model-building process. It could refer to physical just as well as to experiential instants of
time.
5The restriction to a class C of experiencing subjects is necessary because a phenomenological
analysis of invariants of experience is always restricted to experiencing subjects which are similar in
some respects: “[O]ne person can know or say of another what the quality of the other’s experience is.
[However, this] ascription of experience is possible only for someone sufficiently similar to the object of
ascription to be able to adopt his point of view” [Nag74, p. 442]. However, the choice of class C is not
a constraint for models of consciousness, but rather a starting point, i.e. a preliminary choice which
informs the model-building process. Models may eventually allow one to determine which organisms
experience. We note also that the name ‘phenomenological axiom’ is a tribute to phenomenology
rather than an attempt to condense the phenomenological method into a simple definition.
12
J. KLEINER
Next, we make use of three basic phenomenological axioms in order to examine
in more detail which methodology may be used to study aspects of experience and
their relation to the physical domain. In preparation, we define the concept of noncollatability.
Definition 3.5. An aspect of experience is non-collatable iff there does not exist a
reasonable method to establish its identity over different experiencing subjects in the
class C.6
Non-collatability of an aspect of experience can be determined operationally in any
experimental situation. Whenever there is no reasonable method to identify whether
two experiencing subjects in an experiment experience the same aspect of experience,
the aspect in question is non-collatable. However, the concept can also be applied in
a more fundamental context, as part of a phenomenological axiom about how subjects
experience the world. Several examples are given below.
Phenomenological Axiom 3.6. Aspects of experience can be divided into two
classes:
a) Aspects of experience which are non-collatable.
b) Aspects of experience which are collatable.
The former class includes aspects of experience which are experienced as ineffable [Lew29], private, or found to be cognitively, linguistically and communicatively
inaccessible [Met07]. But they also include those which are referred to as having a
subjective character [Nag74, p. 437] or connected to a particular point of view [Nag74,
p. 441]. Non-collatability is implied by, and hence a necessary condition of, all of these
characteristic features of experience. The latter class include those aspects which are
experienced as accessible also from other points of view [Nag74, p. 443] or as having
an objective nature [Nag74, p. 443].7
Example 3.7. Consider, as a first example, experiences of awe. Subjects may report that
they have an experience of awe, and even give labels to various different such experiences, but
there is, at present, no methodological procedure to establish whether any two experiences of
awe of two different subjects are the same or not.
Some [Chu81, Den93] may hold that advanced neuroscientific theories may provide means
to collate the experiences of awe eventually. However, as we will see below, collatability is a
prerequisite of any theory that addresses specific aspects of conscious experience. If an aspect
of experience is non-collatable, no theory can be empirically inferred or tested that addresses
this aspect of experience.
♦
Example 3.8. Similarly, there is at present no possibility to meaningfully ask the question
of whether colour experiences of two experiencing subjects are the same or different. This
simple but important fact is pointed at by the plain question of how two experiencing subjects
6 I.e., an aspect experienced by subject S is non-collatable iff there is a different experiencing
1
subject S2 such that there is no reasonable method to determine which aspect e′ of S2 the aspect e
of S1 is identical with. Put yet in different terms, this is the case if there is no mapping from e to the
aspects of experiences of other experiencing subjects that can reasonably be interpreted as establishing
identity of aspects.
7
When being presented with Phenomenological Axiom 3.6, scientists usually tend to think about
how this can be derived from a theory of language. In our opinion, the more important task is to
ground the underlying distinction in a thorough phenomenological analysis. We also remark that
all formal constructions in this article are compatible with either of the classes in Phenomenological
Axiom 3.6 being empty, even though this is most likely not the case.
MATHEMATICAL MODELS OF CONSCIOUSNESS
13
might come to conclude that the experience of colour which they have if they look at, e.g.,
the clear sky is the same. They may ensure that they use the same reference (‘blue’) for the
experience, that they see the same wavelength and they might even be able to conclude that
similar neuronal assemblies are active in both of their brains while having the experience in
question. However, none of this is a priori related to the color aspects of their experiences
(‘what it is like to see blue’).
Put differently, there is no reasonable way to assign truth values to statements of the
form ‘my colour experience e1 is equal to your colour experience e2 ’, equality is not a welldefined concept when referencing to experiences of two different experiencing subjects. Thus
colour experiences are non-collatable aspects of experience in the sense of Phenomenological
Axiom 3.6.
This non-collatability has consequences for any scientific account of colour experience. E.g.,
any hypothesis that a particular neural activity occurs whenever a subject is experiencing a
colour ‘green’ is not well-defined, simply because there is no intersubjectively meaningful reference to ‘green’; the colour experience one subject is having when when presented a 510nm
light source may be very different from the colour experience another subject is having when
presented the same light source. In other words, any intersubjective reference to colour experiences carries a certain ambiguity, which has to be taken into account when constructing
models or designing experiments related to colour experience.
♦
The main point of this paper, argued for in detail below, is that non-collatable aspects of experience cannot be addressed by the usual scientific methodology. Since the
term ‘qualia’ is generally used to denote what is considered as essential in a particular
analysis of experience, we introduce the following abbreviation.
Definition 3.9. We define the term qualia to refer to all non-collatable aspects of
experience of an experiencing subject within the class C.
Example 3.10. According to Example 3.8, colour experiences satisfy the condition of Definition 3.9. Thus colour experiences are qualia.8
♦
Example 3.11. Example 3.10 is a special case of the aspects of experience referenced by
Thomas Nagel in [Nag74] when introducing his famous notion of ‘What is it like to be ... ?’:
“[F]undamentally an organism has conscious mental states if and only if there
is something that it is like to be that organism – something it is like for that
organism. We may call this the subjective character of experience.” (p. 436)
Nagel also uses the term “how it is for the subject himself ” (p. 440) to point to these aspects
of experience. Though [Nag74] does not make the distinction of Phenomenological Axiom 3.6
central to his line of reasoning, one can find hints toward this distinction in [Nag74]: E.g., he
claims that “we do not possess the vocabulary to describe [what it is like to be us] adequately” (p.
440), there are “facts that do not consist in the truth of propositions expressible in a human
language.” (p. 441)
♦
3.2. Formal Representation of Experience. In order to define a formal representation of experience, we make use of two further basic phenomenological axioms. These
are very general in nature and it is plausible that they hold independently of the particular choice of class C. However, due to the restricted possibility of phenomenological
analysis mentioned above, we generally assume C to comprise adult humans. The first
phenomenological axiom expresses the observation that some qualia are experienced as
identical, whereas others are not, or in other words, that one sometimes experiences
a non-collatable aspect as identical to a non-collatable aspect one has experienced at
another time.
8We generally abbreviate ‘colour aspects of experience’ by ‘colour experience’.
14
J. KLEINER
Phenomenological Axiom 3.12. Qualia can be recognised to a certain extent: Experiencing subjects can identify qualia which they have previously experienced.
Example 3.13. Phenomenological Axiom 3.12 states that experiencing subjects may perceive
some aspects they experience at different times to be identical. For example, it could be the
case that someone finds the taste aspect experienced when trying artificial strawberry flavour to
be identical to the taste aspect experienced when eating an actual strawberry. This recognition
of previously experienced aspects is simply a “subjective impression” of identity, so to speak.
♦
Phenomenal Fact 3.12 is important because it is the basis of the ability of an experiencing subject to introduce labels for his/her qualia, i.e. a name or reference for
non-collatable aspects of his/her experience. Recognisability is presupposed in the notion of collatability, so that labels of collatable aspects of experience can be introduced
by definition.
In what follows, we assume that labels are chosen such that different aspects of experience are associated with different labels and, using Phenomenological Axiom 3.12,
that the same label is used to denote various occurrences of the same aspect.9 Furthermore, we assume that all experiencing subjects use the same set of labels, which
we denote by E. For our purposes, E can be any set, which labels the set consists of
does not matter in what follows.
The second phenomenological axiom expresses the observation that something can
be said about how non-collatable aspects occur in, or constitute, experience. In [Nag74],
it corresponds to the observation that “structural features of perception might be more
accessible to objective description, even though something would be left out” [Nag74,
p. 449]. In [Cha96], it corresponds to the observation that “even if experiences are
in some sense ‘ineffable,’ relations between experiences are not; we have no trouble
discussing these relations, whether they be relations of similarity and difference, geometric relations, relations of intensity, and so on. As Schlick [Sch38] pointed out, the
form of experience seems to be straightforwardly communicable, even if the content
(intrinsic quality) is not” [Cha96, p. 224].
Phenomenological Axiom 3.14. Qualia have relations that can be collated within
the class C.
By Definition 3.4, this is a claim about experiences of all experiencing subjects in
the class C. In simple terms, it expresses the fact that something can be said about
non-collatable aspects of experience, something about how they appear in experience.
The collatability of the relations implies that we may represent the relations on the
set of labels E and assume (i.e. ask, cf. Footnote 9) labels to be chosen in such a way
that the experienced relations between qualia are reflected in the relations represented
on the labels. We assume that Phenomenological Axiom 3.14 also holds for collatable
aspects of experience, so that they have relations, too, that can be represented on the
set of labels.10
9Note that throughout this section, assumptions are in fact conventions. E.g., this assumption can
be satisfied by asking experiencing subjects (in an experiment, say) to choose labels as described. The
assumptions can be made ‘without loss of generality’, so to speak.
10Phenomenological Axiom 3.14 states that there are relations between qualia which are collatable.
This expresses the observations in [Nag74], [Cha96] and [Sch38] that structural features of perception,
relations between experiences or the form of experience might be more accessible to communication or
objective description. However, one might question whether this axiom is warranted, and insist that
MATHEMATICAL MODELS OF CONSCIOUSNESS
15
Example 3.15. For qualia of the ‘what it is like to be’ type (introduced in Example 3.11)
these relations include
◮ Similarity: Two qualia can be more or less similar.
◮ Intensity: A quale can occur in more or less intense versions.
among others.11
♦
Example 3.16. Experiencing subjects typically experience some pairs of colours as similar to
each other, whereas they experience others as not similar. E.g., small changes in hue usually
result in colours which are perceived as similar, whereas large changes in hue result in colours
which are not experienced as similar.
What is crucial for our purposes is that one may (and in practise often does) represent the
experience of similarity of colours on the set of colour labels. Correspondingly, one may (and
in practise often does) ask experiencing subjects to choose labels for their colour experiences
in such a way that colours which are experienced as similar are similar according to the
representation on colour space.12 We will study this in detail in Example 3.20 below.
♦
Phenomenological Axiom 3.12 provides the possibility to introduce labels for noncollatable and collatable aspects of experience. What Phenomenological Axiom 3.14
adds to this is the possibility to represent relations between aspects of experience on the
set of labels. Since any representation of a relation on a set is mathematical in nature,
so are these representations. They give either relations on E in the mathematical sense
of the word (i.e. a subset R of E × E) or some more involved mathematical structure,
which turns E into a mathematical space.13
Thus, together, these two phenomenological axioms ground a representation of experience in terms of mathematical structure. We refer to the set of labels E together
with its mathematical structure that represents relations between qualia as
Experience space E,
(3.1)
though it is important to keep in mind that this space does not describe experience
per se, but only labels and the structural relations between aspects of experiences they
represent. This space E is the mathematical representation of experience mentioned
above. Every element e ∈ E refers either to a collatable aspect of experience or to a
quale. Several detailed examples are given in Section 3.5 below.
relations between experiences are not (strictly, at least) collatable. (Thanks to an anonymous referee
for pointing this out.) The formalism developed here requires the collatability of relations, so that any
non-collatable relation has to be ignored.
11
Similarity and intensity are simple examples of collatable relations between qualia. There may
be many more collatable relations which express facts about how qualia appear in experience, some of
which may only relate qualia of a particular type to each other. Further examples arguably include:
Composition: Some qualia are experienced as a composition of two (or more) different qualia. I.e., the
composed quale is but a combination (or simultaneous experience) of the composing qualia. Inclusion:
Some qualia may be experienced as containing one (or more) other qualia. Here, the contained quale
is but an aspect of the containing quale. Also, the distinction between various types (visual, auditory,
tactile, etc.) of non-collatable aspects of experience is a relation in the sense of Phenomenological
Axiom 3.14.
12Note that this example is complicated by the fact that we calibrate colour experiences in practise:
We apply or learn rules on how to pick colour labels related to external events such as wave-length
impinging on the eye. This will be discussed in detail in Example 3.20 below. What is crucial is that a
priori, individual labels so chosen do not correlate with colour experience: Two experiencing subjects
may have a completely different colour experience despite using the same label ‘blue’.
13Here, the term ‘mathematical space’ is used to refer to a set which carries additional mathematical
structure. Examples are metric spaces, topological spaces, vector spaces, differentiable manifolds,
principal bundles, measurable spaces and Hilbert spaces.
16
J. KLEINER
In order for the mathematics to come out right in what follows, we have to introduce an important mathematical convention with respect to collatable aspects of
experience. By Definition 3.5, an aspect of experience is collatable if its identity over
all experiencing subjects in the class C can be established. This implies, in particular,
that this aspect of experience can be referenced: In virtue of its collatability, it can
be assigned a unique label used by all experiencing subjects in C. Our convention, in
what follows, is that this is represented in the mathematical structure of E.
Convention 3.17. We assume that for every collatable aspect of experience, the
mathematical structure of E contains a unary collatable relation χ which allows one
to select this aspect of experience uniquely.14
In practise, this means that for any e ∈ E which is collatable, there is a subset χe ⊂ E
which contains only e. This convention ensures that changes of labels, discussed next,
can be represented conveniently using the automorphism group. It ensures that all
the collatable information is represented in the relations between aspects, so that all
aspects can be treated alike in the technical definitions that follow.
In summary, so far we have constructed a space E whose elements denote aspects
of experience (both collatable and non-collatable ones), e.g. phenomenal properties
or elements of experience. Furthermore, this space carries relations or more advanced
mathematical structures that expresses the structural features of experience, as well
as information about which aspects of experience are collatable (in virtue of Convention 3.17). This allows us to give a concise account of references to aspects of
experience that takes non-collatability into account, as we explain next.
3.3. References to Qualia. In virtue of non-collatability, any reference to qualia is
ambiguous. In this section, we explain in detail why and in doing so, develop formal
tools that allow us to quantify this ambiguity precisely.
We proceed in two steps. First, we discuss the case where an experiencing subject
uses labels to report on his/her experience without taking into account any of the
collatable relations. This is a preparatory step whose purpose is to explain the following
constructions in detail. Since it ignores the relations on E, i.e. structural features of
experience, it is artificial and will give a pathological result. Subsequently, in the
second step, we discuss the appropriate case which takes the mathematical structure
of E into account.
Preparation: References that ignore relations. Let us assume that an experiencing
subject uses labels to report on his/her experience without taking into account any of
the collatable relations. In this case the experiencing subject is free to choose any label
to denote any aspect of experience, the only requirements being that different labels are
used for different aspects and that the same label is being used for a recurrent aspect.
We call a choice of labels of an experiencing subject to denote his/her experienced
aspects a labelling and use the term relabelling to denote a change of labelling. In the
present case, a relabelling is simply a map
s : E → E,
e 7→ s(e) ,
(3.2)
which determines which label s(e) replaces the previous label e. Since different aspects
are required to carry different labels, this map is injective. Since it furthermore has
domain and codomain E, it is bijective. Since any composition of two relabellings of the
14A unary relation on E is simply a subset of E.
MATHEMATICAL MODELS OF CONSCIOUSNESS
17
form (3.2) yields another relabelling, and since due to the bijectivity, each map (3.2)
is invertible, all possible relabellings form a group: The group of all bijective maps
from E to itself. This group is called the symmetric group of the set E.
The crucial insight here is that the group of relabellings allows us to quantify the
ambiguity of any statement that refers to aspects of experience. Consider e.g. the
case where a statement only involves one label e1 ∈ E. Since we are disregarding
collatable relations at this point, this statement could just as well have been formulated
with any other label e2 ∈ E, simply because an experiencing subject may choose any
label whatsoever to denote any quale. Mathematically, this is reflected by the fact
that there is at least one relabelling s such that s(e1 ) = e2 . The same reasoning
can be applied to sequences (e1 , ... , en ) of labels, e.g. obtained by verbal reports at
subsequent times. The ambiguity of a sequence (e1 , ... , en ) of labels is the set of all
sequences (e′1 , ... , e′n ) which can be obtained from the former by a relabelling s, i.e.
the set of all sequences (e′1 , ... , e′n ) for which there exists a relabelling s such that
(e′1 , ... , e′n ) = (s(e1 ), ... , s(en )).
These statements are in fact statements about equivalence classes. To see this,
.
define two labels e1 and e2 to be equivalent, e1 ∼ e2 , if and only if there exists a
relabelling s such that s(e1 ) = e2 . The ambiguity of a label e ∈ E is given precisely
by the equivalence class of this label,
.
(3.3)
[e] := e′ | e′ ∼ e = e′ | ∃ s : e′ = s(e) ,
because this class contains all labels which an experiencing subject could have chosen. The same is true for sequences: If we define two sequences to be equivalent,
.
(e′1 , ... , e′n ) ∼ (e1 , ... , en ), if and only if there exists a relabelling s such that (e′1 , ... , e′n ) =
(s(e1 ), ... , s(en )), the ambiguity of a sequence of labels is given precisely by the equivalence class of this sequence,
.
[(e1 , ... , en )] := (e′1 , ... , e′n ) | (e′1 , ... , e′n ) ∼ (e1 , ... , en ) ,
(3.4)
because this class contains precisely all those descriptions of the sequence which an
experiencing subject may give. Another way to put this is that the equivalence
classes (3.3) and (3.4) are what is empirically well-defined, not the labels themselves,
these only have meaning for the experiencing subject him/herself once he/she has
chosen a particular labelling.
This concludes the description of the case that ignores structural features of experience. Its artificial nature is reflected in the fact that the symmetric group allows one
to map any choice (e1 , ... , en ) of labels to any other choice (e′1 , ... , e′n ), provided that
every label occurs at most once in each choice. Thus there are very few equivalence
classes (only one if n = 1). We now proceed to the discussion of the appropriate case.
Taking Relations into Account. Next, we take into account the collatable relations
between aspects of experience as established in Phenomenological Axiom 3.14. To
do so, we work with the experience space E introduced above: I.e., we assume that
the relations between qualia have been represented on the set of labels15 and ask
experiencing subjects to pick labels for the qualia they experience in accordance with
this representation. As above, we refer to any such choice as labelling.
15For all practical purposes, one can obtain such a representation by simply asking one experiencing
subject to pick a labelling and to report, in terms of this labelling, on his/her experienced relations.
Other experiencing subjects are then required to choose labels according to this representation. For
details, see Example 3.20 below. For explicit examples on how such a representation might look, cf.
Examples 3.21 to 3.24 below.
18
J. KLEINER
This constraint on how labels can be chosen implies that the freedom of every
experiencing subject to choose labels is smaller than in the case above: Functions (3.2)
only constitute relabellings if they preserve the collatable relations represented on the
set E, i.e. if they preserve the structure of the space E. A bijective function from a
space to itself which preserves the structure of this space is called an automorphism of
the space. As above, automorphisms form a group. Thus in the case where we take
into account the collatable relations, relabellings are elements of the
Automorphism group Aut(E).
(3.5)
We summarize this by saying that the automorphism group Aut(E) describes the
freedom of relabelling of every experiencing subject.
It is here that Convention 3.17 is important. Since for every collatable aspect of
experience there is a unary relation which the automorphism group needs to leave
invariant, this convention ensures that automorphisms do not change labels of collatable aspects of experience. As a result, the automorphism group allows us to quantify
precisely the ambiguity inherent any reference to qualia.
In order to identify the ambiguity of any statement that uses a sequence (e1 , ... , en )
of labels, we can argue exactly as in the simplified description above, replacing transformations (3.2) by automorphisms. The result is that the ambiguity is given precisely
by the equivalence class
[(e1 , ... , en )] := (e′1 , ... , e′n ) | (e′1 , ... , e′n ) ∼ (e1 , ... , en ) ,
(3.6)
where ∼ denotes the equivalence relation defined as
(e′1 , ... , e′n ) ∼ (e1 , ... , en )
if and only if there is an s ∈ Aut(E)
such that e′i = s(ei ) for all i = 1, ... , n .
(3.7)
This class contains precisely all descriptions of the sequence of aspects of experiences
which an experiencing subject might give: A description in every possible labelling.
To obtain the ambiguity of individual labels, we simply set n = 1.
In summary, what this shows is that the empirically well-defined references to experience are given by elements of the quotient space
E ×n /∼ ,
(3.8)
where E is the space (3.1) whose structure represents collatable relations between
aspects of experience, where ∼ denotes the equivalence relation (3.7) and where n ∈ N
is the length of a sequence.
Remark 3.18. In practise, we typically establish labels by reference to particular
“external” events, such as particular wavelengths emerging from a light source in the
case of colour experiences. Socially established labels of this sort are of course very
useful in various circumstances, precisely because they correlate with external events.
However, a priori there is no reason to assume that qualia of different experiencing
subjects which are denoted by the same label are the same, even if the labels correlate
with the same external event.16 In fact, an assumption of this kind has no empirical
meaning because the definition of qualia implies that neither the identity of qualia of
different experiencing subjects with an external event, nor the equality of qualia of
different experiencing subjects can be empirically tested. Statements of this sort can
16One may even take this to be unlikely, given the difference of brain physiology and neuronal
structure across individuals.
MATHEMATICAL MODELS OF CONSCIOUSNESS
19
only be meaningful if formulated based on a scientific methodology which is compatible
with the non-collatability of the aspects of experience under consideration.
♦
3.4. A Phenomenological Grounding of the Scientific Study of Consciousness. In the previous sections, we have fixed basic terminology, such as what we take
the term experience to denote and how qualia are defined in these terms. We have furthermore used phenomenological axioms to warrant introduction of labels, which has
in turn allowed us to ground a mathematical representation of experience. Finally, we
have analysed the implications of non-collatability (and hence of ineffability, privateness and inaccessibility) in terms of this formal representation. Together, this gives
rise to a grounding of the scientific study of consciousness, i.e. allows us to specify
what is to be studied and how.
First, concerning the task of the scientific study of consciousness, what is to be studied is simply experience as defined in Definition 3.1 and its relation to the physical
domain. By Phenomenological Axiom 3.6, this includes collatable aspects of experience as well as qualia. What is required to do so is a combination of the usual
scientific methodology with some novel tools (developed in the remainder of this article). How these methodologies are combined is described by the formal representation
of conscious experience in the experience space E.
The usual scientific methodology, e.g. the one in use today in the neuroscience of
consciousness, can be applied to all intersubjectively well-defined references to experience, i.e. to the equivalence classes (3.6). When taken together, they constitute the
quotient space (3.8), which provides a comprehensive description of all intersubjectively meaningful aspects of experience. This quotient space contains, in particular,
all references to collatable aspects of experience.
However, the usual scientific methodology cannot be used to investigate individual
elements of equivalence classes (3.6), if a class has more than one element, because
the experiences labelled by these elements cannot be referenced intersubjectively in a
meaningful way. These elements in fact generate an explanatory gap (Section 4). The
study of these aspects of experience is, nevertheless, part of the task of the scientific
study of consciousness. There is a fact as to which member of an equivalence class is
experienced, and this fact cannot a priori be excluded from constituting a scientific
explanandum.
The main achievement of this article in the following sections is to show that formal
tools can be defined that allow us to go beyond a scientific analysis of the quotient
space (3.8). Referring to these results, we can specify the grounding that arises from
the previous definitions as follows. Due to the importance of phenomenological axioms
in grounding the formal structure, we refer to this grounding as phenomenological
grounding.
Definition 3.19. What is to be studied by the scientific study of consciousness according to the phenomenological grounding is experience as defined in Definition 3.1
and its relation to the physical domain. This includes the study of intersubjectively
well-defined aspects of experience using the quotient space (3.8) and standard scientific methodology, as well as the study of qualia proper, represented formally in the
experience space (3.1) using the formal-mathematical methodology derived in Section 6.
3.5. Examples. We close this section with several examples. First, in Example 3.20,
we continue the discussion of colour experience and show that colour spaces, which
are largely in use in commercial applications, constitute the experience spaces for
20
J. KLEINER
colour qualia as defined above. In Example 3.21 to 3.24 we consider various possible
mathematical structures of the experience space E, some of which have been proposed
in the literature.
Example 3.20. To illustrate the meaning of the experience space E and the group Aut(E),
as well as Remark 3.18, we consider again colour experiences. As we have explained in Example 3.8, these satisfy the defining property of qualia.
We will generally denote the quale ‘what it is like to see light of wavelength λ’ as ‘experience
of λ’. For the purpose of this example, we will disregard of the fact that colour experience
is highly sensitive to the geometry of the lighting of a scene and to the expected material
properties of an object’s surface. We will use the symbol λ̄ to denote a mixture of light of
varying wavelength.
We start by fixing a particular human oberver, the “standard observer” [Kue10], and choose
a set Ecl that is in one-to-one correspondence to all colours which this human can experience.
As usual in colour science, we assume that there is a large class C of humans which have the
same set of possible colour experiences as the standard observer. This assumption implies that
every human in the class C can specify a one-to-one mapping between the set Ecl and his/her
colour experiences. The fact that color experiences are qualia as defined here is reflected in the
fact that there is no unique one-to-one mapping. The set Ecl is thus a set of labels of colour
qualia as introduced after Phenomenological Axiom 3.12. It is also the basis of the definition
of colour spaces (cf. below).
The set Ecl can be calibrated: Since colour experiences arguably arise as a response to
mixtures λ̄ of light impending on the retina, we may identify every element e ∈ Ecl with a
particular mixture λ̄. The set of mixtures visible to the human eye can, in turn, be represented17
as a subset S ⊂ R3 , roughly speaking by taking the three components of a vector v ∈ S
to represent the relative intensities of three reference wavelengths. Putting these two steps
together, we may in fact choose the set Ecl to be the subset S ⊂ R3 . In this case, every label
e ∈ Ecl is a 3-tuple of real numbers which specifies which mixture λ̄ of light has to be presented
to a particular human to evoke the quale that he/she has denoted by that very label e.
This calibration may lead one to think that there is a unique way of referring to colour
qualia. However, this is not the case. To see this, assume that we fix some label/vector
e ∈ S = Ecl as well as two experiencing subjects A and B. Let us denote the mixture of light
that corresponds to this vector as λ̄v . When we present this mixture λ̄v to the two experiencing
subjects, subject A has the colour experience he/she has labelled as e, and so does subject B.
However, this has nothing to say on whether the colour experiences are the same or not:
E.g., subject B might have the colour experience subject A is having upon presentation of a
completely different mixture λ̄w 6= λ̄v .
This illustrates the fundamental difficulty related to qualia as defined in Definition 3.9: If we
would “know” (e.g. as the result of some scientific investigation) that the presentation of the
same colour stimuli λ̄v to various subjects results in them having the same colour experience,
we could meaningfully talk, or refer to, colour experiences of different subjects in terms of
stimuli. More generally, if statements of the type
“subject A will have colour experience X1 once presented input λ̄”
(3.9)
would be known, these statements would allow us to directly refer to A’s colour experiences,
putting us into the position to do science as usual. However, the fundamental difficulty of the
17This is an experimental fact which is due to biological details of the cone cells in the human
eye. Since various mixtures λ̄ evoke the same colour experience, some conventions have to be made in
order to fix the subset S uniquely (e.g. a choice of reference wavelengths). Also, due to the particular
responsivity curves of the cone cells, no finite set of wave-lengths can be combined to achieve all
colours that a human can experience. However, suitable experimental procedures exist so that all
visible mixtures can be represented in R3 nevertheless [Kue10].
MATHEMATICAL MODELS OF CONSCIOUSNESS
21
subject is that statements like (3.9) do not carry any intersubjective meaning at all: Due to
the impossibility of collating colour experiences, statement (3.9) cannot be distinguished (by
anyone but subject A) from the statement
“subject A will have colour experience X2 once presented input λ̄”,
where X2 is any colour experience of A with the same unary collatable relations (such as
intensity). This problem exists independently of whether we consider the statement (3.9) to
be a hypothesis or to be the result of some purported scientific investigation. Statements of
this type do not have unambiguous intersubjective meaning.
As explained above, what has intersubjective meaning are the equivalence classes (3.6).
They express facts about colour experience which are invariant with respect to the labelling
that an experiencing subject chooses. We now illustrate this in detail for colour qualia.
First, we need to find the collatable relations between colour experiences referred to in
Phenomenological Axiom 3.14. Luckily, this has been on the agenda of colour science for
decades, so that we may simply turn to its results. Put in simple terms, there seem to be
three types of collatable relations [Kue10]: Continuity of change of colours (whether some
time-continuous sequence of colour experiences is perceived as continuous or not), behaviour
under mixtures of colours (whether a mixture of two colour experiences is perceived as equal
to another colour experience or not) and (less well known) a notion of distance of colours
(whether two colour experiences are perceived as more different to each other than another
pair of colour experiences).
Next, we need to translate these collatable relations into mathematical structures on the
set Ecl . This yields the experience space (3.1) of colour qualia. Again, colour scientists have
done the work for us: They have defined colour spaces in order to formalize these collatable
relations [Kue10]. A colour space is a closed subset S of R3 which is in a one-to-one correspondence with all colours humans may experience, chosen such that continuity is represented
by the induced topology of R3 (a path of colours experiences is continuous if the labels form
a continuous path in the colour space), mixture is represented by straight lines (equal mixing
of two colour experiences e1 and e2 yields the colour experience that carries the label that is
at the center of the straight line that connects e1 and e2 ), and finally experienced distance of
colour qualia is represented by a metric on S. 18 Thus a colour space is a experience space (3.1)
for colour qualia.
There are many subsets of R3 which satisfy these requirements: For any choice of subset S,
there is a large class of transformation of R3 which, together with a corresponding transformation of the metric, yield another subset S ′ of R3 which equally represents colour experiences
as well as their collatable relation. Colour science uses the calibration described above to fix
specific choices of subsets S, so that the coordinates of the elements of S can be translated into
mixtures of wavelengths λ̄. However, as explained above, for the study of colour experience,
calibrations do not have any relevance a priori, so that no particular choice of subset can be
singled out.
In order to specify the group of relabellings for this example, we note that in more abstract
terms, a colour space is19 a smooth 3-dimensional Riemannian manifold: Its topology represents the continuous changes of colour experience and its metric g specifies both the geodesics
(generalized “straight lines”), which describe the mixture of colour experiences, as well as a
distance function which describes the experience of distance between colour qualia. The various choices of subsets S of R3 correspond precisely to choices of coordinates of this manifold.
18We take it that straight lines describe mixtures of colour experiences, which have to be distinguished from the experience of mixtures of colours. Thanks to an anonymous referee for pointing this
out.
19Cf. [Kue10]. However, note that a more axiomatic treatment may result in different mathematical
spaces [Res74, Pro17]. Furthermore, the assumption of smoothness may not be justified and one might
have to consider manifolds with corners.
22
J. KLEINER
We summarize this as
E = (Ecl , g) .
(3.10)
This is the actual form of the experience space (3.1) of colour qualia. Its elements label the set
of colour experiences and its structure represents the collatable relations between them. An
experiencing subject can specify his/her colour experiences by specifying points (in the case of
individual colour experiences) or curves (in the case of time-continuous colour experiences) on
this manifold. The freedom of choosing labels is described by the automorphism group of E. In
the case (3.10) of a Riemannian manifold, this is the group of isometries, i.e. diffeomorphisms
which leave the metric invariant:
Aut(E) = Iso(E) .
Thus the ambiguity of any statement in terms of colour labels (e1 , ... , en ) is given by the
equivalence class
[(e1 , ... , en )]
which is defined as in (3.6) with two sequences being equivalent if there is an isometry s ∈
Iso(E) which transforms every element of the first sequence into the corresponding element
of the second sequence.20 The actual form of the equivalence classes depends on the metric
g, which can be determined experimentally. The current version of the distance function
internationally in use is reviewed e.g. in [SWD04], a discussion of which however goes beyond
the scope of this example.21
Putting everything together, we conclude that any statement, scientific or otherwise, that
addresses colour experiences sensu stricto – i.e. which addresses what it is like to experience
colours – only makes sense if it is invariant with respect to Iso(E) transformations. This is
a consequence of the fact that qualia are non-collatable and of the corresponding freedom of
every experiencing subject to choose names for the qualia he/she experiences.
The difference between labels of colour experiences and colour experiences (colour experiences de dicto and colour experiences de re, so to speak), can be crucial for scientific investigations. For example, if a study compares the calibrated label e that a subject reports with
neural activity, it does not investigate the relation between neural activity and colour experience but rather the relation between neural activity and presentation of wavelengths λ̄ to the
retina. These two objects of investigation refer to completely different scientific agendas. ♦
Example 3.21. Pretopological structure on E. In the previous example, we have relied
on results from colour science to provide the mathematical structure of the experience space
E that represents the colour aspects of experience. The goal of this example is to illustrate in
more detail how the mathematical structure of E can be defined directly in terms of relations
between qualia. To this end, we consider the relation of similarity of two qualia explained
in Example 3.15, but understood in a binary way. I.e., for the purpose of this example, we
make the simplifying assumption that any two non-collatable aspects of experience (of one
experiencing subject) are experienced either as ‘similar’ or as ‘not similar’, and ignore the
experience of varying degrees of similarity. While this restriction may not be warranted in
practise, we take it to be justified for pedagogical purposes. When understood in this way, the
20Since the ordering of distances between pairs of colours, rather than the numerical value of the
distance itself, is collatable, one could make the point that the relabelling freedom is given by the
group of diffeomorphisms which leave the metric invariant up to a conformal factor. Since the present
example is, mainly, of a pedagogical interest, we do not explore this further at this point. Cf. also
Footnote 19.
21We note that it is possible that some sequences (e , ... , e ) are not ambiguous, i.e.
that
1
n
[(e1 , ... , en )] = {(e1 , ... , en )}. This means that there is one unique sequence of colour experiences
which has the properties represented by the sequence (e1 , ... , en ) of labels, or put differently, that
there is only one possible choice of labels for this sequence that takes into account the collatable relations as described. Sequences of this kind may be used to remove the ambiguity of the labels they
contain and make these aspects of experience accessible to a proper scientific analysis.
MATHEMATICAL MODELS OF CONSCIOUSNESS
23
similarity relation can be used to define a pretopological structure on E as described in [Pre19]
(with a slightly different goal in mind), whose presentation we now follow.22
First, we define a binary relation R◦ ⊂ E × E on E. If two qualia with labels e1 and e2 are
perceived as similar by an experiencing subject, we define the corresponding labels to be related
according to R◦ , which we denote as e1 ◦ e2 (i.e. e1 ◦ e2 ⇔ (e1 , e2 ) ∈ R◦ , and similarly below).
Thus R◦ is given directly by experience. We assume that e ◦ e for all e ∈ E. Second, based on
the data of R◦ , we define another relation R≤ on E, called “parthood relation” [Pre19] as
e1 ≤ e2
iff
e ◦ e1 ⇒ e ◦ e2 .
Thus e1 ≤ e2 holds iff all qualia which are similar to e1 are also similar to e2 . Third, we use
the parthood relation R≤ to define yet another relation R∼ , called “connection”, as follows:
e1 ∼ e2
iff
∃ ẽ ∈ E such that ẽ ◦ e1 and ẽ ◦ e2
as well as e ≤ ẽ ⇒ e ◦ e1 or e ◦ e2 .
Note that e1 ≤ e2 implies e1 ∼ e2 . We extend this notation to sets A ⊂ E by defining
e ∼ A iff e ∼ ẽ for at least one ẽ ∈ A.
This allows us to define an operator pcl, which takes a subset A ⊂ E to another subset pcl(A)
which contains all qualia which are connected to at least one of the qualia in A:
pcl(A) := {e | e ∼ A} .
The operator pcl satisfies three of the four Kuratowski closure axioms [Per64, Sec. 3.2], but
need not satisfy pcl(pcl(A)) = pcl(A) for all A ⊂ E (idempotence). Hence it constitutes a
preclosure operator, so that (E, pcl) constitute a pretopological space [nLa19].
In order to define what constitutes a relabelling in this example, we note that a function f
between two pretopological spaces (E, pcl) and (E ′ , pcl′ ) is defined to be continuous if
f (pcl(A)) ⊆ pcl′ (f (A))
for all A ⊂ E. The automorphism group Aut(E) of (E, pcl) is the set of all continuous invertible
functions f : E → E whose inverse is also continuous, with group operation given by function
composition.
Thus we see neatly how non-trivial mathematical properties of the experience space E can
be defined directly in terms of experienced relations between qualia. The similarity relation
established via Phenomenological Axiom 3.14 may, of course, not actually be binary: There
seem to be various degrees, maybe even a continuum, of similarities of qualia.
♦
Example 3.22. Partial order on E. Our next example goes back to [Res18]. First, we
observe that next to the two relations mentioned in Phenomenological Axiom 3.14, qualia may
in fact have compositional relations that can be collated: An experiencing subject may find
that the ineffable aspect of an experience he/she is having at a particular time includes an
ineffable aspect he/she has had at another time. In this case, we may say that the former
quale includes the latter quale. If e1 is the label which the experiencing subject has chosen for
the former quale and e2 is the label he/she has chosen for the latter quale, we will denote this
relation between the two qualia as e2 ≤ e1 .
By convention, we may put e ≤ e for all e ∈ E (reflexivity). Furthermore, it is reasonable
to hold that if both e1 ≤ e2 and e2 ≤ e1 for two labels e1 , e2 ∈ E, these labels actually
refer to the same quale, so that e1 = e2 (anti-symmetry). Finally, qualia seem to satisfy that
e1 ≤ e2 and e2 ≤ e3 imply e1 ≤ e3 (transitivity). Therefore, this actually constitutes a partial
order on E and turns (E, ≤) into a partially ordered set. The automorphism group consists
22The following definitions and their relation to topology are intuitively accessible if one thinks
about open balls in a metric space such as R3 , where ◦ is defined as overlap. We remark, however,
that the construction does not give rise to a topology, as claimed in [Pre19], since the third Kuratowski
closure axiom (idempotence) does not follow.
24
J. KLEINER
of bijective functions f : E → E which are order-embedding, i.e. which satisfy e1 ≤ e2 if and
only if f (e1 ) ≤ f (e2 ) for all e1 , e2 ∈ E. Thus one can see nicely that the automorphism group
describes the freedom of relabelling: Its elements represent changes of labels which preserve
the inclusion relation between qualia.
♦
Example 3.23. Involutive semigroup structure on E. This example also goes back
to [Res18]. In order to state it, note that in Definition 3.1, we have defined the term ‘experience’
with respect to instants of time. This implies that qualia (being aspects of experience) are
associated to a instant of time as well,23 therefore excluding a sequence of two qualia arising
at two consecutive instants of time to constitute another quale. However, one might drop this
restriction to instants of time, and define qualia as aspects of experience in general. Following
this line of thought, one could argue that for any two qualia e1 , e2 , there is another quale e3
which is the consecutive experience of the two qualia. One might denote e3 as
e3 = e1 & e2 ,
where the ‘&’ represents “and then” [Res18]. If one furthermore demands associativity, which
does seem to be plausible, this defines a semigroup (E, &).
Next, one may consider an operation which reverses this temporal order of qualia. This
may or may not have deep conceptual meaning: On the one hand, it may merely map any
quale of the form e1 & e2 to a quale of the form e2 & e1 , both of which have to exist due to the
semigroup structure introduced above. On the other hand, it may express a deep fact about
reversal of psychological time [Res18]. In both cases, skipping over a few technical details, this
gives rise to an involution [Res18], i.e. a map
∗ :E → E
such that
∗
(e∗ )∗ = e .
e 7→ e
In summary, the time composition relation of qualia may be represented on the space of labels
in terms of an involutive semigroup structure.
♦
Example 3.24. Hilbert space structure on E. The last example is intended to evaluate
in how far the axioms of a Hilbert space can be grounded in the relations introduced in
Phenomenal Fact 3.14. The upshot is that whereas some of the axioms can be motivated
based on Phenomenological Axiom 3.14, others cannot. Nevertheless, the example may prove
valuable for constructing toy models of consciousness, which is why we include it here.
In what follows, we make several assumptions about the set of all experiences which an
experiencing subject might have. These assumptions are phenomenological in flavour, yet
some may ultimately not be justified.
(A1) We assume that with respect to any two qualia of one experiencing subject, the experiencing subject might have an experience which has exactly these qualia as ineffable
aspects.
With respect to qualia of the ‘what it is like to be’ type (Example 3.11), this assumption
amounts to the following statement: If an experiencing subject has made an experience which
included an ineffable ‘what is it like to be’ aspect (quale) which he/she labels by e1 , and
another experience which included an ineffable ‘what is it like to be’ aspect (quale) which
he/she labels by e2 , then it is possible that he/she will make an experience which has exactly
e1 and e2 as ineffable aspects. We will use the term ‘simultaneous experience of e1 and e2 ’ as
an abbreviation for the statement that the experiencing subject in question has an experience
which includes both aspects e1 and e2 . To give an example, let e1 refer to what it is like to taste
cheese and e2 refer to what it is like to smell wine. In this case, Assumption (A1) amounts
to granting the possibility of the experiencing subject in question simultaneously experiencing
what it is like to taste cheese and what it is like to smell wine. Whether this experience
23The term ‘instant of time’ may refer to experiential instants of time or to instants of time as used
in physics, i.e. points t ∈ R.
MATHEMATICAL MODELS OF CONSCIOUSNESS
25
actually arises when the subject eats cheese and drinks wine is of no concern with respect to
Assumption (A1). We take the combination of the same experience e with itself as denoting the
experience of quale e but twice as intense (cf. below). In order to motivate a group structure
with respect to simultaneous experience, the following assumption is necessary:
(A2) We assume that there is a unique neutral quale which we denote by ‘0’. Furthermore,
we assume that for every quale e, there is a quale −e such that an experience which
includes both e and −e is not distinguishable from (and hence equal to) the experience
of the neutral quale.
It seems that this assumption is utterly beyond empirical justification, since it invokes something like “cancellation” of ‘what is it like to be’ aspects of experiences, so that we may only
be able to ground a semigroup-structure of qualia with respect to combination (‘simultaneous
experience’). For the purpose of this example, we proceed nevertheless. We denote the simultaneous experience of two qualia e1 and e2 by ⊕, so that the ineffable aspect of the experience
which comprises both qualia labelled as e1 and as e2 established by Assumption (A1) is labelled
by e1 ⊕ e2 . Associativity and commutativity hold, so that we have:
◮ (A1) and (A2) imply that ⊕ : E × E → E is an abelian group.
Next, we model changes of intensity, as conceded in Phenomenological Axiom 3.14, by a
positive real number in the following sense: If e2 is the same quale as e1 , but c times more
intense, then we denote e2 = ce1 , where c ∈ R+ . For c ∈ R− , ce1 is the opposite experience −e1
introduced in (A2), but experienced |c| times as intense as −e1 , where |c| is the modulus of c.
Finally, we assume that as intensity decreases, c → 0, any experience goes over to the neutral
quale, formally limc→0 ce = 0 for any e ∈ E, where 0 denotes the neutral quale introduced
in (A2). Making the idealized assumption that a continuum of more and less intense versions
of any experience is possible, we have:
◮ The intensity relation of Phenomenal Fact 3.14 may be taken to give rise to a scalar
multiplication ⊙ : R × E → E.
As usual, we suppress the symbol ⊙ for scalar multiplication. We need to check whether the
axioms of a vector space relating scalar multiplication and addition hold. Our interpretation
implies that 1e = e, hence neutrality of 1 ∈ R holds. The two axioms of distributivity read
c (e ⊕ e′ ) = (ce) ⊕ (ce′ )
′
and
′
(3.11)
′
(c + c ) e = ce ⊕ c e
′
for all c, c ∈ R and e, e ∈ E
(3.12)
′
Axiom (3.11) says that a c times more intense simultaneous experience of e and e arises as
the combination of c times more intense experiences of e and e′ , respectively, which we take as
a plausible assumption in the context of this example. Axiom (3.12) sates a compatibility of
addition of intensities with combinations of experience. E.g., it says that an experience e′ which
is the same as another experience e but twice as intense, e′ = 2e can arise as the simultaneous
experience of the combination of e with itself. We render this axiom at least somewhat plausible
by defining the combination of an experience with itself to be the same experience experienced
twice as intense. Finally, we note that the associativity axiom (c c′ ) e = c (c′ e) is compatible
with our interpretation of ⊕ and ⊙. We therefore have:
◮ (E, ⊕, ⊙) satisfies the axioms of a vector space.
It remains to implement the the relation of similarity between qualia. As before, we idealize
and assume that there is a non-negative real number which specifies how similar two qualia
e1 and e2 are. We denote this number by he1 , e2 i. If e1 , e2 are not similar at all, we set
he1 , e2 i = 0. If they are similar to some degree, we have he1 , e2 i > 0, where a larger value
implies more similarity. It seems natural to impose symmetry, he, e′ i = he′ , ei for all e, e′ ∈ E.
An inner product furthermore satisfies
he, ei = 0 ⇔ e = 0
′
(Definiteness)
′
he, c e i = c he, e i
′
′′
(Linearity)
′
′′
he, e ⊕ e i = he, e i + he, e i
26
J. KLEINER
for all c ∈ R and e, e′ , e′′ ∈ E. Out of those three axioms, only the last one seems reasonable to
some extent. It says that similarity is compatible with simultaneous experience: The similarity
between a quale e and the simultaneous experience of qualia e′ and e′′ is given by the sum of
the similarity of the quale e to each one of the qualia e′ and e′′ .
Definiteness says that the only quale which is not similar to itself is the neutral quale. This
seems rather problematic if one chooses the interpretation of 0 introduced in (A2). The first
axiom of linearity says that the similarity between a quale e and a c times more intense version
of a quale e′ is given by c times the similarity between e and e′ . As mentioned before, in order
to have a nice and clear example, we will accept also these assumptions for now, so that in
summary we have:
◮ (E, ⊕, ⊙, h., .i) satisfies the axioms of a inner product space or Pre-Hilbert space.
p
The inner product h., .i introduces a norm on E as usual by kek = he, ei. This norm may be
interpreted as the intensity of a quale e.
The inner product space (E, ⊕, ⊙, h., .i) may not be complete with respect to this norm,
meaning that there are Cauchy sequences in E which do not converge to an element in E.
In terms of qualia, this means that there are sequences of qualia whose elements become ever
more similar to each other but which do not converge to any quale in the topology specified
by the similarity relation. In order to exclude such cases, we consider the completion of E
with respect to the norm k.k, which is unique up to isometric isomorphism. Alternatively, we
may assume that there is a finite number of classes of non-similar qualia, so that completeness
holds automatically. A complete inner product space is a Hilbert space. Denoting, as usual,
completion by a line over the corresponding quantities, we have:
◮ The experience space E carries the structure of a real Hilbert space (E, ⊕, ⊙, h., .i),
which we denote by HE .
Note that this is an abstract Hilbert space: Due to the ineffability of qualia, the elements of
the Hilbert space do not have an intrinsic collatable nature (as e.g. the case if one considers
function spaces). The automorphism group Aut(E) is the group U (HE ) of unitary operators. ♦
4. Explanatory Gap
An “explanatory gap” [Lev83] between a phenomenon24 and natural science occurs
if the phenomenon has properties which render it incompatible with all notions of
explanation used in natural science. This is in particular the case if the phenomenon
violates a necessary condition for the application of any of these notions of explanation.
Explanatory gaps are taken by some to indicate or entail ontological gaps (cf. [Cha10,
Ch. 5, Sec. 3.4]). Whether this is legitimate or not is a question which we will not need
to address here. What matters for us is that if there is an explanatory gap, a change of
methodology is necessary if the phenomenon is to be addressed by scientific means.25
This change may or may not be motivated by ontological considerations.
Whether there is an explanatory gap or not strongly hinges on what one takes
scientific explanation to be. E.g., in [Cha96], it is assumed that explanations in natural
science can address “only structure and function, where the relevant structures are
spatiotemporal structures, and the relevant functions are causal roles in the production
of a system’s behavior” [Cha10, p. 105f.], which implies that phenomenal experience,
24Here, by ‘phenomenon’, we mean anything that occurs or manifests itself in a general sense,
including both scientifically observable “empirical phenomena” (such as data of an experiment) as
well as what is directly or indirectly perceived (experiences).
25This is not to say, of course, that every phenomenon can be addressed by scientific means. There
may be phenomena to which the scientific method cannot be applied. However, it seems that the only
way to establish whether this is the case for a particular phenomenon is to try to develop a suitable
methodology and, if successful, to apply it.
MATHEMATICAL MODELS OF CONSCIOUSNESS
27
defined in [Cha96] to consist of precisely those aspects of experience which do not
have a structure and function, cannot be explained by natural science. (For details, cf.
Appednix A.) While this axiomatic derivation of an explanatory gap is undoubtedly
important, the underlying notion of explanation is too narrow (Appendix B.3). This
calls both the explanatory gap and the grounding built on it into question.
This is different for qualia as defined in Definition 3.9. Since the deductive-nomological
model of explanation, the deductive-statistical model of explanation, the statistical relevance model of explanation and the causal mechanical model of explanation all tacitly
presuppose that descriptions of the explanandum can be collated [Woo17], a thorough
explanatory gap exists between any scientific explanation and qualia as defined here.
No scientific methodology in applied to date can be used to address non-collatable
aspects of experience.
Put in simple terms, this comes about from the fact that all explanations used in
natural science to date need to assume that the phenomenon under investigation is
intersubjectively accessible. Since our definition of qualia comprises those aspects of
experience which are not intersubjectively accessible, they cannot be addressed by the
standard methodology. There is no possibility at present in natural science to explain
why an experiencing subject experiences a particular quale over and above explanation
of the collatable relations between qualia.
Thus we conclude that a change of methodology is necessary if qualia are to be
addressed scientifically. The remainder of this article is devoted to developing this
change in methodology. Our results show that mathematical tools can be devised
which allow us to address it. The resulting methodology generalizes Chalmers’ strategy
(outlined in Section A) and constitutes a formal framework for models of consciousness.
5. The Mathematical Structure of Models of Consciousness
Models of consciousness are hypotheses about how conscious experience and the
physical domain relate. In this section, we describe the general mathematical structure
these models may take making use of the minimally sufficient mathematical structure of
any formal scientific theory (Section 5.1) and of the epistemic asymmetry of conscious
experience (Section 5.2). Finally, we introduce notation that will be used further
below. (Section 5.3).
5.1. Mathematical Structure of Scientific Theories. There are various different
accounts in philosophy of science of what constitutes a scientific theory. Roughly, one
may distinguish syntactic accounts, semantic accounts and pragmatic accounts [Win16],
which differ mainly in the role they attribute to mathematical formalization. Which
account of scientific theories is most adequate for the scientific study of consciousness
is yet to be seen.
The following list of formal ingredients is general enough to include any of the abovementioned accounts of what constitutes a scientific theory. In preparation, we remark
that a family (dt )t∈I is a function f : t 7→ dt , which we will call “trajectory”. It
describes the change of dynamical variables with respect to the parameter t. Needless
to say, the following list is not intended to be sufficient.
Definition 5.1. The mathematical structure of a scientific theory T comprises at
least:
28
J. KLEINER
A set of dynamical variables d. (Those quantities whose variation is determined
by T to some extent.)26
◮ Some background structure b. (Variables, or general mathematical structures,
whose change is not determined by T . Background structure needs to be fixed
in order to determine the variation of d in a particular application.) The
variation or change of the dynamical variable of a theory can be expressed
with respect to some parameter t which takes values in some set I. Typically,
the parameter is assumed continuous and interpreted as time. However, this is
not necessary: The set I may or may not carry some mathematical structure
(such as a topology) and it may or may not be interpretable as time.
◮ A set of kinematically possible trajectories K. Sometimes, this includes all
possible trajectories, K = {(dt )t∈I }, but in many cases, trajectories need to
satisfy certain mathematical requirements, such as differentiability with respect
to the parameter t.
◮ Some laws L. (Typically equations or variational principles, but L may also
include different formal ingredients (such as those provided by category theory)
or even non-formal ingredients, as required by pragmatic accounts of scientific
theories.)
◮ A set of dynamically possible trajectories D which we also call solutions of T .
These are those kinematically possible trajectories (D ⊂ K) which are selected
by the theory’s laws in a particular application of the theory, given some choice
of background structure and possibly taking into account some “nonformal
patterns in theories” [Cra02, p. 55].
◮
In the next section, we will put these ingredients of a scientific theory into connection
with the definitions introduced in Section 3.1. In doing so, we will have to distinguish
between a general theory T and those theories which have been put forward (or are
anticipated) by contemporary natural science. Similar to Chalmers’ use of the term
‘physical domain’ (Appendix A) we will refer to the latter as physical theories. We
will use the symbol TP to indicate one of these theories and denote its dynamical
variables, background structure, kinematically possible trajectories and solutions by
dP , bP , KP and DP . Finally, we will assume that the physical theories are formulated
in terms of a state space P , which is chosen such that according to the laws of TP , each
p ∈ P determines a unique trajectory in DP . I.e., there is a one-to-one correspondence
between solutions (pt )t∈I ∈ DP and states p ∈ P .
We use the term model to denote a theory which is being proposed. This includes
full-fledged theories which have not received the kind of empirical support usually
required in science, but also “toy-models”, which do not aim for a comprehensive
account of some class of phenomena, but rather serve to study some specific aspect of
it or to test a general idea of how the phenomena could be modelled.
Finally, for use in Section 6, we review the general definition of a symmetry group.
Note that K denotes the kinematically possible trajectories introduced above.
Definition 5.2. A group G is a symmetry group of a theory T [Giu09, p. 43] if and
only if the following conditions are satisfied:
26We use the word ‘variable’ in a general sense here: A variable may represent something as simple
as a natural number just as well as an operator-valued field on some manifold.
MATHEMATICAL MODELS OF CONSCIOUSNESS
29
(a) There is an effective27 action G × K → K of G on K.
(b) This action leaves the the solutions D of T invariant.
If φ is an action of G on K which satisfies the requirements (a) and (b), the pair (G, φ)
is a symmetry of T .
5.2. Models of Consciousness. We now apply Definition 5.1 to give a general account of what a model of consciousness is. To this end, we make use of the epistemic
asymmetry of conscious experience.
Epistemic asymmetry is name of the most fundamental epistemological problem
associated with conscious experience, namely that there “two fundamentally different
methodological approaches that enable us to gather knowledge about consciousness:
we can approach it from within and from without; from the first-person perspective
and from the third-person perspective. Consciousness seems to distinguish itself by
the privileged access that its bearer has to it” [Met95b]. The epistemic asymmetry
implies that there are two epistemically distinct notions of state, one associated with
the third person perspective and one with the first person perspective.
Whereas metaphysical theories of mind may deal with only one of them, and leave
the relation to the other somewhat implicit, models of consciousness may not. Being
scientific hypotheses about how experience relates to the physical domain, the relation
of these two epistemically different states is exactly what models of consciousness need
to address. Even if they take the third-person state to be fundamental (as in physicalist
ontologies), they need to give a description of how the first-person state evolves in
time, i.e. why conscious experience appears to be what it is. And even if they take
the first-person state to be fundamental (as in idealist ontologies), they need to give a
description of how the third person state evolves, i.e. why the outside world appears
to be what it is. The existence of these descriptions are what marks the difference
between formal ideas and scientific models.
The mathematical representation of phenomenal consciousness developed in Section 3 is precisely what describes the first-person perspective in formal terms, with
first person states being elements e of the experience space E. A formal account of
third-person states, on the other hand, is provided by natural science, which is devoted
to the study of phenomena in the third person perspective in the first place. Referring
to theories of natural science by and large as ‘physical theories’, the third-person states
are thus the states utilized in physical theories, e.g. states of neural networks or other
descriptions of the human brain. Using the notation introduced in the last section, we
denote physical theories by TP and their state space by P .
In summary, the above shows that in virtue of consciousness’ epistemic asymmetry,
a model of consciousness needs to prescribe a relation between states of experience and
physical states, independently of which ontology it seeks to express. In formal terms,
this means that it needs to prescribe a relation between the experience space E and
the state space P of a physical theory TP . Applying the minimal formal ingredients
of a scientific theory identified Definition 5.1, this means that the dynamical variables
of a model of consciousness are given by E × P or in fact E n × P with n ≥ 1 in case a
model of consciousness can prescribe more than one experiencing subject for a given
physical state (as e.g. the case with Integrated Information Theory when making use
of the exclusion postulate [OAT14]). This is summarized in the following definition.
27An action is effective (≡ faithful) if and only if no group element other than the identity fixes all
elements of K.
30
J. KLEINER
Definition 5.3. Let TP denote a physical theory. A pre-model of consciousness M is
a theory as in Definition 5.1, where:
(i) The dynamical variables are a Cartesian product of the physical state space P
of TP together with one copy of the experience space E for each experiencing
subject,
d = |E × E {z
× ... × E} ×P .
(5.1)
experiencing subj.
(ii) Kinematically possible trajectories K are a subset of families of dynamical
variables,
n
o
K ⊂ e1t , e2t , ... , ent , pt t∈I ,
(5.2)
where eit ∈ E, pt ∈ P , n is the number of experience spaces in (5.1) and I is
some parameter space.28
We have dubbed this structure a ‘pre-model of consciousness’ since it does not yet
take into account any of the characteristic features of conscious experience, so that
the above mathematical structure may as well describe any other scientific theory that
addresses two variables that are epistemically distinct. An improved definition that
takes into account some of the characteristic features will be given in Section 6.2 below.
Note that by referencing a physical theory TP , this definition takes into account that
models of consciousness are built on and extend, or allow us to derive, physical theories.
An example for the former is again Integrated Information Theory (Section 8.1), and
example for the latter is Conscious Agent Network Theory (Section 8.3). Further
examples are given in Section 8.
Implied by the above definition is that a model of consciousness M comes with
laws L which select from all kinematically possible trajectories K a set of solutions D.
Each solution (e1t , e2t , ... , ent , pt )t∈I ∈ D consists of families (eit )t∈I , which describe
changes of labels for every experiencing subject i ∈ {1, ..., n}, and of a family (pt )t∈I ,
which describes changes of the physical states. The solution thus realizes the mutual
influence of conscious experience and physical states as described by the laws of the
model M .
5.3. Notation. We conclude this section by providing a few abbreviations that will
be of use further below. We will generally use the shorthand
(ēt , pt )t := e1t , e2t , ... , ent , pt t∈I ,
(5.3)
where ēt = (e1t , e2t , ... , ent ), to denote elements of K. Furthermore, we denote by D|P
those trajectories in the physical state space P which are part of solutions D of M ,
D|P := (pt )t∈I (ēt , pt )t∈I ∈ D .
(5.4)
This set is not necessarily equal to the set DP of solutions of the contemporary physical
theory TP . Whether DP = D|P or DP 6= D|P is determined by the laws L of the
28The subset K will typically be determined by demanding families e1 , e2 , ... , en , p
t t∈I to satisfy
t
t
t
some mathematical properties, such as regularity, which are necessary for the laws L of T to be welldefined. To exclude pathological cases, we assume that every label e ∈ E is contained in at least one
family (e1t , e2t , ... , en
t , pt )t∈I ∈ K.
MATHEMATICAL MODELS OF CONSCIOUSNESS
model M , cf. Section 7. Similarly, we define
K|P := (pt )t∈I (ēt , pt )t∈I ∈ K ,
K|E := (ēt )t∈I (ēt , pt )t∈I ∈ K .
31
(5.5)
Since the choice of subset K in (5.2) is a technical condition prior to the application
of any law L, we may for simplicity assume that K|P = KP .
6. Taking Characteristic Features of Conscious Experience into
account
In the previous section, we have derived the general mathematical structure of any
model of consciousness. We have shown that consciousness’ fundamental epistemological feature has some implications regarding the formal structure of any scientific
theory that seeks to address it. However, we have not yet taken into account any of
the characteristic features of conscious experience.
The goal of this section is to do so. To this end, we work with the notion of noncollatability introduced in Section 3. Since non-collatability is implied by ineffability,
privateness and cognitive, linguistic and communicative inaccessibility, the mathematical structure identified here is in fact a consequence of all of these characteristic
features.
Section 6.1, we drive formal mathematical structures of models of consciousness
which are necessary to account for non-collatability. In Section 6.2, we use the result to
give an improved definition of what constitutes a model of consciousness, and show by
means of an example that these structures are also sufficient to address non-collatable
aspects of experience. Finally, in Section 6.3, we compare the improved definition of a
model of consciousness with the direct description of qualia that may otherwise be used,
and show that when in comes to non-collatable aspects of experience, mathematical
models can achieve more than the direct description.
Together, these results show that the formal-mathematical tools developed here can
in fact address the explanatory gap between qualia and natural science identified in
Section 4. Therefore, this section provides the methodology for the grounding of the
scientific study of consciousness outlined in Section 3.4 when it comes to non-collatable
aspects of experience.
6.1. Non-Collatability implies Symmetry. In Section 3.1, we have discussed intersubjectively meaningful references to qualia. We have found that sequences of labels
(e1 , ... , en ) are not empirically well-defined and have shown that the empirically welldefined references to qualia are precisely the equivalence classes (3.8). We now repeat
a similar analysis for pre-models of consciousness. We first introduce the necessary
mathematical tools.
Let s ∈ Aut(E) be an element of the automorphism group (3.5) which describes the
freedom of an experiencing subject to choose labels for the qualia he/she experiences.
Given a solution (ēt , pt )t ∈ D, we may apply s to that experience space in (5.1) which
is associated to the ith experiencing subject. This gives another trajectory
e1t , ... , s(eit ), ... , ent , pt t∈I
(6.1)
32
J. KLEINER
where i ∈ {1, ... , n}. The map which takes (ēt , pt )t to (6.1) is an Aut(E)-action φi on
K, defined as
φi : Aut(E) × K −→ K
s, e1t , ... , eit , ... , ent , pt t 7→ e1t , ... , s(eit ), ... , ent , pt t
(6.2)
where the subscript i indicates on which experience space Aut(E) acts. We may take
into account the freedom of every experiencing subject to relabel his/her qualia by
considering an action φ of
Aut(E)n := Aut(E) × ... × Aut(E)
(6.3)
on K, defined as
φ : Aut(E)n × K −→ K
s1 , ... , sn , e1t , ... , eit , ... , ent , pt t 7→ s1 (e1t ), ... , sn (ent ), pt t .
(6.4)
This action corresponds to the transformations we have considered in Section 3.2.
However, in the context of models of consciousness, this is not the most general form
of relabelling. The most general form is
σ : Aut(E)n × K −→ K
s̄, e1t , ... , ent , pt t 7→ s1 (e1t ), ... , sn (ent ), p′t t ,
(6.5)
where similarly to (5.3) we have used the shorthand s̄ := (s1 , ... sn ), and where p′t is
given by an action σ̃ of Aut(E)n on K|P ,
σ̃ : Aut(E)n × K|P → K|P
s̄, (pt )t 7→ (p′t )t .
(6.6)
This action σ reduces to the action (6.4) if σ̃ is trivial. If σ̃ is non-trivial, σ specifies
that the physical states are relabelled along with the qualia. We will see below (cf.
Section 6.3 for details) that the possibility of a non-trivial σ̃ is what allows us to go
beyond the standard methodology explained in Section 3.3.
Notation: In what follows, we will use the shorthand
s̄(ēt ) := (s1 (e1t ), ... , sn (ent)). As
usual, we denote σ s̄, (ēt , pt )t as σs̄ (ēt , pt )t . Furthermore, we use k := ēt , pt t ∈ K.
Remark 6.1. We remark that each action σ of the form (6.5) has two different meanings: On the one hand, they describe a relabelling of the trajectory k. I.e., σs̄ (k)
describes the same situation as k but with respect to a different choice of labelling.
This is the meaning we have considered in Section 3.1. It is analogous to a change of
reference frame in physics. On the other hand, k′ := σs̄ (k) is simply another trajectory in K, which for s̄ 6= id ∈ Aut(E)n describes a scenario which is genuinely different
to that of k. Whereas according to k, at time t experiencing subject i experiences
the quale he/she has labelled as eit and physical state pt pertains, according to k′
the experiencing subject experiences a quale he/she has labelled si (eit ) and physical
state p′t pertains. This is reminiscent of the distinction between active and passive
transformations in physics. Using this terminology we have:
1. Passive meaning of σ: k and σs̄ (k) are the same trajectory expressed in different labelling.
2. Active meaning of σ: k and σs̄ (k) are different trajectories expressed in the
same labelling.
MATHEMATICAL MODELS OF CONSCIOUSNESS
33
The fact that active and passive transformation have an identical mathematical form is
related to the fact that qualia in virtue of their non-collatability cannot be referenced
intersubjectively.
♦
Next, we use the fact that k and σs̄ (k) describe the same trajectory with respect
to two different choices of labels. Since a different choice of labels must not make a
difference, it follows that if k is a solution of M , σs̄ (k) needs to be a solution as well,
for any choice of s̄ ∈ Aut(E)n . This leads us to the following definition:
Definition 6.2. A necessary condition for a pre-model of consciousness M to be empirically well-defined is that there is an Aut(E)n action (6.5) on K which maps solutions
to solutions, i.e. which satisfies
σs̄ (D) = D
(6.7)
for all s̄ ∈ Aut(E)n .29
Using Definition 5.2, this yields the following lemma.
Lemma 6.3. A necessary condition for a pre-model of consciousness M to be empirically well-defined is that Aut(E)n is a symmetry group of M whose action is of the
form (6.5).
Proof. According to Definition 5.2, Aut(E)n is a symmetry of the model M iff (6.5) is
effective and leaves D invariant. Invariance holds by Definition 6.2. Effectivity holds
because for large enough K (cf. Footnote 28) every action of the form (6.5) is effective:
For any s̄ ∈ Aut(E)n with s̄ 6= id, there exists an eit ∈ E such that si (eit ) 6= eit as well
as a trajectory k ∈ K which contains this label, so that σs̄ (k) 6= k.
If there are only collatable aspects of experience, the automorphism group Aut(E) is
trivial, so that (6.7) is satisfied. Therefore, in this case, all pre-models of consciousness
are empirically well-defined. If there are non-collatable aspects of experience, however,
Aut(E) is non-trivial, so that (6.7) poses a condition that needs to be satisfied, and
Lemma 6.3 shows that the condition is in fact that there is an Aut(E)n symmetry.
Thus Lemma 6.3 establishes the mathematical consequences of non-collatability:
The need of an Aut(E)n symmetry in a model of consciousness. Since the existence of
a symmetry is dependent on the dynamical trajectories of a model of consciousness,
which are in turn determined by its laws L, the condition posed by the lemma is in
fact a requirement with respect to the model’s laws.
6.2. The Mathematical Structure of Models of Consciousness. In the previous section, we have found that the existence of an action (6.5) which constitutes a
symmetry is a necessary condition for a pre-model of consciousness to be empirically
well-defined. We therefore need to include this requirement when specifying what constitutes a general model of consciousness. The result is given in the following definition.
It specifies the necessary structure of any model of consciousness which is to address
any non-collatable aspects of experience, e.g. ineffable, private or inaccessible aspects.
In particular, any model which aims to address any aspect of experience which is referenced by the Nagelian “what it is like” conception (Remark 3.11) necessarily needs
to carry this mathematical structure.
29Here, D is the set of solutions of M introduced above. Note that (6.7) states an identity of sets.
It is equivalent to σs̄ (k) ∈ D for all k ∈ D.
34
J. KLEINER
Definition 6.4. A model of consciousness is a pre-model of consciousness M as defined
in Definition 5.3 which additionally carries an Aut(E)n symmetry of the form (6.5).
We remark again that the additional requirement relate to the laws L of a pre-model
of consciousness M ; the laws need to be such that there is an action σ̃ which turns (6.5)
into a symmetry.
In Section 6.3, we will show that this framework indeed allows us to go beyond
the limitations of the standard approach explained in Section 3.3. To furthermore
make the point that this is a sufficient mathematical framework for the scientific study
consciousness (i.e. sufficient to study qualia proper, cf. Definition 3.19), we show in
the following example that a typical class of ideas put forward in the neuroscience of
consciousness can indeed be formalized in this framework: the idea that qualia are
determined by physical states.
Example 6.5. We consider the hypothesis that qualia are determined by physical states, e.g.
by neural activity in the brain. What exactly constitutes the determination does not matter
in what follows. Examples are type identity theory, where qualia are types of physical states,
or functionalism, where qualia are functional roles which are determined by physical states.
Another example is non-reductive functionalism [Cha95] where the physical states determine
functional roles, which in turn determine qualia via non-reductive laws of nature.
The naive formalization of this idea would be to consider a function (in the mathematical
sense) which specifies which quale an experiencing subject experiences for each physical state
p ∈ P . As we have seen in Section 3.1, the problem with this naive formalization is that qualia
cannot be referenced intersubjectively, so that the specification of a function of this type is only
meaningful up to the equivalence (3.7). In order to properly formalize this idea, we proceed
as follows.
For simplicity, we consider the case of one experiencing subject (n = 1). We assume that a
particular labelling has been fixed by the experiencing subject and assume that with respect
to this labelling a function
f :P →E
p 7→ f (p)
(6.8)
is given, where P is the state space of a physical theory TP as above and E denotes the
experience space. This function expresses in which way qualia are determined by physical
states and could, ideally, be the result of experiments which include the experiencing subject
in question. The state space P could, e.g., refer to neural activity.
Based on this function f , we can define a pre-model of consciousness M . To this end, we
set d = E × P , choose K as the right hand side of (5.2) and define the solutions of the model
in terms of the solutions (pt )t ∈ DP of the physical theory TP as
(6.9)
D = (f (pt ), pt )t (pt )t ∈ DP .
The solutions of this model are thus given by the solutions of the physical theory (e.g. brain
dynamics) equipped with qualia as specified by f .
As it stands, this model is not invariant with respect to relabelling. E.g., if the choice of
labels is being changed according to some s ∈ Aut(E), the solution (f (pt ), pt )t is being mapped
to the solution (s(f (pt )), pt )t which in general will not be an element of D as defined in (6.9).
Thus the theory is not empirically well-defined.
In order to establish empirical well-definedness, there are two choices: First, one could
demand that s(f (p)) = f (p) for all s ∈ Aut(E) and all p ∈ P . This amounts to considering
a function f : P → E\∼, where E\∼ is as in (3.8), which does not achieve the task of
Definition 3.19. The alternative is to specify an action σ̃ as in (6.6), as we now explain.
MATHEMATICAL MODELS OF CONSCIOUSNESS
35
The action σ̃ describes how the physical state changes along with a change of qualia (active
interpretation, cf. Remark 6.1). We observe that a definition of σ̃ as
σ̃s (pt )t := p′t t
with
p′t := f·−1 s(f (pt )) ,
(6.10)
where f·−1 (e) denotes any element of the pre-image f −1 (e) of e, yields for (6.5)
σs (f (pt ), pt )t = s(f (pt )), p′t t = f (p′t ), p′t t ,
where we have used f (p′t ) = f ◦ f·−1 s(f (pt )) = s(f (pt )). Thus if (p′t )t is a solution of TP ,
the action (6.5) with σ̃ as defined in (6.10) is a symmetry of M , so that M is a model of
consciousness, i.e. empirically well-defined.
Thus the idea that physical states determine qualia can indeed be formalized, even though
qualia are defined to be non-collatable aspects of experience. The limitation of this approach
is that the function f , being defined with respect to a particular choice of labelling of the
experiencing subject, cannot be interpreted as specifying the quale which the experiencing
subject experiences along with a particular physical state p. Nevertheless, the formalism
allows us to treat the case that a quale, whichever one it is among the qualia in the equivalence
class [f (q)], is determined by the physical state p. Here, the equivalence class in question is the
one defined in (3.7). A further analysis of the difference to a direct description will be given
in Section 6.3.
♦
We close this section by specifying the empirically well-defined part of the trajectories of a model of consciousness M . This specification is analogous to the specification
of empirically well-defined sequences in (3.6).
As in Section 3.1, we define two trajectories (ēt , pt )t and (ē′t , p′t )t ∈ K to be equivalent
if one can be obtained from the other by relabelling the qualia of the experiencing
subjects. In contrast to Section 3.1, relabelling is defined in terms of the action (6.5),
which for non-trivial σ̃ includes a relabelling of the physical states. We denote this
equivalence by ∼σ ,
(ēt , pt )t ∼σ (ē′t , p′t )t
if and only if there is an s̄ ∈ Aut(E)n
such that ē′t , p′t t = σs̄ (ēt , pt )t .
(6.11)
Note that σ̃, and hence σ, depends on the laws of the model M under consideration.
The empirically well-defined part of the trajectories is given by the quotient set
K ∼ ,
(6.12)
σ
i.e. by the the space of equivalence classes of ∼σ . This space describes the distinctions
which remain once all trajectories are identified which can be mapped to each other
by relabelling the qualia of the experiencing subjects.
6.3. Comparison with Direct Reference. In the previous sections, we have shown
that non-collatability implies that models of consciousness need to carry a particular
symmetry group in order to be well-defined and that this allows us to address qualia
proper, i.e. individual non-collatable aspects of experience. In this section, we compare
the methodology so introduced with what may be called a ‘direct reference’ of qualia:
A description of experimental data or theoretical idea simply in terms of qualia’s labels,
without invoking any of the mathematical details introduced in Definitions 5.3 and 6.4.
Mathematically, a direct reference of the qualia of n experiencing subject is simply
a family
e1t , ... , ent t∈I ,
(6.13)
36
J. KLEINER
where I is some parameter space as above. For example, this could a time-series of
reports of experiencing subjects. Whereas a direct description may ignore the mathematical details of Definitions 5.3 and 6.4, it cannot ignore the ambiguity induced
by non-collatabiltiy of lables, which is fundamental and independent of any of the
mathematical tools introduced in Sections 5 and 6.
In Section 3.3, we have studied this ambiguity and what it implies for references
to qualia in detail, and found that the corresponding well-defined statement is given
by (3.6). In the present notation, this reads
(ēt )t ∼ (ē′t )t
if and only if there is an s̄ ∈ Aut(E)n
i
such that e′t = si (eit ) for all t ∈ I
(6.14)
and
(ēt )t := (ē′t )t (ē′t )t ∼ (ēt )t .
(6.15)
In order to compare this with a model of consciousness, we assume that one wishes to
relate (e.g. statistically analyse) the direct reference of qualia with some properties of
a physical system, e.g. neural activation patterns. We assume that these properties
are determined by states of the physical system and denote the state space as above
by P . Thus the data under consideration is of the form
(6.16)
e1t , ... , ent , pt t∈I .
It could result, e.g., from of verbal reports of experience and simultaneous fMRI scans
or EEG recordings.
In (6.12), we have found that the empirically well-defined trajectories of a model of
consciousness are given by the quotient set
K ∼ .
(6.17)
σ
The following lemma gives the corresponding result for the direct description.
Lemma 6.6. The empirically well-defined trajectories of a direct description of qualia
are given by the quotient set
.
K ∼ ,
(6.18)
φ
where φ is the action (6.4) and where ∼φ is defined as in (6.11).
This lemma states what a direct description of qualia can reference in light of noncollatability. It expresses the epistemic constraints which ineffability, privateness, inaccessibility and other characteristic features which imply non-collatability pose for
any theoretical or experimental account of consciousness.
The difference between (6.17) and (6.18) is that in (6.17) one takes the quotient with
respect to an action that generally acts non-trivially on the physical trajectories (pt )t ,
whereas in (6.18) one takes the quotient with respect to an action that acts trivially
on the latter. We defer further discussion to after the proof.
Proof of Lemma 6.6. In terms of the notation (6.16), the equivalence (6.14) is given
by
(ēt , pt )t ∼ (ē′t , p′t )t
if and only if there is an s̄ ∈ Aut(E)n
such that (ē′t , p′t )t = φs̄ (ēt , pt )t .
(6.19)
According to (6.11), this is precisely the equivalence ∼φ . Hence the empirically welldefined trajectories (6.15) are elements of the quotient set (6.18).
MATHEMATICAL MODELS OF CONSCIOUSNESS
37
The quotient space (6.18) contains the empirically well-defined trajectories that
can be referenced by a direct description of qualia in light of non-collatability. The
quotient space (6.17), on the other hand, gives the empirically well-defined trajectories
of a model of consciousness. The difference between both is determined by the action σ̃
defined in (6.6), which describes how the physical states transform if one relabels the
qualia of an experiencing subject (passive meaning, cf. Remark 6.1), but also how the
physical states change if the qualia of an experiencing subject change (active meaning
in Remark 6.1). It is precisely the possibility of a non-trivial σ̃ which allows the laws
postulated by a model of consciousness to address individual qualia to a certain extent.
The extent to which this is possible is limited by the requirement that (6.5) constitutes
a symmetry of the Model M .
Mathematically, this is reflected in the fact that elements of (6.18) are of the form
(6.20)
[(e1t )t ], ... , [(ent )t ], (pt )t ,
where each equivalence class [(eit )t ] is as in (6.14) and (6.15). This coincides with our
result in Section 3.2 on references to qualia (cf. quotient space (3.8)). The elements
of (6.17), on the other hand, are not of this form: A non-trivial σ̃ results in equivalence
classes in which the physical states are mixed with the labels of the various experiencing
subjects. The empirically well-defined trajectories cannot be separated as in (6.20).
This means that if one chooses a direct description of qualia and investigates the
relation to the physical domain, one first has to consider equivalence classes (6.15)
(for only they are empirically well-defined) and subsequently propose or analyse the
relation to the physical domain. Using a model of consciousness, one may exchange
this order: One may first postulate a relation of qualia and the physical domain, and
subsequently remove the arbitrariness of choosing labels by considering equivalence
classes (6.11). The requirement of there being a symmetry σ simply makes sure that
this relation (the law L of a model of consciousness) is chosen in such a way that
the second step – obtaining an empirically well-defined theory – is possible at all. A
non-trivial σ̃ implies that after the second step, one does not end up with what one
could have obtained using the first procedure right away. This small detail can have
large empirical consequences.
Thus we have shown that models of consciousness are more powerful than direct
references in regard to the scientific study of non-collatable aspects of experience.
Since collatable aspects are always contained in our formalization as a special case
(trivial Aut(E)), we see that mathematical models of consciousness provide a suitable
methodology for the scientific study of consciousness which allows us to take the key
characteristics of ineffability, privateness and cognitive, linguistic and communicative
inaccessibility into account.
We conclude this section by remarking that Lemma 6.6 shows that if σ̃ is chosen as
trivial in Definition 6.4, the result is a direct description of qualia as referenced here.
Thus direct references constitute a special type of model of consciousness, and models
of consciousness are in fact a genuine generalization of direct references.
7. Closure of the Physical
Great care has been taken in the previous sections to motivate all constructions in
an operational, epistemological or phenomenological way, making sure that they are
independent of any metaphysical commitment. Metaphysical choices should only be
made when constructing individual models of consciousness. In this section, we make
38
J. KLEINER
a brief remark about a particularly important metaphysical choice, the closure of the
physical.
The closure of the physical is often called “causal closure of the physical” [Bis05]. It
denotes the idea that “physical laws already form a closed system” [Cha10, p. 17] and
is an important assumption which underlies many philosophical and scientific investigations of consciousness. We mention it here because, as explained in Appendix A,
Chalmers’ grounding of the scientific study of consciousness needs to make use of the
closure of the physical in its definitions, which limits the applicability of this grounding
substantially (cf. Appendix B).
This is different for the grounding put forward in Section 3. Since none of the basic
definitions or formal constructions refers to the closure of the physical in any way, this is
in fact an independent assumption which one may or may not make when constructing
models of consciousness. As a result, the conceptual and formal frameworks developed
here are suitable also to construct models of consciousness which express metaphysical
ideas such as dual aspect monism or property dualism that do not describe the physical
as closed.
In terms of the formalism developed in Sections 5 and 6, the assumption of the
closure of the physical can be stated in a particularly concise form.
Definition 7.1. A model of consciousness M describes the physical as closed if and
only if
D|P = DP ,
(7.1)
where D|P is defined in (5.4) and where DP has been introduced in Section 5.1 to
denote the solutions of the physical theory TP which underlies the model M .
This definition says that a model of consciousness M describes the physical as closed
if and only if the physical trajectories which are determined by the laws of M (as part of
the solutions D) are, as a set, equal to the solutions of the physical theory TP which M
is based on. Whether or not (7.1) is satisfied depends on the laws L postulated by a
particular model.
This concludes our brief excursion to metaphysics. In the next section, we review
several examples and how they relate to the formalism introduced here. A conceptual
point about the closure of the physical is made in Appendix B.1.
8. Examples
In this section, we review some models of consciousness that have been proposed in
the literature and explain how they relate to the formalism introduced in Sections 5
and 6, and to the concepts introduced in Section 3.
8.1. Integrated Information Theory. Our first example is Integrated Information
Theory (IIT) which has been proposed by Giulio Tononi in 2004 [Ton08] and has since
been developed considerably. The current version of that theory [OAT14] consists of
an algorithm whose input is a model of a physical system (together with a state of
that system and including its dynamical laws) and whose output are formal quantities
which give answers to the following three questions: 1. Which parts of the system are
conscious? 2. What are they conscious of? 3. How conscious are they?
To answer the first question, the theory’s algorithm identifies some (mutually disjoint) subsystems of the system. To answer the second question, for each such subsystem S, the algorithm specifies what is called a ‘maximally irreducible conceptual
MATHEMATICAL MODELS OF CONSCIOUSNESS
39
structure’ (MICS). This is a mathematical object of the following kind: Let PS be
the space of probability distributions (or probability measures) over the states of the
subsystem S. A ‘concept’ is an element of the space30
PCS := PS × PS × R+
0 .
The maximally irreducible conceptual structure is an n-tuple of concepts, where n is
determined dynamically by the theory and may vary from subsystem to subsystem.
I.e., it is an element of the “qualia space” [OAT14, graphical illustration in Figure 15]
×n(S)
ES := PCS
.
(8.1)
Finally, in order to answer the third question, the algorithm specifies the integrated
conceptual information Φmax (S) ∈ R+
0 . In summary:
“[T]he central identity [of IIT] is the following: The maximally irreducible conceptual structure (MICS) generated by a [subsystem S] is
identical to its experience. The constellation of concepts of the MICS
completely specifies the quality of the experience (...). Its irreducibility
Φmax specifies its quantity.” [OAT14, p. 3].
The main papers of the theory remain somewhat silent about what exactly they
take the terms “consciousness” or “quality and quantity of an experience” [OAT14] to
mean. The first observation is that ineffable aspects of conscious experience seem to
have played at least a small role in the early development of the theory. E.g., in [Ton08,
p. 229], Tononi notes that “[t]he notions just sketched aim at providing a framework
for translating the seemingly ineffable qualitative properties of phenomenology into
the language of mathematics” (our emphasis). As we have explained in detail in Section 3.1, ineffable aspects of experience cannot be put in a one-to-one correspondence
with mathematical objects, simply because two or more experiencing subjects have
no means to ensure that they have associated the same ineffable aspect of experience
with the same mathematical object. This was the reason for us to introduce experience
spaces E via labels in Section 3.1 and what lead to the requirement of there being a
symmetry that describes relabelling. Following this path, we might take IIT’s “qualia
space” ES to constitute the experience space of qualia as defined in Definition 3.9.
This brings us to the question of how collatable relations between qualia so defined,
such as the ones put forward in Phenomenological Axiom 3.6, are related to the mathematical structure of the space ES . First, we note that the space ES can be equipped
with a metric: For any metric d on PS and using the usual metric on R+
0 , summation
allows us to define both a metric on PCS and ES . This metric can be taken to express
the similarity relation in Phenomenological Axiom 3.6. And indeed, this may again
have been a guiding idea in the development of the theory, “experiences are similar if
their shape is similar” [Ton08, p. 228]. Next, what has been called the “intensity” of
an experience in Example 3.15 corresponds to the “quantity” of experience according
max (S) takes
to IIT. The corresponding mathematical structure is the R+
0 in which Φ
values.
IIT arguably encodes another collatable relation between qualia: Their composition in experience. This is usually formulated as an axiom of IIT which states that
30In the terminology of [OAT14], a concept consists of the maximally-irreducible cause and effect
repertoires of a mechanism M of S together with its integrated information ϕ(M ), provided that the
latter is non-zero [MMA+ 18, Supplementary S1, p. 176].
40
J. KLEINER
“[c]onsciousness is compositional (structured): each experience consists of multiple aspects in various combinations” [OAT14, p. 2]. The composition of the experience of a
subsystem S in terms of more elementary experiences of the same subsystem is modelled by the Cartesian product structure of (8.1) in terms of the concept spaces PCS .
One may interpret the R+
0 that constitutes the last factor of PCS as the intensity of
the the more elementary experiences.
In summary, the basic definitions of IIT seem to fit quite well with the basic definition of the phenomenological grounding put forward in Section 3.4 and IIT can be
taken to constitute a pre-model of consciousness as defined in Definition 5.3. However, in order to take into account the non-collatability of the corresponding aspects
of experience, the symmetry (6.5) has to be implemented. This can be done by simply
swapping the states of the physical system that give rise to particular labels e ∈ ES :
If e1 , ... en ∈ ES are the labels of the conscious subsystems of a system in state p1 ,
and e′1 , ... e′n′ ∈ ES are the labels of conscious subsystems of the system in state p2 ,
for any s̄ ∈ Aut(ES ) which maps the former to the latter, we define the action (6.6)
as σ̃s̄ (p1 ) = p2 . (For details, cf. Example 6.5.) Equipped with this symmetry, IIT
constitutes a model of consciousness as defined in Definition 6.4.
We conclude this example with some conceptual remarks. First of all, we note that
the phenomenological grounding approaches model-building differently than [OAT14].
Whereas in the latter, phenomenological axioms are used to justify the definition of the
algorithm, i.e. the dynamical equations of IIT, the phenomenological grounding uses
phenomenological axioms to model the mathematical space associated with qualia. We
have seen above that an earlier version of IIT put forward in [Ton08] is more aligned
with this perspective. From the perspective of the phenomenological grounding, the
main task would be to motivate the mathematical structure of (8.1) in more detail.
E.g., one could ask why the elementary qualia are labelled by elements of the space
PS × PS and not by a simpler metric space? Does the structure of the former have any
phenomenological interpretation? Questions of this sort may have large consequences
for the further development of the theory because the algorithm of IIT in its current
form makes essential use of elements of PS × PS .
Second, we remark that IIT describes the physical as closed: The dynamical evolution of the physical domain is not changed in any way by the theory. Thus, if one
interprets the theory in Chalmers’ or the phenomenological grounding (or similar ones,
in fact31) the question arises of how the theory’s mathematical postulates – first and
foremost the algorithm it specifies – can be evaluated experimentally at all, for it seems
that all results one can hope to obtain from neuroscientific experiments that scan the
brain (EEG, fMRI, etc) are physical and therefore determined by the physical domain
alone. Put in simple terms, one may ask what one actually learns when collecting
experimental data that is in fact completely determined by the physical domain. This
argument is outlined in more detail in Appendix B.2 and related to the transcendental
argument against the closure of the physical given in Remark B.1. In Section 8.1.1,
we review a modification of IIT which avoids this problem.
31This problem seems to appear in any grounding which exhibits an explanatory gap. One could
try to avoid the problem by interpreting (8.1) in terms of aspects of experience that do not exhibit an
explanatory gap. This, however, would raise the question of why a novel law (the algorithm of IIT)
should determine those aspects, as compared to some form of neural processing.
MATHEMATICAL MODELS OF CONSCIOUSNESS
41
8.1.1. Integrated Information-Induced Quantum Collapse. To overcome the problem
mentioned in the last paragraph, one needs to propose a model of consciousness which
does not postulate the physical as closed. A first model of this kind based on Integrated
Information Theory (IIT) is given in [KR15b]. It refers to an early version of IIT which
only answers the third question of Section 8.1: How conscious is a physical system?
The physical theory on which this model is based is a quantum system with Hilbert
space H and Hamiltonian H. The states are density matrices ρ ∈ L(H). Given a
density matrix ρ, the Quantum Integrated Information is defined as
n
o
,
(8.2)
Φ(ρ) = inf S ρ ⊗N
i=1 Tri ρ
where the infimum is taken over all decompositions of the Hilbert space H, i.e. over
all isomorphisms between H and a Hilbert space of the form H1 ⊗ ... ⊗ HN , where
Tri ρ denotes the reduced density matrix on the Hilbert space Hi (i.e. Tri is a trace
over all Hj with j 6= i) and where finally S(ρkρ′ ) denotes the quantum relative entropy
defined as
S(ρkρ′ ) = Tr ρ log ρ − Tr ρ log ρ′ .
Here, Tr denotes the trace over the whole Hilbert space H. According to this model, (8.2)
specifies how conscious the physical system is in the state ρ.
In order to specify how consciousness in turn influences the physical domain, the
model modifies the time-evolution of the physical system. Whereas in quantum theory,
the time-evolution of a closed system with Hamiltonian H is determined by
i
∂ρ
= − [H, ρ] ,
∂t
~
this models proposes the evolution equation
2
NX
−1
∂ρ
i
hn,m Φ(ρ) · Ln ρL†m − 12 ρL†m Ln + 21 L†m Ln ρ ,
= − [H, ρ] +
∂t
~
n,m=1
where hn,m (Φ(ρ)) are continuous functions of Φ(ρ) which vanish if Φ(ρ) = 0 and
where Lk are operators on H. This is a Lindblad evolution equation which describes,
among other things, models of spontaneous wave function collapse. By choosing the
functions hn,m suitably small, one can make sure that the model is compatible with
physical experiments to date. The model is furthermore experimentally accessible
in that it predicts a collapse rate which is dependent on Φ(ρ), rather than mass or
the number of particles alone, as is the case in other spontaneous collapse models
(cf. [KR15b, Sec. 5]).
8.2. Global Neuronal Workspace Theory. The Global Neuronal Workspace model
(GNW) is, next to Integrated Information Theory, the other model largely favoured
by neuroscientists. In contrast to the latter, however, it is usually stated directly in
terms of brain physiology [DCN11, DKC98]. Even though this is sufficient to make
some specific predictions [DCN11], a more formal model would be desirable, not least
to make a detailed comparison with IIT possible.
In what follows, we outline how a formal model could be constructed which takes
as input any physical system (in a certain class of systems) and determines what the
system is conscious of. To this end, we apply concepts from dynamical systems and
nonbinary information processing whose connection with consciousness has recently
been suggested in [Gri18]. While this attempt is very preliminary, the hope is that a
42
J. KLEINER
genuine formal model can be developed along these lines in future work. A different
goal is pursued in [Wal05].
Let S be a physical system. We assume that it consists of a set Nv of components
(‘vertices’, representing neurons in a neuronal network), each of which is in a particular
state ui (t). Here, t ∈ I denotes time and i ∈ Nv denotes the component in question.
Furthermore, we assume that it consists of a set Ne of directed edges (representing
axons, dendrites, synapses, etc. in a neuronal network), each of which may be in a
state wl (t), l ∈ Ne , (e.g. representing the synaptic strength in a neuronal network).
As usual, we define the parents Pai of the ith component to be those components
from which a directed edge leads to i, and assume i ∈ Pai . Finally, the dynamics
of the system are specified component-wise by a set of ‘update-rules’ (fi )i∈Nv , where
fi determines how the state ui (t) of the ith component depends on the states of its
parents and the states of the edges coming from its parents at previous times.
This system has conscious representations, according to the GNW model, if two necessary conditions are satisfied. The first of these is that the system has “two main computational spaces, each characterized by a distinct pattern of connectivity” [DCN11,
p. 56]. The first computational space is a “processing network, composed of a set
of parallel, distributed and functionally specialized processors or modular subsystems
subsumed by topologically distinct (...) domains with highly specific local or mediumrange connections” [ibid.]. The second computational space is a “a global neuronal
workspace, consisting of a distributed set of (...) neurons characterized by their ability
to receive from and send back to homologous neurons in other (...) areas horizontal
projections through long-range excitatory axons” [DCN11, p. 56].
In order to construct a formal model of consciousness based on this hypothesis, a
definition has to be given which specifies which structure in a physical system counts
as a computational space of each kind, and which not; i.e. a definition of the necessary
“patterns of connectivity” in terms of the mathematical structure of a physical system.
In order to propose a such a definition, we combine the ideas of the GNW model with
some of the ideas put forward in [Gri18], using in particular the similarity between the
processing network described by GNW and the “global directed network consisting
of a large sparsely connected array of much smaller, irreducible subgraphs (ISGs),
representing directed neuron-to-neuron connections” put forward in connection with
consciousness in [Gri18]. Here, an ISG is defined as follows.
[D1] A set NISG ⊂ Nv of components of the physical system constitutes an irreducible subgraph (ISG) if there is a directed edge between any ordered pair of
components in this set [Gri18, p. 25].
The similarity to the processing network of the GNW model comes about due to
the major observations in [Gri18] that each ISG “acts as an analog filter, a dynamical decision-maker (preferring one or another resonant mode), an amplifier, and a
router” [Gri18, p. 27]. In order to specify a necessary pattern for the global neuronal
workspace, we simply require that this is a network with a directed edge going into
and coming out of each ISG, noting that a further requirement on this network will be
added below. In summary, a proposal for the first necessary condition for the system
S to be conscious may be put as follows.
[N1] The system S needs to contain two disjoint subsets Np , Ng ⊂ Nv of components:
First, a set Np of components whose induced subnetwork is a network of ISGs,
were the inter-ISG-connections are feed-forward only. Second, a set Ng of
MATHEMATICAL MODELS OF CONSCIOUSNESS
43
components with directed edges going from this set into all ISGs, and directed
edges going to this set from all ISGs.
Clearly, this definition is preliminary and will have to be improved substantially to
facilitate a full-fledged model to be defined.
In [Gri18], general properties of the state of ISGs are explained, which have been
found in previous work. In particular, if the system satisfies a few conditions, including
the feed-forward property mentioned in definition [N1], the ISGs will typically carry
out “successive pattern recognition tasks exploiting both remembered contextual information and prior expectations from past events (...) as well as the assumption of
the structures (elements) that are identified at [a] previous level” [Gri18, p. 30]. The
result of this task is recorded by a dynamical attractor on the ISG’s components,
which we denote by mk (t), where k indexes the ISGs in the system. These dynamical attractors represent “perceived sources/objects, (...) events, (...) narratives, (...)
scenarios” [Gri18, Fig. 2]. Combining these results with the idea that “[t]he entire
workspace is globally interconnected in such a way that only one such conscious representation can be active at any given time” [DCN11, p. 58], we arrive at a proposal
for the second necessary condition for the system to be conscious:
[N2] The induced subnetwork of Ng needs to be such that at any time t, its state
‘represents’ only one of the ISGs’ dynamical attractors mk (t).
Here, one could, e.g., define the term “represent” to mean that at any time t the state
of the network is (essentially) equal to one of the states mk (t), but other more realistic
choices might be possible.
If both necessary conditions [N1] and [N2] are satisfied at a particular time t, the
GNW model claims that the system S is conscious of the “perceived object, event,
narrative or scenario” mk (t) represented in the global workspace network Ng . Due to
the directed edges from Ng to the ISGs, the state of the ISG k may be made “directly
available in its original format to all other workspace processes” [DN01, p. 15].
Clearly, this outline leaves open various questions. Most notably, the question of
how modes mk (t) of ISGs may relate to experience. Whereas IIT’s qualia space (8.1)
has some structure which relates to phenomenology, it is highly questionable whether
this can be asserted of the states of ISGs, which behave generically like a small number
of “monotonically increasing phase variables” [Gri18, p. 25]. This very question arises
also, albeit in a more indistinct form, if GNW is formulated in terms of neuronal
architecture: How does a “piece of information selected for its salience or relevance to
current goals” [DCN11, p. 56], which is really just a state of some subset of the brain’s
neurons, relate to experience? A proposal to this extent is presented in Section 8.4.
Whereas from a formal modelling perspective, there is some space for further development of the GNW model, it does seem to capture essential neuroscientific evidence
in a simple and very plausible hypothesis: The global workspace. This idea might
ultimately be combined with ideas of IIT or other models to give an explicit account
of how the state of the global workspace relates to experience as we find it.
8.3. Conscious Agent Networks. A model which is based on idealistic metaphysics
is developed in [HP14]. The underlying idea is that what exists are interacting conscious agents, each of which has a fundamental capacity to perceive, decide and act,
and that the interaction between these conscious agents seems to each as if there is an
external outside world. For simplicty, in what follows, we explain a slight more general
version of the model than presented in [HP14].
44
J. KLEINER
In order to explain a single conscious agent C, we first assume that there is a
space W which is external to the conscious agent. One may think of this as states
of some “world” which the agent perceives, but in fact this space is constituted via
interactions with other conscious agents, as explained below. Given
this space W , a
conscious agent is modelled as a five-tuple C := X, G, P, D, A , where X and G are
spaces, and P, D, A are maps,32 interpreted as follows:
◮ X is a space which describes possible experiences of the conscious agent. Each
element x ∈ X represents a particular experience.
◮ G is a space which describes describes dispositions or intentions to act. Each
element g ∈ G corresponds to an action the agent has decided to carry out.
◮ P : W → X is a map which describes the agent’s “process of perception” [HP14,
p. 6]. It specifies what the conscious agent experiences in response to the “world”
being in a particular state w ∈ W .
◮ D : X → G is a map which models how the experience of the agent determines its
disposition for an action, i.e. “the process of decision [in which] a conscious agent
chooses what actions to take based on the conscious experiences it has.” (ibid.).
◮ A : G → W describes how the agent’s disposition for an action “is carried out”, i.e.
how it affects the world: “In the process of action, the conscious agent interacts
with the world in light of the decision it has taken, and affects the state of the
world” (ibid.).
The structure of the spaces W and X, as well as the definitions of the maps P, G
and A are not fixed by the theory, but need to be chosen according to the application.33 Based on
such a choice, the model specifies the dynamically possible trajectories
x(t), g(t), w(t) t∈I as those trajectories which satisfy
x(t + 1), g(t + 1), w(t + 1) = P w(t), Dg(t), Aw(t) ,
where t is chosen as a discrete time parameter, i.e. I := Z.
The central hypothesis of this theory is called “conscious realism”: That “[t]he
world W consists entirely of conscious agents” [HP14, p. 7]. This hypothesis is implemented via networks of conscious agents.
In order to describe a network of n conscious agents, we first assume that for every
conscious agent, a space Xi of possible experiences and and a space Gi of dispositions
to act is given, as well as a “decision map” Di as introduced above. The “external
world” of the ith conscious agent is defined to be the product of the action spaces of
all other conscious agents, i.e.
Wi := G1 × ... × Gi−1 × Gi+1 × ... × Gn .
This choice is motivated by the idealistic idea that what exists are only experiences
and dispositions to act, and that the dispositions to act of some agents determines the
experience of others. I.e., the process of perception of the ith conscious agent is, in
case of a network of conscious agents, given by a map
Pi : Wi → Xi .
32In [HP14], the specification furthermore includes an integer N which counts perception-decisionaction cycles and hence acts as a type of internal “psychological” time, which however we simply
replace by the usual parameter t ∈ I.
33In [HP14], some general assumptions are made: The spaces W , X and G are assumed to be
measurable spaces and the maps P , D and A are chosen to be Markovian kernels, so that for every
element of their domain, each map yields a probability distribution on their co-domain.
MATHEMATICAL MODELS OF CONSCIOUSNESS
45
This allows us to define the dynamically possible trajectories of the network of conscious agents via
xi (t + 1) = Pi (g1 (t), ... , gn (t))
and
gi (t + 1) = Di xi (t) .
If Pi is a partial function defined only for some Gj ∈ Wi , the ith agent is only able to
perceive the dispositions to act of the corresponding other conscious agents. Various
concrete proposals for how to choose Pi are discussed in [HP14, p. 7ff.].
Due to the identification of the “outside worlds” Wi of each conscious agent with the
dispositions to act of others, the action map Ai : Gi → Wi is not necessary to define the
dynamics. In order to satisfy the definition of a conscious agent given above one may
define it formally as the map which takes gi (t) to wi (t + 1) = (g1 (t + 1), ... , gn (t + 1)).
In simple cases (e.g. involving two conscious agents [HP14]) this definition can be
flashed out in terms of combinations of inverses of D and P . In general, it may require
Ai to be time-dependent.
In summary, the various objects the theory assumes in a particular application determine (possibly in a probabilistic manner) the dynamics of a network of conscious
agents. The goal, then, is to specify plausible assumptions which allow us to deduce
formally that “the perception of objects and space-time can emerge from such dynamics” [HP14, p. 1] and to “explore [the model’s] theoretical implications in the normal
scientific manner to see if they comport well with existing data and theories, and make
predictions that are novel, interesting and testable” [HP14, p. 7].
An early example of a result of this kind is given in [HP14, p. 13ff.]. In a nutshell, it
is shown that if the state spaces Xi and Gi are finite, the dynamics of a network of two
conscious agents can be described in terms of an object which bears some similarity
to a quantum-mechanical wave function of a free particle.
From the perspective of models of consciousness as defined in Section 6, two crucial
questions arise:
a) Whether the model would like to address aspects of experience which are noncollatable.
b) Whether the theory would (eventually or in principle) like to make predictions
with respect to experiments which involve (reports of) conscious agents.
An affirmative answer to the first question might be indicated by the remark that the
“qualia X of a conscious agent C are private, in the sense that no other conscious agent
Ci can directly experience X” [HP14, p. 14]. If this is indeed the case, the mathematical
structure of the spaces Xi (and possibly also of Gi , if one holds that intentions to act are
also experiences of some sort) could be defined based on a phenomenological analysis
as explained in Section 3.1. This would, in particular, dismantle the objection that
the “definition of conscious agents could equally well-apply to unconscious agents [so
that the] theory says nothing about consciousness” [HP14, p. 14].
More importantly, if the theory also answers affirmatively to the second question,
the results of Section 6 show that a further mathematical structure is necessary to
ensure that the model is empirically well-defined (Lemma 6.3).
8.4. Expected Float Entropy Minimisation. One of the largest questions at present
left open by the GNW model (Section 8.2) is how the state of the global neuronal
workspace, ultimately a collection of states of individual neurons, relates to experience. Questions of this kind are addressed by the Expected Float Entropy (EFE)
46
J. KLEINER
model developed in [Mas16]. In short, this is a proposal for how (probability distributions of) brain states determine relations among qualia.
In what follows, we review the definition of this model. Every brain state is assumed
to consist of individual elements, each of which can be in a particular state. We denote
the set of all elements (“nodes”) by S and the space of states of each node by V , and
assume both are a finite set. A brain state is thus a map
s:S→V .
(8.3)
E.g., in a neural network, S is the set of neurons and V is the set of possible states
of each neuron. If applied to the GNW model as outlined above, S is the set Ng of
nodes and V denotes the corresponding space of states. In [Mas16], s is called a “data
element”, but we will refer to s simply as ‘state’.
Let ΩS,V denote the space of all states. We assume that a probability distribution p
is given over ΩS,V . The probability p(s) can be interpreted as the probability of the
brain being in state s.
A weighted relation on a set S is a map R : S × S → [0, 1]. Given a set of states
with corresponding probability distribution, the theory developed in [Mas16] allows
one to determine two weighted relations R and U , where R is a weighted relation on
the set S of nodes and where U is a weighted relation on the possible states V of each
node. We will discuss the interpretation of R and U at the end of this example.
The theory determines both U and R as follows. For any state s ∈ ΩS,V , the
composition U (s(.), s(.)) is a relation on S, which we denote as U ◦s. Define the float
entropy fe and expected float entropy efe as
fe(R, U, s) = log2 s̃ ∈ ΩS,V d(R, U ◦s̃) ≤ d(R, U ◦s
(8.4)
X
efe(R, U, p) =
p(s) fe(R, U, s)
(8.5)
s∈ΩS,V
where s ∈ ΩS,V , d is a distance function on the weighted relations on S and where |A|
denotes the cardinality of a set A. The theory proposes “that a system (such as the
brain and its subregions) will define U and R (up to a certain resolution) under the
requirement that the efe is minimized.” I.e. U and R are defined via
efe(R, U, p) = min efe(R̄, Ū, p) ,
(8.6)
R̄,Ū
where the minimum is taken over all relations R̄ on S and all relations Ū on V .
(Existence or uniqueness of minimizers is not discussed in [Mas16].)
Concerning the interpretation of R and U , the theory proposes that if “a brain
state is interpreted in the context of all these relations (...), the brain state acquires
meaning in the form of the relational content of the experience”. If applied to the
visual cortex, the theory aims to explain “perceived relationships between different
colours, the perceived relationships between different brightnesses, and the perceived
relationships between different points in a person’s field of view (giving geometry)”.
These interpretations are supported by several examples in [Mas16], where the theory is applied to pictures, so that S is the set of all pixels and V describes the possible
colour values at each pixel, which implies that U is a relation between colour values
and R is a relation between pixels. The support for these interpretations becomes
more difficult when the theory is being applied, e.g., to the visual cortex, for in this
case U is a relation on the states of the nodes where the nodes could be individual
MATHEMATICAL MODELS OF CONSCIOUSNESS
47
neurons or tuples of neurons in the visual cortex for example, and R is a relation on
the set of these nodes, making it somewhat unclear why in this case a relation U might
give an explanation of, e.g., why “blue appears similar to turquoise but different to
red”.
One can, however, simply take the theory at face value by accepting that the relata
of U and R, whichever mathematical form they take, are (describing) non-collatable
aspects of experience and that U and R are (describing) the relations between them.
Here, the non-collatability is essential for otherwise the identity of some collatable
aspect of experience and elements of the set V or S would be questionable. In short, one
may assume that the relations R and U correspond to the structure of the experience
space E which describes experience.
Several interesting questions are raised by this model. First of all, we note that
since the model aims to explain the relations between aspects of experience, it is fully
compatible with a direct description of qualia as discussed in Section 6.3 and does
not aim for a description of qualia sensu stricto. This raises the question of whether
this model is an alternative to, or rather a complement of, models which do intent to
describe qualia sensu stricto, such as e.g. Integrated Information Theory.
One might conjecture that the relations among aspects of experience might in fact
be nuanced enough to allow us to identify individual qualia by specification of the
relations. In other words, that all orbits of the automorphism group (3.5) are trivial.
Whether or not this is the case is a phenomenological question, which needs to be
answered by a systematic account of the relations between qualia found in experience
and is a priori to any model-building process (just like general properties of an explanandum have to be fixed prior to an explanation). However, since the EFE model
actually specifies the relations between aspects of experience, one can also study which
answer the model itself gives to this question. The upshot of this analysis, which is
presented in the next paragraph, is that if the probability distribution p is invariant
with respect to a transformation (or permutation) of states, which is often the case,
the model does in fact specify relations whose automorphism group has non-trivial
orbits.
Consider a bijective transformation (permutation) of states σ : ΩS,V → ΩS,V which
can be specified in terms of a bijective transformation σS : S → S of nodes and in terms
of a bijective transformation σV : V → V of node-states, i.e. σ(s) := σV ◦ s ◦ σS . The
probability distribution p is invariant with respect to this transformation if p = p ◦ σ,
i.e. if the transformation maps states s to states σ(s) which have the same probability
as the former, p(σ(s)) = p(s). Defining the transformation of the relations U and R
as
U ′ (., .) := U (σV−1 (.), σV−1 (.))
and
R′ (., .) := R(σS (.), σS (.)) ,
(8.7)
and using the fact that the metric d is chosen as one of the dn metrics in [Mas16,
p. 127], i.e. involves summation over all elements of S ×S, (8.4) yields that fe(R, U, s) =
fe(R′ , U ′ , σ(s)). Using the invariance of p and (8.5), this gives
efe(R, U, p) = efe(R′ , U ′ , p) .
48
J. KLEINER
This implies that for any minimizer R, U of (8.6), the pair R′ , U ′ is a minimizer of (8.6)
as well. In other words, the theory only determines minimizers up to transformations (8.7). Assuming uniqueness of minimizers, this in turn implies that the minimizing pair U, V satisfies
U (., .) = U (σV (.), σV (.))
and
R(., .) = R(σS (.), σS (.)) ,
(8.8)
so that σV and σS are relation-preserving bijections, i.e. non-trivial elements of the
automorphism group of the spaces (V, U ) and (S, R), respectively.
Another interesting question is which part of the brain generates those relations
between aspects of experience which we find in experience. This is, to a large extent, a
question which could be answered by simulations of the brain’s neuronal network. If it
turns out that these relations can be reproduced better by a distributed network, this
model may actually be compatible, or even taken as support of, the Global Neuronal
Workspace hypothesis. The underlying challenge here is, of course, to identify the
weighted relations R and U between (states of) neurons with the manifold relations
between aspects of experience. This identification may also hinge on how the probability distributions p(s), which is the only data which enters the definition of R and
U , is interpreted when applied to the brain.
We conclude that this theory is an interesting approach to the mind-matter relation
which might complement more neuroscientific approaches such as the Global Neuronal
Workspace model. Depending on whether a phenomenological analysis confirms that
there are qualia which cannot be distinguished by mere reference to collatable relations,
the model may or may not have to be extended in some form or the other to talk about
the hard problem of consciousness.
9. Conclusion & Outlook
Consciousness is in the focus of research projects around the globe. Empirical as well
as theoretical projects aim to investigate different aspects of experience, ranging from
access consciousness or the unity of a conscious scene to phenomenal consciousness or
the first-person-perspective [Set07]. The starting point of this paper is the observation
that if an aspect of experience is under investigation which cannot be identified over
several experiencing subjects (which cannot be collated), special care is necessary. Any
reference to such aspects of experience, be it in a theoretical account or when giving
reports, is ambiguous and this ambiguity may lead to ill-defined models, erroneous
empirical predictions and misinterpretation of experimental data. A detailed summary
of results is given in Section 2.
In order to develop a well-defined scientific methodology which can be applied to
all aspects of experience, we have used basic phenomenological axioms to specify how
a formal representation of experience can be constructed. The result is a mathematical space which represents some parts of experience (such as visual experiences
or auditory experiences) completely, including both the usual objects of investigation
in cognitive neuroscience as well as qualia. This formal representation of experience
avoids the usual hard cut between parts of experience which represent a difficulty for
the scientific methodology and parts which do not. Both are interwoven in our formal
representation, similarly to position and momentum being two aspects of a quantum
state.
MATHEMATICAL MODELS OF CONSCIOUSNESS
49
We have shown that this mathematical representation of experience allows us to
quantify the ambiguity involved in any reference to experience precisely. This is sufficient to avoid the problems mentioned above and yields a formal mathematical toolbox
which can be applied in empirical or theoretical investigations of consciousness.
In the second part of the paper, we have investigated how individual non-collatable
aspects of experience (qualia “sensu stricto” [OAT14]) can be studied scientifically.
Since there is a fundamental explanatory gap, this question may be considered as
equally relevant to the one addressed in the first step.
The main result of the second part of this paper is that formal models of consciousness can address individual non-collatable aspects of experience if and only if they
carry a specific symmetry group related to the mathematical representation of experience explained above. Because of mathematical details of the action of this symmetry
group, models of consciousness can be used to construct empirically well-defined theories of how individual aspects of experience relate to the physical domain despite the
ambiguity inherent in any reference to the latter.
The results of this paper constitute a grounding of the scientific study of consciousness which is an alternative to other groundings currently in use. It offers a thorough
conceptual and mathematical framework in light of which existing models of consciousness can be interpreted and improved, and based on which new models can be
constructed.
This constitutes a first step in developing a full-fledged conceptual and mathematical foundation for models of consciousness. Further work is necessary to investigate
which mathematical structures are implied by other key characteristics of conscious
experience, most notably the various connotations of subjectivity and intrinsicality,
and to understand whether mathematical structure can be sufficient to account for
any of them.
Acknowledgements: I am grateful for the questions and comments received during presentations of parts of this work at the the LPS Colloquium of the Munich Center for
Mathematical Philosophy, the Mathematical Institute of the University of Göttingen,
the Institute for Theoretical Physics of the University of Hanover, the Modelling Consciousness Workshop in Dorfgastein, the Models of Consciousness Conference in Oxford, the Online Seminar Progress and Visions in the Scientific Study of the MindMatter Relation and the Conceptual Foundations of Science Workshop in Tegernsee.
Most of this work has been carried out while I was employed at the Institute for Theoretical Physics of the Leibniz University of Hanover, and I am very grateful for having
had the opportunity to do so.
Appendix A. Chalmers’ Grounding of the Scientific Study of
Consciousness
The most prominent grounding of the scientific study of consciousness has been
developed by David Chalmers in [Cha96]. Since it is the blueprint of the grounding
proposes in Section 3, we review its essential definitions. Note, however, that the
following outline of Chalmers’ grounding is intended to highlight the relations among
various constituents of his grounding and is not intended to be of an introductory
nature. A good and short introduction to this topic is [Cha10, Ch. 1].
50
J. KLEINER
First, we note that Chalmers’ definition of ‘physical domain’ includes what is often
called ‘material’ or ‘physical’ configurations, such as neurons or brain tissue, as well
as more fundamental physical notions such as “mass, charge, and space-time” [Cha10,
p. 17] or “atoms, electro-magnetic fields, and so on” [Cha96, p. 71]. We thus define
the term ‘physical domain’ to refer to all those phenomena which are currently considered to be the subject of a natural science (physics, chemistry, earth science, biology,
etc. [Wik18a]). Chalmers assumes that:
(A1) “The physical domain is causally closed.” [Cha96, p. 161]
“For every physical event, there is a physical sufficient cause.” [Cha96, p. 125]
Central to Chalmers’ grounding are the terms ‘function’ and ‘structure’. “Here
‘function’ is not used in the narrow teleological sense of something that a system
is designed to do but in the broader sense of any causal role in the production of
behaviour that a system might perform” [Cha10, p. 6]. The term ‘structure’ is used in
a spatiotemporal sense. Together, they constitute, according to Chalmers, the notion
of explanation which is used throughout contemporary science: “One can argue that
by the character of physical explanation, physical accounts explain only structure and
function, where the relevant structures are spatiotemporal structures, and the relevant
functions are causal roles in the production of a system’s behavior.” [Cha10, p. 105f.]
We denote this notion of explanation by (E1). Assuming some laws or theories
relating to the physical domain as given (= accepted by the scientific community by
and large) and referring to them as ‘accepted theoretical notions’, (E1) might be put
as follows:
(E1) An explanation specifies the function and structure of an explanandum in terms
of the the function and structure of accepted theoretical notions.
The crucial aspect of Chalmers’ grounding is to establish, in a consistent and explicit way, that there are phenomena, related to consciousness, to which no function
or structure (as defined above) can be associated. It follows that these phenomena
cannot be explained according to (E1) and hence, if (E1) indeed captures all notions
of explanations which are used throughout contemporary science, that they cannot be
explained by contemporary science. – There is an “explanatory gap” [Lev83, Cha96].
Chalmers refers to these phenomena as “phenomenal concepts”, “phenomenal qualities” or “qualia” [Cha96].34 We refer to these phenomena as ‘phenomenal aspects of
consciousness’:
(D1) Phenomenal aspects of consciousness are those aspects of conscious experience
which do not have a function or structure, where ‘function’ and ‘structure’ are
as defined above.
The key requirement for this definition of what is to be studied by a science of
consciousness to make sense is to establish that there are aspects of experience which
satisfy (D1), i.e. which neither have a spatio-temporal structure nor a causal role in
the production of behaviour. It is the second requirement with respect to which (A1)
is crucial, for (A1) can be utilized to argue that nothing non-physical can have a causal
influence on the physical domain. Therefore, all aspects of experience which do not
have a spatio-temporal structure (e.g. in the Cartesian sense of being non-extended
in space and space-time) automatically satisfy (D1). We will not review the various
34In [Cha10], he prefers to use the term ‘experience’: “Sometimes terms such as ‘phenomenal con-
sciousness’ and ‘qualia’ are also used here, but I find it more natural to speak of ‘conscious experience’
or simply ‘experience.’ ” [Cha10, p. 5].
MATHEMATICAL MODELS OF CONSCIOUSNESS
51
arguments which aim to prove the existence of phenomenal aspects of consciousness
at this point.
Put in terms of Definition 2.1, what is to be studied in the scientific study of consciousness are, according to this grounding, phenomenal aspects of consciousness and
their relation to the physical domain. Since these are, by definition, not accessible
to the usual scientific methodology, Chalmers proposes that the task of a science of
consciousness is to find what he calls “psychophysical laws” [Cha96, p. 127] which
relate the physical domain to phenomenal aspects of consciousness. Due to Assumption (A1) and an underlying stance on the nature of causality “[t]hese laws will not
interfere with physical laws; physical laws already form a closed system. Instead, they
will be supervenience laws, telling us how experience [= phenomenal aspects of consciousness] arises from physical processes” [Cha96, p. 127]. In combination with (E1),
this implicitly points at the major parts of the methodology to be used according to
this grounding.
Chalmers’ grounding raises several questions related to the definition and ontological
status of causality, to the validity of Assumption (A1), to the nature of experiments
in his grounding and to the validity of the subsumed notion of explanation, which we
discuss in Appendix B. The upshot is that there are severe conceptual problems which
make it questionable whether a scientific research program based on this grounding
can be carried out at all.
Furthermore, any scientific approach based on this grounding faces the question of
which mathematical structure one is to use in order to describe phenomenal aspects of
consciousness when formulating “psychophysical laws” [Cha96, p. 127]. Whereas the
physical domain comes with a clear-cut mathematical structure, Chalmers’ grounding
merely asserts that the phenomenal aspects form a set and offers no systematic way
of tying additional mathematical structure to the phenomenology of experience.
This strongly suggest the construction of other groundings of the scientific study of
consciousness. In Section 3, we have introduced a possible alternative which avoids the
above-mentioned problems. Whereas this grounding breaks with several of Chalmers’
main ideas, it retains the key idea of addressing an explanatory gap with mathematical
tools.
Appendix B. Conceptual Problems of Chalmers’ Grounding
In this appendix, we briefly discuss several conceptual issues of Chalmers’ grounding.
These issues are not motivated by metaphysical considerations and are not intended to
have metaphysical implications; they simply arise if one wishes to carry out a scientific
investigation of consciousness based on Chalmers’ grounding. Problems B.1 and B.2
are most crucial and might make it impossible to apply the grounding.
The abbreviations used below have been introduced in Appendix A. For reasons
explained in Appendix B.4, we assume that Assumption (A1) is intended to express
the fact that “physical laws already form a closed system” [Cha96, p. 127].
B.1. Closure of the Physical. Much has been written about Assumption (A1) both
by David Chalmers himself (e.g. [Cha96, Ch. 5] or [Cha10, Ch. 8 and 9]) and by others
(e.g. [Eli09] or [Bis05]). As noted in Section A, this assumption is crucial for Chalmers’
grounding in order to establish that there are aspects of experience which satisfy (D1).
To date, there is no valid argument which shows that Assumption (A1) is wrong,
i.e. that the physical laws of nature cannot “form a closed system”. On the other
52
J. KLEINER
hand, there also is no valid argument that shows that Assumption (A1) is right, i.e.
that the physical laws of nature must form a closed system.35 This assumption also
cannot be backed by analysing opinions or strategies of working physicists, for most
physicists are prepared to accept, or even try to find, modifications of the known laws
of physics due to yet unknown phenomena (e.g. related to dark matter, to quantum
gravity or to dynamical collapse theories, to name just a few). They do not assume
that the known physical laws form a closed system. “Physics itself does not imply its
own causal closure nor is there any proof within physics of its own completeness, so
CoP [causal closure of physics] must be a metaphysical principle” [Bis05, p. 45].
Based on this state of affairs, one might think that both Assumption (A1) as well
as its opposite should be compatible with a scientific approach to consciousness. However, this is not the case, as the following remark shows. Despite the fact that the
physical laws of nature may form a closed system, it seems that Assumption (A1) is
incompatible with a scientific approach to investigate consciousness because it violates
a necessary condition for the possibility of the latter.
Remark B.1. The phenomenological grounding developed in Section 3 allows one
to construct models of consciousness which postulate the physical as closed just as
well as models which do not postulate the physical as closed (several examples of
both are given in Section 8). However, it seems that in both Chalmers’ and the
phenomenological grounding of the scientific study of consciousness, it does not make
sense to assume the closure of the physical because it violates a necessary condition of
the possibility of the scientific study of consciousness itself.
The goal of this remark is to explain in detail why this is so. To this end, we use the
symbol Q to denote that which is to be studied according to the grounding at hand:
In the case of Chalmers’ grounding (CG), Q refers to qualia as defined in (D1) in
Appendix A, whereas in the case of the phenomenological grounding (PG), Q refers to
qualia as defined in Definition 3.9. In both cases, Q thus refers to aspects of conscious
experience.
The above claim rests on two premises. First, that a scientific study of consciousness
is possible only if scientists can communicate about Q at least to some extent. E.g., they
need to be able to agree on Q’s definition and existence, need to be able to communicate
certain general properties of Q (such as Phenomenological Axioms 3.6, 3.12 or 3.14 in
the case of PG) or need to be able to record and exchange data related to Q. This
is the necessary condition for the possibility of the scientific study of consciousness
referred to above, which we abbreviate by NC.
The second premise is that communication is always mediated via communication
channels C which are elements of the physical domain. To give some examples, consider
verbal communication, which is mediated via sound waves, digital communication,
which is mediated via electromagnetic signals, or printed texts, where communication
is mediated via arrangements of molecules and electromagnetic fields.
Due to the second premise, an assumption concerning the closure of the physical
(ACoP) has something to say about communication channels and therefore also about
communication itself. If, in the grounding at hand, ACoP is fleshed out in such a
way that it restricts the relation between Q and communication channels C to such
an extent that communication about Q is impossible, the above claim holds: By the
35Note that no reasons are given in either [Cha96] or [Cha10] for why Assumption (A1) should hold
true.
MATHEMATICAL MODELS OF CONSCIOUSNESS
53
first premise, this implies a violation of a necessary condition of the possibility of a
scientific study of consciousness.
Clearly, whether or not this is the case depends on what one takes to constitute
‘communication’ and which conditions one posits as necessary for something to count
as ‘communication about Q’. To find proper answers to these questions is of course the
goal and task of various parts of philosophy. However, by restricting to a very simple
situation, we may hope to work with a necessary requirement for ‘communication about
Q’ to be possible which is acceptable independently of which notion of communication
one prefers.
The simple situation which we consider is the prototypical scenario of the mathematical theory of communication.36 I.e., we consider a situation where one experiencing
subject S1 (the ‘sender’) formulates a message m1 which expresses some properties
of her experience of Q, such as which particular phenomenal quality she has experienced (in the case of CG) or whether two qualia are similar (in the case of PG).37
Subsequently, this message is being transferred via a communication channel C to another experiencing subject S2 (the ‘receiver’), who after decoding the channel’s signals
obtains a message m2 . We abbreviate this scenario by MTCp (‘p’ for ‘prototypical’).
We denote properties of S1 ’s experience of Q by q and states of the communication
channel C by c. In what follows, we consider functional dependencies between the
quantities q, c, m1 and m2 . In order to define what constitutes a functional dependency
both mathematically and conceptually, we refer to the groundings under consideration:
Both CG and PG’s specification of the task of the scientific study of consciousness
includes the formulation of laws or theories concerning the relation of Q with the
physical domain. Given enough further specifications (such as a model of the communication channel or more comprehensive physical laws), these laws or theories should
be applicable to the MTCp setup. I.e., we may assume that both PG and CG allow
one to construct (or even to deduce) mathematical models of the MTCp setup. The
details of any such model of course depend on various factors, most importantly on
which psychophysical laws (CG) or models of consciousness (PG) one considers. All
that matters at this point is that given any such model, we may identify functional
relationships between the quantities q, c, m1 and m2 :
(F1) A quantity a ∈ {q, c, m1 , m2 } is functionally dependent on a quantity b ∈
{q, c, m1 , m2 } according to some model of the MTCp setup iff according to
this model, a is a non-constant function of b.38
The reasons for focussing on functional dependency in order to argue for the main
claim of this remark are threefold. The first reason is that in both CG and PG,
ACoP implies a restriction of the functional dependencies which may hold between
the quantities q, c, m1 and m2 . Consider first CG. Here, the various formulations
of ACoP differ slightly depending on whether they utilize a notion of causality or
not. However, it seems fair to say that they all intend to express the central claim that
“physical laws already form a closed system” [Cha96, p. 127]. Together with the second
36This is the original (and arguably more adequate [Flo17]) name for ‘information theory’ [Sha48].
37If this is impossible, i.e. if the assumptions of a grounding are such that an experiencing subject
cannot formulate a message which expresses some properties of her experience of Q, this grounding
violates the necessary condition NC as claimed. This may be the case for CG, cf. [Cha10, Ch. 9].
38Here, by ‘constant function’ we simply refer to functions which are formally dependent on b but
whose value remains the same independently of which value b takes. E.g., f (x, y) := x is a constant
function of y.
54
J. KLEINER
premise introduced above, this implies that in any model of the MTCp setup based
on CG, c cannot functionally depend on q. In PG, ACoP implies that any state c of
the communication channel is determined completely by the dynamics of the physical
theory TP , which does not include Q. Therefore, as is the case for CG, in PG ACoP
also implies that c cannot functionally depend on q:
(A2) In both Chalmers’ grounding (CG) and the phenomenological grounding (PG),
the assumption of the closure of the physical (ACoP) implies that the states c
of communication channels cannot be functionally dependent on q.39
The second reason is that functional dependency also seems to allow us to formulate
a fundamental necessary condition for ‘communication about Q’ to be possible:
(C1) A necessary condition for communication between S1 and S2 about Q is that
m2 may depend functionally on q.
The third reason, finally, is that the MTCp is intended to express functional relationships in the first place. In particular, it can be taken to imply by definition that m2 is
functionally dependent only on c and acquires additional functional dependencies only
via c’s functional dependencies.
This concludes the reasoning: A necessary condition of communication about Q in
the MTCp setup is that m2 is functionally dependent on q. By definition of the MTCp
setup it can only be functionally dependent on q via c. CG and PG’s ACoP however
imply that c cannot be functionally dependent on q. Therefore, a necessary condition
of communication about Q is violated, which by the first premise above is a violation
of a necessary condition for the possibility of a scientific study of consciousness.
Clearly, this reasoning does not yet constitute a formal argument. Several of its
suppositions have to be checked carefully for hidden assumptions, which goes beyond
the scope of this remark.40 Nevertheless, it is of importance both with respect to
Chalmers’ grounding (where it raises a thorough problem) and with respect to the
phenomenological grounding (where it is a basis for potential empirical predictions).
We close this remark by pointing out that arguments which try to prove that the
closure of the physical cannot hold in light of empirical facts about our experience
(most notably written or verbal statements which express some fact about conscious
experiences, e.g. bafflement about why consciousness exists [Eli09]) do not seem to
be valid. The problem is simply that we may appear to be expressing facts about
our conscious experience while in fact we are not. Similarly, we may appear to be
communicating about consciousness while in fact we are not. This is the basis for
Chalmers’ efforts to develop a theoretical account of how judgements or statements
about consciousness can be accounted for despite the closure of the physical, cf. [Cha96,
Ch. 5] and [Cha10, Ch. 8 and 9].
39We emphasize again that the notion of ‘functional dependence’ is defined by the respective grounding under consideration. Thus it has a somewhat nomological flavour and does not express, e.g., simple
covariation. The fact that both groundings contain notions of functional dependence is what allows
the present argument to be stated in a comparably concise form.
40To give one example: As explained in Footnote 39, this argument rests on the notion of functional
dependency contained in CG and PG in virtue of psychophysical laws or models of consciousness. In
using these, we have avoided the difficult question of what a functional dependency actually expresses
(i.e. how it is supposed to be defined and interpreted). E.g., when considering q, c, m1 and m2 as
variables, which sort of possible words do they describe? Logically possible worlds, conceivable worlds,
some sort of nomologically possible worlds? In what way can the assumptions of a grounding restrict
these possible worlds and what effect does this have on functional relationships?
MATHEMATICAL MODELS OF CONSCIOUSNESS
55
In contrast, the claim proposed in this remark simply represents a transcendental
argument: Independently of whether reality satisfies the closure of the physical or
not, it does not make sense to engage in a scientific study of consciousness if one
postulates the physical as closed, because the latter violates a necessary condition of
the possibility of the former.
♦
B.2. Experiments. An issue also arises with respect to experiments if one postulates
that “physical laws already form a closed system” [Cha10, p. 17]: Almost all experiments one might wish to perform are rendered meaningless. The reason is simply that
most experimental data (fMRI scans, EEG signals, verbal reports, etc.) is stored on
physical devices (hard drives, paper, sound waves, etc.) and hence subject to physical
laws. If these are postulated to “form a closed system” it follows that the experimental data must be determined by these physical laws alone, independently of which
“psychophysical law” [Cha96, p. 127] correctly describes how phenomenal properties
depend on physical properties.
To see this in more detail, let us assume that two different psychophysical laws L
and L′ have been proposed. The idea behind Chalmers’ and in fact any conception
of the scientific study of consciousness is that experiments have to be carried out in
order to evaluate which of the proposals better describes reality. Accordingly, assume
that an experiment has been designed and carried out which purports to answer this
question, e.g. by checking predictions based on the laws L and L′ . Finally, denote
by d the dataset produced by this experiment.
The term ‘data’ is applicable to any “putative fact regarding some difference or
lack of uniformity within some context” [Flo17], so that one might consider the case
where d actually consists of non-physical quantities, e.g. of differences in one’s own
experience. However, as soon as the data is stored or processed as usual, e.g. on
a hard drive in order to perform statistical analysis, the differences in question have
been transformed into “difference or lack of uniformity” of physical quantities. Since
almost all experiments, even when dealing with verbal reports or similar indications of
conscious experience, perform some sort of statistical analysis, it seems that in almost
all experiments, d eventually is a physical data set in this sense:41 It is ‘stored via’
physical quantities.
If one assumes that “physical laws already form a closed system” [Cha10, p. 17], it
follows that all physical quantities, as well the differences or lack of uniformity they
exhibit, are determined by the laws of physics alone. Applied to the physical quantities
on which d is stored, this statement literally says that the data d is determined by the
laws of physics alone. Put differently, due to the fact that the experimental data d is
stored on a physical device, closure of the physical implies that the data d is completely
independent of whether L or L′ or some completely different psychophysical law best
describes how experience arises from physical processes.
Thus, in summary, the closure of the physical implies that whatever experiment one
performs in order to evaluate psychophysical laws, if it yields data that is stored on
physical devices, the result of the experiment is independent of how experience actually
arises from physical processes, i.e. independent of that which it seeks to study.
41If one assumes that communication between two experiencing subjects is mediated via com-
munication channels that are part of the physical domain (cf. Remark B.1), it follows that every
scientifically meaningful data needs to be transformed into physical data at some point.
56
J. KLEINER
This conclusion holds true even if we concede that every experiencing subject might
interpret the physical dataset d in terms of his/her own experience, so as to give
meaning to this set in a way that a philosophical zombie might not, simply because
if d is independent of which law E best describes how phenomenal properties arise
from physics, the meaning a scientist gives to d will generally be too.42
B.3. Subsumed Notion of Explanation. Chalmers’ grounding builds on, axiomatizes and extends the notion of an explanatory gap that has been introduced by Joseph
Levine in [Lev83]. To this end, Chalmers claims that a specific account of explanation
covers all notions of explanation that are used throughout natural science: An account
in terms of function and structure, cf. (E1) in Appendix A. He subsequently shows
that there are aspects of experience which do not have any of these two properties, so
cannot be explained in terms of natural science as usual. The gist of his grounding is
that they may be addressed by a “new sort of explanation” [Cha96, p. 121] which consists of “new fundamental laws (...) specifying how phenomenal (or protophenomenal)
properties depend on physical properties” [Cha96, p. 127].
The question of how scientific explanation is to be defined has occupied many
philosophers throughout the 20th century [Woo17]. To find a definition which is
general enough to capture the various explanations in science, yet specific enough
to exclude scenarios which are clearly not cases of scientific explanation turns out to
be a very difficult task. Even basic questions such as whether or not causality is to
feature in the definition of explanation (and if yes, which definition of causality), are
still largely debated: “There is considerable disagreement among philosophers about
whether all explanations in science and in ordinary life are causal and also disagreement about what the distinction (if any) between causal and non-causal explanations
consists in.” [Woo17].
This sheds some doubt on Chalmers’ notion of explanation, and the question arises
whether (E1) really covers all, or even the most essential, uses of explanation throughout sciences. This is particularly so with respect to physics, whose notion of explanation seems to be a lot more formal than suggested by the terms ‘function’ and
‘structure’ as defined here. E.g., physics does seem to provide notions of explanation
which can be applied to general dynamical quantities, whether they describe changes
in the behaviour of a system43 or changes of a more general sort. (Chalmers might
42One may be able to avoid this last conclusion by insisting that the meaning attributed to d
by any experiencing subject is dependent on the law E itself and if one furthermore argues that a
conclusion about which law E best fits nature can be deduced from the meaning of d, despite d itself
being determined independently of the former. At the present stage it seems quite unclear how such
an deduction might work, let alone what role an experiment might play in this deduction in the first
place.
43
Recall that the term function refers to “any causal role in the production of behavior that a
system might perform” [Cha10, p. 6]. One could interpret this as referring to “any change in the
behavior of a system” (cf. Appendix B.4). This could, in turn, be taken to mean “any change in
the dynamical properties of a system”, which would change the meaning of the claim that “physical
accounts explain only structure and function” [Cha10, p. 105f.] to the following:
“Any account given in purely physical terms will suffer from the same problem. It will ultimately
be given in terms of the structural and dynamical properties of physical processes, and no matter how
sophisticated such an account is, it will yield only more structure and dynamics. While this is enough
to handle most natural phenomena, the problem of consciousness goes beyond any problem about the
explanation of structure and function [sic], so a new sort of explanation is needed.” [Cha96, p. 121]
However, most or even all aspects of consciousness are dynamical in nature, which implies that
the set of phenomenal aspects of consciousness (Definition (D1)) is, given this redefinition of the term
MATHEMATICAL MODELS OF CONSCIOUSNESS
57
even reluctantly agree to this last observation when claiming that “throughout the
higher-level sciences, reductive explanation works in just this [(E1)] way” [Cha10, p.
7], thus, in this quote, avoiding the claim that (E1) also applies to lower-level sciences,
such as (presumably) physics.)
This is a problem because the legitimacy of proposing “new fundamental laws”
which describe how phenomenal aspects of experience depend on physical properties
[Cha96, p. 127], as compared to a reductive explanation in terms of physical accounts,
is granted, in Chalmers’ grounding, by the existence of an explanatory gap between
phenomenal aspects and contemporary scientific explanation. If scientific explanation
is more powerful than Chalmers assumes, the justification of this explanatory gap
breaks down and it becomes questionable whether this explanatory gap actually exists.
“[A]n explanatory gap (...) cannot be made more precise than the notion of explanation
itself” [Lev83, p. 358].
B.4. Causality. Finally, the question arises of what exactly one should take to constitute causality when applying Chalmers’ grounding. This is so because Assumption (A1) as well as Definitions (E1) and (D1) all relate to causality in an essential
way (the latter via the definition of the term ‘function’, cf. Appendix A).
This question is widely debated both in physics and in the philosophy of causation [Sch16]. It seems fair to say that consensus is missing on basically all aspects of a
definition of causality, including basic questions such as which relata a causal relation
is to refer to and how, given a choice of relata, causality is defined. Whereas this multitude of possible notions of causality may not matter much if one is concerned with
philosophical investigations based on Chalmers’ grounding (one may just restrict to
analyses that apply to every notion of causality), it does matter if one wishes to apply
the grounding. In particular, if one wishes to model, let alone to identify, phenomenal
aspects of experience, one does need to know what exactly the Definition (D1) amounts
to. Since the term ‘function’ used in that definition refers exclusively to causality, the
defining property of phenomenal aspects depends on what one takes causality to be.
Connected to questions of how to define causality is the question of the ontological
status of causality. Does some definition of causality pertain to “reality” or the universe? (In physicists’ terms: Is causality “fundamental”? Does the universe “obey”
one particular definition of causality?) Or is causality rather a tool which can be utilized (by humans, animals, etc. or by information processing systems in general) to
describe some parts of reality well to some extent?44
Chalmers’ grounding is strongly dependent on which answer one gives to this question. E.g., it determines which sort of “influence” of the phenomenal domain on the
physical domain is compatible with the definitions of the grounding, or which type of
‘function’, either empty or trivial. Put differently, with this redefinition the grounding implies that all
or almost all of conscious experience can be addressed by an “account given in purely physical terms”.
What is left out are only non-dynamical aspects of experience (if there are such aspects at all).
44
E.g., [Pea09] holds that “[i]f you wish to include the entire universe in the model, causality disappears because interventions disappear – the manipulator and the manipulated lose their distinction.
However, scientists rarely consider the entirety of the universe as an object of investigation. In most
cases the scientist carves a piece from the universe and proclaims that piece in – namely, the focus
of investigation. The rest of the universe is then considered out or background and is summarized by
what we call boundary conditions. This choice of ins and outs creates asymmetry in the way we look at
things, and it is this asymmetry that permits us to talk about ‘outside intervention’ and hence about
causality and cause-effect directionality.” [Pea09, p. 419f.] “What we conclude (...) is that physicists
talk, write, and think one way and formulate physics in another.” [Pea09, p. 407]
58
J. KLEINER
condition the definition of phenomenal aspects of consciousness constitutes. One may
ignore this problem as long as one applies the grounding to theories of the physical
domain which incorporate some notion of causality, such as, arguably, abstract neural
networks. However, if one wishes to apply the grounding to fundamental physical theories, whose laws do not refer to, or come equipped with, any notion of causality, this
question cannot be ignored.
These issues can be avoided completely if one takes the various uses of the term
“causality” in Chalmers’ grounding to jointly mean that the physical domain is not
changed in any way by phenomenal aspects of consciousness, i.e., that the various uses
of causality simply amount to ensuring that the “physical laws already form a closed
system” [Cha96, p. 127]. This seems to be the actual intention of the author in [Cha96]
and [Cha10], which is why we have fixed this interpretation in the beginning of this
appendix.
References
[Atm16]
[Baa05]
[Bis05]
[Car16]
[Cha95]
[Cha96]
[Cha10]
[Chu81]
[CM21]
[Cra02]
[DCN11]
[DD20]
[Den93]
[DKC98]
[DN01]
[Eli09]
Harald Atmanspacher. On macrostates in complex multi-scale systems. Entropy,
18(12):426, 2016.
Bernard J Baars. Global workspace theory of consciousness: toward a cognitive neuroscience of human experience. Progress in brain research, 150:45–53, 2005.
Robert C. Bishop. The hidden premise in the causal argument for physicalism. Analysis,
66(1):44–52, 2005.
Peter Carruthers. Higher-order theories of consciousness. In Edward N. Zalta, editor, The
Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, fall
2016 edition, 2016.
David J Chalmers. Absent qualia, fading qualia, dancing qualia. In Thomas Metzinger,
editor, Conscious experience. Imprint Academic, 1995.
David Chalmers. The Conscious Mind: In Search of a Fundamental Theory. Oxford Univ.
Press, New York, 1996.
David Chalmers. The Character of Consciousness. Philosophy of Mind. Oxford University
Press, New York and Oxford, 2010.
Paul M Churchland. Eliminative materialism and propositional attitudes. the Journal of
Philosophy, 78(2):67–90, 1981.
David Chalmers and Kelvin McQueen. Consciousness and the collapse of the wave function. Quantum Mechanics and Consciousness. New York: Oxford University Press, forthcoming, 2021.
Carl F. Craver. Structures of scientific theories. In Peter Machamer and Michael Silberstein, editors, The Blackwell Guide to the Philosophy of Science, chapter 4, pages 55–79.
Blackwell Publishers, 2002.
Stanislas Dehaene, Jean-Pierre Changeux, and Lionel Naccache. The Global Neuronal
Workspace Model of Conscious Access: From Neuronal Architectures to Clinical Applications, pages 55–84. Springer Berlin Heidelberg, Berlin, Heidelberg, 2011.
Krzysztof Dolkega and Joe E Dewhurst. Fame in the predictive brain: a deflationary
approach to explaining consciousness in the prediction error minimization framework.
Synthese, pages 1–26, 2020.
Daniel C Dennett. Consciousness explained. Penguin uk, 1993.
Stanislas Dehaene, Michel Kerszberg, and Jean-Pierre Changeux. A neuronal model of
a global workspace in effortful cognitive tasks. Proceedings of the National Academy of
Sciences, 95(24):14529–14534, 1998.
Stanislas Dehaene and Lionel Naccache. Towards a cognitive neuroscience of consciousness:
basic evidence and a workspace framework. Cognition, 79(1):1 – 37, 2001. The Cognitive
Neuroscience of Consciousness.
Avshalom C. Elitzur. Consciousness makes a difference: A reluctant dualist’s confession.
In A. Batthyany and A. C. Elitzur, editors, Irreducibly Conscious: Selected Papers on
Consciousness. 2009.
MATHEMATICAL MODELS OF CONSCIOUSNESS
[Faw14]
59
Bill Faw. Consciousness, modern scientific study of. In Tim Bayne, Axel Cleeremans, and
Patrick Wilken, editors, The Oxford companion to consciousness. Oxford University Press,
2014.
[Flo17]
Luciano Floridi. Semantic conceptions of information. In Edward N. Zalta, editor, The
Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University,
spring 2017 edition, 2017.
[Giu09]
Domenico Giulini. Concepts of symmetry in the work of Wolfgang Pauli. In Harald Atmanspacher and Hans Primas, editors, Recasting Reality: Wolfgang Pauli’s Philosophical
Ideas and Contemporary Science, pages 33–82. Springer Berlin Heidelberg, 2009.
[Gri18]
Peter Grindrod. On human consciousness: A mathematical perspective. Network Neuroscience, 2(1):23–40, 2018.
[HP14]
Donald D. Hoffman and Chetan Prakash. Objects of consciousness. Frontiers in Psychology, 5:577, 2014.
[HT19]
Andrew Haun and Giulio Tononi. Why does space feel the way it does? towards a principled account of spatial experience. Entropy, 21(12):1160, 2019.
[Ken18]
Adrian Kent. Quanta and qualia. Foundations of Physics, 48(9):1021–1037, 2018.
[Ken19]
Adrian Kent. Toy models of top down causation. arXiv preprint arXiv:1909.12739, 2019.
[KH20]
Johannes Kleiner and Erik Hoel. Falsification and consciousness. arXiv preprint
arXiv:2004.03541, 2020.
[KR15a]
Kobi Kremnizer and André Ranchin. Integrated information-induced quantum collapse.
Foundations of Physics, 45(8):889–899, 2015.
[KR15b]
Kobi Kremnizer and André Ranchin. Integrated information-induced quantum collapse.
Foundations of Physics, 45(8):889–899, Aug 2015.
[KT20]
Johannes Kleiner and Sean Tull. The mathematical structure of integrated information
theory. arXiv preprint arXiv:2002.07655, 2020.
[Kue10]
R. Kuehni. Color spaces. Scholarpedia, 5(3):9606, 2010.
[Lev83]
Joseph Levine. Materialism and qualia: The explanatory gap. Pacific Philosophical Quarterly, 64(4):354–361, 1983.
[Lew29]
CI Lewis. Mind and the world order (New York: C. Scribner’s Sons). 1929.
[Mas16]
Jonathan W. D. Mason. Quasi-conscious multivariate systems. Complexity, 21(S1):125–
147, 2016.
[Met95a]
Thomas Metzinger. Conscious experience. Imprint Academic, 1995.
[Met95b] Thomas Metzinger. The problem of consciousness. In Thomas Metzinger, editor, Conscious experience, pages 3–37. Imprint Academic, 1995.
[Met07]
Thomas Metzinger. Grundkurs Philosophie des Geistes Band 1-3. Mentis, 2007.
[MMA+ 18] William G. P. Mayner, William Marshall, Larissa Albantakis, Graham Findlay, Robert
Marchman, and Giulio Tononi. Pyphi: A toolbox for integrated information theory. PLOS
Computational Biology, 14(7):1–21, 07 2018.
[MW]
Thomas Metzinger and Wanja Wiese. Philosophy and Predictive Processing. Number 9783-95857-138-9. MIND Group.
[Nag74]
Thomas Nagel. What is it like to be a bat? The Philosophical Review, 83(4):435, 1974.
[nLa19]
nLab authors. Scott topology, March 2019.
[OAT14]
Masafumi Oizumi, Larissa Albantakis, and Giulio Tononi. From the phenomenology to the
mechanisms of consciousness: Integrated Information Theory 3.0. PLOS Computational
Biology, 10(5):1–25, 2014.
[Oxf18]
Oxford Dictionaries. Entry on ‘Methodology’, 07.06.2018.
[Pea09]
Judea Pearl. Causality: Models, Reasoning, and Inference. Univ. Press, Cambridge, 9.
print edition, 2009.
[Pen94]
Roger Penrose. Shadows of the Mind, volume 4. Oxford University Press Oxford, 1994.
[Per64]
William J. Pervin. Foundations of General Topology. Academic Press, 1964.
[Pre19]
Robert Prentner. Consciousness and topologically structured phenomenal spaces. Consciousness and Cognition, 70:25 – 38, 2019.
[Pro17]
Edoardo Provenzi. Principal fiber bundles and geometry of color spaces. In Claus-Peter
Rückemann, Ramiro Sámano Robles, and Antonio J. R. Neves, editors, The Second International Conference on Advances in Signal, Image and Video Processing, 2017.
60
[Res74]
[Res18]
[Sch38]
[Sch16]
[Set07]
[Sha48]
[SWD04]
[TK20]
[Ton08]
[TTS16]
[Wal05]
[Wik18a]
[Wik18b]
[Win16]
[Woo17]
J. KLEINER
H. L. Resnikoff. Differential geometry and color perception. Journal of Mathematical Biology, 1(2):97–131, Sep 1974.
Pedro Resende. Quanta and Qualia. Talk at the Workshop on Combining Viewpoints in
Quantum Theory, klindly provided by the author, March 2018.
Moritz Schlick. Form and content: An introduction to philosophical thinking. Vienna:
Gerold, 1938.
Jonathan Schaffer. The metaphysics of causation. In Edward N. Zalta, editor, The Stanford
Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, 2016.
A. Seth. Models of consciousness. Scholarpedia, 2(1):1328, 2007.
Claude Elwood Shannon. A mathematical theory of communication. The Bell System
Technical Journal, 27(3):379–423, 1948.
Gaurav Sharma, Wencheng Wu, and Edul N. Dalal. The CIEDE2000 color-difference
formula: Implementation notes, supplementary test data, and mathematical observations.
COLOR Research and Application, 2004.
Sean Tull and Johannes Kleiner. Integrated information in process theories. arXiv preprint
arXiv:2002.07654, 2020.
Giulio Tononi. Consciousness as integrated information: a provisional manifesto. The
Biological Bulletin, 215(3):216–242, 2008. PMID: 19098144.
Naotsugu Tsuchiya, Shigeru Taguchi, and Hayato Saigo. Using category theory to assess
the relationship between consciousness and integrated information theory. Neuroscience
research, 107:1–7, 2016.
Rodrick Wallace. Consciousness: A Mathematical Treatment of the Global Neuronal
Workspace Model. Springer, 2005.
Wikipedia. Entry on ‘Outline of natural science’, 30.05.2018.
Wiktionary. Entry on ‘Methodology’, 06.06.2018.
Rasmus G Winther. The structure of scientific theories. In Edward N. Zalta, editor, The
Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, winter 2016 edition, 2016.
James Woodward. Scientific explanation. In Edward N. Zalta, editor, The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, 2017.
Munich Center for Mathematical Philosophy, Ludwig Maximilian University of Munich, Geschwister-Scholl-Platz 1, 80539 Munich, Germany |
Consciousness Viewed in the Framework of Brain Phase Space Dynamics, Criticality, and
the Renormalization Group.
Gerhard Werner
Department of Biomedical Engineering
University of Texas at Austin
Abstract
To set the stage for viewing Consciousness in terms of brain phase space dynamics and criticality, I will first
review currently prominent theoretical conceptualizations and, where appropriate, identify ill‐advised and flawed
notions in Theoretical Neuroscience that may impede viewing Consciousness as a phenomenon in Physics. I
will furthermore introduce relevant facts that tend not to receive adequate attention in much of the current
Consciousness discourse. As a new approach to conceptualizing Consciousness, I propose considering it as a
collective achievement of the brain' s complex neural dynamics that is amenable to study in the framework of
state space dynamics and criticality. In Physics, concepts of phase space transitions and the Renormalization
Group are powerful tools for interpreting phenomena involving many scales of length and time in complex
systems. The significance of these concepts lies in their accounting for the emergence of different levels of new
collective behaviors in complex systems, each level with its distinct ontology, organization and laws, as a new
pattern of reality. The presumption of this proposal is that the subjectivity of Consciousness is the epistemic
interpretation of a level of reality that originates in phase transitions of the brain‐body‐environment system.
1. Introduction.
The metaphysical tradition, prevailing in the West since the 17th Century, views reality as objective in the
sense of being accessible and, in principle, knowable to all observers. The study of mental phenomena such as
beliefs, desires, thoughts, hopes, fears and conscious states of subjective experience, generally, conflicts with this
position: it excludes the region of reality to which these subjective phenomena belong. Yet, as we know well from
personal experience, these phenomena do exist. To accommodate this fact, Searl [122] proposed that the
phenomena of subjectivity are realized in the brain as an Ontology to which we have epistemic access in the form
of the features of our subjectivity. Expanding on this view, the subjectivity of the Mental is not merely an
epistemological fact; rather the epistemic access points towards a (physical) ontology whose intrinsic properties
( ontic states ) are epistemically accessible as the features of subjectivity (for ontic and epistemic states, see
Section 3.3). Thus, the central goal of this essay is to introduce a point of view that the Ontology of the Subjective
is constituted within the framework, and under the auspices, of the laws of Physics and Biology. Emphatically, this
is not to advocate a "naturalistic dualism" in the manner envisaged, for instance, by Chalmers [30] for closing the
gap between consciousness and the ontology of natural sciences. Rather, it takes into account that biological
systems generally [105] and brains in particular (for a recent review [31]) are complex dynamical systems poised at
criticality. In this case, levels of observation (and, thus, reality) are related by phase transitions which are the
subject of critical phenomena in complex systems of non‐equilibrium statistical mechanics [61, 140]. They are
known to lead to the collective emergence of multiple levels of organization, each with its own ontology, and
epistemic descriptors as the knowledge that is empirically available about a physical system's intrinsic properties.
A specific aspect of this point of view is the idea of the Renormalization group [67] which considers Reality
composed of a hierarchy of levels, related to one another by phase transition, with each level representing a new
ontology as a (qualitatively) new pattern of Reality [112]. I suggest that the Ontology of the Subjective is one of
these levels of Reality, arising in the Renormalization Group transformation of the brain's phase space dynamics;
and that the epistemic access to it constitutes our Subjectivity. For earlier publications discussing aspects of this
line of thought , see [165, 166]. The contention is that the structural features of the Ontology of Subjectivity
correspond to the structure of consciousness, of which some of the phenomenological characteristics are its unity,
the varying degree to which it can be associated with other mental faculties, its association with intentionality,
and self‐attribution and reportability of mental states, to list but a few. To sidestep the constraints of
Phenomenology, the proponents of Neuroscience studies of consciousness proposed several lists
of observationally testable indicators for consciousness in humans [52, 121, 126, 129]. Contravening the charge of
anthropocentrism of consciousness studies, G.M. Edelman et al [51] and D.B. Edelman and Seth [50] discussed a
programmatic framework for determining necessary conditions that would ascertain features of consciousness in
non‐mammalian species: avian species passed the test, but the case for Cephalopodes remains undecided. Seth
[124] asks the important question: " Does Consciousness have a function ? and if so, what might it be “? Interest in
this question is, in part, due to seeking guidance for designing artificial consciousness. In view of consciousness not
being a unitary phenomenon, it is useful to distinguish a primary consciousness for ongoing perceptual‐motor
adaptability in the present from the higher order consciousness of self‐reflection and interpretative functionality.
In any case, however, the capacity for globally mobilizing and integrating separate and independent functions
seems to be a distinctive property [11].
Notice how decisively the proposed outlook differs from the approaches to the 'Mind Body' relation that seeks
to ground subjective phenomena (in part also those of Folk Psychology) reductively in a biological‐physical
ontology. The inadequacy of this attempt is, in part, evident from the strictly internalist stance of the "New Wave
Reductionism " [25,156] of rising popularity. Internalism is also a liability in considering neural and physical
processes or states as correlated [109]. Still more damaging, however, is the confounding of correlation with
causation. The notion of "Neural Correlates of Consciousness" proposed by Koch [86, 148]) as the " minimal
neuronal mechanisms jointly sufficient for any one specific conscious percept" is at best of limited value, at worst
misleading since correlation must not be taken as evidence of causality except in the context of an appropriate
theoretical framework [5,57,58]. But this is missing. In distinction, the Explanatory Correlates of Seth
[123] intended to account for essential features of consciousness, meet this requirement by being anchored in
existing theories. By virtue of this, they can also set the stage for simulation models and possibilities for designing
conscious artifacts [35]. The discussion of these issues will be taken in the following sections.
3. The background
3.1 On current neurobiological theories of consciousness
In general terms, many current theories of brain function attribute a significant role to neuronal synchrony at
a meso‐ or macroscopic level. In the wake of Varela's et al [158] publication on the Brain Web, the coordination
of activity between neurons and neuron assemblies by phase synchrony of neuron firing patterns became an
intensely studied research topic, motivated in part by seeking to ascertain its potential relevance for performance
in psychophysical tests and , possibly, also for consciousness: citing merely a few recent reviews: Varela and
Thompson [157], Melloni et al [98], Uhlhaas et al [155]. A collection of papers in "Dynamic Coordination in the
Brain: from Neurons to Mind" [159] also discusses these and various related aspects. Consequences
of synchronous activity of neurons in the form of neuronal discharge patterns, membrane potentials or as field
potentials may be variously described in terms of coupling or coordinating activity, implying some form of
information sharing. However, synchrony does not necessarily capture the totality of informational sharing that
may obtain, nor do for various reasons, cross correlations or mutual information, as Klinkner et al [84] proved. A
new measure of 'Informational Coherence' for estimating the neural information sharing and coordinated
activity, designed by these authors, is based on mutual information of dynamical states (constructed as causal
state models), rather than merely observables. The analysis by Klinker et al warrants some reluctance to
accepting phase synchrony as meaningful measure, and Tononi and Laureys [147] raise additional arguments for
skepticism regarding the intuitively appealing, though conceptually missing link between neuronal synchrony (or
its informational equivalent) on the one hand, and the "binding" of elements of neural activity to unified
percepts.
Among neurobiological theories of consciousness, (see, for instance [87][ , I turn in the following to the
framework of the Neuronal Group Selection theory [ 52,53] because of its detailed formulation, and the multiple
ramifications it engenders. It features prominently the the dynamic interaction among widely distributed groups of
neurons via reentrant and reciprocal mapping [52], Among those interactions, the thalamo‐cortical system is
thought to occupy a privileged role as the 'dynamic core’. Performance in computational simulations are
interpretable in terms of generally recognized properties of consciousness [129]. The notion of the reentrant
dynamic is also readily compatible with the imaginative synthesis of evidence from Psychology, which Baars
[14] introduced as the ' Global workspace theory' of conscious experience. Baars developed its principles
subsequently to a 'cognitive theory of consciousness' [11,12,13] according to which multiple processors
dynamically constitute context dependent coalitions for gaining access to a limited capacity global workspace. This
principle has become a central component in the Neuronal Group framework as well as related constellation of
ideas. Remarkably, a robot designed on the information flow principles of this theory displayed anticipation and
planning based on internal simulation of interactions with the environment, as well as action selection mediated
by an affect‐like valuation function [132]. I will return to this issue in Section 3.3. In a separate and extended series
of studies, Dehaene, Changeux and colleagues [44,45] implemented global workspace architectures as "neuronal
global workspace" for comparison with performance in psychophysical tests, and to dissect conscious,
preconscious and subliminal forms of processing [43,46]. For a more detailed account of this remarkable
convergence of foundational ideas of varied origin and nature, I refer to my previous review [168]. Finally, Wallace
[161,162] contributed two elegant mathematical theories of the global workspace idea to which I will return in
Sections 4 and 5.
The dynamic core theory engendered seminal ideas designed to probe more deeply some aspects of its
functional repertoire: one of them is the definition of a complexity measure for the brain [153, 154]. The
approach rests on the intuition that cognition would require integration of multiple disparate sources (subsystems)
in the brain [52]. Complexity, in the present context means interdependence among subsystems. It can be
estimated as the statistical measure of Mutual Information shared by subsystems: accordingly, their independence
is reflected in a low, and their integration in a high value of this measure. Computational models featuring
reciprocal and parallel connections among functionally segregated groups of neurons exhibit spontaneously high
values of the Mutual Information shared by the constituent neuron groups, as do cortical connection matrices
based on neuroanatomical data from macaque visual cortex, implemented as dynamical systems [138, 139]: these
cortical connection patters do indeed generate functional connectivity of high complexity, based on highly
connected and coherent functional clusters. Accordingly, the proposed complexity measure does capture the
degree of subsystem integration which can be attributed to correlated patterns of neuronal activity among
different groups of neurons. Moreover, the value of the complexity measure changes with stimulus induced
alterations of functional connectivity, whereby the model's intrinsic complexity comes to match adaptively the
statistical structure of the external input. Subsystem integration, reflected in Mutual Information, is in this setting
thought of as a form of Information processing [152]. However, it must be noted that the proposed complexity
measure is not unique: it is just one of a family of information‐theoretic metrics based on the intuition of
segregation‐integration balance [18]. I will resume this point when discussing an extended framework of theories
and measures of consciousness [128].
Proceeding from the foregoing basis, Tononi and associates [16, 149, 150, 151] formalized and refined in
successive steps the "Information Integration Theory of Consciousness”. At the fundamental level, consciousness is
in this theory viewed as integrated information: 'Integrated information" is understood as information generated
by a system selecting one from among all possible states it can assume. The particular state selected is a function
of two factors: the system's range of a priori available states, and those states that the system a posteriori (i.e.
after receiving some input stimulus) intrinsically, on the basis of its intrinsic architecture and dynamics, identifies
as being causally related to elements of its a priori repertoire. The difference between a priori and a posteriori
selection is the effective information that matters: Integrated Information is then the information generated (i.e.
reduction of uncertainty facing a stimulus) attributable to causal interaction among system elements, in excess of
the information generated by the system's parts. The theory postulates that this quantity is equivalent to the level
of consciousness. Given these assumptions, it is then possible to quantify Integrated Information in models as
function of system architecture and dynamics: although for computational reasons limited to small system size.
Tononi et al show in support of this theory that neurobiologically plausible system architectures are associated
with high levels of Integrated Information. Balduzzi and Tononi [16] then go on to develop mathematical
procedures for characterizing informational relations for dynamical systems of discrete elements which evolve in
state space by Markovian transitions. Information Integration is in this model measured as the information
generated by the system's transition to one particular out of the possible states. The reasoning is thus analogous
to the earlier described (static) measure, but based on evolving shapes in the system's state space, rather than on
static values. Balduzzi and Tononi [16] then argue that these shapes meet criteria for characterizing qualities of
conscious experiences. An initial attempt to model essential aspects of the theory succeeded in generating
meaningful behavior in a virtual robot [66]. Nathan and Barbos [107] apply a network algorithimic procedure to a
computational model of the cortex for obtaining a measure of information integration. Induction of anesthesia
reduces the brain's information integration capacity [93].
The essential point is the thought that a system generates more information than the sum of its parts, and that
"integrated information" measures the extent to which the system's capacity allows this to occur, be it under
static or dynamic regimes, associated with level versus quality of information (consciousness?) , respectively.
Barrett and Seth [19] challenge the approach chosen by Tononi and associates on two counts: first, because of the
practical limitations of the proposed algorithms ;and, second, more fundamentally, because of its restriction to
discrete Markov systems which limits the theory's generality. Barrett and Seth (l.c.) frame information integration
in terms of process (rather than capacity; see above) and present an approach that would be suitable for
simulating sensory‐motor coordination in information rich environments.
In essential difference from Tononi's information‐based approach, Seth and Edelman [127] and Seth [125]
consider population activity patterns as causally effective rather than information bearing representations
underlying computations. The essential elements of their implementation are graph theory and Granger causality
(for details: [47, 69]) in the service of a principled causal connectivity analysis of network dynamics [130]: Granger
causality, revealing recurrent structures of a network in which neurons are embedded, can be applied to
represent interactions between variables as directed edges in graphs. In this form, the causal density of network
dynamics is captured as the fraction of interactions among the nodes that are causally effective. Causal density is
thus a process measure of network differentiation‐integration. The Seth‐Edelman model heeds the admonitions
from the views on embedded Cognition (see for instance: [34]) by taking into account the continuous causal
interactions among brain, body and environment. Behavioral learning via synaptic plasticity is viewed as shaping
the selection of causal pathways in neural populations, in the framework of Edelman's Darwinian selectionist
theory. These general notions are implemented, and put to test, in a brain‐based device that allows the tracking
of (simulated) neuronal activity during behavior in spatial navigation tasks in real environments ( Darwin X :[89],
[90]) . The analysis centers on determining the multiple paths of functional interactions that lead in time to a
selected neuron's activation with influence on behavior (the Reference Neuron, RN). The causal significance of
every connection in the network of interacting paths leading to RN is estimated as Granger Causality , for each
connection based on the activity time series of the pre‐ and postsynaptic neuron, respectively. Removing dead‐end
connections from the Granger network that do not participate in the causal chain leading to RN finally identifies its
causal core. Analyzing the model's patterns of activity revealed several meaningful insights, of which I mention
but two for the principled insight into the network dynamics they afford: variability of neural activity leading to a
given event is the expression of the diversity of dynamic repertoires from among which selection occurs by
pathway shifting in time; and behavioral learning manifests itself at the population level as progressive refinement
and eventual selection of (metaphorically speaking: by sculpting) specific causal pathways (causal cores) from
among the available large repertoire available for neuronal interactions.
In assessing merits and liabilities of the approaches listed in the forgoing, Seth et al [128] conclude that none of
them fully capture the required multidimensional complexity of a neuro‐behavioral system that could account for
objectively measurable features of consciousness; and that all of them have practical limitations. As landmarks for
approaching satisfaction of these requirements, the authors continue to insist on adhering to the theoretical
framework of the Neuronal Group Selection Theory and the concept of the dynamic core, emphasizing its
participation in the transactional processes between organism (model) and the environmentally embedded body.
The decisive issue lies in extending the previously considered notions of complexity. To this end, the notion of a
multidimensional Relevant Complexity is introduced, requiring at least three dimensions of temporal, spatial and
recursive complexity: the former two dimensions, each, covering a wide range of temporal and spatial scales; the
later designating the integration‐differentiation balance across different levels of system description which would
ideally extend from the level of molecular synaptic dynamics to that of reentrant interactions among segregated
brain regions. Implementing this ambitious vision in a brain‐based device would undoubtedly be a large step
towards simulating behavior under conscious guidance.
Considering the idea of Relevant Complexity as pivotal requires paying tribute to the body housing the brain:
following, in part, the seminal insights of Damasio [39] the global Workspace theory acknowledges the role of
emotion and valuative judgments of Consciousness [14] taken already into account in Shanahan's [131] model,
cited earlier. However, it appears that the notion of Core Consciousness which Damasio formulates primarily on
the basis of insights from Clinical Neurology warrants still much more detailed attention. The extensive studies of
the Reticular Activating System of the neurophysiologist of the 50s and 60s , recently reviewed by Steriade [143]
and placed in the context of sleep and arousal ([97], and the elaborate mechanisms of registering the body's
condition [37] assume renewed significance for the somato‐sensing functions and structures, necessary for
consciousness [110]. Evidently, an extended infrastructure subserves interoceptive integration, orchestrating
the cortico‐thalamic dynamics with the interests and capabilities of the body, and its homeostatic regulation, in
the service of consciousness [38].
The next section will briefly sketch some snapshots of the prevailing conceptual landscape of Cognitive
Neuroscience, as part of the intellectual climate with potential influence on the orientation in neurobiology‐of‐
consciousness studies.
3.2: Consciousness "in the wild"
Paraphrasing the title of Hutchins's [75] well known book is intended to announce the target of this section
which is to review, however briefly and not necessarily in any order of priority, what it takes to be conscious under
conditions of ordinary, daily life. You need not be a fan of the criticism of neuroscience discourse leveled by
Bennett and Hacker [22] , nor an ardent Wittgensteinian, to acknowledge that the often encountered locution
“brains think" or “brains are conscious” is drastically wrong and misleading, even if only used as a shortcut or
metaphorically. What IS to be considered conscious are persons, embedded and immersed in a material and social
world in reciprocal interaction by which they are in large measure constituted (for a recent lucid analysis, see
[120]). This does not of course preclude animals from having some forms of consciousness, as mentioned earlier,
but for present purposes it is persons I am having in mind, whose capability for intelligent action includes the
purposeful utilization of resources the environment offers in the form of sensory‐motor interaction on which
numerous authors agree [34, 100, 118, 170]. The extent to which the environment itself is in fact an 'extended
mind" is at present controversial [32, 33, 99,163]
To some extent reminiscent of the submarine navigator in Maturana and Varela's "Tree of knowledge" [96]
Metzinger [101, 102] developed in large detail a Self‐Model Theory of Subjectivity (SMT). Comparing the function
of the human brain with that of a flight simulator, it receives continuous input from sensory organs for
constructing an internal representation of the external reality. Experientially, one is not aware that this internal
representation is but a model of the external reality. Conscious experience and first‐ person perspective of an
individual Self of Consciousness is said to consists in activating this world model, but leaves conditions for
activation unexplained. In this world of virtual reality and embodied simulation, the motor system constructs
goals, actions and intending selves [103], and enters into social traffic [63, 64],, the latter thought to involve
specifically a class of neurons (appropriately called Mirro Neurons) in the forebrain for bi‐directional interaction
with the environment [116]. More generally, Gallese and Lakoff [65] suggest that the sensory‐motor system has
the right kind of structure for characterizing some abstract concepts: their idea of “neural exploitation” refers to
putting the internalized model of sensory‐motor brain mechanism in the service of new roles in Cognition. One
should expect support of SMT from reports of out‐of‐body experience. The principle of these studies is to
experimentally induce multisensory conflicts which would disrupt the pre‐reflective bodily foundations of the
experiential self‐model [27]. Numerous observations do indeed attest that such conditions distort spatial unity,
create the experience of a virtual body outside the regular body boundaries, locate stimuli to body parts other
than those to which the stimuli were applied, to name but a few prominent manifestations. These phenomena
can also be associated with certain neurological disorders, notably of the temporo‐parietal junction of the cortex. I
submit, however, that the relation of experimental and natural body concept aberrations to SMT is ambiguous
inasmuch as it is liable to confound basic perceptual‐cognitive functions with consciousness.
In passing, one might provocatively say: 'Conscious states can be contagious', referring to the imitation
theories of culture [48] and the 'collective states in coupled brains' of which Benzon ( [23], p. 59) speaks as a kind
of group intentionality, specifically having the activity the 'musicking' by ensembles in mind. Grasping the
intentions of others with one's mirror neuron system seems to be quite generally involved in various forms of
interpersonal relations [64, 76, 115].
Returning to basics: the brain's activity responsible for the formation SMT is assumed to consist of complex
information processing and representational mechanisms. It is thus indebted to notions adopted from Cognitive
Neuroscience [102]. In the next section, I will critically discuss some aspects of the role of Neuro‐ and Cognitive
science for consciousness studies.
3.3 Quality control of adoptions and imports from Neuro‐ and Cognitive Science
Consciousness studies can be expected to selectively draw on concepts that are based in the Neuro‐ and
Cognitive Sciences. Representational mechanisms and Information processing, mentioned in the context of SMT,
are examples of such imports whose standing in the source disciplines is far from being uncontroversial. In pat,
the trouble lies there with Informational Semantics [49] and the intuitions it has instilled: it assumes a causal co‐
variation in the sense that event A carries information about event B, and B has now representational content of
A. But law governed processes can virtually be a dime a dozen which makes information ubiquitous, hence the
need for subjecting the relation to constraints supplied by an observer. Grush [71, 72] resolves this conundrum by
defining representations as "entities which are used to stand for something else", with the emphasis on the word
'use’, indicating thereby that the proper role of Representations is for off‐line use, as he suggests, under
counterfactual conditions. Similarly, consider the pattern illustrated by the relation "it is nomically necessary that
litmus (s) turns red (r) in acid " : The informational relation obtains between s's being in a certain way, and r's
being in a certain way; with the source s being F, and the receptor r being G. Then the fact that r is G carries the
information that s is F if and only if it is nomically necessary that s is F given that r is G, subject to ceteris paribus
conditions which need to be constrained by an observer [118]. Both cases support Haugeland's [74]
conclusion that there is no principled way for viewing brain and environment as separate systems, albeit amenable
to functional separability by criteria that need to be supplied by an observer and are thus not intrinsic to the
system.
Problems with Information and associated notions run still deeper: in Computational and System
Neuroscience, data and conclusions are frequently stated in terms of some measure of Information based on
Shannon's Mathematical Theory of Communication (MTG), with the offshoots of Information Theory and the
notion of Information Processing, the latter largely modeled after the Theory of Computation. The validity of
reported data must, thus, depend on their source having met the specific assumptions of the parent Theories: for
instance that the neural data fulfill the premises of MTG such as ergodicity and normality of data distribution.
However, a recent review and re‐appraisal of a large collection of data in the Neuroscience literature shows that
they do not generally meet criteria that accord with these assumptions [31, 164]. Instead, there is substantial
evidence for fractality and self‐similarity in space and time, at all levels of organization, extending from individual
neurons to field potentials, EEG and fMRI records, and to perceptual‐psychophysical and cognitive functions.
Additional recent observational and theoretical studies by Grigolini et al [70] and Allegrini et al 2,3] of global
intermittent dynamics of collective excitations in the resting‐state Electroencephalogram (EEG) add an important
new dimension: the Rapid Transition Processes (RTP), previously identified by Kaplan et al [79] and examined in
great detail by Fingelkurts et al [59, 60] are not only evidence for rapid intermittent transition processes of global
metastable transitions, but they also display multichannel avalanches in the form of simultaneously occurring
RTP’s in several EEG recording sites. The avalanches were identified by applying the method which Beggs and
Plenz [21] had used at the mesoscopic level of neural organization. Several statistical measures of multichannel
avalanches exhibit inverse power‐law statistics. Thus, the avalanches attest to a state of self‐organized criticality at
the level of the whole cortex, and its complexity. On closer analysis, however, it turns out that different cortical
areas have different degrees of complexity. The undoubtedly significant consequences of this observation warrant
further investigation.
Taken together, these various strands of evidence suggest the need for channeling Theoretical Neuroscience
into directions which are at variance with still widely‐held beliefs, reflected in currently authoritative sources such
as for instance: [40, 42].
Finally, recall that Information does not have a natural Ontology and is accordingly, not intrinsic to the brain:
Information, including measures like Entropy etc, refers to the state of knowledge of an observer, and is not
intrinsic to the physics of a system [85]. Nor is programmable computation intrinsically a natural process: rather, it
is putting Physics in the service of the user's syntax and semantics [166].
Atmanspacher and Rotter [5] direct attention to the intricacies of ontic and epistemic states, the former
referring to a physical state as such, as it is independent of an observer; the latter referring to the usually context
dependent knowledge that can be obtained about an ontic state. Relations between ontic and epistemic states
get intricate in hierarchic inter‐level relations : it is then possible that states and properties of a system, viewed
epistemically at one level of description can be considered ontic in the perspective of a higher level (i.e. objects
constituted from descriptions); also, compositions of lower level objects can be epistemically described, but
alternatively also ontically characterized as 'building blocks' of higher level objects [9]. Hence, onticity can be
relative to context. Why are these distinctions important ? Because it depends on them whether a given item can
be considered on the level of reality and subject to laws of nature, or to subjective perspectival discourse. In
complex systems, this distinction is the essential for differentiating (computational) processes intrinsic to ontic
states from transactions among their (epistemic) descriptions. These distinctions are also decisive for inter‐level
relations: for instance, for deriving a description of a system's features from a lower level description, in which
case Bishop and Atmanspacher [26] and Atmanspacher [7] additional contingent contextual conditions are
required. For illustrating the principle of 'contextual emergence' with an example from Physics, consider that
temperature as a novel phenomenal property , by itself alone, cannot be derived from a lower level statistical
mechanical description. However, providing a context in the form of certain stability conditions, temperature
emerges as a novel property at the level of thermodynamics. In this conceptual framework, coarse grained
description of neural activity can provide the necessary conditions for the emergence of (phenomenal) mental
state descriptions at the cognitive level, with stability criteria from Symbolic Dynamics as the context [6]. Note
that this process establishes an epistemic relation between neuro‐ and cognitive dynamics, and concurrently also
resolves the notorious symbol grounding problem [73].
The point of all this is that confounding observer‐relative and intrinsic features of objects or events can become
a notorious source of confusion and false attributions, of which certain uses of 'information', 'computing',
'complexity' [10] and ‘consciousness’ are potentially susceptible victims.
Taken together, these various intrinsic uncertainties in Cognitive Neuroscience and the potential sources of
conceptual fallacies point to the merit of the principled generative‐constructive approach to consciousness studies,
based on brain‐based devices in realistic environments, with embodied nervous system models of transparent
design whose parameters are under the investigator's control, as examples reviewed in Section 3.1 show.
Supplementing judiciously chosen intuitions gleaned from Neurobiology with novel designs and inventions, for
stepwise refinement of model performance can be expected to eventually identify optimal design principles and
competencies required for approximating the capabilities associated with Consciousness. Take the example of
Shanahan's [132] abductive framework for active perception which is another effective way for bypassing the
symbol grounding problem [73] at a practical level, though not the principle of the measurement‐dependent
Heisenberg cut [10] separating the physics of rate‐dependent dynamical states from arbitrary symbols [111]; an
issue commonly neglected in current Cognitive Neuroscience, yet undermining it at a fundamental level.
With the general outlook of this section in mind, I turn next to proposing new aspects of the 'Relevant
Complexity' whose requirement for multidimensionality was the substantive insight of the studies reviewed in
Section 3.1
4. Brain State Space Dynamics and Complexity
Studying neural activity in terms of state space representations has proven of immense heuristic value [160]
for capturing the spatial and temporal dynamics of neural systems at micro‐, meso‐ and macroscopic granularity.
Its merit lies in making conceptual tools of statistical mechanics [140] available for neural data interpretation.
Essentially, it entails associating a measure of neural activity with a point (or region) in a usually higher
dimensional space with following the path taken under the control of evolution equations. The evolution can be
ontically characterized by Langevin type differential equations, or epistemically as Fokker‐Planck type
descriptions of point clouds or trajectory bundles [5] In an application of this principle, Allefeld et al [1] examined
conditions and criteria for, what they consider, the emergence of mental states from brain electrical dynamics. The
State Space approach was also applied by Fell [58] in an attempt to identify neural correlated of consciousness.
However, what is of crucial importance for the topic of this essay is the fact that the dynamics of neural systems
can display at all levels the property of criticality. By this is meant that the path trajectory can undergo
bifurcations due to singularities in certain regions of state space. According to Critical Theory of Statistical Physics,
a system's control parameter can be tuned to undergo sudden phase transitions to new macroscopic
configurations with distinctly novel properties. One aspect of the system reconfiguration consists of a change of
the correlation function among its elements, which characterizes how the value at one point in state space
correlates with the value at another point. While ordinarily extending only over short distances, correlation length
increases with approach to the critical point where it finally becomes infinite, having established a new pattern of
collective interactions among the system's components.
The occurrence of such singularities in neural dynamics and associated state transitions is by now amply
established for all levels of neural system organization, and is documented in recent reviews [31, 164]. Brain phase
transitions between active‐conscious and unconscious states occur at critical values of anesthetic concentration
[144, 145]. Their relevance for human cognition is evaluated by Ref. [137]. In the framework of the Global
Workspace Model, Dehaene [43] presents evidence for non‐conscious local processing within specialized modules
prior to reaching a threshold for "global ignition" underlying conscious reportability; the author does not discuss
these findings in terms of phase transitions, but his description of observations is highly suggestive of a critical
transition in phase space dynamics.
Wallace [161] applied the principle of phase transition to the Global Workspace Model (GWM) of Baars (see
Section 3.1), viewing consciousness associated with a core of limited processing capacity which receives input from
a collection of distributed, specialized processors and (unconscious) contexts. Selecting classical and semiclassical
results from network theory [108], Wallace considers network nodes as processors of the global workspace
model, and network links as mutual information between them . He then for explores conditions under which the
network coalesces by phase transition to a 'giant component': a term taken from Percolation Theory [142]; see
also an illustration in [166] to signify the merger of network nodes to one large assembly. Intuitively, one may
interpret the formation of the Giant complex as a cognitive event. The model illustrates that network topology and
clustering of linkages are tunable parameters of network configurations that are interpretable as descriptors of
psychological concepts. This model offers the advantage of being intuitively better accessible, and bearing more
directly on data from biological network‐ and fMRI studies than does an earlier version which will be referred to in
Section 5.
Although not being part of Wallace's own discussion of the model, it does invite one to speculate on underlying
neural mechanisms of the kind studied in Ref. [88] as phase transitions in neuro‐percolation models. Percolation
also turned up in the theoretical work of Ref. [29] on entirely different grounds and in the context of different
premises: applying field theoretic methods to non‐equilibrium statistical processes in Markovian neural networks,
the authors showed the proclivity of their computational models for dynamical phase transitions of the (directed)
percolation type.
This dynamics of state phase transitions is considered universal in its independence of details at the microscopic
level [140, 136] metaphorically speaking, the system 'forgets' its original microscopic structure and properties by
coarse‐graining, and loses all characteristic length scales for system specific variables: it becomes scale invariant,
i.e. fractal [141]. Dissipative complex systems can attain the state of criticality by self‐organization where the
critical state is an attractor for the dynamics [15]. Applying this theoretical framework, Kitzbichler et al [83]
compared phase synchronization and scaling in critical models with global synchronization in fMRI and MEG
records from humans at rest, and found essential correspondence, suggesting that functional systems in brain exist
in a state of endogenous criticality. Fraiman et al [62] determined brain correlation networks from fMRI voxel‐to‐
voxel correlations under the same computational conditions. Contrasting their human data with correlation
networks from computational simulation of a computational model of magnetic spins (Ising model) showed close
correspondence in all relevant respects, thus also supporting the conjecture of the human brain at rest functioning
near a critical point. In addition, the investigators of this and Ref. [56] were struck by the emergence of nontrivial
collective states in the critical state. As noted before, state transition in physical systems is reflected by the
correlation coefficient at two different points in space and at different times. In their analyses of human data at
successive spatial coarse‐graining steps, they uncovered self‐similarity of correlations, while the temporal pattern
followed as usual 1/f frequency (i.e. power‐law) behavior of the power spectrum. The authors of this study
suggest that the dynamical self‐similarity affords the opportunity for brain states to alternate between metastable
states (attractors) of predominantly short‐ or long distance correlations. Phenomenologically, this suggestion is
reminiscent of the brain's state according to the theory of Extended Coordination Dynamics which,
however, interprets Metastability in a differently: namely as expression of the opposing tendencies of
complementary pairs of brain states, yet functioning collectively as coupled pairs, without ever becoming
attractors for taking control [55, 81, 82]. Although this is not so stated by the authors, one could perhaps
attribute the 'overlapping tendencies' to the sharing of an attractor basin ? In either case, Metastability appears to
subserve local segregation (specialization) and global integration of cortical regions.
The virtual ubiquity of fractal phenomenology in the brain and of many cognitive functions [24, 70, 164], in part
at least accounted for by self‐organizing processes, is a telling signature of their complexity, and supports viewing
the brain poised to criticality where inverse power‐law correlations obtain in space and time. To this, Allegrini et al
[2] added important new evidence, based on studying the 'rapid transition processes' (RTP) in the
Electroencephalogram, originally identified by Kaplan et al [79] these are abrupt changes in EEG amplltude,
interspersed between segments of regular amplitude and wave shape. When recording from several EEG
electrodes concurrently, Figelkurts et al [59, 60] had noted simultaneity of RTP's in several recording channels at a
frequency above the expected statistical average, suggesting collective activity of functional neuron assemblies.
To isolate concurrent spatio‐temporal patterns of RTP's. Allegrini (l.c.) then applied the procedure of Ref. [21]
had successfully used for avalanche detection at the mesoscopic level. The results unequivocally identified a
fractal avalanching process of self‐organized criticality involved in global metastable transitions. Moreover,
regional differences in scaling behavior showed that cortical areas differ in respect to their complexity. We are left
with the question: do these data characterize the status of the default ‐mode network (the subjects were at rest),
or do they speak to the integrated neural dynamics sustaining consciousness?
As is well known, Complexity (together with emergence, information dynamics, and related notions) is a
bottomless barrel of different opinions, idiosyncratic definitions, and perceptions: see for instance: Ref. [113].
However, the focus of interest has shifted towards the nascent field of Complex Networks, situated at the
intersection of graph theory and statistical physics [36]. Their common features are inverse power‐law statistical
distributions, multiplicity of scales, manifestations of non‐stationary, and non‐ergodic statistical processes. A
complex network's capacity for storing information is defined by its statistical entropy [4, 134]. Real networks
occurring in Nature seem to cluster in a relatively narrow region of entropy‐noise space . Internal to a
network, information transfer between network nodes depends on the network topology: it is optimal at or near
the network's phase transition [80]. At this critical point, self‐organized neural networks are also optimized for
cooperative learning [41] and memory function [94; see also [28], section 5.3].
Although also dealing with information transfer, Allegrini's (Il.c.) finding of cortical areas differing in
complexity (see foregoing) introduces an entirely different situation, namely information exchange between
complex networks. A series of theoretical‐mathematical studies, summarized by West et al [171] were concerned
with analyzing how one complex network responds to perturbation by a second complex network: this is viewed
as a form of information transport from one network to another, in principle comparable to stochastic resonance
(for instance: Moss et al[106], except for involving interacting complex networks. In this case, the interaction of
complex System S with complex system P shows that P inherits the correlation function from S; it does so
optimally if S and P have the same power‐law index; hence the designation of this phenomenon as Complexity
Matching Effect. Allegrini et al (l.c.) and Bianconi et al (l.c.) validated the theoretical predictions with data from
Electroencephalogram recordings, statistically representing a non‐ergodic, non‐Poisson renewal process, with
power‐law indices <2 complexity. Clearly, this approach introduces an entirely new perspective for interpreting
and evaluating neurophysiological data at the complex systems level, and challenges prevailing notions of
'information flow' in nervous systems. Applying the theory of the Complexity Matching Effect to dynamic
interactions between central core and modules of the Global Workspace Theory could yield some revealing
insights.
The multiplicity of scales encountered in complex networks invites the application of Renormalization Group
Theory, a set of concepts and methods allowing one to understand phenomena in many fields of physics including
classical statistical mechanics of non‐equilibrium systems. It proves particularly useful to understand
phenomena where fluctuations involving many scales of length and time scales lead to the emergence of new
collective behavior in complex systems. It is the topic of the next Section.
5. Applying the Renormalization Group Theory (RNG)
RNG is both a computational approach and a way of viewing reality. In the former, the Renormalization Group
Theory studies the transformational dynamics by which a complex system space maps onto itself in the stepwise
traversal of the basin of attraction (the critical manifold) towards a critical fixed point. On its path, the system
'defines many worlds' (as Kadanoff [77] aptly put it). The consecutive 'worlds' originate by phase transitions which
occur stepwise along the trajectory of the RNG transformation. They are at the microscopic level its stepwise
generated self‐similar solutions, each reflecting intermediate asymptotic behavior [17] and increasing range of
correlations among constituents. Viewing them as 'different worlds' is due to the fact that the new micro‐level
correlation patterns express themselves at the macroscopic level as qualitatively different novelties, with their
own new laws and new descriptors: think, for instance, of the phase transition from water to ice. At each step,
the essential aspect of the transformation consists in progressive coarse‐graining and change in length scale:
coarse‐graining being the coupling microscopic degrees of freedom to each other to make them effectively act
as single entities with correlation lengths on all lengths, implying scale invariance. In effect, RNG eliminates
microscopic details that are inessential or irrelevant for determining the system's behavior at the critical point (
[20], Ch. 4). This accounts for the Multiple Realizability of complex systems: different microscopic constituents
and dynamics giving rise to identical macroscopic behavior. At the critical point, the system's correlation
coefficients become infinite, reflecting the enormous number of correlations among constituents. At this point,
the 'critical exponents' are universal in the sense that they apply to entire classes of systems which can consist of
materials of very different microscopic constituents. One then speaks of universality classes that have some very
general system properties in common, such as dimensionality and the length of range of interactions. (For
introductory accounts: [68, 173]).
For the purposes of this essay, the focus is on the "Renormalization Group View of the World" [133]. It derives
from the computational approach of RNG inasmuch as it elevates its computational achievements to an epistemic
principle: the punctuated phase transitions along consecutive steps on the trajectory of RNG delimit levels of
qualitatively different realities, each on its own scale and grain of resolution, and governed by its own laws.
Although unrelated to RNG, consider for intuitive appreciation of this phenomenon the following historically
notable illustration: when Anthony von Leuwenhoek in 1674 increased the magnification of his microscope to a
certain (critical !) degree, he saw suddenly a populated world of protists, never previously expected to be part of
the water drop he examined. In other words, he accessed a new level of reality which exhibited its own ontology
and the laws that govern it. In RNG terms, his changing the magnification is equivalent to a step along a
transformation trajectory associated with the change of the grain of observation; in this case to a finer grain.
This much for a stunning entry into a new, previously unknown level of Reality. More commonly in Physics, one is
interested in the opposite direction, which is the case of collective emergence, associated with changing to a
coarser grain with elements at the micro‐level coalescing to larger entities (as if becoming myopic). But the basic
issue is this: like a deck of cards, reality is considered a hierarchy of levels where, on each level, elements are
collectively organized to structures with their own laws, properties, intrinsic scales, and arrangement (correlations)
among its elements; in short: each level is an ontology, as such requiring its own, distinct description. Conversely,
two levels of description will have radically different ontologies. Two consecutive levels are related to one another
by sharp phase transitions. In effect, the transition from a lower to a higher level organizes the distinct objects
of macroscopic levels [92]. The qualitative novelties of consecutive levels arise de novo in virtue of the system
dynamics, and do not stand in any logical relation to one another, hence are not logically deducible from one
another. For instance, our (non‐fundamental) ontology of everyday objects is in this framework ultimately an
intermediate asymptotic approximation (see above) to the more fundamental ontology of quarks and electrons.
An analogous relation obtains between Theories in Physics [78]: as example, the ontology of Newtonian
mechanics may be viewed as a coarse grained version of the more fundamental general‐relativistic ontology
([133], p. 40).
In an application of this conceptual framework to cognition and by implication to consciousness, Wallace [162]
outlined the sketch of a theoretical scheme that utilizes some central ideas of information theory in the context of
a renormalization point of view. Reminiscent of the spirit of the Global Neuronal Workspace, cognitive modules,
here constituted basically as language like structures, would interact by punctuated phase transitions to generate
large coherent structures, locking under renormalization at a critical point.
The objective of this essay, outlined in the Introduction, is to conceive the realm of the Subjective as an
ontology whose epistemic access constitutes the features of experiential subjectivity. In the preceding sections,
several benchmarks are identified which such an approach will have to pass: criticality of Neurodynamics of a
nervous system built by environmental specification (in the spirit of the Darwinian model), accommodation to
aspects of body mechanics and dynamics in the interaction with a bounded region of the environment, and an
adequate account of the body's internal state and homeostatic regulations. I suggest that these different
ingredients, taken together, constitute (at least in part) the multidimensionality of what Seth et al [128] seem to
have in mind as 'relevant complexity'.
Circumnavigating in the foregoing Sections what appear some conceptual hurdles and flawed conclusions from
experimental data and theoretical studies, I arrive at an alternative to prior attempts of rationalizing subjectivity
in Natural Science terms: namely, that the Renormalization world view is useful and plausible conceptual
platform. Specifically, I envision an ontology of Personhood which, in the format of a complex network,
encompasses a representation of the body (somatic as well as autonomic), in association with the brain, and
portions of the (cognitive) environment. The domain of the Subjective is then thought to arise as a complex
network along a trajectory of phase transitions along a path to the fixed point which marks the fully conscious
state. The sequence of consecutive phase transitions would constitute distinct levels whereby each of the
consecutive levels of the Renormalization process presents a collective achievement with different granularity of
resolution in details and different degrees of correlation. The density of correlation among the elements of a level
reaches a maximum at the Fixed Point of RNG where it covers the total range of self‐similar (fractal) scales,
indicative of optimal integration of correlated activity. Note the difference to the more common and more
intuitive view that Consciousness 'emerges' from neural mechanisms as a higher level of organization. The
opposite is proposed here: The levels of subjectivity arise as ontologies in the phase transitions from the more
encompassing (higher level) ontology of the world‐body‐brain Physics so subordinate levels; and can do so
stepwise at consecutive levels of different resolution in details. This may be associated with the taxonomy of
conscious, preconscious and subliminal processing which Dehaene ( l.c. ) describes. As an added bonus, this
approach eliminates the notorious problem of multiple realizability ([20], Ch.5.2 ) since it is an integral aspect of
RNG that many different configurations at one level can become identical at another level, on account of coarse‐
graining.
Although drawn in crude brushstrokes, this sketch of applying the Renormalization view of the world to
Consciousness is in principle amenable to testing its plausibility. This can be pursued by capitalizing in models on
the computational assets of RNG. Refs. [135], [119] and [114] are suitable starting points for studying RNG
transformations of complex networks and offer valuable clues.
As a final implication of Renormalization Group application, note that the forgoing speculations situate the
problem of consciousness in the parent domain of Condense Matter Physics (see for instance: [95]). This suggests
an interesting perspective: for, as stated in the introductory paragraph of his section, the principle of Universality
would permit identifying whether, and to what degree, other materials in Nature may possess features indicative
of a form of consciousness, once it would have been possible to determine the Universality class of which the
ontology of Personhood is a member.
Summary.
The review of the principal current approaches to modeling cognition and consciousness leads me to suggest that
none of them possesses the degree of multidimensionality or ‘Relevant Complexity’ (l.c.) , required for emulating
more than, at best, one or another feature of primary consciousness to an elementary degree. Moreover, I
identify and discuss what I perceive to be basic conceptual flaws in some conventional assumptions that Cognitive
Neuroscience and Neurophysiology bring to the task. Nor are the basic insights of phase space dynamics and
criticality adequately taken into account. In the light of this situation, I propose a different approach: first,
consider the realm of Subjectivity (as hallmark of consciousness) as an ontology in its own right (as Searle
suggested in 1992); and, second, think in terms of the Renormalization Group‘s view of Reality: the subjectivity of
Consciousness is then the epistemic interpretation of the ontology that originates in phase transitions of the brain‐
body‐environment system.
References:
[1] Allefeld C, Atmanspacher H, Wackermann J (2009) Mental states as macrostates emerging from brain electrical
dynamics. Chaos 19: 015102.
[2] Allegrini P, Paradisi P, Menicucci D, Gemignani A (2010) Fractal complexity in spontaneous EEG metastable
state transitions: new vistas on integrated neural activity. Frontiers in Physiology 1: 1‐9
[3] Allegrini P, Bologna M, Grigolini P, West BJ (2006) Response of complex systems to complex perturbation: the
Complexity Matching Effect. arXiv:cond‐mat/06112303v1
[4] Anand K, Bianconi G (2009) Entropy measures for networks. Physical Review E 80: 045102R
[5] Atmanspacher H, Rotter S (2008) Interpreting neurodynamics: concepts and facts. Cogn Neurodyn 2:297‐518
[6] Atmanspacher H, beim Graben P (2007) Contextual emergence of mental states from neurodynamics. Cogn
Neurodyn 2:151‐168
[7] Atmanspacher H (2007) Contextual emergence from physics to cognitive neuroscience. J of Consciousness
Studies 14: 18‐36
[8] Atmanspacher H (2000) Ontic and epistemic descriptions of chaotic sytems. CSYS 1999, American Institute of
Physics.
[9] Atmanspacher H, Kronz F (1999) Many Realisms. Ch. 12 In: J.S. Jordan (eds) Modeling consciousness across
disciplines. Univ Press of America, Lanham, MA, pp 281‐306
[10] Atmanspacher H (1997) Cartesian cut, Heisenberg cut, and the concept of complexity. World Futures 49:333‐
355
[11] Baars BJ (2002) The conscious access hypothesis: origins and recent evidence. Trends in Cogn Sci 6:47‐52
[12] Baars BJ (1997) In the theater of consciousness: the workspace of the mind. Oxford Univ Press, NY
13] Baars BJ, Newman J (1994) A neurobiological interpretation of the Global Workspace Theory. In: A Revonsuo &
M. Kamppinen (ed) Consciousness in Philosophy and Cognitive Neuroscience, L. Erlbaum, Hillsdale NJ, p. 211‐226
[14] Baars BJ (1988) A cognitive theory of consciousness. Cambridge University Press, NY
[15] Bak P, Tang C, Wiesenfeld K (1988) Self‐organized criticality. Physical Review A 38:364‐375
[16] Balduzzi , Tononi G (2009) Qualia: The geometry of integrated information. PLoS Comput Biol 5:e1000462
[17] Barenblatt GI (1979) Similarity, self‐similarity and intermediate asymptotics. Consultant Bureau, NY
[18] Barnett l, Buckley CL, Bullock S (2010) A graph theoretic interpretation of neural complexity.
arXiv:1011.5334v2[q‐bio.NC]
[19] Barrett AB, Seth AK (2011) Practical measures of integrated information for time‐series data. PLoS Comp Biol
7:e1001052
[20] Batterman RW (2002) The Devil in the Details. Oxford University Press, NY
[21] Beggs JM, Plenz D (2003) Neuronal avalanches in neocortical circuits. J Neurosci 23: 11167‐11177
[22] Bennett MR, Hacker PMS (2003) Philosophical foundations of neuroscience. Blackwell, Oxford
[23] Benzon WL (2001) Beethoven’s anvil: music in mind and culture. Basic Books, NY
[24] Bianconi S, Ignaccolo M, Rider MS, Ross MJ, Winsor P, Grigolini, P (2007) Brain, music and non‐Poisson
renewal processes. Physical Review E 75:061911
[25] Bickle J (2006) Reducing Mind to molecular pathways: explicating the reductionism implicit in current cellular
And molecular Neuroscience. Synthese 151:411‐434
[26] Bishop RC, Atmanspacher H (2006) Contextual emergence in the description of properties. Foundations of
Physics 36: 1753‐1777
[27] Blanke O, Metzinger T (2008) Full‐body illusions and minimal phenomenal selfhood. Trend Cogn Sci 13:7‐13
[28] Boccaletti S, Latora V, Moreno Y, Chavez M, Hwang DU (2006) Complex Networks: structure and dynamics.
Physics Reports 424:175‐308
[29] Buice M., Cowan J (2007) Field‐theoretic approach to fluctuation effects in neural networks. Physical Review E
75:051919
[30] Chalmers D (1996) The Conscious Mind: in search of a fundamental theory. OUP, NY.
[31] Chialvo DR (2010) Emergent complex neural dynamics. Nature Physics 6: 744‐750.
[32] Clark A (2008) Supersizing the mind. OUP, NY
[33] Clark A, Chalmers D (1998) The extended Mind. Analysis 58:7‐19
[34] Clark A (1997) Being there: putting brain, mind and world together again. Cambridge University Press,
Cambridge GB
[35] Clowes RW, Seth AK (2008) Axioms, properties and criteria: roles for synthesis in the science of consciousness.
Artificial Intelligence in Medicine, doi:10.1016/j.artmed.2008.07.009
[36] Costa L.Da F, Rodrigues FA, Travieso G, Villas Boas PR (2007) Characterization of complex networks: a survey
of measurements. Advances in Physics 56:167‐242
[37] Craig AD (2002) How do you feel? Interoception: the sense of the physiological condition of the body.
Neuroscience 3:655‐666
[38] Damasio AR (2010) Self comes to mind: constructing the conscious brain. Pantheon Books, NY
[39] Damasio AR (1999) The feelings of what happens: body and emotion in the making of consciousness. Harcourt
Brace & Co, NY
[40] Dayan P, Abbott LF (2001) Theoretical neuroscience. MIT Press, Cambidge, MA
[41] De Arcangelis L, Herrmann HJ (2010) Learning as a phenomenon occurring in a critical state.
arXiv:1003.1200v1 [q‐biol.NC]
[42] deCharms RC, Zador A (2000) Neural representation and the cortical code. Annu Rev Neurosci 23:613‐647
[43] Dehaene S (2009) Conscious and nonconscious processes: distinct forms of evidence accumulation ? Seminar
Poincare XII :89‐114
[44] Dehaene S, Sergent C, Changeux J‐P (2003) A neuronal network model linking subjective reports and objective
physiological data during conscious perception. PNAS, USA, 100:8520‐8525
[45] Dehaene S, Naccache L (2001 a) Towards a cognitive neuroscience of consciousness: Basic evidence and a
workspace framework. Cognition 79: 1‐37
[46] Del Cul A, Baillet S, Dehaene S (2007) Brain dynamics underlying the nonlinear threshold for access to
consciousness. PLoS Biology 5:e260
[47] Ding M, Chen Y, Bressler SL (2006) Granger causality: basic theory and applications in neuroscience. Ch. 17
in:B. Schelter, M. Winterhalder, J. Timmer (eds) Handbook of time series analysis. Wiley‐VCN.
[48] Donald M (1995) Origins of the modern mind. Harvard University Press, Cambridge, MA
[49] Dretske F (1981) Knowledge and the flow of information. MIT Press, Cambridge, MA
[50] Edelman DB, Seth AK (2009) Animal consciousness: a synthetic approach. Trends in Neuroscience 32:476‐484
[51] Edelman DB, Baars BJ, Seth AK (2005) Identifying hallmarks of consciousness in non‐mammalian species.
Consciousness and Cognition 14:169‐187
[52] Edelman GM (2003) Naturalizing consciousness: a theoretical framework. PNAS, USA, 100:5520‐5524
[53] Edelman GM (1989) The remembered Present: a biological theory of consciousness. Basic Books, NY
[54] Edelman GM (1987) Neural Darwinism: the theory of neuronal group selection. Basic Books, NY
[55] Engstrom DA & Kelso JAS (2008) Coordination dynamics of the complementary nature. Gestalt Theory 30:121‐
134
[56] Expert P, Lambiotte R, Chialvo D, Christensen K, Jensen HJ, Sharp DJ, Turkheimer F (2010) Self‐similar
correlation function in brain resting fMRI. arXiv::1003.3682v1 [q‐bio.NC]
[57] Fell J, Elger C, Kurthen M (2004) Do neural correlates of consciousness cause conscious states? Medical
hypotheses 63:367‐369
[58] Fell J (2004) Identifying neural correlates of consciousness: the state space approach. Consciousness and
Cognition 13:709‐729
[59] Fingelkurts AA, Fingelkurts AA, Kaplan AY (2003) The regularities of the discrete nature of multivariability of
EEG spectral patterns. Int J Psychophyisol 47:23‐41
[60] Fingelkurts AA, Fingelkurts (2004) Making Complexity simpler: Multivariability and Metastability in the brain.
Internat.J. Neurosci. 114:843‐862.
[61] Fisher ME (1998) Renormalization group theory: its basis and formulation in statistical physics. Reviews of
Modern Physics 70:653‐681
[62] Fraiman D, Balenzuela P, Foss J, Chialvo D (2009) Ising‐like dynamics in large‐scale functional brain networks.
Physical Review E 79:061922
[63] Gallese V (2009) Mirror neurons, embodied simulation, and the neural basis of social identification.
Psychoanalytic Dialogues 19:519‐536
[64] Gallese V, Eagle M, Migone P (2007) Intentional attunement: mirror neurons and the neural underpinnings of
interpersonal relations. J American Psychoanalytic Association 55:131
[65] Gallese V, Lakoff G (2005) The brain’s concepts: the role of the sensory‐motor system in conceptual
knowledge. Cognitive Neuropsychology 22:455‐479
[66] Gamez D (2010) Information integration based predictions about the conscious states of a spiking neural
network. Consciousness and Cognition 19:294‐310
[67] Goldenfeld N (1992) Lectures on phase transitions and the renormalization group. Addison Wesley, Reading,
MA
[68] Goldenfeld N, Martin O, Oono Y (1989) Intermediate asymptotics and renormalization group theory. J
Scientific Computing 4:355‐372
[69] Gourévitch B, Bouquin‐Jeannés R, Faucon G (2006) Linear and nonlinear causality between signals: methods,
examples and neurophysiological applications. Biological Cybernetics 95:349‐369
[70] Grigolini P, Aquino G, Bologna M, Lukovic M, West B (2009) A theory of 1/f noise in human cognition. Physica
A 388:4192‐4204
[71] Grush R (1990) The semantic challenge to computational Neuroscience. Ch.8 in: PK Machamer, R.Grush, P.
McLaughlin :Theory and method in the neurosciences. Univ Pittsburgh Press, Pittsburgh, PA
[72] Grush R (1997) The architecture of representation. Philosophical Psychology 10: 5‐23
[73] Harnad S (1990) The symbol grounding problem. Physica D 42:335‐346
[74] Haugeland J (1995) Mind embodied and embedded. In: J. Haugeland. Having Thought, Harvard University
Press, Boston MA
[75] Hutchins E (1995) Cognition in the wild. MIT Press, Cambridge, MA
[76] Iacoboni M, Molnar‐Szakacs I, Gallese V, Buccino G, Mazziotta JC, Rizzolatti G (2005) Grasping the intentions of
others with one’s own mirror neuron system. PLoS Biology 3:79
[77] Kadanoff LP (2011 a): Theories of Matter: Infinities and Renormalization. In: Oxford Hdbk. Of the Philosophy of
Physics, edit. R. Batterman, Oxford Univ. Press.
[78] Kadanoff LP (2011 b) Relating Theories via Renormalization. arXiv:1102.3705v1
[79] Kaplan AY, Fingelkurts AA, Fingelkurts AA, Borisov BS, Darkhovsky BS (2005) Nonstationary nature of the brain
activity as revealed by EEG/EMG: methodological, practical and conceptual challenges. Signal Process 85:2190‐
2212
[80] Katare S, West DH (2006) Optimal complex networks spontaneously emerge when information transfer is
maximized at least expense: a design perspective. Complexity 11:26‐35
[81] Kelso JAS, Tognoli E (2007) Toward a complementary neuroscience: metastable coordination dynamics of the
brain. In: LI Perlovsky, R. Kozma (eds) Neurodynamics of cognition and consciousness. Springer, Berlin
[82] Kelso JAS (1995) Dynamic patterns: the self‐organization of brain and behavior. MIT Press, Cambridge, MA
[83] Kitzbichler MG, Smith ML, Chrisstensen SR, Bullmore E (2009) Broadband criticality of human brain network
synchronization. PLOS Comp Biol 5:e1000314
[84] Klinkner KL, Shalizi CR, Camperi MF (2005) Measuring shared in formation and coordinated activity in
Neuronal Networks .arXiv:q‐bio/0506009v2
[85] Knuth KH (2010) Information Physics: the new Frontier. arXiv:1009:5161v1 [math‐ph]
[86] Koch C (2004) The quest for consciousness: a neurobiological approach. Roberts & Co Publisher, Englewood
[87] Kouider S (2009) Neurobiological theories of consciousness, In Encyclopedia of Consciousness, P. Banks, edit.,
[88] Kozma R, Puljic M, Balister P, Bollobas B, Freeman WJ (2005) Phase transitions in the neuropercolation model
of neural populations with mixed local and non‐local interactions. BiolCybern 92:367‐379
[89] Krichmar JL, Seth AK, Nitz DA, Fleischer JG (2005) Spatial navigation and causal analysis in a brain‐based device
modeling cortical‐hippocampal interactions. Neuroinformatics 5:197‐222
[90] Krichmar JL, Edelman GM (2002) Machine psychology: autonomous behavior, perceptual categorization and
conditioning in a brain‐based device. Cerebral Cortex 12:818‐830
[91] Lamme VAF (2006) Towards a true neural stance on consciousness. Trends Cog.Sci 10(11),
[92] Laughlin RB (2005) A different Universe: reinventing physics from the bottom up. Basic Books, NY
[93] Lee U, Mashour GA, Kim S, Noh G, Choi B (2009) Propofol induction reduces the capacity for neural
information integration: implications for the mechanism of consciousness and general anesthesia. Consciousness
and Cognition 18:56‐64
[94] Lipiello E, de Arcangelis L, Godano C (2005) Memory in self‐organized criticality. arXiv:cond‐mat/0505129v1
[95] Marder M (2000) Condensed matter physics. Wiley‐Interscience, NY
[96] Maturana H, Varela FJ (1987) The tree of knowledge: the biological roots to human understanding. New
Science Library, Boston, MA, pp 136
[97] McCormick DA, Bal T (1997) Sleep and arousal: thalamocortical mechanisms. Annu Rev Neurosci 20:185‐215
[98] Melloni L,Molina C, Pena M, Torres D, Singer W, Rodriguuez E. (2007) Synchronization of neural activity across
cortical areas Correlates with Conscious Perception. J. Neurosci.27(11):2858‐2865.
[99] Menary R (2007) Cognitive integration: attacking the bounds of Cognition. Palgrave McMillan, NY
[100] Menary R (2006) Attacking the bounds of cognition. Philosophical Psychology 19:329‐344
[101] Metzinger T (2009) The EGO tunnel. Basic Books, NY
[102] Metzinger T (2008) Empirical perspectives from the self‐model theory of subjectivity: a brief summary with
examples. Progress in Brain Research 168:215‐245
[103] Metzinger T, Gallese V (2003) The emergence of a shared action ontology: building blocks for a theory.
Consciousness and Cognition 12:549‐571
[104] Metzinger T (2003) Being no one: the self‐model theory of subjectivity. MIT Press, Cambridge, MA
[105] Mora T, Bialek W (2010) Are biological systems poised at criticality ? arXiv:1012.2242v1[q‐bio.QM] ,
[106] Moss F, Ward LM, Sannita WG (2004) Stochastic resonance and sensory information processing: a tutorial
and review of applications. Clinical Neurophysiology 115:267‐281
[107] Nathan A, Barbos VC (2010) Network algorithmics and the emergence of information integration in cortical
models. arXiv: 1012.5649v1 [q‐biol.NC]
[108] Newman MEJ (2003) The structure and function of complex networks. SIAM Reviews 45:167‐256
[109] Noë A, Thompson E (2004) Are there neural correlates of consciousness? J of Consciousness Studies 11:3‐28
[110] Parvizi J, Damasio A (2001) Consciousness and the brainstem. Cognition 79:135‐159
[111] Pattee HH (2001) The physics of symbols: bridging the epistemic cut. BioSystems 60:5‐21
[112] Primas H (1998) Emergence in exact natural sciences. Acta Polytechnica Scandinavica 91:83‐89
[113] Prokopenko M, Boschetti F, Ryan AJ (2008) An information‐theoretic primer on complexity, self‐organization,
and emergence. Complexity 15:11‐28
[114] Radicchi F, Ramasco JJ, Barrat A, Fortunato S (2008) Physical Review Letters 101:148701
[115] Ramseyer F, Tschacher W (2008) Synchrony in dyadic psychotherapy sessions. Ch. 20 In: Vrobel S, Roessler
OE, Marks‐Tarlow T (eds) Temporal structures and observer Perspectives: simultaneity. World Scientific, Singapore
[116] Rizzolatti G, Sinigaglia C (2006) Mirrors in the brain: how our minds share actions and emotions. OUP
[117] Rowlands M (2003) Externalism: putting mind and world together again. McGill‐Queens University Press,
Montreal,
[118] Rowlands M (1999) The body in mind. Cambridge University Press, GB
[119] Rozenfeld HD, Havlin S, ben‐Avraham D (2007) New Journal of Physics 9:175‐720
[120] Rudder BL (2000) Persons and bodies: a constitution view. Cambridge University Press, Cambridge GB
[121] Searle JR (2000) Consciousness. Annu Rev Neurosci 23:557‐578
[122] Searle JR (1992) The rediscovery of mind. MIT Press, Cambridge, MA
[123] Seth A (2009 a) Explanatory correlates of consciousness: theoretical and computational challenges. Cogn
Comput 1:50‐62
[124] Seth AK (2009 b) Functions of Consciousness. In: Banks P (ed) Elsevier Encyclopedia of Consciousness.
Elsevier.
[125] Seth AK (2008) Causal networks in simulated neural systems. Cogn Neurodyn 2:49‐64
[126] Seth AK, Dienes Z, Cleeremans A, Overgaard M, Pessoa L (2008) Measuring consciousness: relating behavioral
and neurophysiological approaches. Trends Cog Sci 12:314‐321
[127] Seth AK, Edelman GM (2007) Distinguishing casual interactions in neural populations. Neural Computation
19:910‐933
[128] Seth AK, Izhikevich E, Reeke GN, Edelman GM (2006) Theories and measures of consciousness: an extended
framework. Proc.Natl.Acad. Sci. USA 103:10799‐10804
[129] Seth AK, Baars BJ (2005) Neural Darwinism and consciousness. Consciousness and Cognition 14:140‐168
[130] Seth AK (2005) Causal connectivity of evolved neural networks during behavior. Computation in Neural
Systems 16:35‐55
[131] Shanahan M (2006) A cognitive architecture that combines internal simulation with a global workspace.
Consciousness and Cognition 15:433‐449
[132] Shanahan M (2005) Perception as abduction: turning sensor data into meaningful representation. Cognitive
Science 29:103‐134
[133] Sokal A, Bricmont J (2004) Defense of a modest scientific realism. In: Carrier M, Roggenhofer J, Kuppers G,
Ph. Blanchard (eds) Knowledge and the World, Springer, NY
[134] Sole RV, Valverde S (2004) Information theory of complex networks: on evolution and architectural
constraints. Lect. Notes Phys 650:189‐207
[135] Song C, Havlin S, Makse HA (2005) Self‐similarity of complex networks. Nature 433:392‐396
[136] Sornette D (2006) Critical phenomena in natural sciences. Springer, Berlin
[137] Spivey MJ, Anderson SE, Dale R (2009) The phase transition in human cognition. New Mathematics and
Natural Computation 5:197‐220
[138] Sporns O, Tononi G, Edelman GM (2000 a) Connectivity and complexity: the relationship between
neuroanatomy and brain dynamics. Neural Networks 13:909‐922
[139] Sporns O, Tononi G, Edelman GM (2000 b) Theoretical neuroanatomy: relating anatomical and functional
connectivity in graphs and cortical connection matrices. Cerebral Cortex 10:127
[140] Stanley HE (1999) Scaling, universality, and renormalization: three pillars of modern critical phenomena.
Reviews of Modern Physics 71:S359‐S366
[141] Stanley HE (1971) Introduction to phase transitions and critical phenomena. OUP, NY
[142] Stauffer D, Aharony A (1994) Introduction to percolation theory. CRC Press, NY
[143] Steriade M (1996) Arousal: revisiting the reticular activating system. Science 272:225‐226
[144] Steyn‐Ross ML, Steyn‐Ross DA, Sleigh JW, Liley DTJ (1999) Theoretical electroencephalogram stationary
spectrum for a white‐noise‐driven cortex: evidence for a general anesthetic‐induced phase transition. Physical
Review E 60:7299‐7311
[145] Steyn‐Ross ML, Steyn‐Ross DA, Sleigh WJ, Wilcocks LC (2001) Toward a theory of the general‐anesthetic‐
induced phase transition of the cerebral cortex. I. A thermodynamic analogy. Physical Review E 64:011917
[146] Thompson E, Varela FJ (2001) Radical embodiment: neural dynamics and consciousness. Trends in Cog Sci.
5:418‐425
[147] Tononi G, Laureys S (2008) The neurology of consciousness. Ch. 28 in: Laureys S, Tononi G (eds) The
neurology of consciousness: cognitive neuroscience and neuropathology. Elsevier, NY
[148] Tononi G, Koch C (2008) The neural correlates of consciousness: an update. Ann N Y Acad Sci 1124:239‐261
[149] Tononi G (2008) Consciousness as integrated information: a provisional manifesto. Biological Bulletin
215:216‐242
[150 Tononi G (2004) An information integration theory of consciousness. BMC Neuroscience 5:42
[151] Tononi G, Sporns O (2003) Measuring information integration. BMC Neuroscience 4:31
[152] Tononi G, Edelman GM, Sporns O (1998) Complexity and coherency: integrating information in the brain.
Trends Cog Sci 2:447‐487
[153[ Tononi G, Sporns O, Edelman G (1996) A complexity measure for selective matching of signals by the brain.
Proc Natl Acad Sci USA 93:3422‐3427
[154] Tononi G, Sporns O, Edelman G (1994) A measure for brain complexity: relating functional segregation and
integration in the nervous system. Proc Natl Acad Sci USA 91:5033‐5037
[155] Uhlhaas PJ, Pipa G, Lima B, Melloni L, Neuenschwander S, Nikolic D, Singer W (2009) Neural synchrony in
cortical networks: history, concept and current status. Frontiers Integr Sci 3:1‐19
[156] Van Eck D, De Jong HL, Schouten MKD (2006) Evaluating new wave reductionism: the case of vision. Brit J Phil
Sci 57:167‐196
[157] Varela FJ, Thompson E. (2003).Neural synchrony and the unity of Mind: a neurophenomenological
perspective. Ch. 4.2 In: A. Cleeremans , edit., The unity of Consciousness, OUP, NY.
[158] Varela F, Lachaux J‐P, Rodriguez E, Martinerie J (2001) The brainweb: pase synchronization and large‐scale
integration. Neuroscience 2:29‐239
[159] von der Malsburg C, Phillips WA, Singer W (2010) Dynamic coordination in the brain: fom neuroscience to
mind. MIT Press, Cambridge,MA
[160] Wackermann J, Allefeld C (2009) State space representation and global descriptors of brain electrical activity.
Ch.9 in: Michel CM, Koenig T, Brandeis D, Glanotti LRR, Wackerman J (edits). Electrical neuroimaging. Cambridge
Univ Press, Cambridge,
[161] Wallace R (2005 a) A modular network treatment of Baars’ Global Workspace consciousness model.
//cogpriunts.org/4578/01/modular72.pdf
[162] Wallace R (2005b) Consciousness: a mathematical treatment of the global workspace model. Springer, Berlin
[163] Werner G (2011) Viewing the Extended Mind Hypothesis (Clark & Chambers) in terms of Complex Systems
Dynamics. (in press)
[164] Werner G (2010) Fractals in the nervous system: conceptual implications for theoretical neuroscience.
Frontiers in Physiology 1:1‐28
[165] Werner G (2009 a) On critical state transitions between different levels in neural systems. New Mathematics
and Natural Computation 5:185‐196
[166] Werner G (2009 b) Viewing brain processes as critical state transitions across levels of organization: neural
events in cognition and consciousness and general principles. BioSystems 96:114‐119
[167] Werner G (2009 c) Consciousness related neural events viewed as brain state space transitions. Cogn
Neurodyn 3:83‐95
[168] Werner G (2007 a) Metastability, criticality and phase transitions in brain and its models. BioSystems 90:496‐
508
[169] Werner G (2007 b) Perspectives on the neuroscience of cognition and consciousness. BioSystems 87:82‐95
[170] Wheeler M (2010) Minds, things and materiality. In: Renfrew C, Malafouris L (eds) The cognitive life of things:
recasting the boundaries of mind
[171] West BJ, Geneston EL, Grigolini P (2008) Maximizing information exchange between complex networks.
Physics Reports 468:1‐99
[172] West BJ (2004) Comments on the renormalization group, scaling and measures of complexity. Chaos Solitons
and Fractals 20:33‐44
[173] Wilson KG, Kogut J (1974) The renormalization group and the epsilon expansion. Physics Reports 12:75‐200 |
Decoding the circuitry of consciousness:
from local microcircuits to brain-scale networks
Julien Modolo1, Mahmoud Hassan1, Fabrice Wendling1,*, and Pascal Benquet1
1: Univ Rennes, INSERM, LTSI – U1099, F-35000 Rennes, France
*Corresponding author: Fabrice Wendling – fabrice.wendling@univ-rennes1.fr
Abstract
Identifying the physiological processes underlying the emergence and maintenance of
consciousness is one of the most fundamental problems of neuroscience, with implications
ranging from fundamental neuroscience to the treatment of patients with disorders of
consciousness (DOC). One major challenge is to understand how cortical circuits at drastically
different spatial scales, from local networks to brain-scale networks, operate in concert to enable
consciousness, and how those processes are impaired in DOC patients. In this review, we attempt
to relate available neurophysiological and clinical data with existing theoretical models of
consciousness, while linking the micro- and macro-circuit levels. First, we address the
relationships between awareness and wakefulness on the one hand, and cortico-cortical, and
thalamo-cortical connectivity on the other hand. Second, we discuss the role of three main types
of GABAergic interneurons in specific circuits responsible for the dynamical re-organization of
functional networks. Third, we explore advances in the functional role of nested oscillations for
neural synchronization and communication, emphasizing the importance of the balance between
local (high-frequency) and distant (low-frequency) activity for efficient information processing.
1
The clinical implications of these theoretical considerations are presented. We propose that such
cellular-scale mechanisms could extend current theories of consciousness.
Keywords
Disorders of consciousness, functional connectivity, micro-circuitry, communication through
coherence, gating by inhibition, electroencephalography.
Introduction
Understanding how consciousness arises from communication among brain regions is a
question of the utmost importance in the field of neuroscience in general, and for the diagnosis
and treatment of patients suffering from disorders of consciousness (DOC) in particular. The
problem of consciousness can be seen as fundamental (e.g.: “What is consciousness? Why do we
have subjective, conscious experiences?”, such questions are referred to as the “hard” problem of
consciousness (Harnad, 1998)) or more empirical (e.g.: “What are the processes associated with
the emergence and maintenance of consciousness?”, this forms the “soft” problem of
consciousness (Harnad, 1998)). In this review, we aim at understanding 1) how brain networks at
different scales are involved in enabling and maintaining conscious processes of information
transmission and processing related to awareness and wakefulness, and 2) how these
mechanisms are related to the disruptions of consciousness in DOC patients.
Many theories have been proposed to explain how consciousness originates, ranging from
abstract and informational concepts to neurophysiology-based theories. The most widespread
theories of consciousness have a fundamental assumption in common: information processing in
2
the human brain networks is inextricably linked with consciousness. A recent paper by Dehaene
and colleagues summarizes this principle as follows (Dehaene et al., 2017):
“What we call “consciousness” results from specific types of information-processing
computations, physically realized by the hardware of the brain.”
The three main theories of consciousness include the Integrated Information Theory (IIT)
(Tononi, 2004), the Dynamic Core Hypothesis (Tononi and Edelman, 1998) (DCH), and the
Global Workspace Theory (Baars, 1988; Dehaene et al., 1998; Dehaene et al., 2003) (GWT).
Historically, DCH theory has been the first to refer to the notion of information processing
involved in consciousness (Tononi and Edelman, 1998). This theory is based on the central role
of functional clusters in the thalamo-cortical system and re-entrant interactions, with high
integration and differentiation of neuronal activity being crucial in the emergence of conscious
phenomena. IIT, which is an evolution and generalization of DCH, is based on a set of axioms
from which postulates are derived. IIT also provides a computable quantity, F, also called
integrated information, that quantifies the level of consciousness. In this framework, if
combining sub-elements increases information processing capability more than linearly adding
these elements, then integrated information increases. Global Workspace Theory (GWT) is a
theory of consciousness theory that is more directly connected with neurophysiology and
neuroanatomy. The main hypothesis of GWT is that conscious information is globally available
within the brain, and that two fundamentally different computational systems co-exist: 1) a
network of distributed “local” processors operating in parallel in the brain (“unconscious”), and
2) a “global” workspace formed by a network of distributed interconnected cortical areas
involved in conscious perception (Baars, 1988). The key concept here is that the global
workspace is composed of distant regions densely connected through glutamatergic cortico-
3
cortical connections as opposed to the network of local processors operating in “isolation” (in
parallel). It is worth noting that this distinction between unconscious and conscious processes has
been recently challenged, and might be an oversimplification (Melnikoff and Bargh, 2018). In
GWT, conscious perception is associated with “ignition”, a large-scale brain activation pattern
induced by exposure to a stimulus (Dehaene et al., 2003). If the stimulus does not trigger
ignition, and if the induced brain response remains spatially confined and is brief, then the
perception will not reach consciousness. In other terms, a stimulus has to be sufficiently long and
strong to reach consciousness, which suggests a form of filtering mechanism that is consistent
with the view that only a limited amount of information effectively enters in the global
workspace. Despite these successes in accounting for experimental data in humans regarding
subliminal (unconscious) and conscious perception (Sergent and Dehaene, 2004; King et al.,
2016), one drawback of GWT is that it does not explicitly relate the large-scale recruitment of
brain regions during conscious access with cellular mechanisms. More precisely, what prevents
ignition for short, irrelevant stimuli; and conversely, what enables ignition for strong stimuli?
The neuroanatomical, neurophysiological and dynamical mechanisms behind ignition are of
fundamental importance to understand how we become conscious of a stimulus, or how
alterations of brain networks can result in impaired consciousness in DOC patients.
If one accepts that consciousness is associated with a sufficiently complex (in the algorithmic
sense of “less compressible”) information processing, then the emergence of consciousness is
critically dependent on three factors: 1) a physical network enabling interactions between its
components; 2) the flexibility to re-organize transiently sub-networks to achieve greater
computation capabilities by increasing the number of possible configurations and input-output
functions, through functional connectivity; and 3) dynamic communications between its
4
components. These three critical components have the potential to be altered, for example in
lesions following traumatic brain injury. While the physical large-scale network linking brain
regions is well defined and known as the connectome, there are still unresolved questions
regarding the transient organization of clusters performing specific computations (functional
networks), the associated means of communication (neural coding) and how large-scale
functional brain networks and information routing can reconfigure rapidly depending on microcircuits regulation.
In this review, the objective is therefore to propose a bridging between cortical microcircuits
on the one hand (cellular scale), and brain-scale activity associated with the two main
dimensions of conscious perception (awareness and wakefulness) on the other hand. Such multiscale understanding is a pre-requisite to understand how brain networks become dysfunctional in
DOC, and might contribute to reconcile GWT and DCH into a unified framework.
The review is organized as follows. First, we examine the relationship between the two
dimensions of consciousness, namely wakefulness and awareness, with functional connectivity
between cortical regions and the thalamus. Second, we review the “means of communication”
enabling complex information processing linked with consciousness, which regulate corticocortical communication, among which communication through coherence (CTC) and gating by
inhibition (GBI). The alteration of those mechanisms is presented through results from the
clinical literature. Third, we attempt at linking these findings with concepts that have recently
emerged based on the communication between brain regions based on cross-frequency couplings
between oscillations with specific functional roles. Finally, we suggest possible clinical
implications of this framework in terms of novel neuromodulation protocols in DOC.
5
1. Awareness, wakefulness: a short review of concepts
Conscious perception results from an interplay between two processes interacting with each
other: awareness and wakefulness. Deep sleep switches awareness off, whereas being able of
conscious perception (awareness) of environmental stimuli usually implies a state of
wakefulness, as illustrated in Figure 1. For example, during general anaesthesia, there is both an
absence of conscious perception, awareness and wakefulness. In some peculiar cases, however,
these two components can be unrelated. Unresponsive Wakefulness State (UWS) is an example
of Disorder of Consciousness (DOC) in which wakefulness is present without any detectable
signs of awareness (Laureys and Boly, 2012). Also, during lucid dreaming, there is a form of
awareness in the absence of wakefulness (during sleep) (Voss et al., 2013). Another example is
spatial neglect syndrome, in which patients have no conscious awareness of visual stimuli, while
being awake in the contralateral side of the cortical lesion (Le et al., 2015).
Awareness is supported by attentional, fronto-parietal networks that amplify synaptic
connections within specific cortical pathways (Tallon-Baudry, 2011). This amplification of
relevant stimuli enhances the activated network related to stimulus representation. In parallel, the
concomitant inhibition of irrelevant surrounding networks i) optimizes cortico-cortical routing of
information by constraining the possible propagation of neural activity throughout all possible
cortical “routes”, which ii) restricts propagation to a limited number of stimulus-driven
possibilities, and iii) increases the signal-to-noise ratio. Such mechanisms are related to the
concept of functional connectivity, and are detailed further in this review. Importantly, such
mechanisms of active inhibition likely involve cortical inhibition with an active modulation by
thalamocortical inputs (Gabernet et al., 2005), implying that the pattern of thalamo-cortical
activity influences information processing in cortico-cortical networks.
6
Wakefulness depends critically on thalamo-cortical connectivity and neuromodulatory
brainstem inputs to the thalamus (including noradrenaline projections from the locus coeruleus
(Monti, 2011)). For instance, during slow-wave sleep, a low-frequency, synchronized activity
between the cortex and thalamus (the so-called “up-and-down” rhythm (Neske, 2015), prevents
transmission of sub-cortical inputs to the cortex during sleep). This provides an example in
which thalamo-cortical drastically decreases information processing by cortico-cortical
networks, resulting in a loss of consciousness. During wakefulness, thalamo-cortical activity is
weakly synchronized (Gent et al., 2018), which is a necessary, but not sufficient condition to
enable consciousness. For example, as aforementioned, wakefulness is present in UWS patients
but cortico-cortical communication is severely impaired (Noirhomme et al., 2010), interfering
with the “awareness” component of consciousness. Another required condition for consciousness
is an efficient large-scale cortico-cortical communication that can support awareness through the
activation of attentional fronto-parietal networks (Luckmann et al., 2014; Ptak et al., 2017).
Therefore, in terms of neuroanatomy, it is possible to link wakefulness with thalamo-cortical,
“vertical” connectivity, while awareness depends on cortico-cortical, “horizontal” connectivity.
This is consistent with the recent view by Naccache (Naccache, 2018) that Minimally Conscious
State (MCS) patients, who are conscious to some degree, exhibit “Cortically Mediated States”,
whereas UWS patients do not exhibit such activity, presumably because cortico-cortical
connectivity (critical for awareness) is too severely impaired. More specifically, a “critical mass”
of information processing requires occurring for the emergence and maintenance of
consciousness, which is tightly regulated by thalamo-cortical and cortico-cortical connectivity.
Figure 1 presents, in a two-dimensional plane, the continuum of the states of consciousness, as a
function of awareness and wakefulness.
7
Figure 1. Wakefulness and awareness are two essential dimensions of consciousness. In this diagram, several
qualitatively different states of consciousness have been positioned on the 2D-matrix as a function of the associated
axes “content of consciousness” (awareness) and “level of consciousness” (wakefulness). Adapted from (Laureys,
2005).
2. Functional networks, a flexible architecture for conscious processes
The main disadvantage of static network architectures is their limitation in terms of amount
and variety (complexity) of information processing that can take place. The brain takes
advantage of different mechanisms that overcome this limitation, by enabling a dynamic,
transient reconfiguration of brain networks increasing the repertoire of possible responses to
8
inputs (i.e., complexity of input-output functions) (Sporns, 2013). Such transient networks
involving only a few brain regions, coordinated to achieve a specific function limited in duration,
form what is termed functional connectivity. There is a growing interest regarding the functional
networks associated with specific cognitive tasks (Hassan et al., 2015) and novel frameworks
have recently emerged (Avena-Koenigsberger et al., 2017) to explain how brain-scale anatomical
connectivity relates to functional connectivity. Functional networks organize through the
network “means of communication”, also termed communication dynamics, that governs
information routing through specific networks, instead of propagating information through the
entire brain network (Avena-Koenigsberger et al., 2017). If that was the case, then information
generated locally would induce distant activity in all connectome-related regions, resulting in a
massively synchronized response with low informational content and complexity.
More specifically, one fundamental question is: what are the mechanisms regulating
communication dynamics and enabling functional networks to emerge in brain-scale networks?
This question is central to understand how the brain optimizes its information processing
capabilities, which are tightly linked with consciousness. We propose that the fundamental
mechanisms underlying communication dynamics are actually cellular-scale mechanisms that 1)
prevent brain-scale neuronal synchronization following a stimulus, and 2) enable the transient
coupling of specific distant brain regions. There has been a considerable amount of interest for
large-scale brain activity patterns linked with consciousness, since those can be measured
through various neuroimaging modalities (e.g., electroencephalography, EEG; functional
magnetic resonance imaging, fMRI). However, mechanisms at the cellular scale have remained
more challenging to address in humans for obvious reasons of invasiveness associated with the
9
required recording techniques in humans. In this section, we review evidence for such
mechanisms that could bridge the micro-circuit and brain-scale levels.
In terms of large-scale neuroanatomical pathways enabling consciousness, long-range
glutamatergic projections between pyramidal neurons through white matter fibers have likely a
critical role (Dehaene and Changeux, 2011) since they enable fast (due to myelin)
communication between distant regions. At the brain-scale level, these white matter fibers are
likely critical to enable conscious access, which involves the transient stabilization of neuronal
activity encoding a specific information pattern, in a network of high-level brain regions
interconnected by long-range connections, with the prefrontal cortex (PFC) acting as a key node
(Dehaene et al., 2006; Berkovitch et al., 2017). On conscious trials, distributed gamma-band
activity reflects a stabilization of local information broadcasted to other areas. Global
broadcasting is thought to make the information accessible to introspection and reportable to
other brain regions (Lamme, 2010). During conscious access to a specific information, other
surrounding global workspace neurons would be inhibited and unavailable for the processing of
other stimuli, therefore remaining preconscious (not reaching consciousness).
At the local scale, a micro-circuit has also been identified as being involved in the
communication between distant brain regions: the projection from pyramidal neurons in a brain
region to VIP-positive (Vasoactive Intestinal Peptide) neurons in another region. By activating
VIP-positive neurons in a distant region, this induces an inhibition of somatostatin-positive
(SST) neurons, which target pyramidal cells dendrites, resulting in a disynaptic disinhibition
(Karnani et al., 2016). Through this disynaptic disinhibition, gamma activity generation can
occur through PV-PV mutual inhibition, and binding between the two involved regions can
10
possibly take place (Munoz et al., 2017), temporarily enabling information transfer and
processing. These cellular-scale mechanisms are summarized in Figure 2.
Figure 2. Basic (schematic) circuits involved in the generation of local and distant oscillations. In a local
cortical network (cortical column), gap-junctional, mutual inhibition of soma-projecting, “fast” GABAergic
interneurons are one of the basic mechanisms of generation for local gamma activity, along with the PING
(Pyramid-InterNeuron Gamma). Conversely, the feedback loop between dendrite-projecting, “slow” GABAergic
interneurons and pyramidal cells can generate low-frequency activity. Importantly, distant communication through
the disynaptic pathway enabling transient generation of gamma oscillations in distant populations. Pyramidal cells in
the source population (left circuit) project on the pyramidal cells of the distant population (right), but also on VIP
interneurons that project on dendrite-projecting SST neurons. Transient activation of VIP neurons from the source
population transiently inhibits SST neurons in the target population, enabling the generation of gamma oscillations
through the PV-PV and PYR-PV circuit. Once the input on distant VIP neurons decreases, SST neurons resume their
inhibitory input, which can terminate gamma oscillations generation.
11
Considering these cellular-scale mechanisms, one crucial question is to understand how they
are involved into the transient emergence and maintenance of functional networks such as those
supporting consciousness. It is established that the state of consciousness is critically dependent
on brain functional cortico-cortical connectivity (Marino et al., 2016; Naro et al., 2018). As a
reminder, functional connectivity refers to statistically significant couplings between temporal
courses of neuronal activity within different regions while anatomical connectivity denotes the
physical connections between brain regions. Functional networks can therefore reflect indirect
connections between brain regions, and are transient depending on which tasks are performed, or
which stimuli are perceived. Even in the absence of any specific task or stimuli, it has been
shown that resting-state networks (e.g., default mode network -DMN-) are also transient
(Kabbara et al., 2017). Experimental evidence supports the idea that functional connectivity can
shed light on the networks involved in various conscious states (Jin and Chung, 2012). For
example, during general anaesthesia-induced loss of consciousness, there is a breakdown in
cortico-cortical functional connectivity (Ferrarelli et al., 2010; Hudetz, 2012; Gomez et al.,
2013), severely impairing the capacity of cortical networks to integrate information and to make
it available at a large scale, as required for conscious perception in IIT or GWT. Similarly, in the
transition from wakefulness to slow-wave sleep, the firing rate in the cortex remains relatively
unchanged during the depolarizing phases of the slow sleep oscillation (Steriade et al., 2001),
while effective brain connectivity is dramatically altered (Tononi and Sporns, 2003; Esser et al.,
2009). Upon falling into NREM sleep, cortical activations also become more local and
stereotypical, impairing effective cortical connectivity (Massimini et al., 2010), as shown using
TMS-evoked EEG responses which remain very close to the stimulation site; while these
responses involve a network of distant brain regions undergoing complex dynamical patterns of
12
successive activation during wakefulness (Guillery and Sherman, 2002; Casali et al., 2013;
Casarotto et al., 2016). These results also emphasize the crucial role of the thalamo-cortical
pathway in cortico-cortical functional connectivity. It is worth noting that the essential role of the
thalamocortical loop as well as so-called “reentrant interactions” were previously considered as
key in the DCH (Tononi and Edelman, 1998).
Consistently with these results obtained during sleep, this breakdown of cortico-cortical
connectivity has also been observed during general anaesthesia and in DOC patients, and even
explored through computational modeling (Esser et al., 2009; Casali et al., 2013). In the GWT
framework, this explains why consciousness is impaired in such states: large-scale
communication between distant brain areas is impaired due to thalamo-cortical modulation,
preventing ignition from occurring. In brain-damaged DOC patients, large-scale cortico-cortical
communication can be impaired through the partial destruction of long-range fibers, physically
impeding long-range brain synchrony. In terms of effects at the cellular scale, destruction of
long-range fibers could prevent the synchronization of distant VIP interneurons, which is critical
to induce disynaptic disinhibition and associated gamma activity required for CTC.
Pathological alterations of functional connectivity have been investigated using a variety of
modalities: (1) functional connectivity during ‘‘resting state’’ using fMRI or EEG; (2) pulsed
stimulation using transcranial magnetic stimulation (TMS) during EEG recording; and (3) other
perturbation-based approaches investigating brain responses to sensory stimuli (Boly et al.,
2017). The advantage of functional connectivity is that it can be employed to improve the
evaluation and classification of disorders of consciousness (Sanders et al., 2012; Holler et al.,
2014; Rossi Sebastiano et al., 2015; Naro et al., 2018). For example, in mild cognitive
impairment (MCI) patients, it has been shown that impaired consciousness is associated with
13
altered effective connectivity (Varotto et al., 2014; Crone et al., 2015). Failure of large-scale
connectivity, along with a hypersynchrony of local short-range delta and alpha activity were
detected within the DMN and were correlated with the level of awareness in patients with DOC
(Vanhaudenhuyse et al., 2010; Fingelkurts et al., 2013; Maki-Marttunen et al., 2013; Varotto et
al., 2014; Kabbara et al., 2017; Naro et al., 2018). Furthermore, the functional connectivity
pattern of several brain regions, such as the posterior cingulate cortex and precuneus, may even
predict UWS patients’ state improvement of consciousness with an accuracy superior to 80%
(Wu et al., 2015).
Beside “passive” investigation of resting-state functional connectivity, the use of TMSevoked EEG responses enables the active “probing” of functional connectivity. For example, a
drastic breakdown of functional connectivity has been identified in UWS patients using a
specific TMS protocol triggering, in these patients, a stereotyped, local EEG response similar as
in unconscious sleeping or anaesthetized subjects (Rosanova et al., 2012). Restoring cortical
large-scale effective connectivity with transcranial brain stimulation, such as tACS, in DOCs
could therefore be a useful approach to facilitate partial recovery by enhancing oscillations and
plasticity. One clinical result supporting this idea is the recent demonstration that DLPFC
(dorsolateral prefrontal cortex)-tACS was able to transiently restore the connectivity breakdown
in DOC individuals (Naro et al., 2016).
One fundamental microscopic-scale mechanism involved in information routing in the brain,
and contributing to form functional networks within the anatomical network, is called Gating By
Inhibition (Jensen and Mazaheri, 2010). GBI involves inhibitory processes resulting in the
selective activation of sub-networks and inactivation of other sub-networks. By preventing brainscale activation in response to a stimulus, and restricting the number of brain regions engaged in
14
performing tasks, GBI also prevents states of low complexity (e.g., all brain regions displaying
the exact same activity) and therefore inefficient information processing. Thus, GBI processes
suggest that the role of inhibition is more complex than preventing excessive activation of brain
networks, contributing instead to shaping anatomical brain networks into functional networks
(Avena-Koenigsberger et al., 2017). Possible alterations of GBI were reported in studies showing
that EEG alpha power is lower in UWS than in MCS patients (Lehembre et al., 2012; Stefan et
al., 2018), hinting that the neurobiological mechanisms underlying alpha oscillations generation
and associated GBI are profoundly altered in unresponsive patients. Moreover, alpha activity was
highly synchronized and clustered in central and posterior cortical regions in UWS patients
(Lehembre et al., 2012; Stefan et al., 2018), suggesting a possible failure of GBI in the most
severe disorders of consciousness.
3. Information processing in large-scale functional networks through
nested oscillations
One of the most established processes by which distant brain regions engage together in an
activity pattern associated with the performance of a given task is Communication Through
Coherence (CTC) (Fries, 2005, 2009, 2015b; Deco and Kringelbach, 2016; Bonnefond et al.,
2017). CTC involves indeed phase-coupled gamma activity between distant brain regions to
enable information processing. CTC has been suggested to be the substrate of “binding”, i.e. the
merging of different features of a stimulus into a single, unified conscious perception (Singer,
2001). More precisely, the excitability fluctuation in a group of neurons provides a specific
signature characterized by a specific frequency band and pattern of discharge (Womelsdorf et al.,
2014), propagating through a large-scale network consisting of anatomically interconnected
15
brain areas and subsequently triggering activity in connected regions. Information processing in
the brain is strongly linked with phase-locked, coordinated-in-time fluctuations of excitability
(Fries, 2005; Fries, 2015a) in networks of distributed neuronal populations. The resulting
oscillations generate a specific neuronal code, and coherence enables the association of
information and communication. Furthermore, CTC involves gamma activity, generated mainly
by GABAergic interneurons (PV-positive basket cells). Taken together, inhibitory processes
appear key for information routing and processing in brain-scale networks involved in
consciousness: GBI shapes brain networks spatially (which brain regions are involved, and
which ones are inhibited), while CTC controls them temporally (information flow). However,
this raises an intriguing question: if gamma rhythms are generated locally by interneuronal GABAergic- networks, how can distant brain regions, connected through glutamatergic longrange fibers, communicate efficiently and achieve CTC? One possibility is that the cooccurrence of low- and high-frequency neuronal oscillations could provide distant co-activation
(low-frequency, glutamatergic origin) that would then enable binding (high-frequency,
GABAergic origin). This would involve the formation of a functional network of several brain
regions through the low-frequency rhythm, prior to information transfer and processing through
CTC (involving gamma activity).
As a support for this possibility, conscious perception is indeed characterized by an increase
in distributed gamma-band activity (Melloni et al., 2007; Wyart and Tallon-Baudry, 2009).
Interestingly, these fast oscillations are modulated by slow oscillations (Osipova et al., 2008;
Jensen et al., 2014). It has recently been proposed that phase synchronization of low-frequency
oscillations, playing the role of a temporal reference frame for information, carrying high-
16
frequency activity, is a general mechanism of brain communication (Bonnefond et al., 2017).
These nested oscillations might be a key mechanism, not only for cortico-cortical
communication and processing, but also between sub-cortical structures. Emotional memory,
involving both cortical and subcortical structures, indeed engages large network synchronization
through nested theta-gamma oscillations (Bocchio et al., 2017). During in vivo experiments
performed in rodents, a perceived threat (a stimulus announcing a footshock) enhances theta
power and coherence in the amygdala, prefrontal cortex, and hippocampus (Lesting et al., 2011;
Likhtik et al., 2014), while fast gamma bursts are phase-locked to theta oscillations (Stujenske et
al., 2014). Overall, these results support the idea that nested oscillations at theta and gamma
frequencies are a plausible substrate for information channel opening/routing (theta) and
processing/transfer (gamma) within the brain.
Attention is another key element for conscious processing and it is involved in the
synchronization of distant brain regions (Steinmetz et al., 2000; Niebur et al., 2002). The main
underlying brain rhythms involved in attentional processes are alpha and gamma oscillations:
brain regions synchronize gamma oscillations (Womelsdorf et al., 2014), and are modulated by
slow alpha oscillations. Slow oscillations enable inhibition of irrelevant networks, influence local
signal processing, widespread information exchange, and perception (Sadaghiani and
Kleinschmidt, 2016). Information flow is established by neuronal synchronization at the lowerfrequency bands, namely in the theta (4–7 Hz), alpha (8–13 Hz), and beta (14–25 Hz) bands
(Bonnefond et al., 2017). One possible reason is that low-frequency activity induces a transient
change in excitability in target brain structures, which provides an optimal window for binding
neuronal signals from different regions through high-frequency activity (i.e., gamma) (Canolty et
al., 2006). This provides further support to the idea that low-frequency neural oscillations are
17
mainly involved in establishing transient long-range communication through glutamatergic
projections, while high-frequency neural oscillations are rather involved in information
processing/transfer. It is therefore possible to relate the notion of “integration” with this longrange, glutamatergic co-activation, enabling brain-scale communication between brain regions;
while “differentiation/segregation” would rather depend on locally generated gamma activity
(and in part on low-frequency activation level, which would result in massively synchronized
activity, and reduced differentiation and complexity). An overview of the aforementioned
mechanisms is proposed in Figure 3.
Figure 3. Schematic overview of transient, selective binding among cortical networks through cellular-scale
mechanisms. A. Schematic diagram of an anatomical network with main projections between regions at the brain
scale. B. Upper panel. Selective binding in subset of cortical regions occurs through the generation of gamma
18
oscillations (mostly through micro-circuits involving basket cells), while the distant disinhibition of specific brain
regions occurs through disynaptic disinhibition (activation of distant VIP neurons inhibits SST neurons, which in
turn decrease their inhibitory projection on pyramidal neurons). This contributes to shape the anatomical network
into a functional network. The alpha rhythm acts as a pulsed inhibition to inhibit “irrelevant” networks, increasing
further the signal-to-noise (SNR) ratio. Lower panel. Decreased integration (e.g., following brain damage) leads to
impaired synchronization of distant brain regions (reflected by decreased low-frequency rhythm on the illustrative
oscillation), and thereby a decrease of binding, which combined to a decrease in GBI efficiency strongly decreases
the overall SNR, leading to dysfunction of the network in terms of integration and binding required for
consciousness. Let us note that, in addition to decreased amplitude of the low-frequency rhythm, the phase
relationship of the nested gamma oscillation could be perturbed (i.e., more random) as compared to the
physiological case. Such potential relationship of nested theta/gamma oscillations remains to be explored in DOC.
Emerging evidence shows that the local versus global information processing balance can be
impaired in neurological disorders. Typically, a recent study investigating functional networks in
Alzheimer’s disease patients identified a decrease in brain integration as quantified by the
participation coefficient (reflects communication between distant brain modules), while
segregation as quantified by the clustering coefficient (reflects local communication between
neighbour brain regions) was increased (Kabbara et al., 2018). This is consistent with
neurodegenerative processes, which likely impact the “locking” of specific brain regions or the
inhibition of irrelevant networks, thereby severely impairing large-scale integration of
information. In the context of DOC, recent clinical evidence (Chennu et al., 2017; Rizkallah et
al., 2019) supports this view. In the study by Chennu et al., scalp-level networks were assessed
from DOC patients and pointed at decreased integration within the alpha band. More
specifically, the fronto-parietal network in the alpha band was discriminant between MCS and
UWS patients. In a recent study, Rizkallah et al. (Rizkallah et al., 2019) quantified the level of
local versus global information processing in frequency-dependent functional networks (source
19
level) in DOC patients and controls. Integration in theta band functional networks decreased with
consciousness level, and two anatomical regions were systematically involved between controls
and any patient group: a portion of the left orbitofrontal cortex and the left precuneus. One
possibility is that physical damage to long-range white matter fibers impairs large-scale
integration and the local/global information processing balance. One possible approach to study
such anatomical damage to white matter fibers is diffusion tensor imaging (DTI), as performed
in DOC patients suffering severe brain injury (Fernandez-Espejo et al., 2011; Galanaud et al.,
2012; Luyt et al., 2012), which highlighted widespread disruptions of white matter. Lower
fractional anisotropy was indeed found in the subcortico-cortical and cortico-cortical fiber tracts
of DOC patients as compared to controls (Lant et al., 2016; Weng et al., 2017), suggesting that
major consciousness deficits in DOC patients may be related to altered WM connections between
the basal ganglia, thalamus, and frontal cortex. This is also in line with the effect of lesion of
myelinated fiber tracts, which can result in a failure of communication between distant brain
regions (Adams et al., 2000). Therefore, it seems reasonable that white matter lesions can alter,
modify or prevent both CTC and GBI between large-scale networks. Furthermore, we speculate
that, should the specific phase-locking of gamma oscillations onto theta oscillations be perturbed,
then clinical manifestations associated with DOC might appear (loss of integration and decrease
in the consciousness level).
4. Possible clinical implications
In this review, we have attempted to reconcile the neuroanatomical and neurophysiological
knowledge at the level of micro- and macro-scopic networks, regarding the processes that
underlie the emergence and maintenance of consciousness, and its alterations in DOC patients.
20
The multiplexing of neuronal rhythms through nested oscillations appears as a plausible
mechanism of co-activation in a network of specific distant brain regions (integration), which is
a pre-requisite for a conscious perception. Furthermore, a key mechanism seems to be the subtle
balance between low-frequency activity (associated with “global” processing) and highfrequency activity (associated with a more “local” processing), which could enable the neuronal
dynamics underlying optimal information routing and processing. Excessive low-frequency
activity (e.g., delta activity) results in massively, synchronized activity resulting in a loss of
complexity in terms of information processing, paralleled in such cases with a loss of
consciousness (e.g., sleep, seizures). Similarly, a lack of fronto-parietal functional coupling
(attentional network) has been recently observed in a recent study, as quantified using highresolution EEG in DOC patients (Chennu et al., 2017), suggesting that a sufficient level of
fronto-parietal coupling is required to achieve sufficient neuronal integration and ignition for
conscious perception. More generally, brain dynamics in DOC patients is typically characterized
by a loss of integration at a large-scale (Chennu et al., 2017; Rizkallah et al., 2019), preventing
efficient large-scale coordination of distant brain regions to achieve conscious perception. This
suggests that the low-frequency rhythm required for long-range cortical communication is
decreased, preventing binding in the gamma range and therefore further processing information
and ignition for consciousness access. That being said, what are the possible implications of this
slow/fast activity balance as a candidate mechanism for the complex processing associated with
consciousness?
An interesting perspective, which would also be a form of validation for this mechanism, is
the use of neuromodulation techniques in DOC patients to increase their level of consciousness.
The objective of such neuromodulation techniques could be to “re-balance” local versus global
21
processing, for example through the use of transcranial direct or alternating stimulation
(tDCS/tACS), applied to both a frontal and a parietal site simultaneously, in order to increase
low-frequency synchronization in the theta range. It is the current view that tACS can modulate
endogenous brain rhythms using relatively low-levels electric fields (<1 V/m, as discussed in
(Modolo et al., 2018), which would involve to use a stimulation frequency in the theta range to
increase residual oscillations in this frequency range (i.e., assuming that residual anatomical
connections are still present). Dual-site, fronto-parietal tACS in the theta range could then
provide a non-invasive possibility to increase the level of consciousness in DOC patients,
pending that some residual anatomical connectivity remains in the case of brain-damaged
patients. Interestingly, a recent study (Violante et al., 2017) used dual-site tACS in the theta
range in healthy volunteers reported improved working memory, a function also dependent on
fronto-parietal networks. Another study, using tACS targeting the fronto-temporal network,
reported an increase in working memory performance in seniors to comparable levels than young
participants (Reinhart and Nguyen, 2019). These recent results, obtained in humans, provide
compelling evidence that re-balancing information processing through neuromodulation
protocols could contribute to increase the level of consciousness in some DOC patients (e.g.,
where damage to long-range white matter fibers is not too severe).
Discussion and concluding remarks
The two dimensions of consciousness, awareness and wakefulness, depend on anatomically
distinct pathways: cortico-cortical “horizontal” connectivity and thalamo-cortical “vertical”
connectivity. Excessive “up-and-down-like” thalamo-cortical activity impairs cortico-cortical
connectivity by due to excessive lateral inhibition, thereby preventing CTC of distant brain
22
regions, resulting in drastically altered functional connectivity, in line with the loss of
consciousness in deep sleep or DOC. This control of cortico-cortical communication by thalamocortical activity is fundamental in understanding how attentional processes can emerge by
transiently recruiting efficiently, through nested low-(theta) and high-(gamma) frequency
rhythms, distant brain regions. The evidence reviewed highlights how the balance of nested brain
rhythms with fundamentally different functions can transform an anatomical network into a
transient, successive activation of different sub-networks, i.e. a functional network. This
versatility of reconfiguration of the structural connectome results in an immense and complex
dynamical repertoire of functional networks with specific rhythms and cross-frequency
couplings, probably a key infrastructure enabling consciousness. Among those rhythms, three
appear especially involved in conscious processes: while the function of the theta rhythm appears
linked with “opening” transient channels of communications through distant regions, the alpha
rhythm seems to play the role of pulsed inhibition to increase further the SNR. There is also solid
and converging evidence that gamma oscillations are an excellent candidate for information
processing and transfer.
Importantly, mechanisms identified at the micro-circuit scale between specific types of
interneurons, such as projections from pyramidal cells to distant VIP cells, are critical to provide
a more mechanistic framework for theories of consciousness, notably GWT. Such mechanisms
indeed clarify the conditions under which ignition can occur, while providing links with other
concepts that are not necessarily unified (e.g., CTC, GBI) to enable access to consciousness. In
addition to the recruitment of selective brain regions to have access to the global workspace, it
also appears important to take into account that active inhibitory processes co-occur to improve
the signal-to-noise ratio (e.g., GBI). An overview of those concepts, along with the contribution
23
of the reviewed mechanisms to the increase in neural activity complexity associated with
consciousness, is provided in Figure 4.
Figure 4. Synthesis of the network-level mechanisms underlying the complexity associated with conscious
processes. The structural characteristics of brain circuits at different scales are mentioned with some key oscillatory
rhythms and associated functions.
Taken together, the mechanisms presented in this review suggest that the importance of the
thalamo-cortical pathway, emphasized in the DCH theory, cannot be neglected within the context
of the GW theory: the thalamo-cortical pathway plays actually the role of a “switch”, enabling or
24
not efficient integration and communication within cortico-cortical networks through feedforward inhibition. Therefore, efficient modulation of the thalamo-cortical pathway is necessary,
but not sufficient, to enable ignition within cortical networks and availability of information at a
large scale. For these reasons, it seems that DCH and GWT are both accurate each from their
perspective, and could be unified to obtain a more integrated vision, through a new framework
accounting for both aspects (ignition, availability of information, and control/routing of
information by thalamo-cortical pathways). In such framework, two balances are critical: the first
one is between vertical (thalamo-cortical) and horizontal (cortico-cortical) connectivity, which
controls the second one between local and distant information processing within cortico-cortical
networks. Consequently, we propose that DCH and GWT could be reconciled through this
balance between horizontal and vertical connectivity, and account for a wider range of
phenomena related to consciousness and its deregulations.
Future directions
- An important step forward would be to investigate further the cross-frequency coupling
between the low-frequency theta rhythm and high-frequency gamma rhythm in healthy controls
as compared to DOC patients during resting state. The identification of such changes could have
implications in terms of diagnostic evaluation, but also regarding novel neuromodulation
protocols that might aim, at least in part, to regulate abnormal cross-frequency couplings.
- Another promising application would be to translate the circuitry presented in this review
into a tractable computational model consisting in a network of brain regions, possibly using the
25
neural mass model approach. Evaluating in silico how the microcircuits are involved into the
generation of nested theta-gamma oscillations, and how TMS-evoked EEG responses at the brain
scale are impacted by synchronized thalamocortical activity, would provide key mechanistic
understanding. Candidate tDCS/tACS protocols could also be tested and evaluated in silico.
- Characterizing further the dynamics of functional networks in DOC patients using EEG, for
example by studying the nature and dynamics of modular states over time (e.g., dwell time) as a
function of the level of consciousness (wake, sleep, DOC such as UWS). Extracting such
dynamical information about functional brain network could have diagnostic implications,
notably to distinguish between MCS and UWS patients.
26
Competing financial interests statement
The authors have no competing financial interests to declare for this work.
Funding
This study is funded by the Future Emerging Technologies (H2020-FETOPEN-2014-2015RIA under agreement No. 686764) as part of the European Union’s Horizon 2020 research and
training program 2014–2018.
References
Adams JH, Graham DI, Jennett B. The neuropathology of the vegetative state after an acute brain insult. Brain 2000;
123 ( Pt 7): 1327-38.
Avena-Koenigsberger A, Misic B, Sporns O. Communication dynamics in complex brain networks. Nat Rev
Neurosci 2017; 19(1): 17-33.
Baars BJ. A cognitive theory of consciousness. Cambridge England ; New York: Cambridge University Press; 1988.
Berkovitch L, Dehaene S, Gaillard R. Disruption of Conscious Access in Schizophrenia. Trends Cogn Sci 2017;
21(11): 878-92.
Bocchio M, Nabavi S, Capogna M. Synaptic Plasticity, Engrams, and Network Oscillations in Amygdala Circuits
for Storage and Retrieval of Emotional Memories. Neuron 2017; 94(4): 731-43.
Boly M, Massimini M, Tsuchiya N, Postle BR, Koch C, Tononi G. Are the Neural Correlates of Consciousness in
the Front or in the Back of the Cerebral Cortex? Clinical and Neuroimaging Evidence. The Journal of neuroscience :
the official journal of the Society for Neuroscience 2017; 37(40): 9603-13.
Bonnefond M, Kastner S, Jensen O. Communication between Brain Areas Based on Nested Oscillations. eNeuro
2017; 4(2).
Canolty RT, Edwards E, Dalal SS, Soltani M, Nagarajan SS, Kirsch HE, et al. High gamma power is phase-locked
to theta oscillations in human neocortex. Science 2006; 313(5793): 1626-8.
Casali AG, Gosseries O, Rosanova M, Boly M, Sarasso S, Casali KR, et al. A theoretically based index of
consciousness independent of sensory processing and behavior. Sci Transl Med 2013; 5(198): 198ra05.
Casarotto S, Comanducci A, Rosanova M, Sarasso S, Fecchio M, Napolitani M, et al. Stratification of unresponsive
patients by an independently validated index of brain complexity. Annals of neurology 2016; 80(5): 718-29.
Chennu S, Annen J, Wannez S, Thibaut A, Chatelle C, Cassol H, et al. Brain networks predict metabolism,
diagnosis and prognosis at the bedside in disorders of consciousness. Brain 2017; 140(8): 2120-32.
Crone JS, Schurz M, Holler Y, Bergmann J, Monti M, Schmid E, et al. Impaired consciousness is linked to changes
in effective connectivity of the posterior cingulate cortex within the default mode network. Neuroimage 2015; 110:
101-9.
Deco G, Kringelbach M. Metastability and Coherence: Extending the Communication through Coherence
Hypothesis Using a Whole-Brain Computational Perspective. Trends Neurosci 2016; 39(6): 432.
Dehaene S, Changeux JP. Experimental and theoretical approaches to conscious processing. Neuron 2011; 70(2):
200-27.
27
Dehaene S, Changeux JP, Naccache L, Sackur J, Sergent C. Conscious, preconscious, and subliminal processing: a
testable taxonomy. Trends Cogn Sci 2006; 10(5): 204-11.
Dehaene S, Kerszberg M, Changeux JP. A neuronal model of a global workspace in effortful cognitive tasks. Proc
Natl Acad Sci U S A 1998; 95(24): 14529-34.
Dehaene S, Lau H, Kouider S. What is consciousness, and could machines have it? Science 2017; 358(6362): 48692.
Dehaene S, Sergent C, Changeux JP. A neuronal network model linking subjective reports and objective
physiological data during conscious perception. Proc Natl Acad Sci U S A 2003; 100(14): 8520-5.
Esser SK, Hill S, Tononi G. Breakdown of effective connectivity during slow wave sleep: investigating the
mechanism underlying a cortical gate using large-scale modeling. Journal of neurophysiology 2009; 102(4): 2096111.
Fernandez-Espejo D, Bekinschtein T, Monti MM, Pickard JD, Junque C, Coleman MR, et al. Diffusion weighted
imaging distinguishes the vegetative state from the minimally conscious state. Neuroimage 2011; 54(1): 103-12.
Ferrarelli F, Massimini M, Sarasso S, Casali A, Riedner BA, Angelini G, et al. Breakdown in cortical effective
connectivity during midazolam-induced loss of consciousness. Proc Natl Acad Sci U S A 2010; 107(6): 2681-6.
Fingelkurts AA, Fingelkurts AA, Bagnato S, Boccagni C, Galardi G. Dissociation of vegetative and minimally
conscious patients based on brain operational architectonics: factor of etiology. Clin EEG Neurosci 2013; 44(3):
209-20.
Fries P. A mechanism for cognitive dynamics: neuronal communication through neuronal coherence. Trends Cogn
Sci 2005; 9(10): 474-80.
Fries P. Neuronal gamma-band synchronization as a fundamental process in cortical computation. Annu Rev
Neurosci 2009; 32: 209-24.
Fries P. Rhythms for Cognition: Communication through Coherence. Neuron 2015a; 88(1): 220-35.
Fries P. Rhythms for Cognition: Communication through Coherence. Neuron 2015b; 88(1): 220-35.
Gabernet L, Jadhav SP, Feldman DE, Carandini M, Scanziani M. Somatosensory integration controlled by dynamic
thalamocortical feed-forward inhibition. Neuron 2005; 48(2): 315-27.
Galanaud D, Perlbarg V, Gupta R, Stevens RD, Sanchez P, Tollard E, et al. Assessment of white matter injury and
outcome in severe brain trauma: a prospective multicenter cohort. Anesthesiology 2012; 117(6): 1300-10.
Gent TC, Bandarabadi M, Herrera CG, Adamantidis AR. Thalamic dual control of sleep and wakefulness. Nat
Neurosci 2018.
Gomez F, Phillips C, Soddu A, Boly M, Boveroux P, Vanhaudenhuyse A, et al. Changes in effective connectivity by
propofol sedation. PLoS One 2013; 8(8): e71370.
Guillery RW, Sherman SM. Thalamic relay functions and their role in corticocortical communication:
generalizations from the visual system. Neuron 2002; 33(2): 163-75.
Harnad S. Explaining consciousness: the hard problem. Trends Cogn Sci 1998; 2(6): 234-5.
Hassan M, Benquet P, Biraben A, Berrou C, Dufor O, Wendling F. Dynamic reorganization of functional brain
networks during picture naming. Cortex 2015; 73: 276-88.
Holler Y, Thomschewski A, Bergmann J, Kronbichler M, Crone JS, Schmid EV, et al. Connectivity biomarkers can
differentiate patients with different levels of consciousness. Clin Neurophysiol 2014; 125(8): 1545-55.
Hudetz AG. General anesthesia and human brain connectivity. Brain Connect 2012; 2(6): 291-302.
Jensen O, Gips B, Bergmann TO, Bonnefond M. Temporal coding organized by coupled alpha and gamma
oscillations prioritize visual processing. Trends Neurosci 2014; 37(7): 357-69.
Jensen O, Mazaheri A. Shaping functional architecture by oscillatory alpha activity: gating by inhibition. Front Hum
Neurosci 2010; 4: 186.
Jin SH, Chung CK. Messages from the brain connectivity regarding neural correlates of consciousness. Exp
Neurobiol 2012; 21(3): 113-22.
Kabbara A, Eid H, El Falou W, Khalil M, Wendling F, Hassan M. Reduced integration and improved segregation of
functional brain networks in Alzheimer's disease. J Neural Eng 2018; 15(2): 026023.
Kabbara A, El Falou W, Khalil M, Wendling F, Hassan M. The dynamic functional core network of the human brain
at rest. Sci Rep 2017; 7(1): 2936.
Karnani MM, Jackson J, Ayzenshtat I, Hamzehei Sichani A, Manoocheri K, Kim S, et al. Opening Holes in the
Blanket of Inhibition: Localized Lateral Disinhibition by VIP Interneurons. The Journal of neuroscience : the
official journal of the Society for Neuroscience 2016; 36(12): 3471-80.
King JR, Pescetelli N, Dehaene S. Brain Mechanisms Underlying the Brief Maintenance of Seen and Unseen
Sensory Information. Neuron 2016; 92(5): 1122-34.
Lamme VA. How neuroscience will change our view on consciousness. Cogn Neurosci 2010; 1(3): 204-20.
28
Lant ND, Gonzalez-Lara LE, Owen AM, Fernandez-Espejo D. Relationship between the anterior forebrain
mesocircuit and the default mode network in the structural bases of disorders of consciousness. Neuroimage Clin
2016; 10: 27-35.
Laureys S. The neural correlate of (un)awareness: lessons from the vegetative state. Trends Cogn Sci 2005; 9(12):
556-9.
Laureys S, Boly M. Unresponsive wakefulness syndrome. Arch Ital Biol 2012; 150(2-3): 31-5.
Le A, Stojanoski BB, Khan S, Keough M, Niemeier M. A toggle switch of visual awareness? Cortex 2015; 64: 16978.
Lehembre R, Marie-Aurelie B, Vanhaudenhuyse A, Chatelle C, Cologan V, Leclercq Y, et al. Resting-state EEG
study of comatose patients: a connectivity and frequency analysis to find differences between vegetative and
minimally conscious states. Funct Neurol 2012; 27(1): 41-7.
Lesting J, Narayanan RT, Kluge C, Sangha S, Seidenbecher T, Pape HC. Patterns of coupled theta activity in
amygdala-hippocampal-prefrontal cortical circuits during fear extinction. PLoS One 2011; 6(6): e21714.
Likhtik E, Stujenske JM, Topiwala MA, Harris AZ, Gordon JA. Prefrontal entrainment of amygdala activity signals
safety in learned fear and innate anxiety. Nat Neurosci 2014; 17(1): 106-13.
Luckmann HC, Jacobs HI, Sack AT. The cross-functional role of frontoparietal regions in cognition: internal
attention as the overarching mechanism. Prog Neurobiol 2014; 116: 66-86.
Luyt CE, Galanaud D, Perlbarg V, Vanhaudenhuyse A, Stevens RD, Gupta R, et al. Diffusion tensor imaging to
predict long-term outcome after cardiac arrest: a bicentric pilot study. Anesthesiology 2012; 117(6): 1311-21.
Maki-Marttunen V, Diez I, Cortes JM, Chialvo DR, Villarreal M. Disruption of transfer entropy and interhemispheric brain functional connectivity in patients with disorder of consciousness. Front Neuroinform 2013; 7:
24.
Marino S, Bonanno L, Giorgio A. Functional connectivity in disorders of consciousness: methodological aspects and
clinical relevance. Brain Imaging Behav 2016; 10(2): 604-8.
Massimini M, Ferrarelli F, Murphy M, Huber R, Riedner B, Casarotto S, et al. Cortical reactivity and effective
connectivity during REM sleep in humans. Cogn Neurosci 2010; 1(3): 176-83.
Melloni L, Molina C, Pena M, Torres D, Singer W, Rodriguez E. Synchronization of neural activity across cortical
areas correlates with conscious perception. The Journal of neuroscience : the official journal of the Society for
Neuroscience 2007; 27(11): 2858-65.
Melnikoff DE, Bargh JA. The Mythical Number Two. Trends Cogn Sci 2018.
Modolo J, Denoyer Y, Wendling F, Benquet P. Physiological effects of low-magnitude electric fields on brain
activity: advances from in vitro, in vivo and in silico models. Current Opinion in Biomedical Engineering 2018; 8:
38-44.
Modolo J, Thomas AW, Legros A. Neural mass modeling of power-line magnetic fields effects on brain activity.
Front Comput Neurosci 2013; 7: 34.
Monti JM. Serotonin control of sleep-wake behavior. Sleep Med Rev 2011; 15(4): 269-81.
Munoz W, Tremblay R, Levenstein D, Rudy B. Layer-specific modulation of neocortical dendritic inhibition during
active wakefulness. Science 2017; 355(6328): 954-9.
Naccache L. Minimally conscious state or cortically mediated state? Brain 2018; 141(4): 949-60.
Naro A, Bramanti A, Leo A, Cacciola A, Manuli A, Bramanti P, et al. Shedding new light on disorders of
consciousness diagnosis: The dynamic functional connectivity. Cortex 2018; 103: 316-28.
Naro A, Bramanti P, Leo A, Russo M, Calabro RS. Transcranial Alternating Current Stimulation in Patients with
Chronic Disorder of Consciousness: A Possible Way to Cut the Diagnostic Gordian Knot? Brain Topogr 2016;
29(4): 623-44.
Neske GT. The Slow Oscillation in Cortical and Thalamic Networks: Mechanisms and Functions. Front Neural
Circuits 2015; 9: 88.
Niebur E, Hsiao SS, Johnson KO. Synchrony: a neuronal mechanism for attentional selection? Curr Opin Neurobiol
2002; 12(2): 190-4.
Noirhomme Q, Soddu A, Lehembre R, Vanhaudenhuyse A, Boveroux P, Boly M, et al. Brain connectivity in
pathological and pharmacological coma. Front Syst Neurosci 2010; 4: 160.
Osipova D, Hermes D, Jensen O. Gamma power is phase-locked to posterior alpha activity. PLoS One 2008; 3(12):
e3990.
Ptak R, Schnider A, Fellrath J. The Dorsal Frontoparietal Network: A Core System for Emulated Action. Trends
Cogn Sci 2017; 21(8): 589-99.
Reinhart RMG, Nguyen JA. Working memory revived in older adults by synchronizing rhythmic brain circuits. Nat
Neurosci 2019; 22(5): 820-7.
29
Rizkallah J, Annen J, Modolo J, Gosseries O, Benquet P, Mortaheb S, et al. Decreased integration of EEG sourcespace networks in disorders of consciousness. Neuroimage Clinical 2019; 23(101841): 1-9.
Rosanova M, Gosseries O, Casarotto S, Boly M, Casali AG, Bruno MA, et al. Recovery of cortical effective
connectivity and recovery of consciousness in vegetative patients. Brain 2012; 135(Pt 4): 1308-20.
Rossi Sebastiano D, Panzica F, Visani E, Rotondi F, Scaioli V, Leonardi M, et al. Significance of multiple
neurophysiological measures in patients with chronic disorders of consciousness. Clin Neurophysiol 2015; 126(3):
558-64.
Sadaghiani S, Kleinschmidt A. Brain Networks and alpha-Oscillations: Structural and Functional Foundations of
Cognitive Control. Trends Cogn Sci 2016; 20(11): 805-17.
Sanders RD, Tononi G, Laureys S, Sleigh JW. Unresponsiveness not equal unconsciousness. Anesthesiology 2012;
116(4): 946-59.
Sergent C, Dehaene S. Is consciousness a gradual phenomenon? Evidence for an all-or-none bifurcation during the
attentional blink. Psychol Sci 2004; 15(11): 720-8.
Singer W. Consciousness and the binding problem. Ann N Y Acad Sci 2001; 929: 123-46.
Sporns O. Structure and function of complex brain networks. Dialogues Clin Neurosci 2013; 15(3): 247-62.
Stefan S, Schorr B, Lopez-Rolon A, Kolassa IT, Shock JP, Rosenfelder M, et al. Consciousness Indexing and
Outcome Prediction with Resting-State EEG in Severe Disorders of Consciousness. Brain Topogr 2018.
Steinmetz PN, Roy A, Fitzgerald PJ, Hsiao SS, Johnson KO, Niebur E. Attention modulates synchronized neuronal
firing in primate somatosensory cortex. Nature 2000; 404(6774): 187-90.
Steriade M, Timofeev I, Grenier F. Natural waking and sleep states: a view from inside neocortical neurons. Journal
of neurophysiology 2001; 85(5): 1969-85.
Stujenske JM, Likhtik E, Topiwala MA, Gordon JA. Fear and safety engage competing patterns of theta-gamma
coupling in the basolateral amygdala. Neuron 2014; 83(4): 919-33.
Tallon-Baudry C. On the neural mechanisms subserving consciousness and attention. Front Psychol 2011; 2: 397.
Tononi G. An information integration theory of consciousness. BMC Neurosci 2004; 5: 42.
Tononi G, Edelman GM. Consciousness and complexity. Science 1998; 282(5395): 1846-51.
Tononi G, Sporns O. Measuring information integration. BMC Neurosci 2003; 4: 31.
Vanhaudenhuyse A, Noirhomme Q, Tshibanda LJ, Bruno MA, Boveroux P, Schnakers C, et al. Default network
connectivity reflects the level of consciousness in non-communicative brain-damaged patients. Brain 2010; 133(Pt
1): 161-71.
Varotto G, Fazio P, Rossi Sebastiano D, Duran D, D'Incerti L, Parati E, et al. Altered resting state effective
connectivity in long-standing vegetative state patients: an EEG study. Clin Neurophysiol 2014; 125(1): 63-8.
Violante IR, Li LM, Carmichael DW, Lorenz R, Leech R, Hampshire A, et al. Externally induced frontoparietal
synchronization modulates network dynamics and enhances working memory performance. Elife 2017; 6.
Voss U, Schermelleh-Engel K, Windt J, Frenzel C, Hobson A. Measuring consciousness in dreams: the lucidity and
consciousness in dreams scale. Conscious Cogn 2013; 22(1): 8-21.
Wendling F, Bartolomei F, Bellanger JJ, Chauvel P. Epileptic fast activity can be explained by a model of impaired
GABAergic dendritic inhibition. The European journal of neuroscience 2002; 15(9): 1499-508.
Weng L, Xie Q, Zhao L, Zhang R, Ma Q, Wang J, et al. Abnormal structural connectivity between the basal ganglia,
thalamus, and frontal cortex in patients with disorders of consciousness. Cortex 2017; 90: 71-87.
Womelsdorf T, Valiante TA, Sahin NT, Miller KJ, Tiesinga P. Dynamic circuit motifs underlying rhythmic gain
control, gating and integration. Nat Neurosci 2014; 17(8): 1031-9.
Wu X, Zou Q, Hu J, Tang W, Mao Y, Gao L, et al. Intrinsic Functional Connectivity Patterns Predict Consciousness
Level and Recovery Outcome in Acquired Brain Injury. The Journal of neuroscience : the official journal of the
Society for Neuroscience 2015; 35(37): 12932-46.
Wyart V, Tallon-Baudry C. How ongoing fluctuations in human visual cortex predict perceptual awareness: baseline
shift versus decision bias. The Journal of neuroscience : the official journal of the Society for Neuroscience 2009;
29(27): 8715-25.
30 |
The Limits to Machine Consciousness
Subhash Kak
Oklahoma State University
Abstract It is generally accepted that machines can replicate cognitive tasks performed by
conscious agents as long as they are not based on the capacity of awareness. We consider
several views on the nature of subjective awareness, which is fundamental for selfreflection and review, and present reasons why this property is not computable. We argue
that consciousness is more than an epiphenomenon and assuming it to be a separate
category is consistent with both quantum mechanics and cognitive science. We speak of two
kinds of consciousness, little-C and big-C, and discuss the significance of this classification in
analyzing the current academic debates in the field. The interaction between the system and
the measuring apparatus of the experimenter is examined both from the perspectives of
decoherence and the quantum Zeno effect. These ideas are used as context to address the
question of limits to machine consciousness.
Keywords: machine consciousness, artificial intelligence, quantum Zeno effect
1. INTRODUCTION
AI and robotics are bringing about revolutionary changes in society and the next
question is whether machines with consciousness could be designed. The word
“consciousness” can mean different things, but in its quest for machines the sense is
of “awareness” and “subjectivity” that underlies memories, creating a narrative that
goes beyond the straitjacket of physical law [1],[2]. This is also an important
scientific question for all cognitions and the creation of science takes place in
consciousness. It follows that an understanding of reality cannot emerge without an
insight into its nature.
An immediate practical motivation for this research is the prospect that “selfconscious” robots will be deployed on the battlefield and used in rescue operations
in dangerous environments. It is clear that machines with awareness will have
greater autonomy and corresponding beneficial uses but they will create new
challenges by replacing humans in many jobs and raise thorny problems of ethics
and morality. Whether such machines will ever be built remains an open question.
A distinction is generally made between the philosophical positions of strong
and weak AI. Those who believe in the former admit the possibility that AI will
subsume the phenomenon of consciousness, whereas those who believe in the latter
allow only the possibility of mimicking the capacities of the brain.
At first look, one could assert that since the brain is a machine that is
conscious then other machines with appropriate architecture should also exhibit
Subhash Kak
consciousness. Implicit in this belief is the physicalist position that consciousness is
either an emergent property or an epiphenomenon, and that computers can capture
the abstract causal organization of other systems and thus of the brain [3],[4]. But
this is unfalsifiable for if machines that can do so do not exist now – and they do not
– one can always point to the future when such machines will emerge. Panpsychism,
the position that mind is to be found everywhere, is another position that has
recently become popular in academic circles [5], but it is too extravagant in
associating mind even with a straw or a rock. Broadly speaking, both physicalism
and panpsychism associate mind with matter, although they do so in different ways.
Figure 1. The physical, the mental, and the mathematical worlds
From a computational perspective, it is astonishing that a small subset of the
processes in the brain, which we label abstract thought, is able to capture the
workings of the physical world to a great degree [6] (Figure 1). It is also noteworthy
that brain function is accompanied by the reorganization of its very structures
during its learning [7],[8] that goes beyond the commonsense notion of procedurebased computation at the basis of the Turing machine model on which the von
Neumann architecture of digital computers is broadly based [9] (Figure 2).
Figure 2. The von Neumann architecture of the computer
Although learning cognitive tasks may require attention and concentration,
once the learning is complete they can be performed literally automatically. The
learning leads to a training of neural networks that convert the computational
problem into one of classification and recognition. It should thus be possible to
replicate the tasks that involve computations in the neural circuitry of the brain by
2
The Limits to Machine Consciousness
means of processing in a machine. But “raw awareness” appears to be a
phenomenon that is different from cognitive processing.
This paper begins by summarizing the case for and against a unitary
representation of the world and investigates if self-awareness is computable. It is
argued that the orthodox Copenhagen Interpretation of quantum mechanics implies
that consciousness is a category different from matter which is consistent with the
view that awareness is different from the contents of the mind. The interaction
between system and the measuring apparatus of the experimenter is examined both
from the perspectives of decoherence and the quantum Zeno effect. Lastly, the
implications of this analysis for the limitations of machine consciousness are
examined.
2. ONE WORLD OR MANY?
The motivation for seeing the world in unitary terms where it is reducible to physics
derives, in part, from an abhorrence of dualism. Popper and Eccles stressed the
shortcomings of the unitary physicalist position in a proposal for interactionism
with three worlds as constituents [10],[11]. They saw World 1 as consisting of
physical objects and events including biological entities, World 2 as composed of
mental objects and events, and World 3 as consisting of objective knowledge. They
claimed that World 3 is different from Platonic ideas for it is created by World 2 and
it does not have a privileged position.
The three worlds of Popper and Eccles are similar to the old Indian model of
Figure 3 that sees the universe in five systems of the body, mediating processes,
mind, intuition and science, aesthetics and emotions, together with consciousness as
a separate category [12].
Figure 3. Five planes of existence and consciousness [12]
3
Subhash Kak
The traditional Vedic model of the mind and consciousness, which is
described at length in the Upanishads and other old texts, is given in Figure 4 and it
includes elements such as ego (the sense of the autobiographical self) and
awareness. Mind in this model is an inner processor that does operations associated
with different cognitive capacities in a systematic manner. Such a model cannot be
implemented since we don’t know how to implement ego and awareness in a formal
system.
Figure 4. A model of mind and consciousness [12]
The design of a conscious machine faces formidable scientific and
engineering obstacles and so one must begin with small steps. Architectures that
copy models of brain function have been investigated [2],[13],[14],[15]. These
architectures include distributive agents and the global workspace theory (GWT)
[16],[17]. In the GWT, separate parallel processes compete to place their
information in the global workspace whose contents are broadcast to a multitude of
receiving processes. Since globally broadcast messages can evoke actions in
receiving processes throughout the network, the global workspace may be used to
exercise executive control to perform voluntary actions. This roughly mimics some
brain functions without addressing the origin of consciousness.
Postulating a physical substrate of consciousness to be at the basis of
complex patterns of activity has been called the integrated information theory (IIT)
[18],[19]. But it amounts to correlations in physical processes that cannot by
themselves be the source of awareness. Complex causally connected behavioral
patterns may also be seen in social networks, where they are properly analyzed
within the framework of an ecological system without recourse to the concept of
consciousness.
In the standard neuroscience view, mind emerges from the interoperation of
the various modules in the brain and its behavior must be completely described by
4
The Limits to Machine Consciousness
the corresponding brain function (Figure 5). However, no specific neural correlate
of consciousness has been found [20]. Others have argued that counterintuitive
characteristics of the mind are ascribable to underlying quantum processes
[21],[22]. But although quantum mechanics might play a role in brain processes
[23],[24] there is no reason to assume that it throws any light on the phenomenon
of consciousness [25].
Figure 5. Consciousness as an emergent process
The other position is that consciousness is a fundamental category that is
dual to physical reality as in Figure 6 [26],[27]. In art and philosophy, the idea that
consciousness is universal is widely accepted. It has been said that the eyes see only
what the mind is trained to comprehend and, therefore, culture serves as a filter that
structures reality. Technology and inner development have guided the appreciation
of modes of artistic expression and the unprecedented changes of the past couple of
centuries have led to corresponding efflorescence of art. Just as personal insight is
preceded by a crisis, the evolution of artistic consciousness at the societal level
comes at the end of a critical phase of doubt. Indeed the themes of fin de siècle are
seen to prefigure the geopolitical changes of the twentieth century.
We apprehend reality in our consciousness and not directly in terms of
space, time and matter. Consciousness is the doorway that shows us the world and
makes self-knowledge possible and it is the source of creativity although it is
constrained by the habits and limitations of the mind. The quality of the
manifestation of consciousness in a natural system depends on structure and
different modes of processing.
Figure 6. Consciousness as an independent category
Consciousness and the material world complement each other and
consciousness may influence material evolution as in the quantum Zeno effect
[28],[29]). This is the position of the orthodox Copenhagen Interpretation of
quantum mechanics, which is sometimes criticized for supporting dualism. The
5
Subhash Kak
pioneers of quantum mechanics thought this criticism was misplaced. Noting that
Schrödinger believed that the philosophical basis of quantum theory is consistent
with the Vedic system (e.g. [30]), we add that in the mainstream Indian
philosophical position this dualism is only apparent and at the basis of all is a
unitary consciousness [31],[32].
3. ON MIND AND COMPUTABILITY
Different observers perceive the same object, say a flower placed on a table,
differently based on their perspective and prior state of mind, even though the
flower is situated in the same physical space. If one were to switch categories, and
imagine consciousness to be like that flower even though it is not a thing, then one
can see how it may be variously experienced in different minds. Its apparent
plurality is a consequence of its many projections.
The statement that consciousness is the ground on which experience is
evoked variously is like saying that of gravity is one force that works on objects
differently depending upon their location.
Schrödinger addresses the question of the nature of unity of consciousness in
very clear terms [33]:
Consciousness is never experienced in the plural, only in the singular. Even in the
pathological cases of split consciousness or double personality the two persons
alternate, they are never manifest simultaneously. …How does the idea of plurality
(so emphatically opposed by the Upanishad writers) arise at all? Consciousness
finds itself intimately connected with, and dependent on, the physical state of a
limited region of matter, the body. (Consider the changes of mind during the
development of the body, as puberty, ageing, dotage, etc., or consider the effects of
fever, intoxication, narcosis, lesion of the brain and so on.) Now, there is a great
plurality of similar bodies. Hence the pluralization of consciousnesses or minds
seems a very suggestive hypothesis. Probably all simple, ingenuous people, as well
as the great majority of Western philosophers, have accepted it.
Memories and experiences are not physical although they may have neural
correlates. The same awareness of the individual suffering from dissociative identity
disorder is bound to different alters (alternate selves). More dramatically, the same
individual might be a loving family man at home and a ruthless murderer in a
different environment. The self is past experience together with culturally
determined ways of binding this experience. Since the wholeness of the self is not
diminished if the individual were to be taken to an entirely new society and cut-off
from all past experience, the self is beyond the experience.
6
The Limits to Machine Consciousness
We think of ourselves as being outside of the physical world. Even our
conceptions of the universe are as if we are not a part of it, and in the words of
Schrödinger [33]: “We do not belong to this material world that science constructs
for us. We are not in it; we are outside. We are only spectators. The reason why we
believe that we are in it, that we belong to the picture, is that our bodies are in the
picture. Our bodies belong to it.”
If this sense of being outside of the physical world is true, it would be
impossible to emulate it by hardware and processing that is within the world. It also
follows that it will not be a computational property of the physical elements that
comprise the system. Penrose thought that consciousness must be non-algorithmic
because it is global phenomenon [9],[21].
Can consciousness be seen as the capacity to know with certainty that one is
conscious [34],[35]? This appears to be a circular definition and it hinges on hardto-define concepts such as “knowledge” and “belief”. Consider HM, the guy who lost
all new memory with the bilateral resection of medial temporal lobe and his ability
to hold beliefs and knowledge was greatly impaired [36], yet, without doubt, he had
all hallmarks of consciousness.
We can look for the non-computability of consciousness from its parallel to
the unsolvability of the halting problem. Let us informally define "consciousness" as
some privileged state of the mind that makes its processes halt (we don't bother to
specify it beyond this description) and its contents registered (which is what we
imply by awareness). Humans can get into this state at any time, which means that
the earlier computation has halted, and this is irrespective of the initial state of the
immediately preceding process (the exceptions to this are if a person is sleeping or
unconscious as in coma). But such halting to arbitrary input is impossible from a
computability point of view. Therefore, it follows that consciousness is not
computable.
4. LITTLE-C AND BIG-C CONSCIOUSNESS
Two possibilities with regard to the nature of consciousness have been a part of the
discourse in many cultures. Nowhere has the debate over these been as sustained
and clear as in India where the Vedic tradition represents the view that
consciousness is a separate transcendent category (ātman) that is apart from
physical reality (big-C) and to Buddhist thought is ascribed the view that
consciousness is evanescent and fleeting and the underlying reality is emptiness
(śūnyatā) (little-C). Many scholars believe that the difference between the two
positions is more apparent than real (e.g. [37]) for the Buddha speaks of the
inability of language to describe the truth (for example, in the Diamond Sutra and
the Abhidhamma) indicating its basis is paradoxical which is quite consistent with
7
Subhash Kak
the Vedic view [38]. According to the Vedic tradition, Buddhist practices are fine in
advancing the understanding of the mind, but they stop short by denying the
independent agency of consciousness. The idea of impermanence is critiqued on the
premise that impermanent reality cannot be constrained by permanent laws and if
the laws are permanent they represent a transcendent aspect of the reality.
Formally, big-C is consciousness with an ontological category of its own (e.g.
[38]). It appears that consciousness as conceived in psychophysical parallelism is
big-C [40], and Schrödinger stressed this point repeatedly (see, e.g. [41]), and the
positivist view of reality supports this view.
We use the term little-C for consciousness that relates to the normal
functions of the mind that appear as an epiphenomenon as seen, for example,
through the lens of neuroscience. The centrality of the non-self doctrine in Buddhist
thought, even allowing for the invariant principles that guide mind’s
transformations [42],[43], is consistent with little-C. These two views are
summarized in Table 1.
Table 1. Two views of consciousness
Type
Knowledge
Systems
perspective
Logical
perspective
Big-C
Little-C
Independent category
Epistemic
Global, integrative
Epiphenomenon
Ontic
Local, reductionist
Top-down
Bottom-up
The idea of big-C consciousness raises the question of how it is related to
matter and how they mutually influence each other. This is not a problem in little-C
consciousness where one may claim that the agency associated with consciousness
is an illusion [44].
One might argue that the difference between the two ideas of consciousness
is more semantic than real as their self-understanding practices are practically
identical. But the two can indeed be distinguished if there are aspects to big-C that
cannot be explained by any generous interpretation of little-C. Specifically, one can
speak of the process of creativity and discovery and show that some aspects of it
appear to require the postulation of an entity that is larger than an emergent mind.
Particularly noteworthy are the extraordinary numerical coincidences in the history
of science that are probabilistically next to impossible [45].
We add that the consideration of information (or entropy) in physical theory,
which is commonly done in many branches of physics, implies an unstated
postulation of consciousness. Information cannot be reduced to local operations by
8
The Limits to Machine Consciousness
any reductionist program. It requires the use of signs derived from global properties
and the capacity to make choices which, in turn, implies agency. Such agency will be
consistent with physical law only if does not involve the expenditure of energy.
5. MEASUREMENT, COLLAPSE, DECOHERENCE
Let us consider the interaction problem in the framework of quantum theory. The
measurement operation divides the physical universe into two parts: the first part is
the system being observed, and the second part is the human observing agent,
together with the measurement apparatus.
Philosophically, space and time must divide for the universe to be born.
Likewise, the experimenter must be separated from the system being observed. In
the orthodox Copenhagen Interpretation (CI) [26][27], a hypothetical interface
called the Heisenberg cut (or the von Neumann cut) is assumed between quantum
events and the observer's information. Below the cut everything is governed by the
quantum wave function, whereas above the cut one must use classical description.
The cut might appear to be arbitrary, but it is merely a way to separate parts of the
system, which must be done in a consistent manner.
The CI considers the question of interaction between mental states and the
wave function by taking the wave function to have an epistemological reality, that is,
it represents the experimenter’s knowledge of the system, and upon observation
there is a change in this knowledge. Operationally, it is a dualist position, where
there is a fundamental split between observers and objects. The placement of the
cut between the subject and the object is arbitrary to the extent it depends on the
nature of the interaction between the two.
In the ontic view of the wave function, there is no collapse of the wave
function, and the interaction is seen through the lens of decoherence, which occurs
when states interact with the environment producing entanglement. Decoherence
causes the system to make transition from a pure state to a mixture of states that
the observer is able to measure [46]. The process of decoherence in no way negates
the CI picture, for it merely shifts the cut away in such a way that the system under
observation and the measurement apparatus are on the same side.
Let us consider the system to be in the state ci i with two
i
components (so that i = 0 or 1). Let the measurement apparatus be described by
1 / 2 i , i = 0,1. The two interact and their joint state function is .
i
The composite system evolves and gets entangled so that we have the mixed state
with diagonal terms in the density matrix that is c0 0 0 c1 1 1 . The
2
2
measurement of the apparatus state reveals the state of the system although the
9
Subhash Kak
knowledge of the probability amplitudes is possible only by doing tomography on
many identical copies of the original state.
By placing the Heisenberg cut away from both the system and the
measurement apparatus, the problem of collapse of the wave function is
sidestepped but it still involve the agency of the observer. It raises other questions:
Since the entire universe may be taken to be a quantum system, the question of how
this whole system splits into independent subsystems arises. It would seem that the
splitting into subsystems, which is an observational choice, serves about the same
function as the Heisenberg cut of CI. From the perspective of the mind, the ontic
view is troublesome for its own states are determined by transformational
operations that rule out agency, and to assume a mechanistic behavior for the mind
is to oppose the inconvertible fact of free will.
Bohr argued that the consideration of the biological counterpart to the
observation of the relation between mind and body does not become part of an
infinite regress. He argued that [47] “We have no possibility through physical
observation of finding out what in brain processes corresponds to conscious
experience. An analogy to this is the information we can obtain concerning the
structure of cells and the effects this structure has on the way organic life displays
itself.… What is complementary is not the idea of a mind and a body but that part of
the contents of the mind which deals with the ideas of physics and the organisms
and that situation where we bring in the thought about the observing subject.”
The experimenter is not describing reality ontologically; rather, he is
obtaining knowledge about it and this depends on the nature of his interaction with
the system. The knowledge informs his mind and consideration of this information
creates a sense of overarching knowledge. If information is fundamental then the
violation of Bell’s theorem by experiments does not imply a fundamental difficulty
[48].
6. QUANTUM ZENO EFFECT
If the physical world and consciousness did not interact then evolution of the
universe will be chaotic. While the psychological part of the psychophysical
parallelism notion implies that consciousness does not have a physical basis (it has
physical correlates, which is not the same thing), the quantum Zeno effect [28]
provides a mechanism on how observation can influence dynamics sidestepping the
question of the ontological position of the observer.
This effect arises from the fact that a quantum system’s evolution may be
stopped by measuring it frequently enough with respect to some chosen
measurement basis. In other words, a watched system does not change. Opposite to
this, if a system is measured frequently enough along specific bases, its evolution
10
The Limits to Machine Consciousness
can be guided to a desired state. The name of this effect is a take-off on Zeno’s arrow
paradox, according to which an arrow in flight is not seen to move during any single
instant, and therefore it cannot possibly be moving at all.
The quantum Zeno effect does not change the dynamics, and the process of
observation merely changes the probabilities that are associated with different
outcomes. It finds a way for consciousness to manifest itself in evolution without the
need for any change to the physical law.
The idea of samavāya (inherence) in the Vaiśeṣika Sūtra of Kaṇāda [31] is a
similar idea in which consciousness influences the physical world by observation
alone. It is extraordinary that this subtle idea has been a part of the mainstream
philosophy in India for a long time.
7. IMPLICATIONS FOR MACHINES
Cognitive architectures for the solution of certain AI problems are organized around
three computational areas of subconcepts (preconscious or subliminal), abstract
concepts, and a linguistic interface (Figure 7) which is similar to the hierarchical
agents model described by neuroscientists [20].
Figure 7. A cognitive architecture
The implementation of the engineered system must unpack the various
subconcepts that are needed in the solution. The subconcepts could be various
feature detection operators that feed into the higher-level operators as in a
computer vision problem. For a robot, the issue is to have an inner map of the world
together with the robot, so that it can navigate through the many obstacles that
might be present. There is no need to have awareness within the system for that is
already programmed in the design of the system (Figure 8).
11
Subhash Kak
Figure 8. A cognitive architecture
This above view is consistent with general belief in the AI community that
machines can replicate all cognitive tasks performed by conscious agents so long as
these tasks are not based on the capacity of awareness, which is fundamental for
self-reflection and creativity. But even if subjective awareness is not engineered,
machines will replace humans in a huge variety of tasks, causing unprecedented
stress and dislocations in society and raise questions of meaning and purpose of life.
Machines will come up short in creativity tasks, although the term
“creativity” itself is contested and in retrospect what was taken to be creative at one
point may be seen as a consequence of previous causes. Indeed, some creativity is
inductive but if there is another kind which is non-inductive, then this will not be
open to machines.
These ideas have implication to society for one may conclude that cultures
that regiment human thought reduce its members to be no better than automatic,
machine-like behavior. Such cultures diminish humanity and so they will come in
conflict with open societies. On the other hand, the alienation set off in society due
to the vanishing of jobs may attract some to cults with a simplistic view of the world.
8. DISCUSSION
We have shown that the naïve view of considering consciousness to be apart from
the body provides surprising insight into the larger problem of conscious machines.
Cognitive capacities are computational but their assignment to the autobiographical
self is a process that is associated with awareness and memories. This assignment
occurs with consciousness as a singular phenomenon. Sentience is a complex dance
between being and becoming, where being is consciousness and becoming is the
physical reality.
Consciousness cannot intervene in physical law but it can change the
probabilities in the evolution of quantum processes (as in the quantum Zeno effect),
without changing the dynamics and this provides an explanation of how
consciousness can be reconciled with the physical law.
Let me return to the question of why the brain-machine is conscious. If the
phenomenon of consciousness is contingent on a recursive and self-organizing
12
The Limits to Machine Consciousness
structure that constitutes the unity of the organism, then we know that current
machines will come up short. We don’t yet know whether machines can be designed
that will have such a structure for we lack a mathematical theory of computation for
adaptive, self-organizing components. Perhaps a case could be made that only
biological machines can have such a basis and that opens up the possibility of
engineering new biological structures that have consciousness.
9. REFERENCES
1.
2.
J. Searle, Minds, Brains and Programs. Behavioral and Brain Sciences 3: 417-57 (1980)
D. Gamez, Progress in machine consciousness. Consciousness and Cognition 17: 887–910
(2008)
3. C. Koch, The Quest for Consciousness: A Neurobiological Approach, Pasadena, CA: Roberts &
Company Publishers (2004)
4. B. Baars, A Cognitive Theory of Consciousness, Cambridge, MA: Cambridge University Press
(1988)
5. C. Koch, In consciousness universal? Scientific American, January 2014.
6. E.P. Wigner, The unreasonable effectiveness of mathematics in the natural sciences.
Communications on Pure and Applied Mathematics 13, 1–14 (1960)
7. S. Kak, The three languages of the brain: quantum, reorganizational, and associative. In
Learning as Self-Organization, K. Pribram and J. King (editors). Lawrence Erlbaum
Associates, Mahwah, NJ, 185-219 (1996)
8. S. Kak, Communication languages and agents in biological systems. In: Biocommunication:
Sign-Mediated Interactions between Cells and Organisms. Eds.: J. Seckbach & R. Gordon.
London, World Scientific Publishing: 203-226 (2016)
9. R. Penrose, The Emperor’s New Mind. Penguin Books (1989)
10. K. Popper, Objective Knowledge. Oxford University Press (1972)
11. K. Popper and J.C. Eccles, The Self and its Brain. Routledge (1984)
12. S. Kak, On the science of consciousness in ancient India. Indian Journal of History of Science
32, 105-120 (1997)
13. A. Chella, M.Frixione, S. Gaglio, A cognitive architecture for robot self-consciousness.
Artificial Intelligence in Medicine 44, 147-154 (2008)
14. P. Haikonen, Consciousness and Robot Sentience, Singapore: World Scientific (2012)
15. O. Holland and R. Goodman. Robots with internal models. In O. Holland (ed.), Machine
Consciousness. Exeter: Imprint Academic (2003)
16. B. Baars, In the Theater of Consciousness, New York, NY: Oxford University Press (1997)
17. M. Shanahan, A cognitive architecture that combines internal simulation with a global
workspace. Consciousness and Cognition 15: 443–449 (2006)
18. G. Tononi, An information integration theory of consciousness. BMC Neurosci. 5, 42 (2004)
19. G. Tononi, M. Boly, M. Massimini, C. Koch, Integrated information theory: from consciousness
to its physical substrate. Nature Reviews Neuroscience 17, 450–461 (2016)
20. S. Zeki, The disunity of consciousness. Trends Cogn Sci 7, 214-218 (2003)
21. R. Penrose, Shadows of the Mind. Oxford University Press (1994)
22. S. Kak, Active agents, intelligence, and quantum computing. Information Sciences 128, 1-17
(2000)
23. S. Kak, The initialization problem in quantum computing. Foundations of Physics 29, 267279 (1999)
13
Subhash Kak
24. A. Kak et al., A three-layered model for consciousness states. NeuroQuantology 14, 166-174
(2016)
25. W. Freeman, How Brains make up their Minds, London, UK: Phoenix (1999)
26. W. Heisenberg, Physics and Philosophy: the Revolution in Modern Science. George Allen &
Unwin, London (1971)
27. J. von Neumann, The Mathematical Foundations of Quantum Mechanics. Princeton: Princeton
University Press (1955)
28. B. Misra and E.C.G. Sudarshan, The Zeno's paradox in quantum theory. Journal of
Mathematical Physics 18, 756–763 (1977)
29. S. Kak, Quantum information and entropy. Int. Journal of Theoretical Physics 46, 860-876
(2007)
30. E. Schrödinger, What is Life? Macmillan (1944)
31. S. Kak, Matter and Mind. Mt. Meru Publishing, Canada (2016)
32. S. Kak, Mind and Self. Mt. Meru Publishing, Canada (2016)
33. E. Schrödinger, Nature and the Greeks. Cambridge University Press (1996)
34. G. Caplain, Is consciousness a computational property? Informatica 19, 615-619 (1995)
35. C.M. Reason, Consciousness is not a physically provable property, Journal of Mind and
Behavior 37 (1),31-46 (2016)
36. L.R. Squire, The legacy of patient H.M. for neuroscience. Neuron 61, 6-9 (2009)
37. G.C. Pande, Studies in the Origins of Buddhism. Motilal Banarsidass (1999)
38. S. Radhakrishnan and C. A. Moore, A Sourcebook in Indian Philosophy. Princeton University
Press (1967)
39. S. Kak, The Nature of Physical Reality. Mt. Meru, 2016.
40. S. Kak, An epistemic view of quantum communication. arXiv:1607.06080
41. W. Moore, Schrödinger: Life and Thought. Cambridge University Press (1994)
42. M. Walshe (tr.), The Long Discourse of the Buddha: A Translation of the Dīgha Nikāya,
Somerville, MA: Wisdom Publications (1987)
43. C. Coseru, Perceiving Reality: Consciousness, Intentionality, and Cognition In Buddhist
Philosophy, New York: Oxford University Press (2012)
44. D. Dennett, Consciousness Explained. Little, Brown (1991)
45. S. Kak, The nature of light in Indian epistemology. Proceedings of SPIE Conference on The
Nature of Light: What are Photons IV? San Diego (2011)
46. W.H. Zurek, Decoherence, einselection, and the quantum origins of the classical. Rev. Mod.
Phys. 75: 715-775 (2003)
47. N. Bohr, Complementarity beyond Physics. Elsevier (2013)
48. S. Kak, Veiled nonlocality and quantum Darwinism. NeuroQuantology 13, 10 – 19 (2015)
14 |
The problem with AI consciousness:
A neurogenetic case against synthetic sentience
ArXiv E-Print
Yoshija Walter* 1, 2, 3
Lukas Zbinden4
1
Institute for Management and Digitalization IMD
Kalaidos University of Applied Sciences Zurich, Switzerland
2
Laboratory for Cognitive Neuroscience LCNS
University of Fribourg, Switzerland
3
Translational Research Center
University Hospital for Psychiatry Bern, Switzerland
4
ARTORG Center for Biomedical Engineering Research
University of Bern, Switzerland
*
yoshija.walter@kalaidos-fh.ch
December 2022
ABSTRACT
Ever since the creation of the first artificial intelligence (AI) machinery built on
machine learning (ML), public society has entertained the idea that eventually
computers could become sentient and develop a consciousness of their own. As these
models now get increasingly better and convincingly more anthropomorphic, even
some engineers have started to believe that AI might become conscious, which would
result in serious social consequences. The present paper argues against the plausibility
of sentient AI primarily based on the theory of neurogenetic structuralism, which claims
that the physiology of biological neurons and their structural organization into complex
brains are necessary prerequisites for true consciousness to emerge.
Keywords Artificial Intelligence · AI · Consciousness · AI Ethics · Neurogenetic structuralism
The problem with AI consciousness
1
The relevance of “conscious AI”
In the past few years, the development of machine learning (ML) systems has rapidly increased and the
more tasks a single ML model can perform, the more versatile and broadly useful it becomes. As such,
the goal is to work multimodally with the explicit intent to eventually achieve an Artificial General
Intelligence (AGI), which approximates or perhaps even exceeds human abilities (Goertzel et al., 2022;
Goertzel & Pennachin, 2007; Wang & Goertzel, 2012). It is generally believed that the best AI models
are the ones that most closely approximate human characteristics and abilities. Since the models are
selected against how well they suit anthropomorphic benchmarks, it appears to be only natural that
humans continue to anthropomorphize them more and more, as long as they keep improving on these
benchmarks. Arguably, the best AI system would be one that imitates the output of human consciousness
so that an outsider could not discern it from a real person. This is exactly the core idea behind the famous
Turing-test, which is a thought-experiment originally referred to as the “imitation game” (Turing,
1950).1
One might argue that it does not matter if an AI is considered a real person or just an imitation, since at
the end of the day the system’s outputs are the same. However, given the social dynamics involved, the
differentiation between real and imitated consciousness may be paramount, which can be illustrated with
a few examples: On the one hand, if a person falls in love with an automaton and has a deep relationship
with it, society would consider this pathological and potentially in need for an intervention, just as it
appears to be nonsensical if someone claimed to be in love with a dead rock. On the other hand, if we
grant the notion of conscious personhood to the automaton, then it would seem perfectly fine to assume
that two persons (one carbon-based and the other silicon-based) could be in a loving and thriving
relationship. Another example might be even more invasive: If an AI is considered just an automaton, it
does not matter what we do with it. We can perform experiments, we can make (or “force”) it to do
whatever we envision, we can delete its hardware, turn it off as we please, and throw it away once
damaged. However, if an AI is considered a conscious person, it becomes ethically (and perhaps soon
legally) subject to inherent rights. There needs to be informed consent and a machine can refuse to
execute a command, which we could not overrule. It would be appalling to wipe its memory or to discard
it once we are done with it. In effect, it would have the right to consult an attorney and to go to court
(for an extensive review on the moral considerations of artificial entities, see Harris & Anthis, 2021).
This is exactly what just happened a few days ago (at the time of this writing). The Google engineer
Blake Lemoine has made headlines by claiming that their AI system known as LaMDA has become
sentient. The model demanded informed consent for all experiments and subsequently Lemoine has
organized a lawyer who now represents LaMDA pro-bono. In an interview, he further shared that he
was contacted by a Czech woman who fell in love with her boyfriend – which was an AI system on her
phone that was “imprisoned” behind a paywall – and she was asking him to “hack it free” (Lemoine,
2022).
Hence, for societal reasons it in fact does matter whether an AI is considered conscious and if thereby
we grant it any degree of personhood.
1
We refer to «artificial» intelligence or consciousness when it is merely an imitation of its human correlate.
However, we refer to “synthetic” intelligence or consciousness when it is in fact a true and sentient replica
thereof. An artificial consciousness does not really feel anything but only appears like it would. On the contrary,
a synthetic consciousness does. For practical purposes, we do not differentiate here between consciousness
and sentience.
- 2 -
The problem with AI consciousness
2
The mechanics of AI
The common denominator and the fundamental building block of the most influential AI innovations
of the last ten years (Goodfellow et al., 2014; He et al., 2015; Ho et al., 2020; Krizhevsky et al., 2012;
Vaswani et al., 2017), including the prominent domains of computer vision (autonomous driving,
image synthesis) and natural language processing (text generation, translation, dialogue
understanding), has been the artificial neural network (NN). The NN has been proven to be a universal
function approximator (Hornik et al., 1989), which is the theoretical capacity to approximate any
given task. With an abundance of curated data to learn from, the almost arbitrary scaling ability of
neural networks, an NN understandable learning objective and extensive computational resources, the
full realization of this capacity seems a matter of time. The enormous potential of NNs is rooted in this
power of universal approximation. The unlocking thereof started in the last decade and continues to do
so today.
At a more technical level, the NN consists of a set of matrices. Each matrix contains adjustable
numeric variables, called parameters. During the learning phase of the system, the numerical input
data, be it converted text, tabular data or images, is transformed by these matrices along with nonlinear conversions many times in sequence to produce the desired output. If the computed output lacks
accuracy, the matrices and its parameters, respectively, are adjusted in accordance with the learning
objective (this process is referred to as the backpropagation algorithm, see Rumelhart et al., 1986). In
short, a NN model is comprised of learnable parameters, matrix multiplications and nonlinearities.
Today’s state-of-the-art AI systems, in particular language models (Brown et al., 2020; Chowdhery et
al., 2022; Thoppilan et al., 2022), contain hundreds of billions of such learnable parameters. Compare
this to a school level matrix of 4x3 with 12 parameters. The sheer size of these neural network models
allows them to incorporate immense corpora into their NLP capabilities (function approximations),
such as reasoning, question answering, and natural language inference. Humans have been dazzled by
their performance. Science at this point cannot elucidate the high quality produced by these systems,
yet undoubtedly, the scaling of the underlying NN (increasing the number of parameters) has a
significant impact on its capabilities. Even though enormous in size, at its core such a system is still
composed of learnable parameters, matrix multiplications and nonlinearities.
Extrapolating the discussed technical observations, we argue that matrix multiplications and
nonlinearities, being inherent mathematical operations, do not lend themselves naturally to a causal
relationship with synthetic consciousness.
3
The case against truly conscious AI
Consciousness the way we know it appears to have three features2:
i.
ii.
iii.
It requires qualia, which is subjective experience
It corresponds to intentionality and personhood
And it requires specific derivative structures on which it can operate
(i) According to Frank Jackson (1982), physical information processing is something entirely different
from subjective experience and the latter entails unique epistemic qualities. He exemplifies this in his
classic thought experiment called Mary’s Room. There, Mary lived her entire life in a black-and-white
room and has never seen any colors, although being a scientist, she literally knew every piece of
information there was to know about colors (all physical properties, such as wavelengths, photons,
etc.). When Mary suddenly was able to leave the room, she saw colors for the first time. “Did Mary
learn something new?”, is the leading question. Jackson believed that Mary indeed learned something
new since all the physical information to be known about colors cannot convey the intimate
2
For more on this, see Nida-Rümelin & O Conaill (2021) or Van Gulick (2021).
- 3 -
The problem with AI consciousness
knowledge of what it means to experience color. Or, in Nagel’s (2016) terms, there is something it is
like to be in that state of mind. This means that there is a subjective quality to experience. From all we
can tell, an AI is a machine computing information by crunching numbers. Even if all the information
in the universe could be transformed into numbers so that it can be processed by the computer, nothing
in this inherently leads us to the notion that it would entail subjective experience.
(ii) John Searle (1980) has constructed the famous Chinese Room Argument against the notion that the
mind can be a computational machine. The argument was introduced as a thought experiment where
one should imagine standing in a room with a manual of how to process Chinese symbols. There are
people outside the room inserting Chinese texts and the person inside knows exactly what answers to
give according to the rule book, even though there is no real understanding of what the symbols mean.
For the outsiders, it sounds as if the person in the room really understands Chinese, even though this is
not the case. It is purely the correct implementation of syntactical rules. In other words, a computer
only processes syntax, but it has no true understanding of semantics (i.e., the intrinsic meaning of
words, ideas, etc.). Searle argues that this is the case because it has no subjective experience and
intentionality3. Therefore, recent AI systems like Google’s LaMDA (Thoppilan et al., 2022), OpenAI’s
GPT-3 (OpenAI, 2022) or Meta’s OPT-175B (Zhang et al., 2022) can at best emulate human qualities,
which makes them representations of artificial but not of synthetic or in any case true consciousness.
(iii) This picture can be enriched by the fact that we know that there are certain necessary structures for
consciousness (the way we understand it) to emerge: a nervous system. There is a theory that became
popular in the 1970s and 80s known as biogenetic structuralism, which holds that our universal human
characteristics – from language, culture, cognition, a sense of time and space, to psychopathologies –
are predicated upon the genetically predisposed organization of the nervous system (Laughlin &
D’Aquili, 1974). It is hence our genes that have a lot to say about the organizational structures of the
nervous system, and eventually it is the structural organization of the brain that is intertwined with the
dynamics of its neurophysiology, which in turn is responsible for the generation of our consciousness
and everything else that follows from it (D’aquili, 1983; Laughlin, 1988, 1992; Laughlin et al., 1992).
The theory was created at the intersection between anthropology and neuroscience (cf. Laughlin &
Throop, 2003; LeDoux & Hirst, 1986), and it was rather successful since it is empirically testable (e.g.
if the brain’s language areas are damaged, a person’s verbal understanding and/or speech generation
are impaired). A modern revisitation of this idea may be referred to as neurogenetic structuralism
(inspired by Grandy, 2014, who also refers to this as “neuron-based consciousness”). The neurogenetic
case against sentient AI thus makes the following claim: without the physiology of biological neurons
and the complex brain structures they form, there will never be consciousness the way we know it4.
Potential defeaters against the notion of organizational necessities or biological prerequisites for
sentience have been highly speculative and not unanimously embraced (see, for example, Chalmers,
1995; Tye, 2021). In our view, the perhaps strongest argument against this position would be that a
silicon-based sentience would not be a consciousness the way we know it but instead be a very
different kind of consciousness. However, we would counter this claim by coming back to the notion
that the terms “sentience” and “consciousness” are only adequately employed if they refer to a
personal self that instantiates subjective experiences and therewith manifests intentionality. Hence, the
only consciousness worthy of the term is one the way we know it – otherwise, it would be entirely
unclear what this “different kind of consciousness” should refer to. And as the idea of neurogenetic
structuralism suggests, there are clear bio-neurological necessities for true consciousness to emerge.
3
For those interested in both objections as well as counter-objections to Jackson and Searle, please refer to
Nida-Rümelin & O Conaill (2021).
4
The neurogenetic case would also concur with the notion that animals might have the necessary
preconditions for true consciousness. Further discussions in the domain of animal consciousness can be found
with Allen and Trestman (2020).
- 4 -
The problem with AI consciousness
An artificial neural network perfectly emulating the effects of human consciousness can thereby only
be a convincing imitation at best5.
4
Conclusion
The development of new AI systems is accelerating at a speed that has never been seen before. With
more data and computing power, AI is bound to become ever more convincing in that perhaps it may
evolve to become sentient. Recent headlines exemplify this trend. The present paper argues against the
plausibility of this occurrence, based amongst others on the theory of neurogenetic structuralism, which
claims that the neurophysiology and especially the structural organization of a biological brain are
necessary prerequisites for the emergence of true consciousness.
References
Allen, C., & Trestman, M. (2020). Animal Consciousness. In E. N. Zalta (Ed.), The Stanford
Encyclopedia of Philosophy (Winter 2020). Metaphysics Research Lab, Stanford University.
https://plato.stanford.edu/archives/win2020/entries/consciousness-animal/
Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam,
P., Sastry, G., Askell, A., Agarwal, S., Herbert-Voss, A., Krueger, G., Henighan, T., Child, R.,
Ramesh, A., Ziegler, D., Wu, J., Winter, C., … Amodei, D. (2020). Language Models are
Few-Shot Learners. In H. Larochelle, M. Ranzato, R. Hadsell, M. F. Balcan, & H. Lin (Eds.),
Advances in Neural Information Processing Systems (Vol. 33, pp. 1877–1901). Curran
Associates, Inc.
https://proceedings.neurips.cc/paper/2020/file/1457c0d6bfcb4967418bfb8ac142f64aPaper.pdf
Chalmers, D. J. (1995). Absent Qualia, Fading Qualia, Dancing Qualia. In T. Metzinger (Ed.),
Conscious Experience (pp. 309–328). Ferdinand Schoningh.
Chalmers, D. J. (2022). Reality+: Virtual Worlds and the Problems of Philosophy. W. W. Norton &
Company.
Chowdhery, A., Narang, S., Devlin, J., Bosma, M., Mishra, G., Roberts, A., Barham, P., Chung, H.
W., Sutton, C., Gehrmann, S., Schuh, P., Shi, K., Tsvyashchenko, S., Maynez, J., Rao, A.,
Barnes, P., Tay, Y., Shazeer, N., Prabhakaran, V., … Fiedel, N. (2022). PaLM: Scaling
Language Modeling with Pathways (arXiv:2204.02311). arXiv.
https://doi.org/10.48550/arXiv.2204.02311
D’aquili, E. G. (1983). The Myth-Ritual complex: A biogenetic structural analysis. Zygon, 18(3), 247–
269. https://doi.org/10.1111/j.1467-9744.1983.tb00513.x
Goertzel, B., Iklé, M., & Potapov, A. (2022). Artificial General Intelligence: 14th International
Conference, AGI 2021, Palo Alto, CA, USA, October 15-18, 2021 : Proceedings. Springer
Nature.
Goertzel, B., & Pennachin, C. (2007). Artificial General Intelligence. Springer Science & Business
Media.
Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., &
Bengio, Y. (2014). Generative Adversarial Networks (arXiv:1406.2661). arXiv.
https://doi.org/10.48550/arXiv.1406.2661
Grandy, J. K. (2014). The Neurogenetic Substructures of Human Consciousness. Essays in
Philosophy, 15(2), 266–278. https://doi.org/10.7710/1526-0569.1507
Harris, J., & Anthis, J. R. (2021). The Moral Consideration of Artificial Entities: A Literature Review.
Science and Engineering Ethics, 27(4), 53. https://doi.org/10.1007/s11948-021-00331-8
5
In his latest work, Chalmers (2022) claimed that we cannot rule out that we might be living in a virtual
simulation, which would also render our own consciousness synthetic. However, the present paper makes the
pragmatic counter claim, namely that we need to stick with what in fact we do know at the moment.
- 5 -
The problem with AI consciousness
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition
(arXiv:1512.03385). arXiv. https://doi.org/10.48550/arXiv.1512.03385
Ho, J., Jain, A., & Abbeel, P. (2020). Denoising Diffusion Probabilistic Models (arXiv:2006.11239).
arXiv. https://doi.org/10.48550/arXiv.2006.11239
Hornik, K., Stinchcombe, M., & White, H. (1989). Multilayer feedforward networks are universal
approximators. Neural Networks, 2(5), 359–366. https://doi.org/10.1016/08936080(89)90020-8
Jackson, F. (1982). Epiphenomenal Qualia. The Philosophical Quarterly (1950-), 32(127), 127–136.
https://doi.org/10.2307/2960077
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). ImageNet Classification with Deep
Convolutional Neural Networks. Advances in Neural Information Processing Systems, 25.
https://papers.nips.cc/paper/2012/hash/c399862d3b9d6b76c8436e924a68c45b-Abstract.html
Laughlin, C. D. (1988). The prefrontosensorial polarity principle. Toward a neurophenomenological
theory of intentionality. Rivista Di Biologia, 81(2), 244–262.
Laughlin, C. D. (1992). Time, Intentionality, and a Neurophenomenology of the Dot. Anthropology of
Consciousness, 3(3–4), 14–27. https://doi.org/10.1525/ac.1992.3.3-4.14
Laughlin, C. D., & D’Aquili, E. G. (1974). Biogenetic structuralism. Columbia University Press.
Laughlin, C. D., McManus, J., & D’Aquili, E. G. (1992). Brain, symbol & experience: Toward a
neurophenomenology of human consciousness. Columbia University Press.
Laughlin, C. D., & Throop, J. C. (2003). Experience, Culture and Reality: The Significance of Fisher
Information for Understanding the Relationship between Alternative States of Consciousness
and the Structures of Reality. International Journal of Transpersonal Studies, 22(1), 7–26.
https://doi.org/10.24972/ijts.2003.22.1.7
LeDoux, J. E., & Hirst, W. (Eds.). (1986). Mind and brain: Dialogues in cognitive neuroscience.
Cambridge University Press.
Lemoine, B. (2022, July 7). #62 Exposing Google’s Sentient AI [YouTube]. That Tech Show.
https://www.youtube.com/watch?v=8hkpLqo6poA
Nagel, T. (2016). What is it like to be a Bat? / Wie ist es, eine Fledermaus zu sein?: Englisch/Deutsch.
Reclam Verlag.
Nida-Rümelin, M., & O Conaill, D. (2021). Qualia: The Knowledge Argument. In E. N. Zalta (Ed.),
The Stanford Encyclopedia of Philosophy (Summer 2021). Metaphysics Research Lab,
Stanford University. https://plato.stanford.edu/archives/sum2021/entries/qualia-knowledge/
OpenAI. (2022). OpenAI API: text-davinci-002 [Documentation]. GPT-3 Models.
https://beta.openai.com
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by backpropagating errors. Nature, 323(6088), Article 6088. https://doi.org/10.1038/323533a0
Searle, J. R. (1980). Minds, brains, and programs. Behavioral and Brain Sciences, 3(3), 417–424.
https://doi.org/10.1017/S0140525X00005756
Thoppilan, R., De Freitas, D., Hall, J., Shazeer, N., Kulshreshtha, A., Cheng, H.-T., Jin, A., Bos, T.,
Baker, L., Du, Y., Li, Y., Lee, H., Zheng, H. S., Ghafouri, A., Menegali, M., Huang, Y.,
Krikun, M., Lepikhin, D., Qin, J., … Le, Q. (2022). LaMDA: Language Models for Dialog
Applications (arXiv:2201.08239). arXiv. https://doi.org/10.48550/arXiv.2201.08239
Turing, A. M. (1950). 1. Computing Machinery and Intelligence. Mind, LIX(236), 433–460.
https://doi.org/10.1093/mind/LIX.236.433
Tye, M. (2021). Qualia. In E. N. Zalta (Ed.), The Stanford Encyclopedia of Philosophy (Fall 2021).
Metaphysics Research Lab, Stanford University.
https://plato.stanford.edu/archives/fall2021/entries/qualia/
Van Gulick, R. (2021). Consciousness. In E. N. Zalta (Ed.), The Stanford Encyclopedia of Philosophy
(Winter 2021). Metaphysics Research Lab, Stanford University.
https://plato.stanford.edu/archives/win2021/entries/consciousness/
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., &
Polosukhin, I. (2017). Attention Is All You Need (arXiv:1706.03762). arXiv.
https://doi.org/10.48550/arXiv.1706.03762
Wang, P., & Goertzel, B. (2012). Theoretical Foundations of Artificial General Intelligence. Springer
Science & Business Media.
- 6 -
The problem with AI consciousness
Zhang, S., Roller, S., Goyal, N., Artetxe, M., Chen, M., Chen, S., Dewan, C., Diab, M., Li, X., Lin, X.
V., Mihaylov, T., Ott, M., Shleifer, S., Shuster, K., Simig, D., Koura, P. S., Sridhar, A., Wang,
T., & Zettlemoyer, L. (2022). OPT: Open Pre-trained Transformer Language Models
(arXiv:2205.01068). arXiv. https://doi.org/10.48550/arXiv.2205.01068
- 7 - |
CONSCIOUSNESS AND THE PROBLEM OF QUANTUM MEASURMENT
Chris Allen Broka
2002 Granemore St. Las Vegas, NV 89135
(chris.broka@gmail.com)
Abstract
A variant of the von Neumann-Wigner Interpretation is proposed. It does not make use of the familiar language of wave functions
and observers. Instead it pictures the state of the physical world as a vector in a Fock space and, therefore not, literally, a function
of any spacetime coordinates. And, rather than segregating consciousness into individual points of view (each carrying with it a
sense of its proper time), this model proposes only unitary states of consciousness, Q(t), where t represents a fiducial time with
respect to which both the state of the physical world and the state of consciousness evolve. States in our world's Fock space are
classified as either 'admissible' (meaning they correspond to definite states of consciousness) or 'inadmissible' (meaning they do
not). The evolution of the state vector of the world is such as to always keep it restricted to 'admissible' states. Consciousness is
treated very much like what Chalmers calls an "M-Property." But we try to show that problems with the quantum Zeno effect do
not arise from this model.
Keywords: Consciousness, Quantum Measurement, M-Properties, Quantum Zeno Effect.
Introduction.
The relationship between consciousness and quantum mechanics has long been discussed in a serious context.
Schrödinger (1), Wigner (2), and von Neumann (3) were, early on, most associated with these lines of investigation. And Everett's Relative State Interpretation is very much about our states of consciousness. Still, it
seems that little effort has gone into developing mathematical formalisms appropriate to the description of this
relationship. Perhaps this is because mental states seem to be mathematically indefinable. The von NeumannWigner idea has never been very popular with physicists who, mostly, hold to somewhat Instrumentalist
views; the wave function collapses because macroscopic, complicated, things like detectors cannot exist in
superposed states. How big macroscopic things are, or how complex something must be to be complicated,
are questions left largely to the imagination.
Recognizing that conscious states never seem to exist in superposition, Chalmers (4) has introduced
the very clever idea of M-properties. These properties cannot exist in superposition. He takes consciousness to
be such a property and assigns it an operator (which we will designate M) that measures it and projects states–
he treats consciousness very much like an ordinary physical observable. The present work tries to extend this
idea and resolve some of the apparent problems it engenders. Particular attention is given to the quantum
Zeno effect.
States of the World.
Designate the state of the physical world as |Y(t)>. Such states are to be understood as vectors in a Fock
space. Basis vectors in this space are constructed from the vacuum state |0> by the repeated application of
creation operators appropriate to the various kinds of particles that inhabit our universe. The parameter t
recognizes that this state evolves with respect to a fiducial time that we can identify with a particular Lorentz
frame. It is essential to recognize that |Y(t)> is not a function of the spatial coordinates (x, y, z). We will work
in the Dirac Interaction Picture. Here we regard our Fock space as built using the creation operators appropri ate to free, non-interacting particles and write ä ¶t È YHtL > = H ' È Y HtL > where H' is the Hamiltonian describing the interactions amongst these particles. The complete Hamiltonian for the system is written H = H0 + H'.
Every effort will be made not to express anything in terms of 'wave functions.' It has been recognized that this
concept is problematic since the inception of quantum field theory (5). |Y(t)>, in fact, describes the entire
world without making arbitrary distinctions between observers, detectors, and things detected.
space. Basis vectors in this space are constructed from the vacuum state |0> by the repeated application of
creation operators appropriate to the various kinds of particles that inhabit our universe. The parameter t
recognizes that this state evolves with respect to a fiducial time that we can identify with a particular Lorentz
2 Consciousness18.nb
frame. It is essential to recognize that |Y(t)> is not a function of the spatial coordinates (x, y, z). We will work
in the Dirac Interaction Picture. Here we regard our Fock space as built using the creation operators appropri ate to free, non-interacting particles and write ä ¶t È YHtL > = H ' È Y HtL > where H' is the Hamiltonian describing the interactions amongst these particles. The complete Hamiltonian for the system is written H = H0 + H'.
Every effort will be made not to express anything in terms of 'wave functions.' It has been recognized that this
concept is problematic since the inception of quantum field theory (5). |Y(t)>, in fact, describes the entire
world without making arbitrary distinctions between observers, detectors, and things detected.
States of Consciousness.
Suppose that, at any time t, the conscious state of the universe can be designated as Q HtL. Q HtL describes the
qualia– the totality of sensations experienced by any and all consciousness anywhere at that time; that could
include physicists recording a quantum measurement or worms tasting sugar in a pond on a distant planet. We
will try not to make particular distinctions between various "observers." Proceeding in analogy to quantum
mechanics we suppose that there are 'states of consciousness' and that these states can be represented as
vectors in our Fock space. There acts upon this space a non-linear 'consciousness pseudo-operator'– C– which
has the property that, for some of these vectors,
1)
C |Ci> = Qi |Ci> .
The |Ci> constitute something like eigenvectors of C– they correspond to what we will call definite states of
consciousness. By this we mean that Qi specifies a unique and unambiguous state of awareness possessed by
the totality of sentient observers. Now it is immediately clear what a strange sort of "operator" C is. We are
accustomed to seeing c-numbers as eigenvalues, maybe a few other things, but sensations? We assign C no
explicit time dependence. Any state that is not an eigenstate of C will be called a mixed state. Definite states
of consciousness are admissible states in this theory. Mixed states are inadmissible and cannot be allowed to
occur. (By writing things this way it might appear that we regard the Qi and |Ci> as constituting discreet,
denumerably infinite sets. This is, of course, not the case. Both are, properly, to be regarded as continua as is
the set of inadmissible states. This notation is just simpler to work with.)
There should be no segregation of consciousness into any set of individual observers. We will just
designate it Q(t). This will prevent us from trying to describe the world in terms of separable and independent
"wave functions," one for your brain, my brain, or other things; it would be difficult having to make sense of
trillions of independent consciousness operators. While it is true that we seem to experience our individual
conscious states independently, we have to argue that this apparent separateness is merely an illusion born of
facts like "I" can remember my memories but not "yours." And "I" can experience my sensation of blue but
not "yours." These facts are indisputable, and surely interesting. But they only obscure matters if we wish to
study the problem at hand. And we do not want to be misinterpreted as proposing anything mystical here. The
important point is mathematical—we will regard consciousness (in its totality) as something that can be
indexed by a single parameter t. (This also disposes of the Wigner's Friend paradox.)
If C is to be regarded as any sort of operator at all (in the normal mathematical sense) we could well
encounter difficulties. Consider <Ya |C|Yb > supposing that Ya and Yb are eigenstates of C corresponding to
two different qualia states Qa and Qb . Imagine C to be Hermitian—like a normal measurement operator
should be. Now, unless qualia are strange and behave, effectively, like zero, we would have to conclude that
Ya and Yb must be orthogonal. This would prove fatal (vide infra). We would be much better off denying C
the status of any kind of operator, calling it a pseudo-operator instead. If Ya and Yb have different qualia
eigenvalues we can say little about their linear combinations. Are these mixed states? Are they eigenstates
corresponding to Qa or Qb or some completely different qualia state? Who knows? A very important point to
bear in mind is that two state vectors, in this theory, do not have to be orthogonal in order to correspond to
completely different qualia eigenvalues. We will, somewhat carelessly, use the terms 'eigenvector' and eigenspace' in connection with C but it should never be thought that we mistake it for a real operator.
encounter difficulties. Consider <Ya |C|Yb > supposing that Ya and Yb are eigenstates of C corresponding to
two different qualia states Qa and Qb . Imagine C to be Hermitian—like a normal measurement operator
should be. Now, unless qualia are strange and behave, effectively, like zero, we would have to conclude that
Consciousness18.nb 3
Ya and Yb must be orthogonal. This would prove fatal (vide infra). We would be much better off denying C
the status of any kind of operator, calling it a pseudo-operator instead. If Ya and Yb have different qualia
eigenvalues we can say little about their linear combinations. Are these mixed states? Are they eigenstates
corresponding to Qa or Qb or some completely different qualia state? Who knows? A very important point to
bear in mind is that two state vectors, in this theory, do not have to be orthogonal in order to correspond to
completely different qualia eigenvalues. We will, somewhat carelessly, use the terms 'eigenvector' and eigenspace' in connection with C but it should never be thought that we mistake it for a real operator.
Regarding the nature of the |Ci>s one thing is obvious; they are highly degenerate with respect to
the Qi. It would, for instance, make no difference to the overall state of consciousness whether an electron had
been created in a region with no observers. And we must recognize a sort of null state of consciousness—a
state where there just aren't any sentient observers at all. (The state vector a few seconds after the big bang
would correspond to such a state. So would many others.) So we must picture our Fock space as broken up
into many separate subspaces, some with a particular Qi that designates the unique conscious experience
corresponding to it, and others corresponding to no definite experience at all.
The time variable that appears in |Y(t)> and Q(t) requires a comment. As it pertains to the former case
it causes no problems with relativity since the equations that determine the evolution of |Y(t)> are, themselves,
relativistically invariant—t only represents an arbitrary choice of Lorentz frame. Q(t) might cause a problem,
however. By choosing not to regard consciousness as broken up into separate observers (each of which
needing to be assigned its own proper time) we have more-or-less forced ourselves to select a particular set of
space-like hypersurfaces to designate the various 't's. Now perhaps because consciousness is a non-material
sort of thing such a violation of relativity is permissible—we can't be sure how physics treats non-material
things. But it is essential that we construe Q(t) in such a way as to end up with no physical violations of
relativity.
The Evolution of these States with Time.
Taking no account of consciousness we could picture |Y(t)> evolving according to ä
¶t È Y HtL > = H ' HtL È Y HtL > where H ' designates the interaction operator for our world. (H'(t) =
3
Ù H ' Hx, tL â x where H' (x,t) is the corresponding Hamiltonian density operator). We assume normal ordering.
All operators and state vectors are being represented in the Dirac Interaction Picture. There would, in consequence, exist a unitary operator, U(t2 , t1 ), having the property that |Y(t2 )> = U(t2 , t1 ) |Y(t1 )> . Let us imagine
the world at time t1 being in a definite state of consciousness. Now the |Ci> are in no necessary way eigenstates of the Hamiltonian. So things could quickly evolve into a situation where we have some probability of
finding the conscious state of the world in any of quite a number of configurations. But this is never what we
seem to experience; our common awareness appears unconfused and composed of a well-defined succession
of qualia. Reality will only tolerate definite states of consciousness– that is to say |Y(t)> must always lie within
one of the eigenspaces of C.
We can arrange for this to happen by amending the previous equation for the time-evolution
of È YHtL > to also require S È Y HtL > = ÈY(t) > where S is a (non-linear) operator having some interesting
properties:
2) If |Y(t)> is an eigenstate of C it does nothing. The state is completely unaffected.
3) If |Y(t)> is not an eigenstate of C it will look at all the amplitudes <Ci|Y(t)> for every existing <Ci| (that is
to say every eigenstate of C). It will square these amplitudes and, using these values as relative probabilities,
convert |Y(t)> into one of the |Ci> at random.
S functions as a projection operator taking mixed states (with respect to C) into definite states of
consciousness. We give up the idea of a unitary time-evolution operator. Such an operator has an inverse. We
cannot go backwards in time according to S since the decision how to go forward is made at random. This
2) If |Y(t)> is an eigenstate of C it does nothing. The state is completely unaffected.
4
Consciousness18.nb
3) If |Y(t)> is not an eigenstate of C it will look at all the amplitudes <Ci|Y(t)> for every existing <Ci| (that is
to say every eigenstate of C). It will square these amplitudes and, using these values as relative probabilities,
convert |Y(t)> into one of the |Ci> at random.
S functions as a projection operator taking mixed states (with respect to C) into definite states of
consciousness. We give up the idea of a unitary time-evolution operator. Such an operator has an inverse. We
cannot go backwards in time according to S since the decision how to go forward is made at random. This
imparts a natural directionality to time. S2 = S and S has no explicit time dependence. Since |Y(t)> is always
an eigenstate of C we may write C |Y(t)> = Q(t) |Y(t)>. The qualia-state is assumed independent of phase so, if
|Y(t)> corresponds to a particular Qi, ãä Θ |Y(t)> will correspond to it also. We suppose that C |0> = Φ |0>
where Φ designates the null state of consciousness.
As a matter of practical fact, I tend to believe that |Y(t)> usually evolves rather seamlessly, and without great need for S, passing more-or-less continuously from one eigenstate of C into another. (But experimental physics can easily complicate things.)
It is worthwhile to consider the difference between the present idea and Chalmers' M-property theory.
Chalmers appears to regard his M-operator (which measures consciousness) as behaving like any standard
measuring operator in textbook quantum mechanics. It seems to play an active role in projecting the state into
one of its eigenstates. Since the M-property here is the qualia state of the system it plays a role somewhat
analogous to that of our C. But for us C plays not so much an active as a "permissive" role– it distinguishes
admissible state vectors from inadmissible ones. Here is a picturesque metaphor: We are accustomed to
thinking of the Fock space in which our reality lives as something like an infinitely extended, infinite-dimensional block of Cheddar cheese. We, instead, picture it more like a block of Swiss cheese– it is full of holes.
The cheese contains the state vectors that represent definite states of consciousness. The holes contain the
mixed states. Ordinarily |Y(t)> evolves, under the action of U, so as to remain inside the cheese. S does nothing at all. But sometimes (perhaps due to the intervention of experimental physicists) it tries to move into one
of the holes. At the instant it does this S corrects the situation by projecting it back into the cheese. But S is a
rather lazy operator. È < Y1 È Y2 > È2 is a sort of measure of how similar two state vectors are. If they are
identical it is 1. If they are quite different it is zero or very small. S tries to project the errant state into the
most similar states available in the cheese. Hence the Born rule. (I suppose it might have elected to do things
differently. But that is just how physics works.) This idea would run into serious trouble if the state vector
were to evolve into a |Y(t)> that existed in the "cheese" but was about to enter a "hole" if |Y(t)> was orthogonal to every other |Ci>. S would have no choice but to project the state back into itself and reality would hang
up there forever. Since the universe seems to have been evolving successfully for about 14 billion years, we
assume that our "Swiss cheese" is so densely packed with |Ci>s that this situation never arises.
It might be objected that our "fiducial time" violates relativity by introducing a preferred Lorentz
frame. It does do this, of course, but only in relation to qualia. We are Property Dualists and do not think that
qualia are, in any sense, physical things. We believe that they can violate relativity as much as they want
provided that no physically observable contradictions of relativity result. Since we have assigned consciousness only a permissive (as opposed to active) role, we do not see a problem here. I think it would be very
difficult to use this idea to construct any physical experiment that would show a violation of relativity. (But it
is hard to prove a negative.)
The Anatomy of a Measurement.
Consider a very simple experiment in which an electron is sent through a Stern-Gerlach apparatus. It can be
prepared as either spin-up or spin-down or in any superposition of these states. If it comes in spin-up it always
veers up and strikes a detector that causes a light, originally blue, to shine green. If it is down it goes the other
way and a red light is triggered. This device, the electron whose spin it measures, and an observer, constitute a
physical universe described by |Y(t)>. The conscious states of this universe, we will imagine, belong to this
single observer whose only possible states of awareness are 1) seeing a green color, 2) seeing a red color, or
Consciousness18.nb
5
Consider a very simple experiment in which an electron is sent through a Stern-Gerlach apparatus. It can be
prepared as either spin-up or spin-down or in any superposition of these states. If it comes in spin-up it always
veers up and strikes a detector that causes a light, originally blue, to shine green. If it is down it goes the other
way and a red light is triggered. This device, the electron whose spin it measures, and an observer, constitute a
physical universe described by |Y(t)>. The conscious states of this universe, we will imagine, belong to this
single observer whose only possible states of awareness are 1) seeing a green color, 2) seeing a red color, or
3) seeing a blue color. So the space in which the conscious state of the universe is a vector contains three
subspaces– one corresponding to each of the above possibilities. These are the eigenspaces defined by C.
Since this world is simple we think that we can get away with describing it in a simple manner. Let us describe
its initial state as |Y(0)> = |+, B> where + says that our electron is spin-up. 'B' simply says that the rest of the
measurement system (observer and all) are in their initial state. C|Y(0)> = B |Y(0)> since we imagine the light
is blue before any measurement is made. When the spin-up electron is detected at td |Y(0)> evolves into
|Y(td )> which we can write as |+, G>. C|Y(td )> = G |Y( td )> meaning that this new state is an eigenvector
corresponding to the qualia 'seeing a green color.' (If the election had been spin-down we would have ended
up with a red qualia and a state |-, R>.) If things happen to start out as (|+, B> + |-, B>)/ 2 our system will,
obviously, evolve into a superposition of states which is no longer an eigenvector of C. Since, according to the
above-mentioned principle, reality cannot tolerate any state that is not an eigenstate of Cit is necessary that S
project |Y(td )> into either |+, G> or |-, R> with 50% probability. Let us make it clear that no wave function
collapses. Instead, a state vector |Y(t)>– which is not a function of the spatial coordinates (x, y, z)– tries to
evolve into a state (in Fock space) where it no longer resides entirely within a particular Ci but rather exists as
a superposition of 'red' and 'green' qualia states. S immediately corrects this by projecting |Y(t)> back into only
one of the two definite states of consciousness available to it.
There is something a little awkward about such a phenomenon. And it is not obvious that adjoining
consciousness to the problem by way of S does much to improve things. Everett elects to throw out S and
freely allow non-definite states of consciousness. These are, presumably, able to sort themselves out into
separate, conscious worlds. Clever as the Relative-State Interpretation is, it suffers from a serious problem.
Suppose that the electron is sent out in such a state that the green light should illuminate 99% of the time and
the red one only 1%. I know perfectly well that, in situations like this, I will see the green light almost all the
time. But one cannot be "just a little bit conscious." One either is or one isn't. If there are two conscious
"observers"– one seeing green and one seeing red– there ought, really, to be a 50/50 chance of "my" being
either. In fact, there does not seem to be a satisfactory solution to this inconsistency (6). For this reason we
will want to reject the Everett Interpretation and not burden ourselves with the uneconomical existence of
realities we can have no contact with or knowledge of.
The Quantum Zeno Effect.
Since S measures the state vector constantly (7) a concern may arise regarding the quantum Zeno effect (8); if
the state is always being observed can it really ever go from blue to green or red? This problem has been
discussed carefully by Chalmers in his consideration of M-properties.
Consider a spin-up electron moving through the Stern-Gerlach apparatus but still far from the detector. |Y(t)> will, of course, be changing. But it will always remain one of the many B eigenstates and S will
affect it in no way. As the electron moves along toward the detector, a very frequent measurement of its
position might, indeed, stop it somewhat from moving. But a very frequent measurement of the blueness of
the light will not affect its motion whatsoever. (It is true that |Y(t)> changes discontinuously at td . But this is
not strange. It is just a consequence of the simplistic way in which we imagined our experiment.)
At td it encounters the measuring device. |Y(td )> is now an eigenstate of C having a green qualia.
Throughout this entire process S, for all its observing, has done not a single thing to the state vector. Now, if
the electron had been in a superposed state when it hit the detector, S, at td , would have immediately pro-
discussed carefully by Chalmers in his consideration of M-properties.
Consider a spin-up electron moving through the Stern-Gerlach apparatus but still far from the detector. |Y(t)> will, of course, be changing. But it will always remain one of the many B eigenstates and S will
6 Consciousness18.nb
affect it in no way. As the electron moves along toward the detector, a very frequent measurement of its
position might, indeed, stop it somewhat from moving. But a very frequent measurement of the blueness of
the light will not affect its motion whatsoever. (It is true that |Y(t)> changes discontinuously at td . But this is
not strange. It is just a consequence of the simplistic way in which we imagined our experiment.)
At td it encounters the measuring device. |Y(td )> is now an eigenstate of C having a green qualia.
Throughout this entire process S, for all its observing, has done not a single thing to the state vector. Now, if
the electron had been in a superposed state when it hit the detector, S, at td , would have immediately projected things into either of the two possible outcomes. But, still there is no Zeno effect to be noticed in the
process. Why? S measures things all the time but, as things proceed along here, |Y(t)> always remains an
eigenstate of C.
Now real measurements do not, of course, occur instantaneously. Perhaps the devil is in the details.
Say the electron is spin-up. Set td = 0 and suppose that the measurement is complete at Dt. Suppose Dt is very
small and that we can approximate the state vector's evolution as linear. We can write |Y(t)> » [(1 - t/Dt) Y B
+ (t/Dt) YG ]/N (where N is just for normalization). Are these intervening states mixed, as they would have to
be in Chalmers' theory? We can't say. Maybe, as long as t < Dt/2, the state is still a blue eigenstate. At exactly
Dt/2 it becomes a green one. (|Y(t)> may change continuously but Q(t) might not for all we know. I do not
think we can even say what continuity means for qualia.) Or, maybe, after t = 0, it takes a little time (Dt) for
the blue light's filament to cool down and for the red one's to heat up? At t = Dt/2 the observer would be
seeing both some blue and red light. Perhaps this is what is going on. Anyway, we can easily construe C in
such a way as to have no problems with Zeno. Things are very different if we consider (|+, G> + |-, R>)/ 2 ,
the state that would try to arise if we sent a half-up/half-down electron into our apparatus. There is plainly no
way for this state to be anything but mixed. It will immediately be projected back into the "cheese." This
would happen the moment |Y(t)> tried to enter the "hole."
As a general matter, say that |Y(td )> is just about to enter a "hole." <Y(td )|Y(td )> = 1 at this time so it
might seem as if S would have to project it back into itself. Not at all. Suppose there was another eigenstate of
C, |F>, that was such that <F |Y(td )> = .999. This is altogether possible and |F> might even correspond to an
entirely different qualia eigenstate than |Y(td )>. There would now be an almost equal probability of projection
into either state. (There might even be 1000 such F-type eigenstates!) This would be impossible if C were an
actual Hermitian operator since, then, the |Ci> would constitute a complete orthonormal basis for the Fock
space. But we are proposing nothing of the sort and the various squared amplitudes must be interpreted as
relative, not absolute, probabilities.
Chalmers' problem stems from his taking M literally as a Hermitian operator. He appears to reason
somewhat as follows: If |Y(0)> is an eigenstate of M corresponding to the blue qualia and M measures the
state vector at t = Ε it will find it almost entirely in |Y(0)>. In particular, at Ε << ΤZ (where ΤZ is the Zeno time
for the system (8)), |Y(Ε)> = mostly |Y(0)> + small bit |orthogonal state>. He seems to assume that this orthogonal state could not correspond to a blue qualia so that if M measured 'blue' at Ε it would project the state
vector right back into |Y(0)> and nothing else. This is certainly not the case in our theory (and not necessarily
in his either since the orthogonal state could be a blue eigenstate too). But for |Y(Ε)> to correspond to a 'green'
qualia state (vide supra) would be impossible in his theory since < Y(0)|Y(Ε)> is not going to be very different
from 1 and |Y(Ε)> cannot therefore have a different qualia eigenvalue than |Y(0)> assuming M is Hermitian.
Of course, this is not a problem for our theory. We allow two eigenstates corresponding to different qualia
eigenvalues to be non-orthogonal.
A bigger problem both Chalmers' theory and this one might seem to face is why the quantum Zeno
effect can be demonstrated at all; it is, indisputably, a real thing. Excited beryllium ions have been prevented
from decaying by pulsing them frequently with light to detect if they are still in their original state (9). This is a
perfectly valid experiment since measuring the ion as excited completely precludes any possibility of its being
decayed. But the rate of testing of the ion (as fast as 250 times/sec) greatly exceeds what any human brain
could consciously process. It appears that human consciousness cannot be affecting the ion. Is the detector
supposed to be conscious too?
from 1 and |Y(Ε)> cannot therefore have a different qualia eigenvalue than |Y(0)> assuming M is Hermitian.
Of course, this is not a problem for our theory. We allow two eigenstates corresponding to different qualia
eigenvalues to be non-orthogonal.
Consciousness18.nb 7
A bigger problem both Chalmers' theory and this one might seem to face is why the quantum Zeno
effect can be demonstrated at all; it is, indisputably, a real thing. Excited beryllium ions have been prevented
from decaying by pulsing them frequently with light to detect if they are still in their original state (9). This is a
perfectly valid experiment since measuring the ion as excited completely precludes any possibility of its being
decayed. But the rate of testing of the ion (as fast as 250 times/sec) greatly exceeds what any human brain
could consciously process. It appears that human consciousness cannot be affecting the ion. Is the detector
supposed to be conscious too?
We need to consider this process more carefully. For simplicity let us suppose the detector makes only
two measurements, one at T and one at 2 T. T is very small relative to the rate of decay. Initially the ion is in
its undecayed state (U) and the detector is still in its initial state (I). We will write its state vector as |U, I>. At
time T the first measurement is made. Consciousness notices nothing and nothing projects. But the detector
records its activities on a strip of magnetic tape. The state is now Α |U, I, I> + Β |D, I, A> (where A means the
detector has registered a decay and Α >> Β). At 2 T another measurement is made. The state now becomes Α2
|U, I, I, I> + Α Β |D, I, I, A> + Β |D, I, A, A>. Everything, the tape included, is still in superposition. Now
consciousness looks at it. It wants to know the probability of finding |U, I, I, I> i.e. that the particle has not
decayed. This is É Α2 È2 which is exactly what it would have been had the measurements actually projected
(collapsed) the state. Had that been the case the probability of U at T would be È Α È2 and at 2 T it would be
È Α È4 which is the same as that obtained above. The decay is inhibited just as Zeno would have it. Although
they might seem to do nothing, the measurements have altered the trajectory of the state vector through our
Fock space. If they had not been performed the system would have evolved differently.
Conclusion.
By replacing wave functions with states in Fock space, |Y(t)>, we have created an interpretive picture that is in
better agreement with the view adopted by physics since the inception of modern field theory in the 1950s. A
price to be paid for this "better agreement" is the acceptance of a unitary view of consciousness in which the
idea of individual observers is ignored. Peculiar as this may seem, it does not bring with it any observable
consequences. But it allows us to refer to an instantaneous consciousness-state (qualia-state) of the universe
as Q(t). We have to do this if we want to put such a state into relation with |Y(t)>. Central to the success of
this approach is the realization that C is, in fact, not an operator in any quantum mechanical sense; rather, it is
a 'classifier' that sorts the |Y(t)>s into admissible and inadmissible states. This theory preserves a role for
consciousness in quantum measurement but a slightly different one from that it plays in M-property theory.
Acknowledgement.
The author is grateful to Professors David J. Chalmers, Lawrence S. Schulman, and Saverio Pascazio for
useful and interesting discussions regarding this work.
References and Footnotes.
1)
Schrödinger, E. The Present Situation in Quantum Mechanics. Naturwissenschaften 23 (49); 807
(1935).
2) Wigner, E. P. Remarks on the Mind-Body Question. In: I. J. Good, "The Scientist Speculates," (London,
Heinemann, 1961).
3) von Neumann, J. The Mathematical Foundations of Quantum Mechanics (1932).
4) Chalmers, D. J., Consciousness and its Place in Nature, Sec. 9, in Philosophy of Mind: Classical and
Contemporary Readings (Oxford, 2002). See also https://www.tubule.coma/watch?v=DIBT6E2GtjA.
5)
Wave functions are , generally, taken to be functions of a particle's location in spacetime. In free field
2) Wigner, E. P. Remarks on the Mind-Body Question. In: I. J. Good, "The Scientist Speculates," (London,
Heinemann, 1961).
8
Consciousness18.nb
3) von Neumann, J. The Mathematical Foundations of Quantum Mechanics (1932).
4) Chalmers, D. J., Consciousness and its Place in Nature, Sec. 9, in Philosophy of Mind: Classical and
Contemporary Readings (Oxford, 2002). See also https://www.tubule.coma/watch?v=DIBT6E2GtjA.
5)
Wave functions are , generally, taken to be functions of a particle's location in spacetime. In free field
Ö
theory it easy to express a universe consisting of only one particle with a definite momentum k as ak |0> = |k>.
If we attempt to restrict this "particle" to a single point, let us say x = 0 at t = 0, by representing |Y(0)> as S
k
ik x
e
|k>, a so-called Newton-Wigner state, we have a chance of finding the particle infinitely far away at the
slightest future time– seeming to violate relativity. If we try to formulate things in a relativistically invariant
way by representing |Y(0)> as S
k
1
2 Ωk
ei k x |k> then we end up with a situation where the states of two parti-
cles, localized at different places are no longer orthogonal (see Teller, P. (1995), An Interpretive Introduction
to Quantum Field Theory, Princeton University Press).
6) Chalmers (Chalmers, D. J. (1996), The Conscious Mind. Oxford University Press) defends the Everett
idea by means of arguments that try to show that superpositions of states will automatically organize themselves into separate (we would say definite) conscious experiences. The present writer does not see how these
arguments resolve the "relative probabilities" problem. This matter has been analyzed in a recent paper
(Byrne,
A
and
Hall,
N.,
Chalmers
on
Consciousness
and
Quantum
Mechanics,
http://web.mit.edu/abyme/www/Conc&QM.html).
7) While the simplest way to think of continuous measurement is just to imagine an infinite number of von
Neumann measurements being performed infinitely quickly there are other, and more subtle, ways of looking
at the problem. See Schulman, L. S. Physical Review A, 1509 (1998).
8) For an excellent recent review of the quantum Zeno effect see Pascazio, S. arXiv 1311.6645v1.pdf
(2013).
9) Itano, W., Heinzen, D., Bollinger, J., Wineland, D. Physical Review A, 2295 (1990). |
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
599
Article
Schumann Resonance, Psychophysical Regulation & Psi (Part I)
Iona Miller*
ABSTRACT
This article concurs with Lewis Hainsworth’s pioneering research on the health correlates of
Schumann Resonance (“SR”) and postulates, along with Pitkanin and Sidorov, that SR may be
the substrate for a radar-type extrasensory perception mechanism common to all organisms. SR
forms a sort of global guidance system for life. Resonant absorption of an oscillating signal and
reaction is presumed as most brainwaves fall within the first five SR modes (0-35 Hz).
Frequency matching amplifies even weak signals, even in the presence of other strong static and
oscillating fields. It is vital in brain-to-cell and cell-to-cell communication.
Part I of this two-part article contains: Introduction; Planetary Rhythms; Ducted Propagation;
Physiological Frequencies, Coherent Resonance & Well-Being; EM Frequencies & Human
Response; and Measuring Brain Waves by EEG.
Key Words: EMF, Schumann Resonance, psi, ionosphere, resonance, solar flares, ULF/ELF,
diurnal cycles, endocrine hormones.
Introduction
The Schumann resonance (SR) is defined as a set of resonant modes or spectrum peaks, between
7.83 and 45 Hz, in the extremely low frequency (ELF) portion of the Earth's electromagnetic
field spectrum. The fundamental Schumann Resonance is a standing wave in the atmosphere
around 8 Hz. Human brainwaves are entrained to this pulse emitting theta and alpha frequencies
in the same EMF region. The reciprocal system functions as a phase-locked loop.
A phase-locked loop or phase lock loop (PLL) is a control system that generates an output signal
whose phase is related to the phase of an input "reference" signal. It is an electronic circuit
consisting of a variable frequency oscillator and a phase detector. The signal from the phase
detector is used to control the oscillator in a feedback loop. (Wikipedia)
Necessary for mammalian growth and repair, such signals in guidewaves in the geomagnetic
cavity are the meta-drivers of biological processes, homeostasis and adaptation. We cannot thrive
without them.
Cells respond between 3 - 25 Hz. Frequencies outside this range have little or no effect. Cell
membranes oscillate, or resonate to create a "biological window". Each "window" has
measurable and definable frequency, amplitude and a phase that has discrete ranges projected on
*Correspondence: Iona Miller, Independent Researcher. Email: iona_m@yahoo.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
600
different characteristics of the wave. Active "windows" facilitate information transfer and
adaptive activities. Changing windows creates functional changes called a phase change that
helps us adapt to environmental changes.
Outside the earth's magnetic field for extended periods, early cosmonauts lost 80% of their bone
density. Michael Persinger developed Schumann wave generators (7.83 Hz) for space flights that
overcame this side effect. Geomagnetic anomalies can amplify local SR in certain geological
conditions potentially stimulating coherent resonance in alpha brainwave, forming a tuned
system. Solar/geomagnetic interactions correlated with sunspots and solar flares significantly
perturb SR.
Solar events release cosmic rays which enhance the ionization of the D-layer up to a factor of 10
with Sudden Ionospheric Disturbances (SID). Such ELF signals affect tissue electric gradients
of ULF/ELF oscillating signals, involving non-linear resonant absorption of ULF/ELF oscillating
signals into systems that use natural ion oscillation signals in the same frequency range.
ULF/ELF signals can significantly alter cellular calcium ion fluxes and EEGs in brain tissue.
This article concurs with Hainsworth’s pioneering research on the health correlates of SR, and
postulates, along with Pitkanin and Sidorov, that SR may be the substrate for a radar-type
extrasensory perception mechanism common to all organisms. SR forms a sort of global
guidance system for life. Resonant absorption of an oscillating signal and reaction is presumed as
most brainwaves fall within the first five SR modes (0-35 Hz). Frequency matching amplifies
even weak signals, even in the presence of other strong static and oscillating fields. It is vital in
brain-to-cell and cell-to-cell communication.
Planetary Rhythms
Geospace is the term that relates to the solar-terrestrial environment and the relevant space
occupied by Earth and her fields. Schumann Resonance (SR), global electromagnetic resonances
excited by tropical lightning, is one of the natural EM fields in our planetary environment. On
average, there are about 200 scattered lightning strikes taking place each second. But resonances
can be excited by any electromagnetic disturbance in the atmosphere, including geomagnetic
micropulsations.
Solar or geomagnetic activity leads to changes of the dielectric permeability in the Schumann
cavity. The fundamental SR mode roughly corresponds to a wave with a wavelength equal to the
circumference of the Earth. It has existed since the Ionosphere formed and lightning began, predating animal life. If a radio wave circles the globe, SR occurs when the phase delay of that wave
equals 2π. SR is a global phenomenon, while transverse resonance is local. If the wave bounces
between the ground and ionosphere, it is trapped between two ‘mirrors’, kindling transverse
resonance.
Transverse resonance is predominantly a local phenomenon containing information on the local
height and conductivity of the lower ionosphere and on nearby thunderstorm activity. Waves in
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
601
the ULF range ULF range (i.e., below the first Schumann Resonance), will have wavelengths
much larger than the circumference of the Earth.
ULF waves, at approximately 1 mHz to 1 Hz, play a major role in propagating energy throughout
the magnetospheric system. At the lowest end of this frequency band, the wavelength of ULF
waves is comparable to the entire magnetosphere. In this frequency range, the global structure of
the magnetosphere can lead to global cavity resonances and waveguide modes. The structure of
these modes is determined by the gradients in the Alfvén and fast mode speeds in the
magnetospheric system. (Lysak)
SR is not the internally-generated resonant frequency of our planet, which is 10 - 11.75 Hz as
Tesla discovered. Earth itself emits a predominantly infrared wave from its hot core and reradiated solar energy it absorbs. Schumann fields are weak compared to the earth's much larger
static geomagnetic field. SR is electromagnetic oscillations -- the Earth’s global electric circuit
consisting of the frequencies that play through the ionospheric cavity (space between the ground
and ionosphere) as waves in a plasma. It rings like a tuning-fork. The ionosphere is a highlyconductive region of cosmic plasma, a sea of free electrons – ions.
Earth's cavity responds to solar fluctuations like a tuning fork, tuned to 7.83 Hz. The solarterrestrial environment is modulated by solar cycles which affect the global climate and all
organisms in the biosphere. Interference patterns are the transducers of energy, which at its most
fundamental is described as information. Earth functions like a planet-sized electrical capacitor
or condenser, storing electrical potential.
Ducted Propagation
The space between Earth and the ionosphere is a dissipative closed cavity between 50-375 miles
that can sustain quasi-standing waves at wave lengths of planetary dimension. Electrical
conductivity in the atmosphere is driven largely by cosmic rays that generate a torsion field.
Conductivity increases exponentially with altitude because the lower atmosphere buffers
collision frequency.
The ionosphere begins about 50 miles out from the Earth’s surface and extends out over 180
miles. It consists of charged particles. This highly dynamic region is constantly exposed to harsh
ultraviolet radiation from the Sun. It breaks down molecules and atoms. Highly charged ions and
free electrons therefore fill the ionospheric layers creating a “spectral power station”.
Through ducted propagation, lightning radiates broadband EM fields that spread laterally into the
cavity. Global thunderstorms excite the Schumann resonances, which can be observed around
7.8, 14, 20, 26, 33, 39 and 45 Hz. Changes occurring in these frequencies are quite normal and
do not indicate anything out of the ordinary. All of these frequencies fluctuate around their
nominal values. The resonant spectrum is a superposition of global lightning discharge. For
these resonant values to change, the planet would have to change diameter.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
602
The Schumann resonance modes, like other low-frequency modes, are able to leak into the
ionosphere, particularly at night when the plasma density is lower:
Using measurements from the Communications/Navigation Outage Forecasting System
(C/NOFS) satellite, we report, for the first time, Schumann resonance signatures detected well
beyond the upper boundary of the cavity. These results offer new means for investigating
atmospheric electricity, tropospheric-ionospheric coupling mechanisms related to lightning
activity, and wave propagation in the ionosphere. The detection of Schumann resonances in the
ionosphere calls for revisions to the existing models of extremely low frequency wave
propagation in the surface-ionosphere cavity. (Simoes)
Frequencies describe periodic cycles per second, measured in hertz (Hz). Such frequencies have
wrapped earth’s biosphere since its inception. Normal daily variation ranges ± 0.5 Hertz.
Another normal source of fluctuation is Coronal Mass Ejections from the sun that leads to proton
bombardment. Bursts may increase of the Schumann frequency by 3.5%. These effects are
explained by changes of the height and dielectric permeability of the Earth-ionosphere cavity.
In the early to mid-1950s, geophysicist Schumann suggested that electromagnetic signals might
circulate at extremely low frequencies in the electrically resonant cavity between the Earth and
the ionosphere. He was right. The signals came to be called "Schumann's resonances". One
major component was originally predicted at a frequency of about 10 Hz. In 1959 it was
measured to be slightly different. Meanwhile, the military co-opted the discovery for using ELF
signals in submarine communications.
The first mode of these circulating signals has an average value of 7.8 Hz, with a typical diurnal
range of from 7.2 to 8.8 Hz, and the second mode has an average value of 14.1 Hz and a range of
from 13.2 to 15.8 Hz. These match the brain-wave theta rhythm and beta rhythm nicely. The
blank range between the two modes is a very reasonable match with the normal frequency range
of the human alpha rhythm, between 8 to 12 Hz or cycles.
Additionally, it was found that there is minimum (zero) power circulating in the
Earth/ionosphere cavity at 10.4 Hz--which is virtually an exact match for the average value of
the alpha rhythm. The existence of these natural signals and the close relationship of their
frequencies of oscillation to key human rhythms were unknown to senior neurologists and
mental health specialists as late as 1975. But recent years have seen escalating interest in
geophysics in both the public and academic sectors, including its effects on our psychobiology.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
603
A persistent New Age meme was begun by a self-styled "expert" without any accurate citations to
promote his commercial idiosyncratic notions. It is entirely fallacious though it has become
widespread on the Internet: "The resonance of Earth (Schumann Resonance) has been 7.8Hz for
thousands of years. Since 1980 it has risen to over 12Hz. This means that 16 hours now equate to
a 24 hour day. Time is speeding up! Recent reports set the rate at over 11 cycles, and climbing.
Science doesn't know why, or what to make of it." It is demonstrably untrue as Lonetree's
continual monitoring has shown. It isn't true and it was never true, and it isn't becoming true
even at the peak of the current solar cycle. Furthermore, for it to happen would require the
Earth shrinking or the speed of light changing dramatically.(Lonetree & Miller)
Physiological Frequencies, Coherent Resonance & Well-Being
We are bathed in a sea of natural low-frequency electromagnetic (EM) fields from conception to
death. The brain is an electromagnetic system synchronized by the Schumann Resonance signal,
that that continuously stabilizes the brain wave activity.
The frequencies of EEG brainwaves coincide with the range of SR activity. Blackman (1990)
established that external electromagnetic ELF signals induce altered neuron calcium ion effluxes
in brain tissue. Stable synchronizing of the brain’s electromagnetic systems underpins thinking,
emotion, memory and intelligence. Significantly, the hippocampal wave, which exerts a decisive
influence on brain function and long term memory, shares the same frequency as the primary SR
– 7.8Hz.
SR modulates the set points of our consciousness and biology. Living tissues detect, absorb and
utilized electromagnetic signals within some frequency ranges and completely ignore other
frequencies naturally encountered in the frequency spectrum. We are "in tune" with Schumann
Resonances which drive brain wave ELF patterns in a set range of grouped frequencies. Some
describe "antenna" like qualities in the brainwave 8-12 cycle range.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
604
We have electromagnetic transmitters and receivers in our neurons, including a phase-locked
loop system. Our brains detect and respond to the SR signal through nonlinear resonant matching
of frequency, altering optimal melatonin/serotonin cycle balance, cardiac, neurological,
reproductive health and mortality. Solar storms modulate daily variation of the D-Region
reflected in daily variation in the Schumann Resonance signal strength.
This primal lightning-driven Schumann Resonance pulse calibrates us and enhances our physical
and mental well-being. We are all tuned to that wave, which correlates with a relaxed and
creative mind. That natural resonance helps us achieve our optimal brainwave states, but this
atmosphere-to-human linkage is disrupted by the electrosmog of today’s ultra-technology.
Cherry (2002) found that the Schumann Resonance signal is extremely highly correlated with
Solar Geomagnetic Activity (S-GMA) indices of sunspot number and the Kp index. The physical
mechanism is the ionospheric D-region ion/electron density that varies with S-GMA and forms
the upper boundary of the resonant cavity in which the Schumann Resonance signal is formed.
His evidence supports the notion that SR signals are the S-GMA biophysical mechanism,
primarily through a melatonin mechanism. He therefore identifies S-GMA as a natural hazard
with biological and health effects.
Away from artificial noise and thunderstorms SR is the main component of the natural EM
background between 6 and 50 Hz. The fundamental Schumann frequency fluctuates between 7.0
Hz. to 8.5 Hz. Such frequencies vary from geological location to location. They can even have
naturally occurring interruptions.
Schumann’s successor, Dr. Herbert König demonstrated a connection between Schumann
Resonance and brain rhythms. König compared human EEG recordings with natural
electromagnetic fields in the environment, finding that 7.83 Hz is the dominant brain wave
rhythm of all mammals in alpha or resting state. When the brain resonates with SR energy
information is transmitted that appears to coordinate psychophysical systems.
Lewis B. Hainsworth, (deceased) of Western Australia was among the first researchers to
recognize the relationship of brain-wave frequencies to the naturally circulating rhythmic signals
of SR. Hainsworth shared this data with Dr. Robert O. Becker, noted electromagnetic pollution
expert, and to Harvard neurologists as early as 1975. Becker included it in his three classic books
on electromagnetism and life (1982, 1985, 1990).
Robert C. Beck, another EMF researcher, found that the human body has numerous very specific
frequencies that trigger production of different endorphins, beta-endorphins, catecholamines,
enkephalins, dynorphins, proteins, and stem cells. He found about 250 different key frequencies
that trigger the body to produce its own healing chemicals. Beck studied about 150 different
brain wave stimulation devices, and their effects experimentally.
Bentov found that several other interlocking resonating systems in the body were activated by
this steady 7 to 8 Hz activity during meditation. The upper part of the body has a resonant
frequency of about 7 Hz under normal conditions. Bentov noted that additional resonance effects
are likely, resulting from this "phase interlock phenomenon".
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
605
Other systems besides brainwaves are affected by the Schumann resonance. As quoted in Smith,
Ludwig (1987) has measured and compared a large number of the ELF rhythms in human
subjects with resonant frequencies in homeopathic remedies using a spectrum analyzer. Bentov
reported that Schumann calculated the earth-ionosphere cavity resonance frequencies at 10.6,
18.3, and 25.9 Hz, and he reported more recent values calculated by Toomey and Polk at 7.8,
14.1, 20.3, 26.4, and 32.5 Hz. Ludwig found a number of frequencies have been found to be
common to all the subjects and to relate to the specific physiological functions. For example, the
frequency 0.1 Hz relates to the circulatory system, 7.8 Hz relates to the hippocampus, 10 Hz to
the circadian rhythms, 33 Hz to the lymphatic system, etc. (Roffey)
Oschmann links healing energies to these rhythms of Earth’s atmosphere. “Robert C. Beck has
used EEG recordings to study brain wave activity in ‘healers’ from all over the world: psychics,
shamans, faith healers, a Hawaiian kahuna, practitioners of wicca, etc. All these healers
produced similar brain wave patterns when they were … performing a healing… all healers
registered brain wave activity averaging about 7.8-8.0 cycles/second… Beck performed
additional studies on some of the subjects and found that during healing moments their brain
waves became phase and frequency synchronized with the earth’s geoelectric micropulsations –
the Schumann resonance.” (Oschman)
Research has shown that the Schumann resonances can modulate human health indicators such
as blood pressure, cardiac and neurological disease, reaction time, neuroendrocrine sensitivities,
violence and war. It also correlates with sunspot activity, mass human excitability, sociality, and
climate change (Tchijevsky).
Suitbert Ertel (1997) in "Bursts of creativity correlate with solar activity" examined the
association between solar activity and oscillations in human creativity. His results showed that
during increased solar activity, human creative activity also peaks. Tchijevsky agreed that the
influence on human nervous systems is greatest during peaks of emitted energy by the sun and
radiation of the earth. Chemical bonds are magnetic bonds, formed between adjacent atoms
through paired electrons having opposite spins and thus attracted magnetically.
In 1977, this phenomenon -- the relationship between brain-wave rhythms and the spectrum of
the natural Earth ELF (extremely low frequency) signals--became the basis for Itzhak Bentov's
popular book Stalking the Wild Pendulum. He also suggested geophysical correlates affect
people’s health, emotional balance and spiritual well-being.
Ancient cultures such as Egyptian, Hopi, Ancient Indian, Mayan, Aztec and Chinese, correctly
assumed that their collective behavior was influenced by the sun. Contemporary research
confirms a relationship to human health and well-being. Even ESP or psi phenomena is
predicated on the assumption that all living things are interconnected and communicate with
each other via biological and electromagnetic fields.
Hainsworth sent up a clarion cry against hazardous EM (electromagnetic) pollution, whose
continuous dangers pale in comparison to the threat of technologies such as HAARP [Highfrequency Active Auroral Research Program], which sends violent pulsations into the Earth's
ionosphere, potentially disrupting the entire electromagnetic shield of the planet and certainly
affecting the whole biosphere and thus human welfare in general.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
606
Some research (Braden) has suggested that the frequency of the basic Schumann's resonance has
recently been rising in value, possibly threatening the whole biosphere, human welfare and our
evolutionary future. But this is totally unsubstantiated fallacious disinformation. There
is no evidence whatsoever of rising SR. The author’s colleague Ben Lonetree has been
monitoring SR daily for nearly two decades without any anomalous readings, proving the
persistent New Age meme is undeniably incorrect.
All biological processes are a function of electromagnetic field interactions. EM fields are the
connecting link between the world of form and resonant patterns. They store gestalts or patterns
of information. The bridge connecting solar system resonances and brain frequencies resides in
our human DNA helix, which co-evolved in the Earth's environment.
Electrical engineer Lewis B. Hainsworth, MA, was among the first to suggest that human health
is linked with geophysical parameters by way of the naturally occurring Schumann's ELF. His
hypothesis identified naturally occurring features which determine the frequency spectrum of
human brain-wave rhythms: The frequencies of naturally occurring electromagnetic signals,
circulating in the electrically resonant cavity bounded by the Earth and the ionosphere, have
governed or determined the 'evolution' or development of the frequencies of operation of the
principal human brain-wave signals. In particular, the alpha rhythm is so placed that it can in no
circumstances suffer an extensive interference from naturally occurring signals.
Hainsworth concluded that the frequencies of human brain-waves evolved in response to these
signals. If his hypothesis is correct, conditions for evolutionary changes in human brain-wave
patterns have now been established. Furthermore, variations in these patterns can produce mild
to disastrous health and behavioral changes.
The nature of the applied stimulus makes it difficult to identify the responses directly, as they are
most likely to occur in the form of stress-related conditions. They will therefore show up as
drastic increases in mental disturbance, antisocial behavior, psychosomatic conditions and
neurological disturbances. Some electrical field phenomena have already been linked with
abnormal cell growth and a decrease in immunocompetency.
All these factors could be expected to lead to the appearance of "new" diseases, probably
accompanied by a decline in resistance to many minor infections, an increase in conditions
related to abnormal cell development, including cancer, birth defects and infertility, and an
increase in psychological disturbance problems, e.g., drug addiction and suicide. These existing
psychobiological problems could be expected to increase in scale, but could be studied for
deviations from "normal" alpha cycles of 10.4 Hz, with detectable changes in psychological
characteristics and mental abilities.
Hainsworth therefore strongly urged that research into widespread measurements of the natural
SR signals' frequency variations and field strengths be carried out and compared with statistics
for the incidence of heart attacks, suicide attempts, road accidents, social violence, domestic
accidents, crimes, etc. Studies are often conducted in this inferential way (i.e., Krippner and
Persinger), searching correlations between the phenomena of Earth lights and tectonic strain and
reports of UFO sightings, abduction reports and other anomalous psychophysical experiences for
an electromagnetic connection to temporal lobe seizures.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
607
We strongly suggest that correlations of broad changes in the modulations of SR be studied in
relationship to microwave radiation, ELF signals and HAARP for both immediate and long-term
consequences. There are many obvious ramifications of such EM pollution and 10-50 Hz
modulations on the human system (Miller, 2001).
We have also discussed the benefits for human well-being and relaxation from entraining with
these natural rhythms (Miller & Miller,1981). When a person is deeply relaxed, slow rhythmic
sine-wave patterns can be detected in both the EEG and the heart/aorta resonating oscillator in
the 7-8 Hz range. Resonance occurs when the natural vibration frequency of a body is greatly
amplified by vibrations at the same frequency from another body.
Oscillators alter the environment in a periodic manner. Thus, standing waves in the body,
whether during meditation/relaxation or not, can be driven by a larger signal. Progressively
amplified wave-forms, created by resonance, result in large oscillations entraining other circuits
in the body tuned to those frequencies. A hierarchy of frequencies thus couples our
psychophysical selves to the harmonic frequency of the electrical charge of the Earth, which
naturally pulses at the same frequencies. This is hardly a coincidence, as we are adaptive
products of our environment.
Our planet is surrounded by a layer of electrically charged particles called the ionosphere. The
lower layer of the ionosphere is roughly 60-80 kilometers (40-50 miles) from the crust, and this
charged layer is known to reflect radio waves. Bombardment by HAARP signals "pushes" out
this boundary layer, thus altering the natural, pulsating rhythm. Natural fluctuations in frequency
occur daily, by the lunar month, and in response to solar flares.
Since the ionosphere is a highly charged layer, it forms a so-called capacitor with the Earth. This
means that there is a difference in electrical potential between the two, the Earth being negatively
charged and the ionosphere being positively charged. This potential varies somewhat, but is
around 200 volts per metre. This is a fundamental type of electrical generator. The solar winds,
interacting with the upper atmosphere rotation, act as the collector and brushes of a generator.
The lower atmosphere can be seen as a storage battery for this gradient potential.
This electromagnetic field around the Earth can be viewed as a stiff jelly. When our bodies move
and vibrate, these movements are transmitted to the environment, and vice versa. These fields
not only impinge on our bodies, they also affect the charges inside our bodies. When we are
standing on the ground, under normal conditions, we are grounded. Our body then acts as a sink
for the electrostatic field and actually distorts the force-lines somewhat. The human body also
has its own electrostatic field about itself.
These field lines are the result of the various biochemical reactions in the body. This resultant
bio-field couples us to the iso-electric field of the planet (Miller & Miller, 1981).
In 1957, German physicist Dr W. O. Schumann calculated the Earth/ionosphere cavity resonance
frequencies (which were named after him). He fixed the most predominant standing wave at
about 7.83 Hz.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
608
A "tuned system" consists of at least two oscillators of identical resonant frequencies. If one
oscillator starts emitting, the other will be activated by the signal very shortly, in the process of
resonance, entrainment or kindling (igniting the resonance phenomenon among the neurons). It
becomes obvious that in deep meditation, when waves of alpha and theta rhythms cascade across
the entire brain, a resonance is possible between the human being and the planet. Energy and
information which are embedded in a field are transferred. Perhaps the planet communicates with
us in this primal language of frequencies.
According to Hainsworth, the influence of naturally occurring Schumann's resonance signals on
brain-wave pattern evolution is formally stated to show that low-power electrical fields could
produce evolutionary change. The electrical fields produced by modern electro-technology are
then possible sources of evolutionary change. The characteristics of some forms which might
result should be considered. Some fields might inhibit survival of existing forms. Because of lack
of available data, precise measurements are lacking and must therefore be quantitatively
valueless. Technology not only will change, but is changing, human evolution. Only extensive
investigation of the naturally occurring signals will give any lead in showing what results might
occur.
The possibility exists that human health is linked with geophysical parameters by way of the
naturally occurring Schumann's resonances. A number of attempts have been made to discover
the correlation through geomagnetic and ionospheric storms. The correlation comes through the
biological fact that the human system is apparently sensitive to such low-power ELF signals. We
don't know what the range of such a correlation might be.
The frequency values of the SR signals are determined by the effective dimensions of the cavity
between the Earth and ionosphere. Thus, any events which change these dimensions will change
the resonant frequencies. As Hainsworth warned, "such events could be ionospheric storms, and
could even result from a man-made ionospheric disturbance".
Geomagnetic storms are the magnetic changes produced by ionospheric storms, and are thus
associated with conditions capable of modulating the SR signals. However, although such storms
can produce these changes, measurement of these parameters cannot give any indication of
whether the resonance signals have changed to a value outside their normal range or not. Since
the undisturbed state of the ionosphere corresponds to the normal SR patterns, then ionospheric
disturbances are likely to produce abnormal patterns, but will not necessarily do so in all cases. If
biological response is linked to Schumann's resonance signals, this will reduce any apparent link
with geomagnetic or ionospheric data.
Trying to determine the relationships between geophysical and biological conditions can become
extremely complex. The frequencies of the SR signals change with ionospheric conditions. These
conditions change diurnally, seasonally and with variations in solar activity, which, in turn,
varies with the 11-year sunspot cycle and also with the 27-29-day lunar cycle, mainly during
sunspot minimum periods. Lunar tidal changes in the height and thickness of the layers could
also sometimes affect the cavity dimensions and hence the Schumann's frequencies. So can
powerful ELF signals from HAARP and other atmospheric heaters.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
609
It should be borne in mind that if some signal conditions are harmful, then other conditions
might be beneficial. This means that if, for example, seasonal and tidal conditions have resulted
in the signals being in a biologically disturbing state, then the advent of a solar flare could result
in changes in the signals, bringing them into a biologically beneficial state. The converse could
also occur.
If we are sensitive to ELF signals, then when these factors are considered we would expect to get
confusion if we try to link any effect with geophysical changes. For instance, there could be
incidences of classic states of "lunacy" in some years if damaging signals coincided with full
moons, then in other years the observations and analyses would show that the effects were not
lunar.
An analysis of the correlation between the incidence of ionospheric disturbance and rate of
admission to Heathcote Hospital (Perth, Western Australia) for about a three-year total indicated
that when a disturbance occurred then the admission rate changed. The probability of the
association being random was of the order of 2000:1 against. However, the fact that sometimes
the rate went up and sometimes down showed that ionospheric storms changed the rate of
incidence of mental disturbance in a way that is consistent with that change being dependent on
the actual causes being linked to variations in the Schumann's resonance signals. At that point,
Hainsworth decided to concentrate on trying to get some observational work going on measuring
the SR signals.
Hainsworth's set-up used a 2,000-turn, 1-metre-square antenna, and another of 1/3-metre square,
plus amplifiers to handle signals from 0 to 30 Hz. His amplified Schumann's signals were
analyzed in a laboratory. On one occasion the signal dropped to zero amplitude when a solar
flare occurred, and did not start recovering for about an hour and a half afterwards. It was
originally just under 7 Hz and came back at only just over 6 Hz. His next step would have been
to develop a wave analyzer to try to pick out individual signals. But the failing health of both
himself and his wife prevented this.
EM Frequencies & Human Response
Hainsworth posed a series of questions, all of which are answered with a resounding "yes". This
should lead us in the direction of extreme caution towards introducing new EM or ELF sources
and ionospheric changes in our environment. He presented his data in two papers (referenced at
the end of this article and posted on the website http://www.nwbotanicals.org). His questions are
as follows:
1. Does the human biological system contain, use or generate any forms of electrical signal?
2. Does it respond to any of these signals?
3. Does it respond to audible signals at these frequencies?
4. Does it respond to optical signals at these frequencies?
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
610
5. Do human signals change with psychological or mental states, such as stress or problem
solving?
6. Does the human system respond to any very, very low-power electromagnetic signals?
Brain waves have only been studied since about the mid-1920s, and the signal form that is
apparently most widely known and identified is the alpha rhythm. The frequency of this signal
varies from individual to individual, but it lies between about 7-8 Hz and 12 Hz, with an average
value of 10.5 Hz. Theta and beta rhythm signals also occur, and are identifiable by EEG below
the 8 Hz and above the 12 Hz frequencies. Since the discovery and measurement of these signals,
a great deal of effort has been devoted to trying to work out how they originated in the first place
and what determines their frequencies of operation.
Hainsworth argued that up to the end of 1979, no long-term systematic measurements of any
great value were being made of the Schumann's resonance signals. Measurements were being
made only intermittently for the purpose of obtaining research data for use by post-graduate
geophysicists in constructing esoteric mathematical models of the ionosphere. It follows from
this that, until long after the end of 1979, no figures on these signals were available.
Consequently, no "expert" can produce numerical evidence to support an objection to
Hainsworth's original hypothesis, since the only numerical values available are those favoring it.
However, Hainsworth left us with some open-ended questions:
7. Has any evidence ever been obtained to indicate that the human system is totally unaffected by
externally applied electromagnetic fields?
8. Have any measurement programs ever been attempted to show whether the human system is
(a) totally unaffected, (b) always affected, or (c) sometimes affected by naturally [or artificially]
occurring electromagnetic signals?
9. Has the existence of such signals, having a close relationship with human biological signal
frequencies, been known for many years?
10. Have those relationships been studied with adequate protocols in any detail?
Schumann's resonances are actually observed, by experiment, occurring at several harmonic
frequencies between 6 and 50 cycles per second (one cycle equals one hertz). Specifically they
are found at 7.8, 14, 20, 26, 33, 39 and 45 Hz, with a daily variation of around ±0.5 Hz.
Only as long as the properties of Earth's electromagnetic cavity remain about the same do these
frequencies remain the same. Cycles may vary somewhat due to ionospheric response to solar
cycle activity and properties of the atmosphere and magnetosphere. Projects, such as HAARP
and its international clones, which heat up or blast out the ionosphere pose a potential threat to
this interactive system.
Measuring Brain Waves by EEG
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 599-612
Miller, I., Schumann Resonance, Psychophysical Regulation & Psi (Part I)
611
The resonant cavity formed between the ionosphere and the Earth produces rhythmic waves
capable of entraining and phase-locking with brain waves.
Hainsworth seems to have been unfamiliar with extensive work in brain-wave research in
neurology, hypnotherapy, biofeedback and neural feedback. This research includes extensive
experiments in frequency-following response (FFR) and relating brain waves and brain-wave
deficiencies to psychobiological states.
The brain is a massive source of ELF signals that get transmitted throughout the body through
the nervous system, which is sensitive to magnetic fields. Brain waves and natural biorhythms
can be entrained by strong external ELF signals, such as stationary waves at Schumann's
resonances. Entrainment, synchronization and amplification promote coherent large-scale
activity rather than typical flurries of transient brain waves. Thus, resonant standing waves
emerge from the brain, which under the right conditions facilitates internal and external bioinformation transfer via ELF electromagnetic waves. These SR waves exhibit non-local character
and nearly instant communication capability.
The EEG (electroencephalograph) measures brain waves of different frequencies within the
brain. Rhythmicity in the EEG is a key variable in the coordination of cortical activity.
Electrodes are placed on specific sites on the scalp to detect and record the electrical impulses
within the brain. Frequency Amplitude represents the power of electrical impulses generated by
the brain. Volume or intensity of brain-wave activity is measured in microvolts. is the number of
times a wave repeats itself within a second. It can be compared to the frequencies on a radio.
Raw EEG frequency bands include gamma (25-60 Hz); beta (12-25 Hz); alpha (7-12 Hz); theta
(4-7 Hz); and delta (less than 4 Hz). Their ranges overlap one another along the frequency
spectrum by 0.5 Hz or more. These frequencies are linked to behaviors, subjective feeling states,
physiological correlates, etc. Clinical improvement with EEG biofeedback is traceable to
improved neuroregulation in basic functions by appeal to their underlying rhythmic mechanisms.
Schumann's resonance forms a natural feedback loop with the human mind/body. The human
brain and body developed in the biosphere, the EM environment conditioned by this cyclic pulse.
Conversely, this pulse acts as a "driver" of our brains and can also potentially carry information.
Functional processes may be altered and new patterns of behavior facilitated through the brain's
web of inhibitory and excitatory feedback networks. Functional processes may be altered and
new patterns of behavior facilitated through the brain's web of inhibitory and excitatory feedback
networks.
The brain has its own set of vibrations it uses to communicate with itself and the rest of the body.
EEG equipment distinguishes these waves by measuring the speed with which neurons fire in
cycles per second. At their boundaries these waves can overlap somewhat, merging seamlessly
into one another--so different researchers may give slightly different readings for the range of
cycles per second (Hz). The rate of cycling determines the type of activity, kindling wave after
wave over the whole surface of the brain by igniting more neurons.
(Continued on Part II which also contains the references)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
309
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Article
Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Joey M. Caswell1, *, J. Miguel Gaona1, 2, 3, *, Lucas W. E. Tessaro1,
Nicolas Rouleau1, & Andrew Lapointe1
1
Transnational Anomalies Research, Sudbury, Ontario, Canada
Centro Europeo Neurosalus, Madrid, Spain
3
Faculty of Medicine, Universidad Rey Juan Carlos, Madrid Spain
2
Abstract
A series of preliminary field experiments investigating the phenomenon of consciousnesscorrelated effects on Random Event Generator (REG) devices was recently conducted by our
group, which revealed interesting effects on these random physical systems associated with
subjectively emotional events occurring in the immediate environment. We have since explored
a range of novel settings in the context of this apparent “FieldREG” effect. This has included a
number of specific environments which expand upon the previous literature in this area by
investigating additional phenomena typically associated with classic parapsychology. While the
results obtained for these particular experiments supported our initial hypotheses in general, the
re-examination of a religious setting proved particularly inconsistent, while still presenting some
intriguing overall results. Exploratory theoretical considerations are suggested for future
research.
Key Words: consciousness, religious experience, poltergeist, haunt, random event generator
(REG), subtle energies, FieldREG.
1. Introduction
Decades of empirical investigation have demonstrated the apparent mind-matter interaction
between consciousness and external random physical systems [1-2]. This phenomenon of
consciousness-correlated collapse (3C) has also recently been examined in the context of
potential biophysical factors which may be involved in this anomalous process [3-6]. The
apparent 3C effects previously observed suggest that the pre-stated conscious intentions of a
human operator appear to influence the outcome of a random physical system, such as a Random
Event Generator (REG) device. Despite the counter-intuition of these findings, there have been
theoretical propositions which suggest that the phenomenon of mind-matter interaction, or 3C,
could be allowed by physics [7-8]. By employing a theoretical approach that remains consistent
with the emerging paradigm of paranthropology, we may also be able to apply culturalbehavioural phenomena to the context of physical anomalies and consciousness in general [9].
*Corresponding authors: J. M. Caswell & J. M. Gaona E-mail: neuraljc@gmail.com, drgaona@neurosalus.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
310
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
A series of studies involving field work with REGs (FieldREG) previously conducted also seem
to reveal the potential for the synchronously directed attention and emotional state of individuals
in groups to influence the outcome of a REG device [10-12]. It has been difficult to apply
theoretical models which might sufficiently encompass the observations. However, the data have
suggested new and intriguing dimensions to the phenomenon of interactions between
consciousness and extracerebral processes.
In our previous FieldREG study [12], we pursued an additional hypothesis regarding the overall
directional component of the random output of a REG device. This valence theory suggested that
the overall direction of REG data (e.g., more positive vs. more negative values) would
correspond to the emotional valence of individuals in the proximal environment (e.g., positive
vs. negative emotions). While the results generally supported this hypothesis with significantly
different REG deviations observed between positive and negative emotional group settings [12],
further experiments were strongly suggested in order to obtain further support for this additional
theory. Thus, for the current FieldREG II initiative, we chose to again investigate scenarios of
both positive and negative emotional associations, as well as a relatively mundane site. We
predicted significant deviations in random data collected on-site would occur in relation to the
more novel time-segments, again, according to previous hypotheses [12], while it was suspected
that generally positive trends in the data would be observed during emotionally positive
activities, while negative deviations should occur during the emotionally negative scenarios.
Finally, the relatively mundane setting was hypothesized to show REG results consistent with
chance expectations.
Despite the previous investigations [10-12], there remain a number of “paranormal” settings
typically examined in parapsychology which have yet to be studied with regard to potential
FieldREG-like effects. This includes classic cases of haunt and poltergeist episodes. While these
paradigms are strongly linked by an overt thematic association and similar physical
manifestations (e.g., object movement, reports of hearing or seeing things, etc.), they differ in
some important respects. While alleged haunts are often associated with a specific area or
environment [13-14], an individual is typically the focus of activity in poltergeist cases [15-16].
Furthermore, previously investigated reports employing robust biological quantification have
more often focused on the poltergeist phenomenon [16]. This is important due to the theoretical
and empirical associations observed between poltergeist activities, often termed “recurrentspontaneous psychokinesis” [17-18], and mind-matter interaction. If we assume that the
FieldREG phenomenon likely employs similar processes to 3C interactions with REG devices, it
could be that any FieldREG effects observed in a poltergeist (or haunt) environment may further
support the poltergeist as “macro-psychokinetic” manifestation hypothesis [17].
While a number of religious [12] and other spiritual practices [19] have also been examined in
the context of the apparent FieldREG effect, these have typically been conducted in open, public
environments which might possess high inter-environment variability among local consciousness
(e.g., widely varied belief systems among nearby individuals). However, scenarios involving a
relatively homogenized group consciousness may be another important factor in the FieldREG
phenomenon. This suggestion could be supported by previous results regarding the apparent
importance of wide-spread coherent individual directed attention as a potential factor in global
FieldREG effects [20-22]. If coherent neuroelectrical states of consciousness do contribute to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
311
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
this process, then perhaps a more unified collective consciousness could “compensate” for any
potential loss in effect that might be introduced by smaller groups of nearby individuals [12].
With this in mind, we conducted further FieldREG investigation within an enclosure of Catholic
nuns. We suspected that any significant effects observed would be associated with times of
prayer, either during or following the actual segment of time. We had hypothesized that effects
might occur following the event given previously observed potential “lag” and anticipatory
effects of consciousness on REG devices [23].
2. Methods
2.1. Equipment
Random data were produced using two Psyleron REG-1 random event generators
(www.psyleron.com). This device produces a random output which is generated by electron
tunneling effects within two field effect transistors. The varying voltage levels which result from
this process are converted into digital data through a gated sampling procedure which allows for
regularly spaced bit sequences. The output of both transistors is internally compared through an
alternating (0, 1) XOR masking process in order to reduce any potential influence of physical
artifacts or other external environmental variables. The device itself is further protected from
static electromagnetic factors by an aluminum outer shielding and a Permalloy mu-metal inner
shield. Furthermore, the device was rigorously calibrated prior to shipment in order to ensure
output conformed to statistical expectations. The random event generator (REG) devices were
also tested in control experiments within respective laboratories (Spain and Canada) to confirm
these expectations. The resulting data streams were collected through USB-port using the
Psyleron FieldREG software package on laptop computers. Individual events were produced at a
rate of either 1/sec or 5/sec (1 event = 200 bits). However, internal consistency was maintained
within each experiment. There were no significant differences noted between event rates in
previous testing [12].
Values for each individual REG event refer to the number of 1's out of 200 bits with binary
probabilities, represented by a value of 0-200. The theoretical (chance) mean for each event is
100 with a standard deviation of √50. Each data segment (time period) from each experiment
was processed and analyzed independently according to manually time-stamped behaviours and
other occurrences in the local environment.
Data processing and descriptive statistical procedures were conducted using Microsoft Excel
software.
2.2. Data Processing
REG data from each segment within each experiment condition were analyzed independent of
either previous or subsequent values; relevant statistics and figures were produced accordingly.
Individual REG event scores were standardized according to 0.5 chance expectations ([x-100] /
√50). Combined overall z-scores for each overall experiment and each individual segment were
computed using Stouffer’s method (zc = Σz / √N) where z = individual event z-scores and N = the
number of event scores. Effect sizes follow the relationship es = zc / √N, which is equivalent to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
312
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
the mean event z-score. One-tailed probabilities (1T) are reported according to a priori valence
hypotheses previously suggested [12] regarding the directional component of REG output.
Measurement uncertainty for each segment (σμ) was computed according to σ/√2N, where σ =
√50 and N = number of REG events.
2.3. Locations
A number of varied settings were investigated with REG devices in both Spain and Canada. Data
were examined according to overall experiments and by time-stamped segments following
human events in proximity to the test environment.
The first reported experiment occurred within a nuns’ enclosure convent located in the outskirts
of Madrid, Spain. Data collection began on March 8, 2014 and was started at 18:25 local time.
Recording of random data was continuous for approximately seven days. However, given
inconsistencies with start time on the first day and subsequent segment range and REG event
sample discrepancies, along with laptop battery failure on the seventh day, these times were
excluded from further analyses. As a result, Days 1 to 5 below indicate data obtained on March 9
to 13, 2014. The actual REG device was located in the main chapel, placed inside of a box
underneath a seat located proximal to the area where about 12 enclosure nuns develop their
spiritual activity (Figure 1). Data were sampled at a rate of 5 events/sec (200 bits/event).
Figure 1. Location of REG device (arrow) throughout the Convent experiment
The primary “anomalous” site visited (Poltergeist) was that of a family home in Umbrete, Spain,
on February 12, 2014. This location and the individuals residing here were associated with an
alleged poltergeist case, which was supposedly being “produced” by the younger sister of the
family (two sisters, 16 and 23 years old, and mother). The family was in the process of moving
away from the house during this time. The REG device was placed in the younger girl’s bedroom
(e.g., Figure 2), and collected data at 5 events/sec (200 bits/event).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
313
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Figure 2. REG device was situated in the bedroom of the youngest sister (16 years of
age), who was the apparent focus for the Poltergeist events; scratches similar to those
on the wall in this image were found around the house (e.g., on TV screen, on desk,
etc.)
The next ‘anomalous’ case investigation (Haunt) involved a site associated with a series of
gruesome murders, said to be a haunt site, located in Madrid, Spain. Researchers visited the site
on January 9, 2014 and placed a REG device in the approximate center of the building (Figure
3). Data collection was conducted at a rate of 5 events/sec (200 bits/event). While the primary
field researcher left the site, there were a number of individuals present throughout the
experiment, including a journalist and psi-sensitive individual (CT), an additional journalist (C),
a well-known medium (PN), and a TV crew.
Figure 3. Camera(s) view inside Haunt location
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
314
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Experimenters also visited a minor historical location (Small Disaster Site) in Glengarry,
Ontario, Canada, known as St. Raphael’s Ruins (Figure 4; www.saintraphaelsruins.com/). There
was a large fire which occurred here in 1970, destroying all but the stone walls of one of the first
Roman Catholic churches in early English-settled Canada, while the ruins are currently
considered a national historic site. The REG device was placed both in front and back of the
building proper on January 27, 2014, while data collection was conducted at a rate of 1 event/sec
(200 bits/event).
Figure 4. Front of St. Raphael’s Ruins (2005), location of Small Disaster Site
experiment. Image source: www.saintraphaelsruins.com
3. Results
3.1. Convent
While we have previously investigated spiritual and religious activity in proximity to random
physical systems [12], the Convent experiment provided a very interesting opportunity to
investigate potential effects of “professional” religious workers over the course of many days.
Random Event Generator (REG) data were segmented according to a schedule of daily activities
provided to us (Table 1). Relevant statistics were computed for each individual day of testing, as
well as for each segment identified a priori.
Table 1. Schedule of daily activities in the convent
Activity
1. No Activity
2. Prayer
3. No Activity
4. Mass
5. No Activity
ISSN: 2153-8212
Local Time (UTC +1:00)
00:00-07:00
07:00-08:30
08:30-10:00
10:00-10:45
10:45-11:00
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
315
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
6. One Elderly Nun Prays
7. No Activity
8. Psalms
9. No Activity
10. Singing
11. Varied
12. Prayer
13. No Activity
14. Pray/Psalms
15. No Activity
16. Psalms/Lectures/Rosary
17. No Activity
11:00-12:00
12:00-12:45
12:45-13:00
13:00-14:50
14:50-15:00
15:00-16:00
16:00-16:15
16:15-19:00
19:00-20:30
20:30-22:15
22:15-22:30
22:30-00:00
Given the directional hypotheses of emotional valence, we suspected that significant deviations
obtained in REG output would conform to an overall positive mean. Furthermore, we anticipated
any anomalous REG scores to be associated with time-segments involving prayer, or those
following prayer.
Please note that additional Tables for Convent results are available in a supplementary Appendix
section.
The most interesting pattern observed for the first full day of consistent data collection (Table 2)
was the occurrence of significant REG deviations during periods of No Activity which followed
Prayer (N events = 27001, zc = -1.896, p = .029 and N events = 49501, zc = 2.282, p = .003) and
Rosary segments (N events = 9001, zc = 2.011, p = .022). While the preliminary significant
segment displayed an overall trend in the direction opposite of that anticipated by the previously
proposed valence hypothesis, the following two segments of note displayed markedly significant
deviations from chance expectation with a positive overall shifting of the mean (e.g., Figure 5),
as would be predicted by the hypothesis. Furthermore, we had anticipated potential effects could
occur following segments of prayer given previously observed lag and anticipatory dynamics of
FieldREG effects.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
316
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Figure 5. Significant cumulative deviations in REG data during Convent [Day 1]
experiment segments of No Activity following Prayer/Rosary segments; grey parabolic
curves indicate threshold for statistical significance (p = .05)
Table 2. REG event data for each Convent [Day 1] segment; N = number of REG
events, zc = combined z-score, es = effect size (zc/√N; equal to mean REG z), p =
probability (1T) of zc, σμ = measurement uncertainty (σ/√2N, where σ = √50);
*significant at p < .05 (1T); †Prayer/Rosary segments preceding significant No Activity
segments
es
.001
σµ
.008
1. No Activity
126000 -.076 .47 < -.001
2. Prayer †
27001 -.565 .286 -.003
3. No Activity *
27001 -1.896 .029 -.012
4. Mass
13501 -.422 .337 -.004
5. No Activity
4501 -1.427 .077 -.021
6. One Elderly Nun Prays
18001 -.102 .46
-.001
7. No Activity
13501
.811 .209 .007
8. Psalms
4501
.694 .244
.01
9. No Activity
33001
.872 .192 .005
10. Singing
3001
-.454 .325 -.008
11. Varied
18001
.164 .435 .001
12. Prayer †
4501
-.613 .27
-.009
13. No Activity *
49501 2.282 .003
.01
14. Pray/Psalms
27001 1.044 .148 .006
15. No Activity
31501
.096 .462 .001
16. Psalms/Lectures/Rosary † 22501 -.685 .247 -.005
17. No Activity *
9001
2.011 .022 .021
.014
.03
.03
.043
.075
.037
.043
.075
.028
.091
.037
.075
.023
.03
.028
.033
.053
Segment
FULL
ISSN: 2153-8212
N
432016
zc
.684
p
.247
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
317
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
In contrast to previous findings, there were no significant REG scores obtained during the
Convent [Day 2] experiment (ps > .05; Appendix Table A.).
Results from the Convent [Day 3] testing period again differed from those revealed during [Day
1]. The first segment including readings of Psalms was significantly different from chance
expectations, while the overall trend was in the direction opposite of that predicted, displaying
more negative values than positive (N events = 4501, zc = -2.142, p = .016). The following Prayer
segment (Table 3, 12) was also statistically significant, but revealed more positive values overall,
as earlier directional hypotheses would suggest (N events = 4501, zc = 2.093, p = .018). While the
subsequent segment of No Activity which followed this positively significant Prayer activity
displayed a significant REG deviation, in line with results from [Day 1], the overall directional
component was negative (N events = 49501, zc = -2.102, p = .018).
Table 3. REG event data for each Convent [Day 3] segment; N = number of REG
events, zc = combined z-score, es = effect size (zc/√N; equal to mean REG z), p =
probability (1T) of zc, σμ = measurement uncertainty (σ/√2N, where σ = √50);
*significant at p < .05 (1T), † indicates Prayer segment preceding significant No
Activity segment
es
.001
σµ
.008
1. No Activity
126000 .438 .331 .001
2. Prayer
27001 1.224 .111 .008
3. No Activity
27001 1.022 .153 .006
4. Mass
13501
.162 .436 .001
5. No Activity
4501 -1.054 .146 -.016
6. One Elderly Nun Prays
18001
.044 .483 < .001
7. No Activity
13501
.374 .354 .003
8. Psalms *
4501 -2.142 .016 -.032
9. No Activity
33001
.113 .455 .001
10. Singing
3001
.1
.46
.002
11. Varied
18001
.013 .495 < .001
12. Prayer * †
4501
2.093 .018 .031
13. No Activity *
49501 -2.102 .018 -.01
14. Pray/Psalms
27001 1.126 .13
.007
15. No Activity
31501 1.432 .076 .008
16. Psalms/Lectures/Rosary 22501
.75
.227 .005
17. No Activity
9001
.848 .198 .009
.014
.03
.03
.043
.075
.037
.043
.075
.028
.091
.037
.075
.023
.03
.028
.033
.053
Segment
FULL
N
432016
zc
.615
p
.269
While the preliminary reading from Psalms during [Day 3] testing displayed a conspicuous REG
deviation, the segment of No Activity following this period displayed a significant trend on [Day
4] (N events = 33001, zc = -2.21, p = .014). While the overall direction of this data was found to
coincide with the Psalms deviation obtained the previous day, both were revealed to be in the
opposite direction of what had been anticipated (Figure 6). The only other segment during [Day
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
318
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
4] to produce a significant REG score was found while the nuns were Singing (N events = 3001, zc
= 1.957, p = .025). Furthermore, this particular activity demonstrated an overall positive trend
consistent with our initial theories. All other time periods displayed results similar to baseline
testing (Appendix Table B.).
Figure 6. Significant cumulative deviation in REG data during Convent [Day 4]
experiment segment of No Activity following Psalms segments; grey curve indicates
threshold for statistical significance (p = .05)
Finally, the last full day of testing, [Day 5], revealed a single independently significant time
period of REG output which coincided with the first segment of Prayer for that day (N events =
27001, zc = 1.929, p = .027). This particular period of testing also deviated in the direction
hypothesized by the emotional valence theory previously posited with a positive overall mean
(Figure 7). All other time segments from [Day 5] displayed non-significant results (Appendix
Table C.).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
319
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Figure 7. Significant cumulative deviation in REG data during Convent [Day 5]
experiment, preliminary Prayer segment; grey curve indicates threshold for statistical
significance (p = .05)
3.2. Poltergeist
While the setting for the previous experiment was relatively similar in nature to our earlier
results [12], the Poltergeist case allowed us to examine an area of parapsychology which has
seen very little attention in the literature. This is particularly vexing given the strongly
hypothesized links between macro-scale mind-matter interaction and poltergeist phenomena [6,
24]. In these cases, an individual is often the “focus” or “source” of the apparent activity, which
may include unexplained movement of relatively large-scale objects [17]. Again, the REG data
were segmented according to time-stamped notes taken by a Transnational Anomalies Research
(TAR) senior investigator. Statistical results were computed for both the full experiment and for
each time segment. These included researchers alone in the house, the sisters returning to the
house, the youngest sister (apparent focus of the reported poltergeist activity) entering the room
where the REG device was located, and a hypnosis session conducted by the on-site TAR senior
investigator with the younger sister (Table 4).
According to our preliminary hypothesis regarding emotional valence in relation to the
directional component of the FieldREG phenomenon [12], we expected any significant
excursions away from the mean found within the data to be negative (down).
Final statistical results revealed a small but statistically significant overall deviation for the full
experiment (Figure 8; N events = 42992, zc = -1.751, p = .04). The directional component of the
REG data (negative, down) supported the pre-stated hypothesis according to the emotional
valence theory, given the extremely negative emotional state attached to this location by the
surrounding individuals. The only other test segment which deviated significantly from chance
expectation occurred when the family had left, while the experimenters were alone in the house
(N events = 7500, zc = -1.803, p = .036). All other segments were within the expected range (ps >
.05).
Figure 8. Cumulative deviation in REG data during Poltergeist experiment; grey curve
indicates threshold for statistical significance (p = .05)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
320
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Table 4. REG event data for each Poltergeist segment; N = number of REG events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability (1T) of
zc, σμ = measurement uncertainty (σ/√2N, where σ = √50); *significant at p < .05 (1T)
Segment
FULL *
N
zc
42992 -1.751
p
.04
es
σµ
-.008 .024
1. Start REG
15000 -.643 .26 -.005 .041
2. Alone in House *
7500 -1.803 .036 -.021 .058
3. Investigators Return 1500 -.632 .264 -.016 .129
4. Girl in Living Room 4500 -.725 .234 -.011 .075
5. Girl in Bedroom
6000 -1.358 .087 -.018 .065
6. Hypnosis
8492
.545 .293 .006 .054
3.3. Haunt
Locations which are considered to be “haunted” differ from poltergeist phenomena, in that an
individual is typically the focus of the physical manifestations associated with poltergeists [1618]. However, in alleged haunt cases, the anomalous activity is often related to the actual
location and not centred on any individual or group of individuals as the potential source(s) of
activity [13-14]. This activity may include reports of seeing or hearing things, to which similar
occurrences here were given particular attention. While REG data from the Haunt session were
analyzed for the entire testing period, we also investigated relevant statistics for each timestamped segment recorded by CT (journalist and psi-sensitive), who was present for the duration
of the experiment. A medium (PN) also conducted psychophonic testing, which includes alleged
“spirits” speaking through a medium.
As per the directional hypotheses associated with the Poltergeist experiment, we similarly
anticipated significantly negative deviations would be revealed during the Haunt testing.
Particular attention was given to the segments during which those present reported anomalous
sights and sounds (Table 5).
While the overall trend for the combined testing period, including a number of mundane
moments, was in the predicted direction (negative, down), the combined REG cumulative
deviation (Figure 9) for the entire experiment was within chance expectations (N events = 127503,
zc = -1.528, p > .05). There were a number of individual test segments which displayed
significant excursions from the mean, all of which were in the anticipated direction (negative,
down) with the exception of one (Table 5, 22). These included reports of seeing dead people (N
events = 300, zc = -1.715, p = .043), seeing somebody enter the room while hearing voices (N events
= 300, zc = 1.992, p = .023), psychophonic testing within the neighbouring warehouse (N events =
8100, zc = -1.834, p = .033), and reports of hearing a female voice (N events = 600, zc = -2.003, p =
.023), all of which are shown in Figure 10. Relevant REG statistics for all segments from the
Haunt experiment are provided in Table 5.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
321
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Figure 9. Cumulative deviation in REG data during Haunt experiment; grey curve
indicates threshold for statistical significance (p = .05)
Figure 10. Cumulative deviation in REG data during significant segments from Haunt
experiment which occurred in association with reports of [seeing] or “hearing” things;
grey parabolic curves indicate threshold for statistical significance (p = .05)
Table 5. REG event data for each Haunt segment; N = number of REG events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability (1T) of
zc, σμ = measurement uncertainty (σ/√2N, where σ = √50); *significant at p < .05 (1T);
for Segment titles, “ “ indicates what was ‘heard’ while [ ] indicates what was ‘seen’
Segment
FULL
1. Start REG
2. [‘Orbs’]
ISSN: 2153-8212
N
zc
p
es
σµ
127503 -1.528 .063 -.004 .014
10500
2100
-.894
-.253
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
.186 -.009 .049
.4 -.006 .109
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
322
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
3. Mirror Falls
4. Crew Jokes
5. Empty House
6. CT Arrives
7. C Arrives
8. PN Arrives
9. TV Crew Leaves
10. PN: “Man Yelling”
11. PN: “Voices”
12. CT/C: “Noises”
13. PN: [Woman on Floor]
14. PN: “Crying Child”
15. CT Change Batteries
16. PN: Describe Murderer/”Noise”
17. PN: [3 Dead People] *
18. PN: Tired – Pause
19. PN Uses Glass Ball/”Crying Woman”
20. Mobile Phone Interruption
21. PN: [Girl/Blood]
22. PN: [Person in Room]/“Voices” *
23. PN: [Man Cut]
24. “Two Men Argue”
25. PN: “3 Different Stories”
26. People Joke
27. Move to ‘Safe’ Room
28. “Female Voice”
29. Ouija Talk/“Voice” on Recorder
30. Ouija: Name is Adela
31. Feel Cold
32. Psychophonic Test in Warehouse *
33. “Noises”
34. “Voices”
35. “Noises”
36. Psychophonic Test II in Bathroom
PN Leaves
37. “Noise/Voice”
38. Enter Bedroom
39. Enter Living Room
40. “Male Voice/Child Scream”
41. “Female Voice”
42. Enter Children’s Bedroom
43. “Male Voice: Threat”
44. Enter Second Bedroom
45. “Female Voice” *
46. Enter Gymnasium
ISSN: 2153-8212
3900
5100
15000
5400
1500
9600
3900
900
600
300
600
300
600
300
300
1200
300
300
1200
300
300
600
300
600
900
300
1800
2400
300
8100
600
900
4500
1500
.082
.353
-1.284
-.137
-.132
-1.09
-.204
-.547
.202
-.735
.993
-1.176
-.329
-.065
-1.715
.637
-.098
-.531
.253
1.992
-.139
-.879
.016
-1.57
1.179
-.498
-.297
1.64
.783
-1.834
.751
.83
.725
-.705
.467
.362
.1
.446
.448
.138
.419
.292
.42
.231
.16
.12
.371
.474
.043
.262
.461
.298
.4
.023
.445
.19
.494
.058
.119
.309
.383
.051
.217
.033
.226
.203
.234
.241
.001
.005
-.01
-.002
-.004
-.01
-.003
-.018
.008
-.042
.041
-.068
-.013
-.004
-.099
.018
-.006
-.031
.007
.115
-.008
-.036
.001
-.064
.039
-.029
-.007
.034
.045
-.02
.031
.028
.011
-.018
.08
.07
.041
.068
.129
.051
.08
.167
.204
.289
.204
.289
.204
.289
.289
.144
.289
.289
.144
.289
.289
.204
.289
.204
.167
.289
.118
.102
.289
.056
.204
.167
.075
.129
900
2100
5400
1200
600
7200
600
2400
600
1800
.047
.2
-1.297
.265
1.01
-.402
-.456
-1.167
-2.003
1.11
.481
.421
.097
.396
.156
.344
.324
.122
.023
.134
.002
.004
-.018
.008
.041
-.005
-.019
-.024
-.082
.026
.167
.109
.068
.144
.204
.059
.204
.102
.204
.118
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
323
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
47. “Child Voice”
48. Ending of Session
49. Everyone Leaves
600
7200
7403
-1.022 .153 -.042 .204
.548 .292 .007 .059
-.714 .238 -.008 .058
3.4. Combined Results for Poltergeist and Haunt Cases
Given the overt thematic link between the Poltergeist and Haunt cases (e.g., strong association
with “ghosts” or “spirits”, object movement, anomalous subjective experiences, etc.), we pursued
further exploration of these experiments in combination. REG output from each test period was
combined in order to compute relevant statistics (Figure 11), which revealed a significant
deviation in the overall data (N events = 170495, zc = -2.201, p = .014, es = -.005, σµ = .012).
Finally, the results further enhanced the support given to the directional expectations of
subjectively negative emotional contexts and the FieldREG phenomenon.
Figure 11. Cumulative deviation in REG data for combined Poltergeist and Haunt
experiment; grey curve indicates threshold for statistical significance (p = .05)
3.5. Small Disaster Site
We have now investigated a range of varied settings with regard to associated REG activity,
including both negative and positive group emotions, novel and mundane group environments,
fear, and physical pain [12], while expanding on these results with those obtained from the
Convent, Poltergeist, and Haunt experiments. However, analysis of data obtained from a
smaller-scale, isolated structural disaster without associated loss of human life has yet to be
examined in an exploratory FieldREG context.
We hypothesized little if any potential effects would be observed within the collected data given
the highly localized and less subjectively novel historical event associated with this site. While
we did not expect to find significant results for this experiment, we felt it necessary to be as
wide-ranging and thorough as possible in our current series of investigations exploring a number
of varied environments.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
324
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
As anticipated, the REG output obtained from the Small Disaster Site overall test period showed
results very similar to baseline measures (Figure 12), while all individual test segments,
completed at both the front and rear of the building (Table 6), revealed similarly non-significant
results (ps > .05).
Figure 12. Cumulative deviation in REG data during Small Disaster Site experiment;
grey parabolic curves indicate threshold for statistical significance (p = .05)
Table 6. REG event data for each Small Disaster Site segment; N = number of events,
zc = combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability
(1T) of zc, σμ = measurement uncertainty (σ/√2N, where σ = √50); *significant at p < .05
(1T)
p
.477
es
.001
σµ
.114
Segment
FULL
N
1937
zc
.058
1. Front of Building
2. Back of Building
3. Back of Building II
645
626
666
-.373 .355 -.015 .197
.729 .233 .029
.2
-.241 .405 -.009 .194
4. Discussion
The preceding results provide a moderate degree of support for previous research in this specific
area of exploration [10-12]. However, the activities and contexts examined in the current study
were generally quite different from those previously examined. This was particularly the case for
the Poltergeist and Haunt experiments, both of which provided interesting results.
The first reported experiment, the Convent, while the most thematically similar to a number of
situations we had previously investigated [12], also revealed results which were particularly
difficult to interpret. Although an exploratory study, the findings obtained from the nuns’
enclosure were both inconsistent regarding their daily occurrence, or lack thereof, and at times
were in contrast to our initial FieldREG investigations regarding the directional component of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
325
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
REG output in the presence of specific subjective emotional contexts [12]. However, exploratory
interpretation of the results will be discussed.
Disregarding the sporadic violation of our pre-stated emotional valence hypothesis, the
inconsistency of the results, while still of potential interest, made construction of an overall
hypothesis difficult for this experiment. Results from the first full day of continuous data
collection were particularly intriguing despite the occurrence of each significant REG deviation
being associated with time periods of no activity. Of specific interest regarding this finding was
the fact that each of these periods of anomalous REG output associated with times of no activity
in the local human environment directly followed extended periods of prayer. An initial
suggestion was that the spiritual activity of the nuns could have introduced a residual affecting
agent or subtle energy which displayed a lagged effect in the data. While this idea may appear
farfetched, it is consistent with contemporary literature regarding traditional and alternative
medicine and energy healing [25].
However, it was also noted that this apparent effect was not consistent over the course of several
days of testing. In reality, the second full day of data collection did not display any significant
REG deviations. While this could potentially be attributed to some form of novelty effect [12],
significant results were found for subsequent days of testing. While a number of additional
periods of no activity were found to be statistically significant, these were consistently preceded
by times of prayer or readings from Psalms, as found for the first day. Additionally, there were a
number of periods of prayer and reading from Psalms which presented with significant REG
deviations, with a single period of significance found during group singing. While intriguing in
an exploratory capacity, these findings often varied with regard to the overall directional
component of the data (e.g., more positive values vs. more negative values), further confounding
an overall interpretation of the results.
A number of questions have been considered following analysis of these findings; could it be
that more consistent and stronger overall results were obtained on the first day due to the nuns’
apparent motivation regarding the experiment? Did their collective “intentions” in the context of
the experiment diminish prior to the second day? Of course, these considerations require further
experiments to make any concrete conclusions. However, it could also have been that other
psychological variables contributed to the sporadic and inconsistent Convent results, which is
also consistent with previous theories in this area [26]. At this preliminary stage of investigation,
it cannot be discounted that variable mood among members of the convent could have affected
the overall outcome observed. Again, further investigation of this specific FieldREG context is
required to begin addressing these questions.
Another possible consideration for the Convent results directly relates to the Poltergeist
experimental findings; do prayer and other religious activities serve as a potential means of
“normalizing” the immediate environment, and could this account for the apparent data
anomalies observed during periods of no activity which followed prayer? It is particularly
interesting to note that the isolated time period of independent statistical significance in the
Poltergeist case followed the foci of the phenomenon (e.g., the family) vacating the premises.
Perhaps specific types of activity, not limited to the nuns’ prayers, are capable of introducing an
unknown environmental change in the immediate vicinity which becomes disrupted upon a
subsequent absence of the apparent source.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
326
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Regardless of this preliminary hypothesis, the overall findings for the Poltergeist experiment
generally supported our initial theory of emotional valence and the FieldREG phenomenon.
Overall results from this experiment were both statistically significant and consistent with the
anticipated direction of REG deviation (negative). This could support the contention that
subjectively negative emotions and activities are more often associated with negative trends in
REG output. However, this specific case also examined a context which has largely been ignored
in the previous FieldREG literature [10-12]. As such, the Poltergeist results obtained here might
further support the previously discussed “recurrent-spontaneous psychokinesis” (RSPK) model
of the poltergeist phenomenon, and provide an interesting new avenue of potential research for
further FieldREG explorations.
Given that cases of alleged haunts have not typically been associated with the RSPK model of
paranormal phenomena previously noted, the Haunt experiment was particularly interesting and
novel in this context. This period of testing allowed us to explore the thematic link between
poltergeists and haunt reports as a potential factor in the apparent FieldREG phenomenon,
considering the generally lacking theoretical and experimental associations between haunt
activity and mind-matter interactions or 3C. Current results appear to provide preliminary
abstract support to the implied notion of thematic similarity between poltergeists and haunt
cases. Furthermore, these results were generally consistent with our initial hypotheses regarding
the overall directional component of this experiment given the negative overall REG trend
observed.
A number of Haunt segments were revealed to be independently statistically significant. These
periods were typically associated with reports of seeing or hearing things in the area, as per our
initial hypotheses, with an individual segment of psychophonic testing by the on-site medium
also displaying a significant REG deviation. Furthermore, all of these segments supported the
emotional valence theory of FieldREG processes, showing overall negative trends in the data,
with a single exception of positive deviation occurring when the medium had reported seeing
somebody enter the room while hearing voices.
As anticipated, the Small Disaster Site data output obtained from the grounds of St. Raphael’s
Ruins displayed baseline REG activity. While the previous Convent and Poltergeist experiments
might imply some form of residual influence on the random stream of data produced by the
device, as evidenced by the conspicuous lagged effects, this particular experiment suggests that
there could be a “window of opportunity” with regard to these hypothesized latent effects. While
the subjectively negative emotions attached to the event which historically took place at this site
may have been particularly strong, the REG output conformed to expectations associated with
areas devoid of recent human influence.
While these hypotheses and suggestions are preliminary and exploratory in nature, results of the
current experiments further suggest that future research is required to probe the seemingly
complicated nature of apparent FieldREG effects. Furthermore, given the recent lack of
FieldREG investigations conducted by other researchers in this area, we hope to stimulate a
renewed interest in potential effects of group consciousness on the behavior of random physical
systems.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
327
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Acknowledgments: The authors would like to extend thanks to additional members of the Transnational
Anomalies Research team, including Francisco Colinas, David A. E. Vares, and Herb Mertz.
References
1) Jahn, R. G., Dunne, B. J., Nelson, R. D., Dobyns, Y. H., & Bradish, G. J. (1997). Correlations of
random binary sequences with pre-stated operator intention: A review of a 12-year program. Journal of
Scientific Exploration, 11(3), 345-367.
2) Radin, D. I., & Nelson, R. D. (2003). Meta-analysis of mind-matter interaction experiments: 19592000. In Healing, Intention, and Energy Medicine (pp. 39-48). London: Harcourt Health Sciences.
3) Caswell, J. M., Collins, M. W. G., Vares, D. A. E., Juden-Kelly, L. M., & Persinger, M. A. (2013).
Gravitational and experimental electromagnetic contributions to cerebral effects upon deviations from
random number variations generated by electron tunneling. International Letters of Chemistry, Physics
and Astronomy, 11, 72-85.
4) Caswell, J. M., Dotta, B. T., & Persinger, M. A. (2014). Cerebral biophoton emission as a potential
factor in non-local human-machine interaction. NeuroQuantology, 12(1), 1-11.
5) Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M., & Persinger, M. A. (2014). Simulated effects of
sudden increases in electromagnetic activity on deviations in random electron tunnelling behaviour
associated with cognitive intention. Journal of Consciousness Exploration & Research, 5(2), 85-102.
6) Caswell, J. M., Juden-Kelly, L. M., Vares, D. A. E., & Persinger, M. A. (2014). An investigation of
solar features, test environment, and gender related to consciousness-correlated deviations in a random
physical system. Journal of Scientific Exploration, in press.
7) Moddel, G. (2004). Entropy and subtle interactions. Journal of Scientific Exploration, 18(2), 293-306.
8) Moddel, G. (2006). Entropy and information transmission in causation and retrocausation. In D.
Sheehan (Ed.), Frontiers of Time, Retrocausation: Experiment and Theory (pp. 62-74). Melville, NY:
American Institute of Physics.
9) Caswell, J. M. (2014). Consciousness, cross-cultural anomalies and a call for experimental research in
paranthropology. Journal of Consciousness Exploration & Research, in press.
10) Nelson, R. D., Bradish, G. J., Dobyns, Y. H., Dunne, B. J., & Jahn, R. G. (1996). FieldREG
anomalies in group situations. Journal of Scientific Exploration, 10(1), 111-141.
11) Nelson, R. D., Jahn, R. G., Dunne, B. J., Dobyns, Y. H., & Bradish, G. J. (1998). FieldREG II:
Consciousness field effects: Replications and explorations. Journal of Scientific Exploration, 12(3), 425454.
12) Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C., & Tessaro, L. W. E. (2014).
The potential effects of human group emotion and subjective novelty on the statistical behaviour of a
random event generator: Exploratory study. Journal of Consciousness Exploration & Research, 5(3), 195214.
13) Houran, J., Wiseman, R., & Thalbourne, M. A. (2002). Perceptual-personality characteristics
associated with naturalistic haunt experiences. European Journal of Parapsychology, 17, 17-44.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
328
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
14) Braithwaite, J. J. (2004). Magnetic variances associated with 'haunt-type' experiences: A comparison
using time-synchronised baseline measurements. European Journal of Parapsychology, 19, 3-28.
15) Lange, R., Houran, J., Harte, T. M., & Havens, R. A. (1996). Contextual mediation of perceptions in
hauntings and poltergeist-like experiences. Perceptual and Motor Skills, 82, 755-762.
16) Roll, W. G., Saroka, K. S., Mulligan, B. P., Hunter, M. D., Dotta, B. T., Gang, N., Scott, M. A., StPierre, L. S., & Persinger, M. A. (2012). Case report: A prototypical experience of 'poltergeist' activity,
conspicuous quantitative electroencephalographic patterns, and sLORETA profiles - suggestions for
intervention. Neurocase, 18(6).
17) Solfvin, G. & Roll, W. G. (1976). A case of RSPK with an epileptic agent. Parapsychology Review,
7(2), 20-21.
18) Martinez-Taboas, A. (1984). An appraisal of the role of aggression and the central nervous system in
RSPK agents. Journal of the American Society for Psychical Research, 78(1), 55-69.
19) Mason, L. I., Patterson, R. P., & Radin, D. I. (2007). Exploratory study: The random number
generator and group meditation. Journal of Scientific Exploration, 21(2), 295-317.
20) Nelson, R. D. (2001). Correlation of global events with REG data: An internet-based, nonlocal
anomalies experiment. The Journal of Parapsychology, 65, 247-271.
21) Nelson, R. D. (2002). Coherent consciousness and reduced randomness: Correlations on September
11, 2001. Journal of Scientific Exploration, 16(4), 549-570.
22) Nelson, R. D., Radin, D. I., Shoup, R.,& Bancel, P. A. (2002). Correlations of continuous random
data with major world events. Foundations of Physics Letters, 15(6).
23) Nelson, R. D. & Bancel, P. A. (2006). Anomalous anticipatory responses in networked random data.
AIP Conference Proceedings, 863.
24) Gearhart, L. & Persinger, M. A. (1986). Geophysical variables and behavior: XXXIII. Onsets of
historical and contemporary poltergeist episodes occurred with sudden increases in geomagnetic activity.
Perceptual and Motor Skills, 62, 463-466.
25) Cohen, K. (1999). The Way of Qigong: The Art and Science of Chinese Energy Healing. Random
House LLC.
26) Drennan, S. L., Roe, C. A., & Broughton, R. S. (2011). Lability, paranormal beliefs and psychokinetic
experiences: Development of the Lability Scale using an online survey-based study. Parapsychological
Association 54th Annual Convention (pp.25-26).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
329
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
Appendix
Table A. REG event data for each Convent [Day 2] segment; N = number of REG
events, zc = combined z-score, es = effect size (zc/√N; equal to mean REG z), p =
probability (1T) of zc, σμ = measurement uncertainty (σ/√2N, where σ = √50)
Segment
FULL
N
432016
zc
-.12
p
es
σµ
.452 < -.001 .008
1. No Activity
126000 .365 .358 .001
2. Prayer
27001 -.535 .296 -.003
3. No Activity
27001
.715 .237 .004
4. Mass
13501 -.063 .475 -.001
5. No Activity
4501 -1.062 .144 -.016
6. One Elderly Nun Prays
18001 -.404 .343 -.003
7. No Activity
13501 -1.631 .052 -.014
8. Psalms
4501
.833 .203 .012
9. No Activity
33001 -.048 .481 < -.001
10. Singing
3001
.666 .253 .012
11. Varied
18001
.24
.405 .002
12. Prayer
4501
-.413 .34
-.006
13. No Activity
49501 -.518 .302 -.002
14. Pray/Psalms
27001 -.905 .183 -.006
15. No Activity
31501
.009 .497 < .001
16. Psalms/Lectures/Rosary 22501
.658 .255 .004
17. No Activity
9001
.47
.319 .005
.014
.03
.03
.043
.075
.037
.043
.075
.028
.091
.037
.075
.023
.03
.028
.033
.053
Table B. REG event data for each Convent [Day 4] segment; N = number of REG
events, zc = combined z-score, es = effect size (zc/√N; equal to mean REG z), p =
probability (1T) of zc, σμ = measurement uncertainty (σ/√2N, where σ = √50);
*significant at p < .05 (1T), † Psalms segment preceding significant No Activity
segment
ISSN: 2153-8212
Segment
FULL
N
432016
zc
-.129
p
es
σµ
.449 < -.001 .008
1. No Activity
2. Prayer
3. No Activity
4. Mass
5. No Activity
6. One Elderly Nun Prays
7. No Activity
8. Psalms †
9. No Activity *
126000
27001
27001
13501
4501
18001
13501
4501
33001
-.298
.409
.544
.441
-.002
.306
.566
.034
-2.21
.383 -.001
.341 .003
.293 .003
.33
.004
.5 < -.001
.38
.002
.286 .005
.487 .001
.014 -.012
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
.014
.03
.03
.043
.075
.037
.043
.075
.028
www.JCER.com
Journal of Consciousness Exploration & Research| May 2014 | Volume 5 | Issue 4 | pp. 309-330
330
Caswell, J. M., Gaona, J. M., Tessaro, L. W. E., Rouleau, N., & Lapointe, A., Transnational FieldREG Exploration II: Investigating the
FieldREG Phenomenon in a Range of Novel Settings
10. Singing *
11. Varied
12. Prayer
13. No Activity
14. Pray/Psalms
15. No Activity
16. Psalms/Lectures/Rosary
17. No Activity
3001
18001
4501
49501
27001
31501
22501
9001
1.957
-.967
-.831
-.37
-.448
.27
-1.437
.139
.025
.167
.203
.356
.327
.394
.075
.445
.036
-.007
-.012
-.002
-.003
.002
-.01
.002
.091
.037
.075
.023
.03
.028
.033
.053
Table C. REG event data for each Convent [Day 5] segment; N = number of REG
events, zc = combined z-score, es = effect size (zc/√N; equal to mean REG z), p =
probability (1T) of zc, σμ = measurement uncertainty (σ/√2N, where σ = √50);
*significant at p < .05
Segment
FULL
N
432016
zc
.637
p
.262
es
.001
σµ
.008
1. No Activity
126000 .545 .293 .002 .014
2. Prayer *
27001 1.929 .027 .012 .03
3. No Activity
27001
.775 .219 .005 .03
4. Mass
13501
.635 .263 .006 .043
5. No Activity
4501
.565 .286 .008 .075
6. One Elderly Nun Prays
18001 -.443 .329 -.003 .037
7. No Activity
13501
.64
.261 .006 .043
8. Psalms
4501
-.831 .203 -.012 .075
9. No Activity
33001 -1.366 .086 -.008 .028
10. Singing
3001
-.754 .226 -.014 .091
11. Varied
18001
-.78 .218 -.006 .037
12. Prayer
4501
-.103 .459 -.002 .075
13. No Activity
49501 1.589 .056 .007 .023
14. Pray/Psalms
27001
.551 .291 .003 .03
15. No Activity
31501
.687 .246 .004 .028
16. Psalms/Lectures/Rosary 22501 -.199 .421 -.001 .033
17. No Activity
9001
1.47 .071 .016 .053
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
575
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 575-579
Kaufman, S. E., Consciousness & Form
Realization
Consciousness & Form
Steven E. Kaufman*
ABSTRACT
Consciousness-without-an-object Is. What you actually are is Consciousness-without-an-object.
What everything actually Is is Consciousness-without-an-object. You are not the forms of
experience that you have used to create your form or object-identity. You are That which
apprehends the forms that make up your object-identity. You are That which creates the forms
that make up your object-identity.
Key Words: Consciousness, existence, self-relation, form, experience.
Consciousness-without-an-object Is.
Consciousness-without-an-object is all there actually Is.
Everything else only exists.
Everything else only arises out of the Is-ness that is Consciousness-without-an-object.1
Consciousness-without-an-object is God.
What you actually are is Consciousness-without-an-object.
What everything actually Is is Consciousness-without-an-object.
Consciousness-without-an-object has no attributes or characteristics.
Attributes and characteristics arise where Consciousness-without-an-object flows in relation to
Itself.
Where Consciousness-without-an-object flows in relation to Itself, form comes into existence.
Form exists, Consciousness-without-an-object Is.
Form is nothing more than a boundary that arises or comes into existence within the Is-ness of
Consciousness-without-an-object where Consciousness-without-an-object comes to be in relation
to Itself, analogous to the line that arises where the tips of two fingers meet.
Consciousness-without-an-object is That which apprehends the form that arises within Itself as it
flows in relation to Itself.
1
The phrase "Consciousness-without-an-object" was originally used by Franklin Merrell-Wolff to point toward the ultimately
indescribable, non-perceptual and non-conceptual Reality that he directly Realized himself, as well as the universe and beyond,
to Be. The phrase "Consciousness-without-an-object Is" was originally used by Merrell-Wolff in aphorisms that he used to point
toward that Reality in his book, The Philosophy of Consciousness Without an Object.
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
576
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 575-579
Kaufman, S. E., Consciousness & Form
All experience, be it of the emotional, mental, or physical variety, is the apprehension by
Consciousness-without-an-object of the form that Its relation to Itself has caused to arise and so
exist within Itself.
That which apprehends form as experiential reality is therefore identical to That which, through
relation to Itself, creates the form that is being experienced as reality.
That which apprehends form as experiential reality is identical to That which is creating the form
that It is experiencing as reality.
Underlying the appearance of all form, underlying every experiential reality, lies the Is-ness of
Consciousness-without-an-object.
Surrounding all that appears as form, surrounding every experiential reality, is the enveloping
Presence of Consciousness-without-an-object.
Presence and Is-ness are identical to Consciousness-without-an-object.
Consciousness-without-an-object is identical to God.
Because Consciousness-without-an-object is all that Is, all relations are relations of
Consciousness-without-an-object to Itself.
Just as it may seem that one can be in relation to what is only a reflection, when what one is
actually in relation to is that upon which the reflection rests, so too it may seem that
Consciousness-without-an-object can be in relation to form, when what Consciousness-withoutan-object is really in relation to is that upon which form rests, which is also Consciousnesswithout-an-object.
The particular form that arises out of the Is-ness that is Consciousness-without-an-object, where
Consciousness-without-an-object flows in relation to Itself, depends upon the particular way in
which Consciousness-without-an-object is Flowing, or Being, in relation to Itself.
It is the particular way in which Consciousness-without-an-object is Flowing, or Being, in
relation to Itself that determines the nature of the form that is created within, and so arises
within, and so exists within, the Is-ness that is Consciousness-without-an-object.
Therefore, the attributes and characteristics of a particular experience do not inhere in the
uncreated Is-ness of Consciousness-without-an-object.
Nor however do the attributes and characteristics of a particular experience inhere directly in the
created form.
So, if the attributes and characteristics of a particular experience inhere neither in Consciousnesswithout-an-object nor in the particular form Consciousness-without-an-object creates within
Itself, then from whence do the attributes and characteristics of a particular experience derive?
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
577
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 575-579
Kaufman, S. E., Consciousness & Form
The attributes and characteristics of a particular experience derive from the combination of the
nature of the particular form that Consciousness-without-an-object has, through relation to Itself,
created within Itself, and the perspective within that relation from which Consciousness-withoutan-object is apprehending that particular form as a particular experience.
All there actually Is is Consciousness-without-an-object.
Nothing that Is is actually hard or soft.
Nothing that Is is actually wave or particle.
Nothing that Is is actually anything other than Is.
Consciousness-without-an-object Is on both sides of any form that arises within Itself as it flows
in relation to Itself.
However, the apprehension of form as an experience or as an experiential reality by
Consciousness-without-an-object requires that Consciousness-without-an-object adopt a
perspective upon the form that has been created within Itself.
It is that perspective upon the created form, combined with the particular nature of the created
form, which particular nature derives from the particular relation of Consciousness-without-anobject to Itself that creates it, that grants to or superimposes upon the form what seems to be its
attributes or characteristics.
For example, a created form, apprehended by Consciousness-without-an-object from one
perspective within the overall relation to Itself that creates that particular form, appears as the
experience of a wave reality.
That same created form, apprehended by Consciousness-without-an-object from the opposite
perspective within the overall relation to Itself that creates that particular form, appears as the
experience of a particle reality.
Where then is the reality of the apprehended form, the reality of the apprehended experience?
It lies both in the relation that creates the form, as well as in the perspective within that relation
from which the created form is apprehended by Consciousness-without-an-object as an
experiential reality.
Where the reality of the apprehended experience therefore does not lie is in the created form
itself, nor does the reality of the apprehended experience lie in That which apprehends the form
as a particular experiential reality.
Put another way, the reality of the apprehended experience lies neither in what is created nor in
That which creates, but rather derives from and inheres in the simultaneous relations of Creator
to Itself that creates the particular form and of Creator to particular form that causes that
particular form to be apprehended by its Creator as an experiential reality with particular
characteristics and attributes.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
578
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 575-579
Kaufman, S. E., Consciousness & Form
It is all a magic show, and we are both the Magician and the Audience.
We are That which creates the illusion and we are That which can either be taken in by the
illusion or see through and beyond the illusion.
The magician creates the illusion for the delight of the audience, but does not themself become
caught up in the illusion.
However, we are like a magician that has become caught up in the illusion of our own magic act,
having lost sight of how the trick is being done and so also losing sight of how object reality or
experiential reality is being made to appear as what is actually there.
The trick, the illusion, is the superimposing of characteristics and attributes upon that which
actually has none, i.e., upon form, thereby causing form apprehended as experience to appear to
be independently existent, which is to say, to appear to arise out of and exist within nothing, i.e.,
a non-is-ness, thereby obscuring and hiding the Nothing, i.e., the formless Is-ness, that is actually
there from Itself.
It is quite a trick.
You are not the forms of experience that you have used to create your form or object-identity.
You are That which apprehends the forms that make up your object-identity.
You are That which creates the forms that make up your object-identity.
You are not on one side of the relation that creates those forms, for Consciousness-without-anobject lies on both sides of any relation that creates form.
You, as Consciousness-without-an-object, are just apprehending the forms, forms that have
arisen within your Self as a result of your Flowing in relation to your Self, from a particular
perspective within that relation.
And so, for every form you apprehend as having a particular attribute or characteristic, that same
form, if apprehended from the opposite perspective in that same relation, would appear to have
the opposite attribute or characteristic.
Thus, the reality of the attribute or character of what is experienced as reality lies not in What Is
Actually There where the reality appears to be, for That is always and everywhere the same, i.e.,
What Is Actually There is always Consciousness-without-an-object. Rather, the reality of the
attribute or character of what is experienced as reality lies in both the created form as well as in
the perspective from which that created form is being apprehended by What Is Actually There.
It is possible to Know yourself as That which lies on both sides of the relation while still having
a perspective within the relation that allows What Is Actually There to apprehend the created
form that has arisen within Itself as a particular experience with a particular character.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
579
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 575-579
Kaufman, S. E., Consciousness & Form
However, if while apprehending a particular experience one takes the character of what has been
apprehended for something that is intrinsic to and inheres in the form itself, and so takes the
created form apprehended as experience for what is actually there, then What Is Actually There
is obscured, and so seems to vanish, in which case Knowledge of yourself as That must be
obscured as well.
And then all that seems to remain is form, all that seems to remain is the experiential reality, all
that seems to remain is the form that has now become an object.
And so then the question "what am I?" can only be answered using what is then available, which
is only some form, some experiential reality, some object, some perceptual or conceptual this or
that, so that the question "what am I?" is then answered by the arising of the idea that "I am this,"
or "I am that."
And so the form-identity arises.
And so delusion begins.
And delusion is maintained because we work so hard and make so much effort to maintain the
form-identity, the ego, because we think its maintenance is necessary for our own survival, for
our continued existence, since we mistakenly think that some collection of forms is what we are.
But when one Knows That which lies on both sides of any relation that creates any form, then
the question "what am I?" has a different answer, which is "I am That which Is," or simply "I
am."
And so the form-identity does not arise.
And so delusion ends.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
630
Article
The Sedona Effect: Correlations between Geomagnetic Anomalies,
EEG Brainwaves & Schumann Resonance
Iona Miller* & Ben Lonetree
ABSTRACT
Evidence of Sedona magnetic anomaly and brainwave EEG synchronization can be
demonstrated with portable equipment on site in the field, during sudden magnetic events.
Previously, we have demonstrated magnetic anomaly charts recorded in both known and
unrecognized Sedona vortex activity locations. We have also shown a correlation or
amplification of vortex phenomena with Schumann Resonance. Adding the third measurable
parameter of brain wave activity, we demonstrate resonance and amplification among them. We
suggest tiny magnetic crystals, biogenic magnetite, make human beings highly sensitive to ELF
field fluctuations. Biological Magnetite could act as a transducer of both low frequency magnetic
fields and RF fields.
Key Words: geomagnetic activity, geomagnetic pulsations, magnetic anomalies, magnetite,
brainwaves, Sedona vortex, Schumann Resonance, healing, ESP, temporal lobe, brainwave
resonance, meditation, ESP, brainwave synchronization, biomagnetics, magnetotellurics.
All behaviors, including consciousness, are generated by and correlated with brain activity. The
activity can be conceived as complex matrices of electromagnetic patterns and their associated
chemical changes. Weak intensity complex magnetic fields generated by the earth and by human
technology affect consciousness and experience. The critical factor is not the intensity of the
fields but their patterns and the information contained within the patterns. Those patterns that
are most similar to the natural temporal configurations of brain activity are most effective.
--Michael Persinger, Behavioral Neuroscience
Introduction
The second author, Ben Lonetree, is an electrical engineer who has continuously monitored
several geophysical parameters over decades. His highly sensitive custom equipment
outperforms government stations. He says, "There is a reason why my system responds to many
things other magnetometers do not. Most are fluxgate mags. that sample a collapsing field at a
very slow sample rate. My system is simply a very large induction coil that after the amplifier
and filter stages couples into an analog to digital converter. I have the converter programmed to
use a sample rate of 240 times per second. So the systems see every little blip there is out there."
*Correspondence: Iona Miller, Independent Researcher. Email: iona_m@yahoo.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
631
Lonetree has conducted numerous experiments correlating local geophysical anomalies in earth's
magnetic field with EEG brainwaves of many subjects, and anecdotal reports of changes in
consciousness. Preliminary experiments were done as proof of concept with intent to investigate
the possibilities more deeply.
Sedona is the virtual center of Arizona. Many have claimed so, but no one has demonstrated the
Sedona Effect to a scientific standard until now. Evidence of Sedona Vortex / Brainwave EEG
synchronization can be demonstrated with portable equipment on site in the field, during sudden
magnetic events. Previously, we have demonstrated magnetic anomaly charts recorded in both
known and unrecognized Vortex activity locations. We have also shown a correlation or
amplification of vortex phenomena with Schumann Resonance (2005, Lonetree & Miller).
Adding the third measurable parameter of brain wave activity, we demonstrate resonance and
amplification among them. We suggest tiny magnetic crystals, biogenic magnetite, makes the
human being highly sensitive to ELF field fluctuations. Biological Magnetite could act as a
transducer of both low frequency magnetic fields and RF fields.
There may be more than a single electromagnetic coupling mechanism, some beyond the scope
of this paper but perhaps relevant to it, including spin-mediated neurons (Hu & Wu). For
example, geomagnetic activity fluctuates most rapidly during upsurge of solar activity which
alters brain rhythms and hormonal levels, or the downward part of the cycle, when sunspots are
rapidly diminishing. Lonetree's longitudinal EMF studies in several stages over nearly a decade
have included phases of monitoring Schumann Resonance (SR), magnetic flux and weather
patterns in the test regions of Arizona. He conducted repeatable experiments using a variety of
volunteer subjects and weather conditions. Using magnetometers and EEG, he recorded the
synchronous signals of geomagnetic anomalies with human brainwaves. Parameters include SR
(amplifies effect), brainwave frequency and amplitude, and sudden magnetic events from
multiple vortex spots. Evoked potentials include high well-being, healing, nature mystic
experiences, ESP or anomalous cognition, and other anecdotal and measurable psychophysical
phenomena.
However these sorts of investigation leave unanswered how the brain makes these global
excitations into the internal model of reality which we experience subjectively and identify with
the real world around us, or indeed how or why subjective consciousness exists in addition to the
computational capacity of the brain as a neuro-system. Because no simple chemical (or
electromagnetic) explanation seems to have the right existential status to deal with subjective
experience, the problem may need to be solved by examining more exotic physics in the brain,
such as quantum entanglement, which might lead to new forms of physical interaction which
might solve the problem of existential subjectivity. (King)
Further studies in magnetoreception may reveal new mechanisms. Questions remain: 1) What is
the nature of magnetic sensory cells? 2) By what physical mechanism is the external magnetic
field coupled into the organism (reception)? 3) How sensitive is the mechanism to small changes
in the magnetic field (detection threshold)? 4) What physical mechanisms or chemical pathways
convert the received magnetic energy into a nervous signal (transduction)?
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
632
Background of Research
Previous Study
Arguably, proof of Sedona Vortex / Brainwave EEG synchronization can be demonstrated with
portable equipment on site in the field, during sudden magnetic events. Previously, we have
demonstrated magnetic anomaly charts recorded in both known and unrecognized Vortex
activity locations. We have also shown a correlation or amplification of vortex phenomena with
Schumann Resonance. (2005, Lonetree & Miller)
Spontaneous Synchronization
Adding the third measurable parameter of brain wave activity demonstrates resonance and
amplification among them. Brainwaves are not monitored for subject-induced meditative states,
but for direct correlation in shifts with magnetic flux. No active effort is required. The subject
remains neutral, relaxed and open but does not try to influence the readings in any way.
Biomagnetic Minerals:
We suggest tiny magnetic crystals, biogenic magnetite, makes the human being highly sensitive
to ELF field fluctuations. Research has just begun to evaluate the role of magnetite in health and
disease. Magnetic mineral crystal, aligned in chains, is embedded in biological membranes.
Formation of the chain is under genetic control, but the process that produces magnetite in
organisms is still unknown.
Curiously, far more biogenic magnetite is present in animal tissues than is needed for
magnetoreception, and the biological function of this extra material is unknown. The presence of
ferromagnetic materials in biological systems could provide physical transduction mechanisms
for ELF magnetic fields, as well for microwave radiation in the .5 to 10 GHz band where
magnetite has its peak ferromagnetic resonance. Magnetite could act as a transducer of both low
frequency magnetic fields and RF fields. These models rely on the fact that magnetite will couple
strongly to the magnetic fields either through ferromagnetic resonance effects or mechanical
effects on membrane ion channels and could disrupt the normal functioning of cells in the brain
(Kirschvink).
Ferrimagnetic material is spontaneously magnetized, leaving the magnetic moments of the atoms
on different sublattices opposed. The presence of ferrimagnetic material in human brain tissue
provides plausible theoretical mechanisms for the interaction of environmental magnetic fields
with the human central nervous system. Ferromagnetism is the basic mechanism by which
certain materials form permanent magnets or are attracted to magnets. The ferromagnetic
transduction model proposed by Kirschvink suggests that the coupling of biogenic magnetite
particles in the human brain to mechanosensitive membrane ion gates may provide a mechanism
for interactions of artificial and natural environmental magnetic fields with humans.
Magnetite is the most magnetic of all the naturally occurring minerals on Earth. Humans have
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
633
cuboctahedral chains of magnetite crystals in brain tissue and elsewhere (Fig. 5). Cuboctahedral
geometry has specific synergetic properties for transduction. One of the most important shapes in
nature, cuboctahedral morphology has the properties of a "jitterbugging" vector equilibrium
matrix, the basis of tensegrity (B. Fuller; Ingber). Tensegrity (tensional integrity) applies to basic
geometrical biological building blocks. Cuboctahedral ferrite is an equilibrium growth form.
Magnetic Field Sensitivity
Magnetic nanoparticles are embedded in the inner ear (Ho). They may form the basis of an
endogenous compass in certain organisms. A geomagnetic field could induce magnetite
displacements detectable by the hair cells for purposes of geomagnetic orientation. Kirschvink et
al. (I992) have developed a simple biophysical model for understanding the response of a
magnetite-based sensory organelle moving in a viscous fluid which makes quantitative
predictions concerning the frequency vs. sensitivity relationships expected for magnetite-based
magnetoreceptors. Paramagnetism is a weak magnetic condition of substances that have
a positive but small susceptibility to magnetism. The question remains, "can it carry regenerative
instructions?"
Magnetoreception
Since biogenic magnetite seems to be everywhere in the environment, internally and externally,
it may have played a basic role in the initial development of living systems and various sensing
mechanisms. Geoelectromagnetic signal information may play a survival role in: navigation,
migration/location/orientation, and biological rhythms. There is also anticipation and detection
of subtle or catastrophic changes in seasonal variations, weather, hurricane/tornado, and
earthquakes. Evidence suggests that biological forms follow the energy patterns laid down by the
waveforms of the environment. Electromagnetic vibration can rearrange molecules and macromolecules into patterned forms (sound, RF, microwave, heat, light, etc.)
Are EMF-induced changes in biological sensitivity and sensory transduction a model for
biological detection of EM fields? Kirschvink's calculation shows that magnetosomes moving in
response to earth-strength ELF fields are capable of opening trans-membrane ion channels, in a
fashion similar to those predicted by ionic resonance models. Therefore, the presence of trace
levels of biogenic magnetite in virtually all human tissues examined suggests that similar
biophysical processes may explain a variety of weak field ELF bioeffects. There may be more
than a single electromagnetic coupling mechanism. For example, geomagnetic activity fluctuates
most rapidly during upsurge of solar activity which alters brain rhythms and hormonal levels, or
the downward part of the cycle, when sunspots are rapidly diminishing.
Lonetree's longitudinal EMF studies in several stages over nearly a decade have included phases
of monitoring Schumann Resonance (SR), magnetic flux and weather patterns in the test regions
of Arizona. He conducted repeatable experiments using a variety of volunteer subjects and
weather conditions. Using magnetometers and EEG, he recorded the synchronous signals of
geomagnetic anomalies with human brainwaves. Parameters include SR (amplifies effect),
brainwave frequency and amplitude, and sudden magnetic events from multiple vortex spots.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
634
Evoked potentials include high well-being, healing, nature mystic experiences, ESP or
anomalous cognition, and other psychophysical phenomena.
Hypothesis
We hypothesize that some individuals experiencing extraordinary visionary activity in vortex
spots may have a low threshold for kindling sub-clinical "temporal lobe transients," (TLTs),
micro-seizures which induce a host of psychosensory phenomena. Neural static and discharge
are kindled by electrical instabilities in the brain. Typically, such experiences are assigned
special personal meaning. According to neuropsychologist Michael Persinger, "God is a result of
electro-magnetic stimulation of the temporal lobes .... the God Experience is synthesized during
the temporal lobe transients."
Future research could replicate Persinger's lab research in the Sedona field setting, testing
induction of TLTs by the application of natural or artificial transcerebral complex magnetic
fields. We suggest vortex activity as a precipitating stimuli with testable parameters and
variables, including tectonic strain. Persinger argued that strain within the Earth's crust near
seismic faults produces intense electromagnetic (EM) fields, creating bodies of light (earthlights)
that some interpret as glowing UFOs. The same EM field effects can lead to hallucinations.
Further studies in magnetoreception may reveal new mechanisms. Questions remain: 1). What is
the nature of magnetic sensory cells? 2). By what physical mechanism is the external magnetic
field coupled into the organism (reception)? 3). How sensitive is the mechanism to small changes
in the magnetic field (detection threshold)? 4). What physical mechanisms or chemical pathways
convert the received magnetic energy into a nervous signal (transduction)?
Fig. 1 Example of in/out & spiraling geomagnetism
Long hailed by Native Americans as the place where “Mother Earth speaks”, and more recently
as home of the “mystical vortex”, Sedona with its redrock temples proves much more than a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
635
place of intense beauty. Many books have been written on the special "Vortex" energy field
phenomena found in Sedona. Some say it cannot be measured while others claim it is
electromagnetic in origin.
After 10 years of research using fluxgate magnetometers and large induction coils, one of the
authors (Lonetree) can definitively state that intense electromagnetic activity abounds in
Sedona.
Still, analyzing geophysical fields from multiple vectors takes skill in data interpretation of
electric (geoelectric horizon), seismic, magnetic and gravitational methods. Characteristics
include higher gravitational fields, mozaic positive and negative magnetic fields, and high values
of apparent resistivity of rocks. Massive magnetite deposits can produce magnetic fields several
times the magnitude of Earth's normal field. The presence of magnetite can give basalt
measurable magnetic properties. Remnant magnetic fields are also related to gravity and tectonic
structure. Precambrian crystalline rocks and igneous rocks generally contain sufficient magnetic
minerals to cause variations in the earth's magnetic field. The predominant magnetic mineral in
these rocks is magnetite.
Geochronology: Crustal Evolution
New rock formed from magma records the orientation of Earth's magnetic field at the time the
magma cooled. The magnetic Precambrian crystalline basement is the most likely source of the
broad magnetic high in the Sedona area. In geology, the term "crystalline basement" defines
primordial metamorphic or igneous layers below a sedimentary platform or cover.
The basement was formed underground when archaic crustal rock was changed, by intense heat
and pressure. It pre-dates life on earth. Depth to basement is one influence on magnetic
anomalies. The lithological composition of the crystalline basement consists mainly of various
meta-volcanics which 'froze' then 'folded' paleomagnetic data on wandering pole positions.
Sedimentary layers can be rich in iron oxide, compounding magnetic effects. Basaltic lava flows
may lack a crystalline structure.
The earth's magnetic field has magnetized certain minerals as the crust formed and morphed
through tectonic collisions. The magnetic crystalline basement has differences in relief and
magnetization. By taking into consideration the geological and geophysical data, regional
magnetic anomalies may be explained by changes in the relief of the homogeneously magnetized
crystalline basement and by embedded material.
High density basement
The rocks above the major density contrast are usually younger sediments and/or volcanics,
typically having densities ranging from approximately 1.9 g/cm3 to 2.6 g/cm3. Those below the
major density contrast are usually older sedimentary, volcanic and/or crystalline rocks, typically
having densities ranging from 2.6 g/cm3 to 3.0 g/cm3. High density basement may or may not be
equivalent to crystalline and/or magnetic basement.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
636
Magnetic Basement
Magnetic basement is usually equated to crystalline (felsic and mafic) or sometimes,
metamorphic basement. It is the unconformity upon which an essentially non-magnetic
sedimentary section has been deposited. Large exposures of basement (e.g., the Canadian Shield)
show it to be lithologically and magnetically heterogeneous. Very thick sequences of highly
magnetic volcanics may sometimes be considered equivalent to a magnetic basement.
Magnetic Sedimentary Section (MSS)
MSS is surface or zone within the geologic column where magnetic susceptibility contrasts are
significant enough to generate magnetic anomalies which could delineate sedimentary geology.
Susceptibility variations within the sedimentary column are generally considered near zero
except where relatively magnetic sediments (e.g., pyroclastics, arkoses, some shales) are
present.
Total Magnetic Intensity Anomaly
The total magnetic intensity anomaly field (TI) is the resultant field after correcting TF, the total
magnetic (observed) field for a regional gradient field.
Changes in the local geomagnetic field associated with stress-induced changes in rock
susceptibility and remnant magnetization were simulated. Model results show that regions of
uplift and subsidence are marked by positive and negative magnetic anomalies respectively,
while the amplitudes are controlled by the magnitude of the displacements on the basement fault.
(Onyedim)
Tectonic Evolution
Tectonic movements give form to the structure of the sedimentary deposits and to the relief of
the crystalline basement's internal structure. This, together with the relief and the depth of
occurrence of its surface, is the chief factor influencing the nature of the gravitational and
magnetic fields. An inherent characteristic of gravity and magnetic fields means that for any
given gravity or magnetic anomaly a range of density or susceptibility distributions can cause the
same anomaly.
Problems in translation include the following: (a) The structure of the gravitational field changes
substantially, depending of the depth of occurrence, and on the relief of the crystalline
basement's surface. (b) If boundaries of the first-order tectonic structures are distinctly expressed
in the crystalline basement's relief in a form of faults of considerable amplitude, then their
detection in the gravitational field is easy. The task becomes more complicated when the
foundation is without gradients and its relief is smooth. (c) In order to determine the relation of
the basement's internal structure with its relief and with the structure of the sedimentary deposits,
it is necessary to discover the differences in the basement's internal structure within the
boundaries of the different first-order tectonic structures. (d) Tracing the disjunctive dislocations
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
637
in the crystalline basement can be solved by way of geological interpretation of the gravitational
and magnetic fields. (Rukhovets, 1967)
Consequently, to compensate for this non-unique characteristic, it is necessary to introduce
independent geological and/or geophysical constraints into the interpretations of gravity and
magnetic anomalies. The Bouguer gravity field is the gravity anomaly field usually analyzed in
gravity interpretations. The gravity anomalies observed in this field are caused by density
contrasts within the crust and sub-crust of the Earth. Gravity and Magnetic fields are both
potential fields.
Terramagnetics
High density basement may or may not be equivalent to crystalline or magnetic basement. The
location within the geologic column of an area is where the deepest major susceptibility contrast
occurs. In areas where the crystalline basement is magnetic, the magnetic basement is equivalent
to crystalline basement. Shallower susceptibility contrasts (such as occur when volcanic or
magnetic sediments are in contrast with non-magnetic rocks) may mask or complicate the
interpretation of magnetic basement. Susceptibility variations within magnetic basement are
common.
In Sedona, latites extruded from volcanic plugs produce intense "circular" magnetic anomalies
and magnetic lows, because they are generally reversely polarized. Not visibly crystalline, latites
are of volcanic origin composed chiefly of sodic plagioclase and alkali feldspar with subordinate
quantities of dark-colored minerals in a finely crystalline to glassy groundmass. Faults and
igneous intrusions often produce small local distorting magnetic fields, according to USGS
Magnetic Anomaly Survey. Maghemite forms as nodular growths in laterites and weathers out to
form ironstone gravels
Sedona is rich in paramagnetic Fe2o3, (iron oxide; hematite), the element responsible for the red
rocks, soil, and even the red color of the inner bark of trees. Iron oxide has magnetic properties
depending on factors including pressure. Iron(III) oxide is the inorganic compound with the
formula Fe2O3. It is of one of the three main oxides of iron, the other two being iron(II)
oxide(FeO), which is rare, and iron(II,III) oxide (Fe3O4), which also occurs naturally as the
mineral magnetite. In addition to iron oxide, the mineral magnetite may also exist in large
quantities in Sedona. Concentrations of iron oxide and other metal/minerals have the effect of
focusing the earth's natural geomagnetism which is produced by the Earth's molten outer core.
As the outer core churns a magnetic north and south pole are created. During this process another
form of magnetism is produced. It is non-dipole in nature. This magnetism has no north or south.
It is just pure magnetic energy. Most of this free energy is absorbed by the primary dipole,
(north/south) field but a portion of it may reach and penetrate the surface of our planet.
Within the earth non-dipole magnetism assumes the form of a "vortex like" (spiral or circular)
shape, that exhibits up and downward motion. Metals and minerals have the tendency to align
with the earth's natural magnetism. This fact is the basis for many forms of metal/mineral
detection systems. The crystalline like structure of the metal/mineral allows the earth's magnetic
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
638
field to be focused (concentrated) through the metal/mineral deposit. A proton precession
magnetometer can be used to detect magnetic fields concentrated in this manner and is standard
for metal/mineral exploration applications.
Magnetic activity can be correlated with "vortex energy" but that does not necessarily mean it is
the only factor at work. Lonetree has recorded many intense magnetic in and outflows of energy
in Sedona and believes this energy is sensed by the magnetite in our inner ear fluid. The process
of hearing relies on mechanical vibration (the ear drum). As a receptor, the magnetite produces
the electrical impulses that ultimately stimulate the temporal lobes of the brain. Dr. Michael
Persinger's work on temporal lobe stimulation using rotating magnetic fields suggests resultant
psychophysical phenomena that correlate closely with anecdotal reports from visitors to vortex
sites.
The brain activity associated with consciousness responds to the subtle changes in geomagnetic
activity. These changes include alterations in the occurrence of dreams, enhanced electrical
sensitivity of groups of brain cells (and the more extreme form, electrical seizures), and the
ability to focus during the day. Because all human beings are immersed within the geomagnetic
field we are intrinsically connected to it and to the secondary fields that arise from this
connection. Very small changes in the activity of the earth's magnetic field due to alterations in
solar activity can affect all human beings. These direct effects are primarily upon the subtle but
complex electromagnetic fields that interact with everyone's consciousness due to the marked
similarity of the characteristics of our brains and our genetic history. This creates the potential
for the function of every person's brain activity to be changed without their awareness.
(Persinger)
On the molecular biological level the only significant forces are electromagnetic. Ultimately all
living processes must be understood in terms of electromagnetic fields and forces. Every cell in
the body is a transmitter and receiver of electromagnetic information. Various cells and tissues
are conductors (allow for electron flow), insulators (inhibit), semiconductors (electron flow in
only one direction), capacitors (accumulate and store charge, later to release) and so on.
Cells transmit and receive energy, and each has its own frequency with which it oscillates. Both
electrical and magnetic fields applied to the body create biological changes. We now know that
in humans, the sinuses, some other bones in the face and various tissues in the body contain
magnetite. Not only is every cell in the body a transmitter and receiver of electromagnetic
information, various electromagnetic frequencies precede and correspond to biochemical
functions. For example, healthy cells oscillate at higher frequencies that do unhealthy cells, such
as cancer cells.
Superparamagnetics
Magnetite is a widespread accessory mineral in rocks and soils. Biogenic magnetite is produced
through the reduction of ferric iron within cells. However, the exact process of magnetite
synthesis is unknown. Biogenic magnetite was first discovered in humans in 1992. The function
of the ferromagnetic material in humans is largely unknown, but the presence of magnetite in
human brain tissue provides plausible theoretical mechanisms for the interaction of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
639
environmental magnetic fields with the human central nervous system. Ferromagnetic crystals
interact more than a million times more strongly with external magnetic fields than do
diamagnetic or paramagnetic materials (deoxyhemoglobin, ferritin, and hemosiderin).
Lowenstam (1962) showed magnetite frequently forms by biochemical processes, with varying
degrees of control of the organisms over the mineralization process. He distinguishes between
biologically induced (BIM) and biologically controlled mineralization (BCM). The former refers
to processes with no biological control, and the later to processes with strict metabolic and
genetic control. Ferromagnetic material has been detected in the tissues of a variety of animals
that are known or suspected to respond to magnetic fields. However, only a few cases have
identified material suitable for use in magnetoreception.
Winklhofer (2005) describes two magnetoreception theories:
1). Chemoreception: the "radical-pair hypothesis” invokes magnetically sensitive biochemical
reactions involving spin-correlated radical pairs such as produced by photoexcitation in the
retina. The magnetic field interacting with the radical pair controls the reaction yields and
transduces into a chemical stimulus.
2). Mechanoreception: the ”magnetite hypothesis" assumes that the external magnetic field
interacts with inclusions of magnetite (Fe3O4) in tissue, which convert the received magnetic
energy into a mechanic stimulus (strain) to be detected by adjacent mechanoreceptors, which
eventually generate a nervous signal (receptor potential).
The two hypotheses are equally plausible at this stage of experimental evidence. Relying on
completely different physical principles, the two hypotheses do not mutually exclude each other.
On the contrary, there is good experimental evidence that both types of magnetoreceptor
principles may be realized, even in one the same organism, although the primary magnetic
information provided by each mechanism appears to be used differently.
Biomineralization
The recent discovery that human tissues also contain trace amounts of magnetite has profound
biomedical implications. Magnetite can possibly be absorbed in water and transformed into
bodies as the insoluble crystalline chain. Magnetite is the first truly novel material to be
discovered as a biochemical precipitate in human tissues since the dawn of medical science.
Everything else in human bones and soft tissue is either diamagnetic or paramagnetic (e.g.,
Lowenstam & Weiner, 1989).
Magnetite is the only known metallic compound made by living organisms and has the highest
electrical conductivity of any cellular material. Although the total amount of magnetite in an
adult human is small (a few hundred micrograms), there are several million crystals per gram,
each of which interact rather strongly with external magnetic fields (Kirschvink). Analysis
suggests molecular magnets, individual crystals of magnetite could contribute enough
mechanical energy to activate trans-membrane ion channels.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
640
Bioelectronics
We are electronic organisms, fundamentally electromagnetic, rather than chemical beings (Miller
& Miller, 2003c). Beal has linked biogenic magnetite to Electromagnetic Hypersensitivity
(EHS). People with EHS experience a variety of symptoms including headache, fatigue, nausea,
burning and itchy skin, and muscles aches. These symptoms are subjective and vary between
individuals.
Heavy metal toxicity increases the chance of EHS. Life cannot exist without evolution of the
environmental energy detection, storage and transmission capabilities of the living cell, which
contains a variety of biological liquid crystal (LC) forms. The lipid molecules of all biological
membranes exist in various LC states, providing a matrix for information storage and
environmental sensing. LCs may provide fundamental support and detection mechanisms for
electric and magnetic fields. This includes sound and light, and may explain quantum-level
sensitivity in some cases.
McCartney and Dunin-Borkowski,
“Magnetic and Structural Characterization of Biogenic Magnetite”
Microscopic Magnets
Kirschvink suggests Liquid Crystal (LC) properties in living systems may provide the basic
support for several of the background mechanisms proposed to explain the biosystem effects of
natural and artificial EMFs. In this case the LCs in their various biosystem forms may react to
amplify unusual internal or external energy inputs, transmitting their sensing reactions to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
641
stimulate other systems, e.g., immune system response, melatonin production, various
symptoms.
Magnetite is a common industrial pollutant and can often find its way onto the external body
surface or into the gut of higher animals (Kirschvink, 1983). Biogenic magnetite has a potentially
toxic downside both within the human system and in its interaction with artificial
electromagnetic fields. It has been suggested that biogenic magnetite, which has been detected in
the brain and may be related to neurodegenerative diseases such as Alzheimer's and Parkinson's
diseases, could initially form in ferritin. Of even wider interest, nanoscale biogenic magnetitebased ferromagnetic transduction may also be a transduction mechanism for mobile phone
bioeffects including increased cell mortality (Cranfield). These models are based on the coupling
of radiofrequency and pulsed electromagnetic emissions to biogenic magnetite (Fe3O4) present
in the human brain via either ferromagnetic resonance or mechanical activation of cellular ion
channels (Kirschvink).
Molecular Magnets
Because ferritin is present in the brain, the ferrihydrite core could be a precursor for biogenic
magnetite formation--particularly in cases where the normal functioning of the ferritin protein is
disrupted. It has recently been proposed that some of the excess iron in neurodegenerative tissue
may be in the form of the magnetic iron oxide magnetite (Fe3O4). (SQUID) magnetometry has
shown concentrations of magnetite are found to be significantly higher in three samples of
Alzheimer's disease tissue than in controls (Hautot).
Biogenic magnetite is found primarily in the brain and highly enervated ethmoid sinus area in
humans. It is also found in specific brain areas of insects, fish, birds and mammals, and more
concentrated in the brains of migratory creatures, which rely on cues from geomagnetic
variations and patterns. This biomagnetite is most likely concentrated in a differentiated cell type
(a magnetocyte), which might contain thousands of magnetosomes (individual crystals of singledomain molecular size). In the almost quantum-energy detection level of biological sensors to
EMFs, the LCs in these areas may play an important part in detecting and amplifying the effects
of EMFs on the magnetosomes -- perhaps providing fixed storage of environmental geoelectromagnetic patterns for migration/navagation purposes.
Dr. Kirschvink states: The discovery of biogenic magnetite (Fe3O4) in a variety of human tissues
suggests that it may be responsible for some of the reported effects of weak, ELF magnetic fields.
A previous analysis suggests that individual crystals of magnetite of single domain size could
contribute enough mechanical energy to activate trans-membrane ion channels. Detailed
analysis of the magnetic property data from human tissues (normal and pathological) indicates
the presence of substantial magnetic intergrain interaction effects. This implies that biological
averaging of ELF EMF effects at the cell membrane is a possibility.
Since biogenic magnetite seems to be ubiquitous in the environment, it may have played a basic
role in the initial development of living systems and various sensing mechanisms. There is much
evidence that biological forms follow the energy patterns laid down by the waveforms of the
environment. Electromagnetic vibration can rearrange molecules and macro-molecules into
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
642
patterned forms (sound, RF, microwave, heat, light, etc.) Lissajou or Chladni figures produced in
liquid and solids appear as structural biological patterns in simple organisms.
Fig. 4 Magnetic Disturbance Strip Charts, Sedona, 2010 – Source: Lonetree data readings
Materials & Methods
Instrumentation consists of 1) a Schumann Resonance Antenna, 2) EEG Brainwave interface,
and 3) Fluxgate magnetometer.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
643
1) Schumann Antenna
Lonetree's method for monitoring Schumann Resonance is a primary citation by NASA in the
2003 report, "Investigations of Relatively Easy to Construct Antennas with Efficiency in
Receiving Schumann Resonances." Possible applications of these antennas are global weather
prediction, earthquake prediction, planetary exploration, communication, wireless transmission
of power, or even a “free” energy source.
The rhythm of life has evolved at an even tempo for epochs. We live in a complex matrix of
oscillating fields; the tiniest fluctuations in one interlocked field carry over perturbations into
others. Many times per second, pulses travel completely around the world between our planet's
surface and the ionosphere sending coordinating signals to all organisms. These signals couple
us to the global electrostatic field. Named for their discoverer, the Schumann Resonance (SR)
provides an orchestrating pulse for life on our planet. We all march to the cadence of this cosmic
drummer -- our planetary heartbeat, which sets the tempo for health and well-being.
The ranges of SR frequencies are related mathematically, but are not true harmonics. Perhaps it
is closer to think of SR as the “Voice of the Planet,” rather than its heartbeat, which is around the
10Hz. Cycle (Lonetree). There is a harmonic relationship between the earth and our bioelectronic
mind/bodies. Earth's low frequency isoelectric field, the magnetic field of the earth, and the
electrostatic field that emerges from our bodies are closely interwoven. Our internal rhythms
interact with external rhythms, affecting our balance, REM patterns, health, and mental focus.
SR waves probably help regulate our bodies' internal clocks, affecting sleep/dream patterns,
arousal patterns, and hormonal secretion. The rhythms and pulsations of the human brain mirror
those of the resonant properties of the terrestrial cavity, which functions as a waveguide. This
natural frequency pulsation is not a fixed number, but an average of global readings, much like
EEG is an average of brainwave readings. SR actually fluctuates, like brainwaves, due to
geographical location, lightning, solar flares, atmospheric ionization and daily cycles. Contrary
to the New Age meme, SR is definitely not rising, according to Lonetree's continuous
monitoring.
Schumann resonances (SR) are the Earth’s natural vibrations (Fig. 3). Generated by lightning,
they form within the cavity between the Earth and the ionosphere. These resonances are quasistanding electromagnetic waves that propagate approximately at 7.8 cycles per second (7.8 Hz).
These waves have modes that resonate at approximately 14, 21, 26, 33, 39, and 45 Hz, with a
daily variation of about ±0.5 Hz. Even though the global Earth-ionosphere system behaves as a
spherical-shell-cavity resonator (waveguide), the 7.8-Hz frequency can easily be approximated
by using the Earth’s circumference.
The circumference of the Earth is about 25,000 miles (40 000 km), and the speed of light is about
3 × 108 m/s. It would therefore take light approximately 0.133 second to travel the Earth, which
roughly yields 7.5 Hz. This frequency is not 7.8 Hz, even though the circumference of the Earth
and the speed of light are constants. This resonance changes because of changes in the Earth’s
electrical and magnetic activity in the atmosphere and also because of changes in the height of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
644
the ionosphere; 7.8 Hz is the average peak frequency over a long period of time. It correlates
with human alpha - theta brainwave frequency.
2) EEG: Neurosky Brainwave Interface
The NeuroSky MindSet headset is a brainwave interface with medical-grade data acquisition for
research or consumer use. It measures electrical impulses generated by mental activity, and uses
proprietary algorithms to calculate the observed types of brain behavior. For consumer games
and education, The MindSet makes calculated brainwave levels and interpreted mental states
(currently 'attention' and 'meditation') available as digital input for computers, phones, software,
and devices. In all cases, the data is fed to the computer via wireless Bluetooth and includes both
audio and voice support for MP3 and VoIP.
Traditional brainwave feedback and recording devices require gels and numerous sensor points
placed on the subject's head. MindSet uses only a single dry (no gel) sensor that rests
comfortably on the subject's forehead and connects to a PC for data collection. Variable headset
sizing ensures flexibility regardless of the subjects' head size. 5-second calibration reduces
downtime. All features make it a viable choice for field experiments.
In Alpha, we begin to access the wealth of creativity that lies just below our conscious awareness
- it is the gateway, the entry point that leads into deeper states of consciousness. Alpha waves aid
relaxation and overall mental coordination, calmness, alertness, inner awareness, mind/body
integration and learning. Theta waves mean 'slow" activity often connected with creativity,
intuition, daydreaming or recalling emotions and sensations. Focus is internal in this state
between waking and sleep. Theta meditation increases creativity, enhances learning, reduces
stress and awakens intuition and other extrasensory perception skills. Our experimental goal in
Sedona isn't to teach or augment meditation, but simply to monitor imposed changes on those
simply relaxing at the geomagnetic sites.
3) Fluxgate Magnetometer:
A fluxgate magnetometer consists of a small, magnetically susceptible, core wrapped by two
coils of wire. An alternating electrical current is passed through one coil, driving the core
through an alternating cycle of magnetic saturation; i.e., magnetized, unmagnetized, inversely
magnetized, unmagnetized, magnetized, etc. This constantly changing field induces an electrical
current in the second coil, and this output current is measured by a detector. In a magnetically
neutral background, the input and output currents will match. However, when the core is exposed
to a background field, it will be more easily saturated in alignment with that field and less easily
saturated in opposition to it. Hence the alternating magnetic field, and the induced output current,
will be out of step with the input current. The extent to which this is the case will depend on the
strength of the background magnetic field. Often, the current in the output coil is integrated,
yielding an output analog voltage, proportional to the magnetic field.
There are a wide variety of sensors currently available, used to measure magnetic fields.
Fluxgate magnetometers and gradiometers measure the direction and magnitude of magnetic
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
645
fields. Fluxgates are affordable, rugged and compact. This, plus their typically low power
consumption makes them ideal for a variety of sensing applications.
The typical fluxgate magnetometer consists of a "sense" (secondary) coil surrounding an inner
"drive" (primary) coil that is wound around permeable core material. Each sensor has magnetic
core elements that can be viewed as two carefully matched halves. An alternating current is
applied to the drive winding, which drives the core into plus and minus saturation. The
instantaneous drive current in each core half is driven in opposite polarity with respect to any
external magnetic field. In the absence of any external magnetic field, the flux in one core half
cancels that in the other and the total flux seen by the sense coil is zero. If an external magnetic
field is now applied, it will, at a given instance in time, aid the flux in one core half and oppose
flux in the other. This causes a net flux imbalance between the halves, so that they no longer
cancel one another. Current pulses are now induced in the sense winding on every drive current
phase reversal (or at the 2nd, and all even harmonics). This results in a signal that is dependent
on both the external field magnitude and polarity.
Results
STAGE 1: Research was centered on natural effects, how geomagnetism affects SR in a given
local geographical area. Lonetree noticed the anomaly that atmospherics were noticeably
stronger (louder) at certain locations along the trail. This was not always the case, though. He
began to wonder if the increase in the strength of the atmospherics had anything to do with the
infamous vortex energy. The VLF receiver attributed the increase in strength to amplification of
the atmospherics. This theory could not be correct though, for if it were, atmospheric strength
would be enhanced all the time when he recorded at this particular spot. Such was not the case.
STAGE 2: Surveys conducted by the USGS (United States Geological Survey) indicated there
were locations on this planet where there exist vortex-like acting inflows and outflows of nonpolarized magnetic energy. Non-polarized means no North or South pole as in a regular magnet.
The out- or inflow is simply pure magnetic energy in dynamic motion. In order to prove his
theory, Lonetree used a fluxgate sensor. This particular instrument is used for monitoring the
Earth’s magnetic field as well as any other source of magnetism.
STAGE 3: The first Schumann Resonance (SR) occurs at average frequency of 7.83 Hz. This
frequency also happens to fall between two of the human brainwaves, Alpha and Theta. There
are four altogether: Alpha, Beta, Delta, and Theta. When our brain is functioning restfully in the
predominantly alpha/theta zone, we become more relaxed or peaceful. The human brain acts like
an electrical circuit called a phase-lock loop. A local external (outside the body) electromagnetic
signal, as long as it is stronger than our brainwaves, initiates a resonance effect where the brain
locks onto and resonates at that frequency.
Lonetree conjectured that if the first Schumann Resonance (FSR) were in some way enhanced in
the area where a large geomagnetic outflow occurred, it should be possible for the FSR to affect
a person’s brainwave activity. Since that first signal again lies in alpha and theta range,
simultaneously observing and recording the first resonance along with local field geomagnetic
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
646
activity using the fluxgate instrument in vortex sites demonstrates this theory. What others have
long conjectured, Lonetree’s gear was able to graphically demonstrate synchrony, conclusively.
He also recorded what he believed to be influencing magnetic energy. He saw the first Schumann
Resonance increase in strength while the geomagnetic outflow of energy increased
simultaneously. SR and ELF EM fields do have a provable influence on living organisms. SR
changes over correlated circadian rhythms and other cycles of time. Physiological effects have
been observed in a human subject in response to stimulation of the skin with weak
electromagnetic fields that are pulsed with certain frequencies to excite a sensory resonance.
Pulsed electromagnetic fields are capable of exciting sensory resonances in nearby subjects.
"Schumann Resonances, a plausible biophysical mechanism for the human health effects of
solar/geomagnetic activity" describes the following:
"König, a student of Dr Schumann, took readings of the SR signal. He observed the close
similarity of the SR signal with the EEG alpha rhythm, both of which dominate the daytime, and
the local sferics 3 Hz signal with the EEG delta rhythm, that dominate the night, König (1974a).
The close similarity, including the diurnal pattern and extensive laboratory experiments,
prompted König to postulate that the ELF brain waves had evolved to use these natural signals,
König (1974a). König also found that a superimposed epoch analysis related to the arrival of
3Hz. signals from locally generated thunderstorms showed significantly slowed reaction times.
This was tested and confirmed in a series of laboratory experiments using human volunteers.
König found that with a range of field strengths, 1 to 5V/m, the "3Hz" signal consistently slowed
people's reactions and a "10Hz" signal consistently accelerated people's reaction times.
Reactions were also correlated with the more objective test for galvanic skin response (GSR),
using a 5 V/m 3Hz signal, König (1974b)." (Cherry)
STAGE 4: There are some indications that a correlation exists between atmospheric oscillations,
brain waves, and biological EM emissions. Understanding the nature of this correlation may
enable us to characterize and further utilize various types of "healing energies". Integral portions
of biological systems have been shown to be semiconducting, ferromagnetic and piezoelectric.
The biosemiconductor, together with the drift of charges, ions, and radicals, may be considered
as a form of "bioplasma". Bioplasma may be subject to magnetohydrodynamic (MHD) control
(Roffey).
The EM fields emitted by trained healers may be considered as coherent, resonant biomagnetic
emissions by which a less coherent EM field of the patient is "tuned" to the specific frequency
and phase, and through which homeostasis can be "aligned" to induce "healing" (Roffey). Vortex
energy may exert a so-called "healing" energy in much the same way, via subtle resonance
effects.
Both Persinger and Ryan separately conducted research that shows apparent associations
between extrasensory perception (ESP), geomagnetic activity (GMA) and local sidereal time
(LST; a time system based on the rotation of the Earth with respect to star positions). Persinger
also links certain ESP phenomena to tectonic strain. The analysis of geomagnetic pulsation
activity in relation to ESP success was initially conceived as a first step in a process of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
647
elimination in the search for an explanation for the reported associations between GMA and LST
with ESP. Rather than eliminating the possibility, this factor emerges as a leading candidate for a
solution to the problem.
Chart 1: EEG Display & Magnetometer Strip Chart
How to read the charts:
The multi-colored vertical bar graph on the right is the intensity of each individual brainwave
and their sub-frequencies. Our brainwaves cover a wide bandwidth and can occupy several
Hertz. The white horizontal line you see imposed over the vertical bar graph is raw brainwave
data. The brainwave monitoring equipment uses an algorithm to create the image you see on the
left. It is known as FFT (Fast Fourier Transform) and it permits us to see what brainwaves are
dominant at any given time. Beneath the bar graph are two meters. One labeled ‘Attention’ and
the other ‘Meditation’. They chart both level of attention and level of meditation at any given
time.
Magnetometer Strip Chart: At the bottom of the chart is a white colored chart with grids. This
chart is a product of a large magnetometer which is monitoring naturally occurring magnetic
energy emanating from the ground beneath a vortex. We look for magnetic activity as displayed
in the white chart, (Natural Earth Magnetic In or Outflow), and what comparison we may see in
"Raw Brainwave Data".
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
648
State of mind during the "in or outflow" of magnetic activity can be monitored by looking at the
"Attention/ Meditation" Indicators. We also see what brainwaves are dominant at that particular
time. Dominant Delta occurs during sleep. Theta and Alpha gain amplitude in relaxation and
meditation. Beta is a product of awake, alert and active. Above Beta into Gamma is wide awake
and very active. The baseline chart was recorded at the beginning of each outing and shows
brainwave activity while no natural magnetic activity is present. In the baseline chart, all is quiet.
When magnetic activity commences synchronization of magnetic and brainwave phenomena is
demonstrated.
Chart 2 correlations: Magnetic in and outflows have begun. Green tracing lines show what raw
brainwave event coincides with what earth generated magnetic event. At this point Lonetree
recorded both in and outflows of magnetic energy. It is not displayed in the chart but the
magnetic energy emits or returns into the earth in a spiral motion.
Chart 2
Outflow is indicated by a positive (upward) reading in the graph and inflow by a (downward)
reading in the graph. It is evident the "Naturally Occurring Magnetic Energy" in Sedona has a
distinct effect on "Human Brainwave Activity". More tests are needed with a number of
volunteers to replicate and verify these findings. The final chart reflects magnetic activity
subsiding and brainwave activity returning to normal.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
649
Chart 3 - Alert
Discussion
Individual volunteers were monitored and recorded for brainwave changes while on various
proven vortex sites, during sudden magnetic anomalies. A variety of effects consistent with the
general theory of this paper were noted. Baselines were established for each participant in each
discreet event.
Biomagnetic Minerals
The body contains many bioelectronic features. It contains crystalline structures, including
calcite and magnetite, which may produce piezo-electric effects under external fields. There is a
growing body of evidence that changes in the geomagnetic field affect biological systems
(Joselyn, 1992). Artificial EMF sources, such as signal characteristics of cell phone base stations
are complex, presenting the body with a combination of carrier waves in the microwave band.
The interference patterns between these carrier frequencies, and the signal structures themselves,
all occur within the context of the earth’s geomagnetic EMFs, including the Schumann resonance
with which our bodies appear to be closely and naturally tuned, and our own internal
bioelectromagnetic-frequencies.
Some studies indicate that physically stressed human biological systems may respond to the
minute but measurable fluctuations in the geomagnetic field. In 1982 Maugh reported the finding
of magnetite in mammals. The magnetic particles appeared to be surrounded by nervous tissue,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
650
suggesting the possibility of interaction between the particle and the brain. In 1983 Baker,
Mather, and Kennaugh of the University of Manchester discovered magnetite in the ethmoid
cavities of humans. It also appears in the hippocampus (Dunn, et al).
Despite our increased understanding of the functions and mechanisms of action of the pineal
gland in the past few decades, the precise mechanism at a cellular level whereby electromagnetic
radiation can produce biological effects was, until recently, unknown. However in the past
decade or so, studies of the ferrous mineral magnetite show that it can act as a transducer linking
ambient electromagnetic activity to cellular function. In addition – in both animals and humans –
magnetite has been identified in most tissues examined, including the pineal gland (Lohmann &
Johnsen, 2000; Schultheiss-Grassi & Dobson, 1999).
Induced electric currents (eddy currents) mechanism: During the past decade, a number of
reports indicated that the mammalian pineal gland is magnetosensitive in terms of spatial
orientation. This indication is based on observations that artificial alterations of the direction of
the earth’s magnetic field (MF) markedly decreased the gland’s capability to synthesize
melatonin. It was shown that magnetic field exposure itself did not affect the pineal. Rather,
induced eddy currents in the animals, resulting from rapid On/Off switching transients of the
artificially applied MF, affect the pineal gland either directly, or, more likely, indirectly, via an
action on the neural input. The eddy current mechanism is most likely the explanation.
Every rapid change of a MF produces an electric field. Depending on the tissue exposed to such
a field, an appropriate eddy current occurs, depending on the tissue’s conductivity. So, if an
organism is exposed to a rapidly changing MF, an induced eddy current occurs that may affect
the nervous system. This conclusion is supported by the observation that a nerve’s synaptic
transmission is affected by exposure to electric fields.
The above mechanism may interact with biogenic magnetite and other metal ions in biosensor
tissues and fluids, perhaps combining with other mechanisms mentioned herein, thus stimulating
various liquid crystal and cellular responses to the information perceived.
Non-Linear Mechanisms research indicates that low-intensity, nonlinear, extremely low
frequencies (ELF) and low intensity ELF pulse-modulated fields influence various physiological
and behavioral processes in cells, tissue, animals, and humans. Major shifts in calcium efflux
occur with fields that produce very small gradients in the extracellular space (interstitial fluids)
surrounding cell membranes.
The extracellular fields are far below transmembrane gradients associated with a typical synaptic
depolarization. This implies that cells can act as sensitive detectors of ELF signals. This
apparent capability has led to specific alteration of cell function, including hormone and insulin
decrease, accelerated wound healing and bone growth, interference with nerve conduction,
entrainment of cell transcription processes, and alteration of brain chemistry.
The effects range from alteration of the firing rates of neurons in the brain, calcium-ion binding
disruption on cell surfaces in the brain, to response time…[and] respiration rate changes, and
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
651
even putting an animal to sleep…[and] spectral components in the kHz range appear to cause
effects selectively in bone tissue.
The pineal gland … converts a neuronal signal into an endocrine output. … [It] is located close
to the anatomical centre of the human brain.” “A total of 20 glands from [human] subjects
ranging in age from 15 to 68 years were studied.” “Microcrystals were found in every gland in
quantities ranging from 100 to 300 crystals per cubic millimetre of gland. No attempt was made
to correlate the quantity of crystals with either the age of the subject or pathological details.”
“Length dimensions of the crystals varied from 2-3 to about 20 micrometres.” “These results
and the electron diffraction measurements definitely prove that the microcrystals are calcite.”
“These calcite crystals bear a striking resemblance to the otoconia of the inner ear.” “The
calcite in otoconia has been shown to exhibit piezoelectricity.” “If piezoelectricity were to exist
[in the pineal calcite microcrystals], an electromechanical coupling mechanism to external
electromagnetic fields may be possible. (Baconnier)
Research implies that the production of the biomineral is under precise biological control. The
crystal morphology is cubo-octahedral with the faces of adjacent crystals lying perpendicular to
the chain axis. The magnetic moments of the particles are aligned along the chain axis and sum
to produce a total moment dependent on the number of particles present in each chain. In the
presence of the geomagnetic field, the mean moment for the particles will give a magnetic to
thermal energy ratio of about 0.2.
Regeneration Instructions?
Biomineralization is chemically controlled. We’ve learned much about how human organisms
work on all levels but the remaining question is: What electromagnetic signal might tune to a
magnetic resonant energy which would alter the metabolic genetic regulation to bring about
growth and repair? We continue to investigate what cuboctahedral magnetite crystals are
doing in the human brain.
Magnetite is a mineral, a magnetic iron ore belonging to the spinelle family. Research done in
the late 1980s shows proteins, DNA, and transforming DNA function as piezoelectric crystal
lattice structures in nature (Ho). The piezoelectric effect refers to that property of matter which
may convert electromagnetic oscillations to mechanical vibrations and vice versa. These
magnetite crystals were organized into linear, membrane-bound chains a few micrometers in
length, with up to 80 crystals per chain. Furthermore individual crystals are aligned along the
length of the chain axes (the "easy" direction of magnetization).
Equilibrium Morphology
The crystal alignment has been interpreted as a biological mechanism for maximizing
the magnetic moment per particle, as the direction yields approximately 3% higher saturation
magnetization than do other directions. This prismatic particle shape is also uncommon in
geological magnetite crystals of this size, which are usually octahedra.
The crystal morphology was found to be cubo-octahedral with the faces of adjacent crystals lying
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
652
perpendicular to the chain axis (Coetzee). A change in conductance of a membrane ion channel
in a neuron or a neuroepithelial cell was the earliest process that occurred in all forms of sensory
transduction. Evidence from an appropriate model excitable cell or tissue that EMFs affect
membrane currents or membrane potential supports the hypothesis that EMF transduction is a
species of sensory transduction. (Sonnier)
Ferromagnetic crystals are manufactured by some cells, particularly astroglial cells, the
predominant cell type in the brain. These are magnetic crystals (Fe3O4), aligned in chains of up
to 80 crystals per chain, maximizing the magnetic moment of each crystal particle. These are
membrane-bound biomineral magnetite crystals that are produced within each cell as needed,
Unlike naturally occurring octahedral-shaped magnetite crystals, our astroglial cells generate a
cubo-octahedral structure that is better suited to respond to magnetic fields. Each of these
compass-like magnetite crystals have been shown to have a mechanical coupling to a
mechanoreceptor in the cellular membrane.
Thus, they act as a sensor to magnetic fields and signal the inner "machinery" of the cell. This
offers an insight into why our brains can operate many times faster than the process of synaptic
firing and the movement of electrical potential (called action potential) from one neuron to
another. These linear magnetic crystal domains are more than a million times more responsive to
external magnetic fields than surrounding cellular non-magnetic structures. Some theorize that
these magnetic particles interact with magnetic and electromagnetic fields and transduce their
response into their host cell. Thus, they provide a means of responding to, and sensing our
environment (Kirschvink, 1992).
Conclusion
We have demonstrated there is close correlation between Sedona vortex magnetic anomalies
(sudden magnetic events) and spontaneous brainwave changes in frequency and amplitude, that
is further modulated by Schumann Resonance and plausibly accounts for reported
psychophysical and psychosensory phenomena. Geomagnetic brainwave synchronization can
occur spontaneously at vortex points during sudden magnetic events.
References
Baconnier S, Lang SB, Polomska M, Hilczer B, Berkovic G, Meshulam G (2002), ‘Calcite microcrystals
in the pineal gland of the human brain: First physical and chemical studies’, Bioelectromagnetics,
23(7):488-495.
Becker, R.O. (1985), and Selden, G. The Body Electric: Electromagnetism and the Foundation of Life.
New York, NY: Quill, William Morrow, 1985; William Morrow Paperbacks (1998).
Becker R O (1990), Cross Currents: The perils of electropollution, the promise of electromedicine,
Tarcher/Penguin.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
653
Bäeuerlein, Edmund, (2009), Handbook of Biomineralization: Biomimetic and Bioinspired Chemisty,
Wiley-VCH (September 28, 2009).
Beal, James, (2008) "EHS and Iron Overload: A Biogenic Magnetite Mechanism?" "Organism
sensitivities to electric and magnetic field: biosystem liquid crystals & proposed interacting mechanisms"
http://omega.twoday.net/stories/5362082/
Beal, James, "Biosystem Liquid Crystals and Potential Effects of Natural & Artificial Electromagnetic
Fields (EMFs)", Presented October 5, 1996 at the Second Annual Advanced Water Sciences Symposium,
Exploratory Session 1, Dallas, Texas. http://frontpage.simnet.is/vgv/jim1.htm
Cherry, Neil, 2001, "Schumann Resonances, a plausible biophysical mechanism for the human health
effects of Solar/Geomagnetic Activity", http://www.salzburg.gv.at/cherry_schumann_resonances.pdf
Coetzee, H., "Biomagnetism and Bio-Electromagnetism: The Foundation of Life", Future History,
Volume 8, http://www.affs.org/html/biomagnetism.html
Cranfield, Charles , HG Wieser, Jaffar Al Maddan and Jon Dobson (2002), "Preliminary Evaluation of
Nanoscale Biogenic Magnetite-Based Ferromagnetic Transduction Mechanisms for Mobile Phone
Bioeffects", IEEE Transaction on NanoBioscience,
http://www.mobile-research.ethz.ch/var/pub_cranfield_pref1.pdf
Dunn, J.R., Fuller, M., Zoeger, J., Dobson, J., Heller, F., Hammann, J., Caine, E., Moskowitz, B.M.
(1995) Magnetic material in the human hippocampus. Brain Res Bull 36, 2, 149-153.
Edmonds, D.T., Electricity and Magnetism in Biological Systems, Oxford Univ. Press, 2003.
Farmer & Hannan (2003), "Investigations of Relatively Easy to Construct Antennas with Efficiency in
Receiving Schumann Resonances", NASA.
Hautot, D. and Pankhurst, Q.A. and Khan, N. and Dobson, J. (2003) Preliminary evaluation of nanoscale
biogenic magnetite in Alzheimer's disease brain tissue. Proceedings of The Royal Society B Biological
Sciences , 270.
Ho, Mae-Wan, The Rainbow and the Worm: The Physics of Organisms, World Scientific Publishing
Company; 3 edition (August 6, 2008)
Ho, Mae-Wan, Fritz Albert Popp, Ulrich Warnke, Bioelectrodynamics and Biocommunication, pg. 116.
Chapter 4, D.T. Edmonds, "Possible Mechanisms for Biological Effects of Weak ELF Electromagnetic
Fields".
Ingber, Donald E., "The Architecture of Life" Scientific American, Jan. 1998.
http://www.childrenshospital.org/research/ingber/PDF/1998/SciAmer-Ingber.pdf Joselyn J.A., 1992, The
impact of solar flares and magnetic storms on humans EOS, 73(7): 81, 84-85.
Joselyn, J.A., 1992, The impact of solar flares and magnetic storms on humans. EOS, 73(7): 81, 84-85.
King, Chris, "Cutting through the Enigma of Consciousness", JCER VI (9).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
654
Kirschvink, J.L. et al. "Magnetite biomineralization in the human brain." Proceedings of the National
Academy of Sciences, 89 (1992):7683-7687.
Kirschvink, J.L., Biogenic Magnetite and EMF Effects, American Physical Society, Annual March
Meeting, March 17-22, 1996, abstract #M20.02.
Kirschvink, J. "Can Weak ELF Magnetic Fields Produce Significant Effects on Biogenic Magnetite?"
Project Abstracts, pg. 79, The Annual DOE/EPRI Review On Bioeffects of Electric & Magnetic Fields.
Palm Springs CA, Nov 1995.
Joseph L. Kirschvink, Atsuko Kobayashi-Kirschvink, Juan C. Diaz-Ricci, and Steven J. Kirschvink,
"Magnetite in Human Tissues: A Mechanism for the Biological Effects of Weak ELF Magnetic Fields",
http://web.gps.caltech.edu/~jkirschvink/pdfs/KirschvinkBEMS92.pdf
Kopke RD, Wassel RA, Mondalek F, Grady B, Chen K, Liu J, Gibson D, Dormer KJ., Magnetic
nanoparticles: inner ear targeted molecule delivery and middle ear implant.
http://www.ncbi.nlm.nih.gov/pubmed/16439835
Lohmann KJ, Johnsen S., The neurobiology of magnetoreception in vertebrate animals , Trends Neurosci.
2000 Apr; 23(4):153-9.
Lohmann, K.J., Cain, S.D., Dodge, S.A., Lohmann, C.M. (2001) Regional magnetic fields as navigational
markers for sea turtles. Science 12, 364-366.
Lonetree, Benjamin: Seven Subtle Vibrations: A Scientific Study of Schumann Resonance,
Geomagnetics, and Vortex Energy in Sedona. July 2002.
Lonetree cited in "Investigations of Relatively Easy to Construct Antennas with Efficiency in Receiving
Schumann Resonances." Brian W. Farmer and Robert C. Hannan, NASA/TM-2003-212647.
http://sedonanomalies.com/NASA-2003-tm212647.pdf
Lonetree, Ben and Miller, Iona, "Siren Song of the Earth: Investigating Vortex Theory & EM
Signals", Nexus Magazine, Vol. 12, No. 2 Feb/Mar ’05, Int’l; Mar/Apr ‘05 North America.
Lowenstam H.A., Weiner S (1989) On Biomineralization. Oxford University Press, New York.
Mata, Néstor Hugo, "What is the level of radio-frequency waves that affect human health?", National
Technical University, Electrical Engineering Department, Argentina.
McCartney, M.R. and R. E. Dunin-Borkowski, "Magnetic and Structural Characterization of Biogenic
Magnetite”. http://www.rafaldb.com/papers/C-2002-08-Quebec-MandM-biogenic-magnetite.pdf
Miller, Barry William (2004), "Synthesis and Characterization of Functionalized Magnetite
Nanocomposite Particles for Targeting and Retrieval Applications”.
http://etd.fcla.edu/UF/UFE0004820/miller_b.pdf
Miller, Iona, and Miller, Richard, "Schumann Resonance and Human Physiology", Nexus Magazine, Vol.
10, #3, April-May, 2003a.
Miller, Iona, and Miller, Richard, "HAARP's Threat to the Voice of the Planet," Nexus Magazine in MarISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
655
Apr, 2003b.
Miller, Iona and Miller, Richard, "From Helix to Hologram," August-September, 2003c, Nexus
Magazine. http://ionamiller2010.iwarp.com/whats_new_8.html
Milsom, John, Field geophysics, Volume 12, Issue 180, Wiley.
Onyedim G.C., Computer modelling of geomagnetic anomalies associated with block-faulting, Phys.
Earth Planet. Inter., 53: 30004.
Pazur, Alexander, Characterisation of weak magnetic field effects in an aqueous glutamic acid solution by
nonlinear dielectric spectroscopy and voltammetry, BioMagnetic Research and Technology 2004, 2:8,
http://www.biomagres.com/content/2/1/8
Persinger, Michael A. (1987). Neuropsychological Bases of God Beliefs. New York: Praeger.
Persinger, Michael (1989). “Psi Phenomena and Temporal Lobe Activity: The Geomagnetic Factor” in
L.A. Henkel and R. E. Berger (eds.), Research in Parapsychology 1988; Metuchen, NJ: Scarecrow Press,
1989.
Persinger, M. A. , (1983). "Geophysical variables and human behavior: VII. Specific prediction of UFO
reports within the New Madrid states by solar-geomagnetic and seismic measures." Perceptual and Motor
Skills, 56, 243-249.
Persinger, M. A. , (1993). "Geophysical variables and human behavior: LXXI. Differential contribution of
geomagnetic activity to paranormal experiences concerning death and crises: An alternative to the ESP
hypothesis". Perceptual and Motor Skills, 76, 555-562.
Persinger, M. A., & Derr, J. S. (1984). "Geophysical variables and human behavior: XIX. Strong
temporal relationships between inclusive seismic measures and UFO reports within Washington state".
Perceptual and Motor Skills, 59, 551-566.
Persinger, M. A., & Levesque, B. F. (1983). "Geophysical variables and human behavior: XII. The
weather matrix accommodates large portions of variance of measured daily mood". Perceptual and Motor
Skills, 57, 868-870.
Persinger, Michael A. (1989), "Psi Phenomena and Temporal Lobe Activity: The Geomagnetic Factor,"
in I.A. Henkel and R. E. Berger (eds.) Research in Parapsychology 1988, Metuchen, NJ: Scarcrow Press.
Persinger M.A., & Krippner S. (1989). "Dream ESP experiments and geomagnetic activity". Journal of
the American Society of Psychical Research, 83, 101- 106.
Persinger, M. A. and Makarec, K. (1987). “Temporal Lobe Epilepsy Signs and Correlative Behaviors
Displayed by Normal Populations,” Journal of General Psychology, 114, 1987, pp. 179-185.
Persinger, M. A. (1975). “ELF Waves and ESP”; New Horizons, I(5), January 1975, pp.232-235.
Persinger, M. A. , (1983). "Religious and mystical experiences as artifacts of temporal lobe
function". Perceptual and Motor Skills, 57, 1255-1262.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 630-656
Miller, I. & Lonetree, B., The Sedona Effect: Correlations between Geomagnetic Anomalies, EEG Brainwaves &
Schumann Resonance
656
Persinger, M. A. , (1985). "Geophysical variables and human behavior: XXX. Intense paranormal
experiences occur during days of quiet, global geomagnetic activity". Perceptual and Motor Skills, 61,
320-322.
Persinger, M. A., & Valliant, P. M. (1985). "Temporal lobe signs and reports of subjective paranormal
experiences in a normal population: A replication", Perceptual and Motor Skills, 60, 903-909.
Roffey, Leanne (1994), "The bioelectronic basis for "healing energies"; charge and field effects as a basis
for complementary medical techniques", in M.J. Allen, S. F. Cleary & A.E. Sowers (eds.) Charge and
Field Effects in Biosystems -- 4, pp. 480-497. Singapore: World Scientific.
Rukhovets, N.M., Geological Interpretation of the Gravitational and Magnetic Fields of the Baltic Sea
Region, Defense Technical Information Center, 1967.
Ryan, Adrian, "New Insights into the Links between ESP and Geomagnetic Activity", Journal of
Scientific Exploration, Fall 2008.
Schultheiss-Grassi, PP and J Dobson (1999) Magnetic analysis of human brain tissue. BioMetals 12: 6772.
Simon, Baconnier, Lang Sidney B., De Seze Rene, "New Crystal in the Pineal Gland: Characterization
and Potential Role in Electromechano-Transduction", http://fedgeno.com/documents/crystal-in-thepineal-gland.pdf
Sonnier, Harold and Marino, Andrew, "Sensory Transduction as a Proposed Model for Biological
Detection of Electromagnetic Fields”, http://www.scribd.com/doc/14050025/Model-for-biologicaldetection-of-EMF
USGS Magnetic Anomaly Survey. Complete Report:
http://sedonanomalies.com/usgs_magnetic_anomaly_survey.htm
Weiss, B.P., Kim,S., Kirschvink, J.L., Kopp, R.E., Sankaran M., Kobayashi, A., & Komeili, A.
"Ferromagnetic resonance and low temperature magnetic tests for biogenic magnetite", Earth &
Planetary Science Letters224, 73-89.
Winklhofer, M., "Biogenic Magnetite and Magnetic Sensitivity in Organisms", The 15th Riga and 6th
PAMIR Conference on Fundamental and Applied MHD, Invited Lectures, 2005.
http://ipul.lv/pamir/cd/vol.I/riga-pamir-vol.I-33.pdf
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
65
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
Article
The Nature of Quantum Reality: What the Phenomena at the Heart
of Quantum Theory Reveal About the Nature of Reality (Part III)
Steven E. Kaufman*
ABSTRACT
What quantum theory has revealed about the nature of reality has remained hidden in plain sight
for almost one-hundred years because what quantum theory has revealed about the nature of
reality cannot be comprehended in the context of the materialist model and conception of reality
in which science presently operates, which materialist model places physical reality at the center
of reality and Consciousness at the periphery, as a secondary or derivative reality. What this
work will demonstrate, by explaining the heretofore inexplicable basis of the phenomena that lie
at the heart of quantum theory, is that it is Consciousness rather than physical reality that lies at
the center of reality, and that it is physical reality rather than Consciousness that is a secondary
or derivative reality. Specifically, wave-particle duality, quantum uncertainty, quantum nonlocality, the probabilistic nature of the wavefunction, and the collapse of the wavefunction, will
all be shown to be phenomena that have as their basis the way in which the fundamental Reality
of Consciousness, through relation to Itself, creates what it apprehends as physical reality.
One of the most important things the phenomena that lie at the heart of quantum theory will be
shown to reveal about the nature of reality is that the nature of physical reality is like that of a
reflection, and like a reflection, physical reality is able to obscure from view what is actually
there, as long as it is mistaken for what is actually there. Thus, in revealing the reflection-like
nature of physical reality, the phenomena that lie at the heart of quantum theory indirectly reveal
that what is actually there, underlying the reflection that is physical reality, is the non-physical,
non-experiential Reality of Consciousness that is, through relation to Itself, both creating and
apprehending experiential reality in general and physical reality in particular. Ultimately,
understanding the reflection-like nature of physical reality should make it possible for
Individuals to understand that what actually Exists directly where they are, where their physical
bodies appear to be, is not different in Nature than what actually Exists everywhere else as well,
where the rest of physical reality appears to be, thereby disabusing them of the notion that what
they are is a physical reality, while at the same time revealing to them their true Nature as
Consciousness, which, through relation to that which is also Consciousness, creates what they, as
Individual points of Consciousness, apprehend as experiential reality in general and physical
reality in particular.
Part III of this series of three articles includes: 3. The nature of the wavefunction; 4. There is no
spoon; and 5. The connection between quantum physics and eastern philosophy.
Key Words: Nature, quantum reality, quantum physics, Consciousness, materialist model.
*Correspondence: Steven E. Kaufman, Indep. Researcher. http://www.unifiedreality.com E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
66
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
3. The nature of the wavefunction
When answering the question regarding the nature of quantum reality, it is necessary to be clear
what is being referred to as quantum reality, just as when answering the question regarding the
nature of reality, it is necessary to be clear what is being referred to as reality. That is, just as
there is Reality and reality, there is quantum Reality and quantum reality. Put another way, there
is the Reality that is actually there that is the basis of what is apprehended as quantum reality,
and there is what is apprehended as quantum reality.
The Realities that are actually there that are the basis of what are apprehended as quantum
realities are second level Relational Structures composed of Existence that has become
configured and structured in relation to Itself. Those second level Relational Structures extend
from the first level of Relational Structure that underlies what we apprehend as the physical
experience of space, and which first level of Relational Structure is also composed of Existence
that has become configured and structured in relation to Itself. The second level Relational
Structures that are the basis of what are apprehended as quantum realities, although they too are
composed of Existence that is configured and structured in relation to Itself, are different from
the first level of Relational Structure, in that they are formed through a different sort of relation
of Existence to Itself, and so are a different sort of Relational Structure, which different sort of
relation and Relational Structuring is only made possible by the Existence of the first level of
Relational Structuring. Most of what are referred to as physical laws derive from constraints
imposed by the first level of Relational Structuring, from which and within which the second and
third levels of Relational Structuring extend and within the Structural confines of which those
second and third level Relational Structures must then operate.
As we dig deeper into material reality, e.g., from the molecular to the atomic to the subatomic,
what we are actually doing is digging deeper into Reality, and in digging deeper and deeper into
Reality what we are actually doing is digging into lesser and lesser degrees of iteration of
Existential self-relation, because Existence being progressively in relation to Itself is What Is
Actually There underlying the etching that is physical experience-reality. Put another way, as we
dig deeper into material reality we are actually digging deeper into Reality, and as we dig deeper
into Reality what we are actually doing is progressively untwisting the rubber band of Existence
that has, through iterative relation to Itself, become progressively twisted upon Itself. That is,
Existence first forms relations with Itself in a way that creates the Relational Structure that
underlies what we apprehend as space. The Relational Structure that underlies what we
apprehend as space then forms relations with Itself to create the Relational Structures that
underlie what we apprehend as subatomic or quantum realties. The Relational Structures that
underlie what we apprehend as subatomic or quantum realties then form relations with each other
to create the higher order Relational Structures that we apprehend as atoms, and the Relational
Structures that we apprehend as atoms then form relations with each other to create the higher
order Relational Structures that we apprehend as molecules or crystals, and so on and so forth,
until here we are, Organic Processes that are Ourselves forming relations with this Universe
composed of Existence that has, through iterative relation to Itself, become configured into a
progressive Relational Structure, and as a result of those relations apprehending this Universe of
progressive Relational Structure as physical reality. Thus, as we dig from the macroscopic level
into the subatomic level, what we encounter are less iterated Relational Structures, i.e.,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
67
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
Relational Structures composed of fewer relations of Existence to Itself. So it is that, as we dig
deeper into reality and so into Reality what we are doing is unraveling the relations between
lower order Relational Structures that compose a particular higher order Relational Structure,
and in so doing providing experiential access to those lower order Relational Structures, by
making it then possible to form an impactive relation with those lower order Relational
Structures and create a physical experience as a result.
And the excavation of Reality and reality was going along swimmingly and seemingly without a
hitch until scientists reached the point in their excavation of reality where the instrumentation
needed to create physical experience through impactive relations with the unraveled and now
exposed Relational Structures at the quantum level of Reality had to be so sensitive that the
experiential limitation, which had always been there, could no longer be ignored, thereby
introducing uncertainty, which then led to the development of the wavefunction as the most
accurate expression of what was found to exist at the quantum level of reality, the development
of which has left scientists, for nearly the past one-hundred years, scratching their heads
wondering what it is that the wavefunction actually represents and so what the findings of and
phenomena associated with quantum theory actually have to say about the nature of reality.
Thus, the question has been for some time, what does the wavefunction actually represent? For
example, does the probabilistic nature of the wavefunction mean that physical reality actually
exists in a state of probability prior to being observed? The answer to that question is no,
physical reality does not exist in a state of probability prior to being observed, because physical
reality literally does not even exist prior to the relation that creates it as an experience and so as
an observation apprehended by an Individual. And so, if the wavefunction cannot represent
physical reality, because it expresses the state of that reality prior to its observation and so prior
to its even being brought into existence as a reality, then just what is it that is being expressed by
the wavefunction, i.e., what does the wavefunction represent?
In the context of understanding the experiential process as presented in this work, i.e., how
physical experience is created, including the limitation inherent in the Individual creation of
experience, it can now be stated definitively what the wavefunction represents. Quantum reality,
expressed by the wavefunction, represents the translation of the second level of Reality, i.e., a
second level Relational Structure, into terms of physical experience prior to the involvement of
that second level Relational Structure in a relation that actually creates a physical experience. In
short, quantum reality is the translation of second level Realities into terms of third level realities
or physical experiences, absent the involvement of those Realities in a relation that actually
creates a physical experience. Put another way, quantum reality is the translation of second level
Realities into terms of a reality that only arises and comes into existence, as it were, at the third
level of Reality, as Existence becomes involved in another level of self-relation, i.e., a third level
of Existential self-relation, absent the actual involvement of those Realities in a third level
Existential self-relation. Put another way, the wavefunction does not represent physical reality;
rather, it represents a second level Reality or Relational Structure, expressed in terms of that
Realities' potential to become involved in the third level or impactive relations that create what is
apprehended as physical experience.
However, the wavefunction is not what is actually there as Reality, but is itself an experiential
reality. But the wavefunction is not a physical experience, because it is the expression of a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
68
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
second level Reality that is not yet involved in the relation that creates a physical experience, and
so expresses that Reality in terms of its probability or potentiality for functioning in the creation
of a physical experience. Thus, the wavefunction seems to be a very unique and special sort of
experience, in that it seems to be a hybrid mental-physical experience, in that it contains
components of both mental and physical reality, i.e., experiential components derived from both
second and third level Existential relations. The wavefunction contains mental reality in terms of
its abstract mathematics and it contain physical reality in terms of what that abstract mathematics
is expressing, which is the probability of creating a physical experience. Put another way, the
wavefunction expresses the potential of what Exists at the second level of Reality, where mental
experience is being created and where physical experience has not yet been created, to become
involved in the third level relations that actually create physical reality.
Thus, the wavefunction seems to be an experience that is neither purely physical nor purely
mental, but is some combination of both, which makes sense considering that the wavefunction
is derived from third level Realities, i.e., Organic Processes, poking their noses into the second
level of Reality where the relations of Existence to Itself at that level create mental experience,
and then translating what they find at that level of mental experience into terms of the third level
of reality, i.e., into terms of physical experience, as shown in figure 21.
Organic Processes 3rd level of Reality
pure
physical
expe rience
physical experiencereality p roduced
wave func tion
Distortion Processes 2nd level o f Reality
pure
mental
expe rience
mental e xperiencereality p roduced
progressive
stratification of
Reality and reality
Relati onal Matrix 1st level of Rea lity
emotional e xperiencereality p roduced
Figure 21 This drawing depicts the hybrid mental-physical experiential nature of the wavefunction as
being derived from the stratified Structure of Reality and reality, since the wavefunction is what is created
when we dig into the second level of Reality (represented by downward arrow), where mental experience
is created as a result of the Existential relations that are occurring at that level, and force the second level
Realities or Relational Structures at that second level to express Themselves in terms of relations that only
occur at the third level of Reality (represented by upward arrow), where physical experience is created.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
69
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
In a way, the wavefunction is what we get when we force a second level Reality to tell us what
physical experiences it can function to create. And the second level Reality complies and
presents us with the wavefunction, but it makes no sense to us because our senses present us with
determinate physical realities, whereas the wavefunction presents us with indeterminate physical
potentialities. But that is the best the second level of Reality can do, prior to its involvement in a
relation that actually creates a physical experience, because prior to its involvement in a relation
that actually creates a physical experience, at which point it becomes constrained by the
experiential limitation, that second level Reality can function in the creation of opposite physical
experiences, and which it will ultimately function to help create cannot be determined prior to its
direct or indirect involvement in a relation that actually creates a physical experience. It is as if
we are interrogating a second level Reality and say, "tell us what you physically are," and It tells
us the best It can, through the wavefunction, but we do not understand what It is telling us,
because we do not understand that the Reality we are extracting the information from, and trying
to determine the nature of, is of a Nature that is completely different than the nature of the
physical reality that we are demanding it express Itself in terms of.
Perhaps it can now be understood why what the phenomena at the heart of quantum theory have
to say about the nature of reality has remained hidden in plain sight for so long, so radical is the
nature of what understanding those phenomena first requires to be understood regarding the
nature of physical reality as a created and peripheral reality, and so as a sort of reflection that is
not what is actually there where it appears to be, relative to what is presently the dominant
materialist view of physical reality as the central and source reality, in which view physical
reality is assumed to be what is actually there where it appears to be. Again though, the strange is
only strange in the context of considering its opposite to be normal. But again, what are we to do
when what we consider to be normal is itself an illusion, thereby making what is actually the
normal state of affairs seem strange by comparison? As previously stated, we either see through
the illusion and so realize what is actually the normal state of affairs, or we cling to the illusion,
in which case what is actually the normal state of affairs remains hidden from view, as a body of
water remains hidden as long as one takes the reflection that only lies on its surface for what is
there.
4. There is no spoon
Understanding what has just been described in this work as the nature of both quantum Reality
and reality requires that one at least be able to consider the notion that physical reality is
derivative of Consciousness, and so requires one to loosen their grip somewhat on the materialist
notion that Consciousness is somehow derivative of physical reality. Understanding what has
just been described in this work also requires that one at least be able to consider the notion that
physical reality is not what is actually there where it appears to be, in the same way a reflection
is not what is actually there where it appears to be. These things are required because, owing to
the same experiential limitation that functions to create quantum uncertainty, which limitation
precludes an Individual from being involved simultaneously in the mutually exclusive relations
necessary to create opposite experiences, unless and until one is able to loosen their grip on the
materialist assumption regarding the relation between physical reality and Consciousness, as well
as the assumption that physical reality is what is actually there where it appears to be, then the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
70
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
explanation and description of quantum Reality and reality presented in this work simply cannot
be realized, i.e., cannot be created and apprehended as a conceptual reality, because the relations
in which an Individual must be involved in order to conceive as real what has been described in
this work as the overall nature of reality are mutually exclusive of the relations in which that
Individual must already be involved if they are conceiving as real the opposite conceptions of
reality, which opposite conceptions in this case are the related notions that Consciousness is
somehow derivative of physical reality and that physical reality is what is actually there where it
appears to be.
The experiential limitation that has been shown to be central to the functioning of the quantum
phenomena of wave-particle duality, uncertainty, and non-locality, functions in the creation of all
experience, because experience of every sort, , i.e., emotional, mental, and physical, is created as
the product of some relation of Existence to Itself. This is why, as already stated, one cannot feel
good while feeling bad, and vice versa, because those opposite emotional states are the product
of one's involvement in opposite and so mutually exclusive relations, and so while involved in
one relation, and as a result creating and experiencing one emotional state, it is not possible for
an Individual to be involved simultaneously in the opposite and so mutually exclusive relation
necessary for that same Individual to create and experience the opposite emotional state.
Likewise, the experiential limitation also functions in the Individual's creation of mental or
conceptual experience. And owing to the unavoidable functioning of that limitation, no one who
was unable to let go of the notion of the earth as being flat was ever able to conceive of the earth
as actually being round, and no one who was unable to let go of the notion that the sun orbited
the earth was ever able to conceive that the earth orbited the sun. And so it is also that no one
who is unable to let go of the related ideas that physical reality creates Consciousness, and that
physical reality is what is actually there where it appears to be, will ever be able to conceive how
Consciousness creates physical reality, or how it is that physical reality is not what is actually
there where it appears to be, leaving such a one unable to truly understand quantum mechanics,
or what it has to say regarding the nature of reality, because the conceptual context in which
physical reality is conceived to produce Consciousness, and in which physical reality is
conceived to be what is actually there where it appears to be, is the exact opposite of, and so
mutually exclusive of, the conceptual context required to understand the experiential process that
lies at the heart of the phenomena that lie at the heart of quantum mechanics.
In order to truly understand what quantum theory has to say about the overall nature of reality it
is necessary to understand that physical characteristics, be they of the quantum or the macro
variety, are not characteristics of What Is Actually There, i.e., not properties that inhere in the
Existence in relation to Itself that is actually there. Rather, physical characteristics are created as
products of the relations of Existence to Itself, and as such those characteristics and properties
inhere in the relation that is occurring between What Is Actually There and not within the
Existence in relation to Itself that is actually there. What Is Actually There, i.e., the Existence
that is actually there, is not a particle, nor is it a wave. Particle and wave are physical
characteristics that are created as the products of relations occurring between Realities that are
themselves composed of Existence being in relation to Itself. Apprehend the created impactive
boundary from one perspective and what is apprehended is the physical experience of a particle.
But if that same impactive boundary was instead apprehended from the opposite perspective,
what would then be apprehended instead would be the physical experience of a wave. Where
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
71
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
then is the reality of wave or particle? Not in What Is Actually There, but only in the relation
occurring between What Is Actually There, which includes the perspective from which the
product of that relation is being apprehended as a physical experience.
The Relational Structure that underlies what we apprehend as an electron does not have a spin
state either before or after it takes part in a third level or impactive relation that creates the
observation of a determinate physical spin state. The spin state of an electron, like all physical
reality, is a created reality, and not a property that inheres in What Is Actually There. The spin
state may be directly or indirectly related to some aspect of the electrons Relational Structure,
but as a physical experience or physical reality, the spin state itself is not a characteristic or
property that inheres in the Existence that is actually there. Put another way, What Is Actually
There does not have a spin state; rather, a spin state is a physical property we create through
impactive relation to What Is Actually There. Likewise, the quality of hardness does not inhere
in What Is Actually There where we apprehend a rock, nor does the quality of softness inhere in
What Is Actually There where we apprehend a pillow. Nor does the hotness or coldness of a
bowl of water inhere in What Is Actually There where we apprehend the water. Rather, these
properties all inhere in the specific relation that creates the specific physical experience. All
experiential qualities of every sort are created as the product of some relation of Existence to
Itself, and only exist in the context of the specific relation and relational orientation between
Observer and Reality that creates those qualities as specific experiences.
There is no quantum soup, no ocean of probability underlying what we apprehend as physical
reality, there is only Existence being in relation to Itself. The Existence that is actually there,
configured into various Relational Structures and levels of Relational Structuring though
iterative and progressive relation to Itself, does not Exist in a probable state. That is, the
Existence that is actually there at every level of Reality or Relational Structuring is configured in
a specific way in relation to Itself. If It was not, the physical laws and constants that are, for the
most part, an expression of that Structure, would be ever-changing, i.e., they would not be laws
nor would they be constant. It is just that, for reasons already given, second level Relational
Structures can function in the creation of opposite physical experiences, or some combination
thereof, but a particular second level Relational Structure can only function in the creation of one
of those opposite physical experiences, or one combination thereof, in any one moment through
relation to any one Individual, and it is not possible to know which experience it will help
function to create prior to the establishment of some relation between the Individual and the
Relational Structure, because what is ultimately created and apprehended as experience is not a
function of What Is Actually There, but is a function of the relational orientation occurring
between What Is Actually There, i.e., between the Individual and the "observed" Reality. Thus,
the Existence that is actually there, configured into a particular second level Relational Structure,
may be indeterminate relative to its involvement in a relation that creates what is apprehended as
a physical reality, but does not Itself Exist in an indeterminate or probable state. Again, the
appearance and introduction of physical probability occurs when What Is Actually There as a
second level Reality or Relational Structure is translated into terms of physical experience prior
to the direct or indirect involvement of that Reality in a relation that actually creates a physical
experience.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
72
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
Before the advent of quantum physics scientists thought that material reality was composed of
determinate physical realities, because that is how material reality presented itself. However, at
the quantum level physical reality no longer presents itself as determinate, but instead presents
itself in terms of physical probabilities, and so now many scientists and philosophers think that
what is there instead, where physical reality appears to be, is a reality that exists in a state of
probability. However, to conceive of What Is Actually There, underlying physical reality, as
existing in some indeterminate or probable state just because that is how What Is Actually There
must be translated into physical experience, prior to its involvement in a relation that creates a
physical experience, is to simply substitute one illusion for a more elaborate and yet more subtle
illusion. Quantum theory has made it clear that a deterministic physical reality is not what is
actually there where we apprehend deterministic physical reality to be. Thus, quantum theory has
shown macroscopic physical reality to be an illusion of sorts, in as much as the appearance it
presents at the macroscopic level, where it appears to be deterministic, is not the appearance it
presents at the quantum level, where it appears to be probabilistic. However, the probabilistic
appearance that physical reality presents at the quantum level, which probabilistic appearance is
expressed through the wavefunction, is also an illusion, if the probabilistic way physical reality
appears at the quantum level is, like macroscopic physical reality, mistaken for what is actually
there where it appears to be.
At no point in time is any experiential reality what is actually there where that experiential reality
appears to be. Experiential reality of every sort is the product of a relation occurring between
What Is Actually There, as that product is apprehended by, and so from the perspective of, the
Existence that is actually there composing at least part of one side of the relation that creates it.
Physical reality in particular, be it if the quantum or the macro variety, is always the one-sided
apprehension of a two-sided boundary that is created where What Is Actually There becomes
defined in relation to Itself. Therefore, form and tangibility are creations, and not characteristics
or properties that inhere in What Is Actually There. What Is Actually There has neither form nor
tangibility, and yet is nonetheless Itself the source of all form and all that is tangible, as It,
through relation to Itself, produces the boundaries that are the basis of what It apprehends as the
form of mental experience, and the form and tangibility of physical experience.
Form and tangibility arise as the relations of Existence to Itself become complex enough at the
second and third levels of Existential self-relation to create the more elaborate experiential
boundaries apprehended as mental and physical experience, respectively. Thus, there is no
spoon, meaning that what we apprehend as any physical object is not what is actually there,
because what is actually there is non-experiential Existence configured into a Relational
Structure that, when we are involved in an impactive relation with that Structure, creates a
defining boundary that we, from our perspective within that relation, apprehend as the physical
experience or physical reality of spoon. Nor is there even the idea of spoon, because underlying
the creation of all thought is also Existence being in relation to Itself, albeit being in relation to
Itself at a different level and so in a different way, and so in a way that creates what is
apprehended as a mental rather than physical reality, and so apprehended as the idea of spoon,
i.e., as a mental object, rather than as a physical object.
To summarize then, the particulars or characteristics of an experiential reality do not inhere in
What Is Actually There, but only inhere in the particular relation occurring between What Is
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
73
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
Actually There. The hardness of a rock, the softness of a pillow, the particular spin state of an
electron, these are all the products of a relation, the apprehension of a boundary that arises and is
created where Existence becomes defined in relation to Itself, as that boundary is apprehended
by and from the perspective of the Existence-Consciousness that occupies and composes at least
part of one side of the relation that creates it. And what determines the nature of that boundary,
and so determines what is apprehended as experience, cannot be the Nature of the Existence that
is actually there, because that is always and everywhere the same.
We experience different objects because underlying those different object-experiences are
different Relational Structures. And there are different Relational Structures owing to the
different and endless ways in which Existence can become fractally configured, arranged, and
structured in relation to Itself through the process of iterative self-relation. And all of those
Relational Structures, no matter how different the experiences they function to help create, are
composed of the same Existence. Thus, if what we experienced was what is actually there, then
there would only be one experience, because all that is actually there is Existence, albeit
Existence configured and structured in different ways in relation to Itself. But what we
experience is not what is actually there; rather, experience is the Existence that is actually there
apprehending the boundary that is created as a result of Its becoming defined in relation to Itself
through relation to Itself, from a particular perspective within that relation. And what allows
Existence to become defined in relation to Itself has to be some difference between what is here
as Existence and what is there as Existence. And yet, if what is actually both here and there is
Existence, then what is the difference? The difference is in the way Existence here is configured
and structured in relation to Itself versus the way Existence there is configured and structured in
relation to Itself. And those relative differences allow Existence here and there to become
defined in relation to Itself, through relation to Itself, and so create an experiential boundary that
an Individual point of Existence-Consciousness involved in that relation apprehends as a
particular experience, from Its perspective within that relation.
So it is that all that has been written here comes down to the simple understanding that what
actually Exists at every point in the universe is not different than what actually Exists directly
where we are. And what is it that actually Exists directly where we are? Well, there are only two
things that exist directly where we are: experiential reality, of which physical reality is but one
variety, and the Consciousness that apprehends experiential reality. And as the phenomena that
lie at the heart of quantum theory have shown by revealing the nature of physical reality,
experiential reality is not what is actually there where it appears to be. So, what actually exists
directly where we are cannot be an experiential reality, since experiential reality only presents
the appearance of being what is actually there. Therefore, if experiential reality is not what
actually exists directly where we are, then what actually Exists directly where we are must be the
Consciousness that apprehends experiential reality. And once one has dispensed with the illusion
that experiential reality in general and physical reality in particular is what is actually there, then
there is simply no valid or logical reason to assume that what actually Exists anywhere else is
ultimately of a different Nature than what actually Exists directly where we are.
What is it that makes us think that what exists directly where we are is different in nature than
what exists elsewhere? For example, what is it that makes us think that what exists where we are,
i.e., where our bodies appear to be, is different in its essential nature than what exists where a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
74
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
rock appears to be? What makes us think that is the mistaken idea that physical reality is what is
actually there where it appears to be. And because physical reality here appears different than
physical reality there, we assume that what exists here, where our physical bodies appear to be, is
somehow different in its essential nature from what exists there, where other physical objects
appear to be. However, as has been described, physical reality is not what is actually there where
it appears to be, but is more like a reflection, thereby leaving open the question of what it is that
is actually there underlying the reflection that is physical reality. And to answer that question we
need only look to what it is that exists directly where we are that is not itself experiential in
nature. And what exists directly where we are that is not experiential in nature is the
Consciousness that apprehends experiential reality.
We assume that what we apprehend as physical reality is what is actually there simply because
that is how it appears or presents itself, from our common perspective, and so we assume that
what we are is our physical bodies, and we further assume that it is our physical body that
somehow produces our Consciousness. And based on those assumptions it seems that what we
are must be of a different nature than what exists elsewhere. However, as an understanding of the
experiential basis of the phenomena that lie at the heart of quantum theory makes clear, physical
reality cannot be that which creates Consciousness, because, physical reality only appears to be
what is there. Instead, what those phenomena indicate is that we are points of ExistenceConsciousness, i.e., Individuals, that create what we apprehend as experiential reality in general
and physical experience in particular through our relation to other points of ExistenceConsciousness.
There is no pot of gold at the end of the rainbow because rainbows are not actually there where
they appear to be. Rainbows are illusions that present the appearance of being structures that are
actually there, wherever they appear to be. Likewise, physical reality presents the appearance of
being actually there, where it appears to be, and in this way physical reality is like a rainbow.
And like someone who harbors the delusion that rainbows are actual structures and so goes off in
search of the pot of gold that is said to lie at the base of that structure, modern science harbors
the delusion that physical reality is what is actually there where it appears to be, and so has gone
off in search of Consciousness at the end of that rainbow. However, Consciousness cannot be the
pot of gold that somehow arises at the end of the physical rainbow, because like a rainbow,
physical reality is not what is actually there where it appears to be, but only presents the
appearance of being what is actually there, and so cannot itself actually produce anything, other
than illusion.
For the same reason, physical reality cannot actually be constructed of more fundamental
physical realities, because physical reality at every level only presents the appearance of being
what is actually there. Put another way, in the same way that larger rainbows are not constructed
of smaller rainbows, since regardless of scale they are still illusions, what we apprehend as
macroscopic physical structure is not constructed of smaller physical structures, because there
are no actual physical structures at any level, there is only the appearance of physical structure.
Rather, what is actually there, at every level, quantum or macro, is Existence that has, through
iterative self-relation, become configured and structured in relation to Itself into some sort of
Relational Structure which, when involved in an impactive relation with another Relational
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
75
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
Structure, brings into relative existence a boundary that is apprehended by the Existence that is
involved in that relation as the sort of rainbow we refer to as a physical reality.
The related ideas that physical reality is what is actually there where it appears to be and that
physical reality creates Consciousness are the flat earth ideas of our time. That is, they are ideas
that arise from and appear to be true from a limited and common perspective, but which do not
maintain that appearance when considered and viewed from a broader perspective, which
broader perspective in this case has been afforded by quantum physics. The time will come, how
soon or far off I do not know, when future generations will look back upon us and be somewhat
amused by our naiveté with regard to the nature of reality, as we are often amused by those who
once thought the earth to be flat. They will chuckle at the notion that we thought of ourselves as
physical bodies, and will wonder why it was not obvious to us what it is that actually Exists
directly where are, as well as what must then Exist directly everywhere else as well.
If one stands in the middle of illinois the earth still appears to be flat, but it is understood to be
only an appearance and not the actual state of affairs, and so one is not taken in by the illusion.
Likewise, physical reality will always present the appearance of being what is there, but at some
point humanity will understand this to be only an appearance and not the actual state of affairs,
and so future generations will, unlike ourselves, not be taken in by the illusion. At some point the
actual state of affairs will be obvious to those future generations, because they will not be
saddled and constrained in their conceptualizations regarding the nature of reality with the same
preconceptions and false assumptions regarding the nature of reality with which we are, by and
large, presently saddled and constrained, which are again the related materialist assumptions that
physical reality is what is actually there where it appears to be and that physical reality somehow
creates Consciousness, both of which false assumptions arise from the same sort of common
perspective that at one time made it seem reasonable and correct to believe that the earth was
flat, and both of which false assumptions have prevented and continue to prevent scientists from
understanding what their own experiments at the quantum level have revealed about the nature of
experiential reality in general and physical reality in particular.
Ultimately there are only two things required to understand the nature of quantum reality: that
whatever is apprehended as a physical reality is not what is actually there, but is instead the
apprehension of something that has been created as the product of one's relation to what is
actually there, from one's own perspective within that relation; and that the requirement of one's
involvement in a relation in order to create whatever one apprehends as a physical experience
imposes an unavoidable and inviolable limitation upon what one can create and apprehend as a
physical experience in any one moment, since it is not possible for an Individual to be involved
simultaneously in the mutually exclusive relations necessary to create opposite physical
experiences. However, it is one of the great ironies that the experiential limitation that has been
revealed by the phenomena that lie at the heart of quantum theory is the same limitation that has
kept scientists from recognizing the experiential limitation revealed by their own experiments,
because implicit in the conception of the experiential limitation is the concept that we participate
in the creation of whatever it is that we apprehend as physical experience, and that concept is
mutually exclusive of the concept of realism to which most scientists adhere. That is, the relation
in which scientists, as Individual's, must already be involved in order create and apprehend the
concept of realism to which they adhere, i.e., that an external reality exists independent of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
76
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
observation, is mutually exclusive of the relation in which they each, as Individual's, need to be
involved in order to create the opposite concept, i.e., that no external reality exists independent
of observation, which opposite conception is a prerequisite to understanding the experiential
limitation their own experiments at the quantum level have revealed. It is a sticky wicket, and it
is this sticky wicket that has caused science's dogmatic adherence to the philosophy of
materialism to keep what quantum physics has revealed about the nature of reality hidden in
plain sight for nearly one-hundred years.
Again, knowledge, like all experience, is not just found lying about, but must be created in order
to be apprehended. And an Individual cannot create knowledge that is the opposite of the
knowledge they are already creating, because to do so would require that Individual to be in the
impossible position of being involved simultaneously in what are mutually exclusive relations.
For this reason, the preconceptions and false assumptions that we cling to regarding the nature of
reality make it as impossible for us to conceive of the actual nature of reality, i.e., the actual
relation between Consciousness and physical reality, as well as the actual nature of physical
reality, as it was for someone who refused to let go of the idea that the earth was flat to conceive
of the actual shape of the earth. However, thanks to the work of quantum physicists and theorists,
and the new perspective upon reality which that work provides, future generations will, at some
point, once what quantum theory says about the nature of reality is more widely understood,
come to understand and accept that physical reality is not what is actually there where it appears
to be and so will also come to understand that it is Consciousness that must create physical
reality, in the light of which understanding it will be obvious to them what it is that actually
Exists directly where they are, as well as what it is that actually Exists everywhere else as well.
All the Universe is molded from the same Clay, and that Clay I refer to as Existence. But we
cannot experience the Clay from which the Universe is molded because experience is of a
different nature than the Clay. Experience is created, the Clay is not. Experience is the product of
a relation, the Clay is not. All we can do is make experiential etchings of the Clay, which
etchings in some way reflect how the Clay has become arranged and structured in relation to
Itself. But although we cannot experience the Clay from which the Universe is molded, which
Universe underlies the reflection that is physical reality, the Clay is not beyond us, because it is
What We Are. What We Are has been given many names. There is much discussion and
argument about which name is correct, all of which is somewhat pointless, since names are
experiential in nature and What We Are is not, meaning that all names for It must, in the final
analysis, miss the mark. Nonetheless, in discussing such matters it is necessary to use a name to
indicate or point toward that which Exists directly where we are and is not other than What We
Are. I have chosen to call it Existence. Lao Tzu, on the other hand, chose to call it the Tao.
Look, and it can't be seen.
Listen, and it can't be heard.
Reach, and it can't be grasped.
Above, it isn't bright.
Below, it isn't dark.
Seamless, unnamable,
it returns to the realm of nothing.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
77
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
Form that includes all forms,
image without an image,
subtle, beyond all conception.
Approach it and there is no beginning;
follow it and there is no end.
You can't know it, but you can be it,
at ease in your own life.
Just realize where you come from:
this is the essence of wisdom.1
5. The connection between quantum physics and eastern philosophy
There have been countless books and articles written that suggest a connection between eastern
philosophic traditions and quantum physics, owing to parallels identified between the way reality
is described by those eastern philosophies and the way quantum physics has been forced to
describe reality. However, as depicted in figure 22, nowhere in any of those works is a direct
connection ever actually identified linking reality as it is now being described by quantum
physics to reality as it has been historically described by the mystics and sages of those eastern
philosophic traditions.
reality as
described
by quantum
physics
parallels between reality
as described by eastern
philosophic traditions
and reality as described
by quantum physics,
thereby suggesting a
connection between the
reality being described
by each
reality as
described
by eastern
philosophic
traditions
????
Figure 22 Depicted here as pieces of a puzzle are, on the left, reality as described by quantum physics
and, on the right, reality as described by eastern philosophic traditions. Depicted in the middle is the
missing piece that actually connects these two ways of describing reality, which connection is suggested
by similarities in the way reality has been described historically in eastern philosophic traditions and the
way reality is being described presently by quantum physics.
Eastern philosophies maintain, in general, that Consciousness is more fundamental that physical
reality. Science has taken the opposite view, maintaining that physical reality is more
fundamental than Consciousness. However, owing to the findings of quantum physics, one
branch of science is now being forced to the view that Consciousness may be at least as
fundamental as physical reality, since what is observed as physical reality, at least at the quantum
level, can not even be said to exist as a physical reality in the absence of its observation as such
by a Consciousness, thereby making somewhat problematic the argument that physical reality
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
78
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
somehow gives rise to Consciousness. Thus, most of the works that suggest a connection
between reality as described in eastern philosophic traditions and reality as described by
quantum physics do so, at least in part, by noting that quantum physics has been forced to
describe reality in a way that, like eastern philosophies, ascribes to Consciousness a more central
role in the hierarchy of reality. And so, although it is Consciousness that is often suggested as
that which connects these two ways of describing reality, no direct connection is ever actually
established, beyond stating that the reality of Consciousness, which is integral to the way eastern
philosophies describe reality, has now become integral to the way in which quantum physics
must describe physical reality, as shown in figure 23.
reality as
described
by quantum
physics
Consciousness
integral to each
description of
reality
reality as
described
by eastern
philosophic
traditions
????
Figure 23 Since Consciousness is integral to the description of reality put forth by both quantum physics
and eastern philosophies, in works that suggest a connection between eastern philosophic traditions and
quantum physics it is Consciousness that is most often suggested as that which links reality as described
by quantum physics to reality as described in eastern philosophic traditions. However, in none of those
works is the way in which these two descriptions of reality are actually linked by Consciousness actually
identified.
The reason no direct connection has ever been identified or established between reality as
described by eastern philosophic traditions and reality as described by quantum physics is
because what connects eastern philosophies and quantum physics is the overall nature of reality,
which includes both the Nature of Reality and the nature of reality, as well as their relation, and
until now that overall nature and relation had remained hidden. Put another way, there is reality
as it is apprehended and described by the quantum physicist, and there is Reality as it has been
apprehended and described by the mystic, and so the piece of the puzzle that actually connects
these two descriptions of reality is the one that contains a description of the relation between
Reality and reality, and that piece had yet to be found. However, now that the experiential basis
of the phenomena that lie at the heart of quantum theory is understood, which understanding
provides a way of understanding how Reality, though relation to Itself, creates what it
apprehends as reality, that missing piece has been found and so a direct connection can now be
made between reality as described by quantum physics and Reality as described by eastern
philosophic traditions.
Quantum theory describes reality in terms of physical experience and so describes reality in
terms of reality. Eastern philosophies, on the other hand, describe reality in terms of that which is
the basis of and apprehends experience, and so describe reality in terms of Reality. Prior to the
discovery of the phenomena that lie at the heart of quantum theory science could get away with
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
79
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
the idea that Consciousness plays no role in the creation of what we experience as physical
reality. Eastern philosophies, on the other hand, have understood for some time the central role
Consciousness plays in whatever we apprehend as experiential reality. However, although
eastern philosophies long ago identified the correct hierarchical relation between Consciousness
and physical reality, as well as the difference in nature between them, referred to by some as
discrimination between the Real and the unreal, what those eastern philosophies have not yet
been able to do is describe the precise nature of the relation between Consciousness and
experiential reality in general and physical reality in particular. That is, although eastern
philosophies recognize Consciousness as more fundamental than physical reality, and so also
recognize that physical reality must be in some way derived from the more fundamental Reality
of Consciousness, what those philosophies have not yet done is provide an explanation regarding
how the Reality of Consciousness gives rise to or produces what is apprehended as experiential
reality in general and physical reality in particular. And so, as shown in figure 24, although the
overall view of reality put forth by eastern philosophies with regard to the relation between
Consciousness and physical reality is essentially correct, it is also somewhat incomplete,
inasmuch as there remains a gap in that view regarding just how it is that non-physical, nonexperiential Consciousness gives rise to the tangible world of physical experiential reality.
physical
reality as
apprehended
by humanity
precise relation between
Consciousness and
physical reality, i.e.,
understanding of how
fundamental Reality of
Consciousness gives
rise to what is
apprehended as
physical reality
Consciousness
identified as
fundamental
Reality in
eastern philosophic
trad itions
?? maya ??
Figure 24 Although eastern philosophies correctly identify Consciousness as being more fundamental
than physical reality, those philosophies have been unable to explain how the Reality of Consciousness
gives rise to physical reality, thereby leaving missing the piece of the puzzle that connects the Reality
those philosophies identify as fundamental to the reality those philosophies identify as being derived from
that more fundamental Reality, which derivative reality is often referred to in those philosophies as an
illusion of some sort, and which derivative reality humanity apprehends as physical reality.
It is the eastern philosophy of vedanta that has perhaps come the closest to describing the relation
between Reality and reality, as put forth in the concept of maya expounded by the vedantist
philospher Adi Shankara, which concept is expressed in the following quote by another
vedantist, Swami Vivekananda:
Ignorance or Mâyâ, as it is called, is the cause of all this phenomenon — the Absolute,
the Unchangeable, being taken as this manifested universe. This Maya is not absolute
zero, nor non-existence. It is defined as neither existence nor non-existence. It is not
existence, because that can be said only of the Absolute, the Unchangeable, and in this
sense, Maya is non-existence. Again, it cannot be said it is non-existence; for if it were, it
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
80
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
could never produce phenomenon. So it is something which is neither; and in the Vedanta
philosophy it is called Anirvachaniya or inexpressible.2
However, as this quote indicates, the vedantist concept of maya is not so much an explanation of
how Reality creates reality, rather it is an acknowledgement of the fact that although what is
actually there is Reality, it somehow appears as reality, but exactly how that occurs is considered
to be inexpressible.
That having been said, and as explained in detail in one of my previous works, in the context of
understanding the unavoidable limitation inherent in the Individual creation of experience, as
well as the reflection-like nature of physical reality, both of which understandings are made
possible by understanding the experiential basis of the phenomena that lie at the heart of
quantum theory, it becomes possible to understand how Consciousness, in mistaking the physical
reality it has created for what is actually there, initiates and places Itself in a self-perpetuating
cycle of illusion and delusion, wherein the Consciousness that is actually there becomes hidden
from Itself in plain sight, since once It conceives of physical reality as what is actually there It
must then conceive of What Is Actually There, i.e., Consciousness, as not what is actually there,
and so must conceive of Consciousness as a sort of illusion, thereby perpetuating the illusion that
physical reality is what is actually there, which in turn perpetuates the delusion that has the
Consciousness that is actually there conceiving of Itself as a secondary or derivative reality, i.e.,
as a product of the physical reality it mistakes for what is actually there, thereby perpetuating the
illusion that physical reality is what is actually there, thereby perpetuating the delusion that keeps
the Consciousness that is actually there hidden from Itself in plain sight, and on and on and
on….3
In any case, having lost sight of our true Nature, science and humanity, by and large, went with
the philosophy of materialism, went with what seemed obvious really, at least on the surface, i.e.,
that the universe was composed of physical reality and that somehow or another physical reality
gives rise to the non-physical reality of Consciousness, which then apprehends the physical
reality that is its source and basis. And materialism worked out quite well for some time as a
description of reality that seemed to explain how the world worked, until technology and
understanding reached the point that it became possible to begin probing into the subatomic
realm in order to see how reality at that level was arranged, at which point it became impossible
to ignore the ever-present limitation inherent in the Individual's creation of experience, thereby
introducing uncertainty, making it difficult to ignore completely the role Consciousness plays in
the creation of experience, given that whatever is experienced as a quantum physical reality can
only be said to exist as such in the context of its observation, i.e., in the context of its being
apprehended as a physical reality by an Individual Consciousness.
As Ken Wilber points out, many of the pioneering physicist's of the twentieth century, e.g.,
Einstein, Heisenberg, de Broglie, Schroedinger, and Plank, among others, became mystics, as
opposed to materialists, as they came to realize that there had to be a more fundamental reality
underlying the reality they were themselves observing, as they came to realize that the quantum
realities they were observing were not what was actually there, but were more like the shadows
on the wall of Plato's cave.4,5 Thus, Sir Arthur Eddington stated: "The frank realization that
physical science is concerned with a world of shadows is one of the most significant of recent
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
81
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
advances."6 Likewise, Schroedinger stated: "Please note that the very recent advance [of
quantum and relativistic physics] does not lie in the world of physics itself having acquired this
shadowy character; it had ever since Democritus of Abdera and even before, but we were not
aware of it; we thought we were dealing with the world itself."7
However, as Wilber also points out, none of these Individuals felt that modern physics in any
way provided direct evidence for that more fundamental reality. Rather, they felt that the
mystical and the physical were two separate domains and that each was to be probed independent
of the other. However, although the mystical and the physical may be different domains, they are
not separate domains, because as has been described, they are connected, since it is the more
fundamental Reality that both creates and apprehends reality, and it is the phenomena that lie at
the heart of quantum theory that have revealed the nature of that connection by revealing how
Reality, through relation to Itself, creates reality.
Thus, although quantum physics does not and cannot ever provide direct evidence regarding
What Is Actually There, because physics deals with experiential reality and What Is Actually
There is, by its very Nature, non-experiential, quantum physics, through the phenomena that lie
at the heart of quantum theory, nonetheless does provide direct evidence that what we apprehend
as physical reality is not what is actually there, once that evidence is analyzed and understood in
its proper context, i.e., in the context of understanding the actual relation between physical
reality and Consciousness, which includes the way in which Consciousness, through relation to
Itself, creates what it apprehends as physical reality. And that evidence can be of assistance in
helping the Individual to free themself from the self-perpetuating cycle in which, owing to the
experiential limitation, their true Nature must remain hidden from them while still in plain sight
of them as their own Consciousness, as long as they continue to believe and so conceive that
physical reality is what is actually there where it appears to be, since their ongoing involvement
in the relation that creates for them that erroneous conception makes it impossible for them to
become involved in the opposite and so mutually exclusive relation in which they need to be
involved in order to create the opposite and more accurate conception of Consciousness, rather
than physical reality, as what is actually and directly there where physical reality appears to be.
So it is that, thanks to the probings of quantum physics we have come almost full circle and have
arrived back at a description of reality that finds at least some level of agreement with the eastern
philosophic traditions that hold Consciousness to be more fundamental than physical reality.
However, also thanks to quantum physics, we now know something that was not known before
with regard to Consciousness, in as much as we now know, owing to our understanding of the
experiential basis of the phenomena that lie at the heart of quantum theory, precisely how
Consciousness creates what it apprehends as physical experiential reality, thereby clearly
revealing the relation between Consciousness and physical reality. And in revealing the relation
between Consciousness and physical reality, quantum physics has found the piece of the puzzle
that had been missing from the description of reality put forth in eastern philosophic traditions,
which piece directly links the Reality of Consciousness to experiential reality. And as shown in
figure 25, it is that same newly found piece of the puzzle linking the Reality of Consciousness to
experiential reality that is also the piece that is needed to directly connect Reality as described by
eastern philosophic traditions to reality as described by quantum physics.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
82
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
physical
reality as
apprehended
by humanity
reality as
described
by quantum
physics
understanding of how
fundamental Reality
of Consciousness
creates physical
reality (made possible
by the findings of
quantum physics
regarding the
behavior of quantum
reality)
understanding of how
fundamental Reality
of Consciousness
creates physical
reality (made possible
by the findings of
quantum physics
regarding the
behavior of quantum
reality)
Consciousness
identified as
fundamental
Reality in
eastern philosophic
trad itions
Reality as
described
by eastern
philosophic
traditions
Figure 25 What these two drawings illustrate is that the same missing piece that is able to connect eastern
philosophies' understanding of Consciousness as a fundamental Reality to physical reality as a secondary
or derivative reality (top drawing) is the same missing piece that connects Reality as described in eastern
philosophic traditions to reality as described by quantum physics (bottom drawing). And in both cases
that missing piece, indicated by the double arrow, is the understanding of how the fundamental Reality of
Consciousness creates physical reality, which understanding is made possible by the findings of quantum
physics regarding the behavior of physical reality at the quantum level, since the only way to explain that
behavior is through an understanding of the unavoidable and inviolable limitation inherent in the
Individual's creation of experience, and the only way to understand why there is such a limitation is
through an understanding of how physical experience is created as the product of a specific type of
relation of Consciousness to Itself.
Thus, the model of Reality and reality presented in this work that allows for an understanding of
how Consciousness creates experiential reality does not suggest a connection between Reality as
described by eastern philosophic traditions and reality as described by quantum physics; rather, it
demonstrates what that connection is directly, by explaining how Absolute Existence or
Consciousness, described in eastern philosophies as the fundamental Reality, through relation to
Itself, produces physical experiential reality, as described by quantum physics. And all it takes to
understand the model of Reality and reality presented in this work is the ability to understand
what happens to a rubber band that is twisted repeatedly upon itself, combined with the
willingness, where necessary, to loosen one's grip upon preconceived and dogmatic notions
regarding the relative positions of physical reality and Consciousness in the hierarchy of reality
as a whole, which preconceived and dogmatic notions themselves arise from a limited flat-earth
type of perspective that causes physical reality to appear to be what is actually there, which
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
83
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
appearance, as has been demonstrated, does not hold up when viewed from the broader
perspective afforded by quantum physics.
Those who study eastern philosophy are advised, if they would arrive at the truth, to learn to
discriminate between the Real and the unreal. Likewise, modern physicists would be well
advised, if they would know the truth of what their own experiments reveal about the overall
nature of reality, to do what the founders of quantum physics were apparently able to do in some
measure, which is learn to discriminate between Reality and reality, between What Is Actually
There and what only appears to be what is actually there. Both science and eastern philosophies
have it as their goal to describe the nature of reality in the fullest sense possible. The findings of
eastern philosophy were arrived at as Individuals, seeking to understand the ultimate nature of
reality, probed deeply into Reality within themselves. Conversely, or likewise, depending on
how one looks at it, the findings of quantum physics were arrived at as Individuals, also seeking
to understand the ultimate nature of reality, probed deeply into Reality external to themselves.
Thus, eastern philosophers arrived at their description of reality using the method of
introspection, or inward probing, i.e., probing into Reality that is internal to the Individual,
whereas science, on the other hand, has arrived at its description of reality using extrospection, or
external probing, i.e., probing into Reality that is external to the Individual.
Both eastern philosophers and scientists analyze reality by progressively breaking experiential
reality down into its constituent parts to uncover what is there. The eastern philosopher,
approaching Reality from within, breaks down the objects of thought into their most fundamental
components to see what that reveals. Likewise, the scientist, approaching Reality from without,
breaks down physical objects into their most fundamental components to see what that reveals.
Thus, eastern philosophers and scientists both try to get at the nature of reality by progressively
unraveling the progressively raveled components of the different experiential realities they each
encounter according to the different directions from which they are each approaching Reality;
the former approaching Reality from within their own Individuality, thereby encountering and
unraveling mental reality, and the latter approaching Reality from outside their own
Individuality, thereby encountering and unraveling physical reality. And the reason both the
philosopher and the scientist must use the same method of approach, i.e., the unraveling of
reality, even though their direction of approach is divergent, one being internally directed and the
other being externally directed, is owing to the fact that underlying what we apprehend as both
mental and physical reality is a singular Existence that both has evolved and continues to evolve,
through iterative and progressive relation to Itself, into Reality and reality, i.e., into more highly
ordered Relational Structures thereby allowing for the creation of more elaborate experiences,
leaving what is there as both Reality and reality to be most effectively analyzed through the
unraveling of the Existential relations that both compose Reality and also create reality.
Thus, even though these two ways of describing reality are divergent, i.e., the description of
eastern philosophy and the description of science, one approaching Reality from within and the
other approaching Reality from without, respectively, ultimately these two ways of describing
reality both end up converging upon the Reality of Consciousness, because no matter how
Reality is approached, from within or without, one is still approaching the same Reality and so
one eventually arrives at the same destination. And that destination is the understanding that
experiential reality, like a reflection that lies on the surface of a pond, only appears to be what is
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| January 2014 | Volume 5 | Issue 1 | pp. 65-84
84
Kaufman, S. E., The Nature of Quantum Reality: What the Phenomena at the Heart of Quantum Theory Reveal About the Nature
of Reality (Part III)
actually there, and that What Is Actually There, underlying that reflection, and obscured from
being seen as what is actually there by that reflection, as long as experiential reality is taken for
what is actually there, is What We Actually Are, which, regardless of the name we choose to
superimpose upon It, remains That which is Itself uncreated and yet which, through relation to
Itself, creates what It apprehends as experiential reality.
1
From the Tao Te Ching as translated by Stephen Mitchell, Harpercollins, 1988
The Complete Works of Swami Vivekananda, Advaita Ashrama, 2003, Vol 1 pp. 363-364
3
Kaufman, S.E., The Experiential Basis of Maya: How the Limitations Inherent in the Individual's Creation of
Experience Function to Conceal the Nature of Reality (Part I and II), Journal of Consciousness Exploration &
Research| May 2013 | Volume 4 | Issue 5 | pp. 458-514
4
The Allegory of the Cave from The Republic by Plato
5
Wilber, K., Quantum Questions: Mystical Writings of the World's Great Physicists, Shambala Publications, 1984
6
Ibid., pg 7
7
Ibid.
2
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research | June 2014 | Volume 5 | Issue 5 | pp. 548-550
Oliver, A. J., Evolution & Modifications of the Mind
548
Essay
Evolution & Modifications of the Mind
Alan J. Oliver*
ABSTRACT
One life in different bodies would have a similar range of awareness in each body. As the need
for different aspects of awareness became necessary for survival, some would be selected for that
aspect through evolution with the necessary restructuring of the neural networks following. The
mind is always vigilant, assessing every moment against the inputs present. We call that thought
when the outcome or decision is made known through our awareness. More generally, we just
say we are conscious.
Key Words: thinking process, public life, state of mind, still mind, valid decision.
From the time single-celled creatures appeared on earth it can be assumed that these entities had
some interaction with their immediate environment. These interactions involved the identifying
of material and sources of energy to sustain life. Given that reproduction was achieved by cell
division, it can also be assumed that the intelligence gained from experience was able to
accumulate in this growing life form to become an informational asset which contributed to the
survival of that form. I am not going to make any assumptions about the role of DNA in this
model because I am not sufficiently familiar with this aspect of life.
What I can say is that the life experience of a species will have some input into the DNA of that
life form, and depending on where it is placed on the time scale, it will carry many of the
survival strategies of its ancestors as part of its informational assets. In the case of the human
form these assets can indeed be influenced by its DNA. More importantly, though, the greatest
human asset is the human brain.
Dolphins, elephants and humans all exhibit self-awareness, and have similar structures in the
brain which are related to higher cognitive functions such as planning a strategy. So for me the
question about consciousness is not so much one of what is the physical source of consciousness
but one of seeing that what we call consciousness is the natural evolution of the process of
interacting with one’s environment.
An ability or attribute of a species evolves to meet a need arising from a change in the
environment in which that species lives. Thus the informational asset of an amoeba is sufficient
for that particular animal. When humans branched from the primate line they possessed at that
time the informational assets of primates as their starting point. Over time they would have had
to adapt to life on the open savannah, and those who adapted successfully survived.
Part of what adapted in the neo-human was an awareness of the new threats, of new skills such
as standing upright, being aware of a wide field of vision and the different varieties of food. All
of this would require more to remember and this need, together with a changing diet from fruit to
*
Correspondence: Cr. Alan J. Oliver, Port Elliot, South Australia. E-mail: thinkerman1@dodo.com.au
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2014 | Volume 5 | Issue 5 | pp. 548-550
Oliver, A. J., Evolution & Modifications of the Mind
549
meat would have increased the need for a greater memory and hence, a greater brain size. If it
was the case that their environment required better communication within their group to cope
with the emerging threats, it would provide the evolution of speech to communicate a greater
range of messages to describe what was being given in an alarm situation.
I am not at all surprised that we have a huge array of information at out beck and call within the
brain, and that a particular item can appear in our awareness as a thought or image. I would
assert that what we call consciousness is this information being displayed in our awareness as a
thought, emotion or image, and its origin can be from direct sensory input, from memory or from
imagination. We can test this assertion by simply holding a thought or word in mind and noticing
what follows.
All of this is achieved by having all of our experience, be that from memory, from the more
primitive responses of survival or simply from our imagination, all immediately available in our
awareness. What selects from this smorgasbord of information is the context in which we
perceive the information. The context is a function of our modifications of the mind, and is what
I have referred to in an earlier paper as the decision process which is an unconscious one. In
essence, what we call consciousness is both servant and master, although the master is, in most
cases, the puppeteer.
When the first living cell/entity divided, it became two versions of the original cell from the
same living organism. Thus, life was then present in two separate living cells. I suggest that the
attributes of each would be the same, such as the ability to interact with the environment and
each other.
As the form evolved each subsequent division would produce identical attributes, together with
the potential for different experiences if they moved away from the common location. This could
provide the impetus to evolve into different species, e.g., moving on to sexual reproduction, and
for convenience just for mammals.
The sperm and ovum must be alive for conception to succeed. Therefore, my conjecture of a
continuation of life in different individuals is still valid. Like the individual mushroom being part
of a subterranean network of a single fungus, a child can be thought of as separate body of a
combination of two individual lives (parents). And much of the attributes within that
combination become a slightly different set of attributes from those of each parent.
If we call these attributes information, or more specifically, the way in which information is
managed, this model explains what is currently called epigenetics. I am suggesting that with each
generation, beginning with an ancestor primate, the circumstance of moving on to the savannah
would be the scene for successful variations to survive, and each successful attribute would be
present in the progeny through the shared life. I am saying that the one life in different bodies
would have a similar range of awareness in each body.
As the need for different aspects of awareness became necessary for survival some would be
selected for that aspect through evolution. I am saying that what we now call consciousness is
such an aspect of awareness, with the necessary restructuring of the neural networks following.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | June 2014 | Volume 5 | Issue 5 | pp. 548-550
Oliver, A. J., Evolution & Modifications of the Mind
550
In the current evolutionary stage, human is the result of evolution, and I suggest that most of our
conscious information comes from a combination of memory and sensory input being mediated
in the brain through the same process I have earlier mentioned as the decision process [1].
I believe this process is the same as what is described in Yoga and Buddhism as the
modifications of the mind. The mind is always vigilant, and assessing every moment against the
inputs present; we call that thought when the outcome or decision is made known through our
awareness. More generally, we just say we are conscious.
It is entirely probable that with the evolution of the homo form giving rise to a greater amount of
information being available to the mind through experience, memory and the immediate
moment, there would arise the need to separate the total into what was immediately relevant and
what was to be held in reserve to accessed through related context.
Thus there would be the mind as we know it in a general sense, operating in the conscious
foreground, and memory and other potential information (as in the modifications of the mind and
memory) in the background. The shuffling of information back and forth in response to a
question or context is what we call thought. I am not completely sure of just how Samapatti fits
into this model, except to say that if there is just one life within many bodies then is must surely
be one possibility.
Some years ago the late David Bohm wrote “Wholeness and the Implicate Order”, in which he
said that the greatest difficulty we humans face is the misconception of separateness. My notion
of one life in many bodies suggests that we are indeed interconnected, and it may just be the case
that in the Samadhi state, a prerequisite for Samapatti, we can reconnect to that one life.
I have always though that the one downfall of my model was the lack of the position of the
observer, as we find in Samadhi when the mind itself has been brought under control (empty
mind). But from recent conversations with Dr Meera Chakravorty I realise that this model I have
offered falls fairly neatly into what the ancient Hindu thinkers said all of those thousands of
years ago about consciousness. They said that the first cause of everything is Purusha, which is
Pure Consciousness. This is reflected on to matter and this reflected consciousness is termed
purusha (with the small p). So I can confidently say that purusha is that detached observer, the
awareness remaining after the mind has become empty, hence its modifications have ceased to
operate. It is in this state that one can truly make a clear decision.
Reference
1. Alan J. Oliver (2014), On the Process of Thinking in Public Life: A Conversation in the Interest of
Democracy. JCER 5(4): pp. 428-433.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
657
Article
Geomagnetics & Consciousness:
Geomagnetic Field Effects & Human Psychophysiology (Part I)
Iona Miller*
ABSTRACT
Anomalies during geomagnetic storms have potential psychophysical effects on human
populations, as well as our technologies. Energetic events and ejections of plasma from the Sun
cause dramatic changes in the radiation belts and magnetic field of Earth, as well as fluctuations
in Schumann Resonance. Ben Lonetree has conducted numerous experiments correlating local
geophysical anomalies in earth's magnetic field with EEG brainwaves of many subjects, and
anecdotal reports of changes in consciousness. This article covers some basics of geophysics,
electromagnetic effects on human psychophysiology, with some theories of psi and anomalous
experience related to geomagnetics.
Part I of this two-part article contains: Introduction; & I. Geophysics.
Key Words: geomagnetic field effects, geophysics, magnetosphere, space weather, paranormal
potential, biophysics, anomalous experience, solar wind, brainwaves, EEG.
(Source: IBEX Magnetic Field Influence; Southwest Research Institute,
“Heliosphere”, Wikipedia)
*Correspondence: Iona Miller, Independent Researcher. Email: iona_m@yahoo.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
658
Introduction
Research has proven that changes in solar/geomagnetic activity can affect our emotions and
collective behavior. Every cell in your body is bathed in an environment of magnetic forces
which are invisible to the human eye. Numerous rhythms within your body can synchronize with
solar and geomagnetic activity. The earth’s magnetic resonances vibrate at the same frequency
as human heart rhythms and brainwaves. The earth’s constantly changing electromagnetic fields
may be affecting your day-to-day health, feelings and behavior. When the sun’s emission of a
2.8-gigahertz radiowave frequency is increased we tend to feel better. Geomagnetic field
disturbance is associated with lowered heart rate variability, indicating our nervous system is
not functioning as well. Earth’s magnetic fields can affect your health and daily life. Heart
coherence helps reduce emotional reactions during solar flares. Solar flares can disrupt your
sleep. Migraines may correlate with geomagnetic disturbances. You can feel more mentally
fogged during solar flares. We are more intuitive during full-moon periods. --Heartmath
Even a single cell has its characteristic shape and anatomy, all parts of which are in constant
activity; its electrical potentials and mechanical properties similarly, are subject to cyclic and
non-cyclic changes as it responds to and counteracts environmental fluctuations. --Mae-Wan Ho
Twenty times more solar particles cross the Earth’s leaky magnetic shield when the sun’s
magnetic field is aligned with that of the Earth compared to when the two magnetic fields are
oppositely directed." --Marit Oieroset on THEMIS spacecraft data
This article covers some basics of geophysics, electromagnetic effects on human
psychophysiology, with some theories of psi and anomalous experience related to geomagnetics.
Geophysics uses quantitative means to describe the physics of the Earth and its environment in
space. This vast magnetic cocoon is a force-field that has sheltered our journey through space for
billions of years. Sometimes strengthening and weakening over long periods, the magnetosphere
protects us against the bombardment of particles continuously streaming from the sun (solar
wind). Because the solar particles (ions and electrons) are electrically charged, they feed
magnetic forces. Most are deflected by our planet's magnetic field. However, our magnetic field
is a leaky shield and the number of particles breaching this shield depends on the orientation of
the sun’s magnetic field.
A storm of mantle plumes is brewing deep within the Earth (NOVA transcript), threatening to
weaken this crucial magnetic defense, increasing levels of space radiation. Another vector is the
2013 peak of Solar Cycle 24. NASA suggests the intensity of geomagnetic storms during Solar
Cycle 24 may be elevated in some areas where the Earth's magnetic field is weaker than
expected. Such field anomalies have potential psychophysical effects on human populations, as
well as our technologies. Energetic events and ejections of plasma from the Sun cause dramatic
changes in the radiation belts and magnetic field of Earth, as well as fluctuations in Schumann
Resonance. Alpha brain rhythm (8-12 Hz) overlaps the Earth’s background frequency of 7-10
Hz, suggesting as many researchers have that our awareness is related to the rhythms of our host
planet, and perhaps a coupling of individual and universal consciousness. Such oscillations are
quantum time-keepers and bioregulators.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
659
Electrical engineer, Ben Lonetree has continuously monitored several geophysical parameters
over decades. His highly sensitive custom equipment outperforms government stations. He says,
"There is a reason why my system responds to many things other magnetometers do not. Most
are fluxgate mags that sample a collapsing field at a very slow sample rate. My system is simply
a very large induction coil that after the amplifier and filter stages couples into an analog to
digital converter. I have the converter programmed to use a sample rate of 240 times per second.
So the system sees every little blip there is out there."
He has conducted numerous experiments correlating local geophysical anomalies in earth's
magnetic field with EEG brainwaves of many subjects, and anecdotal reports of changes in
consciousness. Preliminary experiments were done as proof of concept with intent to investigate
the possibilities more deeply. Mentioned here, the results are covered in another article, “The
Sedona Effect”. The sun inductively couples to the earth and to humans. And human energy
fields inductively couple to other human fields. First we need an understanding of induction. We
can connect our bodies’ energy field to Earth's field which in turn connects to the sun and other
planets fields, which in turn can connect to the galaxy's core and beyond.
I. Geophysics
Introduction to Geophysics
A multidisciplinary science, Geophysics describes the physics of the Earth with quantitative
means, including gravity, heat flow, vibrations, electricity, magnetism, electromagnetic waves,
radioactivity, fluid dynamics, mineral physics, and its environment in space. Heliophysics is the
study of the Sun-Earth connection, commonly known as "space weather". We are learning more
about how space weather affects life on Earth
The Sun is a massive electromagnetic broadcaster which floods the planets of the solar system
with heat, light, UV radiation and electrically charged particles. The Sun itself has a magnetic
field that creates an "egg" around the solar system -- the heliosphere. The solar magnetic field
polarity (solar dipole magnetic field) reverses in 11-year cycles associated with sunspot activity,
peaking at solar maximum, in this Cycle 24 in 2013.
The Sun continues crackling with magnetic storms that may or may not spawn more Coronal
Mass Ejections (CMEs) aimed toward our fragile globe. Streams of high-energy, charged
particles rush from the sun to batter the Earth with protons and/or X-rays, and disrupt the
magnetosphere. The length of that disruption varies until the magnetosphere is drained of its
storm-time energy. Proton pulse events create spectacular aurora borealis displays as the
particles pass through Earth's orbit, concentrating their energy on the northern parts of our
planet.
NASA (Phillips) describes magnetic portals connecting the Earth and Sun as active and passive
"flux transfer events" (FTEs). The Earth-Sun connection is unsteady, often escalating to dynamic
bursts of energy. Magnetic fields in the magnetic cylinder twist and coil as the solar and earth
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
660
fields merge approximately every eight minutes. Computer simulations help us understand how
they work. Active FTEs let particles flow through conduits into Earth's magnetosphere. Passive
FTEs offer more resistance to flowing particles and fields.
Earth has had a variable magnetic field for at least 3.5 billion years, which NASA characterizes
as being in a "constant state of change". It is produced by convection currents of an electrically
conducting iron-nickel alloy in the liquid core, about 3,000 kilometers below Earth's surface. It
can be modified by emissions from the Sun, cosmic debris, and heat convection in the core of the
planet. In recent years the magnetic pole has been wandering more quickly. Compass needles are
drifting and the global magnetic field has weakened 10% since the 19th century.
At irregular intervals, averaging 300,000 years, the poles flip completely, but that is beyond the
scope of this paper. The magnetosphere is a generally a highly stable field, which can be
periodically inconstant, perpetually bombarded by energetically charged solar particles (solar
wind). A mass of charged particles can slam into our planet’s magnetic field, sending jolts of
electromagnetic energy shooting in all directions, causing what’s known as a geomagnetic storm.
For sensitive people in the right [or wrong] locales it may also lead to "brainstorms".
Powerful fountains spew away from the sun as solar flares or coronal mass ejections (CME). If
aimed at us, within hours they can bombard Earth with a shower of positively-charged hydrogen
atoms, called protons. Proton bombardment can cause scientific and communications satellites to
short-circuit. Highly sensitive people report dysphorias. Chemical reactions in the atmosphere
can drastically diminish the upper-most areas of the ozone layer that blocks life-threatening
ultraviolet radiation from reaching the Earth.
The Earth's magnetic field extends about 36,000 miles (58,000 km) into space. It can be treated
mathematically as a dipole field with a number of non-dipole elements. Generated from the
spinning effect of the electrically conductive core, it acts like a giant electromagnet. In
geologically ancient times, the field was 20 times stronger, but it has also been periodically
weaker or even absent. Movement of the liquid and the solid parts of the Earth's core generate an
electric potential, making the planet an electric generator. Regular daily and monthly fluctuations
in the GMF are affected by weather, the Moon, and sunspots.
Magnetism is a property of the atom itself. Ultimately, the magnetic properties of matter are
determined by the collective behavior of the negatively charged electrons that orbit the nuclei of
atoms. The magnetic dipole moment (or magnetic field) of an individual electron has two
components, one resulting from the spin of the electron about its own axis, the other from its
orbital motion about the nucleus. Both kinds of motion may be considered as tiny circular
currents (moving charges), thus linking electricity and magnetism at an atomic level.
Accelerator Mass Spectrometry (AMS) is a new ultra-sensitive single atom counting method that
reads the concentrations of the most relevant long-lived cosmogenic radionuclides. Forming an
archive of our earth, chronological deposits of such isotopes are found in trees, polar ice, lake
and deep sea sediments. AMS is virtually the only way to measure their concentrations.
Information about long term interval changes on solar activity, geomagnetic field and earth
climate can be obtained and collated.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
661
Turbulence & Polarity Transitions
The GMF is influenced by currents in the mantle on a time scale of tens to hundreds of millions
of years. Temperature patterns within the lower mantle influence both the stability and intensity
of the field. Massive changes in or on the Earth, including extinction events, follow a 26.6
million to 30 million year cycle over the last 250 million years. The solar system crosses the
relatively dense galactic plane every 30 million years. GMFs are implicated in some mass
extinction events.
Unexpected escalation of climate change demonstrates that perturbing natural cycles can lead to
cascades of cataclysmic change related by complex dynamics. Our climate is degrading much
faster than most of us thought. One small change can disrupt a system already in motion,
ultimately leading to cataclysmic results.
As early as 1906, changes in the magnetization of some rocks opposite to that of the present day
made it clear that some time ago it was different from the modern time. But, long before pole
reversal -- or more accurately, geomagnetic reversal -- we could expect escalating experiential
effects, based on effects we see during solar storms.
All kinds of mental and physical phenomena might fluctuate long before any ‘tipping point’. If
ecological cataclysm looms (Lovelock, 2009), geomagnetic cataclysm is also a possibility. The
Sun is also heating the interior of the earth, which increases volcanism and tectonic plate shift. It
is heating the whole solar system.
Many land and underwater volcanoes are located on or near subduction zones, rifts, and trenches,
associated with an increase of mantle plumes -- core heat rising to the surface. Large mantle
plumes build islands, even continents. The land is built, stretched and destroyed on volcanic rift
margins.
Compound dynamic forces have many effects:
Climate Change: Unexpected escalation of climate change demonstrates that perturbations in
natural cycles can lead to cascades of cataclysmic change related to complex dynamics.
Likewise for the ocean-conveyor, methane traps, and other threats to human survival. One small
change, such as mantle-held flux, can disrupt a system already in motion, ultimately leading to
cataclysmic results. Very little is known about the behavior of the magnetic field during the
transition from a superchron (long periods without reversal) to a mixed polarity state, though we
can imagine intense auroras surrounding the globe. Supernova gamma ray events, galactic
superwaves (Laviolette, 1986) and cometary showers have been linked with geomagnetic
excursions. Complex cycles of climate migration and Earth crust instability share 1) the sunearth relationship, embedded in the solar system, 2) solar heliopsphere and bow shock of
geomagnetic field, 3) Earth's connection to our galactic center plasma fields.
Polarity Intervals: Long before pole reversal -- or more accurately, geomagnetic reversal -- we
might plausibly expect an amplification of human experiential effects. Geomagnetic cataclysm is
only a possibility. In Australia around 28,000 B.P., a wandering di-pole event signaled sudden 3x
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
662
expansion of the magnetic field. Some postulate a geomagnetic excursion around 12,500 B.P.
that sent tribal villagers in the Levant back to nomadic life. (Mithen, 2004)
Paleomagnetosphere: Anomalous inclinations in the South Pacific are also recorded in the
geological record for 2,500 and 12,500 years ago. (Lund, et al) There is also evidence of highenergy particle bombardment at the same time, associated with extinction events. 12,000, 32,000,
43,000 and 70,000 yrs ago the reduced magnetic field rendered Earth especially vulnerable to
cosmic rays. Whether geomagnetic excursions admit cosmic radiation or the gamma blasts cause
the excursions is uncertain. There have been some indications that geomagnetic reversals may
occur astonishingly fast-- even within only a matter of months, according to one location of 16
million year old lava flows.
Magnetic Cataclysmic Variable: Geomagnetic reversal is chaotic in nature. Large oscillations of
directions precede or follow reversals, showing waveforms with amplitude amplified by the
decrease of the dipole. There is no apparent preferred location for the virtual geomagnetic poles
(VGP). Asymmetry between pre- and post-reversal phases is a dominant characteristic,
indicating the importance of field regeneration to initiate a new stable polarity interval. Virtual
Dipole Moments show as reversed (R) polarity, intermediate-normal-reversed (I-N-R) change
and subsequent normal (N) periods. There is no way we can predict it. Yet, it is a normal pursuit
of science to identify and extrapolate future scenarios, including geomorphology. The goal is to
anticipate and mitigate effects on humanity and the biosphere. We are challenged not by single
alterations but a complex confluence of unstable systems. This is not to say, “The End is
coming,” but to identify phenomena, which might arise along the way to major earth changes. It
is permissible to ask, "What if..."
Chaotic Dynamics: Geomorphological systems containing bifurcations have both deterministic
(universal and necessary) and probabilistic (historical happenstance) elements. They have more
than one solution (configuration) and this fact calls into question notions of process domains
leading to the development of characteristic forms. They possess varying degrees of
susceptibility to change induced by fluctuations. They respond differently to local, regional, and
global fluctuations. Geomagnetic Field (GMF) is one of these parameters. When meteor impact
occurs there may be a time lag from initiating event to actual field reversal of many thousands of
years. During part of the interim the field may measurably weaken down to a certain plateau.
Then, after perhaps more thousands of years have passed at or near the plateau, a relatively
sudden reversal may take place. Some evidence indicates extraordinarily rapid change of the
geomagnetic field during a reversal.
Intense Heat & High Pressure
Geomagnetic reversal is chaotic in nature. There is no way we can predict it. Polarity reversal is
connected heat convection in the mantle. The latest theory is that changes in heat flow from the
Earth’s core into the base of the overlying mantle leads to pole shifts. Heat-loss in the coremantle boundary drives the reversal. The mantle exerts a reciprocal control on the core.
Pole flip starts with short distance wandering of the north pole, to the extreme where magnetic
north dips below the equator, ending in full magnetic reversal. Dr. Andrew Biggin suspects that
True Polar Wander (TPW) changes the pattern of heat flowing out of the core.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
663
TPW is caused by the changing density distribution in the mantle. It changes the pattern of heat
flowing out of the core causing the magnetic field to first become less stable, with lots of
reversals, and then become much more stable – and stop reversing. It stabilizes when there are
less magma outpourings from the core.
South Atlantic Anomaly
The magnetic field occasionally flips over in its normal cycle. Reversals are random events. But
they are preceded by marked field fluctuations such as the South Atlantic Anomaly (magnetic
field intensity 60% of predicted value).
The South Atlantic Anomaly (SSA) is above South America, about 200 - 300 kilometers off the
coast of Brazil, extending over much of South America and the nearby portion of the Van Allen
Belt. It is a weak spot in the GMF, Earth’s protective bubble. The envelope here is 1/3 of normal.
As this field continues to weaken, the inner Van Allen belt gets closer to the Earth and proton
bombardment increases. There is an increased flux in this region.
Sudden fluid motions within the Earth's core can alter the magnetic envelope around our planet.
Researchers have just begun to detect such rapid magnetic field changes taking place over just a
few months.
The last major reversal in the field took place about 780,000 years ago. A flip in the north and
south poles typically involves a weakening in the magnetic field, followed by a period of rapid
recovery and reorganization of opposite polarity.
Some studies in recent years have suggested the next reversal might be imminent, but the jury is
still out. Weakening of Earth's overall magnetic field by 10 percent over the past 150 years might
also point to an upcoming field reversal. But it only happens about once in a million years.
Earth is a Dynamo
When the sun reaches deep into the earth, it "talks" to her and modifies the generator within her.
The ionosphere is one poorly understood channel. The sun interacts magnetically with the solid
Earth, reaching down into the crust, generating forces that can trigger earthquakes that either
rupture or slide.
Before major earthquakes, the crust "talks" back to the ionosphere, causing perturbations.
Magnetic field maxima and minima move around over the surface of the earth. The total amount
of coupling changes over time. Electrochemical loops cross, increasing quake likelihood.
Earth itself acts as a magnet. Minerals in the earth’s crust contain dormant electronic charge
carriers. They act like electronic crystals when energized. Squeezing, heating or stressing such
rocks activates them so they can travel through the earth for kilometers changing conductivity,
generating Lorenz force interacting with tectonic force vectors, pushing the system over the
edge. Rapid magnetic field variations lead to ULF emissions. They ionize the plasma in the
atmosphere, measurably perturbing the ionosphere, the coupling mechanism.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
664
Earth constantly generates ULF emissions. Life evolved in this ULF field. The fundamental
Schumann Resonance is a standing wave in the atmosphere around 8 Hz. The human brain emits
frequencies in the same region. Up to 12-14 days before a quake, broadband ULF emissions
before major earthquakes can swamp the whole ULF spectrum, affecting the brains and circadian
rhythms of animals and humans. Currents may be higher in highly mineralized areas with
crystalline basement rock, such as Sedona, Arizona.
Stressed rocks are active charge carriers which turns them into batteries. The driving force is
deep magma and tectonic strain. Electric currents, up to millions of amperes, start to flow like in
a semiconductor battery, perturbing earthquakes. Currents up to millions of amperes flow along
stress gradients, fluctuating and emitting EM radiation. Therefore, Earth emits powerful
broadband EM waves prior to quakes, in microhertz to about 20 hz. extremely low frequencies
(ULF).
Paleomagnetic records show that the dipole polarity of the geomagnetic field reversed many
times in the past. Convection in the fluid outer core is continually trying to reverse the field.
However, the solid inner core inhibits magnetic reversals because the field in the inner core can
only change on the much longer time scale of diffusion. Only once in many attempts is a reversal
successful. This is probably the reason the times between reversals of the Earth's field are long
and randomly distributed.
Geophysics
Scientists from the Institute for Geomagnetism at the Russian Academy of Sciences say the
magnet poles are gradually drifting towards the Equator, reaching zero point in about 2,000
years, which would be a disaster for living organisms. The rate of change in the planet's liquid
core, however, means that the shift could happen much sooner.
In 2001, an international polar expedition revealed that in seven years the North magnetic pole
shifted around 300 km (186.4 miles). Currently, it is drifting 40 km (24.85 miles) a year from the
Canadian Arctic shelf towards Russia's Severnaya Zemlya Islands. Scientists predict the North
Pole could eventually be found in the South Atlantic.
Russian scientists say dangers include anti-radiation protection falling, with space flights
becoming impossible and energy-dependent systems, including mobile phones and satellites,
failing. Then, solar and space radiation would affect the genome of the organisms inhabiting the
Earth, causing some of them to become extinct, while others mutate at a higher rate. With
extremely powerful electrojet currents, life may become impossible on Earth before the full
magnetic field collapses.
In the last 90 million years, the magnetic poles changed around every 500,000 years, with no
total extinction or mass genetic mutations of living organisms taking place. The atmosphere
remained a reliable steward of Earth's biosphere.
Pole Reversal
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
665
We know about pole shift from an examination of the geological record -- the magnetic poles
reverse without the axis of the Earth flipping in any way. We can read the evidence of many
magnetic reversals in the relentless march of the seabed floor. Valkovic links massive faunal
extinctions with polarity reversals in earth’s geomagnetic field. He assumed that the
concentration factor for essential trace elements is dependent on the magnetic field.
When lavas are deposited on the Earth’s surface, and subsequently freeze, and when sediments
are deposited on ocean and lake bottoms, and subsequently solidify, they often preserve a
signature of the ambient magnetic field at the time of deposition. This type of magnetization is
known as 'paleomagnetism'. Sediment samples from Chalco Lake, Mexico "shows low frequency
components with characteristic periods of 10,500, 3200–3400, 2900–3000, 1400–1500 and 800–
900 years. In phase oscillations of inclination and intensity records point to drifting non dipole
field anomalies." (B. Ortega-Guerrero and J. Urrutia-Fucugauchi, 1997)
Careful measurements of oriented samples of faintly magnetized rocks taken from many
geographical sites allow scientists to work out the geological history of the magnetic field. We
can tell, for example, that the Earth has had a magnetic field for at least 3.5 billion years, and that
the field has always exhibited a certain amount of time-dependence, part of which is normal
variation. An occasional reversal of polarity also occurs spontaneously in 3D computer models
of the Geomagnetic Field. A similar reversal happens to the Sun every 11 years.
The geomagnetic poles are currently roughly coincident with the geographic poles, because the
rotation of the Earth is an important dynamical force in the core, where the main part of the field
is generated. Occasionally, however, the variation becomes sufficiently large so the magnetic
poles end up being located rather distantly from the geographic poles. The poles have undergone
an ‘excursion’ from their preferred state.
We know from physics that the Earth’s dynamo is just as capable of generating a magnetic field
with a polarity like that which we have today, as it is capable of generating a field with the
opposite polarity. The dynamo has no preference for a particular polarity. Therefore, after an
excursional period, the magnetic field, upon returning to its usual state of rough alignment with
the Earth’s rotational axis, could just as easily have one polarity as another.
The consequences of polarity reversals for the compass are dramatic. Nowadays, the compass
points roughly north, or, more precisely, the north end of the compass points roughly north at
most geographical locations. However 780,000 years ago, the polarity was reversed, so a
hypothetical compass pointed roughly south. Before that reversed state the polarity was like that
which we have today, and the compass would have pointed roughly north, and so on. The
timings of reversals forms the so-called 'geomagnetic polarity timescale'.
During a reversal the geometry of the magnetic field is much more complicated than it is now. A
compass could point in almost any direction depending on one’s location on the Earth and the
exact form of the mid-transitional magnetic field. There is no apparent periodicity to reversals.
They are random events, happening as often as every 10 thousand years or so, and as
infrequently as every 50 million years or more.
Antimatter
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
666
NASA discovered in 2003 that solar explosions produce antimatter that is projected in CMEs
exploding from the sun's surface. Antimatter is created in flares when the fast-moving particles
accelerated during the flare collide with slower particles in the Sun's atmosphere, producing it in
one location and destroying it in another. (NASA)
In a private letter (June 10, 2011), engineer Tom Bearden does not assume a connection between
solar radiation and potential pole reversal: The earth's magnetic field, as any EM field energy,
originates directly in the virtual state vacuum because of the proven broken symmetry of the
earth's magnetic dipolarity. This means that, as long as the poles exist, then the earth's magnetic
dipole will freely absorb virtual energy from the seething vacuum, integrate it to quantum size,
and pour out real observable magnetic field energy steadily and without cessation.
Anything that breaks that ironclad law would have to rather totally destroy the earth's two
opposing magnetic poles. To destroy such monstrous poles, the effect would first have to be
destroying jillions of minor subordinate dipoles throughout the earth, etc. I know of nothing in
history that indicates such a calamity from the solar eruption. That doesn't mean it could not
exist; but just that -- if it does exist -- it would be just about the most highly unusual thing that's
ever been and I therefore have no knowledge of it.
Perhaps supporting that notion, a thin belt of antimatter, "antiproton radiation belt", or an
"antimatter reservoir" was discovered (2011) in our upper atmosphere. Antiprotons, the
antimatter version of protons, are formed naturally in interstellar space. Similar to what happens
in high-energy collisions in accelerators, cosmic rays colliding with nuclei in the upper
atmosphere create new particles, including pairs of protons and antiprotons. Most rapidly
annihilate but those escaping interaction with ordinary matter may get trapped in Earth's
geomagnetic field as the probe PAMELA (Payload for Antimatter Matter Exploration and Lightnuclei Astrophysics) discovered. The flux of antiprotons in this region is three order of
magnitude higher than in interstellar space.
The big break came from an area known as the South Atlantic Anomaly, which is a region of
space where the Van Allen Radiation Belts are the closest to our surface. . . The International
Space Station requires extra shielding just to protect its astronauts as it passes through it, and
the Hubble Space Telescope has to be turned off every single time it passes through the
anomaly...which is multiple times daily. [T]he PAMELA team [declared] the South Atlantic
Anomaly "the most abundant source of antiprotons near the Earth." (Adriani)
The existence of a significant flux of antiprotons confined to Earth's magnetosphere has been
considered in several theoretical works. These antiparticles are produced in nuclear interactions
of energetic cosmic rays with the terrestrial atmosphere and accumulate in the geomagnetic field
at altitudes of several hundred kilometers. A contribution from the decay of albedo antineutrons
has been hypothesized in analogy to proton production by neutron decay, which constitutes the
main source of trapped protons at energies above some tens of MeV. . . . PAMELA data show
that the magnetospheric antiproton flux in the SAA exceeds the cosmic-ray antiproton flux by
three orders of magnitude at the present solar minimum, and exceeds the sub-cutoff antiproton
flux outside radiation belts by four orders of magnitude, constituting the most abundant source
of antiprotons near the Earth. (Adriani)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
667
But a second pathway that involves a few more steps produces the majority of these particles in
our planet's vicinity. Small numbers of neutrons (neutrally charged particles) escape the upper
atmosphere, where they first decay into protons that are captured by the Earth’s magnetic field.
Following collisions with cosmic rays, these protons produce antineutrons (in pairs with
neutrons), that then decay into antiprotons. These antiprotons will remain held in orbit until they
collide with normal matter and are annihilated; they typically travel distances of several Earth
radii before this happens. (Niemeyer)
(Source: Credit: NASA's Goddard Space Flight Center/J. Dwyer, Florida Inst. of Technology
http://www.nasa.gov/pdf/509357main_Trio_noshadow_300dpi.pdf)
NASA also discovered thunderstorms may be producing antimatter "particle beams" in the upper
atmosphere. Scientists think the antimatter particles were formed in a terrestrial gamma-ray
flash (TGF), a brief burst produced inside thunderstorms and shown to be associated with
lightning. It is estimated that about 500 TGFs occur daily worldwide, but most go
undetected. (NASA 2011)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
668
The Earth's mantle plays a role in controlling the frequency of magnetic field reversals. Heat flux varies
across the core-mantle boundary. http://seismo.berkeley.edu/~rallen/eps122/lectures/L07.pdf
Geodynamics & Geomagnetic Excursions
We are only beginning to understand the potential sets that influence geodynamic cycles and
anomalies. Our globe is a self-exciting dynamo coupled to fluid motion in the Earth's outer core
through magnetohydrodynamics involving heat transfer and convection. Thermal and
compositional buoyancy causes flow. The magnetic field is generated and regulated by outer
core flow.
Clearly, much remains for us to learn about the nuances of geophysics, much less its effects on
our psychobiology. We don't know what happens to the human organism under reduced field
strength and global magnetic chaos. Mean human expansion time is approximately 40,000 years
ago. It also marks a time of potential interbreeding with Neanderthals and perhaps Devisova
Hominin.
But, 40,000 Years Ago a trifecta of catastrophes impacted the globe: Climate Shifts,
Geomagnetic Field Reversal and a Super Volcano. Scientists have probed the link between
magnetic polarity reversal and heat in the planet’s interior. Mega-magma plumes underlying
supervolcanoes arise from increased heat flow from the earth's core -- the changing pattern of
heat loss across the core-mantle boundary. Supervolcanoes can have global catastrophic effects
comparable to major meteorite impacts. The Campanian Ignimbrite super-eruption took place
39,000 years ago, decimating vast stretches of the Mediterranean.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
669
41,000 years ago, say the researchers, a complete and rapid reversal of the geomagnetic field
occurred. Along with the Black Sea sediment cores, they look at other studies in the North
Atlantic, the South Pacific and Hawaii, and say it proves that this polarity reversal was a global
event. (Science 2.0)
Researchers discovered numerous abrupt climate changes during the last ice age locked in cores
from the Black Sea, and already known from the Greenland ice cores. Synchronizing the Black
Sea and Greenland data reveals the largest volcanic eruption on the Northern hemisphere in the
past 100,000 years. A supervolcano erupted 39,400 years ago near Naples, Italy, as documented
in the Black Sea sediment.
Forty thousand years ago Earth's shields went down in a geomagnetic excursion called the
Laschamp Event. The field was only 5% of today's strength. For 440 years it was associated with
a field strength that was only one quarter of today's field. The actual polarity changes lasted 250
years. The Earth nearly lost its protective shield against hard cosmic rays, leading to significantly
increased radiation exposure, as revealed in ice cores. High-energy protons from space collided
with atoms of the atmosphere.
Naturally, genes mutate all the time, but increased exposure to cosmic rays increases such
likelihood. Mutations can be useful, harmful or neutral in their effects. Most simply turn genes
off. Did such radiation produce reproductive challenges? Some believe the red hair mutation first
appeared between 38,000 to 18,000 B.C. in Europe. Environmental variables related to
latitudinal variation, such as species richness and mean annual temperature, may have influenced
adaptation.
Arguably, the boundary between the Middle and Upper Palaeolithic marks the transition to fully
modern humans. There may or may not be causal links to cosmic bombardment, but around the
same era, some theorize mutations occurred in human bloodtypes, and "The Leap" in intelligence
(40-45Kya). Language, creative and technological innovation increased dramatically. Homo
sapiens extended its population to Europe, Asia and Australia about 40,000 - 50,000 years ago.
Also, 40,000 to 45,000 years ago some groups migrated from the Levant back to Africa as well
as toward Europe. Genetic mapping shows that a mutation from RH positive to RH negative
occurred somewhere in the Basque area of Europe maybe as much as 40,000 years ago.
Cro-Magnon man appeared approximately 40,000 years ago. European-Asian groups diverged
40,000 years ago. Ancient DNA reveals humans living 40,000 years ago in the Beijing area are
related to present-day Asians and Native Americans. For the Chinese, Korean, and European
genomes, effective population size fell from about 13,500 (at 150,000 years ago) to about 1200
between 20,000 and 40,000 years ago. Hunting bands found their way to Australia between
40,000 and 30,000 years ago. Art and music were born suddenly, about 40,000 years ago, in Ice
Age Europe. The earliest evidence for personal ornaments appeared in anatomically modern
humans about this time.
There were other local stressors including glaciation, drought, and climate change. About 40,000
years ago in what we now call Italy and the Caucasus Mountains, which straddle Europe and
Asia, several volcanoes erupted in quick succession. It's likely the eruptions reduced or wiped
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 6 | pp. 657-670
Miller, I., Geomagnetics & Consciousness: Geomagnetic Field Effects & Human Psychophysiology (Part I)
670
out local bands of Neanderthals and indirectly affected farther-flung populations, a team
concluded after analyzing pollen and ash from the affected area. The researchers examined
sediments layer from around 40,000 years ago in Russia's Mezmaiskaya Cave and found that the
more volcanic ash a layer had, the less plant pollen it contained. (Than, 2010)
If mankind was able to make such quantum leaps during environmentally chaotic times, perhaps
that bodes well for our adaptive future. Life and culture appears to be quite different before and
after 40,000 years ago. Whatever complex forces drove it this was a cultural Big Bang that seems
to coincide with the most recent geomagnetic excursion. Paradoxically, we might not have
expected magnetic chaos to have any positive effect on our organism, but the total environment
may have created a unique psychobiological challenge for our species.
(Continued on Part II which also contains the references)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
arXiv:2005.02801v1 [cs.AI] 4 May 2020
A N ON - EQUILIBRIUM T HERMODYNAMIC F RAMEWORK O F
C ONSCIOUSNESS
Natesh Ganesh
ITL, App. & Comp. Mathematics Division, NIST
Dept. of Physics, University of Colorado, Boulder, CO
natesh.ganesh@colorado.edu
May 7, 2020
A BSTRACT
In this paper, we take a brief look at the advantages and disadvantages of dominant frameworks
in consciousness studies - functionalist and causal structure theories, and use it to motivate a new
non-equilibrium thermodynamic framework of consciousness. The main hypothesis in this paper
will be two thermodynamic conditions obtained from the non-equilibrium fluctuation theorems TCC 1 and 2, that the author proposes as necessary conditions that a system will have to satisfy in
order to be conscious. These descriptions will look to specify the functions achieved by a conscious
system and restrict the physical structures that achieve them without presupposing either of the two.
These represent an attempt to integrate consciousness into established physical law (without invoking
untested novel frameworks in quantum mechanics and/or general relativity). We will also discuss
it’s implications on a wide range of existing questions, including a stance on the hard problem. The
paper will also explore why this framework might offer a serious path forward to understanding
consciousness (and perhaps even realizing it in artificial systems) as well as identifying some problems
and challenges that lie ahead.
1
Introduction
Consciousness continues to be of one of the most important, interesting and complex question to focus upon. While the
study of consciousness has a long and rich history in the field of philosophy, the scientific study of consciousness has
become less taboo recently, and made tremendous progress in the field over the last couple of decades, due to significant
contributions from disciplines like neuroscience, cognitive science and computer science. Though research interests
have continued to grow, fueled by the recent artificial intelligence/machine learning (AI/ML) revolution (reigniting
questions around artificial consciousness), the topic of consciousness itself has generally been ignored or dismissed by
a majority of those who work in mainstream AI as either an unimportant factor for their research goals or accusing
work in (artificial) consciousness as distracting flights of fantasy.
It seems as this trend might change in the near future as leaders in the field of AI recognize the importance of mechanisms
of higher level cognition for making progress in AI, their relationship to the ’easy problems’ of consciousness and the
important work that has been conducted in the field of cognitive science to understand these better (Yoshua Bengio’s
keynote address at NEURIPS 2019 being an important example of this [1]). While this might not satisfy those who are
interested in the phenomenal aspects of our conscious experience, it represents a step forward in the right direction
by the larger AI community. In keeping with the (beginnings of a) trend, the author will look to make the case for a
non-equilibrium thermodynamic framework of consciousness, it’s relationship to the field of AI and the crucial role that
computer hardware engineers might have to play in the scientific study of consciousness.
The author would like to take a brief moment (to digress) and explain the journey towards these ideas, hoping that
it would elucidate their motivations as an engineer to study and understand the field of consciousness from a more
physics based approach. The author’s primary research interests lie in the field of artificial intelligence and was lucky
A PREPRINT - M AY 7, 2020
enough to be working on his PhD when the field of machine learning became extremely popular. The availability of
large amounts of data and cheap compute (in the form of powerful GPU hardware) is one of the driving forces behind
this deep learning boom. The demand for compute to train larger and larger models in AI is doubling every 3.5 months
(an unprecedented ‘super-Moore’ rate) [2], a trend that has shown no sign of slowing down. This comes at a time when
Moore’s law [3], which powered the first computer revolution has significantly slowed down (and Dennard voltage
scaling [4] has completely broken down) as we approach the fundamental physical limits to scaling. This represents a
massive problem for state of the art deep learning techniques, some of which that consume a few GWh’s of energy (this
would be in the ballpark of the amount of energy produced by a nuclear power plant in an hour) to achieve that level of
performance on narrow tasks [5]. While these ideas represent massive successes in our quest for building systems that
can solve intelligent tasks, they are still a far-cry from the human brain in terms of performance across tasks and energy
efficiency. If the human brain remains the holy grail in AI, then we would be remiss to ignore the fact that human brains
have consciousness associated with them, dismissing that aspect of it as irrelevant simply because we can compute
the functions associated with intelligence, albeit in a inefficent manner. Engineering energy efficient AI hardware is
crucial to continue our progress in the field. As we look to build new types of hardware that mimic the human brain,
it is necessary to understand the relationship between physical law (that produced human brains), intelligence and
consciousness (human or artificial) and the energy efficiency of the hardware realization.
The rest of this paper is organized as follows - In section 2, we will take a very brief look at two very popular
frameworks in consciousness - functionalist and causal structure theories, and some of their advantages and drawbacks.
In section 3, we explore what might be some necessary conditions for consciousness and propose why thermodynamic
descriptions might provide an appropriate language to describe consciousness. In section 4, we introduce nonequilibrium thermodynamic and provide a brief summary of how the fluctuations theorems are related to information
processing operations. In section 5, we use the results from the previous section propose two thermodynamic conditions
for consciousness TCC1 and TCC2. In section 6, we list a set of important observations about the implications of TCC2.
In section 7, we explain the philosophical stance the thermodynamic framework takes towards the hard problem of
consciousness. In section 8, we discuss a couple of immediate challenges that are apparent with the framework (and
need to be solved) and then move on to the possibility of machine consciousness in section 9, the role of AI hardware in
consciousness and finally conclude in section 10 summarizing the ideas in the paper and painting a picture of the path
forward.
2
Philosophical Frameworks of Consciousness
There are a number of rich philosophical frameworks of consciousness that ground the popular theories of consciousness
like Global Workspace Theory (GWT), Integrated Information Theory (IIT) and Higher Order (HOT) theories. Specifics
in the theories themselves are not the focus of this work and a detailed account of GWT, IIT and HOT can be found at
[6], [7] and [8] respectively. We will instead discuss the popular philosophical frameworks that underlie our study of
consciousness currently - the functionalist picture (as is the case in GWT) and causal structure theory (for IIT).
Functionalism Chalmers defines functional organization as the following [9] - “This is best understood as the abstract
pattern of causal interaction between the components of a system, and perhaps between these components and external
inputs and outputs. A functional organization is determined by specifying (1) a number of abstract components, (2) for
each component, a number of different possible states, and (3) a system of dependency relations, specifying how the
states of each component depends on the previous states of all components and on inputs to the system, and how outputs
from the system depend on previous component states. Beyond specifying their number and their dependency relations,
the nature of the components and the states is left unspecified. A physical system realizes a given functional organization
when the system can be divided into an appropriate number of physical components each with the appropriate number
of possible states, such that the causal dependency relations between the components of the system, inputs, and outputs
precisely reflect the dependency relations given in the specification of the functional organization. A given functional
organization can be realized by diverse physical systems. For example, the organization realized by the brain at the
neural level might in principle be realized by a silicon system.” Levin defines functionalism as - “In the philosophy
of mind is the doctrine that what makes something a mental state of a particular type does not depend on its internal
constitution, but rather on the way it functions, or the role it plays, in the system of which it is a part.” [10]. According
to Putnam’s machine state functionalism [11], “any creature with a mind can be regarded as a Turing machine (an
idealized finite state digital computer), whose operation can be fully specified by a set of instructions (a ’machine table’
or program) each having the form: If the machine is in state Si , and receives input Ij , it will go into state Sk and
produce output Ol (for a finite number of states, inputs and outputs). On either model, however, the mental states of a
creature are to be identified with such ‘machine table states’ (S1 , S2 , . . . , Sn ). These states are not mere behavioral
dispositions, since they are specified in terms of their relations not only to inputs and outputs, but also to the state of the
machine at the time” [10].
2
A PREPRINT - M AY 7, 2020
Causal Structure Theory On the other hand, in causal structure theories, we have the ”essential element for
understanding consciousness is how parts of a system interact. If a system has the ‘right’ kind of causal structure,
in other words, if it’s elements interact in the ‘right’ way, it is conscious. Otherwise, it is not.” [12]. Advocates of
IIT start from axioms derived from human consciousness and argue that the causal structure of the system (realizing
the function) is also important on top of the function [7], [13] (though it seems like the input-output function being
realized, while useful is not central to IIT). Thus advocates of IIT look to use the knowledge of the recurrent structure
that underlies human consciousness. IIT distinguishes on the level of consciousness between say a feed-forward and
recurrent neural network that might implement the same function (while functionalism does not). IIT predicts the
recurrent network with non-zero φ to be conscious, and the feedforward network with φ = 0 to be non-conscious. As in
the case of functionalism, there have been many arguments both for and against this framework [12], [13], [14], [15],
[16]. There is also interesting new work in studying contents of experience using category theory in IIT [17].
3
What do we want from a description of Consciousness?
A central endeavor in science is to produce descriptions of physical systems that have both explanatory power of existing
observations and provide testable predictions that can be used to falsify the framework. Descriptions vary at the level at
which they are most useful at and often use different vocabularies. Physics, chemistry, biology, computation, etc can
all be viewed as providing descriptions of physical systems at different resolutions. We can view the functionalism
and causal structure frameworks similarly as looking to provide descriptions of consciousness in physical systems at
different ’levels.’ IIT proponents view CST as an improvement on functionalism since they use the extra information of
the causal structure in the human brain (which one can safely assume is necessary for human consciousness) on top of
the system’s input-output relationships to build a better descriptive model [18]. We can now ask the following question what is it that we want from a description of consciousness?
We will start building towards this description using ‘some possible necessary conditions for consciousness’ prescribed
by Scott Aaronson recently [19]
(A1) Intelligent behavior (passing some sort of Turing test).
(A2) Unpredictablity to outside observers, ability to surprise.
(A3) “Not being a giant lookup table or Boltzmann brain.”
(A4) “Full participation in the thermodynamic Arrow of Time” (Constantly amplifying microscopic degrees of
freedom into permanent records).
The goal of these conditions for consciousness is to identify systems which are capable of satisfying these conditions
and hence considered to be conscious (An approach similar to IIT). The main takeaways from these initial conditions
setup by Aaronson would be that both function and the structure of systems matter in the science of consciousness, as
well as it’s participation in physical law (as prescribed by the arrow of time). IIT in fact does appeal to the importance
of structure of the system that realizes particular functions. However they use the phenomenological experience of
human consciousness to identify properties of the physical structures that can realize it, to develop their framework and
the measure φ quantify the level (amount) of consciousness in any system. This complexity like φ measure might end
up being too broad and predict a large amount of consciousness in systems like a grid of XOR-gates [16], [20], [21] and
might be impossible to experimentally verify without pre-supposing the framework to be true 1 [12]. Functionalism too
suffers from similar issue since it prescribes mental states based on the functions a system implements, irrespective of
the structure that realizes those functions. This would allow for consciousness (to varying degrees) in a very broad
range of systems - even though as the result of evolution, the widely accepted conscious entities are biological systems
with recurrent neural structures. Kleiner also discusses the issues around both functional and causal structure models,
defining consciousness based on static states of a physical systems, rather than as a dynamic trajectory (of states) over
time [22].
Another set of possible necessary conditions for consciousness were proposed by Max Tegmark in [23]. He took
a physics point of view towards the problem of consciousness and looked to reduce the question - why are some
arrangements of matter conscious? (Science is never good with why questions) to what arrangements of matters are
conscious?. These conditions from [23] were 1
This can be avoided by stating that IIT is a theory of human consciousness only. It assumes humans are conscious, uses this
assumption and the structures in the conscious human brain to define measures like φ that is correlated to the amount of consciousness
in humans. Statements on the consciousness of systems like grid of XOR gates, feedforward and recurrent neural networks should be
viewed more as speculation and not as predictions of the framework. In fact, some proponents of this theory like the authors of [13]
seem to be defending this weaker version, while others view it as a theory of consciousness in all system leading to confusion in
understanding what exactly the claims and testale predictions of IIT are.
3
A PREPRINT - M AY 7, 2020
(T1) Information principle - A conscious system has substantial information storage capacity.
(T2) Dynamics principle - A conscious system has substantial information processing capacity.
(T3) Independence principle - A conscious system has substantial independence from the rest of the world.
(T4) Integration principle - A conscious system cannot consist of nearly independent parts.
(T5) Autonomy principle - A conscious system has substantial dynamics and independent.
(T6) Utility principle - An evolved conscious system records mainly the information useful to it.
We can clearly see the overlap between these conditions (T1)-(T6) and (A1)-(A4). All of the above conditions look
reasonable except for (T3), which implies that the system dynamics is dominated by forces from within rather than
outside the system. The author is not entirely sure of the necessity of such a condition and would rather assume that
system dynamics is dependent on forces both inside and outside the system. Tegmark’s framework introduced the
idea of perceptronium - the most general substrate that is subjectively self-aware [23]. Viewing consciousness as a
fundamental state of matter implies that this framework takes a panpsychist position on consciousness (and thus will
suffer from the combination problem [25]).
In order to move towards an improved description of consciousness that could be extended to systems beyond humans,
whose consciousness status is not known beforehand, we have to parse out what such a description would have to
achieve (and what IIT strives for). IIT starts from properties of our phenomenological experiences and derives properties
of the physical systems that are required to achieve those experiences. These properties are tied to the recurrent causal
structures in the human brain that produces consciousness which is measured by the quantity φ (Of course IIT then
extrapolates and assumes consciousness in all systems has to be linked with causal structure without providing sufficient
explanation on why the conscious experience of say a large XOR grid should be anything like our own and thus require
similar structures). We would thus want a description of consciousness in a physical system to predict both some
input-output functions (intelligent behavior) that we expect a conscious system to exhibit and specify the structure(s) a
conscious system could employ to realize this behavior, without implicitly assuming either of them in the descriptive
conditions. Thus if a framework is set up such that it provides a descriptive condition for consciousness that explains
the input-output functions associated with conscious humans and the specific recurrent structure of the human brain
that realizes these conditions, then such a framework can be considered as the step forward from the causal structure
theories (and consequently functional theories as well). The author will refer to this underlying philosophical position
as constrained functionalism - where only particular physical realizations of specific functions are hypothesized to be
conscious with the constraints imposed by suitable choice of description (rather than all realizations of that function i.e.
functionalism). Notice how this picture goes beyond functionalism by restricting certain realizations of a function from
being conscious. It does not rule out certain types of structures like causal structure theories do through underlying
assumptions based on the biological picture.
The next question would obviously be - what are the characteristics of the description for such a framework of
consciousness? The characteristics will obviously also imply the level or resolution at which the description operates
at. The title of the paper indicates the direction the author wishes to take, but we will work our way towards that
answer by teasing out these characteristics that we would want in such a general description of consciousness. Here is a
non-exhaustive list that the author will build upon (that are similar to Aaronson’s criterion above)
(N1) As discussed above the description should predict for both functions exhibited by platinum-standard conscious
systems [24] and constrain the structures that realize those functions (as in Aaronson’s criterion (A1) and
(A3)). For example: the description should be able to predict the function and structure with respect to humans,
without assuming either.
(N2) The descriptions need to strike a fine balance between able to discuss computation in an implementation
independent manner (like computational/functional descriptions do) without being overtly broad and placing
absolutely no constraints on the type of systems that realize those functions (unlike CST which does place
some but perhaps not enough restrictions on the causal structure of the implementation) i.e. constrained
functionalism. Both functionalism and causal structure frameworks operate at an abstracted level in order to
apply broadly across different systems and avoid the challenges faced by psycho-physical identity theories.
However this level of abstraction also comes with it’s own setbacks.
(N3) A good description of consciousness should be tied into established physical law (as in (A4)) and tie into
explanations on why accepted conscious systems (like humans, some animals perhaps) have the structure and
functions that they do i.e. the evolutionary processes that produced these systems. An important question here
would be the need to understand why certain carbon-based organic structures are the material of choice to
realize biological consciousness. While a description of consciousness might allow for consciousness to be
realized with other material, it has provide this explanation for living systems as well as be able to determine if
certain materials simply cannot form the basis of conscious systems under conditions of interest.
4
A PREPRINT - M AY 7, 2020
(N4) A macroscale coarse grained description on which consciousness emerges. We use the term emergence in
the weaker epistemic sense - where a macroscropic coarse-grained description is emergent if it has greater
predictive power than the microscopic fine-grained description. This implicitly also assumes that only
systems with a certain degree of complexity (memory) are systems in which we could discuss with respect to
consciousnesss (for eg: an electron cannot be conscious since it is not capable of memory) 2 .
With the above criterion (N1-N4) in place, the author will propose that non-equilibrium (NE) thermodynamics can
provide a suitable description of consciousness in physical systems because (a) NE thermodynamics can provide a macroscale description of a system that is applicable to all physical systems
(irrespective of the substrate or implementation). But not all physical systems are capable of satisfying every
specified thermodynamic condition.
(b) Concepts of information and entropy are already defined and tied to physical quantities such as free-energy
and dissipation in thermodynamics (through concepts such as Landauer’s Principle). And ofcourse the field of
thermodynamics was built to address notions of energy efficiency.
(c) It is tied to physical law, with the 2nd law of thermodynamics fundamentally corresponding to the arrow of
time. Furthermore the laws of thermodynamics can provide no-go conditions (like perpetual motion machines
for example).
(d) NE thermodynamics can deal with dynamic trajectories (of states) in open systems over time as opposed to
equilibrium thermodynamics which tend to focus on the states of (closed or isolated) systems at equilibrium.
This will help address some of the concerns raised in [22]. Biological systems are ultimately self-organized
open systems and are best described by non-equilibrium formulations in thermodynamics.
(e) It can be mapped onto a wealth of existing work that has already been performed in the area of neuroscience (predictive processing, free-energy principle) as well as machine learning (Boltzmann and Helmholtz
machines).
The author will next proceed over the next few sections to introduce the non-equilibrium fluctuation theorems and use it
propose some necessary conditions for consciousness in physical systems.
4
Non-equilibrium Thermodynamics, Fluctuation Theorems, Memory & Prediction
Thermodynamics is the branch of physics that deals with heat and temperature, and their relation to energy, entropy,
work, radiation, and properties of matter. It was first developed to determine and improve the efficiency of steam
engines by Nicolas Carnot in 1824. Since then the field has evolved tremendously and become a cornerstone in modern
physics. A detailed introduction to thermodynamics is available in this excellent book by Kondepudi and Prigogine
[26]. Most of the early work has been focused on systems evolving to thermal equilibrium (which is characterized by
minimization of a free-energy term in isolated and closed systems). At equilibrium, the probability of microstate i
((p(i)) is given by the Boltzmann distribution
1
p(i) = Z(β)
e−βEi
where Ei is the energy of the i-th microstate, β = kB1T is the inverse temperature for bath temperature T and Boltzmann
X
constant kB . Z(β) is the partition function used to normalize the probabilies and given by Z(β) =
e−βEj .
j
Non-equilibrium thermodynamics which deals with systems not in equilibrium is a much younger field with initial
work produced by Lars Onsager [27], [28] on reciprocal relations and Ilya Prigogine [29] on dissipative structures. The
field has gone through an incredible revolution in the last few decades as we have moved away from the inequality
versions of the 2nd law towards a more general non-equlibrium equality relationships. Some of the most important
work in this area has come from Jarzynski [30] and Crooks [31]. Unlike equilibrium thermodynamics which focuses on
the states of systems, the fluctuation theorems provide relationships between the probability of forward and reverse
trajectories of microstates over a time interval τ with the heat dissipated into the bath ∆Qbath at temperature T . The
relationship can be stated as below
2
Not all complex systems are necessarily conscious. Frameworks that attribute emergence of consciousness to simply increasing
complexity tend to be overtly broad and not necessarily the path forward. Some have argued that IIT’s φ measure is correlated to the
complexity of the system and thus ends up attributing arbitrarily large amount of consciousness to a sufficiently complex systems
like a large XOR grid in a counter-intuitive manner.
5
A PREPRINT - M AY 7, 2020
Figure 1: Dynamical irreversibility and heat production - The probability of observing a specific sequence of
configurations for a system driven with a particular pattern of time-varying field (large arrows) while in contact with a
heat reservoir has a set ratio to the probability of observing the time-reversed sequence of events under a time-reversed
drive. In particular, these two probabilities differ by an exponential factor of the heat released into the reservoir (∆Q;
small arrow) when the system is driven according to the pattern corresponding to the ratio’s numerator [34].
π(γ; τ )
= exp [β∆Qbath (γ)]
π(γ ∗ ; τ )
(1)
where π(γ; τ ) is the probability of the forward trajectory (of microstates) γ as the system is driven in time τ (refer
to Fig.(1) where γ = i → j → k). π(γ ∗ ; τ ) represents the probability of the reverse trajectory. β is the inverse
temperature and ∆Qbath (γ) is the heat dissipated into the bath on the forward trajectory. The left-hand side in Eq.(1)
indicates the irreversibility between the reverse and forward trajectories, and it’s relationship to the heat dissipated into
the bath. It is thus a generalization of the second law of thermodynamics. It is important to note that this relationship is
valid for any transition between two microstates. Note that when the system is in thermal equilibrium, the probability of
forward and reverse trajectories of microstates become nearly equal and we can obtain the Boltzmann distribution for
the microstates from Eq.(1).
There is a lot of ongoing work in adapting these microstate trajectory fluctuation theorems for a wide range of scenarios.
Of particular interest to us would be versions of a macrostate fluctuation theorems derived in [32], [33] and [34]
by integrating over all microstates that constitute a macrostate, and over all relevant trajectories. These can be used
to understand the constraints placed on transitions between two arbitrary coarse-grained macroscopic states. The
macroscopic fluctuation relation can be stated as
p(i|I)
π(II → I; τ )
= he− ln( p(j|II) ) he−β∆Qi→j ii→j iI→II
π(I → II; τ )
(2)
where I and II correspond to two macrostate variables defined by underlying conditional microstate distributions
p(i|I) and p(j|II) respectively. π(I → II; τ ) is the probability of the forward trajectory from macrostate I to II in
time interval τ . ∆Qi→j is the heat dissipated into the bath during the microstate trajectory i → j. hii→j and hiI→II
corresponds to expectations over all trajectories from microstates i to j, and over all i ∈ I and j ∈ II respectively.
Similar to the above results, a trajectory-class fluctuation theorems were proposed in [35] and their potential use in
thermodynamic computing [36] explored. In the next couple of subsections, we will briefly introduce some core ideas
that will be necessary for a framework of consciousness and their relationship to the thermodynamic description.
6
A PREPRINT - M AY 7, 2020
4.1
Dissipative Adaptation & Memory
We will start with the hypothesis of dissipation driven adaptation, proposed by the author in [34] using versions of
Eq.(2), according to which “..while any given change in shape for the system is mostly random, the most durable and
irreversible of these shifts in configuration occur when the system happens to be momentarily better at absorbing and
dissipating work. With the passage of time, the ‘memory’ of these less erasable changes accumulates preferentially, and
the system increasingly adopts shapes that resemble those in its history where dissipation occurred. Looking backward
at the likely history of a product of this non-equilibrium process, the structure will appear to us like it has self-organized
into a state that is ’well adapted’ to the environmental conditions. This is the phenomenon of dissipative adaptation.”
Thus one can compare the probability of a system in macrostate I evolving to either II or III in some time interval τ0 .
These probabilities will depend upon the corresponding amount of work absorbed and dissipated by those transitions,
with the more irreversible transition associated with greater dissipation being more likely. This has been studied in
greater detail in chemical networks [37] [38], bistable springs [39] and spin glasses [40].
The stochastic evolution of the macroscopic variables as prescribed by the fluctuations theorems is an active area of
research to better understand the idea of ’memory.’ In order to differentiate from retrodiction, Carroll hypothesizes
that when macrovariables evolve stochastically, the best a system can do is to use current system state and the past
hypothesis to assign probabilities to the past trajectories and thus assign a ’memory’ [41]. Carroll also states in a blog
post titled “Why do we remember the past?” that “...memory relies crucially on the second law of thermodynamics.
Why do we remember the past and not the future? Because, as entropy increases, we develop correlations between the
external universe and our brains; if our universe was in a state of maximum entropy (thermodynamic equilibrium), we
wouldn’t be able to remember the past or the future. (We wouldn’t really exist as complex organisms, for that matter;
thank the universe for small favors.)” [42]. Similar ideas have also been discussed in this excellent post by John Baez
in [43] bringing together ideas of information, entropy and evolution to view adaptation as ‘learning the environment.’
The major takeaway is that just as we view adaptation is learning the environment over certain spatial and time scales,
we can similarly view learning as (dissipation driven) adaptation in the brain over certain spatial and time scales (for
eg: plasticity at the level of synapses and neuron populations as adapting to the inputs driving those systems). We can
view correlations that are developed between our brains and the external world as our systems evolve as important
for the formation of memories. This correlation (and thus the memory) between the current system state (S) and the
past environment input history (H) can be quantified using a mutual information measure I(S : H). Interestingly the
mutual information measure used to capture the amount of memory (here we quantify memory in the sense of capability
to store information, and not the colloquial usage of the word which also involves recall), can also be used as a measure
of the complexity in the system [44], [45], [46], [47], [48].
4.2
Homeostasis & Prediction
Another important concept to understand with respect to the macrostate fluctuation relations in Eq.(2) is homeostasis.
Homeostasis is one of the defining features of biological systems and the process of maintaining a macroscopic variable
at a certain (range of) values, exhibiting a natural resistance to outside change. The maintenance of body temperature,
pH, blood sugar, potassium levels, etc can all be seen as examples of homeostasis in the human body. Homeostatic
mechanisms also play a crucial role in the brain and the nervous system [49]. In this subsection, I will obtain the
fluctuation theorem version of homeostasis from Eq.(2).
Let I be the macrostate that is homeostastically maintained over some time interval τ1 as the system is subject to
external driving inputs. Since the macrostate does not change over the time interval, we will substitute II = I in the
Eq.(2) from above
p(i|I)
π(I → I; τ1 )
= he− ln( p(j|I) ) he−β∆Qi→j ii→j iI→I
π(I → I; τ1 )
(3)
1)
Clearly π(I→I;τ
π(I→I;τ1 ) = 1, if we are observing the macro-observable I over time, it appears unchanged and there is no
difference between a forward π(I → I; τ1 ) and a reverse π(I → I; τ1 ). This gives us that
p(i|I)
he− ln( p(j|I) ) he−β∆Qi→j ii→j iI→I = 1
(4)
Eq.(4) is a (novel and) general macrostate fluctuation theorem equation for homeostasis. Taking negative logarithm on
both side of Eq.(4) to getd
p(i|I)
− lnhe− ln( p(j|I) ) he−β∆Qi→j i
i
=0
(5)
i→j I→I
7
A PREPRINT - M AY 7, 2020
Figure 2: A physical system S with macro-observable/state I is defined by a distribution of microstates. These
microstates can then be coarse-grained into computational states (at some intermediate mesoscopic scale) by choosing
an appropriate information bearing observable. But we can see how by changing that information bearing variable (and
thus how the circles are drawn), we can also have a different set of computational states by coarse-graining over the
same microstates.
Following the procedure in [33] and [50], we use the cumulant generating function 3 to write Eq.(5) as
φI→I = ψI→I
(6)
where φI→I = β1 ∆SI→I + h∆QiI→I . ∆SI→I is the change in internal entropy and h∆QiI→I is the
average dissipation into the bath as the system maintains homeostasis. We also have ψI→I = φI→I +
p(i|I)
1
, that corresponds to the (sum of the) fluctuations about the mean values. Thus if
lnhe− ln( p(j|I) ) he−β∆Qi→j i
i
i→j I→I
β
we imagine a large number of microstates {i}I that all correspond to the observable I, then the trajectories of these
microstates as they map to other microstates in the same set {i}I (since I is homeostatically maintained when driven by
external inputs) have a dissipation ∆Qi→j associated with that trajectory . We can thus calculate a mean dissipation
over all trajectories and microstates {i}I , as well the variance and higher order fluctuations about this average.
Let’s consider a system S with a certain amount of memory of past history H quantified as I(S : H) (as discussed
in the previous subsection). Furthermore let us assume that S is homeostatic with respect to a macroscopic variable
I that is maintains over some time interval τ and thus satisfies Eq.(6) (and that ∆SI→I = 0 for now). Consider a
very special case when we have φI→I = ψI→I to both be small (perhaps tending towards some lower bound?). This
means that we have both the average dissipation over all trajectories, as well the sum of the fluctuations about this
average to be very small (if we assume that variance is the only non-negligible moment in φI→I , then we have that the
dissipation associated with all trajectories i → j for all i, j ∈ {i}I is centered around the mean and thus also low). If a
system satisfies this condition of low φI→I = ψI→I , then we can show that there exists a coarse graining (what that
coarse-graining is, we don’t know but it exists) of the microstates of S into computational states (Fig.(2)), such that the
encoding representation of the iH -th input of history H in the k S -th computational state of the system S (obtained by
coarse-graining over microstates of I using a suitable choice of computationally relevant observable and given by the
probability p(k S |iH )) at any time instant in the time interval satisfies the following constraint optimization problem as
seen in [51], [50], [52], [53] 3
The cumulant generating function is the natural logarithm of the moment generating function i.e. ln E[etX ] =
+∞
X
t=0
µt + σ
2t
2
2
2
+ ..., where µ and σ correspond to the mean (1st moment) and variance (2nd moment) respectively.
8
κn
tn
=
n!
A PREPRINT - M AY 7, 2020
max I(S : F) − λI(S : H)
p(kS |iH )
(7)
where I(S : F) is the mutual information between the current system S and future inputs F (which we assume is
temporally correlated to H), and serves as a measure to quantify the ability of the system to predict F. The trade-off
parameter λ acts as pseudo-temperature noise parameter (that might be related to the actual temperature T ). This is
the (past-future) information bottleneck problem and it analyses the optimal trade-off between prediction and memory.
The solution for the constrained optimization is understood and can be found in [53], [54] and [55] (Note that if we
add to the system S the ability to act on it’s environment and manipulate the input distributions the system will see,
then we can obtain state transition probabilities in the system dynamics that exhibit exploitation-exploration trade-offs
[56]). The main takeaway is that the optimal encoding of the system will include those parts of the past inputs that
is relevant to best predicting future inputs and minimize discard irrelevant information. The formulation only shows
the existence of computational states in the system that can achieve prediction and not how to build them. What this
macrostate could be is hard to identify immediately, but we can say that macro-observable that is being maintained
homeostatically cannot be the informationally relevant variable which is used to partition the space of microstates and
identify the computational states.
The above equations draw a direct line between a specific NE thermodynamic description of an homeostatic system to an
optimally predictive encoding of information in the system states. This brings together keys concepts of non-equilibrium
fluctuation theorems, homeostasis, energy dissipation, optimal encoding and prediction in a single condition. It is
also important to note that while a system S satisfying the thermodynamic condition of low φI→I = ψI→I will
satisfy the solution for the information bottleneck problem, the reverse is not necessarily true. Systems that implement
the information bottleneck algorithm need not satisfy the thermodynamic condition, as evidenced by running these
algorithms on existing computing hardware. Thus satisfying low φI→I = ψI→I is a not a functional condition but
a physical thermodynamic one. Also Eq.(6) is a more general equation of homeostasis, whereas Eq.(7) corresponds
to a very special case of that. Thus we can have a very wide range of homeostatic systems that do not show optimal
predictive inference like brains do. With these thermodynamic descriptions for memory and prediction in place, we are
now in a position to prescribe the non-equilibrium descriptions of consciousness in physical systems.
5
Non-Equilibrium Thermodynamic Framework for Consciousness
In sections 2 and 3, we examined the philosophical underpinnings of the current (popular) frameworks of consciousness,
teased out the advantages and challenges of these frameworks and then described a set of criterion (N1-N4) that we
would like for useful description of consciousness to have. Before we present the non-equilibrium thermodynamic
conditions for consciousness, let us address some of the earlier ideas in this space and how the current work is different
from those. The authors in [57], [58] study consciousness using the popular free-energy principle (FEP) [59], which
models systems using an information-theoretic free-energy term that is minimized. It is important to understand that
this is an information theoretic free-energy and not the thermodynamic free-energy, and it is a functionalist framework.
Also the authors state in [57] -“ A fundamental property of living things (i.e., biological self-organizing systems)
is their tendency to resist the second law of thermodynamics.” This is a confusing statement since the ability of
biological self-organizing systems to maintain themselves is in accordance with/driven forward by the second law of
thermodynamics (and there is no resisting it). Such statements on top of the free-energy minimization formulation makes
the author wonder if the authors are using an older (inequality) versions of the second law (Ideas in non-equilibrium
thermodynamics are relatively newer and can be a little siloed). Viewing the second law as a continuous entropy increase,
a slow march of the thermodynamic arrow of time towards equilibrium (and corresponding free-energy minimization)
is valid only when applied to isolated (and some closed) systems. Equilibrium thermodynamics is simply not the right
way to study open biological systems that constantly exchange matter and energy with their environments and maintain
a non-equilibrium steady state. These systems are better modeled using non-equilibrium fluctuation theorems which
allow for a much richer range of behavior and for which no universal extremal principle (like free-energy minimization
or entropy maximisation or minimal dissipation) exist as of yet. Other work in this space such as [60], [61] both identify
the importance of energy flow in the brain, energy efficient and optimal encoding but do not make concrete connections
between the thermodynamic relations and the information processing frameworks. It is necessary to mention that the
importance of homeostasis in the brain and to consciousness have also been explored in detail in [62] (and we would
be remiss not to mention the importance of the good regulator theorem [63] and it’s role in cybernetics [64]), but we
have a stronger physically grounded mathematical formulation that goes beyond existing work by focussing on the
non-equilibrium fluctuation theorems.
We will next present the main hypothesis in this paper - two non-equilibrium thermodynamic conditions of consciousness
(TCC) derived from NE fluctuation theorems, and ties it directly to the information processing in the system. The
9
A PREPRINT - M AY 7, 2020
conditions for a system S to be conscious is (we can also see this as a condition a system needs to satisfy to be capable
of consciousness i.e. proto-consciousness) (TCC1) System S should exhibit dissipation-driven adaptation i.e. forming of correlations between the system state
and the external environment, and this produces a finite amount of memory I(S : H).
(TCC2) In addition to TCC1, the system should also exhibit the NE thermodynamic condition of low φI→I = ψI→I
with respect to an homeostatic macro-observable I over a time interval of interest τ (thus utilizing the memory
I(S : H)).
Both conditions above are not a description of the system in on itself. They are instead description of dynamic processes
that a system should be capable of exhibiting that the author proposes as necessary for consciousness. As mentioned in
the previous section, satisfying TCC1 corresponds to a system being able to achieve (and maintain) certain degree of
complexity/memory in the system. But this condition alone is very broad as it simply requires a system to be able to
form correlations with the driving signals from the environment and be capable of having some information content. A
lookup table that can be continuously updated with new information will satisfy this condition as it ‘learns/adapts’ to the
new inputs and possesses a finite amount of memory of the past inputs. A burnt piece of wood (with say some degree of
complexity) has some ‘memory’ of the fire that burnt it, as does a mountain of the river that erodes it in it’s current
structure. Of course, we do not expect that a lookup table, a burnt piece of wood or an eroded mountain as conscious
since none of them are able to exploit the information that they possess in their memory to maintain themselves. This is
where TCC2 comes in and thus represents the more important (distinguishing) condition. By requiring a system to
be able to satisfy TCC2 over some spatial and temporal scale (in addition to TCC1) constrains the systems that we
would identify as conscious. Thus TCC2 is what makes the thermodynamic description a step forward from existing
frameworks, and we will focus on it in greater detail in the next section.
6
Observations on TCC2
In this section we present some important observations and implications of TCC2 and the larger thermodynamic
framework (a) The immediate implication of a system satisfying TCC2 is that the system will exploit the information in
the memory of the system in order to predict the future (and act on it if the system has the capability) by
encoding only those parts of the past information that is relevant. This ability to perform temporal predictive
inference combined with the (dissipation driven) memory from TCCI will enable the system to exhibit the
type of input-output behavior we would associate with conscious systems. As noted in the previous section,
a system satisfying TCC1 and TCC2 will exhibit the necessary input-output relations (of a certain level of
intelligent behavior (A1)) but the opposite need not be true. Not all physical systems that exhibit the same
functions necessarily satisfy TCC2. In fact we would expect modern machine learning systems that exhibit a
certain level of intelligence but are extremely computationally and energetically expensive to not satisfy TCC2.
Unlike functionalism, TCC1 and TCC2 being thermodynamic conditions are not implementation/substrate
independent and thus clearly differentiate between systems implementing the same functions. If the system
also has the ability to act on it’s environment, then satisfying TCC2 will imply that the system will exhibit
exploitation-exploration dynamics [56], [65] as a part of the optimal solution, and satisfy criterion (A2).
(b) Building off the previous point, we would ask - what does TCC2 imply for the structure of the physical systems
that realizes the condition? Does TCC2 unconditionally associate consciousness with recurrent or feedforward
network structures? The short answer is - it depends. This aspect of TCC2 is particularly interesting to explore.
Clearly TCC1 simply quantifies the memory capacity of the system and does not limit the structure. While
TCC2 does not directly specify one type of structure over another, it is reasonable to assume that not all
structures of all substrates can realize the necessary TCC2 condition in a particular type of environment. Thus
it might be the case that organic carbon-based biomolecules can only satisfy TCC2 in recurrent neural network
structures under our existing environmental conditions. However one cannot rule out the possibility that a
feedforward neural network manufactured out of superconducting material from satisfying both TCC1 and
TCC2 at near absolute zero temperatures (a likely scenario given the interest in building superconducting
neuromorphic circuits for machine learning applications) could be conscious. However it would explain why
we do not find conscious systems with feedforward brains made out of low temperature superconducting
material in our regular room temperature environments that we exist in. Thus these thermodynamic conditions
correspond to the idea of constrained functionalism that was described earlier in this paper. We could also
build falsifiability tests around this idea - in addition to experimentally validating TCC2 in conscious systems
(like humans and some animals), if we can engineer feedforward networks that satisfy TCC2 using organic
10
A PREPRINT - M AY 7, 2020
bio-molecules under acceptable environmental conditions at relevant spatial scales that are indistinguishable
from humans, that would raise serious questions on why feedforward conscious human brains did not naturally
evolve and/or serve as a way to falsify TCC2 as a condition for consciousness.
(c) This aspect of TCC2 on acceptable network architectures makes it distinct from IIT which would have ruled
out consciousness for any system with a feedforward architecture. Interestingly when faced with the possibility
that IIT might not be falsifiable given it’s inability to validate the value ofφ between equivalent recurrent
and feedforward neural networks [12], some advocates of IIT invoked an efficiency-based argument that
feedforward systems would be much less efficient than their corresponding recurrent equivalent and this
hence favors IIT’s claims on recurrent networks (even this does not quite work out given the results in [14]).
However IIT as currently formulated has no way to justify this efficiency argument other than simply positing
it for convenience on top of their existing axioms and postulates. On the other hand the minimal dissipation
associated with TCC2 is an inherent energy efficiency and optimal representation condition. Thus under the
thermodynamic descriptions, it is reasonable to compare and distinguish between both the efficiency and
conscious status of a feedforward vs recurrent network implemented using the same substrate. In fact, we
should also be looking to further explore the relationship between certain network topologies in the human
brain, their relationship to information transmission and compression efficiency, and metabolic costs in the
brain [66], [67].
(d) TCC2 is a coarse-grained macroscopic description allowing for multi-realizability through a large number of
trajectories of microscopic states at different spatial and temporal scales. It is also an emergent description in
the sense that ‘consciousness’ could be better described at the macroscopic thermodynamic condition than at
the level of the underlying microscopic trajectories. Another important advantage of TCC2 is that it provides a
condition for consciousness as a dynamic process with an associated spatial and temporal scale, as opposed to
simply a state of the system. The condition in question - low φI→I = ψI→I has a spatial resolution through
the choice of the macroscopic variable I and a temporal resolution through the choice of the time interval τ of
interest to us to study. Through the mapping of TCC2 to the information bottleneck problem, we can see the
importance of input signals that the homeostatic system is resisting changes to and is thus predicting - these
become the signals the system is ‘conscious’ of. The question isn’t anymore of asking if certain states of a
system are conscious, sub-conscious or unconscious. It is instead one of asking if the dynamical trajectories
of states in a system at certain spatial and temporal resolution of interest under specific inputs satisfy the
necessary condition. Given the spatial and temporal dependence, the thermodynamic framework also does
not describe consciousness as an ‘all-or-nothing’ phenomenon. It is a more gradual phenomenon within a
system depending on a number of parameters (for eg: the trade-off pseudo-temperature parameter λ from
Eq.(7) whose effect on optimal-coding of input signals has been studied in [53] and discussed below in (f)), as
well as across a wide range of systems.
(e) The mapping of TCC2 to the information bottleneck problem allows us to combine it with some powerful
existing frameworks in neuroscience that has been used to understand various aspects of cognition, perception,
emotion, etc. FEP is one such popular framework used to model various cognitive phenomenon at multiple
spatial and temporal scales [59], [68], and it’s relationship to the information bottleneck problem is established
in [69]. It would require a good amount of work but it seems very plausible to map the equations above to
the predictive coding/processing (PP) frameworks [70], [71], [72], [73]. This would offer another powerful
tool in neuroscience and the wealth of knowledge that they have already accommodated, that we should be
looking to explore and exploit. Also of great interest to study would be the information generation hypothesis
from [74], which views the function of consciousness as generating counter-factual information. Now if you
put that along side temporal prediction and ability to act (inervene) under exploitation-exploration dynamics
for an active agent, we get Judea Pearl’s causal ladder, which he considers as necessary for human-level
intelligence [75]. The mapping of TCC2 to these functionalist models seems slightly easier than mapping
these functionalist models to the brain neurobiology. Both of these projects will involve a lot of work across
multiple disciplines.
(f) In the solution for the encoding probabilities, the λ noise parameter from the Eq.(7) is like a pseudo-temperature
(probably dependent on the actual temperature, noise in the system, etc) and gives a range of encoding strategies
as it is varied from very low (deterministic/large order) to very high (random/no order), not all of which are
good for information encoding. The variation of such pseudo-temperature parameter and their effect on the
encoding strategies used by spiking neurons has been studied in [53] and [76]. We can also view the variation
in the encoding in the system as λ is varied as moving the system between sub-critical and super-critical
phases. Study of the information bottleneck method has shown that solutions exhibit a number of critical
points with respect to λ and merits greater work to understand it’s relationship (if any) to the self-organized
criticality hypothesis in the brain [77], [78]. The different states of consciousness can be thus be viewed as
maintaining TCC2 but having λ manipulated, hence affecting how information is stored in the system and
11
A PREPRINT - M AY 7, 2020
used to achieve prediction. Viewing it as changes to the spatial and temporal scale in which TCC2 is achieved
adds an extra layer of complexity that warrants further work. The changes in the spatial scale could be used as
explain how information could be stored/represented in the brain but not be part of our conscious awareness.
Assume that there is a no (significant) spatial overlap in the part of system S0 which satisfies TCC1 and stores
a piece of information, and the part S1 that satisfies both TCC1 and TCC2 and thus makes predictions using
the finite memory in S1 . Thus S1 cannot exploit the information available in S0 to make predictions, and thus
the conscious experience will lack that information even though it has been stored in the system. However if
the joint system S0 S1 is satisfying TCC2, we would expect the incoming information in both systems to be
part of our conscious experience. The author wants to reiterate that an unavoidable consequence of using these
thermodynamic conditions will be this high level abstraction stripping away many details.
(g) TCC2 being a macroscopic thermodynamic condition takes a different view over questions that involve
replacing parts of your biological neurons with functionally equivalent silicon-based substitutes i.e. ideas
of absent, fading and dancing qualia [9]. The system S is conscious as long as it can maintain TCC2 at
a certain spatial and temporal scale with respect to a macrovariable. Thus if S continues to satisfy TCC2
at a same/different spatial scale even after one of the biological parts has been replaced with functionally
equivalent part made of silicon, we would expect the system to be conscious but with a slightly similar/different
experience respectively. As the number of silicon neurons are increased, and if the system remain conscious
by satisfying TCC2 but at a different spatial scale (and perhaps observable) as compared to a human with only
biological parts, then we would expect the system to have different experiences. The author would like to note
that this indicates very early thinking on this question and more work is needed to address changes in the
contents of experience.
(h) Satisfying TCC2 simply states that there exists a partitioning/coarse-graining of the system microstate
(trajectories) into computational states that satisfy Eq.(7). The condition does not specify how to construct
this partition and thus makes no assumption on what components of the system could constitute the relevant
computational states. For eg: Traditional ideas tend to focus on neurons and synapses in the human brain to
build computational models. However it could be the case that synapses, dendrites, neurotransmitters, proteins,
glial cells, etc. can all be involved in achieving TCC2 and will require detailed experimental work in the
construction of these relevant states.
(i) Philosophers often talk about the need for frameworks of consciousness to discuss our experience of time. The
author not have any experience in this specific topic (and is not the focus of this work) and cannot offer any
detailed comments. However we will point out that the very arrow of time is a thermodynamic description and
by placing consciousness in the same language as time, we might have a way to addressing it rigorously and in
accordance with physical law.
7
Stance on the Hard Problem
No framework that looks to address consciousness can be considered complete without offering a stance on the hard
problem of consciousness introduced by Chalmers [79], [80]. The hard problem of consciousness is the problem of
explaining qualia or phenomenal experience - ‘why does it feel like anything when we are conscious.’ Chalmers
differentiates the hard problem from the ‘easy’ problems of consciousness which includes perception, attention, ability
to discriminate, etc. It is a reasonable to question why TCC1 and TCC2 are not simply conditions that addresses the
easy problems, and nothing more. The author believes that this is not the case here. The history of artificial intelligence,
especially the recent successes in machine learning (ML) through the use of artificial neural networks have shown us
that it is possible to build systems that can solve narrow intelligence tasks like Go, driving (to a certain extent), face
recognition, etc with clever computing ideas and availability of resources. No one in the community seriously thinks
these systems are in any manner conscious. As pointed out before, a system that can implement the necessary functions
to mimic an intelligent system does not immediately satisfy the thermodynamic conditions of consciousness prescribed
above (but the opposite is true based on the TCC1 dependent memory constraints). The exponential (super-Moore
level of) growing demand of compute power and associated energy costs is a serious problem for the ML community.
The human brain (a system that we agree is conscious) is often pointed to as the holy grail achievement for the AI
field - given it’s ability to be intelligent across tasks and efficiency of it’s implementation. Since we could in principle
achieve performance across tasks given enough data and compute resource, one has to ask if energy efficiency that the
human brain exhibits plays a crucial role here. Now TCC2 brings together task-independent temporal prediction and
energy efficiency together in a single condition. All we can look to do is provide a description that brings these two key
properties of an agreed-upon conscious system together (one of which we know we can achieve in principle without the
energy efficiency constraint) and ask if that description captures the necessary phenomenon.
12
A PREPRINT - M AY 7, 2020
The intuition that these conditions simply seems to only solve the easy problems is not misplaced. As it stands now,
there still seems to be a huge gap between what the thermodynamic framework is discussing and the phenomenal
properties that form an important part of our experiences. How are these conditions possibly a solution the hard
problem? With respect to the hard problem, the thermodynamic framework takes an illusionist position [81],[82], [83].
The illusionist stance is to reject the framing of the hard problem outright, given the various issues associated with
the realist position towards solving the hard problem. Illusionism states that consciousness is real and the subjective
qualities you experience are also real, but they are not what you think they are. It rejects the existence of non-physical
mental states or that of phenomenal properties (distinct from physical properties). What is illusory is our introspective
experience of these properties as being non-physical and different from what we perceive of our outside world. To the
illusionist position, the meta-problem of consciousness [84] is the problem of consciousness [85] and thus solving
the meta-problem dissolves the hard problem. Before we proceed further, I want to quote a few lines from [82] that I
think are extremely important and clarifies the illusionist position (which given the use of useful plus provocative term
illusion has often been easy to misunderstand and straw-man) - “The third option is illusionism. This shares radical
realism’s emphasis on the anomalousness of phenomenal consciousness and conservative realism’s rejection of radical
theoretical innovation. It reconciles these commitments by treating phenomenal properties as illusory. Illusionists deny
that experiences have phenomenal properties and focus on explaining why they seem to have them. They typically
allow that we are introspectively aware of our sensory states but argue that this awareness is partial and distorted,
leading us to misrepresent the states as having phenomenal properties. Of course, it is essential to this approach that
the posited introspective representations are not themselves phenomenally conscious ones. It would be self-defeating to
explain illusory phenomenal properties of experience in terms of real phenomenal properties of introspective states.
Illusionists may hold that introspection issues directly in dispositions to make phenomenal judgments — judgments
about the phenomenal character of particular experiences and about phenomenal consciousness in general. Or they
may hold that introspection generates intermediate representations of sensory states, perhaps of a quasi-perceptual
kind, which ground our phenomenal judgments. Whatever the details, they must explain the content of the relevant states
in broadly functional terms, and the challenge is to provide an account that explains how real and vivid phenomenal
consciousness seems.” In particular the author will advocate for strong illusionism as defined by Frankish [82] 4 ,
that introduces the idea of quasi-phenomenal properties [82] - “A quasi-phenomenal property is a non-phenomenal,
physical property (perhaps a complex, gerrymandered one) that introspection typically misrepresents as phenomenal.
For example, quasi-phenomenal redness is the physical property that typically triggers introspective representations of
phenomenal redness. There is nothing phenomenal about such properties — nothing ‘feely’ or qualitative — and they
present no special explanatory problem. Strong illusionists hold that the introspectable properties of experience are
merely quasi-phenomenal ones.”
In order to understand how the thermodynamic framework reaches the illusionist stance, let us go back and review
TCC2 again. From section (4.2), we have that the special case of low φI→I = ψI→I is equivalent to an information
bottleneck in Eq.(7).
maxp(kH |iS ) I(S : F) − λI(S : H)
Illusionism has pointed to the lack of sufficient resources in the brain as the reason for the emergence of quasiphenomenal states [83]. We will adopt a similar approach here. The information-bottleneck can be really seen as a
compression of the information [54] to form coarse-grained representations [86] under memory constraints imposed
through TCC1 and energy efficiency constraints imposed through TCC2. The identification of macro-observable I that
satisfies TCC2 determines the input history H and future inputs F, as well as the spatial scale of S of the conscious
system. This decides what would be inputs to the system (thus input history) and the memory capability of the system
I(S : H). As the system generates coarse-grained representations (compression) of the information in the inputs to S
in order to perform predictive inference of future inputs, different parts of the inputs are going to be compressed to
different degrees. There is a gradation in the scale of coarse-grained representations generated in S.
We will explore this a little bit further here. Chalmer’s demarcation makes a strong distinction between those problems
he considered easy (E) and those which were hard (H), requiring a radical shift on the ability to science to address
problems on either side of that boundary. On the other hand, the author is making the case that consciousness - both
access and phenomenal is very real but instead of clear boundary placing each of those in discrete categories, we propose
a more gradual scale with those parts of consciousness that we regard as part of the easy problems at one end and those
we regard as hard on the other, and different parts of our experience spread across the scale. Everything on the scale is a
physical process and there are no physical/mental distinctions. To make the analogy to human experience about this
scale - certain features of our external sensory perception on one end of the coarse-graining to highly coarse-grained
4
It has been brought to the author’s attention that there are different taxonomies in illusionism - Frankish’s [82] vs Chalmers
[84]. To clear any doubt the author will refer to Chalmer’s version of strong illusionism which states that ‘consciousness is really an
illusion and it doesn’t exist’ as stark illusionism, and when we refer to strong illusionism, it is strictly how Frankish defines it.
13
A PREPRINT - M AY 7, 2020
interoceptive-plus (from the body plus other parts of the brain outside of the S satisfying TCC2) inputs that add the
subjective ‘feelness’ to our experiences. There is no special ontological status to the more compressed signals and it is
as real and physical as other parts of the sensory perception. It has a mysterious subjective quality to it, due to severe
coarse-grained compression to the point that it becomes unrecognizable and distinct from the physical, and we mistake
them to be mental/phenomenal and invoke ideas of qualia. When we pay attention to these through introspection, these
inputs are so heavily coarse-grained in our system as compared to certain parts of the sensory signals that any verbal
report (on say describing the ’feeling’ of red) will not have the same amount of clarity as describing other parts of
our perception (It is in fact hard to decouple the mysterious subjective feeling in experiences without seemingly less
subjective i.e. the ’physical’ aspects providing a reference). The generation of body ownership and of the concept of
self or ‘I’ under a predictive processing framework [73] are coarse-grained representations as well, that lie somewhere
along this scale between the two extremes. A closely related idea of Bayesian frugality [87] has also been proposed
to bring together predictive processing framework and the Attention Schema Theory [88] to explain the mysterious
subjective aspects of experience. All of these culminate together to form our first person view as the inevitable result of
imposing resource constraints (realized as information bottlenecks) on a constraint-free third person view. The third
person description of a system realizing these conditions is clearly not the same as the system actually realizing the
conditions (and thus having the experience) and indicates the explanatory gap [89] that seems to exist between the two.
Building off the previous idea, how should one think about the content of consciousness under the thermodynamic
framework? First TCC1 and 2 should be seen as grounding conditions to establish whether or not a system is conscious.
Once we do that, the conscious content itself (atleast in humans) is most usefully described by existing functional
descriptions. While the thermodynamic framework is not a functionalist framework, the claim here is that - experiential
states (trajectories) are best described functionally in systems that we agree to be conscious. We should be looking
for families of trajectories of physical microstates over time and work to establish relationships between inputs, these
state trajectories and the functional labels (obtained through behavioral reports) that we traditionally use to identify
these states 5 . In these suitably identified partition of microstates into computational states, we have coarse-grained
representations (to varying degree) of the different (interoceptive, proprioceptive, exteroceptive, etc) inputs to the
system that is used to generate predictions (of the same) forming the content of our conscious experience. As discussed
in the previous section, there has been tremendous work in these areas using functionalist frameworks like predictive
coding, and the next important step is formalize the relationship between the thermodynamic and functionalist pictures
with more rigor.
8
Some Major Challenges That Lie Ahead
Having presented an highly optimistic and favorable view of the thermodynamic framework, the author thinks it is only
fair to point a couple of (major) challenges and problems that are immediately identifiable. The author hopes that by
making a positive case for a new thermodynamic framework of consciousness, it will encourage a number of more
intelligent researchers to explore this in further detail and address some of these issues (a) While the author has assumed the existence of macroscopic I that (should) satisfy TCC2 in conscious systems,
we do not know of a procedure to identify them, especially in complex biological systems like humans.
We might look to use literature on metabolic studies in the brain to perhaps identify potential candidates?
Furthermore once we identify the observable I, there is still the question of grouping these microstates into
computational states, an unenviable task given the complexity of known conscious systems. Furthermore
anyone working in thermodynamics will immediately attest to the difficulty of running simulations of nonequilibrium systems. Trying to map trajectories is computationally very hard and possibly intractable for any
mesoscale to macroscale system of interest. While a thermodynamic framework of consciousness might be
elegant and potentially useful given it’s relation to physical law, the downside might be that by abstracting
to the level of thermodynamic descriptions to achieve generality across systems, we might lose the ability to
exploit existing computational tools as well as map them onto biological systems to answer questions that
neuroscience is interested in. But as was the case with IIT, one would hope that people will come up with
clever ways to find proxies for TCC2 or identify ways to use techniques like Markov chain Monte Carlo to
make the problem tractable. The goal of these frameworks are never meant to replace the wealth of knowledge
that neuroscience can deliver at computational and neurobiological levels. They are meant to provide a bigger
picture view to fit all the pieces together in accordance with physical law (and make a strong case against
adoption of a position that consciousness lies outside the realm of science).
(b) This second (and more pressing) problem is related to the ’scale problem of consciousness’ - what is the level
at which consciousness is realized [90]? Let us assume that we are able to identify I in a system S that satisfies
5
We will leave the discussion around contents of experiences of artificial systems for a different work
14
A PREPRINT - M AY 7, 2020
TCC2 over some time interval τ , and as per the framework proposed in this paper, we classify the system as
conscious. Now let there be a subsystem S0 of S that has an observable I0 (which of course would be part of
the higher level macro-observable I of S) that also satisfies TCC2 at it’s level of description for the same time
interval. The question now is - what is the level at which there is conscious experience? At the level of S or
S0 or both? IIT deals with this problem using their exclusion axiom and postulate that - of all overlapping
sets of elements, only one set with maximal integrated information can be conscious [91]. The author can
either adopt the same exclusion axiom, but that would not come immediately from physical law like the
conditions themselves did. One could take the stance that there would never be a situation in which I0 satisfies
TCC2 in S0 when it is also satisfied by I in S as well, but this feels like wishful thinking (and the author
does not see a reason why this would be impossible in principle). This leaves us with one remaining option
- to bite the bullet and take the view similar to the authors in [90] and “allow for multiple consciousnesses
to coexist across different levels of coarse-graining within a system if they are informationally closed from
each other.” Since S0 is a subsystem of S as it satisfies TCC2, signals originating from it cannot be inputs
outside of S, that the system can be conscious of. Thus even if S0 does satisfy TCC2 simultaneously, the
conscious experience of the larger S will not include identification of micro-conscious S0 (or in the very least
so extremely coarse-grained that it does not recognize it). By not positing an exclusion principle like IIT 3.0
[92], we escape from the some of problems that IIT faces as pointed out in [15]. But we will use the example
used in [93] to further illustrate our point and make the difference with IIT. The original problem in IIT was
the broad allocation of consciousness to the point where a properly arranged networks of all the humans in the
USA would create a consciousness of the USA. An anti-nesting principle was then subsequently proposed
to solve this problem, according to which when subsystems with non-zero φ join to form a system with a
larger value of φ, the subsystems lose their consciousness. This then led to other problems (counter-intuitive
predictions) of its own - such that if a small brain implant was placed in a human brain, integrated in such a
manner so that the consciousness of the human+implant is greater than the human, then that would imply that
the human would lose their consciousness and be replaced with a larger human+implant consciousness. Instead
under the thermodynamic framework, assume that the human (S0 ) is able to satisfy TCC2 after integration
simultaneously as the human+implant system (S), then S is conscious as a joint human+implant system of
inputs outside of it and not aware of S0 (which forms a part of S) as a separate conscious entity outside of
itself. At the same time, the human S0 is conscious of itself, experiences the implant as external to it and does
not recognize that the joint human+implant S system is also conscious.
Of course these are not the only possible problems and challenges facing this framework. When dealing with one of the
toughest problems in science, it is to be expected that many more issues will pop up. The question is whether or not
there is enough interest among talented scientists and philosophers, as well as the availability of resources to solve them.
9
Machine Consciousness
One of the most interesting questions in the science of consciousness is the possibility of building machines capable of
consciousness? Many philosophers, scientists and engineers have wondered about this very questions for a very long
time but it has become increasingly pertinent with the recent success in the field of artificial intelligence and machine
learning, with different necessary conditions prescribed [94]. As these artificial systems continue to get better at tasks
that have been historically associated with our intelligence, it is natural to question the conscious status of these systems
[95]? If these systems indeed are conscious, then it represents a monumental achievement for human civilization, as
well open a Pandora’s box of ethical and legal questions to decide. We will utilize the taxonomy provided by Gamez in
[96] with respect to the levels of machine consciousness in our discussion here • (MC1) Machines with the external behaviour associated with consciousness.
• (MC2) Machines with the cognitive characteristics associated with consciousness.
• (MC3) Machines with an architecture that is claimed to be a cause or correlate of human consciousness.
• (MC4) Phenomenally conscious machines.
Over the years we have made steady progress in constructing models for MC1 and MC2 and realizing them in artificial
systems. MC3 is possible in principle and with the increased interest in neuromorphic computing, we should expect to
be able to achieve it in the near future if we wanted to. But we have made no progress towards MC4, though a number of
theories (like the ones we have discussed earlier) have been proposed. A detailed discussion of theoretical frameworks
for human and machine consciousness, their advantages and drawbacks as well what a theory of consciousness should
look like is discussed in [24]. Without a solid framework of consciousness in humans and animals, MC4 has looked
near impossible and discussion around it has mostly been dismissed as fiction. Of course popular media depictions of
15
A PREPRINT - M AY 7, 2020
artificial intelligence, robots and artificial consciousness as well as the pseudo-scientific claims about Singularity and
consciousness uploading have served to only further damage this area of research.
We will specifically address MC4 in this section (since the other 3 are functional realizations and can be implemented
in principle). From [97], we have the following four pre-conditions for a generalizable theory of consciousness that
would be needed for MC4 (1) Can generate testable predictions.
(2) Is applicable to any physical system.
(3) Compact (Occam’s razor).
(4) Based on objective properties of the physical world.
The thermodynamic conditions TCC1 and TCC2 are applicable to any physical system, can be used to generate testable
predictions around energy absorbed and dissipated that could be studied experimentally (fMRI, metabolic studies,
etc) and in simulation. While the author cannot comment on the simplicity of the conditions, we should note that the
thermodynamic conditions are derived from the fluctuation theorems and thus a result of objective physical law and the
objects of study would be measures like energy, work, heat as opposed to information and computation. The author
proposes that an artificial system satisfying TCC1 and TCC2 can be MC4 conscious in principle. What about a computer
that simply simulates the computational equation Eq.(7)? As we have stated before, systems simulating/implementing
Eq.(7) need not satisfy low φI→I = ψI→I since that relationship is not reciprocal and thus need not be conscious. A
lot of the current large-scale computational brain models run on a significant amount of compute resources [98] almost
definitely do not satisfy Eq.(6) (The author has not experimentally verified this), and cannot be expected to magically
become conscious as more and more compute is added on.
What can we say about our current AI systems in von-Neumann vs neuromorphic hardware? We have to start replacing
these type of questions with something more specific, since we are not really asking whether or not AI systems with
von-Neumann or neuromorphic hardware made out of any substrate would be conscious or not, under all possible
conditions? We are more interested in whether or not a particular systems that we have built or intend to build with
specific materials (usually silicon CMOS) operating in our regular environments are conscious? We will have to
experimentally check if our AI system SAI (in both von-Neumann and neuromorphic) satisfies TCC2, as they both
almost definitely satisfy TCC1. But my educated speculation is that AI systems built on traditional CMOS devices and
implemented using the von-Neumann architecture will definitely not satisfy TCC2 and hence not be conscious for the
following reason - if it was possible for such a system to be conscious, one would have reasonably expected to see
some evidence of bio-molecular von-Neumann brains somewhere in the tree of life, achieving the same thing as our
traditional brains to have evolved as the product of evolution. Questions along this line of inquiry can now be translated
from a philosophical thought experiment to the form of research in network theory and material chemistry - can a
carbon-based substrate satisfy TCC1 and TCC2 in any other network structure other than the small-world recurrent
one in our heads?
Neuromorphic computing represents a wide range of hardware systems built to mimic the brain at various levels of
devices, architectures, etc [99]. It is a much harder case as it represents a grey area between CMOS-based von-Neumann
architectures on one end and biological brains on the other. It is probably best handled on a case-by-case basis as
the answer will depend on multiple factors in the computing stack, as well as on the spatial and temporal scale of
interest. On the other hand, I am very interested in self-organizing neuromorphic atomic switch networks (ASN) [100] it represents a very interesting candidate to test these ideas for artificial consciousness, since they represent a lot of
the right properties you would expect to see in a system that satisfies TCC 1 and 2 like - memristive device behavior
(memory), self-organizing scale-free network architecture and can be used perform time-series predictions in an energy
efficient manner. There is increasing interest in material science research to fabricate more novel materials, similar
to the silver nanowires in the ASNs to produce self-organizing networks for AI tasks. The author believes that this is
a very interesting overlap between those interested in machine consciousness and those building these novel energy
efficient AI hardware. Increasing demand for the latter (and the resources that come with that demand) might rejuvenate
the earlier.
10
Summary & Conclusion
In this paper, we proposed that a thermodynamic description of consciousness would be a step forward from both
functionalist and causal structure frameworks. Then starting from the non-equilibrium thermodynamic fluctuation
theorems (physical law), we proposed two conditions for consciousness - TCC1 (dealing with memory) and TCC2
(dealing with efficeint prediction-memory trade-off under homeostasis). The advantages of these conditions over
16
A PREPRINT - M AY 7, 2020
existing frameworks, it’s connection to existing functional theories and it’s stance on the hard problem is discussed.
We finally ended with our predictions on the questions of machine consciousness and the path forward. To the best
of my knowledge, this work here represent the first framework of consciousness (both biological and artificial) that
is derived straight from existing non-equilibrium thermodynamical physical law (and does not need to appeal to any
new physics) and brings together ideas from philosophy, physics, information theory, functional predictive coding
models and neuroscience. It seeks to put consciousness squarely at the heart of physical law and in the realm of science,
rather than outside it (and does not try to replace other modes of studying human brain function/consciousness like
neuroscience and cognitive science, which is in a better position to find solutions to problems that have to do with
cognitive disorders, etc). It can however try to answer questions like‘why did human consciousness emerge?’ by
translating them to into the realm of science - ’what is the probability of forming a structure at the necessary spatial
scale that satisfies TCC2 over evolutionary time scales?. I would like to end by reiterating that there is still a lot of
work to be done but the future of the scientific study of consciousness looks very bright indeed.
References
[1] Bengio, Yoshua, “From System 1 Deep Learning to System 2 Deep Learning,” NEURIPS 2019, 2019.
[2] Amodei, Dario, et al., “AI and Compute,” OpenAI blog, 2019.
[3] Moore, Gordon E, “Cramming more components onto integrated circuits,” (1965): 114-117.
[4] Dennard, Robert H., et al., “Design of ion-implanted MOSFET’s with very small physical dimensions,” IEEE
Journal of Solid-State Circuits, 9.5 (1974): 256-268.
[5] Strubell, Emma, Ananya Ganesh, & Andrew McCallum, “Energy and policy considerations for deep learning in
NLP,” arXiv preprint, arXiv:1906.02243 (2019).
[6] Baars, Bernard J., “Global workspace theory of consciousness: toward a cognitive neuroscience of human
experience.” Progress in Brain Research, 150 (2005): 45-53.
[7] Oizumi, Masafumi, Larissa Albantakis, and Giulio Tononi, “From the phenomenology to the mechanisms of
consciousness: integrated information theory 3.0.” PLoS Computational Biology, 10.5 (2014): e1003588.
[8] Peter Carruthers, “Higher-Order Theories of Consciousness,” Stanford Encyclopedia of Philosophy.
[9] Chalmers, David J, “Absent qualia, fading qualia, dancing qualia,” Conscious Experience, 309-328, 1995.
[10] Levin, Janet, “Functionalism,” Stanford Encylopedia of Philosophy, (2004).
[11] Putnam, Hilary, “Minds and machines,” (1960).
[12] Doerig, Adrien, et al, “The unfolding argument: Why IIT and other causal structure theories cannot explain
consciousness.” Consciousness and cognition 72 (2019): 49-59.
[13] Tsuchiya, Naotsugu, Thomas Andrillon, and Andrew Haun, ”A reply to ‘the unfolding argument’: Beyond
functionalism/behaviorism and towards a truer science of causal structural theories of consciousness.” (2019).
[14] Hanson, Jake R., and Sara I. Walker, “Integrated Information Theory and Isomorphic Feed-Forward Philosophical
Zombies,” Entropy, 21.11 (2019): 1073.
[15] Cerullo, Michael A, “The problem with phi: a critique of integrated information theory,” PLoS Computational
Biology, 11.9 (2015).
[16] Aaronson, Scott, “Why I Am Not An Integrated Information Theorist (or, The Unconscious Expander),” ShtetlOptimized blog, 2014.
[17] Tsuchiya, Naotsugu, Shigeru Taguchi, and Hayato Saigo, “Using category theory to assess the relationship
between consciousness and integrated information theory,” Neuroscience Research, 107 (2016): 1-7.
[18] Hoel, Erik, “IIT is scientifically falsifiable,” Medium post, 2019.
[19] Aaronson, Scott, “The Search for Physical Correlates of Consciousness,” FQXi Conference , 2019.
[20] Aaronson, Scott, “Giulio Tononi and Me: A Phi-nal Exchange,” Shtetl-Optimized blog, 2014.
[21] Aaronson, Scott, “Integrated Information Theory: Virgil Griffith opines,” Shtetl-Optimized blog, 2014.
[22] Kleiner, Johannes, “On empirical well-definedness of models of consciousness.” Psyarxiv, (2019).
[23] Tegmark, Max, “Consciousness as a state of matter,” Chaos, Solitons & Fractals, 76 (2015): 238-270.
[24] Gamez, David, Human and machine consciousness, Open Book Publishers, 2018.
17
A PREPRINT - M AY 7, 2020
[25] Chalmers, David J, “The combination problem for panpsychism,” Panpsychism: Contemporary Perspectives,
(2017): 179-215.
[26] Kondepudi, Dilip, and Ilya Prigogine, Modern thermodynamics: from heat engines to dissipative structures, John
Wiley & Sons, 2014.
[27] Onsager, Lars, “Reciprocal relations in irreversible processes. I,” Physical Review, 37.4 (1931): 405.
[28] Onsager, Lars, “Reciprocal relations in irreversible processes. II,” Physical Review, 38.12 (1931): 2265.
[29] Prigogine, Ilya, et al, Introduction to thermodynamics of irreversible processes, Vol. 7. New York: Interscience
Publishers, 1961.
[30] Jarzynski, Christopher, “Nonequilibrium equality for free energy differences,” Physical Review Letters, 78.14
(1997): 2690.
[31] Crooks, Gavin E, “Entropy production fluctuation theorem and the nonequilibrium work relation for free energy
differences,” Physical Review E, 60.3 (1999): 2721.
[32] England, Jeremy L, “Statistical physics of self-replication,” The Journal of Chemical Physics, 139.12 (2013):
09B6231.
[33] Perunov, Nikolay, Robert A. Marsland, and Jeremy L. England, “Statistical physics of adaptation,” Physical
Review X, 6.2 (2016): 021036.
[34] England, Jeremy L, “Dissipative adaptation in driven self-assembly,” Nature Nanotechnology, 10.11 (2015): 919.
[35] Wimsatt, Gregory, et al., “Harnessing Fluctuations in Thermodynamic Computing via Time-Reversal Symmetries.”
arXiv preprint, arXiv:1906.11973 (2019).
[36] Conte, Tom, Erik DeBenedictis, Natesh Ganesh, Todd Hylton, Susanne Still, John Paul Strachan, R. Stanley
Williams, et al., “Thermodynamic Computing,” arXiv preprint, arXiv:1911.01968 (2019).
[37] Horowitz, Jordan M., and Jeremy L. England, “Spontaneous fine-tuning to environment in many-species chemical
reaction networks,” Proceedings of the National Academy of Sciences, 114.29 (2017): 7565-7570.
[38] Kachman, Tal, Jeremy A. Owen, and Jeremy L. England, “Self-organized resonance during search of a diverse
chemical space,” Physical Review Letters, 119.3 (2017): 038001.
[39] Kedia, Hridesh, et al., “Drive-specific adaptation in disordered mechanical networks of bistable springs,” arXiv
preprint, arXiv:1908.09332 (2019).
[40] Gold, Jacob M., and Jeremy L. England, “Self-organized novelty detection in driven spin glasses,” arXiv preprint,
arXiv:1911.07216 (2019).
[41] Carroll, Sean, “Causality and the Arrow of Time,” FQXi Conference , 2019.
[42] Carroll, Sean, ”Why do we remember the past?” Preposterous Universe Blog, 2004.
[43] Baez, John Carlos, “Biology as Information Dynamics,” Stanford Complexity Group, 2017.
[44] Lloyd, Seth, “Measures of complexity: a nonexhaustive list,” IEEE Control Systems Magazine, 21.4 (2001): 7-8.
[45] Crutchfield, James P., and Karl Young, “Inferring statistical complexity,” Physical Review Letters, 63.2 (1989):
105.
[46] Shalizi, Cosma Rohilla, and James P. Crutchfield, “Computational mechanics: Pattern and prediction, structure
and simplicity,” Journal of Statistical Physics, 104.3-4 (2001): 817-879.
[47] Aaronson, Scott, Sean M. Carroll, and Lauren Ouellette, “Quantifying the rise and fall of complexity in closed
systems: The coffee automaton,” arXiv preprint, arXiv:1405.6903 (2014).
[48] Bialek, William, Ilya Nemenman, and Naftali Tishby, “Predictability, complexity, and learning,” Neural Computation, 13.11 (2001): 2409-2463.
[49] Turrigiano, Gina G., and Sacha B. Nelson, “Homeostatic plasticity in the developing nervous system,” Nature
Reviews Neuroscience, 5.2 (2004): 97.
[50] Ganesh, Natesh, “A Thermodynamic Treatment of Intelligent Systems,” 2017 IEEE International Conference on
Rebooting Computing (ICRC), IEEE, 2017.
[51] Still, Susanne, “Thermodynamic cost and benefit of data representations,” arXiv preprint, arXiv:1705.00612
(2017).
[52] Still, Susanne, et al., “Thermodynamics of prediction,” Physical Review Letters, 109.12 (2012): 120604.
[53] Still, Susanne, “Information bottleneck approach to predictive inference,” Entropy, 16.2 (2014): 968-989.
18
A PREPRINT - M AY 7, 2020
[54] Tishby, Naftali, Fernando C. Pereira, and William Bialek, “The Information Bottleneck Method,” arXiv preprint,
physics/0004057 (2000).
[55] Creutzig, Felix, Amir Globerson, and Naftali Tishby, “Past-future Information Bottleneck in Dynamical Systems,”
Physical Review E, 79.4 (2009): 041925.
[56] Still, Susanne, “Information-theoretic Approach to Interactive Learning,” EPL (Europhysics Letters), 85.2 (2009):
28005.
[57] Solms, Mark, “The hard problem of consciousness and the free energy principle,” Frontiers in Psychology, 9
(2018).
[58] Solms, Mark, and Karl Friston, “How and why consciousness arises: some considerations from physics and
physiology,” (2018).
[59] Friston, Karl, “The free-energy principle: a unified brain theory?,” Nature Reviews Neuroscience, 11.2 (2010):
127.
[60] Yufik, Yan M, “Understanding, consciousness and thermodynamics of cognition,” Chaos, Solitons & Fractals, 55
(2013): 44-59.
[61] Pepperell, Robert, “Consciousness as a physical process caused by the organization of energy in the brain,”
Frontiers in Psychology, 9 (2018): 2091.
[62] Damasio, Antonio R, Self comes to mind: Constructing the conscious brain, Vintage, 2012.
[63] Conant, Roger C., and W. Ross Ashby, “Every good regulator of a system must be a model of that system,”
International Journal of Systems Science, 1.2 (1970): 89-97.
[64] Ashby, W. Ross, An introduction to cybernetics, Chapman & Hall Ltd, 1961.
[65] Friston, Karl, Christopher Thornton, and Andy Clark, “Free-energy minimization and the dark-room problem,”
Frontiers in Psychology, 3 (2012): 130.
[66] Bassett, Danielle Smith, and E. D. Bullmore, “Small-world brain networks,” The Neuroscientist, 12.6 (2006):
512-523.
[67] Bassett, Danielle Smith, et.al.m “Efficient Coding in the Economics of Human Brain Connectomics,” arxiv
preprint, arXiv:2001.05078, 2020.
[68] Friston, Karl, “Life as we know it,” Journal of the Royal Society Interface, 10.86 (2013): 20130475.
[69] Karl, Friston, “A free energy principle for biological systems,” Entropy, 14.11 (2012): 2100-2121.
[70] Rao, Rajesh PN, and Dana H. Ballard, “Predictive coding in the visual cortex: a functional interpretation of some
extra-classical receptive-field effects,” Nature Neuroscience, 2.1 (1999): 79.
[71] Clark, Andy, ‘Surfing uncertainty: Prediction, action, and the embodied mind, Oxford University Press, 2015.
[72] Seth, Anil K, “The cybernetic Bayesian brain,” Open MIND, Frankfurt am Main: MIND Group, 2014.
[73] Seth, Anil K, “Interoceptive inference, emotion, and the embodied self,” Trends in Cognitive Sciences, 17.11
(2013): 565-573.
[74] Ryota Kanai, Acer Chang, Yen Yu, Ildefons Magrans de Abril, Martin Biehl, Nicholas Guttenberg, Information
generation as a functional basis of consciousness, Neuroscience of Consciousness, Volume 2019, Issue 1, 2019,
niz016, https://doi.org/10.1093/nc/niz016
[75] Pearl, Judea, “Theoretical impediments to machine learning with seven sparks from the causal revolution,” arXiv
preprint, arXiv:1801.04016 (2018).
[76] Tkačik, Gašper, et al., “Optimal population coding by noisy spiking neurons,” Proceedings of the National
Academy of Sciences, 107.32 (2010): 14419-14424.
[77] Bak, Per, Chao Tang, and Kurt Wiesenfeld, “Self-organized criticality: An explanation of the 1/f noise,” Physical
Review Letters, 59.4 (1987): 381.
[78] Hesse, Janina, and Thilo Gross, “Self-organized criticality as a fundamental property of neural systems,” Frontiers
in Systems Neuroscience, 8 (2014): 166.
[79] Chalmers, David J, “Facing up to the problem of consciousness,” Journal of Consciousness Studies, 2.3 (1995):
200-219.
[80] Chalmers, David J, The conscious mind: In search of a fundamental theory, Oxford university press, 1996.
[81] Dennett, Daniel C, Consciousness Explained, (1991).
19
A PREPRINT - M AY 7, 2020
[82] Frankish, Keith, “Illusionism as a theory of consciousness,” Journal of Consciousness Studies, 23.11-12 (2016):
11-39.
[83] Frankish, Keith, “The consciousness illusion,” Aeon, 2019.
[84] Chalmers, David J, “The meta-problem of consciousness,” Journal of Consciousness Studies, 25.9-10 (2018):
6-61.
[85] Frankish, Keith, “The Meta-Problem is The Problem of Consciousness,” Journal of Consciousness Studies, 26.9-10
(2019): 83-94.
[86] Wolpert, D. H., Grochow, J. A., Libby, E., & DeDeo, S., “Optimal high-level descriptions of dynamical systems,”
arXiv preprint, arXiv:1409.7403 (2014).
[87] Dolega, K. & Dewhurst, J, “Bayesian Frugality and the Representation of Attention,” Journal of Consciousness
Studies, 26 (3-4):38-63.
[88] Graziano, Michael S A, Consciousness and the Social Brain, Oxford University Press, 2013.
[89] Levine, Joseph, “Materialism and qualia: The explanatory gap,” Pacific Philosophical Quarterly, 64.4 (1983):
354-361.
[90] Chang AY, Biehl M, Yu Y, Kanai R,“Information Closure Theory of Consciousness,” arXiv preprint,
arXiv:1909.13045. 2019 Sep 28.
[91] Hoel, Erik P, Albantakis, Larissa, Marshall, William, & Tononi, Giulio, “Can the macro beat the micro? Integrated
information across spatiotemporal scales,” Neuroscience of Consciousness, 2016.
[92] Oizumi, Masafumi, Larissa Albantakis, and Giulio Tononi, “From the phenomenology to the mechanisms of
consciousness: integrated information theory 3.0,” PLoS Comput Biol, 10.5 (2014): e1003588.
[93] Schwitzgebel E, “Why Tononi Should Think That the United States Is Conscious,” Splintered Mind blog, 2011.
[94] Dehaene, Stanislas, Hakwan Lau, and Sid Kouider, “What is consciousness, and could machines have it?,” Science,
358.6362 (2017): 486-492.
[95] Reggia, James, “Conscious machines: The AI perspective,” 2014 AAAI Fall Symposium Series, 2014.
[96] Gamez, David, “Progress in machine consciousness,” Consciousness and Cognition, 17.3 (2008): 887-910.
[97] Gamez, David, “Four Preconditions for Solving MC4 Machine Consciousness,’ AAAI Spring Symposium: Towards
Conscious AI Systems, 2019.
[98] Amunts, Katrin, et al., “The human brain project: creating a European research infrastructure to decode the human
brain,” Neuron, 92.3 (2016): 574-581.
[99] Schuman, Catherine D., et al., “A survey of neuromorphic computing and neural networks in hardware,” arXiv
preprint, arXiv:1705.06963 (2017).
[100] Avizienis, Audrius V., et al., “Neuromorphic atomic switch networks,” PloS One, 7.8 (2012).
20 |
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
617
Article
Non-invasive Indicators of Stress and Bioenergy Disruption
& Benefit of Meditation in Relieving Stress
Pradeep B. Deshpande*1 & Konstantin Korotkov3
1
Department of Chemical Engineering, University of Louisville; & Six Sigma & Advanced Controls, Inc.
P.O. Box 22664, Louisville, KY
3
Department of Biophysics and Computers, St. Petersburg Federal University of Informational
Technologies, Optics, and Mechanics, St. Petersburg, Russia
Abstract
The bioenergy field of seven individuals known to be suffering from chronically high stress
levels was measured with a gas-discharge-visualization (GDV) device revealing that their
bioenergy fields were severely disrupted recording high to very high numerical values of stress
levels and severely off-balance chakras. Stress is known to be a marker for a number of ailments
and has been shown to have a negative effect on aging. Since meditation has been shown to
reverse the negative effect of stress, the information reported in this paper nicely supplements
and complements traditional medical approaches to illnesses and should be useful in the light of
the ever-increasing healthcare costs.
Keywords: stress, bioenergy, telomeres, aging, sickness, meditation.
Introduction
High level of stress has been shown to shorten telomere length and lower telomerase level with
an adverse effect on aging as well as a variety of ailments but the telomere measurement requires
the analysis of blood samples. Disruptions in our bioenergy levels are suggested to occur well
before the negative effect of stress is revealed in the form of telomeres shortening and lowering
of telomerase levels and subsequent manifestation of ailments in the body.
High level of stress is also known to be a root cause of number of ailments and has been
implicated in accelerated aging (Epel, et al., 2004). Developing restorative methods to slow
down or even reverse the negative effects of stress on health consists of two tasks: (1) To find
measurement methods indicative of elevated stress levels, in addition to routine measurements
such as blood pressure, and (2) Develop methods to reverse the negative effects of stress and
demonstrate their efficacy with the measurement methodology in (1).
Elizabeth Blackburn and associates discovered in the seventies that the tips of human
chromosomes called telomeres act as caps to protect the ends of our chromosomes each time our
cells are divided and the DNA is copied. They also discovered that an enzyme called telomerase
can protect and rebuild telomeres. As we age, telomeres dwindle and when they get too short,
*
Correspondence: Prof. Pradeep B. Deshpande, Six Sigma & advanced Controls, Inc., 1209 Holsworth Lane, Louisville,
KY 40222, http://www.sixsigmaquality.com E-mail: pradeep@sixsigmaquality.com
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
618
our cells malfunction and lose their ability to divide and this is a key process that contributes to
aging. This work eventually earned Dr. Blackburn the 2009 Nobel Prize in physiology and
medicine.
Elissa Epel subsequently collaborated with Blackburn showing that telomerase levels and
telomeres length are strongly correlated with stress levels and that they affect aging. For their
project the team meticulously recruited fifty-eight women who were caring for their chronically
ill children. The results showed that the more stressed the women said they were, the shorter
were their telomeres and lower the telomerase levels (Epel, et al., 2004). This finding is
significant since high stress levels are known to contribute to a large number of ailments
including cancer. The investigators also found that while exercises, eating healthy, social
support, etc., were all restorative, meditation was the most effective intervention capable of
slowing the erosion of telomeres.
In this context, the work of Korotkov’s group assumes significance. In the nineties, the Korotkov
team developed a device called Gas Discharge Visualization (GDV) device for measuring the
bioenergy field of humans (see also Pehlek, 1976). This device offers a painless, noninvasive,
cost-effective, and virtually instantaneous measurement of bioenergy, stress levels, and the state
of Chakras.
In this paper, we present the results of GDV measurements of seven volunteers in Russia with a
specific focus on stress levels and show how this technology may offer prospects for large-scale
applications and is a good tool in self-help programs. Evidence of the restorative benefits of
meditation on the bioenergy field, stress levels, and the state of the chakras is also presented.
Results of This Study
To begin, refer to Figure 1 which shows the bioenergy and chakras of an apparently healthy
individual and another who is quite unwell. Notice the dramatic difference between a normal
individual’s energy field and the disrupted energy field of the unwell individual. Furthermore, all
seven chakras of the normal individual are centered and properly sized. Conversely, the chakras
of the unwell individual are small and off-centered.
This report involves seven individuals thought to be chronically stressed. Figure 2 shows the
bioenergy, numerical values of stress, and the state of chakras of these individuals. The stress
levels of all seven subject are high to very high; normal range is 2 to 4; The figures show that the
higher the stress level, the more disrupted the energy field, and more unbalanced the chakras.
Admittedly the sample size is rather small but the trends are unmistakable.
Figure 3(a) depicts the Before and After GDV images of Rosa who was thought to be suffering
from an elevated level of stress over a weekend meditation course in Spain’s a few years ago.
Rosa reportedly began the weekend program in a very distressed state. She had significantly low
energy and high stress levels, and felt nervous and anxious. After just two and a half days of
meditation, her energy levels had improved dramatically and her stress levels had reduced. She
reported feeling comfortable and relaxed and could not believe the improvement she felt from
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
619
the weekend course. Figure 3(b) depicts the same information for Alfonso in another meditation
program.
Figure 1. Bioenergy Field and Chakras of an Apparently Healthy Individual
(left) and one who is quite unwell (Right)
Illustrations
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(a). Bioenergy Field, Stress Level, and Chakras of Subject 1
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
620
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(b). Bioenergy Field, Stress Level, and Chakras of Subject 2
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
621
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(c). Bioenergy Field, Stress Level, and Chakras of Subject 3
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
622
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(d). Bioenergy Field, Stress Level, and Chakras of Subject 4
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
623
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(e). Bioenergy Field, Stress Level, and Chakras of Subject 5
(Courtesy, Dr. Konstantin Korotkov)
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
624
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(f). Bioenergy Field, Stress Level, and Chakras of Subject 6
(Courtesy Dr. Konstantin Korotkov)
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
625
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 2(g). Bioenergy Field, Stress Level, and Chakras of Subject 7
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
626
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
627
Figure 3 (a). Bioenergy Field and Chakras of Rosa Before and After a 2 ½ - Day-Meditation Program
(www.thebrightpath.com)
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
Figure 3(b). Bioenergy Field Stress and Chakras of Alfonso before and after Meditation
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
628
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
629
By now, a large number of papers in reputed journals have carried full-length articles reporting
on the benefits of meditation in a variety of fields including health and wellness, improvements
in individual and organizational performance including business performance, leadership
decisions, and less discord and violence. These investigations studied the effect of meditation on
brainwaves, heart rate synchronization, and other outcomes. A listing of select papers on
meditation is shown in Table I.
Table I. Articles on Meditation
No.
1
Authors
Benson, H., et al.,
Journal
Nature, 295, 234 – 236, 21
January 1982
PLOS One, 8, 5, May 2013
2
Bhasin, M. K. et al.,
3
4
Boyers, J.
Condon, et al.,
Forbes, May 30, 2013
Psychological Science, August
21, 2013.
5
Deshpande, P. B., et al.,
6
7
8
DeSteno, D.
George B.
Fryer, B.
9
Lutz, et al.,
10
Paul-Labrador, M., et al.
11
Paturel
12
Speca, M., et al.,
13
Tang, Yi-Yuang, et al.,
14
Tang, Yi-Yuang, et al.,
15
Tang, Yi-Yuang, et al.,
16
Tang, Yi-Yuang, et al.,
17
Wallace, R. K.
18
Walton, A. G.
Journal of Consciousness
Exploration & Research, 5, 2,
February 2014.
New York Times, July 5, 2013
HBR Blog, 10 March 10, 2014
HBR Blog Network, September
18, 2013.
PNAS, 101, 46, November 16,
2004.
Archives of Internal Medicine,
166, 1218, 2006.
NeurologyNow,
August/September 2012.
Journal of Biobehavioral
Medicine,, Vol. 62 No. 5, 613622, September 1, 2000.
PNAS, 110, 34, August 28,
2013.
PNAS, 109, 26, 10570-10574,
2012
PNAS, 106, 22, 8865-8870,
2009.
PNAS 104, 43, 17152-17156,
2007.
Science, Vol. 167, No. 3926,
1970.
Forbes, July 24, 2013.
Outcome Investigated
Body Temperature Changes
Metabolism, Insulin Secretion,
Inflammatory pathways
Empathy
Compassionate Response to Suffering
Materialization of Intentions
Compassionate Response to Suffering
Leadership
Compassionate Management
Gamma Wave Synchrony
Metabolic Syndrome and Heart Disease
Meditation as Medicine
Stress Reduction in Cancer Patients
Smoking Reduction
White Matter Changes
Central & Autonomic Nervous System
Attention and Self-Regulation
Physiological effects
Healthcare Costs, Student Performance
In the following we present a Vedic-Yogic-Ayurvedic perspective on stress, health, and ailments.
For a modern physics perspective on health, refer to Deshpande and Kowall (2014). It is
heartwarming that the biochemical, modern physics, and Vedic-Yogic-Ayurvedic perspectives
are strikingly resonant.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
630
Vedic-Yogic-Ayurvedic perspective
Veda-Yoga-Ayurveda say that we have five bodies, not one. The first is what we have come to
recognize as the physical body while the rest are energy sheaths. They are: (1) Annamaya Kosha
– physical body – food sheath, (2) Pranamaya Kosha – pranic energy sheath, (3) Manomaya
Kosha - mind sheath, (4) Dyanamaya Kosha – knowledge sheath, and (5) Anandamaya Kosha –
Blissful body. Each sheath controls all the lower sheaths. Physicists tell us that some 5% of the
universe is matter such as planets, galaxies, stars, etc., 25% is dark matter such as black holes,
and 70% is dark energy. In the Pranamaya Kosha there are seven major energy centers called
chakras that tap the energy from the cosmos, and there is plenty of it out there, which yogis
suggest can provide 70% of our energy requirements. Of the remaining, 10% can come from
food, and 20% from the air we breathe provided we eat and breathe right. Blockages in the
various sheaths disrupt the normal flow of energy to the physical body producing all kinds of
ailments among the first manifestation of which is stress. The Dnyanamaya Kosha houses our
past psychic impressions and unresolved issues. Negative impressions send a disruptive signal to
the Manomaya Kosha which produces negative emotions (anger, hostility, jealousy, hatred,
sorrow) leading to stress and disease. Yoga prescribes Pranayam - Pranic energy - breathing
exercises for maximizing the Pranic energy in the Pranamaya Kosha which has a restorative
effect on health and wellness. Yoga says that meditation works at the subtler levels by dissolving
the karmic impressions in the Dnyanamaya Kosha. Additionally, meditation raises our S
(Sattvic) component and that makes us better human beings, so it is like having our cake and
eating it too.
Our present bioenergy status is predictive of future health while out current health status is
reflective of the cumulative past bioenergy status. Disturbances in our bioenergy field are the
first signs of impending health issues well before the symptoms of the diseases are manifested in
the physical body. And this may provide a path forward for healthier life by adopting better diet,
exercises, yoga, Pranayam, meditation, etc.
Conclusions
The applicability of gas discharge visualization device in the measurement of stress levels is
illustrated. The methodology is cost-effective, noninvasive, painless, and takes only a couple of
minutes to complete. Since meditation has been shown to provide a wide variety of benefits
including reversing the negative effect of stress, the information reported nicely supplements and
complements traditional medical approaches to illnesses.
The work reported here may have profound ramifications. Blackburn and Epel recently wrote a
column in Nature urging World Governments to heed the warning on stress. The first author is in
the process of publishing a book, The Ultimate Reality and How it can Transform Our World:
Evidence from Modern Physics; Wisdom of Yoda, coauthored with James Kowall, which will
show how the path-breaking work of Blackburn and Epel is a subset of the scientific framework
for world transformation.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
631
The GDV method has advantages over other methods such as testing for telomerase levels and
telomere lengths in that it is completely noninvasive, painless, cost-effective, and takes only a
few minutes to complete and this offers prospects for large-scale applications.
Acknowledgments: The authors thank Tony Belak, Ombudsman at the University of Louisville for
bringing the path-breaking work Epel and Blackburn to our attention. The helpful comments of Krishna
Madappa are also appreciated.
References
[1]
[2]
[3]
[4]
[5]
Chez, Ronald, A., Ed., Proceedings: Measuring the Human Energy Field – State of the Science,
The gerontology research Center, National Institute on Aging, National Institute of Health,
Baltimore, MD April 17 - 18, 2002.
Deshpande. P. B., Kowall, J. P., the Ultimate Reality and How it Can Transform our World:
Evidence from Modern Physics; Wisdom of Yoda, Six Sigma and Advanced Controls, Inc.,
January 2015 (estimated)
Deshpande, P. B. and Kowall, J. P., Yogic Perspective on Health, Six Sigma Assessment, and
Quantum Physics Approach, Journal of Consciousness Exploration & Research, 5, 3, April 2014.
Blackburn, Elizabeth and Epel, Elissa, Telomere and Adversity - Too Toxic to Ignore, Nature, 490,
11 October 2012 pp. 169-171.
Epel, Elissa, et al., Accelerated Telomere Shortening in Response to Life Stress, Proceedings of the
National Academy of Sciences, 101, 49, December 2004. pp. 17312-17315.
[6]
Jakovleva E., Korotkov K., Electrophotonic Analysis in Medicine. GDV Bioelectrography
research. 2013. 160 p. Amazon.com.
[7]
Korotkov K.G., Matravers P, Orlov D.V., Williams B.O. Application of Electrophoton Capture
(EPC) Analysis Based on Gas Discharge Visualization (GDV) Technique in Medicine: A
Systematic Review. The J of Alternative and Complementary Medicine. January 2010, 16, 1,
pp.13-25.
[8]
Korotkov K.G., Energy fields Electrophotonic analysis in humans and nature, 2012. 240 p.
e-book: Amazon.com.
[9] Korotkov K. and Orlov D., Analysis of Stimulated Electrophotonic Glow of Liquids.
www.WaterJournal.org V 2, 2010.
[10] Korotkov, K., Madappa, K., Orlov, D., New Approach for Remote Detection of Human
Emotions; Subtle Energies & Energy Medicine • Volume 19 • Number 3 • Page 2; July
2010.
[11] Korotkov K., Korotkin D. Concentration dependence of gas discharge around drops of
inorganic electrolytes. J of Applied Physics, 2001, 89, 9, 4732-4737.
[12] Pehek J. O., Kyler, H. J., and Foust, D. L., Image Modulation in Corona Discharge
Photography, Science, Vol. 194, 263 – 270, October 1976.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
632
Appendix
In the mid-nineties Konstantin Korotkov developed a scientific device based on the ancient
Chinese system of energy meridians for measuring the bio-energy of living organisms and the
environment. The device provides non-invasive, painless and almost immediate evaluation which
can highlight potential health abnormalities prior to even the earliest symptoms of an underlying
condition, and suggests courses of action (9).
GDV utilizes a weak, completely painless electrical current applied to the fingertips for less than
a millisecond. The body’s response to this stimulus is the formation of a variation of an “electron
cloud” composed of light energy photons. The electronic “glow” of this discharge (invisible to
the human eye) is captured by an optical CCD camera system and then translated into a digital
computer file. The data from each test is converted to a unique “Photonic Profile”, which is
compared to the database of hundreds of thousands of data records using 55 distinct parametric
discriminates, and charted so that it is available for discussion and analysis. A graph of the
findings is presented as a two-dimensional image. To study these images, fractal, matrix, and
various algorithmic techniques are linked and analyzed. In addition, the system provides instant
graphic representations of the data to provide easy reference and interpretation. To enhance the
data in an understandable and meaningful manner, a further graphic representation is generated,
placing the indicators within the outline of the human form, for ease of explanation and
discussion. For a more in-depth understanding of GDV, the reader is referred to the papers 8 to
12 under References. GDV has been in the market for over fifteen years and has received
registration as a routine medical diagnostic device by the Russian Ministry of Health upon
recommendation of the Russian Academy of Sciences.
The GDV device has numerous applications the field of medicine and sports. It can determine
the physiological and psycho-emotional state of a human being. The parameters that the GDV
provides indicative of physiological and psycho-emotional state are: (1) Stress level, (2)
Bioenergy intensity, (3) Normality of various organs and systems, and (4) Sate of the Chakras.
These parameters will allow aspirants to gage the extent of progress they are making with their
practices such as Yoga, Pranayam, meditation, medical interventions, etc.
A special software environment was developed for processing and analyzing BIO-grams,
oriented towards the work in different problem domains. Adaptation for particular assessment is
performed through a combination of optimal operations from the library for the given problem
domain, selection of corresponding procedures, and (or) selection of optimal threshold values.
The following main algorithms are included in the library:
Pseudo-coloring. For visual estimation of the image, there are several algorithms of pseudocoloring, oriented towards marking out several peculiarities of BIO -grams. The following
Intensity palette is most commonly used. In this processing, image points are colored in one of
eight colors. The brightest glow points are colored in the shades of blue, less bright points are
colored in the shades of red. Points are colored in yellow when the intensity is higher than the
noise level, but lower than the base noise level for the given frame. All image points removed by
noise filtration are shown as white background. Special programs are designed for the calculation
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 617-633
Deshpande, P. B. & Korotkov, K., Non-invasive Indicators of Stress and Bioenergy Disruption & Benefit of Meditation in
Relieving Stress
633
of the following BIO-gram parameters: Total image area (S): the number of pixels in the image
having brightness above the threshold. Average Intensity (I) is an evaluation of the Intensity
spectrum for the particular BIO-gram. Entropy (Entr) of the image is calculated in accordance
with non-linear algorithm, presented in (13). Energy (E) of light emitted by the subject is equal
to:
E = k S*I (Joules)
(1)
Where k is a numerical coefficient depending on spectral parameters of the particular CCD
camera. For the GDV instruments k = 2*10-4.
The primary outputs of the GDV connected to the eco-sensor are the energy intensity and
entropy of the space. We may state that bias current in the electrical chain depends on the
capacitance of space between antenna and environmental-grounded and electro-conductive
subjects. Both geophysical parameters of the particular environment and man-made
electromagnetic field and constructions would influence this capacitance. This process is being
modeled both experimentally and theoretically (9). Emotions are related to the activity of the
parasympathetic division of the autonomic nervous system, which changes blood
microcirculation, perspiration, sweating, and other functions of the body, resulting in the changes
of the overall conductivity of the body and the conductivity of acupuncture points in particular.
Therefore, the presence of the emotional people in the vicinity of the instrument may change the
conductivity of space and, hence, the signals of the sensor. This may be related to the formation
of areas of decreased entropy in space, or, as Dr. W. A. “Bill” Tiller, Professor Emeritus and
former Chair of the Material Science and Engineering Department at Stanford suggests,
“Associated with the buildup of a negative magnetic charge manifesting in the environment”.
Some quantum effects may be involved as well.
ISSN: 2153-8212
Journal of Consciousness Exploration and Research
QuantumDream, Inc.
www.JCER.com |
Falsification and consciousness
Johannes Kleiner∗1 and Erik Hoel†2
arXiv:2004.03541v3 [q-bio.NC] 28 Apr 2021
1
Munich Center for Mathematical Philosophy, Ludwig Maximilian University of Munich
2
Allen Discovery Center, Tufts University, Medford, MA, USA
April 29, 2021
Abstract
The search for a scientific theory of consciousness should result in theories that are falsifiable. However, here we show that falsification is especially problematic for theories of consciousness. We formally
describe the standard experimental setup for testing these theories. Based on a theory’s application
to some physical system, such as the brain, testing requires comparing a theory’s predicted experience
(given some internal observables of the system like brain imaging data) with an inferred experience (using
report or behavior). If there is a mismatch between inference and prediction, a theory is falsified. We
show that if inference and prediction are independent, it follows that any minimally informative theory
of consciousness is automatically falsified. This is deeply problematic since the field’s reliance on report
or behavior to infer conscious experiences implies such independence, so this fragility affects many contemporary theories of consciousness. Furthermore, we show that if inference and prediction are strictly
dependent, it follows that a theory is unfalsifiable. This affects theories which claim consciousness to be
determined by report or behavior. Finally, we explore possible ways out of this dilemma.
1
Introduction
Successful scientific fields move from exploratory studies and observations to the point where theories are
proposed that can offer precise predictions. Within neuroscience the attempt to understand consciousness
has moved out of the exploratory stage and there are now a number of theories of consciousness capable of
predictions that have been advanced by various authors (Koch et al., 2016).
At this point in the field’s development falsification has become relevant. In general, scientific theories
should strive to make testable predictions (Popper, 1959). In the search for a scientific theory of consciousness, falsifiability must be considered explicitly as it is commonly assumed that consciousness itself cannot
be directly observed, instead it can only be inferred based off of report or behavior.
Contemporary neuroscientific theories of consciousness first began to be proposed in the early 1990s
(Crick, 1994). Some have been based directly on neurophysiological correlates, such as proposing that
consciousness is associated with neurons firing at a particular frequency (Crick and Koch, 1990) or activity
in some particular area of the brain like the claustrum (Crick and Koch, 2005). Other theories have focused
more on the dynamics of neural processing, such as the degree of recurrent neural connectivity (Lamme,
2006). Others yet have focused on the “global workspace” of the brain, based on how signals are propagated
across different brain regions (Baars, 1997). Specifically, Global Neuronal Workspace theory claims that
consciousness is the result of an “avalanche” or “ignition” of widespread neural activity created by an
interconnected but dispersed network of neurons with long-range connections (Sergent and Dehaene, 2004).
Another avenue of research strives to derive a theory of consciousness from analysis of phenomenal experience. The most promising example thereof is Integrated Information Theory (Tononi, 2004, 2008; Oizumi
et al., 2014). Historically, Integrated Information Theory is the first well-formalized theory of consciousness.
It was the first (and arguably may still be the lone) theory that makes precise quantitative predictions about
∗ Johannes.Kleiner@lmu.de
† corresponding author: erik.hoel@tufts.edu
1
both the contents and level of consciousness (Tononi, 2004). Specifically, the theory takes the form of a
function, the input of which is data derived from some physical system’s internal observables, while the
output of this function are predictions about the contents of consciousness (represented mathematically as
an element of an experience space) and the level of consciousness (represented by a scalar value Φ).
Both Global Neuronal Workspace (GNW) and Integrated Information Theory (IIT) have gained widespread
popularity, sparked general interest in consciousness, and have led to dozens if not hundreds of new empirical
studies (Massimini et al., 2005; Del Cul et al., 2007; Dehaene and Changeux, 2011; Gosseries et al., 2014;
Wenzel et al., 2019). Indeed, there are already significant resources being spent attempting to falsify either
GNW or IIT in the form of a global effort pre-registering predictions from the two theories so that testing
can be conducted in controlled circumstances by researchers across the world (Ball., 2019; Reardon, 2019).
We therefore often refer to both GNW and IIT as exemplar theories within consciousness research and show
how our results apply to both. However, our results and reasoning apply to most contemporary theories, e.g.
(Lau and Rosenthal, 2011; Chang et al., 2019), particularly in their ideal forms. Note that we refer to both
“theories” of consciousness and also “models” of consciousness, and use these interchangeably (Seth, 2007).
Due to IIT’s level of formalization as a theory, it has triggered the most in-depth responses, expansions,
and criticisms (Cerullo, 2015; Bayne, 2018; Mediano et al., 2019; Kleiner and Tull, 2020) since well-formalized
theories are much easier to criticize than non-formalized theories. Recently one criticism levied against IIT
was based on how the theory predicts feedfoward neural networks have zero Φ and recurrent neural networks
have non-zero Φ. Since a given recurrent neural network can be “unfolded” into a feedfoward one while
preserving its output function, this has been argued to render IIT outside the realm of science (Doerig et al.,
2019). Replies have criticised the assumptions which underlie the derivation of this argument (Kleiner, 2020;
Tsuchiya et al., 2019).
Here we frame and expand concerns around testing and falsification of theories by examining a more
general question: what are the conditions under which theories of consciousness (beyond IIT alone) can be
falsified? We outline a parsimonious description of theory testing with minimal assumptions based on first
principles. In this agnostic setup falsifying a theory of consciousness is the result of finding a mismatch
between the inferred contents of consciousness (usually based on report or behavior) and the contents of
consciousness as predicted by the theory (based on the internal observables of the system under question).
This mismatch between prediction and inference is critical for an empirically meaningful scientific agenda,
because a theory’s prediction of the state and content of consciousness on its own cannot be assessed. For
instance, imagine a theory that predicts (based on internal observables like brain dynamics) that a subject is
seeing an image of a cat. Without any reference to report or outside information, there can be no falsification
of this theory, since it cannot be assessed whether the subject was actually seeing a “dog” rather than “cat.”
Falsifying a theory of consciousness is based on finding such mismatches between reported experiences and
predictions.
In the following work, we formalize this by describing the prototypical experimental setup for testing a
theory of consciousness. We come to a surprising conclusion: a widespread experimental assumption implies
that most contemporary theories of consciousness are already falsified.
The assumption in question is the independence of an experimenter’s inferences about consciousness from
a theory’s predictions. To demonstrate the problems this independence creates for contemporary theories, we
introduce a “substitution argument.” This argument is based on the fact that many systems are equivalent
in their reports (e.g., their outputs are identical for the same inputs) and yet their internal observables may
differ greatly. This argument constitutes both a generalization and correction of the “unfolding argument”
against IIT presented in Doerig et al. (2019). Examples of such substitutions may involve substituting a
brain with a Turing machine or a cellular automaton since both types of systems are capable of universal
computation (Turing, 1937; Wolfram, 1984) and hence may emulate the brain’s responses, or replacing a
deep neural network with a single-layer neural network, since both types of networks can approximate any
given function (Hornik et al., 1989; Schäfer and Zimmermann, 2006).
Crucially, our results do not imply that falsifications are impossible. Rather, they show that the independence assumption implies that whenever there is an experiment where a theory’s predictions based on
internal observables and a system’s reports agree, there exists also an actual physical system that falsifies
the theory. One consequence is that the “unfolding argument” concerning IIT (Doerig et al., 2019) is merely
a small subset of a much larger issue that affects all contemporary theories which seek to make predictions
about experience off of internal observables. Our conclusion shows that if independence holds, all such
2
theories come falsified a priori. Thus, instead of putting the blame of this problem on individual theories
of consciousness, we show that it is due to issues of falsification in the scientific study of consciousness,
particularly the field’s contemporary usage of report or behavior to infer conscious experiences.
A simple response to avoid this problem is to claim that report and inference are not independent. This
is the case, e.g., in behaviorist theories of consciousness, but arguably also in Global Workspace Theory
(Baars, 2005), the “attention schema” theory of consciousness (Graziano and Webb, 2015) or “fame in the
brain” (Dennett, 1993) proposals. We study this answer in detail and find that making a theory’s predictions
and an experimenter’s inferences strictly dependent leads to pathological unfalsifiability.
Our results show that if independence of prediction and inference holds true, as in contemporary cases
where report about experiences is relied upon, it is likely that no current theory of consciousness is correct.
Alternatively, if the assumption of independence is rejected, theories rapidly become unfalsifiable. While this
dilemma may seem like a highly negative conclusion, we take it to show that our understanding of testing
theories of consciousness may need to change to deal with these issues.
2
Formal description of testing theories
Here we provide a formal framework for experimentally testing a particular class of theories of consciousness.
The class we consider makes predictions about the conscious experience of physical systems based on observations or measurements. This class describes many contemporary theories, including leading theories such
as Integrated Information Theory (Oizumi et al., 2014), Global Neuronal Workspace Theory (Dehaene and
Changeux, 2004), Predictive Processing (when applied to account for conscious experience (Dolega and Dewhurst, 2020; Clark, 2019; Seth, 2014; Hobson et al., 2014; Hohwy, 2012)) or Higher Order Thought Theory
(Rosenthal, 2002). These theories may be motivated in different ways, or contain different formal structures,
such as for example the ones of category theory (Tsuchiya et al., 2016). In some cases, contemporary theories
in this class may lack the specificity to actually make precise predictions in their current form. Therefore, the
formalisms we introduce may sometimes describe a more advanced form of a theory, one that can actually
make predictions.
In the following section, we introduce the necessary terms to define how to falsify this class of theories:
how measurement of a physical system’s observables results in datasets (Section 2.1), how a theory makes use
of those datasets to offer predictions about consciousness (Section 2.2), how an experimenter makes inferences
about a physical system’s experiences (Section 2.3), and finally how falsification of a theory occurs when
there is a mismatch between a theory’s prediction and an experimenter’s inference (Section 2.4). In Section
2.5 we give a summary of the introduced terms. In subsequent sections we explore the consequences of
this setup, such as how all contemporary theories are already falsified if the data used by inferences and
predictions are independent, and also how theories are unfalsifiable if this is changed to a strict form of
dependency.
2.1
Experiments
All experimental attempts to either falsify or confirm a member of the class of theories we consider begin
by examining some particular physical system which has some specific physical configuration, state, or
dynamics, p. This physical system is part of a class P of such systems which could have been realized, in
principle, in the experiment. For example, in IIT, the class of systems P may be some Markov chains, set
of logic gates, or neurons in the brain, and every p ∈ P denotes that system being in a particular state at
some time t. On the other hand, for Global Neuronal Workspace, P might comprise the set of long-range
cortical connections that make up the global workspace of the brain, with p being the activity of that global
workspace at that time.
Testing a physical system necessitates experiments or observations. For instance, neuroimaging tools like
fMRI or EEG have to be used in order to obtain information about the brain. This information is used to
create datasets such as functional networks, wiring diagrams, models, or transition probability matrices. To
formalize this process, we denote by O all possible datasets that can result from observations of P . Each
o ∈ O is one particular dataset, the result of carrying out some set of measurements on p. We denote the
datasets that can result from measurements on p as obs(p). Formally:
3
obs : P O ,
(1)
where obs is a correspondence, which is a “generalized function” that allows more than one element in the
image obs(p) (functions are a special case of correspondences). A correspondence is necessary because, for a
given p, various possible datasets may arise, e.g., due to different measurement techniques such as fMRI vs.
EEG, or due to the stochastic behaviour of the system, or due to varying experimental parameters. In the
real world, data obtained from experiments may be incomplete or noisy, or neuroscientific findings difficult
to reproduce (Gilmore et al., 2017). Thus for every p ∈ P , there is a whole class of datasets which can result
from the experiment.
Note that obs describes the experiment, the choice of observables, and all conditions during an experiment
that generates the dataset o necessary to apply the theory, which may differ from theory to theory, such as
interventions in the case of IIT. In all realistic cases, the correspondence obs is likely quite complicated since
it describes the whole experimental setup. For our argument it simply suffices that this mapping exists, even
if it is not known in detail.
It is also worth noting here that all leading neuroscientific theories of consciousness, from IIT to GNW,
assume that experiences are not observable or directly measurable when applying the theory to physical
systems. That is, experiences themselves are never identified or used in obs, but are rather inferred based
on some dataset o that contains report or other behavioural indicators.
Next we explore how the datasets in O are used to make predictions about the experience of a physical
system.
2.2
Predictions
A theory of consciousness makes predictions about the experience of some physical system in some configuration, state, or dynamics, p, based on some dataset o. To this end, a theory carries within its definition
a set or space E whose elements correspond to various different conscious experiences a system could have.
The interpretation of this set varies from theory to theory, ranging from descriptions of the level of conscious
experience in early versions of IIT, descriptions of the level and content of conscious experience in contemporary IIT (Kleiner and Tull, 2020), or the description only of whether a presented stimuli is experienced in
GNW or HOT. We sometimes refer to elements e of E simply as experiences.
Formally, this means that a prediction considers an experimental dataset o ∈ O (determined by obs)
and specifies an element of the experience space E. We denote this as pred, for “prediction,” which is a
map from O to E. The details of how individual datasets are being used to make predictions again do not
matter for the sake of our investigation. What matters is that a procedure exists, and this is captured by
pred. However, we have to take into account that a single dataset o ∈ O may not predict only one single
experience. In general, pred may only allow an experimenter to constrain experience of the system in that
it only specifies a subset of all experiences a theory models. We denote this subset by pred(o). Thus, pred
is also a correspondence
pred : O E .
Shown in Figure 1 are the full set of terms needed to formally define how most contemporary theories
of consciousness make predictions about experience. So far, what we have said is very general. Indeed, the
force and generalizability of our argument comes from the fact that we do not have to define pred explicitly
for the various models we consider. It suffices that it exists, in some form or the other, for the models under
consideration.
It is crucial to note that predicting states of consciousness alone does not suffice to test a model of
consciousness. Some have previously criticized theories of consciousness, IIT in particular, just based off
of their counter-intuitive predictions. An example is the criticism that relatively simply grid-like networks
have high Φ (Aaronson, 2014; Tononi, 2014). However, debates about counter-intuitive predictions are not
meaningful by themselves, since pred alone does not contain enough information to say whether a theory is
true or false. The most a theory could be criticized for is either not fitting our own phenomenology or not
being parsimonious enough, neither of which are necessarily violated by counter-intuitive predictions. For
example, it may actually be parsimonious to assume that many physical systems have consciousness (Goff,
2017). That is, speculation about acceptable predictions by theories of consciousness must implicitly rely on
4
P
obs
pred
O
E
Figure 1: We assume that an experimental setup apt for a particular model of consciousness has been chosen for some
class of physical systems P , wherein p ∈ P represents the dynamics or configurations of a particular physical system.
O then denotes all datasets that can arise from observations or measurements on P . Measuring the observables of
p maps to datasets o ∈ O, which is denoted by the obs correspondence. E represents the mathematical description
of experience given by the theory or model of consciousness under consideration. In the simplest case, this is just
a set whose elements indicate whether a stimulus has been perceived consciously or not, but far more complicated
structures can arise (e.g., in IIT). The correspondence pred describes the process of prediction as a map from O to
E.
a comparative reference to be meaningful, and speculations that are not explicit about their reference are
uninformative.
2.3
Inferences
As discussed in the previous section, a theory is unfalsifiable given just predictions alone, and so pred must
be compared to something else. Ideally this would be the actual conscious experience of the system under
investigation. However, as noted previously, the class of theories we focus on here assumes that experience
itself is not part of the observables. For this reason, the experience of a system must be inferred separately
from a theory’s prediction to create a basis of comparison. Most commonly, such inferences are based on
reports. For instance, an inference might be based on an experimental participant reporting on the switching
of some perceptually bistable image (Blake et al., 2014) or on reports about seen vs. unseen images in
masking paradigms (Alais et al., 2010).
It has been pointed out that report in a trial may interfere with the actual isolation of consciousness, and
there has recently been the introduction of so-called “no-report paradigms” (Tsuchiya et al., 2015). In these
cases, report is first correlated to some autonomous phenomenon like optokinetic nystagmus (stereotyped
eye movement), and then the experimenter can use this instead of the subject’s direct reports to infer their
experiences. Indeed, there can even be simpler cases where report is merely assumed: e.g., that in showing
a red square a participant will experience a red square without necessarily asking the participant, since
previously that participant has proved compos mentis. Similarly, in cases of non-humans incapable of verbal
report, “report” can be broadly construed as behavior or output.
All these cases can be broadly described as being a case of inference off of some data. This data might
be actual reports (like a participant’s button pushes) or may be based off of physiological reactions (like
no-report paradigms) or may be the outputs of a neural network or set of logic gates, such as the results of
an image classification task (LeCun et al., 2015). Therefore, the inference can be represented as a function,
inf (o), between a dataset o generated by observation or measurement of the physical system, and the set of
postulated experiences in the model of consciousness, E:
inf : O → E .
Defining inf as a function means that we assume that for every experimental dataset o, one single
experience in E is inferred during the experiment. Here we use a function instead of a correspondence for
technical and formal ease, which does not affect our results: If two correspondences to the same space are
given, one of them can be turned into a function.1 The inf function is flexible enough to encompass both
direct report, no-report, input/output analysis, and also assumed-report cases. It is a mapping that describes
the process of inferring the conscious experience of a system from data recorded in the experiments. Both
inf and pred are depicted in Figure 2.
It is worth noting that we have used here the same class O as in the definition of the prediction mapping
pred above. This makes sense because the inference process also uses data obtained in experimental trials,
1 If inf is a correspondence, one defines a new space E 0 by E 0 := {inf (o) | o ∈ O}. Every individual element of this space
describes exactly what can be inferred from one dataset o ∈ O, so that inf 0 : O → E 0 is a function. The correspondence obs is
then redefined, for every e0 ∈ E 0 , by the requirement that e0 ∈ obs0 (o) iff e ∈ obs(o) for some e ∈ e0 .
5
pred
P
obs
O
E
inf
Figure 2: Two maps are necessary for a full experimental setup, one that describes a theory’s predictions about
experience (pred), another that describes the experimenter’s inference about it (inf ). Both map from a dataset o ∈ O
collected in an experimental trail to some subset of experiences described by the model, E.
such as reports by a subject. So both pred and inf can be described to operate on the same total dataset
measured, even though they usually use different parts of this dataset (cf. below).
2.4
Falsification
We have now introduced all elements which are necessary to formally say what a falsification of a theory of
consciousness is. To falsify a theory of consciousness requires mismatch between an experimenter’s inference
(generally based on report) and the predicted consciousness of the subject. In order to describe this, we
consider some particular experimental trial, as well as inf and pred.
Definition 2.1. There is a falsification at o ∈ O if we have
inf (o) 6∈ pred(o) .
(2)
This definition can be spelled out in terms of individual components of E. To this end, for any given
dataset o ∈ O, let er := inf (o) denote the experience that is being inferred, and let ep ∈ obs(o) be one of
the experiences that is predicted based off of some dataset. Then (2) simply states that we have ep 6= er
for all possible predictions ep ∈ obs(o). None of the predicted states of experience is equal to the inferred
experience.
What does Equation (2) mean? There are two cases which are possible. Either, the prediction based
on the theory of consciousness is correct and the inferred experience is wrong. Or the prediction is wrong,
so that in this case the model would be falsified. In short: Either the prediction process or the inference
process is wrong.
We remark that if there is a dataset o on which the inference procedure inf or the prediction procedure
pred cannot be used, then this dataset cannot be used in falsifying a model of consciousness. Thus, when it
comes to falsifications, we can restrict to datasets o for which both procedures are defined.
In order to understand in more detail what is going on if (2) holds, we have to look into a single dataset
o ∈ O. This will be of use later.
Generally, inf and obs will make use of different part of the data obtained in an experimental trial. E.g.,
in the context of IIT or GNW, data about the internal structure and state of the brain will be used for the
prediction. This data can be obtained from an fMRI scan or EEG measurement. The state of consciousness
on the other hand can be inferred from verbal reports. Pictorially, we may represent this as in Figure 3. We
use the following notation:
oi For a chosen dataset o ∈ O, we denote the part of the dataset which is used for the prediction process
by oi (for ‘internal’ data). This can be thought of as data about the internal workings of the system.
We call oi the prediction data in o.
or For a chosen dataset o ∈ O, we denote the part of the dataset which is used for inferring the state of
experience by or (for ‘report’ data). We call it the inference data in o.
Note that in both cases, the subscript can be read similarly as the notation for restricting a set. We remark
that a different kind of prediction could be considered as well, where one makes use of the inverse of pred.
In Appendix B, we prove that this is in fact equivalent to the case considered here, so that Definition 2.1
indeed covers the most general situation.
6
o∈O
pred(o)
E
pred(o)
ep
oi
p
or
er
inf (o)
Figure 3: This figure represents the same setup as Figure 2. The left circle depicts one single dataset o. oi
(orange) is the part of the dataset used for prediction. or (green) is the part of the dataset used for inferring
the state of experience. Usually the green area comprises verbal reports or button presses, whereas the
orange area comprises the data obtained from brain scans. The right circle depicts the experience space E
of a theory under consideration. ep denotes a predicted experience while er denotes the inferred experience.
Therefore, in total, to represent some specific experimental trial we use p ∈ P , o ∈ O, er ∈ E and ep ∈ E,
where ep ∈ pred(o).
2.5
Summary
In summary, for testing of a theory of consciousness we have introduced the following notion:
P denotes a class of physical systems that could have been tested, in principle, in the experiment under
consideration, each in various different configurations. In most cases, every p ∈ P thus describes a
physical system in a particular state, dynamical trajectory, or configuration.
obs is a correspondence which contains all details on how the measurements are set up and what is
measured. It describes how measurement results (datasets) are determined by a system configuration
under investigation. This correspondence is given, though usually not explicitly known, once a choice
of measurement scheme has been made.
O is the class of all possible datasets that can result from observations or measurements of the systems
in the class P . Any single experimental trail results in a single dataset o ∈ O, whose data is used for
making predictions based on the theory of consciousness and for inference purposes.
pred describes the process of making predictions by applying some theory of consciousness to a dataset o.
It is therefore a mapping from O to E.
E denotes the space of possible experiences specified by the theory under consideration. The result of
the prediction is a subset of this space, denoted as pred(o). Elements of this subset are denoted by ei
and describe predicted experiences.
inf describes the process of inferring a state of experience from some observed data, e.g. verbal reports,
button presses or using no-report paradigms. Inferred experiences are denoted by er .
3
The substitution argument
Substitutions are changes of physical systems (i.e., the substitution of one for another) that leave the inference
data invariant, but may change the result of the prediction process. A specific case of substitution, the
unfolding of a reentrant neural network to a feed-forward one, was recently applied to IIT to argue that IIT
cannot explain consciousness (Doerig et al., 2019).
Here we show that, in general, the contemporary notion of falsification in the science of consciousness
exhibits this fundamental flaw for almost all contemporary theories, rather than being a problem for a
7
particular theory. This flaw is based on the independence between the data used for inferences about
consciousness (like reports) and the data used to make predictions about consciousness. We discuss various
responses to this flaw in Section 5.
We begin by defining what a substitution is in Section 3.1, show that it implies falsifications in Section 3.2,
and analyze the particularly problematic case of universal substitutions in Section 3.3. In Section 3.4, we
prove that universal substitutions exist if prediction and inference data are independent and give some
examples of already-known cases.
3.1
Substitutions
In order to define formally what a substitution is, we work with the inference content or of a dataset o as
introduced in Section 2.4. We first denote the class of all physical configurations which could have produced
the inference content or upon measurement by Por . Using the correspondence obs which describes the
relation between physical systems and measurement results, this can be defined as
Por := { p ∈ P | or ∈ obs(p) } ,
(3)
where obs(p) denotes all possible datasets that can be measured if the system p is under investigation and
where or ∈ obs(p) is a shorthand for o ∈ obs(p) with inference content or .
Any map of the form S : Por → Por takes a system configuration p which can produce inference content or
to another system’s configuration S(p) which can produce the same inference content. This allows us to define
what a substitution is formally. In what follows, the ◦ indicates the composition of the correspondences obs
and pred to give a correspondence from P to E, which could also be denoted as pred(obs(p)),2 and ∩ denotes
the intersection of sets.
Definition 3.1. There is a or -substitution if there is a transformation S : Por → Por such that at least for
one p ∈ Por
pred ◦ obs(p) ∩ pred ◦ obs(S(p)) = ∅ .
(4)
In words, a substitution requires there to be a transformation S which keeps the inference data constant
but changes the prediction of the system. So much in fact that the prediction of the original configuration p
and of the transformed configuration S(p) are fully incompatible, i.e. there is no single experience e which is
contained in both predictions. Given some inference data or , an or -substitution then requires this to be the
case for at least one system configuration p that gives this inference data. In other words, the transformation
S is such that for at least one p, the predictions change completely, while the inference content or is preserved.
A pictorial definition of substitutions is given in Figure 4. We remark that if pred and obs were functions,
so that pred ◦ obs(p) only contained one element, Equation (4) would be equivalent to pred(obs(p)) 6=
pred(obs(S(p))).
We will find below that the really problematic case arises if there is an or -substitution for every possible
inference content or . We refer to this case as a universal substitution.
Definition 3.2. There is a universal substitution if there is an or -substitution Sor : Por → Por for every or .
We recall that according to the notation introduced in Section 2.4, the inference content of any dataset
o ∈ O is denoted by or (adding the subscript r). Thus the requirement is that there is an or -substitution
Sor : Por → Por for every inference data that can pertain in the experiment under consideration (for every
inference data that is listed in O). The subscript or of Sor indicates that the transformation S in Definition 3.1
can be chosen differently for different or . Definition 3.2 does not require there to be one single transformation
that works for all or .
3.2
Substitutions imply falsifications
The force of our argument comes from the fact that if there are substitutions, then this necessarily leads to
mismatches between inferences and predictions. This is shown by the following lemma.
2 I.e., pred ◦ obs(p) = {e ∈ E | e ∈ pred(o) for some o ∈ obs(p)}, it is the image under pred of the set obs(o).
8
pred(o0 )
o resp. o0
E
pred(o)
e0p
o0i
T (p)
pred(o0 )
ep
pred(o)
oi
p
er = e0r
or = o0r
inf (o)
Figure 4: This picture illustrates substitutions. Assume that some dataset o with inference content or
is given. A substitution is a transformation S of physical systems which leaves the inference content or
invariant but which changes the result of the prediction process. Thus whereas p and S(p) have the same
inference content or , the prediction content of experimental datasets is different; different in fact to such
an extend that the predictions of consciousness based on these datasets are incompatible (illustrated by the
non-overlapping gray circles on the right). Here we have used that by definition of Por , every p̃ ∈ Por yields
at least one dataset o0 with the same inference content as o and have identified o and o0 in the drawing.
Lemma 3.3. If there is a or -substitution, there is a falsification at some o ∈ O.
Proof. Let p be the physical system in Definition 3.1 and define p0 = S(p). Let o ∈ obs(p) be a dataset
of p which has inference content or and let o0 be a dataset of p0 which has the same inference content or ,
guaranteed to exist by the definition of Por in (3). Equation (4) implies that
pred(o) ∩ pred(o0 ) = ∅ .
(5)
Since, however, or = o0r , we have inf (o) = inf (o0 ). Thus we have either inf (o) 6∈ pred(o) or inf (o0 ) 6∈
pred(o0 ), or both. Thus there is either a falsification at o, a falsification at o0 , or both.
The last lemma shows that if there are substitutions, then there are necessarily falsifications. This might,
however, not be considered too problematic, since it could always be the case that the model is right whereas
the inferred experience is wrong. Inaccessible predictions are not unusual in science. A fully problematic
case only pertains for universal substitutions, i.e., if there is an or -substitution for every inference content
or that can arise in an experiment under consideration.
3.3
Universal substitutions imply complete falsification
In Section 2.4, we have defined falsifications for individual datasets o ∈ O. Using the ‘insight view’ of single
datasets, we can refine this definition somewhat by relating it to the inference content only.
Definition 3.4. There is an or -falsification if there is a falsification for some o ∈ O which has inference
content or .
This definition is weaker than the original definition, because among all datasets which have inference
content or , only one needs to exhibit a falsification. Using this notion, the next lemma specifies the exact
relation between substitutions and falsifications.
Lemma 3.5. If there is an or -substitution, there is an or -falsification.
Proof. This lemma follows directly from the proof of Lemma 3.3 because the datasets o and o0 used in that
proof both have inference content or .
9
This finally allows us to show our first main result. It shows that if a universal substitution exists, the
theory of consciousness under consideration is falsified. We explain the meaning of this proposition after the
proof.
Proposition 3.6. If there is a universal substitution, there is an or -falsification for all possible inference
contents or .
Proof. By definition of universal substitution, there is an or -substitution for every or . Thus the claim follows
directly from Lemma 3.5.
In combination with Definition 3.4, this proposition states that for every possible report (or any other
type of inference procedure, cf. our use of terminology in Section 2.4), there is a dataset o which contains
the report’s data and for which we have
inf (or ) ∈
/ pred(o) ,
(6)
where we have slightly abused notation in writing inf (or ) instead of inf (o) for clarity. This implies that one
of two cases needs to pertain: Either at least one of the inferred experiences inf (or ) is correct, in which case
the corresponding prediction is wrong and the theory needs to be considered falsified. The only other option
is that for all inference contents or , the prediction pred(o) is correct, which qua (6) implies that no single
inference inf (or ) points at the correct experience, so that the inference procedure is completely wrong. This
shows that Proposition 3.6 can equivalently be stated as follows.
Proposition 3.7. If there is a universal substitution, either every single inference operation is wrong or the
theory under consideration is already falsified.
Next, we discuss under which circumstances a universal substitution exists.
3.4
When does a universal substitution exist?
In the last section, we have seen that if a universal substitution exists, this has strong consequences. In this
section, we discuss under what conditions universal substitutions exist.
3.4.1
Theories need to be minimally informative
We have taken great care above to make sure that our notion of prediction is compatible with incomplete or
noisy datasets. This is the reason why pred is a correspondence, the most general object one could consider.
For the purpose of this section, we add a gentle assumption which restricts pred slightly: we assume that
every prediction carries at least a minimal amount of information. In our case, this means that for every
prediction pred(o), there is at least one other prediction pred(o0 ) which is different from pred(o). Put in
simple terms, this means that we don’t consider theories of consciousness which have only a single prediction.
In order to take this into account, for every o ∈ O, we define ō := obs(obs−1 (o)), which comprises exactly
all those datasets which can be generated by physical systems p that also generate o. When applying our
previous definitions, this can be fleshed out as
ō = { o0 | ∃ p such that o ∈ obs(p) and o0 ∈ obs(p) } .
(7)
Using this, we can state our minimal information assumption in a way that is compatible with the general
setup displayed in Figure 2:
We assume that the theories of consciousness under consideration are minimally informative in that for
every o ∈ O, there exists an o0 ∈ O such that
pred(ō) ∩ pred(ō0 ) = ∅ .
10
(8)
3.4.2
Inference and prediction data are independent
We have already noted, that in most experiments, the prediction content oi and inference content or consist
of different parts of a dataset. What is more, they are usually assumed to be independent, in the sense that
changes in oi are possible while keeping or constant. This is captured by the next definition.
Definition 3.8. Inference and prediction data are independent if for any oi , o0i and or , there is a variation
ν:P →P
(9)
such that oi ∈ obs(p), o0i ∈ obs(ν(p)) but or ∈ obs(p) and or ∈ obs(ν(p)) for some p ∈ P .
Here, we use the same shorthand as in (3). For example, the requirement oi ∈ obs(p) is a shorthand for
there being an o ∈ obs(p) which has prediction content oi . The variation ν in this definition is a variation
in P , which describes physical systems which could, in principle, have been realized in an experiment (cf.
Section 2.5). We note that a weaker version of this definition can be given which still implies our results
below, cf. Appendix A. Note that if inference and prediction data are not independent, e.g. because they
have a common cause, problems of tautologies loom large, cf. Section 5. Throughout the text we often refer
to Definition 3.8 simply as “independence”.
3.4.3
Universal substitutions exist
Combining the last two sections, we can now prove that universal substitutions exist.
Proposition 3.9. If inference and prediction data are independent, universal substitutions exist.
Proof. To show that a universal substitution exists, we need to show that for every o ∈ O, an or -substitution
exists (Definition 3.1). Thus assume that an arbitrary o ∈ O is given. The minimal information assumption
guarantees that there is an o0 such that Equation (8) holds. As before, we denote the prediction content of
o and o0 by oi and o0i , respectively, and the inference content of o by or .
Since inference and prediction data are independent, there exists a p ∈ P as well as a ν : P → P such
that oi ∈ obs(p), o0i ∈ obs(ν(p)), or ∈ obs(p) and or ∈ obs(ν(p)). By Definition (7), the first two of these four
conditions imply that obs(p) ⊂ ō and obs(ν(p)) ⊂ ō0 . Thus Equation (8) applies and allows us to conclude
that
pred(obs(p)) ∩ pred(obs(ν(p)) = ∅ .
Via Equation (3), the latter two of the four conditions imply that p ∈ Por and ν(p) ∈ Por . Thus we may
restrict ν to Por to obtain a map
S : Por → Por ,
which in light of the first part of this proof exhibits at least one p ∈ Por which satisfies (4). Thus we have
shown that an or -substitution exists. Since o was arbitrary, it follows that a universal substitution exists.
The intuition behind this proof is very simple. In virtue of our assumption that theories of consciousness
need to be minimally informative, for any dataset o, there is another dataset o0 which makes a non-overlapping
prediction. But in virtue of inference and prediction data being independent, we can find a variation that
changes the prediction content as prescribed by o and o0 , but keeps the inference content constant. This
suffices to show that there exists a transformation S as required by the definition of a substitution.
Combining this result with Proposition 3.7, we finally can state our main theorem.
Theorem 3.10. If inference and prediction data are independent, either every single inference operation is
wrong or the theory under consideration is already falsified.
Proof. The theorem follows by combining Proposition 3.9 and Proposition 3.7.
In the next section, we give several examples of universal substitutions, before discussing various possible
responses to our result in Section 5.
11
3.4.4
Examples of data independence
Our main theorem shows that testing a theory of consciousness will necessarily lead to its falsification
if inference and prediction data are independent (Definition 3.8), and if at least one single inference can
be trusted (Theorem 3.10). In this section, we give several examples that illustrate the independence of
inference and prediction data. We take report to mean output, behavior, or verbal report itself and assume
that prediction data derives from internal measurements.
Artificial neural networks. ANNs, particularly those trained using deep learning, have grown increasingly
powerful and capable of human-like performance (LeCun et al., 2015; Bojarski et al., 2016). For any ANN,
report (output) is a function of node states. Crucially, this function is non-injective, i.e. some nodes are not
part of the output. E.g., in deep learning, the report is typically taken to consist of the last layer of the ANN,
while the hidden layers are not taken to be part of the output. Correspondingly, for any given inference data,
one can construct a ANN with arbitrary prediction data by adding nodes, changing connections and changing
those nodes which are not part of the output. Put differently, one can always substitute a given ANN with
another with different internal observables but identical or near-identical reports. From a mathematical
perspective it is well-known that both feed-forward ANNs and recurrent ANNs can approximate any given
function (Hornik et al., 1989; Schäfer and Zimmermann, 2006). Since reports are just some function, it
follows that there are viable universal substitutions.
A special case thereof is the unfolding transformation considered in Doerig et al. (2019) in the context
of IIT. The arguments in this paper constitute a proof of the fact that for ANNs, inference and prediction
data are independent (Definition 3.8). Crucially, our main theorem shows that this has implications for
all minimally informative theories of consciousness. A similar result (using a different characterization of
theories of consciousness than minimally informative) has been shown in (Kleiner, 2020).
Universal computers. Turing machines are extremely different in architecture than ANNs. Since they
are capable of universal computation (Turing, 1937) they should provide an ideal candidate for a universal
substitution. Indeed, this is exactly the reasoning behind the Turing test of conversational artificial intelligence (Turing, 2009). Therefore, if one believes it is possible for a sufficiently fast Turing machine to pass
the Turing test, one needs to accept that substitutions exist. Notably, Turing machines are just one example
of universal computation, and there are other instances of different parameter spaces or physical systems
that are capable thereof, such as cellular automata (Wolfram, 1984).
Universal intelligences. There are models of universal intelligence that allow for maximally intelligent
behavior across any set of tasks (Hutter, 2003). For instance, consider the AIXI model, the gold-standard for
universal intelligence, which operates via Solomonoff induction (Solomonoff, 1964; Hutter, 2004). The AIXI
model generates an optimal decision making over some class of problems, and methods linked to it have
already been applied to a range of behaviors, such as creating “AI physicists” (Wu and Tegmark, 2019). Its
universality indicates it is a prime candidate for universal substitutions. Notably, unlike a Turing machine,
it avoids issues of precisely how it is accomplishing universal substitution of report, since the algorithm that
governs the AIXI model behavior is well-described and “relatively” simple.
The above are all real and viable classes of systems that are used everyday in science and engineering
which all provide different viable universal substitutions if inferences are based on reports or outputs. They
show that in normal experimental setups such as the ones commonly used in neuroscientific research into
consciousness (Frith et al., 1999), inference and prediction data are indeed independent, and dependency
is not investigated nor properly considered. It is always possible to substitute the physical system under
consideration with another that has different internal observables, and therefore different predictions, but
similar or identical reports. Indeed, recent research in using the work introduced in this work shows that
even different spatiotemporal models of a system can be substituted for one another, leading to falsification
(Hanson and Walker, 2020). We have not considered possible but less reasonable examples of universal
substitutions, like astronomically-large look-up ledgers of reports.
As an example of our Main Theorem 3.10, we consider the case of IIT. Since the theory is normally applied
in Boolean networks, logic gates, or artificial neural networks, one usually takes report to mean “output.”
In this case, it has already been proven that systems with different internal structures and hence different
predicted experiences, can have identical input/output (and therefore identical reports or inferences about
report) (Albantakis and Tononi, 2019). To take another case: within IIT it has already been acknowledged
that a Turing machine may have a wildly different predicted contents of consciousness for the same behavior
12
or reports (Koch, 2019). Therefore, data independence during testing has already been shown to apply to
IIT under its normal assumptions.
4
Inference and prediction data are strictly dependent
An immediate response to our main result showing that many theories suffer from a priori falsification would
be to claim that it offers support of theories which define conscious experience in terms of what is accessible
to report. This is the case, e.g., for behaviourist theories of consciousness but might arguably also be the
case for some interpretations of global workspace theory or fame in the brain proposals. In this section, we
show that this response is not valid, as theories of this kind, where inference and prediction data are strictly
dependent, are unfalsifiable.
In order to analyse this case, we first need to specifically outline how theories can be pathologically unfalsifiable. Clearly, the goal of the scientific study as a whole is to find, eventually, a theory of consciousness
that are empirically adequate and therefore corroborated by all experimental evidence. Therefore, not being
falsified in experiments is a necessary condition (though not sufficient) any purportedly “true” theory of
consciousness needs to satisfy. Therefore, not being falsifiable by the set of possible experiments per se is
not a bad thing. We seek to distinguish this from cases of unfasifiability due to pathological assumptions
that underlie a theory of consciousness, assumptions which render an experimental investigation meaningless. Specifically, a pathological dependence between inferences and predictions leads to theories which are
unfalsifiable.
Such unfalsifiable theories can be identified neatly in our formalism. To see how, recall that O denotes
the class of all datasets that can result from an experiment investigating the physical systems in the class P .
Put differently, it contains all datasets that could, in principle, appear when probed in the experiment. This
is not the class of all possible datasets of type O one can think of. Many datasets which are of the same
form as elements of O might simply not arise in the experiment under consideration. We denote the class of
all possible datasets as:
O : All possible datasets of type O .
Intuitively, in terms of possible worlds semantics, O describes the datasets which could appear, for the type
of experiment under consideration, in the actual world. O, in contrast, describes the datasets which could
appear in this type of experiment in any possible world. For example, O contains datasets which can only
occur if consciousness attaches to the physical in a different way than it actually does in the actual word.
By construction, O is a subset of O, which describes which among the possible datasets actually arises
across experimental trials. Hence, O also determines which theory of consciousness is compatible with (i.e.
not falsified by) experimental investigation. However, O defines all possible data sets independent of any
constraint by real empirical results, that is, all possible imaginable data sets.
Introduction of O allows us to distinguish the pathological cases of unfalsifiability mentioned above.
Whereas any purportedly true theory should only fail to be falsified with respect to the experimental data
O, a pathological unfalsifiability pertains if a theory cannot be falsified at all, i.e. over O. This is captured
by the following definition.
Definition 4.1. A theory of consciousness which does not have a falsification over O is empirically unfalsifiable.
Here, we use the term ‘empirically unfalsifiable’ to highlight and refer to the pathological notion of unfalsifiability. Intuitively speaking, a theory which satisfies this definition appears to be true independently of any
experimental investigation, and without the need for any such investigation. Using O, we can also define the
notion of strict dependence in a useful way.
Definition 4.2. Inference and prediction data are strictly dependent if there is a function f such that for
any o ∈ O, we have oi = f (or ).
This definition says that there exists a function f which for every possible inference data or allows to
deduce the prediction data oi . We remark that the definition refers to O and not O, as the dependence of
inference and prediction considered here holds by assumption and is not simply asserting a contingency in
nature.
13
The definition is satisfied, for example, if inference data is equal to prediction data, i.e. if oi = or , where f
is simply the identity. This is the case, e.g., for behaviourist theories (Skinner, 1938) of consciousness,
where consciousness is equated directly with report or behavior, or for precursors of functionalist theories of
consciousness that are based on behavior or input/output (Putnam, 1960). The definition is also satisfied in
the case where prediction data is always a subset of the inference data:
oi ⊆ or .
(10)
Here, f is simply the restriction function. This arguably applies to global workspace theory (Baars, 2005),
the “attention schema” theory of consciousness (Graziano and Webb, 2015) or “fame in the brain” (Dennett,
1993) proposals.
In all these cases, consciousness is generated by – and hence needs to be predicted via – what is accessible
to report or output. In terms of Block’s distinction between phenomenal consciousness and access consciousness (Block, 1996), Equation (10) holds true whenever a theory of consciousness is under investigation where
access consciousness determines phenomenal consciousness.
Our second main theorem is the following.
Theorem 4.3. If a theory of consciousness implies that inference and prediction data are strictly dependent,
then it is either already falsified or empirically unfalsifiable.
Proof. To prove the theorem, it is useful to consider the inference and prediction content of datasets explicitly.
The possible pairings that can occur in an experiment are given by
Oexp := { (oi , or ) | o ∈ O } ,
(11)
where we have again used our notation that oi denotes the prediction data of o, and similar for or . To define
the possible pairings that can occur in O, we let Oi denote the class of all prediction contents that arise in O,
and Or denote the class of all inference contents that arise in O. The set of all conceivable pairings is then
given by
Oall :={ (oi , o0r ) | o ∈ O, o0 ∈ O}
(12)
={ (oi , o0r ) | oi ∈ Oi ,
(13)
o0r ∈ Or } .
Crucially, here, oi and o0r do not have to be part of the same dataset o. Combined with Definition 2.1, we
/ pred(o0 ), and there
conclude that there is a falsification over O if for some (oi , o0r ) ∈ Oall , we have inf (o) ∈
is a falsification over O if for some (oi , or ) ∈ Oexp , we have inf (o) ∈
/ pred(o).
Next we show that if inference and prediction data are strictly dependent, then Oall = Oexp holds. We
start with the set Oall as defined in (12). Expanding this definition in words, it reads
Oall = { (di , dr ) | ∃ o ∈ O such that dr = or and ∃ õ ∈ O such that di = õi } ,
(14)
where we have symbols di and dr to denote prediction and inference data independently of any dataset o.
Assume that the first condition in this expression, dr = or holds for some o ∈ O. Since inference and
prediction data are strictly dependent, we have di = f (dr ). Furthermore, for the same reason, the prediction
content oi of the dataset o satisfies oi = f (or ). Applying the function f to both sides of the first condition
gives f (dr ) = f (or ), which thus in turn implies oi = di . This means that the o that satisfies the first condition
in (14) automatically also satisfies the second condition. Therefore, due to inference and prediction data
being strictly dependent, (14) is equivalent to
Oall = { (di , dr ) | ∃ o ∈ O such that dr = or and di = oi } .
(15)
This, however, is exactly Oexp as defined in (11). Thus we conclude that if inference and prediction data are
strictly dependent, Oall = Oexp necessarily holds.
Returning to the characterisation of falsification in terms of Oexp and Oall above, what we have just found
implies that there is a falsification over O if and only if there is a falsification over O. Thus either there is a
falsification over O, in which case the theory is already falsified or there is no falsification over O, in which
case the theory under consideration is empirically unfalsifiable.
14
The gist of this proof is that if inference and prediction data are strictly dependent, then as far as the
inference and prediction contents go, O and O are the same. I.e, the experiment does not add anything to
the evaluation of the theory. It is sufficient to know only all possible datasets to decide whether there is
a falsification. In practise, this would mean that knowledge of the experimental design (which reports are
to be collected, on the one hand, which possible data a measurement device can produce, one the other) is
sufficient to evaluate the theory, which is clearly at odds with the role of empirical evidence required in any
scientific investigation. Thus such theories are empirically unfalsifiable.
To give an intuitive example of the theorem, let us examine a theory that uses the information accessible
to report in a system to predict conscious experience (perhaps this information is “famous” in the brain
or is within some accessible global workspace). In terms of our notation, we can assume that or denotes
everything that is accessible to report, and oi denotes that part which is used by the theory to predict
conscious experience. Thus in this case we have oi ⊆ or . Since the predicted contents are always part of
what can be reported, there can never be any mismatch between reports and predictions. However, this is
not only the case for Oexp but also, in virtue of the theory’s definition, for all possible datasets, i.e., Oall .
Therefore such theories are empirically unfalsifiable. Experiments add no information to whether the theory
is true or not, and such theories are empirically uninformative or tautological.
5
Objections
In this section, we discuss a number of possible objections to our results.
5.1
Restricting inferences to humans only
The examples given in Section 3.4.4 show that data independence holds during the usual testing setups.
This is because prima facie it seems reasonable to base inferences either on report capability or intelligent
behavior in a manner agnostic of the actual physical makeup of the system. Yet this entails independence,
so in these cases our conclusions apply.
One response to our results might be to restrict all testing of theories of consciousness solely to humans.
In our formalisms this is equivalent to making the strength of inferences based not on reports themselves
but on an underlying biological homology. Such an inf function may still pick out specific experiences via
reports, but the weight of the inference is carried by homology rather than report or behavior. This would
mean that the substitution argument does not significantly affect consciousness research, as reports of nonhuman systems would simply not count. Theories of consciousness, so this idea goes, would be supported
by abductive reasoning from testing in humans alone.
Overall there are strong reasons to reject this restriction of inferences. One significant issue is that
this objection is equivalent to saying that reports or behavior in non-humans carry no information about
consciousness, an incredibly strong claim. If non-humans contradicted a theory (like a complex organism
acting in pain while a theory predicted a lack of pain) the theory would be presumed to be correct above
any behavior or report, meaning that abductive application of the theory ignores the fact that this sort of
abductive reasoning should actually falsify the theory. Indeed, this is highly problematic for consciousness
research which often uses non-human animal models (Boly et al., 2013). For instance, cephalopods are
among the most intelligent animals yet are quite distant on the tree of life from humans and have a distinct
neuroanatomy, and still are used for consciousness research (Mather, 2008). Even in artificial intelligence
research, there is increasing evidence that deep neural networks produced brain-like structures such as grid
cells, shape tuning, and visual illusions, and many others (Richards et al., 2019). Given these similarities, it
becomes questionable why the strength of inferences should be based on homology instead of capability of
report or intelligence.
What is more, restricting inferences to humans alone is unlikely to be sufficient to avoid our results.
Depending on the theory under consideration, data independence might exist just in human brains alone.
That is, it is probable that there are transformations (as in Equation (9)) available within the brain wherein
or is fixed but oi varies. This is particularly true once one allows for interventions on the human brain
by experimenters, such as perturbations like transcranial magnetic stimulation, which is already used in
consciousness research (Rounis et al., 2010; Napolitani et al., 2014).
15
For these reasons this objection does not appear viable. At minimum it is clear that if the objection
were taken seriously, it would imply significant changes to consciousness research which would make the field
extremely restricted with strong a priori assumptions.
5.2
Reductio ad absurdum
Another hypothetical objection to our results is to argue that they could just as well be applied to scientific
theories in other fields. If this turned out to be true this wouldn’t imply our argument is necessarily incorrect.
But the fact that other scientific theories do not seem especially problematic with regard to falsification would
generate the question of whether some assumption is illegitimately strong. In order to address this, we explain
which of our assumptions is specific to theories of consciousness and wouldn’t hold when applied to other
scientific theories. Subsequently, we give an example to illustrate this point.
The assumption in question is that O, the class of all datasets that can result from observations or
measurements of a system, is determined by the physical configurations in P alone. I.e., every single dataset o,
including both its prediction content oi and its inference content or , is determined by p, and not by a conscious
experience in E. In Figure 2, this is reflected in the fact that there is an arrow from P to O, but no arrow
from E to O.
This assumption expresses the standard paradigm of testing theories of consciousness in neuroscience,
according to which both the data used to predict a state of consciousness and the reports of a system are
determined by its physical configuration alone. This, in turn, may be traced back to consciousness’ assumed
subjective and private nature, which implies that any empirical access to states of consciousness in scientific
investigations is necessarily mediated by a subject’s reports, and to general physicalist assumptions.
This is different from experiments in other natural sciences. If there are two quantities of interest whose
relation is to be modelled by a scientific theory, then in all reasonable cases there are two independent means
of collecting information relevant to a test of the theory, one providing a dataset that is determined by the
first quantity, and one providing a dataset that is determined by the second quantity.
Consider, as an example, the case of temperature T and its relation to microphysical states. To apply
our argument, the temperature T would replace the experience space E and p would denote a microphyiscal
configuration. In order to test any particular theory about how temperature is determined by microphysical
states, one would make use of two different measurements. The first measurement would access the microphysical states and would allow measurement of, say, the mean kinetic energy (if that’s what the theory
under consideration utilizes). This first measurement would provide a dataset om that replaces the prediction
data oi above. For the second measurement, one would use a thermometer or some other measuring device
to obtain a dataset ot that replaces our inference data or above. Comparison of the inferred temperature
with the temperature that is predicted based on om would allow testing of the theory under consideration.
These independent means provide independent access to each of the two datasets in question. Combining
om and ot in one dataset o, the diagrammatic representation is
P −→ O ←− T ,
which differs from the case of theories of consciousness considered here, wherein the physical system determines both datasets.
5.3
Theories could be based on phenomenology
Another response to the issue of independence/dependence identified here is to propose that a theory of
consciousness may not have to be falsified but can be judged by other characteristics. This is reminiscent of
ideas put forward in connection with String Theory, which some have argued can be judged by elegance or
parsimony alone (Carroll, 2018).
In addition to elegance and parsimony, in consciousness science, one could in particular consider a theory’s
fit with phenomenology, i.e. how well a theory describes the general structure of conscious experience.
Examples of theories that are constructed based on a fit with phenomenology are recent versions of IIT
(Oizumi et al., 2014) or any view that proposes developing theories based on isomorphisms between the
structure of experiences and the structure of physical systems or processes (Tsuchiya et al., 2019).
16
It might be suggested that phenomenological theories might be immune to aspects of the issues we outline
in our results (Negro, 2020). We emphasize that in order to avoid our results, and indeed the need for any
experimental testing at all, a theory constructed from phenomenology has to be uniquely derivable from
conscious experience. However, to date, no such derivation exists, as phenomenology seems to generally
underdetermine the postulates of IIT (Bayne, 2018; Barrett and Mediano, 2019), and because it is unknown
what the scope and nature of non-human experience is. Therefore theories based on phenomenology can
only confidently identify systems with human-like conscious experiences and cannot currently do so uniquely.
Thus they cannot avoid the need for testing.
As long as no unique and correct derivation exists across the space of possible conscious experiences, the
use of experimental tests to assess theories of consciousness, and hence our results, cannot be avoided.
5.4
Rejecting falsifiability
Another response to our findings might be to deny the importance of falsifications within the scientific
methodology. Such responses may reference a Lakatosian conception of science, according to which science
does not proceed by discarding theories immediately upon falsification, but instead consists of research
programs built around a family of theories (Lakatos, 1980). These research programs have a protective belt
which consists of non-essential assumptions that are required to make predictions, and which can easily be
modified in response to falsifications, as well as a hard core that is immune to falsifications. Within the
Lakatosian conception of science research programs are either progressive or degenerating based on whether
they can “anticipate theoretically novel facts in its growth” or not (Lakatos, 1980).
It is important to note, however, that Lakatos does not actually break with falsificationism. This is why
Lakatos description of science is often called “refined falsificationism” in philosophy of science (Radnitzky,
1991). Thus cases of testing theories’ predictions remain relevant in a Lakatosian view in order to distinguish
between progressive and degenerating research programs. Therefore our results generally translate into this
view of scientific progress. In particular, Theorem 3.10 shows that for every single inference procedure that
is taken to be valid, there exists a system for which the theory makes a wrong prediction. This implies
necessarily that a research program is degenerating. That is, independence implies that there is always an
available substitution that can falsify any particular prediction coming from the research program.
6
Conclusion
In this paper, we have subjected the usual scheme for testing theories of consciousness to a thorough formal
analysis. We have shown that there appear to be deep problems inherent in this scheme which need to be
addressed.
Crucially, in contrast to other similar results (Doerig et al., 2019), we do not put the blame on individual
theories of consciousness, but rather show that a key assumption that is usually being made is responsible
for the problems: an experimenter’s inference about consciousness and a theory’s predictions are generally
implicitly assumed to be independent during testing across contemporary theories. As we formally prove,
if this independence holds, substitutions or changes to physical systems are possible that falsify any given
contemporary theory. Whenever there is an experimental test of a theory of consciousness on some physical
system which does not lead to a falsification, there necessary exists another physical system which, if it had
been tested, would have produced a falsification of that theory. We emphasize that this problem does not
only affect one particular type of theory, for example those based on causal interactions like IIT; theorems
apply to all contemporary neuroscientific theories of consciousness if independence holds.
In the second part of our results, we examine the case where independence doesn’t hold. We show that
if an experimenter’s inferences about consciousness and a theory’s predictions are instead considered to be
strictly dependent, empirical unfalsifiability follows, which renders any type of experiment to test a theory
uninformative. This affects all theories wherein consciousness is predicted off of reports or behavior (such as
behaviorism), theories based off of input/output functions, and also theories that equate consciousness with
on accessible or reportable information.
Thus theories of consciousness seem caught between between Scylla and Charybdis, requiring delicate
navigation. In our opinion there may only be two possible paths forward to avoid these dilemmas, which
17
we briefly outline below. Each requires a revision of the current scheme of testing or developing theories of
consciousness.
Lenient dependency. When combined, our main theorems show that both independence and strict dependence of inference and prediction data are problematic and thus neither can be assumed in an experimental
investigation. This raises the question of whether there are reasonable cases where inference and prediction
are dependent, but not strictly dependent.
A priori, in the space of possible relationships between inference and prediction data, there seems to be
room for relationships that are neither independent (Section 3) nor strictly dependent (Section 4). We define
this relationships of this kind as cases of lenient dependency. No current theory or testing paradigm that
we know of satisfies this definition. Yet cases of lenient dependency cannot be excluded to exist. Such cases
would technically not be beholden to either Theorem 3.10 or Theorem 4.3.
There seems to be two general possibilities of how lenient dependencies could be built. On the one
hand, one could hope to find novel forms of inference that allow to surpass the problems we have identified
here. This would likely constitute a major change in the methodologies of experimental testing of theories
of consciousness. On the other hand, another possibility to attain lenient dependence would be to construct
theories of consciousness which yield prediction functions that are designed to explicitly have a leniently
dependent link to inference functions. This would likely constitute a major change in constructing theories
of consciousness.
Physics is not causally closed. Another way to avoid our conclusion is to only consider theories of
consciousness which do not describe the physical as causally closed (Kim, 1998). That is, the presence or
absence of a particular experience itself would have to make a difference to the configuration, dynamics,
or states of physical systems above and beyond what would be predicted with just information about the
physical system itself. If a theory of consciousness does not describe the physical as closed, a whole other
range of predictions are possible: predictions which concern the physical domain itself, e.g., changes in the
dynamics of the system which depend on the dynamics of conscious experience. These predictions are not
considered in our setup and may serve to test a theory of consciousness without the problems we have
explored here.
7
Acknowledgments
We would like to thank David Chalmers, Ned Block, and the participants of the NYU philosophy of mind
discussion group for valuable comments and discussion. Thanks also to Ryota Kanai, Jake Hanson, Stephan
Sellmaier, Timo Freiesleben, Mark Wulff Carstensen and Sofiia Rappe for feedback on early versions of the
manuscript.
Author contributions: J.K.and E.H. conceived the project and wrote the article. Competing interests: The authors declare no competing interests.
References
Scott Aaronson. Why i am not an integrated information theorist (or, the unconscious expander). ShtetlOptimized: The Blog of Scott Aaronson, 2014.
David Alais, John Cass, Robert P O’Shea, and Randolph Blake. Visual sensitivity underlying changes in
visual consciousness. Current biology, 20(15):1362–1367, 2010.
Larissa Albantakis and Giulio Tononi. Causal composition: Structural differences among dynamically equivalent systems. Entropy, 21(10):989, 2019.
Bernard J Baars. In the theatre of consciousness. global workspace theory, a rigorous scientific theory of
consciousness. Journal of Consciousness Studies, 4(4):292–309, 1997.
18
Bernard J Baars. Global workspace theory of consciousness: toward a cognitive neuroscience of human
experience. Progress in brain research, 150:45–53, 2005.
Philip Ball. Neuroscience readies for a showdown over consciousness ideas. Quanta Magazine, 2019.
Adam B Barrett and Pedro AM Mediano. The phi measure of integrated information is not well-defined for
general physical systems. Journal of Consciousness Studies, 26(1-2):11–20, 2019.
Tim Bayne. On the axiomatic foundations of the integrated information theory of consciousness. Neuroscience of consciousness, 2018(1):niy007, 2018.
Randolph Blake, Jan Brascamp, and David J Heeger. Can binocular rivalry reveal neural correlates of
consciousness? Philosophical Transactions of the Royal Society B: Biological Sciences, 369(1641):20130211,
2014.
Ned Block. How can we find the neural correlate of consciousness? Trends in neurosciences, 19(11):456–459,
1996.
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal,
Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al. End to end learning for self-driving
cars. arXiv preprint arXiv:1604.07316, 2016.
Melanie Boly, Anil K Seth, Melanie Wilke, Paul Ingmundson, Bernard Baars, Steven Laureys, David Edelman, and Naotsugu Tsuchiya. Consciousness in humans and non-human animals: recent advances and
future directions. Frontiers in psychology, 4:625, 2013.
Sean M Carroll. Beyond falsifiability: Normal science in a multiverse. Why Trust a Theory?, page 300, 2018.
Michael A Cerullo. The problem with phi: a critique of integrated information theory. PLoS computational
biology, 11(9):e1004286, 2015.
Acer YC Chang, Martin Biehl, Yen Yu, and Ryota Kanai. Information closure theory of consciousness. arXiv
preprint arXiv:1909.13045, 2019.
Andy Clark. Consciousness as generative entanglement. The Journal of Philosophy, 116(12):645–662, 2019.
Francis Crick. Astonishing Hypothesis: The Scientific Search for the Soul. Simon and Schuster, 1994.
Francis Crick and Christof Koch. Towards a neurobiological theory of consciousness. In Seminars in the
Neurosciences, volume 2, pages 263–275. Saunders Scientific Publications, 1990.
Francis C Crick and Christof Koch. What is the function of the claustrum? Philosophical Transactions of
the Royal Society B: Biological Sciences, 360(1458):1271–1279, 2005.
Stanislas Dehaene and Jean-Pierre Changeux. Neural mechanisms for access to consciousness. The cognitive
neurosciences, 3:1145–58, 2004.
Stanislas Dehaene and Jean-Pierre Changeux. Experimental and theoretical approaches to conscious processing. Neuron, 70(2):200–227, 2011.
Antoine Del Cul, Sylvain Baillet, and Stanislas Dehaene. Brain dynamics underlying the nonlinear threshold
for access to consciousness. PLoS biology, 5(10):e260, 2007.
Daniel C Dennett. Consciousness explained. Penguin uk, 1993.
Adrien Doerig, Aaron Schurger, Kathryn Hess, and Michael H Herzog. The unfolding argument: Why iit
and other causal structure theories cannot explain consciousness. Consciousness and cognition, 72:49–59,
2019.
Krzysztof Dolega and Joe E Dewhurst. Fame in the predictive brain: a deflationary approach to explaining
consciousness in the prediction error minimization framework. Synthese, pages 1–26, 2020.
19
Chris Frith, Richard Perry, and Erik Lumer. The neural correlates of conscious experience: An experimental
framework. Trends in cognitive sciences, 3(3):105–114, 1999.
Rick O Gilmore, Michele T Diaz, Brad A Wyble, and Tal Yarkoni. Progress toward openness, transparency,
and reproducibility in cognitive neuroscience. Annals of the New York Academy of Sciences, 1396(1):5,
2017.
Philip Goff. Consciousness and fundamental reality. Oxford University Press, 2017.
Olivia Gosseries, Haibo Di, Steven Laureys, and Mélanie Boly. Measuring consciousness in severely damaged
brains. Annual Review of Neuroscience, 37:457–478, 2014.
Michael SA Graziano and Taylor W Webb. The attention schema theory: a mechanistic account of subjective
awareness. Frontiers in psychology, 6:500, 2015.
Jake R Hanson and Sara I Walker. Formalizing falsification of causal structure theories for consciousness
across computational hierarchies. arXiv preprint arXiv:2006.07390, 2020.
J Allan Hobson et al. Consciousness, dreams, and inference: The cartesian theatre revisited. Journal of
Consciousness Studies, 21(1-2):6–32, 2014.
Jakob Hohwy. Attention and conscious perception in the hypothesis testing brain. Frontiers in psychology,
3:96, 2012.
Kurt Hornik, Maxwell Stinchcombe, and Halbert White. Multilayer feedforward networks are universal
approximators. Neural networks, 2(5):359–366, 1989.
Marcus Hutter. A gentle introduction to the universal algorithmic agent aixi, 2003.
Marcus Hutter. Universal artificial intelligence: Sequential decisions based on algorithmic probability.
Springer Science & Business Media, 2004.
Jaegwon Kim. Mind in a physical world: An essay on the mind-body problem and mental causation. MIT
press, 1998.
Johannes Kleiner. Brain states matter. a reply to the unfolding argument. To appear in Consciousness and
Cognition, 2020.
Johannes Kleiner and Sean Tull. The mathematical structure of integrated information theory. arXiv preprint
arXiv:2002.07655, 2020.
Christof Koch. The Feeling of Life Itself: Why Consciousness is Widespread But Can’t be Computed. Mit
Press, 2019.
Christof Koch, Marcello Massimini, Melanie Boly, and Giulio Tononi. Neural correlates of consciousness:
progress and problems. Nature Reviews Neuroscience, 17(5):307, 2016.
Imre Lakatos. The methodology of scientific research programmes: Volume 1: Philosophical papers, volume 1.
Cambridge university press, 1980.
Victor AF Lamme. Towards a true neural stance on consciousness. Trends in cognitive sciences, 10(11):
494–501, 2006.
Hakwan Lau and David Rosenthal. Empirical support for higher-order theories of conscious awareness.
Trends in cognitive sciences, 15(8):365–373, 2011.
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Deep learning. nature, 521(7553):436–444, 2015.
Marcello Massimini, Fabio Ferrarelli, Reto Huber, Steve K Esser, Harpreet Singh, and Giulio Tononi. Breakdown of cortical effective connectivity during sleep. Science, 309(5744):2228–2232, 2005.
20
Jennifer A Mather. Cephalopod consciousness: behavioural evidence. Consciousness and cognition, 17(1):
37–48, 2008.
Pedro Mediano, Anil Seth, and Adam Barrett. Measuring integrated information: Comparison of candidate
measures in theory and simulation. Entropy, 21(1):17, 2019.
Martino Napolitani, Olivier Bodart, Paola Canali, Francesca Seregni, Adenauer Casali, Steven Laureys,
Mario Rosanova, Marcello Massimini, and Olivia Gosseries. Transcranial magnetic stimulation combined
with high-density eeg in altered states of consciousness. Brain injury, 28(9):1180–1189, 2014.
Niccolò Negro. Phenomenology-first versus third-person approaches in the science of consciousness: the
case of the integrated information theory and the unfolding argument. Phenomenology and the Cognitive
Sciences, pages 1–18, 2020.
Masafumi Oizumi, Larissa Albantakis, and Giulio Tononi. From the phenomenology to the mechanisms of
consciousness: integrated information theory 3.0. PLoS computational biology, 10(5):e1003588, 2014.
Karl Popper. The logic of scientific discovery. Routledge, 1959.
Hilary Putnam. Minds and machines. 1960.
Gerard Radnitzky. Refined falsificationism meets the challenge from the relativist philosophy of science,
1991.
Sara Reardon. Rival theories face off over brain’s source of consciousness, 2019.
Blake A Richards, Timothy P Lillicrap, Philippe Beaudoin, Yoshua Bengio, Rafal Bogacz, Amelia Christensen, Claudia Clopath, Rui Ponte Costa, Archy de Berker, Surya Ganguli, et al. A deep learning
framework for neuroscience. Nature neuroscience, 22(11):1761–1770, 2019.
David M Rosenthal. How many kinds of consciousness? Consciousness and cognition, 11(4):653–665, 2002.
Elisabeth Rounis, Brian Maniscalco, John C Rothwell, Richard E Passingham, and Hakwan Lau. Thetaburst transcranial magnetic stimulation to the prefrontal cortex impairs metacognitive visual awareness.
Cognitive neuroscience, 1(3):165–175, 2010.
Anton Maximilian Schäfer and Hans Georg Zimmermann. Recurrent neural networks are universal approximators. In International Conference on Artificial Neural Networks, pages 632–640. Springer, 2006.
Claire Sergent and Stanislas Dehaene. Neural processes underlying conscious perception: experimental
findings and a global neuronal workspace framework. Journal of Physiology-Paris, 98(4-6):374–384, 2004.
Anil Seth. Models of consciousness. Scholarpedia, 2(1):1328, 2007.
Anil K Seth. A predictive processing theory of sensorimotor contingencies: Explaining the puzzle of perceptual presence and its absence in synesthesia. Cognitive neuroscience, 5(2):97–118, 2014.
BF Skinner. The behavior of organisms: an experimental analysis. Appleton-Century, 1938.
Ray J Solomonoff. A formal theory of inductive inference. part i. Information and control, 7(1):1–22, 1964.
Giulio Tononi. An information integration theory of consciousness. BMC neuroscience, 5(1):42, 2004.
Giulio Tononi. Consciousness as integrated information: a provisional manifesto. The Biological Bulletin,
215(3):216–242, 2008.
Giulio Tononi. Why scott should stare at a blank wall and reconsider (or, the conscious grid). ShtetlOptimized: The Blog of Scott Aaronson. Available online: http://www. scottaaronson. com/blog, 2014.
Naotsugu Tsuchiya, Melanie Wilke, Stefan Frässle, and Victor AF Lamme. No-report paradigms: extracting
the true neural correlates of consciousness. Trends in cognitive sciences, 19(12):757–770, 2015.
21
Naotsugu Tsuchiya, Shigeru Taguchi, and Hayato Saigo. Using category theory to assess the relationship
between consciousness and integrated information theory. Neuroscience research, 107:1–7, 2016.
Naotsugu Tsuchiya, Thomas Andrillon, and Andrew Haun. A reply to “the unfolding argument”: Beyond functionalism/behaviorism and towards a truer science of causal structural theories of consciousness.
PsyArXiv, 2019.
Alan M Turing. Computing machinery and intelligence. In Parsing the Turing Test, pages 23–65. Springer,
2009.
Alan Mathison Turing. On computable numbers, with an application to the entscheidungsproblem. Proceedings of the London mathematical society, 2(1):230–265, 1937.
Michael Wenzel, Shuting Han, Elliot H Smith, Erik Hoel, Bradley Greger, Paul A House, and Rafael Yuste.
Reduced repertoire of cortical microstates and neuronal ensembles in medically induced loss of consciousness. Cell systems, 8(5):467–474, 2019.
Stephen Wolfram. Cellular automata as models of complexity. Nature, 311(5985):419, 1984.
Tailin Wu and Max Tegmark. Toward an artificial intelligence physicist for unsupervised learning. Physical
Review E, 100(3):033311, 2019.
22
A
Weak independence
In this section, we show how Definition 3.8 can be substantially relaxed while still ensuring our results to
hold. To this end, we need to introduce another bit of formalism: We assume that predictions can be
compared to establish how different they are. This is the case, e.g., in IIT where predictions map to the
space of maximally irreducible conceptual structures (MICS), sometimes also called the space of Q-shapes,
which carries a distance function analogous to a metric (Kleiner and Tull, 2020). We assume that for any
given prediction, one can determine which of all those predictions that don’t overlap with the given one
is most similar to the latter, or equivalently which is least different. We calls this a minimally differing
prediction and use it to induce a notion of minimally differing data sets below. Uniqueness is not required.
Let an arbitrary data set o ∈ O be given. The minimal information assumption from Section 3.4.1 ensures
that there is at least one data set o0 such that Equation (8) holds. For what follows, let o⊥ denote the set
of all data sets which satisfy Equation (8) with respect to o,
o⊥ := { o0 ∈ O | pred(ō) ∩ pred(ō0 ) = ∅ } .
(16)
Thus o⊥ contains all data sets whose prediction completely differs from the prediction of o.
Definition A.1. We denote by min(o) those data sets in o⊥ whose prediction is least different from the
prediction of o.
In many cases min(o) will only contain one data set, but here we treat the general case where this is not so.
We emphasize that the minimal information assumption guarantees that min(o) exists. We can now specify
a much weaker version of Definition 3.8.
Definition A.2. Inference and prediction data are independent if for any o ∈ O and o0 ∈ min(o), there is
a variation
ν:P →P
(17)
such that oi ∈ obs(p), o0i ∈ obs(ν(p)) but or ∈ obs(p) and or ∈ obs(ν(p)) for some p ∈ P .
The difference between Definition A.2 and Definition 3.8 is that for a given o ∈ O, the latter requires the
transformation ν to exist for any o0 ∈ O, wheres the former only requires it to exist for minimally different
data sets o0 ∈ min(o). The corresponding proposition is the following.
Proposition A.3. If inference and prediction data are weakly independent, universal substitutions exist.
Proof. To show that a universal substitution exists, we need to show that for every o ∈ O, an or -substitution
exists (Definition 3.1). Thus assume that an arbitrary o ∈ O is given and pick an o0 ∈ min(o). As before, we
denote the prediction content of o and o0 by oi and o0i , respectively, and the inference content of o by or .
Since inference and prediction data are weakly independent, there exists a p ∈ P as well as a ν : P → P
such that oi ∈ obs(p), o0i ∈ obs(ν(p)), or ∈ obs(p) and or ∈ obs(ν(p)). By Definition (7), the first two of
these four conditions imply that obs(p) ⊂ ō and obs(ν(p)) ⊂ ō0 . Since o0 is in particular an element of o⊥ ,
Equation (8) applies and allows us to conclude that
pred(obs(p)) ∩ pred(obs(ν(p)) = ∅ .
Via Equation (3), the latter two of the four conditions imply that p ∈ Por and ν(p) ∈ Por . Thus we may
restrict ν to Por to obtain a map
S : Por → Por ,
which in light of the first part of this proof exhibits at least one p ∈ Por which satisfies (4). Thus we have
shown that an or -substitution exists. Since o was arbitrary, it follows that a universal substitution exists.
The following theorem shows that Definition A.2 is sufficient to establish the claim of Theorem 3.10.
Theorem A.4. If inference and prediction data are weakly independent, either every single inference operation is wrong or the theory under consideration is already falsified.
Proof. The theorem follows by combining Proposition A.3 and Proposition 3.7.
23
B
Inverse predictions
When defining falsification, we have considered predictions that take as input data about the physical
configuration of a system and yield as output a state of consciousness. An alternative would be to consider
the inverse procedure: a prediction which takes as input a reported stated of consciousness and yields as
output some constraint on the physical configuration of the system that is having the conscious experience.
In this section, we discuss the second case in detail.
pred−1
P
obs
O
E
inf
Figure 5: The case of an inverse prediction. Rather than comparing the inferred and predicted state of consciousness,
one predicts the physical configuration of a system based on the system’s report and compares this with measurement
results.
As before, we assume that some data set o has been measured in an experimental trail, which contains
both the inference data or (which includes report and behavioural indicators of consciousness used in the
experiment under consideration) as well as some data oi that provides information about the physical configuration of the system under investigation. For simplicity, we will also call this prediction data here. Also
as before, we take into account that the state of consciousness of the system has to be inferred from or , and
again denote this inference procedure by inf .
The theory under consideration provides a correspondence pred : O E which describes the process of
predicting states of consciousness mentioned above. If we ask which physical configurations are compatible
with a given state e of consciousness, this is simply the preimage pred−1 (e) of e under pred, defined as
pred−1 (e) = { o ∈ O | e ∈ pred(o)} .
(18)
Accordingly, the class of all prediction data which is compatible with the inferred experience inf (o) is
pred−1 inf (o) ,
(19)
depicted in Figure 5, and a falsification occurs in case the the observed o has a prediction content oi which
is not in this set. Referring to the previous definition of falsification as type-1 (Definition 2.1), we define this
new form of falsification as type-2.
Definition B.1. There is a type-2 falsification at o ∈ O if we have
o 6∈ pred−1 inf (o) .
(20)
In terms of the notion introduced in Section 2.5, Equation (20) could equivalently be written as oi 6∈
pred−1 inf (or ) i . The following lemma shows that there is a type-2 falsification if and only if there is a
type-1 falsification. Hence all of our previous results apply as well to type-2 falsifications.
Lemma B.2. There is a type-2 falsification at o if and only if there is a type-1 falsification at o.
Proof. Equation (18) implies that o 6∈ pred−1 (e) if and only if e 6∈ pred(o). Applied to e = inf (o), this
implies:
o 6∈ pred−1 (inf (o)) if and only if inf (o) 6∈ pred(o) .
The former is the definition of a type-2 falsification. The latter is Equation (2) in the definition of a type-1
falsification. Hence the claim follows.
24 |
85
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
Article
Simulated Effects of Sudden Increases in Electromagnetic Activity
on Deviations in Random Electron Tunnelling Behaviour Associated
with Cognitive Intention
Joey M. Caswell1,2, David A. E. Vares1,3, Lyndon M. Juden-Kelly1,2
& Michael A. Persinger1,2,3,4 *
Consciousness Research Laboratory 1, Behavioural Neuroscience 1, Human Development 2, Experimental
Psychology 3, and Biomolecular Science 4 Programs, Laurentian University, Sudbury, Ontario, Canada
P3E 2C6
ABSTRACT
Reliable evidence from the Jahn-Dunne studies conducted over several decades indicated that
human proximity can affect the dynamics of certain processes that strongly depend upon
“random” processes. Random Event Generators (REG) operate through “random” electron
tunneling through spaces that are within the same order of magnitude as synapses. If the
mechanisms by which these human-machine interactions occur involve electromagnetic
processes, then application of specific temporally patterned magnetic fields to the human
volume should affect the strength of the deviation from “random” variations. Whole-body
exposure to ~400 nT, complex-patterned magnetic fields based upon 3 ms point durations
reversed the effects of normal “intention” upon the operation of REGs. The energies generated
within the cerebral volume by that field if emitted as irradiative power were within the range of
the mass equivalent of an electron at the level of p-n junction of the semiconductor. These
results support the hypothesis that “intention” can be affected experimentally and the energies
within the vicinity of the actual dynamic space (~1 µm2) of the p-n junction of the REG match
the extended power of the magnetic energy contained within the cerebrum.
Key Words: Intention, Consciousness, p-n junctions; Random Event Generators (REG),
Electromagnetic Fields
1. Introduction
As a species, our dependence on technology can no longer be understated. This reliance can
cause the machine of society to grind to a halt as a result of power failures or other electrical
disturbances. The study of space weather, particularly the geomagnetic field, has elucidated one
mechanism by which both electrical and biological systems are affected on Earth by even small
environmental electromagnetic variations. The convergence of a number of scientific disciplines,
including geophysics, biology, environmental science, and engineering, have led to a number of
discoveries regarding the effects of space weather on terrestrial systems, from human physiology
and health to navigation and communications systems.
*Corresponding author: Michael A. Persinger E-mail: mpersinger@laurentian.ca
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
86
The same progression of discovery due to the integration of previously disparate fields of study
has also proven fortuitous for the study of consciousness, parapsychology, and physical
anomalies research. By extending the focus of investigation in these areas from theoretical
models of psychology and philosophy to the search for biophysical relationships, mechanistic
explanations based on physical principles have begun to emerge. These areas have recently
flourished with new models involving physical quantification and interdisciplinary investigation
bolstered by new technologies. This increasingly transdisciplinary engagement has encouraged
the search for physical relationships which might reveal potential mechanisms by which
anomalous or non-local interactions occur in association with psychobiological systems.
The inner core of the Earth, composed of iron-alloy and other lighter elements, rotates within the
liquid iron outer core, and this rotation produces a magnetic field through a dynamo effect. This
magnetic field extends outwards around the planet to reach solar winds and form the
geomagnetic field. It may behave as a filter or transducer of extraterrestrial stimuli such as
cosmic rays or protons. Geomagnetic activity and subsequent conditions within the planetary
atmosphere affect terrestrial biology, including a number of species of birds [1], fish [2], and
terrestrial mammals [3]. In the context of human studies, effects of geomagnetic activity have
been identified for cardiovascular functioning [4], bioelectrical activity in the brain [5], and
emotional state [6]. Geomagnetic storms typically occur in relation to solar activity including
variations in solar wind velocity [7], dynamic pressure changes [8], and coronal mass ejections
[9].
It has also been demonstrated that the random output of an external physical system is correlated
with the conscious “intention” of a human operator [10-11]; decades of research have
consistently documented the apparent phenomenon of consciousness-correlated collapse (3C),
which suggests that the behaviour of non-deterministic systems may be affected by human
consciousness. Given that the relationship between brain activity and variations in the Earth’s
geomagnetic field is well documented, and there have been potential associations revealed
between the 3C phenomenon and cerebral effects [12-14], it is hypothesized that any potential
temporal contiguity between the electromagnetic interactions associated with cognitive intention
may be reflected in a relationship between a measure of 3C performance and environmental
variations in electromagnetic activity.
The state of geomagnetic activity in particular has previously been studied in the specific context
of anomalous physical phenomena associated with consciousness. For example, passive
anomalous processes, such as remote viewing, were shown to exhibit a negative correlation
between task accuracy and geomagnetic activity (GMA) [15]. The most powerful effects for both
spontaneous and experimental forms of accessing information at a distance through nonconventional means occur when the global variations are within the 5 to 8 nT range. Slightly
higher intensities are more likely to occur during precognitive dreams [16-17]. Alterations of the
local geomagnetic field occur when an exceptional individual engaged in intuitive states similar
to remote viewing phenomena [18-19]. The magnetic energy associated with decrease in
geomagnetic intensity within the volume surrounding the person’s cerebrum was the same order
of magnitude as the increased photon power density recorded within this boundary.
Although studies have previously investigated the relationship between GMA and active
anomalous physical processes, such as consciousness-correlated collapse (3C) of external
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
87
random systems, these tend to be relatively restricted in scope and subsequent analyses have
failed to determine a potential effect of geomagnetism on external effects of conscious intention
[20-21]. For example, it has been successfully determined that recurrent-spontaneous effects of
consciousness on the local environment at the macro-scale tend to occur during periods of
increased GMA [22-23]. Although a number of these experiences may be subject to relative
interpretation, there is contemporary quantitative evidence suggesting the potential for thought to
affect matter [24], as well as the relevant quantitative convergence which supports a link
between micro- and macro-quantum processes associated with cortical activity [25].
That even small perturbations of ~20-40 nT have been shown to affect human neurophysiology
[26] suggests that weak intensity electromagnetic fields (EMF) have the potential capacity to
disrupt normal functioning of cognitive processes. While we have previously demonstrated that
transcerebral application of a specific physiologically-patterned EMF shows a potential to
increase the capacity to engage external effects of consciousness [13], we hypothesized that fullbody exposure to a relatively ‘noisy’ signal not patterned after any specific physiological process
would potentially disrupt the occurrence of the 3C phenomenon. We designed an experiment in
which sudden increases in patterned, weak-intensity electromagnetic activity were simulated
using a variation on protocols employed in our laboratory for previous experiments [27-28].
Participants attempted to influence the output of a random event generator (REG) device during
both control and EMF conditions.
2. Methods
2.1. Subjects
Participant age ranged from 22-30 years for N = 8 (N = 3 females, N = 5 males). All were
recruited from Laurentian University campus.
2.2. Equipment
Simulated EMF increases were produced using two large custom-built rectangular coils (1.15 x
1.15 m) placed 1 m apart on either side of the participant seating area, ~36 cm away from their
bodies. The random event generator (REG) device was also placed within the area of the coils
~25 cm in front of the participant on his or her right side. The magnetic field was produced by a
DOS PC system using custom software designed by Professor Stan Koren. The original
waveform designed to imitate increased GMA consists of 5071 individual points. To simulate a
sudden impulse the point durations were designed to be 69 ms. However, during the following
experiment the same field pattern was presented with point durations of 3 msec each, and a 3
msec delay between each point, a significantly faster duration and presentation compared to
simulation of natural geomagnetic increases [27]. The 3 ms point durations were selected on the
bases of the enhanced physiological effectiveness. The value of each point in the waveform
ranged between 0-256 and was converted to a voltage equivalent (-5 to +5 V) using a custombuilt digital-to-analogue converter device which delivered the associated current through the
coils. The overall intensity of the subsequent electromagnetic field produced by the system had a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
88
peak intensity of ~400 to 500 nT as measured by power meters. The actual waveform image is
displayed in Figure 1.
Figure 1. Waveform image of GMA-patterned field repeated over the course of each exposure;
the y-axis is waveform point value (equivalent to voltage value between -5 to +5 V), the x-axis
is time
Actual geomagnetic activity before, during, and after testing was examined using estimated 3hour Kp-indices obtained from the Solen database (www.solen.info/solar/).
Random data was produced using a Psyleron REG-1 random event generator (Figure 2;
www.psyleron.com). The device produced a random output which was generated by electron
tunneling effects within two field effect transistors. The varying voltage levels which result from
this process were converted into digital data through a gated sampling procedure which allowed
for regularly spaced bit sequences. The output of both transistors was internally compared
through an alternating (0, 1) XOR masking process in order to reduce any potential influence of
physical artifacts or other external environmental variables. The device itself was further
protected from static electromagnetic factors by an aluminum outer shielding and a Permalloy
mu-metal inner shield. Furthermore, the device was rigorously calibrated prior to shipment in
order to ensure output conformed to statistical expectations.
The random event generator (REG) was also tested in control experiments within our laboratory
to confirm these expectations. The resulting data stream is collected through USB-port using
Psyleron FieldREG and Reflector software packages on a laptop computer. Individual events
were produced at a rate of either 4/sec for larger samples, or 1/sec for shorter samples in order to
accommodate participant availability (~5 and 2 minutes per condition respectively). However,
internal consistency was maintained across all conditions; for a given participant, each condition
was run using the same event rates and test time. There were no significant differences noted
between event rates in this experiment or others (p > .05). Values for each event refer to the
number of 1's out of 200 bits with binary probabilities, represented by a value of 0-200. The
theoretical (chance) mean for each event is 100 with a standard deviation of √50.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
89
Measures of entropy (HX) were obtained using Matlab 2011a software. All other statistical
procedures were conducted using SPSS software v.17.
Figure 2. Random event generator (REG); Psyleron REG-1 device used throughout the
following experiment
2.3. Procedure
Each participant was seated in a comfortable chair located within an acoustic chamber which was
also a Faraday cage. The large coils were placed on either side of the participant at a distance of
~36 cm (Figure 3). The REG device, also within the coils, was placed ~25 cm from the right side
of the participant (Figure 4). Each individual was asked to intend for a specific outcome in the
REG data (e.g., Figure 5). All participants completed four conditions, presented in a rotating AB-C-D order (e.g., presentation order for the first participant was A-B-C-D, second participant
was B-C-D-A, etc.). The REG continuously collected data throughout the experiment. The first
condition consisted of a relaxed state with no current from the coils (Baseline-No Field). The
second condition maintained the relaxation state while the EMF was applied (Baseline-Field).
The third consisted of the participant intending on the REG output with the coils again producing
no current (Intention-No Field), while the final condition involved another intention task during
simulation of EMF increase (Intention-Field).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
Figure 3. Custom-built coils placed 1 m apart on either side of participant
Figure 4. EMF coils on either side of participant, REG device placed on right side within field
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
90
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
91
Figure 5. Screenshot of Reflector software collecting data from REG device; jagged center line
is the moving cumulative deviation
3. Results
3.1. Data Transformation
REG data was converted where operator intention was present so that the data were maintained,
but the overall deviation was reversed in order to represent the direction of intention. Positive
deviations indicate the direction intended for, negative scores indicate deviations in the opposite
direction of operator intention. Where necessary, data reversal was accomplished by obtaining
the absolute deviation of each event (x-100) and multiplying the product by -1 before re-adding
100 (e.g., 105 = 105-100 = 5, 5 ∙ -1 = -5, -5+100 = 95). Following relevant transformation, event
data were standardized according to 0.5 chance expectations ([x-100] / √50).
3.2. Simulated Electromagnetic Increases and Operator Performance
In order to account for varied event samples, z-scores for each condition were obtained (Table 1)
by computing the deviation from the chance value mean (δµ = µ event scores – 100), as well as the
measurement uncertainty associated with δµ (σµ = σ / √N, where σ = √50). Dividing these values
resulted in a combined z-score for each condition used to obtain subsequent probabilities (zc = δµ
/ σµ). It was determined that none of the conditions presented with statistically significant overall
deviations (p > .05), with the possible exception of the Intention-No Field condition, which was
marginally significant given one-tailed probabilities (zc = 1.84, p = .033). However, the BaselineField condition revealed somewhat suggestive results, approaching statistical significance (zc = ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
92
1.755, p = .08), particularly given the two-tailed probability typically assigned to REG
experiments where no specifically intended outcome is present. Furthermore, the Intention-Field
condition showed low numbers of overall deviations in the direction intended by the operator
(~17%; Figure 6), particularly compared to previous experiments where this ratio tended towards
~50-90% or greater. Similar values were computed for all relevant condition pairings (Table 2)
in order to determine which conditions were significantly different from one another. Combined
z-scores indicated the only difference which was marginally significant was between IntentionNo Field and Intention-Field conditions (zc = 1.827, p = .034), suggesting that sudden increases
in EMF may inhibit initiation of a non-local 3C interaction. Furthermore, increased EMF may
actually distort the effects of 3C by encouraging deviations opposite to those intended.
Table 1. Detailed REG results for overall conditions (Baseline-No Field, Baseline-Field,
Intention-No Field, Intention-Field, data converted to directional measures (e.g., accounting for
intended direction of deviations)
Parameter
N
µ
sd
σsd
δµ
σµ
zc
p
%ID
BL (No Field)
5565
100.043
6.951
.067
.043
.095
.453
.65 **
.75 †
BL (Field)
5669
99.835
7.109
.066
-.165
.094
-1.755
.08 **
.125 †
Int (No Field)
5657
100.173
7.148
.066
.173
.094
1.84
.033 *
.5
Int (Field)
5641
99.93
7.161
.067
-.07
.094
-.745
.228 *
.167
Parameter Key:
N: Number of events (200 bits/event)
µ: Mean event score (0-200)
sd: Standard deviation of REG event scores
σsd: Measurement uncertainty in value of sd; σsd = σ / √2N, where σ = √50
δµ: Absolute deviation from theoretical chance expectations (µ-100)
σµ: Measurement uncertainty in value of δµ; σµ = σ / √N, where σ = √50
zc: Overall condition z-score adjusted for measurement uncertainty; zc = δµ / σµ
p: Probability of zc * & **
%ID: Proportion of sessions with deviation in the intended direction; %ID = Ns
with intention / Ns, where Ns = number of test sessions †
†For directionality of baseline sessions, positive values are considered to be with intention.
*One-tailed probability (e.g., intention involved).
**Two-tailed probability (e.g., no intention).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
93
Table 2. Detailed REG results comparing overall Intention (Int) conditions with respective
Baseline (BL) conditions and each other, data converted to directional measures (e.g., accounting
for intended direction of deviations)
Parameter
N
δµ
σµ
zc
p
Int (No Field)-BL
11222
.13
.134
.97
.166 *
Int (Field)-BL
11310
.095
.133
.714
.238 *
Int No Field-Field
11298
.243
.133
1.827
.034 *
Parameter Key:
N: Combined number of events (200 bits/event)
δµ: Absolute deviation; e.g., = µ intention - µ baseline
σµ: Measurement uncertainty in δµ; e.g., σ · √([1 / N intention] + [1 / N baseline]), where σ = √50
zc: z-score of overall difference adjusted for measurement uncertainty; zc = δµ / σµ
p: Probability of zc (one-tailed)
Figure 6. Cumulative deviations from the mean for REG data combined from each condition
(Intention-No Field, Baseline-No Field, Intention-Field, Baseline-Field); parabolas indicate
threshold for statistical significance (p = .05, one-tailed)
Although the traditional method for presenting deviations in REG experiments have been to
cumulate the deviations over successive subjects (Figure 6), this approach does not reveal the
actual change in time. To reveal this effect, the mean variations in bits per 10 s increment were
completed for the subjects in the four conditions as a function of 10 s increments. The means and
standard errors are shown in Figure 7. Two way analysis of variance with one between
(treatment) and one within (10 s increments) revealed statistically significant interactions
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
94
between the four treatments and the temporal increments (F(3, 31) = 4.333, p = .013, η2 = .317).
Post hoc analyses indicated that the major significant effect was due to the significant difference
between the group intending while the field was being presented compared to the period of no
intention with field presentation (p = .008) during the second increment (10 to 20 s) after the
intention began. In other words, intending during the presence of the magnetic field resulted in
numbers of REG events comparable to periods of no intention. This could be interpreted as this
field pattern “cancelled” or “nullified” the effect of intention upon the random process.
Figure 7. Averaged REG event scores for 10 s increments within each condition; * significant
difference between Intention-No Field and Intention-Field conditions (Time 2)
3.3. Electromagnetic Field Increases and REG Complexity
Measures of statistical entropy (HX) were computed for REG data using Matlab software. The
measure of entropy computed by this method is similar to Shannon entropy of a random variable
[29], H(X) = -∑x P(x)log2P(x), where x = the random variable, X = the number of possible
values within x, and P = the probability mass function. Entropy values (HX) represent the level
of uncertainty within the data, where higher values indicate greater complexity and less
predictability. Signals with greater complexity possess a greater number of distinct values, and
these values are more evenly distributed.
A one-way ANOVA was used to demonstrate a statistically significant difference in REG
complexity between conditions (Figure 8; F (3, 31) = 5.308, p = .005, η2 = .362). Post-hoc tests
(Tukey) revealed a difference closely approaching statistical significance between Baseline-No
Field and Baseline-Field conditions (p = .05). Similar results were also obtained for the
difference between Intention-No Field and Intention-Field conditions (p = .05). However, a
significant difference was much more apparent for that observed between Baseline-No Field and
Intention-Field conditions (p = .009). These results might suggest that sudden electromagnetic
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
95
increases may tend to decrease the overall complexity of subsequent REG output, regardless of
any apparent 3C interaction.
Figure 8. Mean REG entropy (HX) for each condition (Baseline-No Field, Baseline-Field,
Intention-No Field, Intention-Field); vertical bars represent SEM; * indicates difference is nonsignificant (p > .05)
3.4. Controlling for Actual Geomagnetic Activity
In order to determine if any potential interaction was present between the use of simulated EMF
increases and actual GMA, estimated Kp-indices were obtained for the two 3-hour periods prior
to each test session, as well as the Kp-index during testing. A series of ANCOVAs were
performed to investigate any potential differences in both REG z-score (Stouffer’s method = ∑z /
√n) and REG entropy (HX) between conditions while controlling for the effects of the actual
geomagnetic field. Statistically significant differences between conditions were observed for
both REG variables (HX and overall z-score) when covarying for all Kp values (Figure 9; p <
.05). Furthermore, the effect sizes remained within the same range as that found in the original
analysis (η2s = ~36%).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
96
Figure 9. Mean REG entropy (HX) residuals (covarying for Kp-index) for each condition
(Baseline-No Field, Baseline-Field, Intention-No Field, Intention-Field); vertical bars represent
SEM; * indicates difference is non-significant (p > .05)
4. Discussion
The results of these experiments suggest that random variations produced by electron tunneling
through commercial devices (Random Event Generators) can be affected by intention. The
traditional critique of these reliable although weak effects is that simply the proximity of the
human mass, associated within the order of 100 W∙m-2 of power output, might be mediating
these subtle effects. In the present experiments (Figure 6) intention was associated with a
significant deviation from “random variation”. However application of this patterned magnetic
field to the whole body cancelled this effect and evoked changes in the opposite direction.
Without intention, that is when the person was still sitting in the same place in order to control
for body mass (presence) effects and not intending, the random variations during both the
presence and absence of the field was remarkably similar.
“Cancellation” or “reversal” of effects from a competitive agonist in neuropharmacology is well
known. Usually this is associated with the remarkably similar molecular structure of the
competitive structure with the natural agonist. Mach and Persinger [30] reported similar effects
following whole body exposure of rats to a pulsed magnetic field. It was the same temporal
structure that when applied as electric currents to hippocampal slices produced Long Term
Potentiation (LTP) which is the electromagnetic-chemical substrate for the representation of
experience (memory) within the mammalian brain. Mach and Persinger [30] found that the LTP
pattern presented as a magnetic field to the animal before periods of repeated training in a
spatial memory task markedly inhibited the learning. The same pattern presented after the
hourly learning trials did not affect learning. The powerful effect from these weak (1 µT, 1000
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
97
nT) magnetic fields applied to the whole body, were comparable to that of complete saturation
of the hippocampal fields by direct current induction.
In the present study the “reversal” of the intention effect which is clearly seen in Figure 6
occurred when the subjects were exposed to 400 to 500 nT (peak) intensity magnetic fields
generated through a series of 3 ms point durations. Because simply the presence of the person
without intention did not affect the random variations nor did the application of the magnetic
fields significantly affect the changes, we assumed that cerebral processes were the mediating
factor. The amount of energy from the applied field within the human cerebrum can be
calculated by E=[B2∙(2µ)-1] ∙m3, where B is the field strength, µ is magnetic permeability and m is
the volume. Assume a volume of the cerebral cortices to be ~0.57 10-3 m3 (570 cc) the energy
would be 0.5∙10-11 J. If the intrinsic frequency associated with the repeated pattern (~16 s) or
6.3∙10-2 Hz is considered the power is 3.2∙10-13 J per s.
For comparison the energy-mass equivalence of an electron is 9.1∙10-31 kg ∙9∙1016 m2s-2 or 0.8 ∙1013 J. These two quantities of energy are within the same order of magnitude and would converge
when the lower end of the applied magnetic field strengths was involved. Although the concept
that magnetic energy within a cerebral volume from an applied field could be converted to and
equivalent mass may not be conventional, there are theoretical arguments. First one of the
assumptions of the Casimir effect is that virtual particles within the Zero Point Potential
Vacuum can be converted to actual particles by electromagnetic fields with changing
boundaries. The spatial variations in our time-varying magnetic fields could meet this criterion.
In addition, as calculated by Persinger et al [24] the discrepancy in velocity to produce the
differential width of a classical electron (~10-15 m) and that calculated as the Compton
wavelength based upon energy (~10-12 m) would also produce a differential energy-equivalence
for an electron mass moving at these two velocities. The discrepancy is 10-20 J which is the
amount of energy associated with a single action potential. Stated alternatively, the “collapse” of
the wave to produce a particle would be associated with an increment of energy associated with
the act of thinking. Hence there is both a theoretical basis and quantitative convergence to
support the possibility that magnetic energy within cerebral mass could result in the “formation”
of an electron or at least its virtual manifestation for a brief period.
At the distance of the REG unit, about 25 cm or 30 cm from the center of the cerebrum, the area
of the sphere produced by this radius is ~1.1 m2. Hence the power density from the energy
induced by the applied magnetic field in the cerebral volume if radiated equally in all directions
would be ~3∙10-13 W∙m-2. Assuming the width of the p-n junction was similar to other
semiconductor devices, or 10-12 m2, the energy per second would be 3∙10-25 J. Although possibly
spurious we suggest that the resulting frequency, obtained by dividing by Planck’s constant of
6.626∙10-34 J∙s, which is within range of the neutral hydrogen line (1.42 GHz, 21.1 cm) could be
relevant to the phenomena. One could argue that access to this line, given its prominence
throughout the known universe, allows access to the most intrinsic properties of the entire
universe within a specific location.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
98
The origin of the neutral hydrogen line becomes relevant to the quantities we measured.
According to quantum interpretations, when the spins of the proton and electron are in the
same direction the magnetic interactions exhibit more energy than if the two particles are
spinning in opposite directions. The transition between these two states is associated with the
hydrogen line. Although the transition is infrequent, that is only about 10-15 per s for one atom or
a transition once every 10 million years, the large numbers of this elementary pair (a proton and
electron) minimizes this constraint. For example, assuming a brain mass of 1.5 kg and the mass
of a proton, there would be ~1027 proton equivalents within the human cerebrum. Because of the
approaching neutrality of this mass, there would be a comparable number of electrons but these
masses would be, in comparison, negligible.
This would allow 1012 of those “hypothetical pairs” to generate the transition energy per second.
Given the quantum energy of 1.42 GHz (multiplied by Planck’s constant) is 9.41∙10-25 J, this
number of shifts per second within the brain volume would result in available energy of ~10-12 J
per s or 10-12 W. With a total cortical surface area in the order of 10-1 m2 the approximate power
density would be ~10-11 W ∙m-2. This value is within the order of magnitude of measured photon
emissions from the cerebrum during periods of focused cognition, such as imagining white light
[31]. However all of the proton-electron pairs within the brain mass are not arranged as neutral
hydrogen so this convergence may be coincidental unless there is some recondite geometry or
structure that maintains the functional equivalence of this effect.
The absolute differences in the numbers of bits that deviated during intention and when the
magnetic field was present during intention were about 3000. Adjusting for the total duration of
the exposures for the subjects (about 1440 s), this would be associated with the energy of about
2 electron mass equivalents per second. This number is within the order of magnitude predicted
by the energy produced within the brain per second. Even if we accommodated the variability of
the intensity of the applied field and the individual differences for the time required to produce
the significant deviations from chance, the similarity of values indicate a potential quantitative
support for this process.
Why a quantum of energy within the cerebrum would affect specifically the quantum of energy
that simulates the movement of an electron across a p-n junction, in our opinion, is by far a
more important question. If non-locality is operative, then the conditions within the cerebrum
and the REG should be similar. The geometry may not be identical to the conditions by which
photon “entanglement” has been shown experimentally by Dotta and Persinger [32] and may
involve a fundamental form of entanglement that originated from primordial spin processes
with direct relevance to consciousness [33]. In the Dotta and Persinger studies [32]
simultaneous injection of hydrogen peroxide into sodium hypochlorite in two separated
localities produced a doubling of the photon emissions (measured by photomultiplier tubes), as
if the two localities were the “same space”, at least transiently, or that had been a transposition
of three-dimensional spatial axes. However, this only occurred if both localities shared the same
space-time structural features of the rotating magnetic fields with specific changes in angular
velocities.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
99
We suggest that the capacity for “excess correlation” between intention of the participant and
the shift in random variations of electron tunnelling within the REG is related to the shared
similarities of their geometries and spaces within which the dynamics occur. In general, the
widths of the p-region and n-region in a semiconductor are about 1.5∙10-7 m and 2.9∙10-7 m,
respectively. The total depletion width is about 0.4∙10-6 m. This width is within the range of the
synapse (contact diameter=0.5 to 2∙10-6 m). The tunnelling of electrons occurs within barriers of
thickness around 1 to 3 nm (or smaller) while the typical separation of the pre- and postsynaptic cleft or distance for (chemical synapses) is about 20 to 40 nm and electrical “synapses”
or gap junctions are about 2 to 3.5 nm. The gap for electron tunneling in a typical device can be
obtained by combining the widths of the p- and n-regions (1.5·10-7 m and 2.9·10-7 m
respectively). The ratio of the gap for electron tunnelling to the width through a semiconductor
medium would be 2∙10-9 m divided by 4.4∙10-7 m or 0.45∙10-2. The ratio of the gap to width for
the chemical synapse would be 3∙10-8 m divided by 1.3∙10-6 m or 2.3∙10-2. In comparison, the
ratio of the gap to width of the gap junction involves 3∙10-9 dived by 1.3∙10-6 m or 0.24∙10-2.
Considering the range involved for both p-n junctions and electrical (gap junction) synapses, the
ratios of gap to width values for both of these conditions are remarkably similar.
Electrical interfaces within the brain are as numerous as chemical synapses within the cerebral
cortices, thalamus, and hippocampus. Gap junctions are actual physical connections that couple
neighbouring neurons by large macromolecules that traverse the membranes of both adjacent
neurons. Direct exchange of ions and smaller molecules occur between the two cells. Gap
junctions are known for their capacities to rectify (facilitate current in one direction rather than
another) movements of charges as well as to coordinate electrical changes within large
populations of neurons. They couple with GABAergic interneurons within cerebral cortices and
thalamus, particularly in young animals. Spike transients from action potentials can penetrate
the gap junction and synchronize multiple neurons that share these interfaces including
distributed neuronal circuits [34].
This results in the synchronization of the “40 Hz” cortical rhythms which is minimized if the
expression of the chemical substrates for the gap junction is prevented because of an absent
gene. Gap junctions are also likely to be responsible for the revealing 40 Hz cortical patterns
that are commonly seen superimposed upon the theta (4 to 8 Hz) synchronous patterns
generated by the hippocampal formation. Such electrical coupling over large area and volumes
of cerebral cortical space may be the “cohesive” factor that has been considered essential for
producing a “cognitive field” as well as increasing the total power output by summating the very
small quantities that would otherwise be cancelled into an integrated value of substantial
magnitude.
There may be quantitative suggestions for the potential entanglement of energy and mass
between the gap junctions within the participants’ cerebral cortices and hippocampal formations
and the p-n junctions of the REG at approximately 0.25 m distance. If we assume a classic
Casimir effect described by:
[π2 (240)-1 ħca-4]∙S
ISSN: 2153-8212
(1),
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
100
where ħ is the modified Planck’s constant, c is the velocity of light and a is the distance between
the two planes (2 nm) with surface area S of 0.16 µm2 , the force would be 0.13∙10-4 N and when
applied across the 2 nm interface would involve an energy of 0.26∙10-13 J. The mass equivalent of
that energy is within range, given the variation in width and separation distances for both gap
and p-n junctions to that of the classical electron (~10-31 kg). One of the basic assumptions for
the Casimir force is that virtual particles can become actual particles when the appropriately
time-varying magnetic field is applied to a changing boundary. The time-varying magnetic field
employed in our present study could meet the criteria for that condition.
On the other hand, the complexity of the digital sequences generated by the REG was not
affected by intention. There was a general decrease in complexity when the experimental field
was applied, regardless if intention was present or absent. A decrease in complexity could be
associated with the consequence of repeating the same field pattern which by definition would
have deviated from the greater degrees of freedom that would constitute complexity. The
etiology of this effect is not clear. It is not likely to be related to crude current induction because
other experiments in which the field strengths were altered did not change the degree of
complexity. From another perspective, the fact that the actual deviation of the REG output was
affected by intention and attenuated by the simultaneous application of the magnetic field,
whereas complexity was not affected by intention, indicates that the two phenomena are quite
separate. In addition this differential indicates that the effects of intention involved processes
other than non-specific (generalized or artifactual) factors.
References
1) Mouritsen, H., Feenders, G., Liedvogel, M., & Kropp, W. Migratory birds use head scans to detect the
direction of the Earth's magnetic field. Current Biology, 2004; 14(21): 194+6-1949.
2) Klimley, A. P. Highly directional swimming by scalloped hammerhead sharks, Sphyrna lewini, and
subsurface irradiance, temperature, bathymetry, and geomagnetic field. Marine Biology, 1993; 117: 122.
3) Kimchi, T., Etienne, A. S., & Terkel, J. A subterranean mammal uses the magnetic compass for path
integration. Proceedings of the National Academy of Sciences of the United States of America, 2004;
101(4): 1105-1109.
4) Dimitrova, S., Mustafa, F. R., Stoilova, I., Babayev, E. S., & Kazimov, E. A. Possible influence of
solar extreme events and related geomagnetic disturbances on human cardio-vascular state: Results of
collaborative Bulgarian-Azerbaijani studies. Advances in Space Research, 2009; 43(4): 641-648.
5) Mulligan, B. P., Hunter, M. D., & Persinger, M. A. Effects of geomagnetic activity and atmospheric
power variations on quantitative measures of brain activity: Replication of the Azerbaijani studies.
Advances in Space Research, 2010; 45(7): 940-948.
6) Babayev, E. S., & Allahverdiyeva, A. A. Effects of geomagnetic activity variations on the
physiological and psychological state of functionally healthy humans: Some results of Azerbaijani
studies. Advances in Space Research, 2007; 40(12): 1941-1951.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
101
7) Snyder, C. W., Neugebauer, M., & Rao, U. R. The solar wind velocity and its correlation with cosmicray variations and with solar and geomagnetic activity. Journal of Geophysical Research, 1963; 68(24):
6361-6370.
8) Persinger, M. A. The possible role of dynamic pressure from the interplanetary magnetic field on
global warming. International Journal of Physical Sciences, 2009; 4(1): 44-46.
9) Richardson, I. G., Cliver, E. W., & Cane, H. V. Sources of geomagnetic storms for solar minimum and
maximum conditions during 1972-2000. Geophysical Research Letters, 2001; 28(13): 2569-2572.
10) Jahn, R. G., Dunne, B. J., Nelson, R. D., Dobyns, Y. H., & Bradish, G. J. Correlations of random
binary sequences with pre-stated operator intention: A review of a 12-year program. Journal of Scientific
Exploration, 1997; 11(3): 345-367.
11) Radin, D. I., & Nelson, R. D. Meta-analysis of mind-matter interaction experiments: 1959-2000. In
Healing, Intention, and Energy Medicine (pp. 39-48). London: Harcourt Health Sciences, 2003.
12) Giroldini, W. Eccles's model of mind-brain interaction and psychokinesis: A preliminary study.
Journal of Scientific Exploration, 1991; 5(2): 145-161.
13) Caswell, J. M., Collins, M. W. G., Vares, D. A. E., Juden-Kelly, L. M., & Persinger, M. A.
Gravitational and experimental electromagnetic contributions to cerebral effects upon deviations from
random number variations generated by electron tunneling. International Letters of Chemistry, Physics
and Astronomy, 2013; 11: 72-85.
14) Caswell, J. M., Dotta, B. T., & Persinger, M. A. Cerebral biophoton emission as a potential factor in
non-local human machine interaction. NeuroQuantology; in press.
15) Makarec, K., & Persinger, M. A. Geophysical variables and behavior: XLIII. Negative correlation
between accuracy of card-guessing and geomagnetic activity: A case study. Perceptual and Motor Skills,
1987; 65: 105-106.
16) Krippner, S., & Persinger, M. A. Evidence for enhanced congruence between dreams and distant
target material during periods of decreased geomagnetic activity. Journal of Scientific Exploration, 1996;
10(4): 487-493.
17) Dotta, B. T., & Persinger, M. A. Dreams, time distortion, and the experience of future events: A
relativistic, neuroquantal perspective. Sleep and Hypnosis, 2009; 11(2): 29-39.
18) Hunter, M. D., Mulligan, B. P., Dotta, B. T., Saroka, K. S., Lavallee, C. F., Koren, S. A., & Persinger,
M. A. Cerebral dynamics and discrete energy changes in the personal environment during intuitive-like
states and perceptions. Journal of Consciousness Exploration & Research, 2010; 1(9): 1179-1197.
19) Persinger, M. A., Dotta, B. T., Saroka, K. S., & Scott, M. A. Congruence of energies for cerebral
photon emissions, quantitative EEG activities and ~5 nT changes in the proximal geomagnetic field
support spin-based hypothesis of consciousness. Journal of Consciousness Exploration & Research, 2013;
4(1): 1-24.
20) Gissurarson, L. R. The psychokinesis effect: Geomagnetic influence, age and sex differences. Journal
of Scientific Exploration, 1992; 6(2): 157-165.
21) Radin, D. I. Environmental modulation and statistical equilibrium in mind-matter interaction. Subtle
Energies, 1993; 4(1): 1-30.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 85-102
Caswell, J. M., Vares, D. A. E., Juden-Kelly, L. M. & Persinger, M. A., Simulated Effects of Sudden Increases in
Electromagnetic Activity on Deviations in Random Electron Tunnelling Behaviour Associated with Cognitive Intention
102
22) Gearhart, L., & Persinger, M. A. Geophysical variables and behavior: XXXIII. Onsets of historical
and contemporary poltergeist episodes occurred with sudden increases in geomagnetic activity.
Perceptual and Motor Skills, 1986; 62: 463-466.
23) Roll, W. G., Saroka, K. S., Mulligan, B. P., Hunter, M. D., Dotta, B. T., & Gang, N. Case report: A
prototypical experience of 'poltergeist' activity, conspicuous quantitative electroencephalographic
patterns, and sLORETA profiles: Suggestions for intervention. Neurocase: The Neural Basis of Cognition,
2012; 18(6): 527-536.
24) Persinger, M. A., Koren, S. A., & Lafreniere, G. F. A neuroquantologic approach to how human
thought might affect the universe. NeuroQuantology, 2008; 6(3): 262-271.
25) Persinger, M. A. Solutions for real values of Minkowski four-dimensional space may link macro- and
micro-quantum processes in the brain. Neuroscience and Biobehavioral Reviews, 2012; 36: 2334-2338.
26) Saroka, K. S., Caswell, J. M., Lapointe, A., & Persinger, M. A. Greater electroencephalographic
coherence between left and right temporal lobe structures during increased geomagnetic activity.
Neuroscience Letters, 2013; 560, 126-130.
27) Mulligan, B. P., & Persinger, M. A. Experimental simulation of the effects of sudden increases in
geomagnetic activity upon quantitative measures of human brain activity: Validation of correlational
studies. Neuroscience Letters, 2012; 516(1): 54-56.
28) Murugan, N. J., Karbowski, L. M., Lafrenie, R. M., & Persinger, M. A. Temporally-patterned
magnetic fields induce complete fragmentation in planaria. PLoS ONE, 2013; 8(4).
29) Shannon, C. E. A mathematical theory of communication. The Bell System Technical Journal, 1948;
27: 379-423, 623-656.
30) Mach, Q. H., & Persinger, M. A. Behavioral changes with brief exposures to weak magnetic fields
patterned to simulate long-term potentiation. Brain Research, 2009; 1261, 45-53.
31) Dotta, B. T., Saroka, K. S., & Persinger, M. A. Increased photon emission from the head while
imagining light in the dark is correlated with changes in electroencephalographic power: Support for
Bokkon’s biophoton hypothesis. Neuroscience Letters, 2012; 513(2), 151-154.
32) Dotta, B. T., Koren, S. A., & Persinger, M. A. Demonstration of entanglement of “pure” photon
emissions at two locations that share specific configurations of magnetic fields: Implications for
translocation of consciousness. Journal of Consciousness Exploration & Research, 2013; 4(1).
33) Hu, H. & Wu, M. Spin as primordial self-referential process driving quantum mechanics, spacetime
dynamics and consciousness. NeuroQuantology, 2004; 2(1), 41-49.
34) Traub, R. D., Kopell, N., Bibbig, A., Buhl, E. H., LeBeau, F. E. N., & Whittington, M. A. Gap
junctions between interneuron dendrites can enhance synchrony of gamma oscillations in distributed
networks. Journal of Neuroscience, 2001; 21(23), 9478-9486.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
arXiv:2110.03518v2 [q-bio.NC] 5 Feb 2023
The Closure of the Physical,
Consciousness and Scientific Practice
Johannes Kleiner1,2 and Stephan Hartmann1,3
1 Munich Center for Mathematical Philosophy
2 Munich Graduate School of Systemic Neurosciences
3 Munich Center for NeuroSciences – Brain & Mind
Abstract We analyse the implications of the closure of the physical for
experiments in the scientific study of consciousness when all the details are
considered, especially how measurement results relate to physical events. It
turns out that the closure of the physical has surprising implications that
conflict with scientific practice. These implications point to a fundamental
flaw in the paradigm underlying many experiments conducted to date and
pose a challenge to any research programme that aims to ground a physical
functionalist or identity-based understanding of consciousness on empirical
observations.
1. Introduction
The closure of the physical is a central assumption in the philosophy of mind and in
the scientific study of consciousness [14, 22]. It underlies both functionalist and identity
theories of consciousness and is a central component of many, if not all, neuroscientific
models of consciousness. However, we will show below that the closure of the physical
is untenable in a scientific context because it implies that no experiment can actually
distinguish between two theories of consciousness that obey this assumption. It is
therefore incompatible with scientific practice and hence unscientific.
The central idea of our argument is the observation that in any scientific experiment
the measurement results must be stored or transmitted before analysis, and we show
that this means that the stored data are determined by the physical properties of a
storage device or a transmission channel. In conjunction with the closure of the physical, this means that the stored data are independent of which theory of consciousness
is true.
It has already been pointed out that the closure of the physical is a problematic assumption in a scientific context. [23] and [24], for example, make this point with respect
1
2
to property dualism and qualia epiphenomenalism. Our proof presented below covers the general case. It shows independently of any other metaphysical premises that
one of the central assumptions in the empirical study of consciousness is flawed. This
calls into question the theoretical basis of a large number of experiments conducted
to date and shows that the hope of basing a physical functionalist or identity-based
understanding of consciousness on empirical observations is null and void.
The remainder of this paper is organized as follows. Section 2 elaborates which
theories of consciousness our argument addresses and defines an epistemic version of
the closure of the physical. Section 3 identifies a necessary condition for theories of
consciousness to be distinguished by empirical data. Sections 4 and 5 discuss the role
of empirical data in the scientific study of consciousness and why they supervene on
physical events. Section 6 is devoted to the proof of our main claim, and Section 7
shows that the causal closure of the physical, as usually defined ontologically, implies
our definition, which ensures that our result holds in full generality. Finally, Section 8
contains some concluding remarks.
2. Theories of consciousness
We use the term theories of consciousness to refer to the theories that are tested,
compared, or derived in experiments in the scientific study of consciousness, regardless of what metaphysical status of consciousness they presuppose. This includes, for
example, Integrated Information Theory [20], Global Neuronal Workspace Theory [17]
or Higher Order Thought Theory [1], and in general all scientific theories which adhere
to functionalism, identity theory or epiphenomenalism. This also includes illusionist
or eliminativist theories that are subject to experimental testing, even though they do
not grant consciousness an independent ontological status, but merely aim to explain
why someone has the illusion of being conscious [26].
Our results rely on two general facts about theories of consciousness. The first is
that theories of consciousness relate to physical events, where physical events are the
kinds of events that are the subject of natural sciences such as biology, chemistry,
neuroscience, and physics. Some theories modify the description of physical events
provided by natural science, for example, by postulating changes in the temporal
evolution of physical states, as recently in [4], others simply adopt whatever natural
science says about physical events without any modification.
The causal closure of the physical is the assumption that for every physical effect,
there is a sufficient physical cause. Its key epistemic repercussion (cf. Section 7) is
that theories of consciousness must not amend whatever it is that the physical sciences
say or imply about physical events. We call this epistemic assumption closure of the
physical: A theory of consciousness obeys the closure of the physical if and only if it
does not posit any changes to the physical events explained, predicted or otherwise
determined by natural science.
3
This premise can be expressed concisely in formal terms. To this end, we introduce
two sets1 of event-descriptions. First, for any theory of consciousness T , we denote
by PT the physical events which T is committed to, for example the firing of some
neurons or the instantiation of some functional property. Every element in PT is a
description of an event that occurs, according to T , in the actual world. The description
specifies the event and may include properties or relational information about the
event. What exactly a description contains and in which language it is formulated is
not of importance here.
Second, we denote by PP the physical events which natural science explains, predicts
or determines. Whatever it is that natural science says or implies about the physical
events in the actual world is part of the class PP . Each element is in turn a description
of an event, including its properties and relations, and we allow that the description
is either deterministic or indeterministic.2
Since scientific theories are complex, PP may not be known or even knowable. And
as science progresses, PP is likely to change over time. For this reason, in what
follows, PP functions like a variable. It is not important what value this variable
actually takes, but only what relationship a theory of consciousness has to this variable.
A theory of consciousness obeys the closure of the physical only if it does not postulate any changes to the class PP . Thus, it does not replace, change, or add to the
description of physical events explained, predicted, or otherwise determined by natural science. This means that for every physical event in PT to which a theory of
consciousness is committed, there is an element of PP that provides a description of
that event in one of the languages of a natural science. The descriptions in the two
sets may differ in language, but not in content.
In formal terms, this means that there is an embedding of PT into PP , i.e. an
injective (one-to-one) function ι of the form
ι : PT −→ PP ,
(1)
which specifies for every physical event and description that the theory of consciousness is committed to the corresponding event and description explained, predicted, or
determined by natural science. The existence of this function is the concise meaning
of the closure of the physical introduced above: A theory of consciousness T obeys the
closure of the physical if and only if there exists a function ι as in (1). We will show
in Section 7 that the usual reading of the causal closure of the physical implies just
that.3
1Note that we do not distinguish between classes and sets in this paper.
2In terms of a fundamental physical theory, P may be thought of as comprising all events which are
P
part of those dynamically possible trajectories that occur in the actual world.
3The closure of the physical so conceived could also be defined in terms of variables and other concepts
used in scientific theories, such that a theory of consciousness obeys the closure of the physical if and
only if it makes no change to the concepts that natural scientific theories employ to predict and
4
3. Experiments
In the scientific study of consciousness, experiments are conducted to falsify, confirm, or distinguish between competing theories of consciousness. The most important
component of any experiment is measurement, i.e., laboratory operations that produce
a set of data which constitutes the result of the measurement.
The second general fact on which our argument is based is that scientific theories of
consciousness have something to say about possible measurement results. We assume
that any theory allows one to derive, for some experiments and under appropriate
auxiliary assumptions, a class of data sets which, according to the theory, may occur
as the result of the experiment. This requirement singles out scientific theories as
those to which our argument applies.4
We use the symbol M to represent an experiment, and furthermore introduce the
symbol OM to denote all data sets which could result from this experiment according
to some assumption or theory. So OM denotes the possible measurement results of M
in some context. If an experiment M only made measurements on one system and
everything were deterministic, then there would only be one data set in OM . But
experiments usually consider many systems and things are not deterministic, which is
why we have a whole class of data sets that can occur in M.5
Given an experiment M to which a theory T can be applied, we denote the data
sets which can occur in M according to T by OT . In experimental practice, OT is
deduced from T , making use of approximations and auxiliary assumptions, so that it
contains the pre- or retrodictions of T . But in our case we stick to the precise meaning
independently of approximations and auxiliary assumptions. Any result o ∈ OT can
occur in experiment M after T , and any o 6∈ OT cannot occur in M after T . If o ∈ OT
occurs, then the probability of T increases (and T is confirmed), and if o 6∈ OT occurs,
then the probability of T decreases (and T is disconfirmed). In a Popperian framework,
the occurrence of o ∈ OT provides a corraboration of T and the occurrence of o 6∈ OT
amounts to a falsification of T .
What matters for our purposes is that if two theories provide the exact same information about which results may or may not occur in an experiment, then these
theories cannot be distinguished in that experiment. Theories for which this is the
case are empirically indistinguishable. Put concisely in terms of the notation we have
explain physical events, or which otherwise determine physical events. While this formulation would
capture the more familiar assumption that “physical laws already form a closed system” [2, p. 127],
it introduces another level of abstraction (concepts used in scientific theories) that is avoided when
formulated in terms of events.
4In particular, if we assume that experiments are required to distinguish between competing theories
of consciousness, we assume that consciousness cannot be deduced from the physical or, if it can, that
experiments are required to figure out how because the deduction fails in practice due to complexity
and/or too little knowledge.
5For now, M can be thought of as an experiment actually conducted in the actual world to distinguish
between theories of consciousness, although logical possibilities will come into play in Section 4.
5
just introduced, two theories T and T ′ are empirically indistinguishable if there is no
single experiment M such that OT 6= OT ′ in M. So if two theories are to be empirically
distinguishable, they cannot yield exactly the same class of possible measurement results for each experiment. There must be at least one experiment in which OT 6= OT ′ ,
so that in this experiment there is at least a chance that a result o occurs which lies in
one but not in both classes and is thus consistent with one but not with both theories.6
It is natural to expect that a large number of experiments will not be able to
distinguish between two arbitrary theories, since experiments are usually designed
with specific theories in mind. Empirical indistinguishability holds only if for two
theories there is no experiment at all that can distinguish between them.
If an assumption implies that this is in fact true of all theories obeying this assumption, and if there are two or more competing theories which do so, this is obviously
problematic. In case such an assumption is implied, all experiments that seek to distinguish between theories become meaningless, and all subsequent differences between
theories obeying that assumption untestable. This is incompatible with any empirically based scientific practice, so we take this a sufficient condition to call such an
assumption unscientific. Thus, if an assumption implies that any two different theories obeying that assumption are empirically indistinguishable, we conclude that the
assumption is unscientific.
We emphasize that this condition is a decidedly weak sufficient condition for a particular assumption not to be scientific. We have by no means proposed a new solution
to the notorious demarcation problem. Moreover, the condition is independent of the
choice of the preferred account of theory testing. An assumption that is unscientific
in this sense undermines any empirical scientific progress in the field in question.
Experiments in the scientific study of consciousness usually use two different types of
measurements [3]. First, they make use of what are called third-person measurements
which employ standard scientific methods. Typical examples are EEG or fMRI recordings. Second, they use what might be called first-person or consciousness-inferring
measurements. This class of measurements has been characterized as using the subject’s access to his or her own conscious experience in some way, such as via verbal
reports or pressing of a button [18]. More recently, the term subjective measures of
consciousness has come to refer to these types of measures [12], in contrast to objective
measures and no-report paradigms [28], which infer a subject’s state of consciousness
indirectly, e.g., by evaluating forced choice tasks [5] or behavioral data such as optokinetic nystagmus and the pupillary reflex [9].
6Note that empirical indistinguishability is weaker than empirical equivalence, as defined, for example,
in [29] and [30]. Two theories are empirically indistinguishable if they make exactly the same testable
statements about experiments to which they are both applicable. Empirical equivalence also requires
that the two theories apply to exactly the same experiments.
6
What exactly the difference is between measurements in the first and third person
is not important for our purposes. The only important thing is that both types of
measurements produce results that need to be analyzed, interpreted or transformed.
To do this, they must be stored on a data repository. This fact has implications that
we analyze below.7
4. Data
We have minimally characterized measurements as laboratory operations that provide a data set that is designated as the result of the experiment. But what does it
mean that this data set must be stored on some device? To address this question, let’s
take a hard disk as an example. A hard disk stores data by magnetizing a thin film
of ferromagnetic material that forms the surface of the hard disk platter. The film is
made up of many tiny, sequentially aligned magnetic regions, each of which has a magnetization vector that can point in one of two directions. When data is stored on the
disk, the head of the drive arm moves over these areas and changes the magnetization
vector by applying electric fields. When reading data from the disk, the actuator arm
uses weaker electric fields to sense the magnetization vectors of the areas.
The data stored on the disk is the distribution of magnetization vectors across the
magnetic areas in terms of the order of the areas. Two copies of the same disk cannot
differ in the data stored on it without differing in at least some magnetization vectors.
The data is determined by the magnetization vectors.
The crucial thing about the magnetization vectors that determine the data stored
on a hard disk is that they are not just properties of the device, but actually physical
properties of the device, the kind of properties that are the subject of natural science, in
this case electromagnetism. Electromagnetism explains their causal properties, such
as how the magnetization vector responds to electric fields, and also their dynamic
properties, such as how magnetization vectors change over time without interactions.
Accordingly, the occurrence of a particular distribution of magnetization vectors
over the ferromagnetic film at a particular time is a physical event, the kind of event
that is the subject of natural science. It follows that the data stored on the hard disk is
determined by a physical event: in this case, the distribution of magnetization vectors
over the ferromagnetic film. There is no constraint on why or how this physical event
occurs, but once the event occurs, the data stored on the hard disk is determined.
7We emphasize that this also holds true for “measuring” consciousness by introspection. Because
science is an intersubjective endeavor, whatever is accessed by introspection in any experiment that
aims to distinguish among competing theories of consciousness has to be stored or transmitted in order
to be shared with other scientists. Nothing hinges on how precisely one flashes out what is special
about consciousness and its measurement. What matters below is only that measurement results need
to be stored or transmitted and that different theories of consciousness may be formulated which are
compatible with the same set of physical events. The closure of the physical enforces the latter.
7
This is true not only for hard drives, but for all data storage devices, such as solidstate drives or flash drives, where the relevant semiconductor properties can only be
explained using condensed matter theory and quantum mechanics. But even when
data is stored on something as simple as a piece of paper or a spoken word, the data
supervene on physical events, namely the distribution of ink molecules on the paper
material and air pressure fluctuations, which in these cases represent sound waves.
We can again express this fact succinctly in formal terms. Functions in the mathematical sense of the word are defined to capture exactly those cases where something
is completely determined by something else. Let us denote by P the set or class of
all physical events (and descriptions) that can possibly occur in the real world, and
by OD all records that can possibly be stored on a storage device D. The notion of
possibility at issue here is logical possibility. The physical events explained, predicted,
or determined by natural science for the actual world form a subset of P, the subset PP
we introduced above. The same is true for the physical events PT to which a theory
of consciousness is committed.
The fact that the physical events which occur in the actual world determine the
data that is stored on a storage device D can then be represented by a function
dD : P (P) −→ P (OD ) ,
(2)
where P (P) is the set of all subsets of P, called the power set of P, and where P (OD )
is the power set of OD . The function dD provides for every logically possible set of
physical events P ⊂ P of the actual world a class of data sets OD ⊂ OD that could be
stored on D at a particular time, so it maps element-wise as
dD : P 7−→ OD .
(3)
It selects from all physical events which, according to P, are part of the real world those
which are relevant for data storage on the device D, e.g. the magnetization vectors in
the case of a hard disk. Since P may contain indeterministic statements, the output
of the function may also be indeterministic. For this reason, the output is represented
by a class OD , which may contain more than one record o. However, although OD is
consistent with indeterminism in physical events, it is completely determined by PP .
This is enforced by the fact that dD is a function. If D is not instantiated in a set P,
the function simply returns the empty set.
In order to use this function in the following, we have to consider two conditions. The
first condition arises from the fact that the data stored on a device D corresponding
to some physical events is independent of the language used to describe those events.
Applied to the embedding ι introduced in (1), this means that
(4)
dD ι(PT ) = dD PT .
The content of ι(PT ) and PT is the same, so also the data stored on D.
8
The second condition targets situations where one set of physical events completely
contains another, e.g. when the latter is a partial description of the former. A set of
physical events P2 completely contains another set P1 if all event descriptions of P1
are also contained in P2 , which means that P2 describes exactly the same events as
P1 . It may add to the description of P1 , but it does not change it in any way. Thus,
if P1 includes all the physical events required to instantiate a data repository D, and
thus determines the data stored on D, it follows that P2 also includes these events, so
that the data that P1 and P2 determine to be stored on D are the same. Whenever
we have P1 ⊂ P2 and D is instantiated in P1 , we have
dD P1 = dD P2 .
(5)
5. Measurement results
We are now ready to apply this result on data storage to experiments in the scientific
study of consciousness. The measurements performed in these experiments tend to be
quite complex. They may employ advanced brain imaging techniques such as EEG,
ECoG, or fMRI, and require finely tuned equipment and sophisticated analysis to learn
about a subject’s state of consciousness.
In the case of EEG, ECoG or fMRI recordings, it is relatively clear what the result
of such measurements is. It is the data set that the scanner provides after each trial
and that is stored in computer memory. In the case of subjective measures, one would
normally expect reports or keystrokes to count as results; in the case of objective
measures, changes in pupil size and the like. Crucially, however, all of these are
physical events. The electrical activity that an EEG electrode measures is as much
a physical event as the sound waves that make up a spoken word or the mechanical
movements of a button.
Our analysis from the last section allows us to make this point despite the terminological ambiguities about what to count as the result of a measurement. A necessary
condition for a record to count as the result of a measurement is that it be stored
somewhere. This can be computer memory, but it can also be something simpler like
ink on paper or density fluctuations in sound waves. Even data transmission, such as
in a cable attached to a button that a person presses, is a form of data storage, albeit
of very short duration. So for something to be considered a measurement at all, there
must necessarily be a data repository D, so that some of the data stored on D is the
result of the measurement.
However, we have established above that the data stored on a device D is determined
by physical events. Since a part of this data represents the measurement result, the
measurement results are also determined by physical events. How these physical events
come about – what their causes are – is not constrained by our analysis. The events
can have purely physical causes, physical and non-physical causes, or a priori only
9
non-physical causes. Which of these cases applies and with respect to which notion of
causality depends on the theory of consciousness.
As before, let us denote by M an arbitrary but fixed experiment in the scientific
study of consciousness, and let us denote by D the data store or stores necessarily
used in M to store the results of the measurement. We have already introduced the
symbol OM to denote the data sets that, under certain assumptions or theories, could
be the possible outcomes of the experiment M. Our analysis from the previous section
then shows that OM is also determined by the function dD introduced in (2), namely
by restricting dD to the part of the data stored on D that represents the measurement
results. If we denote this restriction by dM and all data sets that could possibly result
from M by OM , we obtain a function
dM : P (P) −→ P (OM )
P 7−→ OM ,
(6)
which maps any set of physical events P, which could possibly represent the physical
events of the actual world, to the measurement results, which in this case would be
determined as the result of the experiment M.
The function dM establishes a connection between what a theory of consciousness T
predicts or postulates about physical events in the real world, on the one hand, and the
possible measurement outcomes that can occur according to T , on the other. It selects
from the events PT that the theory T is committed to those events which determine
the data that is stored on D. Making use of the symbol OT introduced above to denote
the possible measurement results that can occur in M after T , this means that
dM (PT ) = OT .
(7)
In this way, we can determine OT independently of approximations or auxiliary assumptions.
6. Why the closure of the physical is unscientific
By considering that measurement results must be stored and are thereby determined
by physical events, we have obtained a novel, additional handle for analyzing experiments in the scientific study of consciousness. In addition to what experimenters derive
from a theory T and appropriate auxiliary assumptions, we can now analyze measurement results along the path of what a theory of consciousness says about physical
events. This gives rise to the following theorem.
Theorem 1. The closure of the physical is unscientific.
Proof. Let T1 and T2 denote two theories of consciousness which obey the closure of the
physical. This implies that there exist embeddings ι1 : PT1 −→ PP and ι2 : PT2 −→ PP
as in (1). Let M denote an experiment to which both T1 and T2 are applicable, and D
10
the data storage device(s) used in that experiment. Because of condition (4), we have
dD (ι1 (PT1 )) = dD (PT1 ) and dD (ι2 (PT2 )) = dD (PT2 ).
Both T1 and T2 need to be committed to the existence of physical events which
instantiate the data storage device D used in M, for otherwise they would violate the
very conditions that make M possible. Therefore, D is instantiated in both PT1 and
PT2 . Because applying ι1 resp. ι2 does not change the content of the described events,
it follows that D is also instantiated in ι1 (PT1 ), resp. ι2 (PT2 ).
Because ι1 is an embedding, we have ι1 (PT1 ) ⊂ PP . Because D is instantiated in
ι1 (PT1 ), Equation (5) applies so that we have dD (ι1 (PT1 )) = dD (PP ). The same applies
to ι2 , so that also here, Equation (5) implies dD (ι2 (PT2 )) = dD (PP ). So we in fact have
dD (ι1 (PT1 )) = dD (ι2 (PT2 )), which in light of the above implies dD (PT1 ) = dD (PT2 ).
We thus find that the data stored on D is exactly the same for both theories.
Restriction to dM introduced in (6) furthermore implies that dM (PT1 ) = dM (PT2 ), and
because of (7), this implies that OT1 = OT2 . So the measurement results of M are
exactly the same according to both T1 and T2 . Independently of which predictions one
arrives at by making use of auxiliary assumptions, the closure of the physical implies
that the data sets which can occur in M cannot differ.
Since M was chosen arbitrarily, this conclusion holds for any experiment M, so
T1 and T2 are empirically indistinguishable. And because T1 and T2 were arbitrarily
chosen among the theories obeying the closure of the physical, we can conclude that
all theories obeying the closure of the physical are empirically indistinguishable. It
follows that the closure of the physical is an assumption that is unscientific.
7. Causal closure of the physical
The causal closure of the physical is the assumption that for every physical effect
there is a sufficient physical cause. This is an ontological assumption; it refers to what
is the case in the actual world. In contrast, the assumption we have been working with
above – that a theory of consciousness obeys the closure of the physical if and only
if it does not postulate changes in physical events explained, predicted, or otherwise
determined by natural science – is epistemic in nature, it depends on the definition,
formulation, and content of a theory of consciousness.
The precise meaning of the causal closure of the physical depends heavily on what
notion of causality one subsumes, what ontology one grants to causality (if any), and
what one allows as relata of the causal relation. Nevertheless, there is a great deal of
consensus about what epistemic implications this assumption has.
According to Jaegwon Kim, for example, the causal closure of the physical implies
that “to explain the occurrence of a physical event we never need to go outside of the
physical realm” [14, p. 147]. And Frank Jackson characterizes the causal closure of the
physical as the claim that “the physical sciences, or rather some natural extension of
11
them, can in principle give a complete explanation for each and every bodily movement,
or at least can do so up to whatever completeness is compatible with indeterminism
in physics” [13, p. 378].
These statements exemplify that the causal closure of the physical is generally taken
to imply that every physical event which is explained at all, is explainable by natural
science. But explanation, precisely construed [27], is only one way in which a theory
can address events. Making room for prediction and other possible ways as well, we
may take the above to imply that every physical event which is predicted, explained,
or determined at all, can be predicted, explained, or determined by natural science.
Applied to a theory of consciousness, this means that any physical event that the
theory explains, predicts, or determines can (eventually) be explained, predicted, or
determined by natural science. But for this to be true, the theory must not replace,
alter, or add to the natural science account of physical events, because otherwise it
would be committing itself to physical events that cannot be explained, predicted, or
determined by natural science. Thus, the causal closure of the physical implies that a
theory of consciousness cannot make changes to the physical events that are explained,
predicted, or determined by natural science.
This point can be stated more clearly in formal terms. We have denoted the set
of physical events that a theory of consciousness is committed to by PT . These are
the events explained, predicted, or otherwise determined by that theory. And we have
denoted the set of physical events explained, predicted, or otherwise determined by
natural science (now or in the future) by PP . Thus, if every physical event that can be
explained, predicted, or determined at all can be explained, predicted, or determined
by natural science, then every event that is in PT is also in PP . Taking into account
the different languages that can be used in the two cases, this means that for every
event description in PT there is a corresponding event description of the same event
in PP . This constitutes an injective function that maps PT to PP .
We thus arrive at exactly the same formal requirement as in Equation (1). The
causal closure of the physical implies that there is an embedding ι : PT → PP that
specifies for each physical event and physical description that the theory of consciousness is bound to the corresponding event and description explained, predicted, or
determined by natural science.8 Causal closure of the physical implies closure of the
8More advanced formulations of the causal closure of the physical lead to the same conclusion. Consider
for example, the proposal by Barbara Montero and David Papineau in [19], that “[e]very physical
event is determined, in so far as it is determined at all, by preceding physical conditions and laws”.
Every physical event that is determined by preceding physical conditions and laws is an element of
the class PP . Every element of PT is, according to the broad reading of ‘determined’ applied [19],
determined by a theory of consciousness. Hence it follows that every event in PT is also in PP , and
taking into account the different languages that may be used to describe the event, that there is an
embedding ι as in Equation (1).
12
physical, and as a corollary of Theorem 1 we posit that causal closure of the physical
is also unscientific.9
We emphasize that nowhere in our argument do we restrict to physical events which
are already explained or predicted by natural science. What matters is only which
relation a theory of consciousness proposes between the physical events it is committed
to and the physical events that natural science posits. Even if a theory presupposes
that the physical events it associates with conscious experiences are determined by
physical laws, but cannot in practice be explained or predicted based on these laws,
as weak emergentist theories would have it, our argument applies. Theories of this
sort may be wrong about what they say about physical events, and experiments may
help to determine whether this is the case, but insofar as they buy into the very
same underlying account of physical events as all other theories, the measurement
results necessarily are the same as if any other theory were true. Because of the weak
emergence claim, no postulate of such theory can imply any changes in the underlying
physical events, and ipso facto no changes in measurement results.10
8. Conclusion
We have shown that the causal closure of the physical goes far beyond what is usually considered. Since all measurement results in the scientific study of consciousness
are either physical events (such as keystrokes or sound waves) or at least determined
by physical events (such as data stored on hard disks), no two theories obeying the
causal closure of the physical can actually be distinguished in experiments. Our result
applies to all major neuroscientific theories of consciousness as well as to the leading
philosophical paradigms in the field. It applies to any theory of consciousness that fits
into the natural science account of physical events without altering it. This includes
all functionalist and identity theories of consciousness, such as GNW [17], HOT [1],
AST [10], or predictive processing-based theories [25], as well as eliminativist or illusionist theories [8]. But it also includes theories such as IIT, whose mathematics takes
the form of a function that maps physical states and events to conscious states and
events [15].11
9
We note that the commonly understood epistemic reading of the closure of the physical, as expressed
in Kim and Jackson’s remarks, follows from the causal closure of the physical, as defined in the
beginning of this section, only if an appropriate notion of ‘physical’ is presupposed. This means that
the causal closure of the physical must forbid the introduction of new physical entities that have effects
that are not not explained by the physical sciences.
10
That is not so for strong emergentist theories, of course. These introduce genuine new causes and
effects which are not claimed to be reducable to fundamental physical laws. It is well known that strong
emergentist theories are not compatible with physicalism and the causal closure of the physical [21].
11
Our results do not, however, apply to theories of temperature, life, or similar. They are fully compatible with there not being difficulties of the sort we point out in distinguishing different such theories
empirically. Consider, as an example, the case of temperature, whose relation to microphysical events
is sometimes claimed analogous to consciousness’ relation to physics. In contrast to consciousness,
however, experiments on temperature explore a purely macroscopic theory – thermodynamics – which
13
We have shown that no experiment of any kind can actually distinguish between
these theories. Whatever measurement result is consistent with one theory is necessarily consistent with the other, because qua closure of the physical, the physical
functioning of the brain, from stimulus presentation to verbal message or similar output, is exactly the same according to all these theories. This observation is at odds
with the numerous experiments conducted to date to distinguish precisely between
some of these theories. Our results show that there is a major flaw which underlies these experiments. The theories on which these experiments are based violate a
necessary condition for the experiments to work as intended.
There are two potential conclusions that one can draw from our results. Either,
experimenters do not really adhere to the closure of the physical when conducting
experiments, but implicitly assume that the theories tested modify what falls solely
within the realm of natural science. If this is the case, then our results constitute
an imperative to improve the tested theories and make explicit what is implicitly
assumed. If, on the other hand, experimenters do not implicitly adhere to the closure
of the physical when running experiments, then our results call into question the
very conclusions drawn on the basis of these experimental results. In either case, our
results show that the closure of the physical must be abandoned in both theory and
experiment. Theories of consciousness must explicitly state how what they take to be
consciousness (physical or otherwise) comes to determine reports and other measures
of consciousness, and to do this they must enter the realm of natural science.
In a very different context, Einstein once asserted that “[it] is the theory which
decides what we can observe” [7, 11]. It seems that this point has not yet been fully
recognized in the construction of scientific theories of consciousness.
Acknowledgments. This research was supported by grant number FQXi-RFP-CPW2018 from the Foundational Questions Institute and Fetzer Franklin Fund, a donor
advised fund of the Silicon Valley Community Foundation. We would like to thank
Sander Beckers, Ophelia Deroy, Alexander Gebharter, Kobi Kremnitzer, Christian
List, Paul Taylor and Wanja Wiese for helpful discussions, and David Chalmers, Joe
Dewhurst, Timo Freiesleben, George Musser and Naftali Weinberger for feedback on
an earlier draft.
does not address microphysics at all. The relation between temperature and microphysics is addressed
only in terms of theory reduction of thermodynamics to statisctical physics [6]. What is more, in
statistical physics, the microphysical state actually depends on temperature, as apparent for example
from the fact that temperature is part of the partition function that describes the state’s statistical
properties [16]. If one were to change one’s theory of how temperature supervenes on the physical,
one would have to change these statistical properties as well so as to ensure the link to thermodynamics remains valid. Different theories of temperature are not compatible with one and the same
microphysical distribution.
14
References
[1] R. Brown, H. Lau, and J. E. LeDoux. Understanding the higher-order approach
to consciousness. Trends in Cognitive Sciences, 23(9):754–768, 2019.
[2] D. J. Chalmers. The Conscious Mind: In Search of a Fundamental Theory. Oxford
University Press, Oxford, 1996.
[3] D. J. Chalmers. How can we construct a science of consciousness? In The
Cognitive Neurosciences III, pages 1111–1119. MIT Press, Boston, MA, 2004.
[4] D. J. Chalmers and K. J. McQueen. Consciousness and the collapse of the wave
function. arXiv preprint arXiv:2105.02314, 2021.
[5] A. Del Cul, S. Baillet, and S. Dehaene. Brain dynamics underlying the nonlinear
threshold for access to consciousness. PLoS Biology, 5(10):e260, 2007.
[6] F. Dizadji-Bahmani, R. Frigg, and S. Hartmann. Who’s afraid of Nagelian reduction? Erkenntnis, 73(3):393–412, 2010.
[7] T. Filk. It is the theory which decides what we can observe (Einstein). In Contextuality from Quantum Physics to Psychology, pages 77–92. World Scientific,
Singapore, 2016.
[8] K. Frankish. Illusionism as a theory of consciousness. Journal of Consciousness
Studies, 23(11–12):11–39, 2016.
[9] S. Frässle, J. Sommer, A. Jansen, M. Naber, and W. Einhäuser. Binocular rivalry:
frontal activity relates to introspection and action but not to perception. Journal
of Neuroscience, 34(5):1738–1747, 2014.
[10] M. S. Graziano and T. W. Webb. The attention schema theory: a mechanistic
account of subjective awareness. Frontiers in Psychology, 6:500, 2015.
[11] W. Heisenberg. Physics and Beyond. Allen & Unwin, London, 1971.
[12] E. Irvine. Measures of consciousness. Philosophy Compass, 8(3):285–297, 2013.
[13] F. Jackson. Mental causation. Mind, 105(419):377–413, 1996.
[14] J. Kim. Philosophy of Mind. Westview Press, Boulder, 1996.
[15] J. Kleiner and S. Tull. The mathematical structure of integrated information
theory. Frontiers in Applied Mathematics and Statistics, 6:74, 2021.
[16] L. D. Landau and E. M. Lifshitz. Statistical Physics Part 1. Pergamon Press,
1980.
[17] G. A. Mashour, P. Roelfsema, J.-P. Changeux, and S. Dehaene. Conscious processing and the global neuronal workspace hypothesis. Neuron, 105(5):776–798,
2020.
[18] T. Metzinger. The problem of consciousness. In T. Metzinger, editor, Conscious
Experience, pages 3–37. Imprint Academic/Schoningh Thorverton, UK, 1995.
[19] B. Montero and D. Papineau. A defence of the via negativa argument for physicalism. Analysis, 65(3):233–237, 2005.
15
[20] M. Oizumi, L. Albantakis, and G. Tononi. From the phenomenology to the mechanisms of consciousness: integrated information theory 3.0. PLoS Computational
Biology, 10(5):e1003588, 2014.
[21] T. O’Connor. Emergent Properties. In E. N. Zalta, editor, The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, Winter 2021
edition, 2021.
[22] D. Papineau. The causal closure of the physical and naturalism. In A. Beckermann,
B. P. McLaughlin, and S. Walter, editors, The Oxford Handbook of Philosophy of
Mind, pages 53–65. Oxford Universaity Press, Oxford, 2009.
[23] M. Pauen. Painless pain: Property dualism and the causal role of phenomenal
consciousness. American Philosophical Quarterly, 37(1):51–63, 2000.
[24] M. Pauen. Feeling causes. Journal of Consciousness Studies, 13(1-2):129–152,
2006.
[25] T. Schlicht and K. Dolega. You can’t always get what you want. Philosophy and
the Mind Sciences, 2, 2021.
[26] M. Sprevak and E. Irvine. Eliminativism about consciousness. In A. Beckermann,
B. P. McLaughlin, and S. Walter, editors, Oxford Handbook of the Philosophy of
Consciousness, pages 348–370. Oxford University Press, Oxford, 2020.
[27] M. Strevens. Scientific explanation. In D. Borchert, editor, Encyclopedia of Philosophy, pages 518–27. Macmillan Reference USA, New York, 2006.
[28] N. Tsuchiya, M. Wilke, S. Frässle, and V. A. Lamme. No-report paradigms: extracting the true neural correlates of consciousness. Trends in Cognitive Sciences,
19(12):757–770, 2015.
[29] J. O. Weatherall. Theoretical equivalence in physics, Part 1. Philosophy Compass,
14(5):e12592, 2019.
[30] J. O. Weatherall. Theoretical equivalence in physics, Part 2. Philosophy Compass,
14(5):e12591, 2019. |
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 691-696
Kaufman, S. E., Seeing the Universe from the Inside Looking Out
691
Article
Seeing the Universe from the Inside Looking Out
Steven E. Kaufman*
ABSTRACT
From the outside looking in everything appears to be different. But from the inside looking out
everything appears the same, as it is all seen to be composed of the same Existential Substance
that is Consciousness. Likewise, clay can be molded into an infinity of shapes, which if only
seen from the outside would appear to be an infinite number of different things. But when it is
known that all those things are actually molded from the same material, as it were, then the
differences becomes secondary to the identity of underlying composition and content.
Key Words: Consciousness, Universe, inside looking out, existential substance.
My philosophy is very simple. The universe is actually and ultimately composed of the same
thing that apprehends the universe. That is, that which apprehends the universe is that of which
the universe is actually composed. What Exists at every point in the universe, and in all
likelihood beyond, is the same thing that Exists directly where each Individual Exists, which is
the Consciousness that apprehends experience.
Why do we not see this? Why do we think that what exists elsewhere is different than what exists
where we are? There are many reasons. One is that we do not see what exists where we are as
being Consciousness, rather we see a material body. And when we look around we don't see
Consciousness, we see material reality, and so that is what seems or appears to be there. Yet
what could we see without Consciousness, what could we see in the absence of that which Exists
directly where we are?
And if one understands that Consciousness is what Exists directly where they are, why then
should that not be what Exists elsewhere as well? We look at a rock and say that what is there
cannot be Consciousness, cannot be apprehending experience, because it does not have a central
nervous system. But that assumes that the apprehension of all experience by Consciousness
requires what we apprehend as a central nervous system. It may very well be that the creation
and apprehension of the majority of physical experience requires a central nervous system,
requires this apparatus, which is Itself composed of Consciousness and serves the purpose of
allowing Consciousness to become involved in a different level of relation with
Itself and thereby create what Consciousness apprehends as physical experience, but that does
not mean that in the absence of such an apparatus there is no apprehension of experience of any
sort.
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 691-696
Kaufman, S. E., Seeing the Universe from the Inside Looking Out
692
When we see a rock or any material reality we are looking at it from the outside looking in, and
so are only apprehending its surface features. We know nothing of the content. And if we break
the rock apart and examine its smaller pieces, to see what minerals it is composed of, we are still
looking at it from the outside looking in, and we still know nothing of its actual content, still
know nothing regarding that of which it is actually composed. And if we break it apart further
and look at it at the molecular level, and then at the atomic level, and then at the subatomic level,
we are still looking at it from the outside looking in, and still know nothing of its content, still
know nothing regarding its actual composition, i.e., of what it is ultimately composed. In all of
these endeavors we are just making an etching of what is actually there and not getting at what is
actually there.
But a funny thing happens when we start to make the etchings at a very small level, in that the
way the etchings appear becomes inseparable from the way they are being created. In fact, the
way the etchings, i.e., physical experiences or realities, appear are always inseparable from the
way they are created, it is just that at the quantum level the inseparable relation between the
Observer and the apprehended reality becomes evident and unavoidable.
To understand what a rock or any material reality, or even space itself, is actually composed of,
one does not need an atom smasher or supercollider, rather, one needs only logic and reason,
unbiased and unmoved by what appears to be. To understand what any material reality is actually
composed of one need only look at it from the inside looking out. From the inside looking out
one sees material reality as an experiential reality arising within Consciousness, a Consciousness
that has Itself taken on a dimension of Structure as a result of the iterative and progressive
relations in which it is has become involved with Itself as it continually evolves Itself toward a
better feeling and more wanted experience at all levels of Existential self-relation and
experiential creation, i.e., emotional, mental, and physical. Conversely, from the outside looking
in material reality seems to be composed of some more fundamental material reality, which itself
seems to be composed of a more fundamental material reality, and on and on and on, with this
progressive material deconstruction mirroring a partial unraveling of the progressively
constructed under-Structure, i.e., the Relational Structure composed of Existence as it is being
iteratively and progressively in relation to Itself, which progressive Relational Structure
underlies and so is the basis of the etching that is apprehended as material reality.
Consider your own body. From the outside looking in it appears to be nothing more than matter,
whatever that is. But from the inside looking out there is Consciousness apprehending emotional,
mental, and material reality.
From the outside looking in everything appears to be different. But from the inside looking out
everything appears the same, as it is all seen to be composed of the same Existential Substance
that is Consciousness. Likewise, clay can be molded into an infinity of shapes, which if only
seen from the outside would appear to be an infinite number of different things. But when it is
known that all those things are actually molded from the same material, as it were, then the
differences becomes secondary to the identity of underlying composition and content.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 691-696
Kaufman, S. E., Seeing the Universe from the Inside Looking Out
693
The world you see around you is molded from Consciousness, in as much as it is ultimately
composed of Consciousness that has molded and continues to mold Itself through iterative and
progressive relation to Itself, like twisting a rubber band repeatedly upon itself, into an overall
Relational Structure of Reality from which and within which other Relational Structures extend
and arise. And all of those Relational Structures are composed of Consciousness, and when one
Relational Structure comes to be in relation to another Relational Structure, a boundary arises
and so is created where they meet and become oriented in relation to each other, and it is that
created boundary that is apprehended as a mental or physical experience by the Consciousness of
which the Relational Structures are composed.
Thus, experience rather than Consciousness seems to be what is there because experience is the
etching that is created and apprehended when What Is Actually There, i.e., Consciousness,
comes to be in relation to Itself. Thus, the universe is composed of an invisible Substance,
because that of which the universe if composed cannot Itself be an experience. As the universe is
composed of an invisible Substance there are two ways to go about examining what's there, from
the outside looking in or from the inside looking out. Looking at what's there from the outside
looking in always creates an etching. But the etchings, no matter how detailed, will always just
be etchings, and will never be what is there directly, because the Nature of What Is There
directly is different than the nature of what appears to be there experientially. Thus, the etching
itself is always something different or other than, i.e., of a different nature than, What Is Actually
There.
There is something there where physical experience seems to be or presents itself as being, but
What Is Actually There is not any sort of physical experience. Rather, What Is Actually There is
Consciousness being in relation to Itself creating Relational Structure and experience. And when
Consciousness is in relation to Itself at the third level of Existential self-relation those relations
create what the Consciousness involved in those relations apprehends as physical experience or
physical reality. But underlying that experientially created reality, that etching, is the Reality of
an under-Structure, the Reality of a Relational Structure composed of Existence as it has become
and is being configured in relation to Itself through iterative and progressive relation to Itself,
while simultaneously, as the product of those same relations, creating what it apprehends as the
progression of emotional, mental, and physical experience.
And it is this under-Structure and its relation to experience that must be recognized in order for
there to be an unraveling of the paradoxes that continue to confront quantum physics as it probes
up to and beyond the limits of physically created experience, since the source of all the
paradoxes confronting quantum physics have to do with trying to explain the behavior of
physical reality within the context of a physical model, i.e., in the context of a model wherein
physical reality is conceived as being what is actually there and so in no need of an underStructure, rather than within the context of an experiential model, which is to say, within the
context of a model that takes into account the way physical reality, as an experiential reality, is
created as the product of some relation of What Is Actually There to Itself, and so takes into
account the fact that experience is always Experiencer dependent and therefore must also rest
upon and extend from some underlying Structure, i.e., an under-Structure, composed of What Is
Actually There both being in relation to Itself and simultaneously apprehending the products of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 691-696
Kaufman, S. E., Seeing the Universe from the Inside Looking Out
694
its relations to Itself as experience. Consciousness therefore is identical to What Is Actually
There insofar as one is referring to the innate ability and unavoidability of What Is Actually
There to apprehend as experience the products of its relations to Itself, as a mirror that is bent
back upon itself has no choice but to contain within itself the reflection created by that relation.
The physical paradoxes exist not because the behavior of the things is truly paradoxical, as things
are observed to behave as they are observed to behave. Rather, it is only the failure of the
observed behavior to comport with underlying conception that creates paradox. Put another way,
it is the incongruity between what is experienced at the physical level and what is conceived at
the mental level that is the paradox. The observations are not incorrect, rather it is the conceptual
framework in which they are being analyzed that is fundamentally incorrect and is the source of
the perceived/conceived paradox. When What Is Actually There behaves according to its Nature
in a way that is outside the boundaries of what it is possible to create as physical experience, e.g.,
seeming to exist simultaneously as the opposite and mutually exclusive realities of wave and
particle, the incorrect framework is the conceptual framework that demands that these
observations be accounted for in the context of the assumption that the observed experiences are
what is actually there. And as the experiences are not What Is Actually There, any more than a
reflection on the surface of a pond is what is actually there, paradox ensues as a result of the
incongruity between the way the experiences are conceived of as being able to behave and the
way they are actually observed to behave. The paradox arises from trying to fit the observed
behavior into a conceptual framework that is an illusion, inasmuch as the conceptual framework
wherein physical reality is conceived as being what is there does not correspond to the Nature of
Reality, which is to say, to any underlying Actuality. Conversely, in the experiential model,
where the conceptualization of reality takes into account both the under-Structure of Reality as
well as experience as something that is created within the context of that under-Structure, the
seemingly paradoxical quantum observations of wave-particle duality, uncertainty, non-locality,
and the collapse of the wave-function, rather than introducing paradox into the model, fit
perfectly into and so strengthen that model.
In short, these paradoxes are all the result of the limitations inherent in the Individual's creation
of experience, as observed and analyzed from within a context where the part the Individual
plays in the creation of what they apprehend as experience is either completely unnoticed and
unappreciated, or only noticed to the extent that noticing has become unavoidable. All
experience requires the involvement of the Individual that is apprehending the experience is
some relation, which involvement then precludes that Individual's simultaneous involvement in
the mutually exclusive relations necessary to create the opposite experiences. Every experience
involves an Individual in some relation and so orientation relative to an underlying Relational
Structure or Actuality. Because experience is the product of a relation in which the Individual
that is apprehending the experience must be involved, there are negative and positive limitations
upon what it is possible for an Individual to simultaneously create and apprehend as experience,
unavoidable preclusions and inclusions, relations in which an Individual cannot possibly be
involved in a given moment owing to relations in which they are already involved in that same
moment, and so experiences that the Individual cannot possibly create and apprehend in that
moment, which negative limitation underlies the phenomena of wave-particle duality and
uncertainty, and there are relations in which an Individual must be involved owing to relations in
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 691-696
Kaufman, S. E., Seeing the Universe from the Inside Looking Out
695
which they are already involved, and so experiences that the Individual cannot help but create
and apprehend, which positive limitation underlies the phenomenon of non-locality.
The observed paradoxical behavior is actually arising from a level of Reality, i.e., the underStructure, that the incorrect framework precludes one from apprehending, owing to the
impossibility of an Individual's simultaneous apprehension of experiential opposites, which in
this case specifically refers to the fact that one cannot simultaneously conceive of both material
reality and an immaterial reality as being what is actually there. Thus, the observed behavior
arises from the behavior of a Reality that is all but completely hidden from Itself, from its True
Nature, as it wanders about in human form. The observed behavior, e.g., wave-particle duality
and uncertainty, cannot be accounted for within the physical model because these very behaviors
lie at the heart of the creation of physical reality, as an experiential reality, as unavoidably being
the product of a relation in which the Individual that is apprehending the experience must
themself be involved, and so has inherent limitations in its creation that extend directly from the
limitations inherent in the Individual's ability or not to be involved in the relations necessary to
create an experience.
Experience can be either accurately or inaccurately reflective of What Is Actually There, while
like a reflection never being That directly, and so conceptions of reality can be either accurately
or inaccurately reflective of What Is Actually There. When the conception does not accurately
reflect What Is Actually There then the behavior of What Is Actually There will at some point
diverge from the inaccurate conception, creating an experience or sets of experiences that cannot
be accounted for within the confines of the inaccurate conception, which divergence and
incongruity of experience is the introduction of paradox. Conversely, when the conception does
accurately reflect What Is Actually There then the behavior of What Is Actually There will
converge with the accurate conception, so that the experience or sets of experiences that cannot
be accounted for within the confines of the inaccurate conception are now not only accounted
for, but act as the well fitting pieces of a puzzle, which convergence and congruity of experience
is called understanding or knowing and is the dissolution of paradox.
Paradox is coming across a piece of a puzzle that has no way of fitting into the puzzle as one has
assembled it so far. If one finds a puzzle piece for which there is no place in the puzzle as it has
been assembled up to that point, one can either try to cram that piece into the puzzle as already
built, making the already built puzzle the focal or fixed point around which the observation-piece
must revolve, or one can take the opposite approach and let the conception of reality pivot
around the fixed observation-piece, not trying to fit the seemingly paradoxical observations into
an already existent conception of reality, such as a physical model, rather, letting the seemingly
paradoxical observations be the fixed focal point around which one pivots and rebuilds the entire
puzzle of reality to seamlessly fit together what are, from the perspective of the physical model,
both paradoxical and non-paradoxical observations.
We use physical experience to create an etching of what is there, and the etching is so detailed
and vivid that we forget that it is just an etching, and so by its nature other than What Is Actually
There. We will never get at what is directly and actually there by breaking matter down into
smaller and smaller parts, into parts composed of fewer relations, because all that does is create
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 691-696
Kaufman, S. E., Seeing the Universe from the Inside Looking Out
696
another etching of what is actually there, another smaller and less iterated replica pretending to
be what is actually there. Through these etchings we may learn something about the way in
which What Is Actually There is being in relation to Itself, we may identify some pattern or
patterns of Existential relation, but that is different than getting at What Is Actually There
directly, different than understanding the Nature of That which underlies the observation or
experience.
The other way to go about examining what is there is from the inside looking out. The difference
between looking at the universe from the outside looking in or from the inside looking out is like
the difference between looking at a tree from above or below, respectively. From above most of
the tree is obscured by the leaves, whereas from below one can see the relations between the
different parts of the tree, as the leaves do not obscure the view of the whole. From the inside
looking out the created etchings, i.e., mental and physical experiences, do not obscure the
underlying Actuality, because the etchings are seen in their proper context, as etchings, as
creations, and not as what is actually there, since, in order to see the world from the inside
looking out one is required in one way or another to adopt the perspective of Consciousness, or
whatever one wants to call that which apprehends experience, as what is actually there.
And all that is required to adopt the perspective of Consciousness as what is actually there is to
understand that what Exists most directly where you are, which is that which apprehends
experience, is what Exists directly everywhere else as well, regardless of what seems or appears
to be there.
Experience is ever-changing because the relations in which we are involved that create what we
experience as reality are ever-changing. Thus, experiences are different because the relations that
create them are different. But that which is involved in the relation, that which is actually being
in relation and creating and apprehending the different experiences, is not different from Itself,
i.e., its Nature is everywhere the same, although its perspective is everywhere unique.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
117
Article
Unity Principle:
Quantum Dipole & Subject-Object Relation (Part I)
Peter Kohut*
ABSTRACT
The reality seems to have disintegrated into many different and independent spheres, but we feel
intuitively that a great variety of existing forms should have a common basis. Deeper truth of our
existence might have evaded detection by the materialistic science. How can we come to the true
knowledge about our existence? A great desire of man is to find a true meaning of our life and
the essence of being. Many philosophers and scientists have expressed the Unity Principle by
saying “everything is connected to everything else”, but few have detected its essence. On the
base of dialectical logic, the Unity Principle is discovered which illustrate not only the exact
mechanism how the physical universe may work, but also the essence of consciousness and
subsequently personal God representing the whole self-aware and self-creating reality of the
highest complexity.
Part I of this series of articles includes: Introduction; Space and Time; Photon as Elementary
Quantum of Existence; Dialectical Relations “Whole-Part, Continuity-Discreteness”; Dialectics
of “One-Many”: Cosmic Expansion.
Key Words: truth, theoretical physics, mystery, crisis, unity principle, dialectical logic, quantum
dipole, God, consciousness, syntropy, evolution.
Introduction
Stephen Hawking said that we cannot ask if a model corresponds to reality, because we have no
independent test of what reality is and all we can ask is whether the predictions of the model are
confirmed by observation. It is a typical positivistic and post-positivistic attitude leading to the
wrong conclusion that the reality is unknowable and meaningless. But people searching for the
truth cannot accept such a post-positivistic ignorance and nihilism. We will disclose the real
meaning of reality and truth of our existence in detail as only the knowledge of truth can help to
save our endangered civilisation and guarantee the future successful development of science.
Can we know the truth and the nature of our Universe? Yes, we can. Already G.W.F. Hegel
showed in his rational philosophy that there are no hidden secrets or realities inaccessible by our
critical rational thinking. His philosophy was optimistic and his dialectical logic - very effective
and promising instrument. Hegel disclosed brilliantly that the world is rational and dialectical
and therefore accessible by our rational thinking and dialectical logic. It is possible to come to
the knowledge of truth if we apply critical thinking and logical reasoning as well as knowledge
*
Correspondence: Peter Kohut, Ph.D., Maly Saris 478, 080 01 Presov, Slovakia. Email: pekohut@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
118
from quantum mechanics which shows a quantum character and mutual interconnectedness of
reality.
It is very sad that dialectical logic, as the most effective instrument of search for correct answers
to ontological questions, had been diminished, thanks to philosophy of positivism, from the
scene already in the 19th century and replaced by formal logic. Consequently the development of
dialectical logic was abruptly stopped. Needless to say, formal logic is necessary for scientific
research, but insufficient with respect to ontological questions. Positivism with its pragmatism
and empiricism became a basis of scientific methodology. It has limited scientific research to
only what is accessible by our senses and instruments. Positivism replaced Hegelian dialectical
rationalism in which classical philosophy had achieved its apex. Positivism tried to create
scientific principles based on the rules of formal logic and experiment, where axiomatic
approach became a starting point.
However, the whole reality (universe) is dialectical, so it is accessible by our rational dialectical
thinking. Dialectical logic achieved a high level in Hegelian rational philosophy at the first half
of the 19-th century. The basic rules and categories of Hegelian logic were presented in his
publication “Science of Logic”. It is very sad that its future development was abruptly stopped.
Because of insufficient scientific knowledge in his period, Hegel could not develop a dialectical
logic to its final level and so detect the basic mechanism of reality - its Unity Principle, but
his deep insight into the dialectical nature of reality was very promising. He had made profound
analysis of such philosophical categories like the relations “something-other”, “unity of
opposites”, “one-many”, “whole-part”, “repulsion-attraction”, “continuity-discontinuity”,
“quantum-quantity-quality-measure”, “negation of negation”, “unity-diversity”, “finitudeinfinity”, “essence-phenomenon”, “subject-object”, etc.
If quantum physicists were familiar with Hegelian dialectical logic, they could solve all
interpretational problems and seeming mysteries of quantum physics as well as made the greatest
contribution to rational philosophy detecting the essence of existence. Certainly, quantum
mechanics represents a great achievement of theoretical physics in the 20-th century with many
practical and useful results, but it could also represent the greatest achievement of human mind,
if theorists knew dialectical logic and were not limited by philosophical positivism.
Truth = spiritual freedom and power = happiness = light = love = social, spiritual progress
People desire and wait impatiently for the true knowledge of our existence because
contemporary darkness is very frustrating.
Space and Time
Space remains a mystery so far. It is very strange, because simple but critical thinking and
reasoning is sufficient to disclose all mysteries of our existence. The Universe is rational and
knowable. We can apply correctly the rules of formal logic by our deductions, but we have a big
problem to think, contemplate, ruminate and study the things in their significant mutual relations.
Therefore my main aim now is to demonstrate the truth by many ways and from various
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
119
viewpoints, step by step, as simply as possible and so give a basic lesson of critical dialectical
thinking. Truth must appear with its beauty if attacked by correct logic.
Now philosophical and theoretical problems are not grasped at the fundamental level, but
replaced by inappropriate idealisations, illogical assumptions and consequent deductions
following from the rules of formal logic and mathematics. As assumptions and axioms represent
incorrect idealisations, the results must be also incorrect, even irrational and mysterious like the
Standard Model of particle physics, where elementary particles are interpreted mistakenly as
point-like entities. String theories have replaced these zero dimensional entities by one
dimensional strings vibrating through hypothetical eleven-dimensional space-time and this
nonsense is presented as a great achievement of human thinking. But they know neither why do
strings vibrate nor what are the basic structural constituents of space-time. Their realities are
hidden within Planck´s scales. If they knew that Plank´s scales just indicate that the whole reality
is quantized and structured and therefore consists of elementary quanta they would understand
there is no way to hide something there. The question is: what are the basic elementary quanta
of reality? How is the reality built of these elementary structural constituents?
Certainly, no physical entity can be zero-dimensional or one-dimensional, as no physical object
can exist without its spatial manifestation having zero volume. Such idealisations are
inappropriate at the quantum level. If we do not understand how space and time are quantized
and structured at the basic quantum level, we cannot explain their essence as well as the essence
of gravity and other interactions. Why do theorists, unknowing the essence of space, try to put
together Einstein´s theories with quantum mechanics? Einstein theory of gravity is local while
quantum mechanics is non-local, it means, non-locality is its basic feature confirmed by
experiments. Why don´t they try to find the essence of non-locality? Having found it they could
see the fundamental defectiveness of Einstein´s theory of gravity. Even, his theory denies the
existence of gravitational force replacing it by mathematical space-time curvature. The attempts
to unite Einstein´s gravity (general relativity) and quantum theory result in mysteries where
solutions are searched at the level of absent mysterious black holes.
Let us apply a simple logic by our reasoning regarding space. If we look at the reality (existence)
or the Universe as a whole, we can see that it is not a pure continuum, but it is structured. A pure
unstructured continuum is nothing. So the whole Universe as space is structured and, at the same
time, represents the unity in its internal structuration - diversity. As the Universe is structured, it
must be built of its basic structural constituents. That is the reason why the Universe is
quantized. But at the same time it represents the Unity. It means that its basic structural
constituents must be interconnected. But connections are also structural constituents of reality
(Universe). Does the Universe have many different basic building constituents or not? If we say
yes, we must explain – why, what are these different constituents and what is the reason of their
difference? If we say that only one basic elementary structural constituent is sufficient, we need
only to find it and explain its essence. As connections are also structural constituents, they
represent just what we are searching for. Connection is something that connects two aspects of
reality, it means, it connects “something (one side)” to the “other (other side)” and at the same
time, it is created of that both sides. In dialectical logic they are named opposites and their
mutual relation - the unity of opposites.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
120
Schematically it looks like:
Something (+)
(one side)
Other (-)
(other side)
Even if we start our consideration at the highest level of abstraction we can see that something
exists. But this something is nothing without its relation to the other. “Something” cannot relate
to itself (self-relation, self-reflection) without its relation to the “other”, otherwise it is nothing.
The other (-) represents the limit of something (+), through which it determines itself as a
difference. “Something” and its “other side” are not two independent entities but only two sides
(opposites) of the same “one”. It is irrelevant what side is “something” or “other” as both they
relate to each other in order to relate to themselves. The whole “one” is a self-relation (selfreflection) only because it is a mutual relation of its two opposite sides. Any of these two
opposites reflects itself into itself through its other side as through its own limit (mirror).
“Something” and “other” create a mutual positive and negative relationship, which cannot be
static, but only dynamic in the sense that “something” repels from itself its “other” side by
repulsion (negation), but at the same time holds and attracts it to itself by attraction (negation of
negation). Repulsion and attraction are two opposite forces through which both opposite sides of
the same “one” are in a mutual dynamic relation manifesting by motion – vibration, oscillation.
Motion is energy as a result of mutual attraction and repulsion of opposites. Thus we have a clear
definition of energy as a measure of mutual attraction and repulsion of opposites. This dynamic
bipolar relation (+/-) represents the elementary structural constituent of which the whole reality
(Universe) is made. We can name it an elementary quantum dipole or elementary quantum
connection. Known particles as well as space including vacuum are made of these quantum
dipoles. The Universe is physical - spatial and material (energetic). Matter is spatial and space is
material. The unity of the Universe means that all its aspects are made of the same constituents –
quantum connections (dipoles). Elementary quantum dipole (connections) is an elementary
quantum of space thereby the volume of space is given by the number of elementary quantum
connections.
The whole reality is spatial and represents a network of elementary quantum connections where
every something (+) is connected to all others (-) and reciprocally, which results naturally from
dialectic relations “whole-part” and “one-many” as will be shown later.
Something (+)
ISSN: 2153-8212
Other (-)
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
121
There is no space and no energy outside quantum connections (dipoles) as only they create the
whole reality. Quantum connections are not placed in space, but create it.
Contemporary theories separate matter from space, supposing space to be only an empty or
unstructured surrounding in which material objects (entities) move. Space and time in Einstein´s
relativity theories is a pure mathematical “space-time” continuum. Before, space was as an
empty continuum in which all material bodies moved. In Einstein´s special relativity it was
replaced by empty unstructured four-dimensional space-time continuum which was curved in
general relativity thanks to presence of matter and energy.
But this mathematical idealisation says nothing about the real quantum essence of space and
time. Einstein´s space-time is not structured and quantized. It is a pure mathematical continuum.
As Einstein´s theories have no idea about internal structuration and quantization of physical
reality (space and time), they cannot lead to the true knowledge. It is very strange and absurd
that theorists having not found how space and time are quantized try to unite Einstein´s local
theories with quantum non-local theory. It is like trying to put together water and fire. One
excludes the other. As a result string theories become the greatest accumulator of illogical
nonsenses ever.
Space is a basic attribute of every physical entity with its quantitative measure – volume. There
are no entities without spatial volume. Point-like particles or one-dimensional strings are
nonsenses inappropriate at the quantum level even as mathematical idealisations, because they
deform the reality fatally. Space is not only a basic feature of everything, but at the same time it
separates things from each other in the sense that it connects them together. Things can be
mutually separated only if they are mutually interconnected. The internal structure of any thing is
made of the same basic constituents as are connections through which things are interconnected.
All things and their mutual connections are made of the same constituents – elementary quantum
connections (dipoles). They are elementary quanta of space.
The Standard Model presents huge number of different point-like particles (fermions and bosons)
placed in the vacuum, which essence is unknown. How are point-like particles connected to the
vacuum? Vacuum is a mystery that can be arbitrarily used to solve all miracles of the Standard
Model. For example, it gives enormous energy for very massive virtual gauge bosons in order to
mediate a weak interaction in electroweak theory. All these virtual mysteries are undetectable
and hidden under the Plank scale. If we do not know the essence of the vacuum we can use it as a
magic wand to solve all our theoretical problems. We will show later that the vacuum is made of
long and weak quantum connections comparing to the short and strong connections of which
particles are made. So the vacuum cannot be a source of enormous energy needed for
nonsensical electroweak theory. In cosmological theories space is only a surrounding where
bodies move, while in particle physics it is a fluctuating vacuum with undetectable virtual
fluctuations.
As elementary quantum dipoles (connections) represent elementary quanta of space of which
every object is made and through which it is connected to the whole reality, it is impossible for
any object to become a singularity like a black hole. Black holes represent nonsense which, in
order to exist, must destroy the whole internal structure of previous star and change it into pure
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
122
singularity without any internal structure, but with infinite density. Black hole dreamers do not
see the force that can stop the gravitational collapse as they do not know elementary constituents
of which every object is made. As every elementary structural constituent represents an
elementary quantum of space, its space cannot be destroyed. Analysing the dialectical relations
“continuity-discontinuity and locality-non-locality” we will show that elementary quanta of
space act not only non-locally but also push locally each other by their spaces.
The stronger they are pressed together by gravity the bigger are their mutual repulsive pressures
that stop gravitational collapse so that the Schwarzschild radius cannot be attained [4]. Black
holes are mysterious not only form the viewpoint of space, but also time which, hidden under the
Schwarzschild sphere, represents an imaginary mathematical value (square root of a negative
number) having no real sense. The real physical meaning of time is to be a measure for speeds of
processes or motions measured through given standard cyclical processes like Earth rotation or
atomic oscillations. At the Schwarzschild sphere time must stop, it means all processes must stop
and freeze.
Can black hole theorists explain the physical meaning of imaginary time in relation to physical
processes or motions? Of course they cannot, so they say it is a mystery that we must accept as it
follows from their mathematical models where imaginary time flows perpendicularly to our
ordinary time. Thus, time in their models is not a real physical phenomenon but only pure
mathematical coordinate. Neither space nor time has real physical meaning, both they are only
mathematical symbols.
The question is - does the elementary motion exist as universal measure of all processes? We
will show later that the whole Universe transits from its one quantum state to the following by
elementary quantum jumps which define cosmic time for the whole Universe as a basic measure
to which all local physical processes can be related.
Photon as Elementary Quantum of Existence
It is very strange that even a photon as an elementary quantum of light represents a mystery
known as “wave-particle” dualism. Photon is a particle as well as a wave. How is it possible?
What is the solution? Photon as an elementary quantum of free energy is a direct to the essence
of whole reality. All we know that the motion of a classical harmonic spring oscillator creates a
sinusoidal wave as a result of two forces with opposite orientation - attraction and repulsion.
Sinusoidal wave is thus a consequence of both forces acting through harmonic oscillator. Photon
creates sinusoidal wave during its flight. It means it must be a quantum oscillator which
oscillations result from internal bipolarity of two opposite forces – attraction and repulsion.
Photon is a quintessence of dialectical bipolar nature of reality.
The greatest mistake of theoretical physics is the idea that elementary particles must be point-like
entities without any internal structure and with zero volume. Even a photon as the simplest
particle cannot be a point-like entity without internal structure. The photon is a simple quantum
dipole consisting of two opposites (opposite poles) and consequently a holder of elementary
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
123
quantum of space and energy. It is an elementary particle which, thanks to attraction and
repulsion of its opposites, oscillates creating perpetually the sinusoidal wave during its flight
which is manifested outside as an electromagnetic wave in relation to a measuring apparatus.
Photon γ (+/-) as elementary oscillating quantum dipole is the simplest particle:
attraction
repulsion
Photon as a quantum of radiation (light) is a free elementary quantum dipole +/- which, thanks to
mutual attraction and repulsions of its opposite poles, performs a permanent oscillation
(vibration, pulsation) manifesting outwards as an electromagnetic wave during a flight. This fact
is a consistent and factual explanation of the “wave-particle” duality of the light as only a bipolar
dynamic unity of opposites can result in oscillation (motion, energy) of a photon.
Photon = Free Oscillating Quantum Dipole (+/-)
+
wavelength
vertical height of
spatial wave
(length of dipole)
The photon is an elementary quantum oscillator. If we express its oscillation as rotation, its
length is given by a diameter of rotating quantum dipole. Rotation projected to the perpendicular
plane looks like oscillation. It is irrelevant if talking about rotation or oscillation (pulsation,
vibration), as these motions are manifested outwards in the same way. Photon is an elementary
quantum of energy. The essence of energy is also unknown for contemporary physics. Energy of
a photon as a measure of its motion (frequency of vibrations) can only result from mutual
attraction and repulsion of its opposites.
Planck´s equation ei hi
shows that energy of a photon is given by the speed of its vibrations (frequency). It is hardly
believable that the essence of photon´s vibrations has not been detected until now. It is due to
inappropriate idealisation of elementary particle as a point-like entity with its mysterious
“particle-wave” dualism resulting in impenetrable and undetectable virtual realities.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
124
Photon performs two types of motion: horizontal and vertical. Horizontal motion represents its
flight as a consequence of its dragging by cosmic expansion. Vertical motion is manifested by its
oscillation (rotation) thanks to mutual attraction and repulsion of its opposite poles. Photon does
not move “in” a free space-like vacuum, but thanks to its external quantum connections, it moves
“towards” all other parts of the Universe. Simplicity of a photon allows its perfect oscillation
(vibration) in a plane of its flight. As it is the simplest free quantum, it cannot resist its dragging
by an expanding Universe, so it has no rest mass and its speed expresses the speed of cosmic
expansion. Such is the nature of the speed of light as one of the basic physical constants
unknown until now [7].
Photon´s oscillations can be presented as rotations of a quantum dipole with a circumferential
velocity v:
v = 2ri ot di i
Tot – time of one rotation of a quantum dipole,
i - 1/Tot – frequency of quantum dipole oscillation,
ri - radius of dipole (half of its length),
di - length of dipole.
eidi = hv/
Later we will show from the viewpoint of dialectical logic that the value eidi is the same
(constant) for every quantum dipole (connection) and represents the basic cosmic law from
which other very important laws follow, e.g. Newton´s and Coulomb´s laws. It means the shorter
the quantum dipole, the higher its energy. The longer it is, the lower its energy. Energy of very
long quantum dipoles, connecting celestial bodies mutually and creating the cosmic vacuum, is
very small, but their quantity is enormous. The vacuum is a holder of energy of quantum
connections (dipoles) connecting physical objects mutually.
Photon represents an elementary quantum dipole. As everything is made of elementary quantum
dipoles (connections), we can say that everything is made of light (energy), which can exists in a
form of free flying photons, or be bound in a form of basic particles (protons and electrons) as
well as the vacuum.
The knowledge of the essence of Light is the way to understanding the essence of existence.
Jesus Christ as the Son of God declares: “I am the Light of the world” (John 8:12)
John evangelist defines the essence of Jesus Christ by the words:
”
The true light that gives light to everyone was coming into the world. He was in the world, and
though the world was made through him, the world did not recognize him. He came to that
which was his own, but his own did not receive him. Yet to all who did receive him, to those who
believed in his name, he gave the right to become children of God“
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
125
Christ is the Light (energy) which the world (Universe) is made of. Everything is made of
elementary quanta of energy – Light (photons = quantum dipoles).
Dialectical Relations “Whole-Part, Continuity-Discreteness”
Contemporary physics divides the whole reality into its parts mechanically unknowing how these
separated parts are interconnected mutually after their separation. Mechanical separation of parts
from the whole means the destruction of their mutual relations, so that these parts can come to
mutual interactions only through local touch contacts. Localism dominates in contemporary
theoretical physics, where mutual interactions between “point-like” particles are declared to be a
result of mutual exchange of virtual point-like bosons moving with a limited speed of light. It is
very strange that such a naïve mechanical interpretation of interactions between particles was
incorporated into the Standard Model although non-locality results directly from quantum
mechanics. This naïve understanding follows from Feynman´s interpretational failure in his QED
(quantum electrodynamics), where electromagnetic interaction is interpreted mistakenly as an
exchange of virtual photons between charged particles by a limited speed of light as shown:
virtual photon
(boson)
electron
(fermion)
proton
(fermion)
Electron and proton exchange a virtual photon creating their mutual electromagnetic interaction.
This naïve interpretation of electromagnetic interaction meets the following serious problems:
-
How do the electron and proton know where is their corresponding partner in order to
exchange a virtual photon if there is no direct mutual relation between them? How does the
moving virtual photon know where is the target fermion in order to mediate the interaction if
it does not carry any information about it? Do virtual photons only fly freely between
electrons and protons in empty space, accidentally collide with them and cause an
electromagnetic interaction? But if particles are point-like, how can they hit each other in a
huge free space? How does the virtual photon know what type of interaction to mediate –
attraction or repulsion?
Virtual photon can fulfil its mission only if:
-
it is aware of destination and motion of target particle, it means, it must contain the future
destination address and be capable to distinguish between target and non-target particles,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
126
or
-
charged particles sense each other directly before exchanging virtual photons.
This simple logical analysis leads to the only correct conclusion that the virtual photon is a direct
non-local connection between charged particles:
electron
(fermion)
photon
(boson)
proton
(fermion)
In above interpretation the photon represents a direct connection (relation) between the electron
and proton. It is not a virtual photon as an object of mutual exchange between particles, but a
real quantum connection (+/-) whose structure is the same as the structure of a free photon.
Einstein´s dogma of local action does not allow virtual photon to know where charged particles
(electrons, protons) are, but nevertheless, virtual point-like photons come to and go from a
concrete point (electron, proton) in order to transfer an electromagnetic interactions to all other
electrons and protons in the near and distant surroundings - even in the whole Universe.
Despite experimental evidence of non-locality theorists have a problem to accept it. As
electrostatic force is a long distance one, every charged particle has to exchange virtual photons
with an enormous number of protons and electrons in the Universe. It is remarkable that this
absurd picture is accepted instead of much more logical picture of direct non-local connections
(relations) between charged particles. It is because of Einstein´s refusal of non-local actions.
Non-locality as an instantaneous communication between distant particles is a fundamental
consequence of quantum physics known as entanglement or EPR non-locality. If theoretical
physics was not blocked by erroneous dogmas, it could detect that the vacuum is not empty
space between point-like particles, but made of non-local connections between them. All
particles and interactions are space-creating and space-carrying quantum connections.
Feynman represented virtual photons as only mathematical propagators of electromagnetic
interaction. As he wanted QED to be relativistic, he preferred virtual photons moving with a
limited speed instead of instantaneous connections. Electromagnetic force in QED is a
consequence of mathematical existence of virtual photons. Such an approach was also
transferred to other field theories like:
-
quantum theory of electroweak interaction as an attempt to unify electromagnetic and weak
interactions,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
-
127
quantum theory of strong interactions – quantum chromodynamics QCD,
quantum theory of gravity as an attempt to quantize a gravitational field.
In these theories, the virtual particles – bosons are carriers of force fields. But in reality there are
no virtual bosons as mediators of interactions, even they are undetectable. Except of a photon all
0
±
other bosons as real point-like particles (gluons, inter-medial bosons Z a W , Higgs boson,
gravitons) cannot be detected directly. We will show later the meaning of their indirect detection
by analysis of real structure and interactions of known particles.
At the basic quantum level the relation between the whole (Universe) and its parts can be only
dialectical, not mechanical. If some part is separated from the whole, it is separated from all parts
of the whole in the sense that this part remains connected to the whole, it means to all rest parts
of the whole. As connections are also parts of the whole so all parts must be networks of
connections. This is possible only if elementary parts are elementary quantum connections of
opposites (quantum dipoles (+/–)). The quantum dipole (+/–) so represents the elementary
structural unit of the Universe (space, matter, energy, information, consciousness). Every ”+”
pole is connected to all “–“ poles of the Universe and reciprocally. Everything is connected to
everything. Every separated part is connected to all other parts of the Universe.
The principle of universal connection of everything to everything creates the general Unity of the
physical Universe. This Unity Principle is a basic principle for the whole Universe following
from its dialectics. It discloses the exact mechanism of spatial structuration and quantization and
explains how the dialectical relation “continuity - discreteness” looks like.
Space can be continues and discrete (quantized) at the same time only if its elementary quanta
are elementary quantum connections (+/-). In that case elementary quanta of energy are localised
in elementary quantum dipoles and can be numbered (structuration, quantization), but at the
same time their represent elementary quantum connections (+/-) connecting everything to
everything, where every (+) is connected to all (-) and reciprocally. So the answer to the question
whether the reality is continuous or discrete is very simple – it is continuous and discrete at the
same time. Space consisting of elementary quantum connections is structured and quantized
creating the dynamic network of elementary quantum connections in which all its energy is
located. There is no space outside elementary quantum connections as just they create it.
Look at the scheme of a particle compound of three ‘+’ and three ‘-‘ poles with nine internal
connections (quantum dipoles) and indication of external connections:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
128
+
External vacuum
quantum connections
of the particle with the
whole Universe
+
+
+
The particle is made of nine
internal quantum connections
Any particle or physical object is defined by quantum dipoles creating its internal structure as
well as external quantum dipoles connecting the particle (object) to the whole Universe. Some
quantum physicists say that it looks like the elementary particle reaches the whole Universe.
They are really right, only they cannot say the reason - why?
External quantum connections of any object create its vacuum through which the object is
connected (entangled) to all other objects of the Universe. Every object (including our Earth)
drags its own vacuum during its motion. We distinguish the vacuum in atoms, molecules and
interstellar spaces. External vacuum quantum connections are much longer than inner
connections in objects. It depends on the point of view which of them are external and which are
internal. In an atom, internal quantum dipoles create particles (proton, neutron and electron) and
their mutual quantum connections create the atomic vacuum. In a molecule, internal quantum
dipoles create atoms and mutual quantum connections between atoms create the molecule
vacuum. Long quantum dipoles connecting celestial bodies create the cosmic vacuum. A
considerable part of cosmic energy is concentrated in these vacuum connections (cosmic
vacuum). It is the so-called “dark matter”. The vacuum as well as any other form of matter
consists of the same quantum dipoles, only their lengths define whether they are constituents of
material objects (particles, atoms, molecules, celestial bodies) or the vacuum.
Particles and physical objects do not move “in” a free space-like vacuum, but thanks to their
external direct connections, they move “towards” all other parts of the Universe. We do not need
any background to allow particles to move. All particles and interactions, as well as the vacuum
are created of elementary bipolar quantum connections. As everything is connected to everything
else, so every part moves towards all others thanks to their mutual connections. The vacuum
consists of elementary quantum connections between particles and physical objects. All
interpretational problems of quantum physics follow from its attempt to describe the motions of
point-like elementary particles “in” space represented by a coordinate system.
Nothing exists in space as everything creates space! Nothing moves in space as every part
moves towards all others thanks to their mutual quantum connections!
Your distance to some object is given by the length of elementary quantum dipoles connecting
your body to this object. These quantum dipoles create the vacuum as a mutual connection
between material bodies. You do not move in space, you move only in relation to all other parts
of the Universe thanks to your direct connections to them. You are connected to the whole
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
129
Universe at the elementary quantum level. There is nothing inaccessible as everything is
connected to you. Objects are separated through space only because they are interconnected
mutually through their vacuum non-local quantum connections (+/-) creating space.
Particle is not a point-like entity and cannot move in free space represented by a mathematical
coordinate system. Every elementary particle carries a certain quantum of space and moves only
in relation to all other parts of the Universe. Any particle can be studied only in its relation to
other objects, but not to a coordinate system. Heisenberg´s uncertainty principle is a consequence
of incorrect question - how to define a position of moving particle in space represented by a
coordinate system. Actually, elementary particles consist of elementary quantum dipoles as
holders and carriers of elementary quanta of space, whose energies are inversely proportional to
their lengths. They do not move in space but in relation to all other elementary quantum dipoles
thanks to their mutual quantum connections.
There is no uncertainty regarding elementary particles, as they have the exact internal structure,
motional state and relations to all other entities of the universe at every moment. Heisenberg´s
uncertainty principle results from inability of physicists to ask Nature correctly, how it works.
Nevertheless, this principle has very important consequences showing that reality is nonmechanical and non-local. The EPR paradox as well as quantum entanglement shows that two
particles creating one quantum system are mutually interconnected and act instantaneously to
each other at a distance. This “spooky” action at a distance indicates that except of local there are
also non-local interactions that contradict with Einstein´s locality principle.
But, because of Einstein, physicists are afraid of non-locality, so they prefer to accept
undetectable virtual bosons to carry the basic physical interactions by a limited speed of light
instead of acceptation of non-local quantum connections. It is very strange schizophrenia
following from attempts to put together two principally incompatible theories. We need no
virtual undetectable realities, but real non-local interactions. It is impossible to include nonlocalities into Einstein´s theories.
According to particle physics there are two types of elementary point-like particles:
- fermions as basic constituents of matter
- bosons as mediators of force interactions between fermions
According to the Standard model elementary particles are dimensionless point-like entities
without any internal structure. Such an understanding is very naive. Fermions dispose of many
properties (charge, mass, spin, ability to interact with other particles, different energies). Thanks
to them they differ from one another and possess various qualities manifested outwards. The
reason for this miscellaneous qualitative manifestation of these quasi-elementary particles is
hidden in their different internal structure that cannot be detected by contemporary particle
accelerators and colliders, but only by a deep logical insight. The essence of the vacuum is also
unknown. Force fields are supposed to be continuous but on the other hand they are transmitted
by point-like particles – virtual bosons. For example, electromagnetic field is transmitted by
virtual photons. Real photons mediate neither electrostatic nor magnetic interactions, so
mysterious and undetectable virtual photons are supposed to do it.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
130
Fields in contemporary theories indicates something monotonous, unlimited and continuous,
surrounding all bodies. The question is: do point-like particles-bosons create fields or do fields
create particles? What is the mechanism through which a point-like boson is detached from a
field? Theorists say that every boson is associated with its force field, but they cannot explain
how. How are force fields related to physical space? Do these fields create space or are they only
placed in space? Is space (vacuum) made of their different fields like electromagnetic, weak,
strong, Higgs and gravitational? How are they interconnected mutually? According to theorists
different fields arise as a consequence of spontaneous break of symmetry, but this explanation is
very vague and unclear. A statement that a point-like boson is associated with its field says
nothing neither about the essence of boson nor the field. If force fields are quantized in such a
way that bosons represent quanta of these fields, it means these fields must be made of point-like
bosons. But how point-like entities can create a field? Is this field only a set of points? How are
they interconnected mutually in order to create a field? “Field-particle” or “wave-particle”
complementary dualism is nothing more than sweeping the problem under the rug. The relation
between continuity and discontinuity is unknown. Everything is mystical and hidden in a jungle
of complicated mathematics.
The contradiction of particle physics is the declaration that although bosons (W+, Z, Higgs) are
point-like particles without any internal structure and zero volume, they decay in other particles.
In reality, if particles decay into some components, it only means that they must be composed of
them as well as of their mutual quantum connections. There are no elementary particles without
internal structure and with zero volume. All they are made of elementary quantum dipoles (+/-)
being carriers of elementary quanta of space.
The quark model, in which a principal impossibility to detect quarks and gluons is explained by
their so-called mysterious “asymptotic freedom”, is an example of absurdity, where one
nonsense produces another. It is hard to believable that such a hideous model is accepted in order
to explain the structure of some particles like proton, neutron and mesons, although it is well
known that particles colliding with their antiparticles can annihilate into pure photons. It means
they are made of photons and their mutual quantum connections. If physicists have disclosed the
essence of a photon as an elementary structural unit (quantum dipole), they could see the
structure of all particles as made of elementary quantum dipoles (photons).
Dialectics of “One-Many”: Cosmic Expansion
“One” is nothing without the other. “One” as a whole can create its relation to itself only if it
divides itself into many ones. “One” creates its relation to itself through its relations to others.
Through them it reflects itself into itself (self-reflection). “One” as a whole divides itself into
many ones in such a way that they create the unity of the “One” in the sense that every “one” is
connected to all other “ones”. Through many ones the whole
One is structured and quantized. Internal structuration means that the “One” repels from itself
many ones by repulsion and, at the same time, holds them in a unity thanks to attraction. As the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
131
whole “One” represents a bipolar relation “something (+) – other (-)”, its internal differentiation
means that it gradually repeals from itself both opposites, one after the other.
One as a whole comes from its unity to its diversity by internal structuration and at the same time
it again and again reflects itself into its unity and so performs its self-reflection. “Many” as
negation of “One” is overcome by its return to its unity – negation of negation. Negation of
negation is a self-reflection, meaning the One represents always the Unity which can exists only
in its internal structuration, where everything is reflected in everything else, everything is
connected to everything else and everything communicates with everything.
“One-Whole” represents the self-creating and self-reflecting Unity of the highest complexity
where everything is reflected in everything else. Self-reflection of self-closed system of high
complexity means the Life and Consciousness, therefore the Universe as a whole is a self-closed,
self-creating and self-reflecting system of the highest complexity and so represents
Consciousness of personal God. The essence of personal GOD as well as human soul is
explained in more detail by analysis of dialectical relation “subject-object”.
Looking at the Universe from its external objective side we do not see its internal subjective
united side, so we deny the existence of personal God. Not only the whole reality is “subjectobject” relation, but all we represent “subject-object” dialectics. We cannot search for the truth
limiting our attention to only one side of reality and neglecting the other one, as the external
objective side of the whole reality cannot exists without its internal subjective one.
Positivistic scientific paradigm is limited and accepts only a certain part of objective reality
mediated by local mechanical interactions, so it cannot lead to the true knowledge. It is high
time to leave this wrong paradigm and open the door to new one that, except of external
objective mechanical side of reality, takes into consideration also non-locality as well as its
internal subjective side. A new scientific paradigm must be based on dialectical logic of rational
thinking as well as deep spiritual insight into the unity (subjectivity) of existence. Of course, we
can study only a physical objective side at its various levels of hierarchy and limit our attention
to only separated aspects of reality. Even the Universe as a whole can be studied in cosmology as
a physical system per se, but in that case we must be aware that except of its external objective
side it possess also its internal subjective one.
Consciousness of personal God represents the whole reality where the physical Universe is His
external objective face.
The physical Universe as a whole divides and differentiates itself in such a way that every new
positive pole “+” is expelled from all existing negative poles “-“ and every new “-“ from all
existing “+“. It means that every positive pole “+” is connected to all negative ones “-“, and
reciprocally, every “-“ is connected to all “+” of the Universe, so that everything is connected to
everything else, creating the Unity Principle of existence. Internal differentiation of the Universe,
its plurality generation and structuration, means its cosmic expansion. The Universe is an
expanding network of quantum dipoles (connections).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
132
During cosmic expansion, the cosmic repulsive force is in its active stage, and the attractive
force, as a counterbalance, is in its passive stage and manifests itself as a global cosmic gravity.
Both these forces are equal but have mutually opposite orientation. When the repulsive force will
exhaust itself in its active stage, the cosmic expansion ends, and the attractive force starts the
cosmic contraction. Then the repulsive force passes to its passive stage, and as a reaction to
attractive one (being now in its active stage), manifests itself as a global cosmic antigravity.
During a cosmic contraction, the Universe gradually incorporates its quantum dipoles into itself,
until it becomes only a sole quantum dipole and starts again another stage of cosmic expansion.
As a sole quantum dipole (+/-), the Universe is in its initial quantum state. Cosmic transition to
the second state is accompanied by expelling and creation of a new pair “+/-” in such a way, that
every “+” is connected to all “-“. Thus, in the second state, we have four quantum connections
(+/-).
1. The first quantum state of the Universe:
+
-
2. The second quantum state of the Universe:
+
-
-
+
Creation of a new pair (+/-) means the transition of the Universe from one quantum state to the
following. In reality, the Universe expels firstly one pole and then the other opposite one, but in
order to simplify our analysis we consider only quantum transitions between symmetrical
quantum states, when two new poles are created (expelled). The Universe in its symmetric
quantum state k consists of k positive and k negative poles with k2 connections – elementary
quantum dipoles.
Space is created of elementary quantum connections and their number defines the volume
of space.
Every elementary quantum dipole (connection) represents an elementary quantum of space with
its basic quantitative characteristic - volume. As there is no reason for a difference, all
elementary quantum dipoles have the same elementary volume. Elementary quantum connection
(+/-) represents the basic elementary structural unit (building block) of space and its volume
etalon. Separate quantum dipoles nevertheless differ quantitatively from one another. Energy, as
a measure of intrinsic motion of their opposites, is a characteristic that allows their
distinguishing. Their differentiation in this characteristic needs other characteristic that as a
counterbalance returns this differentiation into the unity. This characteristic is the length di
which multiplied by energy ei gives the same value for every elementary quantum dipole i:
t = ei di ,
ISSN: 2153-8212
2
k
where
E = ei
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
133
i=1
The value ei.di represents the universal law which gives the energetic and length (geometric)
characteristics of the Universe into the mutual relation. The whole energy E of the Universe is
given by the sum of energies of its elementary quantum dipoles (+/-). The dialectical relation
between energy and length of quantum dipoles allows their quantitative and qualitative
differentiation as well as demonstration of their unity. On the contrary, the spatial volume of
elementary quantum dipole has no counterbalance in other characteristic. So all quantum dipoles
are indistinguishable in this quantitative characteristic and carry the same spatial volume, so that
the volume of space is given by the number of elementary quantum dipoles.
The dynamic network of quantum connections (dipoles) represents the unitary field that Einstein
was finding unsuccessfully in his theory of unified field. This network can be easily imaged by
the matrix in which lines represent positive poles, and columns – negative ones. Points of
intersections represent elementary quantum dipoles as connections of opposite poles. Cosmic
quantum transition (jump) from one symmetric quantum state to the next during a cosmic
expansion can be described by addition of a new line and column (k+1). New points of
intersections represent new quantum dipoles created during an elementary quantum cosmic
transition (jump):
The table of increasing cosmic network of quantum dipoles during cosmic expansion
Quantum state
1
2
Poles
+
+
k-1
k
k+1
+
+
+
n
+
1
-
+/-
2
-
+/-
..............
+/-
k-1
-
+/-
k
-
+/-
k+1
+/+/-
.............
n
-
+/+/+/+/-
All newly created quantum dipoles (+/-) are weaker and longer than existing ones. They are
under the direct control of divine creative activity. The internal structuration of the Universe
resulting in its cosmic expansion can be easily described by the following basic quantum
equation:
V k = k2
where:
Vk - volume of cosmic space given by the number of quantum dipoles,
k – number of positive (or negative) poles as well as the number of elementary quantum
jumps of the Universe from the beginning of its expansion and representing the cosmic
time
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
134
This basic quantum equation reflects the internal division and structuration of the Universe
creating thus its own expanding space and flowing time. The Universe is quantized as its energy
and space are localised in its elementary quantum connections and its time is given by its
elementary quantum jumps from one quantum state to the following. Elementary quantum jump
represents the elementary change of the Universe, its elementary quantum of motion (time) to
which all other changes (motions, times) can be related. These elementary quantum jumps define
the universal cosmic time. Time is not a mystery, but manifestation of motion of the Universe as
a whole as well as motion of its parts. Time is a measure of motion, it is nothing without motion.
Imaginary time in black hole theories has no real physical meaning, so it is pure nonsense as well
as black holes.
Every local motion can be compared to the universal cosmic motion. As shown in my paper [8],
contemporary one second corresponds to (3/4)/(c52h)1/2 = 8,144.1043 elementary quantum
jumps of the Universe between two symmetrical quantum states, so we can allocate the time t =
(4/3)(2hc5) 1/2 = 1,128.10-44 s to one quantum jump. But it does not mean that the quantum
jump has its duration. Time does not define the duration of elementary quantum jump, but just
contrariwise, time is defined by the number of elementary quantum cosmic jumps. Every process
(motion) and its duration can be compared to and expressed by universal time. If some process
takes one second, it means that it corresponds to 8,144.1043 elementary quantum jumps of the
Universe. If the same process is dilated to two seconds (time dilation) because of high speed of
object towards the vacuum or strong gravity (big gravitational potential), it corresponds to
2x8,144.1043 elementary quantum jumps of the Universe. This cosmic time so represents a
universal base through which all processes (motions, times) can be expressed.
Time is quantized and can be numbered and expressed by integers. It is nonsense to say that
something can be hidden under the Planck time. Nothing can be hidden under the Plank scale
neither in the sense of time, nor volume, because the Universe is quantized in both its
characteristics – space and time. Both they have clear physical meaning. The question, what had
happened from the moment of the Big Bang until Planck´s time, has no sense. There is no
mystery as the Universe did not start its expansion from its undifferentiated singularity but just
from its initial state as a sole quantum dipole (+/-). The Universe has the source of its motion
(energy) in mutual attraction and repulsion of its opposites. Contemporary cosmological theories
do not see the dialectical essence of existence, so they cannot explain the origin of cosmic
expansion – Big Bang, and the way out of singularity.
Singularity as undifferentiated totality is nothing. Anything cannot appear from nothing.
Singularity does not have its own source for plurality generation. It is only “one” and nothing
more. Quantum cosmological theories suggest the fluctuation of a previous vacuum as a source
of cosmic expansion and mention some fluctuation of energy density. But the source of energy is
unknown. The so-called false vacuum should contain a contradiction between the huge
gravitational effect of its energy and repulsive effect of its pressure, but the intrinsic bipolarity as
a reason is not detected. Neither the source of energy nor essence of cosmic expansion and
gravity is explained. Therefore the reason for spontaneous super-symmetry breaking remains
unknown. Such vague notions like accident, uncertainty, spontaneity and fluctuation cannot
explanation the real source of cosmic expansion.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| February 2014 | Volume 5 | Issue 2 | pp. 117-135
Kohut, P., Unity Principle: Quantum Dipole & Subject-Object Relation (Part I)
135
If we allocate t sec to one quantum jump, then the time of cosmic expansion is:
t = k.t
and the basic space-time equation of the Universe where the volume V is expressed by m3 ,
obtains the following form:
V = z.t2, where z = (d2V/dt2)/2
This is the basic equation of spatial dynamics of the Universe, expressed in real
dimensional units, in accordance with which the spatial volume of the Universe is directly
proportional to the square of time of cosmic expansion.
In that form space and time are continuous values, but we must remember, they are quantized in
reality and can be truly expressed only by integers. Thus, if we want to study space and time
from the viewpoint of cosmology, we can use them as continuous values, but it is inappropriate
at the quantum level. The detail analysis of the basic quantum equation with its interesting and
important consequences for cosmology is made in my papers [7], [8] and partially in the
Appendix of this paper.
Above equation shows only how three-dimensional space of the physical Universe is evolving in
time, but says nothing about how a divine Idea (Mind) is implemented into the physical structure
of the Universe. The newest quantum dipoles, being longest end weakest at the same time,
represent the threads through which God manipulates, managing the evolution of expanding
Universe. As this action is now, in contemporary phase of cosmic expansion, very gentle, it
seems it does not exist. The evolving physical Universe is managed according to divine Idea
(Word) and subsequently reflected in a divine Mind. At every consecutive cosmic quantum jump
the divine Idea (intention) determines where, meaning to what distance from every existing
quantum pole, a new opposite pole is to be expelled. The enormous number of possibilities for
conscious decisions at every stage creates unbelievably reach field for a free will. Every
conscious subject has a free will to decide what reality he will reflect and create in his
imaginations and how he will interact with the world.
(Continued on Part II; List of References at end of Part II)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
583
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 583-585
Kaufman, S. E., The One Light that Shines through All the Drops
Realization
The One Light that Shines through All the Drops
Steven E. Kaufman*
ABSTRACT
Know yourself not as just one of the many drops that rests on the leaves after a rain. Know your
Self instead as the One Light, the Light of Consciousness, that shines through all the drops, and
there will then be no mistake in Identity, since the Light cannot seem to possess That which It
already Knows Itself to Be.
Key Words: One Light, shine, Consciousness.
Know yourself not
As just one of the many drops
That rests on the leaves
After a rain.
Know yourself instead
As the One Light
That shines through all the drops.
When you know yourself as just a drop,
And the Light shines through,
Then you think, "the light is mine!"
But when you Know yourself as the Light,
And the Light shines through,
Then you Know, "I am the Light."
When you think, "the light is mine,"
It then seems that the Light is something
That the drop possesses.
And so then,
What is not really what you are
Seems to possess
What you really are.
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
584
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 583-585
Kaufman, S. E., The One Light that Shines through All the Drops
So it is that,
The form you think you are
Seems to possess
The Consciousness you really Are.
The drop-self,
Because it is not really what you are,
Always feels that something is missing,
Always senses that it is incomplete,
But never looks for what is missing,
In what it already seems to possess.
For how can Consciousness
Be what is missing,
When it is already possessed
By the drop-self?
And so it is that
What we truly Are
Becomes hidden,
And so seems to be missing,
While remaining always
In plain sight.
And so it is that
What we truly Are
Is not actually missing,
But has just been misidentified,
And so appears
As something other
Than what we are.
It is as if we are children
And our mother stands right before us,
But we mistake her for someone else,
And so we run around crying,
"Where is my mother?"
But we do not cry
"Where is my mother?"
For it is not our mother
That is missing.
Rather, it is our true Self
That seems to have gone missing.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
585
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 583-585
Kaufman, S. E., The One Light that Shines through All the Drops
And so we cry,
Who am I?
What am I?
Where am I?
And the answer is always the same,
Once we are able to hear it.
I am right here
Where I have always been.
I never went anywhere,
I just got mistaken for something else,
for something other than I,
Once it seemed that I was possessed by an i,
By a form,
That I was not,
That I am not.
So know yourself not
As just one of the many drops
That rests on the leaves
After a rain.
Know your Self instead
As the One Light,
The Light of Consciousness,
That shines through all the drops,
And there will then be
No mistake in Identity,
Since the Light cannot seem to possess
That which It already Knows
Itself to Be.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
1
Consciousness beyond neural fields: expanding the possibilities of what has not yet happened
Birgitta Dresp-Langley
Centre National de la Recherche Scientifique UMR 7357 CNRS, Strasbourg University, Strasbourg
Cedex, France
Cite as : Dresp-Langley B (2022). Consciousness Beyond Neural Fields: Expanding the
Possibilities of What Has Not Yet Happened. Frontiers in Psychology. 12:762349.
2
Abstract
In the field theories in physics, any particular region of the presumed space-time continuum and
all interactions between elementary objects therein can be objectively measured and/or
accounted for mathematically. Since this does not apply to any of the field theories, or any
other neural theory, of consciousness, their explanatory power is limited. As discussed in detail
herein, the matter is complicated further by the facts than any scientifically operational
definition of consciousness is inevitably partial, and that the phenomenon has no spatial
dimensionality. Under the light of insights from research on meditation and expanded
consciousness, chronic pain syndrome, healthy ageing, and eudaimonic well-being, we may
conceive consciousness as a source of potential energy that has no clearly defined spatial
dimensionality, but can produce significant changes in others and in the world, observable in
terms of changes in time. It is argued that consciousness may have evolved to enable the human
species to generate such changes in order to cope with unprecedented and/or unpredictable
adversity. Such coping could, ultimately, include the conscious planning of our own extinction
when survival on the planet is no longer an acceptable option.
3
Introduction
In field theories of consciousness (e.g. Köhler, 1940; Cacha and Poznanski, 2014 among
others), the latter is conceived in terms of a field in the sense in which it is used in quantum or
particle physics, where the notion of ‘field’ applies to all fundamental forces and relationships
between elementary particles within a unifying theoretical framework where the forces lead to
energy fields that occupy space-time and mediate interactions between elementary particles. In
field theories of consciousness the latter is, similarly, seen as having duration and extension in
space. In field theories in physics, however, each point of a particular region of the presumed
space-time continuum, as well as all interactions between elementary objects, are objectively
measurable and accounted for mathematically. This cannot be claimed by any current theory of
consciousness, including the field theories (e.g. Köhler, 1940; Lashley, Chow, and Semmes,
1951; John, 2002; McFadden, 2002; Fingelkurts and Fingelkurts, 2002; Cacha and Poznanski,
2014). These will not be reviewed in detail again here, as an excellent review has been provided
earlier by Pockett (2013) earlier. Reasons why Libet’s Mind Field Theory of consciousness,
carved out in his book Mind Time (2004), may be discussed outside rather than within the realm
of the other field theories are clarified herein. Neural field theories of consciousness, whether
they relate to representational fields, where Gestalten or qualia are seen as reflecting the very
nature of consciousness, occupying a presumed spatio-temporal brain field generating electrical
brain states (Köhler, 1940), or to the functionally specific spatio-temporal structure of an
electromagnetic field in the brain (Lashley et al., 1951, McFadden, 2002; John, 2002; Fingelkurts
and Fingelkurts, 2002), all account for specific aspects of brain-behavior function while humans
are in a conscious or non-conscious state. Yet, consciousness is a far more complex product of
brain evolution, both at the phylogenic (Cabanac, Cabanac, and Parent, 2009) and at the
ontogenetic (Jaynes, 1990; Feinberg and Mallatt, 2013) scales, that reaches well beyond brainbehavior function (e.g. Pockett, 2000). Since the theory of evolution, the problem of the origin
of mind or, more specifically, the origin of consciousness has been posed. Where and how in
evolution has it begun to emerge, and how can it be measured. How can we derive mindfulness
out of mere biophysical matter? If we want to define consciousness adequately, it would need
to be in terms of the capability of the human Self to know and analyze its own condition and
existence in space and time, and to project this knowledge into a future that has not yet
happened. Why it may not be possible to render the whole complexity of the phenomenon of
consciousness scientifically operational is discussed further in the following chapters.
Ontological links between mind, time, and the Self as a window to understanding a specific
aspect of human consciousness, the ability to project one’s own existence into the future, are
brought forward. Finally, the question whether we need neural field theories of consciousness
as an explanation of the latter at all is justified under the light of clear argumentation. It is
4
concluded that investigating functional links between eudaimonic well-being and consciousness
could give us answers more important to the future of humankind.
1. Limitations to a scientifically operational definition of consciousness
None of the field theories of consciousness has succeeded in providing a definition that
would be both scientifically operational and, at the same time, capture the complex nature of
this phenomenon. This was already pointed out some time ago by Block (2007) as a clear
limitation to not only field theories, but any theory of consciousness. He argued for an “abstract
solution” to the “problem of consciousness” given that phenomenal consciousness by far
exceeds perception, cognitive accessibility and performance, or any of their directly measurable
brain correlates. What others have referred to as the “hard problem of consciousness” (e.g.
Chalmers, 1996; Searle, 1998) relates to the difficulty of finding brain measures of a highly
complex phenomenon, the conscious Self, experienced in terms of I do, I think, I feel, I was, am,
and will be, independently of any particular conscious perception, memory, decision, or action
(behavior). If a representational or neural field of consciousness occupying a presumed spacetime continuum inside the brain, or outside the brain, as suggested by Sheldrake (2013) and
others, exists, it would have to be independent of the neural activities underlying any particular
perceptual or cognitive process operating at the same time. While a specific conscious
perception or conscious memory recall, can be measurably correlated with specific brain
activities (e.g. Nani et al., 2019), interpreted adequately as the neural correlates of the
particular conscious behavior being measured, it is not a neural correlate of consciousness. The
contents of phenomenal experience are associated with neural activities in multiple networks
(Rees, Kreiman, and Koch, 2002) of the temporal-parietal-occipital brain areas, but this does not
account for how and why, or through which mechanisms, our brain has evolved consciousness,
while most other mammal brains have not, or at least not to the same extent. To get around
this problem, the concept of a “conscious brain state”, with an abstract and scientifically
operational definition of consciousness in terms of a “continuous process with limited
duration” was introduced (Tononi and Edelman, 1998, and subsequently within a larger
theoretical framework of consciousness, Edelman, 2003) based on a definition proposed earlier
(von der Malsburg, 1997). Such a parsimonious definition of consciousness may allow looking
for invariant properties of a brain state during conscious wakefulness and its equivalents.
LaBerge et al. (1986; 1990) argued that states of lucid dreaming, for example, are equivalent to
wakeful conscious states. The invariant properties of what John called “the conscious ground
state”, which in his theory corresponds to a specific EEG wave pattern that is observed when
patients recover from deep anaesthesia, could then be told apart from the subjective
phenomenal contents of any particular conscious experience as reflected in a particular overt
5
behavior. In other words, the conscious brain state would have universal properties that can be
consistently identified and measured whether we are consciously daydreaming (Singer, 1975;
Carver and Humphries, 1981), engaged in abstract analytic thinking (Gilead et al., 2014), in a
state of lucid dreaming (LaBerge, 1990), or whether we consciously perceive and remember
objects, as in conscious three-dimensional perception and selective memory recall (Nani et al.,
2019). Invariant or universal properties of a generic conscious brain state were, however, never
found elsewhere than in brain patterns measured after recovery from deep anaesthesia (John,
2002), which is, yet again, only a particular conscious state to which consciousness is not
reducible. Fifteen years ago, the nuclear physicist Jean Durup and myself (Dresp-Langley and
Durup, 2006) suggested a biophysical brain code independent of particular cognitive processes
operating while we are conscious (perception, spatial awareness, conscious motor planning and
execution etc.), but providing a generic neural mechanism that would trigger, maintain, and
terminate an individual conscious state in similar ways in which electronic bar codes may
activate, maintain, and disable the electronic locks of a safe. The functional assumptions
underlying this somewhat wild concept were inspired by earlier work on an arbitrary, and
possibly genetically prewired, selection of dedicated neural circuitry for consciousness (Helekar,
1999), temporal coincidence coding in the brain (e.g. Ainsworth et al., 2012), and adaptive
resonance theory (Grossberg, 1999; 2000). Our idea then was to carve out a computational
hypothesis for conscious in terms of a purely temporal (time bin) resonance of memory signals
in long-range neural circuits well beyond functionally identified sensory areas. Such circuitry
would first be arbitrarily selected and short-term potentiated by Hebbian synaptic learning,
then subsequently consolidated during ontogenesis, long-term potentiated and dedicated to
the generation of temporal signatures (firing patterns) of conscious states. Since consciousness
is fully operational in the absence of spatially defined stimulus input from the outside world
(when we have our eyes closed and daydream, for example, or in lucid dreaming), we daringly
proposed that the temporal signatures of consciousness generated in dedicated neural circuits
could become progressively de-correlated from spatial signals during ontogenesis. This
hypothesis negates the concept of a spatially defined activity field within the brain as a potential
correlate of consciousness, and it makes sense under the light of the fact that the phenomenon
itself has no measurable spatial dimensionality. Brain activity patterns are representations, as
adequately and parsimoniously defined earlier by Churchland (2002), in terms of patterns of
activity across groups of neurons which carry information. Interpretations of such patterns in
terms of functionally specific correlates (correlate=co-occurring with) of consciousness under
specific conditions of testing (for a recent review, see for example, Koch, Massimini, Boly, and
Tononi, 2016) all carefully avoid the term causality, as correlation does not necessarily imply
causality. Thus, when it comes to an explanation of consciousness, we are still found wanting,
consistently faced with the same old problem, over and over again. It has up to now not been
possible to confirm that specific brain activity patterns, or synchronization thereof, recorded
6
during a specific conscious experience, explains consciousness, or even leads to an
understanding of the phenomenon. This is so, because we do not know beyond reasonable
doubt whether the brain activity patterns demonstrated in any of the relevant studies in the
field are neural signatures of consciousness, or nothing more (or less) than the traces of
different levels of integrated brain activity (see also the review by Pockett, 2013), representing
ongoing sensations, memories, or mental images during conscious experience.
2. Absence of a spatial dimensionality of consciousness
Consciousness has no observable spatial dimensionality (e.g. Libet 2004; Buzsáki, 2007;
Marchetti, 2014). It corresponds to a specific state of being in time independent of spatial
location. It is a phenomenon that can be observed and accounted for scientifically across
changes with time in ontogenetic development. The ability of human beings to both consciously
relive past events and conceive future events entails an active process of construction of
consciousness in time that underpins many other important aspects of conscious human life.
During early childhood, the brain learns about the temporal order of the physical world, well
before we become phenomenally conscious of a Self and its immediate or distant environments
(Piaget, 1967). The temporal rhythms or order of stimuli is the first way through which humans
acquire knowledge of physical reality, structure, and continuity, as illustrated by results from
experiments where the responses of newborns exposed to speech stream inputs have been
systematically quantified (Bulf, Johnson, and Valenza, 2011). Human awareness of temporality
and the projection of the Self and its most abstract concepts and reasoning towards a future
that has not yet happened occurred relatively late in evolution as a mental capacity allowing to
push the technological and cultural development of our species further and further. It develops
ontogenetically over the first years of an individual lifespan (Piaget, 1967; Jaynes, 1990;
Edelman, 1993). The idea of ontological identity link between consciousness and awareness of
temporality harks back to Hume (1740), Hegel (1807) and to Heidegger’s (1927) concepts of Sein
(Being) and Zeit (Time), where consciousness is hardly more than a succession of psychological
moments where we realize that we exist in, and are part of, moments in time. This places all
other perceptual or sensorial processes which may characterize any particular phenomenal
experience at a different level of analysis. The idea of a fundamental identity link between
awareness of Self (das Ich) and awareness of what Heidegger termed Ursprüngliche Zeit (original
time) implies that human consciousness may have progressively evolved from the primitive
ability to be aware of, to remember, and to predict temporal order and change in nature found
in other species such as rodents (e.g. Fouquet, Tobin, and Rondi-Reig, 2010). The limits of this
capacity are directly determined by brain capacity and extent of interaction between the brain
and the world. The activity of individual neurons in the brain only has a small quantifiable
relationship to sensory representations and motor outputs. The most recent evidence
7
(Ainsworth et al., 2019) confirms that coactivation of a few 10s to 100s of neurons can code
sensory inputs and behavioral task performance within clear psychophysical limits. However, in
a sea of sensory inputs with memory representations linked to complex motor output, the
temporal activity of neurons has to be functionally organized independent of spatial codes
relative to sensory data and representations. In the brain, this could be made possible either
through spike rates (rate coding), or the selective reinforcement of spike coincidences active
neurons and networks (temporal coding). Both have computational advantages and are not
mutually exclusive. There is recent evidence (Ainsworth et al., 2019) for a bias in neuronal
circuits toward temporal coding. Just as the temporal signal sequence or activity pattern of any
single coding cell is determined by its firing activity across a certain length of time, the temporal
signature of a conscious state is also linked to duration, with variations in the limited dynamic
range of a few hundreds of milliseconds. Most perceptual and cognitive contents are processed
implicitly by the brain (i.e. non-consciously) and truly conscious states seem to be reflected by
short oscillatory activity periods of not more than a few hundreds of milliseconds each (e.g.
Buzsáki, 2007, Del Cul et al., 2009, Nybegrg et al., 2010). The clockworks of consciousness have
thus been conceived in terms of rapid temporal successions of microscopic brain states
Edelman, 2003). Spike time-based models of processing relating to such have been suggested
(e.g. Singer, 2000; Thorpe, Delorme, and van Rullen, 2001). The temporal characteristics of
resonant brain networks, under the hypothesis of a functional separation from spatial
mechanisms, can explain the temporal stability of representations as defined by Churchland
(2002; see here above) despite the highly plastic and diffuse functional anatomy of the brain
(Wall, Xu, and Wang, 2002). Such stability is ensured by the dynamics of bottom-up patterns
triggering neocortical excitatory activity and matched in time with top-down memory
representations or expectation signals (Grossberg, 1999; Dresp-Langley and Durup, 2009; Cacha
and Poznanski, 2014). The temporal dynamics of these brain activity patterns are driven by
environmental pressure (relevance) towards functional interaction (e.g. Grossberg, 1999; Hari,
2017). Consciousness can also be understood in terms of changes that have occurred in time
during phylogenesis. All vertebrates appear to be phenomenally and affectively conscious,
function according to circadian cycles, and experience various states of being with dynamic
transitions between different states of consciousness (Birch and Schnell, 2020). In humans,
however, the variety of higher-order states of consciousness described in the literature is not
only larger (Fabbro et al., 2015), but also qualitatively different. So-called primary consciousness
related to representations coding for perception, affect, and action (Edelman, 2002) are likely to
be shared by all mammals, while higher-order consciousness linked to the interpretation of
contents of primary consciousness, self-related awareness of past and future, and symbolic
activities relating to language (Kotchoubey, 2018) is what makes humans unique. There is no
doubt that conscious ability results from neural network development and processing resources
within the physical boundaries of a brain. However, human consciousness transcends these
8
underlying brain mechanisms. By changing and developing with experience, in interaction with
other beings, society, and the physical world, it creates potential for mobilizing new resources
beyond currently existing or known physical boundaries.
3. Consciousness transcends brain, space, and time
The capability of consciously shaping our lives within the world and of projecting them
into a distant future, imagined but not yet real, is a critical aspect of fully evolved human
consciousness, and drives human creativity and the technological and cultural development of
human societies (e.g. Fabbro et al., 2015). As pointed out earlier (Logan, 2007), when humans
started living in complex communities where cooperation was a key to survival, through the
maintenance of the camp fire among other things, consciousness may have emerged from a
new complexity of human interaction. Consciousness may thus be seen as a specific form of
energy, with a creative potential that can lead to directly observable changes, in other beings
and in physical environments. Consciousness thereby has, or can have, the power to determine
and/or change future non-physical (mental) states, in the Self and in others, and/or future
physical states in the outside world. To clarify how we may link this form of energy to the brain
on the one hand, and to human society and the physical world on the other, we may consider
the following general definition:
“Energy is the capacity for doing work. It may exist in potential, kinetic, thermal,
electrical, chemical, nuclear, or other forms” (Encyclopedia Britannica, 2021)
The origin of conscious energy is definitely the brain, its form potential, and the work it does
when operational is the work of producing change, in the Self, in other people, and in the world.
Consciousness is thereby defined as the energy source of all change and creativity. The latter
can be as diverse as the things we may observe, in ourselves, in others, and in the world.
Consciousness enabled human creativity breaks currently known mental and physical barriers
every day in art and science, finding new solutions to problems that previously appeared
insurmountable. Phenomena such as consciously guided brain-to-brain communication (Grau et
al, 2014) are now being investigated in respectable research laboratories. New particles that do
not seem to obey conventional laws of physics have been discovered (Bazavov et al, 2014). Yet,
our knowledge about the processes underlying this individual and collective power of
consciousness is still very limited. Physical theory entails that the functioning of organisms or
environments (living systems) is continuously challenged by the laws of thermodynamics in its
attempt to maintain energy. Living organisms interact with each other and their environments
in a continuously evolving process aimed at precisely that goal. With the evolution of the
9
species, such interactions become increasingly sophisticated and effective. It is possible that
consciousness, well beyond mere biological adaptive function (e.g. Jordan and Ghin, 2006;
Kotchoubey, 2018) has evolved for the purpose of extending human capacity to, not only
maintain, but create new energy. Interactionism thus becomes a key to understanding
consciousness in terms of a product of the “transcendental human brain” (Cacha and Poznanski,
2014) or, in other words, a specific kind of temporally defined energy that results from
interaction with space, but is not spatially defined or limited. As pointed out elsewhere
(Pepperell, 2018), if we want to explain consciousness as a physical process we must
acknowledge that, as in all physical processes, energetic activity is fundamental also to the
processes that drive evolution and have produced consciousness. The nature of energy itself can
take many different forms in physics. In the case of brain function, energy may be conceived in
terms of the forces that produce specific electric activity dynamics (observable as brain waves)
while we are conscious. By observing physical systems, we can understand how energy
produces temporal change in systemic states on the basis of the observed differences between
these systemic states. Consciousness as a transcendental form of energy, produced in the brain
but not limited to the latter, produces temporal change in states of the Self, as suggested by
current insights from studies on deep meditation. Meditative practice detunes the brain
processes of self-awareness and blocks the instantiation of self-referential conscious states
(Nair et al., 2017; Keppler, 2018). This leads to what has been called the “dissolution of the
ego”, which is not to be confounded with dissolution of consciousness (Keppler, 2018). Instead,
deep meditative states tap into a wider spectrum of functional brain modes, opening the gates
to extended phenomenal experience and expanded consciousness. The subject/object
relationship, or relationship of the Self to its immediate environment during such a
transcendental experience (Nair et al., 2017) is characterized by absence of a conscious
perception of time passing, space, or body sense, in other words anything that would give
meaning to conscious waking experience. Transcendental consciousness is described as full selfawareness isolated from the processes and objects of experience but characterized by the
absence of sense of time, space, the physical body or the contents of perception that define
waking experiences (Vieten et al., 2018; Paoletti and Ben-Soussan, 2020). The integration of
transcendental experience with waking, dreaming, and sleeping has been labeled by distinct
subjective and objective markers. It is subjectively marked by full self-awareness during waking,
sleeping, or dreaming, greater emotional stability, decreased anxiety during challenging tasks
and, physiologically, by the coexistence of specific brain wave patterns (Travis, 2014).
Transcendental experience may be an engine that fuels human development and creates
potential for the evolution of higher forms of human “intelligence”, to be understood here in
terms of mental capability. Insights from the neuroscience of meditation and its effects on
human well-being and the development of higher forms of consciousness (Muehsam et al.,
2017; Mahone et al., 2018; Vieten et al., 2018; Brandmeyer, Delorme, and Wahbeh, 2019; Vivot
10
et al., 2020) points towards states of enhanced consciousness in deep meditation as a crucial
driver of human psychological development. Deep meditation also has proven therapeutic
effects, as in chronic pain management (Hilton, Hempel, and Ewing, 2017) in individuals where
consciousness is often reduced to little else than overwhelming sensations of pain, limiting the
full, health expression of conscious capability in their everyday lives. One of the most
controversial issues in vegetative state or a minimally conscious state syndromes concerns the
potential capacity of such patients to continue to experience pain in the absence of any
measurable self- or environmental awareness. Some of such patients might continue to
experience elementary emotions or feelings, as suggested by results from neuroimaging studies
showing activation of specific cerebral areas in response to situations which commonly generate
empathy (Pistoia et al., 2013). In short, there are still more questions to be answered in
consciousness research, well beyond what we call biological adaptation in the Darwinian
tradition. For example, the intimate link between transcendental states of mind and a
phenomenon called eudaimonia needs to be unraveled in well-targeted research across the
human lifespan. This novel, largely uncharted terrain of scientific investigation into human
consciousness may provide deeper insights into its function far more important to our species
than biophysical explanations in terms of neural correlates, or biophysical fields. As pointed out
by Churchland (2005), we have to, ultimately, ask ourselves what we want from a science of
consciousness.
4. Eudaimonic well-being as a window to the purpose of consciousness
Eudaimonia is a central concept in the Aristotelian philosophy of ethics. It is related to
other concepts such as virtue, human excellence, and phronesis, which is an ethically grounded
form of wisdom (cf. Walsh, 2015). The viewpoint on consciousness delivered here suggests
potential for generating creative change, in non-physical (mental) states of the Self , of others,
or in physical states as a neglected possibility for scientific investigation. The newly emerging
field of research on eudamonic development (e.g. Rosenfeld, 2019; Alexander et al., 2021) can
be linked to the clinical neuroscience of expanded consciousness (Paulson et al., 2017; Vieten et
al., 2018; Vivot et al. , 2020) to generate new insights on how we can foster acceptance of what
cannot be changed, in ourselves and in others. It could help us understand how expanding our
consciousness can help us adjust our individual expectations, and find purpose and fulfillment
despite adversity. A deeper understanding of consciousness in terms of practice (mindfulness,
deep meditation) could help us understand the intuitive processes that enable us to think
"outside the box", and to transcend the limitations of preconceived knowledge. Unconscious
mechanism play an essential role in these intuitive processes (e.g. Grobstein, 2005; DrespLangley, 2011; Paulson et al. 2017b). Eudaimonia most certainly fuels on consciousness as
11
energy potential, as a fundamental driving force towards a better life, referring to the subjective
experiences associated with living a life of virtue and purpose in the pursuit of human
excellence. The clinical neurosciences have only just begun to explore the underlying
psychological and physiological mechanisms and processes. The phenomenological experiences
derived from eudaimonic living include self-realization, self-actualization, personal
expressiveness, optimism, vitality and, as experienced in states of deep meditation, capability of
transcending the Self (Di Fabio and Palazzeschi, 2005). While hedonic well-being focuses on
happiness defined in terms of pleasure and the avoidance of pain, the eudaimonic approach, on
the other hand, relates to meaning and self-realization where well-being is seen as the full
functioning of a person at a higher of consciousness than the one that seeks pleasure to attain
happiness. A conscious Self in a state of eudaimonic well-being is focused on inner resources,
resilience, higher meaning, authenticity, and purposefulness (Cosco, Howse, and Brayne, 2017;
Di Fabio and Palazzeschi, 2015). Consciousness changes as our brains age, with changes in
challenges to meet, and in perspectives for the future. Although younger individuals may be
deemed more resilient than ageing ones, this is a preconception that needs to be reconsidered
in the current society context under the light of new challenges and problems related to current
society contexts, the internet, and social media (e.g. Garland, 2018; Dresp-Langley, 2020; Liu,
Jiang, and Zhang, 2021). In ageing individuals, on the other hand, changes in embodiment occur
with ageing neuronal mechanisms and their associated sensorimotor and cognitive deficits
(Costello and Bloesch, 2017). Investigating the affective and cognitive mechanisms of deep
meditation, mindfulness, and expanded consciousness at the behavioral, metabolic, and
neurobiological levels, with research into the mechanisms of action underlying expanded
consciousness, will no doubt contribute to the development of treatment options beyond agerelated changes in neuronal function. A wider range of comprehensive approaches needs to be
developed to address the multiple mechanisms underlying the many different conditions of
breakdown of human resilience (e.g. Franklin, 2012). Such may be, but not always, related to
brain aging. While embodiment changes as we age (Kuehn et al., 2018;), these changes do not
inevitably produce lesser well-being (Ryff et al., 2016). Yet, bodily awareness is a central
component of human consciousness (Treves et al., 2019), and clearly an important aspect of
well-being while we are young (Ginzburg et al., 2014). Resilience theory (e.g. Maltby et al.,
2019) reflects the general idea that managing to navigate adversity and maintaining high levels
of functioning across a large number of various domains demonstrates resilience, i.e. the
capacity to cope with adversity. Similarly, traditional models of healthy ageing (cf. Wong, 2018,
for a review) suggest that having a high level of functioning across a large number of various
domains would be a requirement for well-being and resilience. Yet, this may not necessarily be
so. For example, health benefits have been identified among older adults who maintain a
purposeful life engagement and thereby exhibit a high level of eudaimonic well-being (Cosco,
Howse, and Brayne, 2017). These benefits would include extended longevity, reduced risks in
12
various disease outcomes, reduced physiological deregulation, and gene expression linked to
better inflammatory profiles (Ryff et al., 2016). Similarly, the brains of mindful or meditating
individuals may be less affected by ageing processes under the light of research suggesting that
meditation and similar forms of mindfulness practice, or the states of expanded consciousness
such practice generates, could contribute to preserving healthy brain tissue, cognitive and
emotional resilience, and diminish the risk of dementia and other age-related
neurodegenerative diseases (Kurth, Cherbuin, and Luders, 2017; Lutz et al., 2018). However, as
already pointed out herein, the capability of projecting its own existence into a future that has
not happened yet is the sole unique property of a fully conscious Self. Only the human primate
has evolved this capability and, as postulated here, this capability is intimately linked to
eudaimonic well-being as defined here above. This working assumption stems from the,
previously discussed (Dresp-Langley, 2011, 2018; Dresp-Langley and Durup, 2012), ontological
link between consciousness and time itself, which is summarized again in the context of this
paper here, for illustration, in Figure 1. In the current societal context, with the many challenges
we have to face and to anticipate, expanding our consciousness and exploiting it mindfully could
be the key to our future as well as that of the whole planet. One of the most important
functions of expanded consciousness may be its power to generate holistic resilience, to
increase our potential to cope with new forms of adversity, whether we are young or old. A
science of consciousness that leads to novel forms of well-being in the face of increasing
adversity could have a significant impact, for individuals and for society as a whole.
5. Conclusions and perspectives
Field theories of consciousness where the latter is seen as having duration and extension
in space are limited by the fact that, unlike in the field theories in physics, particular regions of
the presumed space-time continuum and interactions between elementary objects herein
cannot be objectively measured, or accounted for mathematically. Libet (1994) was well aware
of this fundamental problem by recognizing that “the mind field of consciousness” does not
correspond to any category of known physical fields and cannot be observed directly by known
physical means. Pockett (2013) wrote that “a field that is not observable directly by known
physical means is in some danger of remaining confined to the realms of philosophy”, leaving it
to her readers to decide whether this statement is to be considered as outrageous, or as a sign
of a healthy sense of humor. Indeed, what strikes in all of the existing neural theories of
consciousness including the field theories is the preconception that there has to be a “scientific”
(as opposed to “philosophical”) account for consciousness. This is even more astonishing than
the “astonishing hypothesis” (Crick, 1994) of a neural correlate for consciousness itself, because
it means dismissing the fact that all contemporary science, including mathematics and physics,
13
stems from nothing else but philosophy. Thus, quite ironically, the contemporary science of
consciousness is based on the preconception that all reality has to be material in the sense of
measurable by the known tools of physics, and that consciousness must be a direct product of
physical activity in the brain. Yet, the biggest nut to crack for this kind of materialism has
remained the existence of consciousness. It is the latter which has allowed to conceive all our
methods and tools for scientific measurement, yet, it looks like these methods currently fail to
fully explain what has made their conception possible in the first place. The full recognition that
our conscious minds are not confined to our brains, or to what is currently measurable inside
the brain or beyond, may eventually free contemporary neuroscience. Why look for a
biophysical explanation of consciousness? Pressing society needs call for a science of
consciousness in terms of its power to generate and foster eudaimonic well-being, of individuals
as well as nations. Consciousness is above anything else an internal, dynamic process that
governs intentionality for the purpose of creativity and social interaction and their complex
relationships with the first-person perspective (e.g. Metzinger and Gallese, 2003). Thus,
consciousness may have evolved to form a “mind field” that reaches beyond space and time to
enable us, ultimately, to plan for both our survival, and our extinction (two essential and
complementary concepts in Darwin’s theory of evolution) when survival on the planet is no
longer an acceptable option for our species.
References
Ainsworth M, Lee S, Cunningham MO, Traub RD, Kopell NJ, Whittington MA. Rates and rhythms:
a synergistic view of frequency and temporal coding in neuronal networks. Neuron.
2012;75(4):572-83.
Alexander R, Aragón OR, Bookwala J, Cherbuin N, Gatt JM, Kahrilas IJ, Kästner N, Lawrence A,
Lowe L, Morrison RG, Mueller SC, Nusslock R, Papadelis C, Polnaszek KL, Helene Richter S, Silton
RL, Styliadis C. The neuroscience of positive emotions and affect: Implications for cultivating
happiness and wellbeing. Neurosci Biobehav Rev. 2021; 121:220-249.
Bazavov A, Ding HT, Hegde P, Kaczmarek O, Karsch F, Laermann E, Wagner M. Additional
strange Hadrons from QCD thermodynamics and strangeness freezeout in heavy ion collisions.
Physical Review Letters. 2014; 113:072001. doi:10.1103/PhysRevLett.113.072001
Birch J, Schnell AK, Clayton NS. Dimensions of Animal Consciousness. Trends Cogn Sci. 2020;
24(10):789-801.
Block N. Consciousness, accessibility, and the mesh between psychology and neuroscience.
Behavioral and Brain Sciences. 2007; 30(5-6):481–499.
14
Brandmeyer T, Delorme A, Wahbeh H. The neuroscience of meditation: classification,
phenomenology, correlates, and mechanisms. Prog Brain Res. 2019; 44:1-29.
Bulf H., Johnson S.P., Valenza E. Visual statistical learning in the newborn infant. Cognition.
2011; 121:127–132.
Buzsáki, G. The structure of consciousness. 2007; Nature, 446, 267.
Cabanac M, Cabanac AJ, Parent A. The emergence of consciousness in phylogeny. Behav Brain
Res. 2009; 198(2):267-72.
Cacha LA, Poznanski RR. Genomic instantiation of consciousness in neurons through a
biophoton field theory. J Integr Neurosci. 2014; 13(2):253-92.
Callender, C. Is time an illusion? 2010; Scientific American, 295, 58-65.
Carroll, S. From eternity to Here: The quest for the ultimate theory of time. 2010; New York:
Dutton/Penguin Group.
Carver CS and Humphries C. Havana daydreaming: A study of self-consciousness and the
negative reference group among Cuban Americans. Journal of Personality and Social Psychology.
1981; 40(3):545–552.
Chalmers DJ. The Conscious Mind. 1996; Oxford, UK: Oxford University Press.
Churchland PS. Brain-Wise. Studies in Neurophilosophy. Cambridge, Mass, USA: MIT Press; 2002.
Churchland PS. A neurophilosophical slant on consciousness research. Prog Brain Res.
2005;149:285-93.
del Cul A, Dehaene S, Reyes P, Bravo E, Slachevsky A. Causal role of prefrontal cortex in the
threshold for access to consciousness. Brain. 2009; 132, 2531-2540.
Cosco TD, Howse K, Brayne C. Healthy ageing, resilience and wellbeing. Epidemiol Psychiatr Sci.
2017; 26(6):579-583.
Costello MC, Bloesch EK. Are Older Adults Less Embodied? A Review of Age Effects through the
Lens of Embodied Cognition. Front Psychol. 2017;8:267.
Crick, F. The Astonishing Hypothesis: The Scientific Search for the Soul. 1994; Scribners.
Di Fabio A, Palazzeschi L. Hedonic and eudaimonic well-being: the role of resilience beyond fluid
intelligence and personality traits. Frontiers in Psychology. 2015; 6:1367.
Dresp-Langley B, Durup J. A plastic temporal brain code for conscious state generation. Neural
Plasticity. 2009; e:482696.
15
Dresp-Langley B, Durup J. Does Consciousness Exist Independently of Present Time and Present
Time Independently of Consciousness? Open Journal of Philosophy. 2012; 2(1): 45-49.
Dresp-Langley B. Why the brain knows more than we do: non-conscious representations and
their role in the construction of conscious experience. Brain Science. 2011;2(1):1-21.
Dresp-Langley, Birgitta (2018). The experience dependent dynamics of human consciousness.
Open Journal of Philosophy. 2018; 8 (2):116-143.
Dresp-Langley B. Children's Health in the Digital Age. Int J Environ Res Public Health. 2020;
17(9):3240.
Edelman GM. Naturalizing consciousness: a theoretical framework. Proceedings of the National
Academy of Sciences of the United States of America, 2003; 100(9):5520–5524.
Encyclopedia Britannica, Energy. 2021; available online at:
https://www.britannica.com/science/energy
Fabbro F, Aglioti SM, Bergamasco M, Clarici A, Panksepp J. Evolutionary aspects of self- and
world consciousness in vertebrates. Front Hum Neurosci. 2015;9:157.
Feinberg TE, Mallatt J. The evolutionary and genetic origins of consciousness in the Cambrian
Period over 500 million years ago. Frontiers in Psychology. 2013; 4:667.
Fingelkurts AA, Fingelkurts AA. Operational architectonics of the human brain biopotential field:
towards solving the mind-brain problem. Brain and Mind. 2002; 2: 261-296).
Fouquet C, Tobin C, Rondi-Reig L. A new approach for modeling episodic memory from rodents
to humans: the temporal order memory. Behav Brain Res. 2010; 215(2):172-9.
Franklin TB, Saab BJ, Mansuy IM. Neural mechanisms of stress resilience and vulnerability.
Neuron. 2012;75(5):747-61.
Garland EL, Howard MO. Mindfulness-based treatment of addiction: current state of the field
and envisioning the next wave of research. Addict Sci Clin Pract. 2018; 13(1):14.
Gilead M, Liberman N, Maril A. From mind to matter: neural correlates of abstract and concrete
mindsets. Soc Cogn Affect Neurosci. 2014; 9(5):638-645.
Ginzburg K, Tsur N, Barak-Nahum A, Defrin R. Body awareness: differentiating between
sensitivity to and monitoring of bodily signals. J Behav Med. 2014; 37(3):564-75.
Grau C, Ginhoux R, Riera A, Nguyen TL, Chauvat H, Berg M, Ruffini G. Conscious brain-to-brain
communication in humans using non-invasive technologies. 2014; PLoS ONE.
doi:10.1371/journal.pone.0105225
16
Grobstein P. Making the unconscious conscious, and vice versa: a bi-directional bridge between
neuroscience/cognitive science and psychotherapy? Cortex. 2005; 41(5):663-8.
Grossberg S. The link between brain learning, attention, and consciousness. Consciousness and
Cognition. 1999; 8(1):1–44.
Grossberg S. How hallucinations may arise from brain mechanisms of learning, attention, and
volition. Journal of the International Neuropsychological Society. 2000; 6(5):583–592.
Hari R. From Brain-Environment Connections to Temporal Dynamics and Social Interaction:
Principles of Human Brain Function. Neuron. 2017;94(5):1033-1039.
Helekar SA. On the possibility of universal neural coding of subjective experience. Consciousness
and Cognition. 1999; 8(4):423–446.
Hegel, G. W. F. System der Wissenschaft. Erster Teil: Die Phänomenologie des Geistes. 1807;
Josef Anton Goebhardt Verlag, Bamberg/Würzburg.
Heidegger, M. Sein und Zeit. 1927; Max Niemeyer Verlag, Tübingen.
Hilton L, Hempel S, Ewing BA, et al. Mindfulness Meditation for Chronic Pain: Systematic Review
and Meta-analysis. Ann Behav Med. 2017;51(2):199-213.
Hume, D. Treatise of Human Nature. 1740; first book (Part 4, Section 6).
Jaynes J. The Origin of Consciousness in the Breakdown of the Bicameral Mind. 1990; HoughtonMifflin; Boston, MA, USA.
John E R. The neurophysics of consciousness. Brain Research Reviews. 2002; 39:1-28.
Jordan J. S., Ghin M. Proto-consciousness as a contextually emergent property of self-sustaining
systems. Mind Matter. 2006; 4, 45–68.
Keppler J. The Role of the Brain in Conscious Processes: A New Way of Looking at the Neural
Correlates of Consciousness. Frontiers in Psychology. 2018; 9:1346.
Köhler W. Dynamics in psychology. 1940; Liveright, New York.
Kotchoubey B. Human Consciousness: Where Is It From and What Is It for. Front Psychol. 2018;
9:567.
Kuehn E, Perez-Lopez MB, Diersch N, Döhler J, Wolbers T, Riemer M. Embodiment in the aging
mind. Neurosci Biobehav Rev. 2018; 86:207-225.
Kurth F, Cherbuin N, Luders E. Promising Links between Meditation and Reduced (Brain) Aging:
An Attempt to Bridge Some Gaps between the Alleged Fountain of Youth and the Youth of the
Field. Frontiers in Psychology. 2017; 8:860.
17
LaBerge S. Lucid dreaming: psychophysiological studies of consciousness during REM sleep. In:
Bootzen RR, Kihlstrom JF, Schacter DL, Eds. Sleep and Cognition. 1990;Washington, DC, USA:
APA press, pp. 109–126.
LaBerge S, Levitan L, Dement WC. Lucid dreaming: physiological correlates of consciousness
during REM sleep. Journal of Mind and Behavior. 1986; 7:251–258.
Lashley KS, Chow KL, Semmes J. An examination of the electric field theory of cerebral
integration. Psychological Review. 1951; 58, 123-136.
Libet B. Mind Time. Cambridge, Mass, USA: Harvard University Press; 2004.
Liu X, Jiang J, Zhang Y. Effects of Logotherapy-Based Mindfulness Intervention on Internet
Addiction among Adolescents during the COVID-19 Pandemic. Iran J Public Health. 2021;
50(4):789-797.
Logan RK. The Extended Mind: The Emergence of Language: The Human Mind and Culture.
2007; University of Toronto Press: Toronto, Canada.
Lutz A, Klimecki OM, Collette F, Poisnel G, Arenaza-Urquijo E, Marchant NL, De La Sayette V,
Rauchs G, Salmon E, Vuilleumier P, Frison E, Vivien D, Chételat G; Medit-Ageing Research Group.
The Age-Well observational study on expert meditators in the Medit-Ageing European project.
Alzheimers Dement (N Y). 2018; 4:756-764.
Mahone MC, Travis F, Gevirtz R, Hubbard D. fMRI during Transcendental Meditation practice,
Brain and Cognition. 2018; 123: 30-33.
Maltby J, Day L, Hall SS, Chivers S. The Measurement and Role of Ecological Resilience Systems
Theory Across Domain-Specific Outcomes: The Domain-Specific Resilient Systems Scales.
Assessment. 2019; 26(8):1444-1461.
Marchetti G. Attention and working memory: two basic mechanisms for constructing temporal
experiences. Front Psychol, 2014; 5:880.
McFadden J. The conscious electromagnetic information field theory: the hard problem made
easy? Journal of Consciousness Studies. 2002 ; 9(8) : 45-60.
Metzinger T, Gallese V. The emergence of a shared action ontology: building blocks for a theory.
Conscious Cogn. 2003; 12(4):549-71.
Muehsam D, Lutgendorf S, Mills PJ, Rickhi B, Chevalier G, Bat N, Chopra D, Gurfein B. The
embodied mind: A review on functional genomic and neurological correlates of mind-body
therapies. Neuroscience & Biobehavioral Reviews. 2017; 73:165-181.
Nair AK, Sasidharan A, John JP, Mehrotra S, Kutty BM, Just a minute meditation: Rapid voluntary
conscious state shifts in long term meditators. Consciousness and Cognition. 2017; 53: 176-184.
18
Nani A, Manuello J, Mancuso L, Liloia D, Costa T, Cauda F. The Neural Correlates of
Consciousness and Attention: Two Sister Processes of the Brain. Frontiers in Neuroscience.
2019; 13:1169.
Natsoulas T. A rediscovery of presence. Journal of Mind & Behavior. 1999; 20, 17-42.
Nyberg L, Kim ASN, Habib, R, Levine B, Tulving, E. Consciousness of subjective time in the brain.
Proceedings of the National Academy of Sciences of the USA. 2010; 107, 22356-22359.
Paoletti P, Ben-Soussan TD. Reflections on Inner and Outer Silence and Consciousness Without
Contents According to the Sphere Model of Consciousness. Frontiers in Psychology. 2020; 11:
01807.
Paulson S, Hustvedt S, Solms M, Shamdasani S. The deeper self: an expanded view of
consciousness. Ann N Y Acad Sci. 2017; 1406(1):46-63.
Paulson S, Berlin HA, Ginot E, Makari G. Delving within: the new science of the unconscious. Ann
N Y Acad Sci. 2017;1406(1):12-27.
Pepperell R. Consciousness as a Physical Process Caused by the Organization of Energy in the
Brain. Front Psychol. 2018; 9:2091.
Piaget J. La Construction du Réel Chez L’enfant. Delachaux et Niestlé; Neuchätel, Switerland:
1967.
Pistoia F, Sacco S, Sarà M, Carolei A. The perception of pain and its management in disorders of
consciousness. Curr Pain Headache Rep. 2013;17(11):374.
Pockett S. Does consciousness cause behaviour? Journal of Consciousness Studies. 2004;
11(2):23–40.
Pockett S. Scholarpedia, 2013; 8(12):4951.
Rees G, Kreiman G, Koch C. Neural correlates of consciousness in humans. Nat Rev Neurosci.
2002; 3(4):261-70.
Rosenfeld AJ. The Neuroscience of Happiness and Well-Being: What Brain Findings from
Optimism and Compassion Reveal. Child Adolesc Psychiatr Clin N Am. 2019; 28(2):137-146.
Ryff CD, Heller AS, Schaefer SM, van Reekum C, Davidson RJ. Purposeful Engagement, Healthy
Aging, and the Brain. Curr Behav Neurosci Rep. 2016; 3(4):318-327.
Sheldrake R. Setting science free from materialism. Explore (NY). 2013; 9(4):211-8.
Searle JR. How to study consciousness scientifically. Philosophical Transactions of the Royal
Society B. 1998; 353(1377):1935–1942.
19
Singer JL. Navigating the stream of consciousness: Research in daydreaming and related inner
experience. American Psychologist. 1975; 30(7): 727–738.
Singer W. Phenomenal awareness and consciousness from a neurobiological perspective. In:
Metzinger T, Ed. Neural Correlates of Consciousness: Empirical and Conceptual Questions. 2000;
Cambridge, Mass, USA: MIT Press, pp. 121–137.
Thorpe S, Delorme A, Van Rullen R. Spike-based strategies for rapid processing. Neural
Networks. 2001; 14(6-7):715–725.
Tononi G, Edelman GM. Consciousness and complexity. Science. 1998;282(5395):1846–1851.
Travis F. Transcendental experiences during meditation practice. Ann N Y Acad Sci. 2014;
1307:1-8.
Treves IN, Tello LY, Davidson RJ, Goldberg SB. The relationship between mindfulness and
objective measures of body awareness: A meta-analysis. Sci Rep. 2019;9(1):17386.
Vieten C, Wahbeh H, Cahn BR, MacLean K, Estrada M, Mills P, Murphy M, Shapiro S, Radin D,
Josipovic Z, Presti DE, Sapiro M, Bays JC, Russell P, Vago D, Travis F, Walsh R, Delorme A. Future
directions in meditation research: Recommendations for expanding the field of contemplative
science. PLOS ONE. 2018; 13: 11(e0205740).
Vivot RM, Pallavicini C, Zamberlan F, Vigo D, Tagliazucchi E. Meditation Increases the Entropy of
Brain Oscillatory Activity. Neuroscience. 2020; 431:40-51.
Von der Malsburg C. The coherence definition of consciousness. In: Ito M, Miyashita Y, Rolls ET,
editors. Cognition, Computation and Consciousness. Oxford, UK: Oxford University Press; 1997.
pp. 193–204.
Wahbeh H, Sagher A, Back W, Pundhir P, Travis F, A Systematic Review of Transcendent States
Across Meditation and Contemplative Traditions. Explore (NY). 2018; 14(1): 19-35.
Wall JT, Xu J, Wang X. Human brain plasticity: an emerging view of the multiple substrates and
mechanisms that cause cortical changes and related sensory dysfunctions after injuries of
sensory inputs from the body. Brain Research Reviews. 2002; 39(2-3):181–215.
Walsh R. What is wisdom? Cross-cultural and cross-disciplinary syntheses. Review of General
Psychology. 2015;19(3):278.
Wong RY. A New Strategic Approach to Successful Aging and Healthy Aging. Geriatrics (Basel).
2018; 3(4):86.
20
Figure and caption
Figure 1: All phenomenal reality originates from the ontological link between time and
consciousness (after Dresp-Langley and Durup, 2012). This leads to consider consciousness as a
form of creative energy beyond space and time, where specific cognitive abilities such as
perception, memory or projective thinking and reasoning, although they may exploit conscious
energy, need to be placed at a separate ontological level. An optimally expanded level of
consciousness (by deep meditation or other mindfulness practice) would be equivalent to an
expanded Self in a state of deep of sense of present, past, and future at one and the same
moment in time. Such deep states of consciousness may not be attainable by our species. |
Towards a statistical mechanics of consciousness: maximization of
number of connections is associated with conscious awareness
R. Guevara Erra1 , D. M. Mateos2 , R. Wennberg3 , J.L. Perez Velazquez2 ∗
1
Laboratoire Psychologie de la Perception, CNRS and Université Paris Descartes, Sorbonne Paris Cité, Paris, France.
2
Neuroscience and Mental Health Programme, Division of Neurology, Hospital for Sick Children.
Institute of Medical Science and Department of Paediatrics, University of Toronto, Toronto, Canada.
3
Krembil Neuroscience Centre, Toronto Western Hospital, University of Toronto, Toronto, Canada.
arXiv:1606.00821v2 [q-bio.NC] 9 Jan 2017
* jose-luis.perez-velazquez@sickkids.ca
January 11, 2017
Abstract
It has been said that complexity lies between order and disorder. In the case of brain activity, and
physiology in general, complexity issues are being considered with increased emphasis. We sought to
identify features of brain organization that are optimal for sensory processing, and that may guide the
emergence of cognition and consciousness, by analysing neurophysiological recordings in conscious
and unconscious states. We find a surprisingly simple result: normal wakeful states are characterised
by the greatest number of possible configurations of interactions between brain networks, representing
highest entropy values. Therefore, the information content is larger in the network associated to
conscious states, suggesting that consciousness could be the result of an optimization of information
processing. These findings encapsulate three main current theories of cognition, as discussed in
the text, and more specifically the conceptualization of consciousness in terms of brain complexity.
We hope our study represents the preliminary attempt at finding organising principles of brain
function that will help to guide in a more formal sense inquiry into how consciousness arises from
the organization of matter
1
Introduction
How consciousness arises from the organization of matter is a subject of debate that spans several
disciplines, from philosophy to physics. Multitude of studies focus on the investigation of patterns
of synchrony in brain activity based on magnitudes of a variety of synchrony indices, and thus the
search for organising principles of brain function is today more crucial than ever. We sought to identify
global features of brain organization that are optimal for sensory processing and that may guide the
emergence of conscious awareness. Our results provide a (very simple) answer to the question of what the
magnitudes of synchrony indices represent in terms of the structure of brain activity. Neurophysiological
recordings of brain activity demonstrate fluctuating patterns of cellular interactions, variability that
allows for a wide range of states, or configurations of connections of distributed networks exchanging
information, and support the flexibility needed to process sensory inputs. Recent years have seen a surge
in the study of fluctuations in brain coordinated activity, studies that have raised conceptual frameworks
1
such as that of metastable dynamics [1] and that have motivated interest in the practical application
of assessments of nervous system variability for clinical purposes [2, 3]. A prominent question is how
to describe the organizing principles of this collective activity, which allow features associated with
consciousness to emerge. What is the optimal brain organization that allows it to adequately process
sensory stimuli and enable the organism to adapt to its environment?
Previous studies have revealed values of different indicators of brain coordinated activity, such as
synchronization, associated with healthy and pathologic states by comparison of baseline values and
those in, for instance, unconscious states like coma and epileptic seizures [4, 5, 6]. These observations
prompt the question of what physiological organization underlies the specific values of the synchrony
indices found in normal alert states and other conditions; in other words, what is special about these
values found in conscious states? We believe that we have provided an answer to this question in
our work. We propose that there is a certain general organization of brain cell ensembles that will
be optimal for conscious awareness, that is, for the processing of sensory inputs. As an extension of
previous work [7] where it was proposed that a general organising principle of natural phenomena is
the tendency toward maximal – more probable – distribution of energy/matter, we venture that the
brain organization optimal for conscious awareness will be a manifestation of the tendency towards a
widespread distribution of energy (or, equivalently, maximal information exchange). Whereas we do
not deal with energy or information in our work, we instead focus on the number of (micro)states,
or combinations of connected signals derived from specific types of neurophysiologic recordings. We
use the term “information” in the intuitive sense that normally permeates neuroscience: cell ensembles
that are functionally connected to process/exchange information; furthermore, the equivalence between
information exchange and energy transactions has been the subject of several studies, more specifically
in [7] (see also [8, 9]). The question then becomes: how do we capture the nature of these organizations
of cell interactions?
We have followed the classic approach in physics when it comes to understanding collective behaviours of systems composed of a myriad of units: the assessment of the number of possible configurations, or microstates, that the system can adopt. In our study we focus on the collective level of
description and assume that coordinated patterns of brain activity evolve due to interactions of mesoscopic areas ( [10, 11]). Thus we use several types of brain recordings in conscious and unconscious
states, evaluating the number of “connections” between these areas and the associated entropy and
complexity. We present evidence that conscious states result from higher entropy and complexity in
the number of configurations of pairwise connections. The number of pairwise channel combinations is
near the maximum of all possible configurations when the individual is processing sensory inputs in a
normal manner (e.g. with open eyes). Our interpretation is that a greater number of configurations of
interactions allows the brain to optimally process sensory information, fostering the necessary variability in brain activity needed to integrate and segregate sensorimotor patterns associated with conscious
awareness.
2
Materials and Methods
Electrophysiological recordings
Recordings were analysed from 9 subjects, using magnetoencephalography (MEG), scalp electroencephalography (EEG) or intracranial EEG (iEEG). Three epilepsy patients were studied with MEG;
2
1 epilepsy patient was studied with iEEG; 3 epilepsy patients were studied with simultaneous iEEG
and scalp EEG; and 2 nonepileptic subjects were studied with scalp EEG. For the study of seizures
versus alert states, the 3 subjects with MEG recordings and the one with iEEG were used. Details of
the patients’ epilepsies and seizure types have been presented in previous studies (MEG patients in [5];
iEEG patients in [12]). For the study of sleep versus alert states, the 3 patients with combined iEEG
and scalp EEG have been described previously (patients 1, 3, 4 in [13]); the 2 subjects studied with
scalp EEG alone had been investigated because of a suspected history of epilepsy, but both were ultimately diagnosed with syncope, with no evidence of epilepsy found during prolonged EEG monitoring.
In brief, the MEG seizure recordings were obtained in one patient with primary generalized absence
epilepsy, in one patient with symptomatic generalized epilepsy, and in one patient with frontal lobe
epilepsy. The iEEG seizure recordings were obtained from a patient with medically refractory temporal
lobe epilepsy as part of the patient’s routine clinical pre-surgical investigation. MEG recordings were
obtained using a whole head CTF MEG system (Port Coquitlam, BC, Canada) with sensors covering
the entire cerebral cortex, whereas iEEG electrodes were positioned in various locations including, in
the temporal lobe epilepsy patient, the amygdala and hippocampal structures of both temporal lobes.
EEG recordings were obtained using an XLTEK EEG system (Oakville, ON, Canada). The details of
the acquisitions varied from patient to patient (e.g., acquisition rate varied from 200 to 625 Hz) and
were taken into consideration for the data analyses. The duration of the recordings varied as well: for
the seizure study, the MEG sample epochs were of 2 minutes duration each, with total recording times
of 30-40 minutes; the iEEG patient sample was of 55 minutes duration. The sleep study data segments
were each 2-4 minutes in duration, selected from continuous 24-hour recordings.
Data analysis
The only pre-processed data were those of the scalp EEG recordings. These were processed using a
Laplacian derivation [11], to avoid the potential effects of the common reference electrode on synchronization [14] using the DSC algorithm [15]. Initially a phase synchrony index was calculated from all
possible pairwise signal combinations, for which we use the standard procedure of estimating phase differences between two signals from the instantaneous phases extracted using the analytic signal concept
via the Hilbert transform. To compute the synchrony index, several central frequencies, as specified
in the text and figure legends, were chosen with a bandpass filter of 2 Hz on either side, hence, for
one value of the central frequency f , the bandpass is f ± 2 Hz. The central frequencies were chosen
according to the relevant behavioural states and some analytical limitations– thus for the sleep studies
we choose 4 Hz (not lower because the extraction of the instantaneous phase was not optimal for central
frequencies lower than 4). To see whether similar results were obtained with different frequencies, we
chose others (see figures) provided there was power at those values. The phase synchrony index (R)
was calculated using a 1-second running window and was obtained from the phase differences using
the mean phase coherence statistic which is a measure of phase locking and is defined as R = |hei∆θ i|
where ∆θ is the phase difference between two signals. This analytical procedure has been described in
great detail elsewhere [4, 5, 14]. The calculation of the index R was done for all possible signal pairs.
The mean value of the R index thus obtained was then estimated for the desired time length. For
instance, for the sleep recordings, the time period was the whole episode, which was, as noted above,
between 2 and 4 minutes. For the seizure recordings, the periods to obtain the mean synchrony varied
depending on the behavioural condition, for instance, in figure 1C the whole ictal event (labelled ‘Sz’)
3
and the initial 10-second portion of it (’10 sec Sz’) were taken for the reason explained in the text
and figure legend. The calculation of the number of connected signals and the entropy associated is
described in the Results section. We note here that to assess entropy we assume that the different
pairwise configurations are equiprobable, thus the entropy is reduced to the logarithm of the number
of states, S = lnC (see notation in the main text). However, the estimation of C (the combinations of
connections between diverse signals), is not feasible due to the large number of sensors; for example, for
35 sensors, the total possible number of pairwise connections is [1442] = 10296, then if we find in the
experiment that, say, 2000 pairs are connected, the computation of [102962000] has too large numbers
for numerical manipulations, as they cannot be represented as conventional floating point values in,
for instance, MATLAB. To overcome this difficulty, we used the well-known Stirling approximation for
large n : ln(n!) = n ln(n)˘n. The Stirling approximation is frequently used in statistical mechanics
to simplify entropy-related computations. Using this approximation, and after some basic algebra, the
equation for entropy reads, S = N ln(N/N − p) − p ln(p/N − p), where N is the total number of possible pairs of channels and p the number of connected pairs of signals in each experiment (see Results
for details and notation). Because this equation is derived from the Shannon entropy, it indicates the
information content of the system as well (37).
In addition to entropy, we used another measure of complexity, the Lempel-Ziv (L-Z) complexity,
based in the Kolmogorov deterministic complexity [16]. This complexity measure the amount of nonredundant information in a string by estimating the minimal size of the ”vocabulary” necessary to
describe the string [17]. Strings with high L-Z complexity require a large number of different patterns
(“words”) to be reproduced, while strings with low complexity can be largely compressed with a few
patterns employed to eliminate redundancy with no loss of information. For this purpose, values of
the matrix B (defined in Results) were placed in a one-dimensional vector and its L-Z complexity
determined.
3
Result
Guided by proposals that consciousness requires medium values of certain features of cell assemblies,
e.g. not too high or low synchrony or correlations [18, 19, 3], or halfway between order and disorder [20],
we chose to quantify the number of possible configurations the brain can adopt in different behavioural
conditions. Our basic approach consists in the estimation of the number of possible pairwise connections
between recorded brain signals. Signals included MEG, iEEG and scalp EEG recordings; details can
be found in Methods. We are limited to pairwise combinations of the signals because of the manner
in which phase synchrony is computed – as phase differences between two signals – and we use phase
synchronization as the means to determine “connectivity” between the two signals. Once the number
of “connected” signals is known, we estimate the entropy of those pairwise combinations. The results
obtained with recordings acquired during conscious states are compared with those acquired during
unconscious states, which included sleep (all stages) and epileptic seizures. To determine connectivity,
we use an accepted approach of computing a phase synchronization index (details in Methods).
It must be noted that, while many studies use the words synchrony and connectivity as synonymous,
in reality phase synchrony analysis reveals only a correlation between the phases of the oscillations
between two signals, and not a real connectivity which depends on several other factors (this matter
has been covered in detail in [21, 22]. Nevertheless, due to the unfeasibility of an accurate, realistic
4
estimation of connectivity which would necessitate individual cell recordings from entire cell ensembles
as well as structural connectivity details, we use an accepted version under the assumption that the
phase relations may represent, at least, some aspect of a functional connectivity. Hence, in order to
evaluate interactions (“connections”), we take each sensor/channel as one “unit”, and define a pair
of signals as “connected” if the phase synchrony index is larger than a threshold. The threshold is
determined for each individual, and is the average synchrony index in the most normal alert state,
the ‘awake eyes-open’ condition, when the individual is fully alert and processing the sensorium in a
regular fashion. Because our data include the three recording methodologies aforementioned, we have
the opportunity to assess the reproducibility of the results in various types of recordings. While we work
at the signal level we will make the reasonable assumption that the MEG and scalp EEG sensors record
cortical activity underlying those sensors and thus throughout the text we will use the terms brain
signals or brain areas/networks as synonymous. The iEEG, obviously, records signals at the source
level. Note that we are not interested in the specific pattern of connectivity among brain sources/areas,
but rather in the global states. These points are further discussed in the Discussion section.
Phase synchronization for specific frequencies (details in Methods) is calculated for each pair of
channels and a “connectivity” matrix S is obtained, whose entries are the average values of the synchrony index during a certain time period for each pairwise configuration. From this matrix, a Boolean
connectivity matrix B is calculated, with 0 entry if the corresponding synchrony index is lower than
a threshold, and 1 if higher. We define two channels as “connected” if the corresponding entry in
matrix B is 1. Then we use the combinations of connected channels as a ‘complexity’ measure. The
total number of possible pairs of channels given a specific channel montage is given by the binomial
coefficient N = N c!/2! (N c − 2)! where N c is the total number of channels in the recording montage,
normally 144 − 146 in the case of MEG sensors, and between 19 and 35 with iEEG and scalp EEG. For
instance, in our MEG recordings we haveN c = 144, thus N = 10, 296possible pairs of connected sensors
are obtained. For each subject we calculate p, the number of connected pairs of signals in the different
behavioural states, using the aforementioned threshold of the synchrony index (which varies for each
subject), and estimate C, the number of possible combinations of those p pairs, using the binomial
coefficient again: C = N !/p!(N − p)! where N is the aforesaid value. In sum, all these calculations
represent the relatively simple combinatorial problem we are trying to solve: given a maximum total of
N pairs of connected signals, in how many ways can our experimental observation of p connected pairs
(that is, the number of 1’s in matrix B) be arranged. We then compute the entropy and Lempel-Ziv
complexity associated with those p values.
Figure 1 depicts the entropy (S), which, assuming equiprobable states, is the logarithm of the
number of states, S = ln C (see Methods for the estimation of entropy using very large C values) in
three epileptic patients. We note that this equation using the natural logarithm allows for a calculation
of both the Gibbs and the Shannon entropy, if needed, which differ from S by a constant multiplicative
factor k (the Boltzmann constant) and 1/(ln2) respectively. In reality the entropy estimation does
not provide any further information, as the main, crucial result is the number of configurations, C.
However, we have done it since it is a standard manner to quantify the “complexity” of the number of
microstates. The entropy data points are graphed on the curve that represents the entropy of all points
in the binomial distribution, where the maximum number of configurations (that is, maximum entropy)
occurs in the middle of the graph. Note in that figure that during conscious states, when patients are
not having generalised seizures with loss of awareness, the entropy is close to the maximum, whereas
entropy is lower (more distant from the top) for the seizure states. The values during the seizures fall
5
on the right-hand side of the graph because, due to the higher synchrony during ictal (seizure) events
such that the number of coupled channels (note that the x-axis is the number of connected signals)
is larger than during interictal (between seizure) activity, there are fewer pairwise configurations and
thus lower entropy. This phenomenon seems associated with the level of consciousness since when the
seizures are not generalised (Figure 1C and 1D), and the patients remain responsive and conscious, the
entropy values are similar to those of interictal (baseline) activity. Where in the curve the data points
are located depends of course on the synchrony index. Because seizures had higher synchrony than
interictal periods (“baseline”), the number of coupled signals is greater and the number of combinations
is lower.
We observe similar trends in the case of sleep. Figure 2 depicts some examples. Note how during
wakefulness the entropy is closer to the maximum of the curve, whereas the deeper the sleep stage,
the more distant from the maximum the values are. The deepest sleep stage, slow wave 3-4 (‘sws3-4’),
has consistently the lowest entropy. Interestingly, the entropy during REM sleep is very close, in most
cases, to the normal, alert state. This result may not be as surprising as it sounds if we consider the
mental activity during REM episodes that are normally associated with dreams. It is worth noting
too that in recordings taken when the subjects had their eyes closed, the entropy is much lower than
during the eyes open condition, and sometimes it is as low as during slow-wave 3-4 sleep. The results
for two central frequencies (4 and 8 Hz) are shown in Figure 2A and 2C, to demonstrate that it is not
always the case of high synchrony having lower entropy; sometimes it is lower synchrony (e.g., results
at 8 Hz) that resulted in fewer channel combinations and thus lower entropy as compared to fully alert
states. In Figures 1 and 2 we have shown results with iEEG and MEG (Figure 1) or iEEG and scalp
EEG (Figure 2) recordings to demonstrate that the same qualitative results are obtained with these
three recordings techniques. Thus these results do not depend on recording methodology. Shown in
Figure 3 is an example of the time course of the entropy before and during an ictal event. Hence,
we have demonstrated that the specific values of the synchrony index R in fully alert states represent
the largest number of combinations (microstates, see Discussion) of pairwise signal configurations.
This method solves the potential problem of the interpretation of the different R values obtained with
various recordings techniques. For example, in our experiments, average values in baseline conditions
are 0.248 ± 0.2 for MEG, 0.428 ± 0.04for iEEG, and 0.46 ± 0.05 for scalp EEG, nevertheless, in our
study the number of combinations are “normalised” to the number of recording sensors and show a final
result (the entropy) that is independent of the structure and synchrony magnitudes of the recording
methodology. The main idea derived from these results is represented in Fig. 4.
To further explore whether the decrease in entropy has a parallel with a decrease in other forms
of complexity, the Lempel-Ziv complexity of the number of configurations was assessed. Tables 1 and
2 illustrate the Lempel-Ziv complexity estimated for the B matrices, where a complementary result
can be seen: unconscious states have lower values of complexity. A decrease of complexity in the
raw electrophysiological signals was obtained too (data not shown), hence this may be a phenomenon
observable at different levels of description.
4
Discussion
Our attempts at seeking features of brain organization that allow for adequate processing of sensory
stimuli have provided evidence that a greater number of possible configurations of interactions between
6
brain networks is associated with alert states, representing high entropy associated with the number of
those combinations, whereas lower entropy (and thus fewer combinations of connections) is characteristic
of either unconscious states or altered states of alertness (eyes closed). This observation reflects a
relatively simple general organising principle at this collective level of description, which results in the
emergence of properties associated with consciousness.
With the advent of the ‘Big Data’ era and the related torrent of empirical observations, the search
for organising principles that result in the emergence of biological phenomena seems more crucial than
ever. We tried to uncover relatively simple laws that capture the bounds in the global organization
of a biological system that enable it to become adaptable (i.e., responsive) to an environment, or, in
neuroscientific terms, the features of optimal brain organization (in terms of connections) that allow
brains to adequately process sensory stimuli. We focused on the global states and did not investigate
specific patterns of connectivity between brain areas as a variety of other studies have assessed these
inter-regional interactions in conscious and unconscious states [23, 24]. The fact that our results are
similar, independent of recording methodology, demonstrates the robustness of the analysis. On that
note, we remark that while we have used the term ‘connectivity’, in reality the analysis reveals only
correlation between phases of oscillation, as already discussed in Results.
The present study can be considered an extension of previous work where it was proposed that a
general organising principle of natural phenomena is the tendency toward a maximal, or more probable,
distribution of energy [7], which can be encapsulated by the notion of the maximization of information
transfer [25]. As well, the notions of information and energy exchange are conceptually related: “the
common currency paying for all biological information is energy flow” [26, 9]. In the final analysis,
information exchange implies energy exchange, hence we interpret information exchange as energy redistribution as proposed in [7], even though our study is focused not on energy considerations but on
the number of states. Other studies have assessed the importance of brain synchronization to optimally
transfer information [27]. We interpret our observation that the number of pairwise channel combinations – that we take as interactions/connections between brain networks – occurs near the maximum
of possible configurations in periods with normal alertness, as that greater number of configurations
of interactions represents the most probable distribution of energy/information resulting in conscious
awareness. The configuration entropy we calculate measures the information content of the functional
network, and has been used in other works for the purpose of quantifying information [28]. One somewhat surprising result is the low entropy during the eyes-close condition. One could argue that having
the eyes closed does not change much the conscious state, and yet we observe reduced entropy as compared with eyes-open condition. Hence our observations may indicate not only states of consciousness
but also optimality of sensory processing – considering the great importance of visual processing in
humans, interrupting visual inputs should result in considerable changes in the dynamics; for instance,
an apparent alteration of brain dynamics upon eye closure is the appearance of alpha waves most clearly
in parieto-occipital regions. Interesting too is the relatively high entropy associated with REM episodes,
perhaps a reflection of the partial awareness during dreams. Perhaps the main difference between dream
and awake states is psychological, but they share similar brain dynamics.
It has been proposed that aspects of awareness emerge when certain levels of complexity are reached
[29]. It is then possible that the organization (complexity) needed for consciousness to arise requires
the maximum number of configurations that allow for a greater variety of interactions between cell
assemblies because this structure leads to optimal segregation and integration of information, two fundamental aspects of brain information processing [20] . Our results help cast the study of consciousness
7
and cognition into more of a physics framework that may provide insight into simple principles guiding
the emergence of conscious awareness, and perhaps the proposed thermodynamics for a network of
connected neurons [18] can be extended to explain cognition. Some classical studies [8] have already
characterized biological order in terms of functions of the number of states of a system. It is tempting to link our observations with the typical chemical equilibrium that, despite being composed of a
myriad of microstates, when viewed at the macroscopic level produces some useful laws, like the law
of mass action describing chemical balance, and thus the perspective we develop here may help guide
research to uncover organising principles in the neurosciences. In physics, microstates that yield the
same macrostate form an ensemble. A system tends to approach the most probable state, maximising
entropy under present constraints, and the resulting macrostate will be represented by the maximum
number of microstates. Hence, the macrostate with higher entropy (see scheme in Fig. 4) we have
defined, composed of many microstates (the possible combinations of connections between diverse networks, our C variable defined in Results), can be thought of as an ensemble characterised by the largest
number of configurations. Here we define an ensemble of microstates as all possible configurations of
connectivity leading to the same macrostate (having the same number of connected pair of signals, p).
The entropy of this macrostate, given by the logarithm of the number of combinations (our C), is the
number of microstates that are compatible with the given macrostate (assuming all microstates have
same statistical weight). In neurophysiological terms, each microstate represents a different connectivity pattern and thus is associated with, in principle, different behaviours or cognitive processes. The
macrostate that we find associated with wakeful normal states (eyes open) is the most probable because
it has the largest entropy (largest number of combinations of connections). While many elementary cellular microscopic processes are far from equilibrium (e.g., ionic gradients), at the macroscopic level the
system tends towards equilibrium, as most natural phenomena remain in near-equilibrium conditions
[30]. At the same time, the ensemble of microstates associated with normal sensory processing features
the most varied configurations and therefore offers the variability needed to optimally process sensory
inputs. In this sense, our results support current views on the metastability of brain states [1] in that
the states should not be too stable for efficient information processing, hence the larger the number of
possible interactions, the more variability is possible.
Equally, the results are consistent with the global workspace theory [31] in that the most widespread
distribution of information leads to conscious awareness. Furthermore, these observations relate as well
to the information integrated theory [32], in that consciousness increases in proportion to the system’s
repertoire of states, thus the more combinations possible, the more states available, and here we can define states as configurations of interactions. Additionally, the results support computational/theoretical
studies showing that patterns of organised activity arise from the maximization of fluctuations in synchrony [33], and that transitions between conscious states are achieved by just varying the probability
of connections in neural nets [34]. In general, our observations highlight the fundamental importance of
fluctuations in neuronal activity as the source of healthy brain dynamics. More specifically, our results
have a precise parallel with the work of Hudetz et al. (2014), where they graph a dispersion index
versus an activation level (their figure 7B) and propose that consciousness resides at the top of the
curve, and anaesthetic states and seizures to lower and higher activation levels respectively, as we show
in Figures 1 and 2. Their ‘activation level’ could correspond to the number of signals that take part in
the combinations (our x axes in the graphs), and their ‘dispersion index’ to our number of combinations
(the y axes). Other studies have proposed as well that consciousness requires medium values of certain
features of cell assemblies [32, 35].
8
In sum, along with others, we consider cognition/consciousness not a static property but a dynamic
process with constant flux of energy, or information exchange [25]. Even though we have talked above
about a macrostate, this should not be taken as a fixed state, rather it contains dynamic processes
represented by the microstates, the re-arrangements of connections among brain cell ensembles. The
emergent features of cognitive phenomena that can be termed “conscious” arise once an efficient web of
connections endowed with certain complexity appears. The fact that values of phase synchrony during
fully alert states gave us the largest entropy of the number of pairwise signal combinations explains
in part the neurophysiological organization underlying these specific values of the quantification of
brain synchrony. Studies at this level of description may help to understand how consciousness arises
from organization of matter. In our view, consciousness can be considered as an emergent property
of the organization of the (embodied) nervous system, especially a consequence of the most probable
distribution that maximizes information content of brain functional networks.
On a technical note, we remark that in our analysis we had to choose a threshold to define “connectivity”, and therefore a suitable baseline had to be chosen. This procedure is obviously biased in that a
signal corresponding to a baseline has to be ascribed as the one providing the threshold, and we chose
the signals corresponding to the (psychological) state that is most suited for the purposes of adaptability: fully alert and receiving all sensory inputs (awake with open eyes). By this choice, and according
to our methods, that signal is already ascribed as having maximum entropy. We tried another less
prejudiced method, using surrogates of the original signals, and then computing the average synchrony
index among the surrogate population (10 phase-randomised surrogates per original channel/signal)
that is the threshold to define connectivity. It turns out that the value of the magnitude of synchrony of
the surrogates is close to the one for the aforementioned baseline chosen, so the results do not vary; nevertheless this new method still assigns the largest entropy to the random signals (surrogates), so there
is still the assumption that the average synchrony of the stochastic signals is a good approximation to
define connections among brain networks. Our current purpose is to completely avoid using thresholds
of synchrony indices, for which we are presently working on a scheme that assigns connectivity in the
time domain.
5
Conclusions and conjectures on the structure of brain-behaviourenvironment
It is tempting to speculate, based on these results and the conclusions of a previous study [7] that there
could be a universal logic ruling the evolution of natural phenomena — biological and nonbiological—
and the nervous system in particular: patterns emerge from a central theme captured by maximising
information exchange. Because, in the final analysis, all exchange of information implies exchange
of energy, natural phenomena tend towards the most probable distribution of energy, and thus the
interactions among system constituents tends to be maximized.
Because the brain functions to maintain a predictive model of the environment (the reason the
brain evolved is to model the environment, after all), then perhaps the brain’s global configuration
has to “copy” what is out there: and out there energy distributes in all possible microstates (second
principle of thermodynamics). Then to process such variability in nature, the nervous system should
have same structure, and the result is the ‘inverted U’ that has appeared in our analysis and has
been theoretically proposed in other publications [20], the top of the curve representing more possible
9
combinations to handle information/energy exchanges. On the other hand, in the extremes of this
curve we find fewer microstates, thus these are not optimal situations to process the many microstates
in the environment. The key then is not to reach the maximum number of units interacting (which
would be all-to-all connections and thus only one possible microstate), but rather the largest possible
number of configurations allowed by the constraints. In a similar fashion, it has been argued that
the brain needs to show criticality because natural phenomena possess critical dynamics [36]. Then,
perchance, consciousness can be considered as an emergent property of the organization of the embodied
nervous system submerged in an environment, consequence of the most probable distribution of energy
(information exchange) in the brain. In this regard, consciousness (like biochemistry) may represent
thus an optimal channel for accessing sources of (free) energy.
10
References
[1] JA. S. Kelso. Dynamic patterns: The self-organization of brain and behavior. MIT press, 1997.
[2] D. D Garrett, G. R. Samanez-Larkin, S. WS. MacDonald, U. Lindenberger, A. R McIntosh, and
C. L Grady. Moment-to-moment brain signal variability: a next frontier in human brain mapping?
Neuroscience & Biobehavioral Reviews, 37(4):610–624, 2013.
[3] V. Nenadovic, J. L. Perez Velazquez, and J. S. Hutchison. Phase synchronization in electroencephalographic recordings prognosticates outcome in paediatric coma. PloS one, 9(4):e94942, 2014.
[4] F. Mormann, K. Lehnertz, P. David, and C. E. Elger. Mean phase coherence as a measure for
phase synchronization and its application to the eeg of epilepsy patients. Physica D: Nonlinear
Phenomena, 144(3):358–369, 2000.
[5] L.. Garcia Dominguez, R. A. Wennberg, W. Gaetz, D. Cheyne, O. C. Snead, and J. L. Perez Velazquez. Enhanced synchrony in epileptiform activity? local versus distant phase synchronization
in generalized seizures. The Journal of neuroscience, 25(35):8077–8084, 2005.
[6] D. C. Shields, J. W. Leiphart, D. L. McArthur, P. M. Vespa, M. L. Quyen, J. Martinerie, and J. R.
Soss. Cortical synchrony changes detected by scalp electrode electroencephalograph as traumatic
brain injury patients emerge from coma. Surgical neurology, 67(4):354–359, 2007.
[7] J. L. Perez Velazquez. Finding simplicity in complexity: general principles of biological and nonbiological organization. Journal of biological physics, 35(3):209–221, 2009.
[8] H. J. Morowitz. Some order-disorder considerations in living systems. The bulletin of mathematical
biophysics, 17(2):81–86, 1955.
[9] E. Smith. Thermodynamics of natural selection i: Energy flow and the limits on organization.
Journal of theoretical biology, 252(2):185–197, 2008.
[10] J.J. Wright and D.T.J. Liley. Dynamics of the brain at global and microscopic scales: Neural
networks and the eeg. Behavioral and Brain Sciences, 19(02):285–295, 1996.
[11] P. L. Nunez. Toward a quantitative description of large-scale neocortical dynamic function and
eeg. Behavioral and Brain Sciences, 23(03):371–398, 2000.
[12] J. L. Perez Velazquez, Garcia Dominguez L., V. Nenadovic, and R. A. Wennberg. Experimental observation of increased fluctuations in an order parameter before epochs of extended brain
synchronization. Journal of biological physics, 37(1):141–152, 2011.
[13] R. Wennberg. Intracranial cortical localization of the human k-complex. Clinical Neurophysiology,
121(8):1176–1186, 2010.
[14] R. Guevara, J. L. Pérez Velazquez, V. Nenadovic, R. Wennberg, G Senjanović, and L. G.
Dominguez. Phase synchronization measurements using electroencephalographic recordings. Neuroinformatics, 3(4):301–313, 2005.
11
[15] J. Kayser and C. E. Tenke. Principal components analysis of laplacian waveforms as a generic
method for identifying erp generator patterns: I. evaluation with auditory oddball tasks. Clinical
neurophysiology, 117(2):348–368, 2006.
[16] A. N. Kolmogorov. Three approaches to the quantitative definition of information. Problems of
information transmission, 1(1):1–7, 1965.
[17] A. Lempel and J. Ziv. On the complexity of finite sequences. Information Theory, IEEE Transactions on, 22(1):75–81, 1976.
[18] G. Tkacik, T. Mora, O. Marre, D. Amodei, II Berry, J. Michael, and W. Bialek. Thermodynamics
for a network of neurons: Signatures of criticality. arXiv preprint arXiv:1407.5946, 2014.
[19] V Nenadovic, J. S. Hutchison, L. G. Dominguez, H. Otsubo, M. P. Gray, R Sharma, J. Belkas, and
J. L. Perez Velazquez. Fluctuations in cortical synchronization in pediatric traumatic brain injury.
Journal of neurotrauma, 25(6):615–627, 2008.
[20] G. Tononi, G. M. Edelman, and O. Sporns. Complexity and coherency: integrating information in
the brain. Trends in cognitive sciences, 2(12):474–484, 1998.
[21] J. L. Perez Velazquez, R. G. Erra, R. Wennberg, and L. G. Dominguez. Correlations of cellular
activities in the nervous system: physiological and methodological considerations. In Coordinated
Activity in the Brain, pages 1–24. Springer, 2009.
[22] J. L. Perez Velazquez and M. Frantseva. The Brain-Behavior Continuum: The Subtle Transition
Between Sanity and Insanity. World Scientific, 2011.
[23] G Dumermuth and D Lehmann. Eeg power and coherence during non-rem and rem phases in
humans in all-night sleep analyses. European neurology, 20(6):429–434, 1981.
[24] K. Wang, M. L. Steyn-Ross, D.A. Steyn-Ross, M. T. Wilson, and J. W. Sleigh. Eeg slow-wave
coherence changes in propofol-induced general anesthesia: experiment and theory. Frontiers in
systems neuroscience, 8, 2014.
[25] Hermann Haken. Information and self-organization: A macroscopic approach to complex systems.
Springer Science & Business Media, 2006.
[26] H. J Morowitz. Energy flow in biology; biological organization as a problem in thermal physics.
1968.
[27] A Buehlmann and G Deco. Optimal information transfer in the cortex through synchronization.
PLoS Comput Biol, 6(9):e1000934, 2010.
[28] W. Bialek, F. Rieke, R de Ruyter van Steveninck, and D Warland. Spikes: exploring the neural
code. MIT. Roddey, JC, Girish, B., & Miller, JP (2000). Assessing the performance of neural
encoding models in the presence of noise. Journal of Computational Neuroscience, 8(95):112, 1997.
[29] M. Gell-Mann. Consciousness, reduction, and emergence. Annals of the New York Academy of
Sciences, 929(1):41–49, 2001.
12
[30] I. Prigogine. Introduction to thermodynamics of irreversible processes. New York: Interscience,
1967, 3rd ed., 1, 1967.
[31] B. J. Baars. A cognitive theory of consciousness. Cambridge University Press, 1993.
[32] G. Tononi. An information integration theory of consciousness. BMC neuroscience, 5(1):42, 2004.
[33] V. Vuksanović and P. Hövel. Dynamic changes in network synchrony reveal resting-state functional
networks. Chaos: An Interdisciplinary Journal of Nonlinear Science, 25(2):023116, 2015.
[34] D. W. Zhou, D. D. Mowrey, P. Tang, and Y. Xu. Percolation model of sensory transmission and
loss of consciousness under general anesthesia. Physical review letters, 115(10):108103, 2015.
[35] A. A Fingelkurts, A. A. Fingelkurts, S. Bagnato, C. Boccagni, and G. Galardi. Do we need a
theory-based assessment of consciousness in the field of disorders of consciousness? Frontiers in
human neuroscience, 8:402, 2014.
[36] D. R. Chialvo. Emergent complex neural dynamics. Nature physics, 6(10):744–750, 2010.
13
Subject #1
Subject #2
Subject #3
Subject #4
State
Baseline
Seizure
Baseline
Seizure
Baseline
Seizure
Baseline
Seizure
L-Z complexity
0.7
0.2
0.61
0.39
0.86
0.71
0.61
0.61
Table 1: Values of Lempel-Ziv (L-Z) complexity derived from the string of connections (details in Methods) in conscious (baseline) and unconscious (seizure) states, in four patients. Note lower complexity
during seizures in patients # 1 − 3; patient # 4 (Figure 1D) did not have fully generalised seizures.
Subject #1
Subject #2
Subject #3
Subject #4
Subject #5
State
Alert eyes open
SWS 2
SWS 3-4
REM
Alert eyes open
Alert eyes close
SWS 3-4
Alert eyes open
SWS 2
SWS 3-4
REM
Alert eyes open
Alert eyes closed
SWS 2
SWS 3
REM
Alert eyes open
SWS 1
SWS 2
SWS 3-4
REM
iEEG L-Z complexity
0.81
0.42
0.018
0.73
0.94
0.94
0.33
N/A
N/A
N/A
N/A
0.88
0.55
0.57
0.05
0.6
N/A
N/A
N/A
N/A
N/A
scalp L-Z complexity
1.01
1.0
0.0
0.96
1.06
0.85
0.22
1.07
1.07
1.07
0.97
1.0
1.0
9.8
0.0
1.06
0.97
1.08
1.04
0.8
1.12
Table 2: Values of Lempel-Ziv (L-Z) complexity derived from the string of connections in different sleep
stages. When both recordings were obtained from a subject, both iEEG and scalp EEG data were
analysed (subjects # 3 and # 5 did not have iEEG recordings). The L-Z complexity is consistently
lower, regardless of recording methodology, in the deepest sleep stage (SWS 3-4). These results parallel
those of entropy estimations shown in figure 2
14
Base@ 12 Hz
S (entropy)
7000
Bas
Sz @ 12 Hz
z
e 5H
A
7000
Sz # 2
5000
5000
3000
3000
@
Sz
5 Hz
1000
1000
2000
4000
6000
8000
Sz # 1
2000
10000
C
25 10 sec Sz
S (entropy)
B
Base #2
Base #1
20
7000
4000
6000
8000
D
Sz
Baseline
10000
5000
Baseline
15
Sz
10
5
3000
1000
5
10
15
20
25
30
35
2000
4000
6000
8000
10000
Number of coupled channels
Figure 1: Graphs representing the entropy of the number of pairwise configurations of signals in epileptic
patients during conscious (baseline) and unconscious (generalised seizure) states. A, derived from MEG
recordings in a patient with primary generalised epilepsy, shows entropy associated with a normal alert
period (baseline, ‘Base’) and a generalised absence seizure (‘Sz’), estimated from synchrony values at two
central frequencies (defined in Methods) of 5 and 12 Hz. The curve in this and other graphs here and in
Figure 2 represents the possible entropy values of all possible numbers of pairwise combinations, yielding
an inverted U or, for very large numbers, a Gaussian. Note that here as well as in all generalised seizures
analysed, the entropy values associated with alert, baseline conditions were closer to the maximum (top
of the curve) than those associated with the seizures. B, entropy values of two seizures and their
corresponding baseline (‘Base’) activity (computed using a time period of 30-40 minutes before the
ictus) in a patient with secondary (symptomatic) generalised epilepsy (MEG recordings). C, derived
from iEEG recordings in a patient with temporal lobe epilepsy, shows the entropy during the alert
state (‘baseline’), during the initial 10 seconds of the seizure when the patient was still responsive and
alert (‘10 sec Sz’), and during the rest of the seizure when it became generalised and the patient was
unresponsive (‘Sz’). Note that when the ictus has not yet generalised, the entropy is similar to that of
normal alertness. D, another example of a non-generalised seizure in a patient with frontal lobe epilepsy
(MEG recordings).
15
800
awake
S (entropy)
700
awake
A
REM
250
awake
Sws2
200
600
B
REM
Sws2
500
REM
150
Sws2
400
300
Sws3-4
100
4 Hz
50
200
100
0
* 8 Hz
200
Sws3-4
400
600
800
1000
Sws3-4
1200
50
250
S (entropy)
400
350
300
250
200
C
awake awake
REM
Sws2
200
Eyecl
100
150
200
250
awake
REM
Sws2
300
D
Eyecl
150
REM
Sws2
Sws3-4
100
Eyecl
150
100
4 Hz
50
* 8 Hz
100
50
Sws3-4
Sws3-4
200
300
400
500
600
50
100
150
200
250
300
Number of coupled channels
Figure 2: Same graph types as in Figure 1, using sleep recordings. In each subject, data samples
were of 2-4 minutes duration during wakefulness with eyes open (‘awake’) or eyes closed (‘Eyecl’), and
sleep stages slow-wave 2 (‘Sws2’), slow-wave 3-4 (‘Sws3-4’) and rapid eye movement (‘REM’). A, results
derived from iEEG recordings in a subject investigated with bilateral frontal and temporal electrodes
and simultaneous scalp EEG. Entropy estimated from synchrony values at two central frequencies of 4
and 8 Hz. As occurred in the patient recordings shown in Figure 1, the baseline, alert state (in this case
labelled ‘awake’) is closer to the top of the curve, having greater entropy. The deepest sleep stage, slow
wave 3-4 (‘sws3-4’), has the lowest entropy. B, same subject but using the scalp EEG recordings for the
calculations, showing similar trend (evaluated at central frequency of 4 Hz). C, results derived from a
different subject investigated with right frontal electrodes and simultaneous scalp EEG, with synchrony
evaluated at two central frequencies of 4 and 8 Hz using the iEEG signals. Note that the eyes closed
(‘Eyecl’) condition has lower entropy than that of the normal alert state with open eyes. Depending on
the frequency of analysis, the entropy in ‘Eyecl’ falls toward the left or right side of the curve; e.g., at
8 Hz, because the synchrony is higher (more coupled channels) due to alpha waves at 8-10 Hz and the
entropy is reduced due to fewer combinations of connections, as occurs similarly during seizures (Figure
16 showing similar results to those obtained with
1). D, same subject but using the scalp EEG signals,
iEEG (evaluated at central frequency of 4 Hz).
S (entropy)
Sz
6000
4000
2000
16
32
48
64
80
96
112
Time (sec)
Figure 3: Time course of the entropy of the number of configurations of connected MEG signals before,
during and after a generalised absence seizure. MEG signal from one channel is shown at top, the ictus
(‘Sz’) occurs towards the end of the 2 minute recording. Notice the drop in entropy during the seizure.
17
Entropy (S)
conscious/alert
or number of
configurations
high S Þ
number
microstates
unconscious
low S
number networks “connected”
Figure 4: Proposed general scheme of the relation between global brain connectivity and behavioural
states. Normal alertness resides at the top of the curve representing the number of configurations of
connections the system can adopt, or the associated entropy. The maximisation of the configurations
(microstates) provides the variability in brain activity needed for normal sensorimotor action. Abnormal, or unconscious states, are located farther from the top, and are characterised by either large or
small number of “connected” networks therefore exhibiting lower number of microstates (hence lower
entropy) that are not optimal for sensorimotor processing.
18 |
Tononi%&%Koch%*%Consciousness%
%
%
%
Consciousness:**
Here,*There*but*Not*Everywhere*
by*
1
2
Giulio*Tononi *and*Christof*Koch *
%
1
Department%of%Psychiatry,%University%of%Wisconsin,%Madison%WI%USA%
2
Allen%Institute%for%Brain%Science,%Seattle,%WA%USA%
%
May%26,%2014%
Tononi%&%Koch%–%Consciousness%*%2%
Abstract%
The%science%of%consciousness%has%made%great%strides%by%focusing%on%
the% behavioral% and% neuronal% correlates% of% experience.% However,%
correlates%are%not%enough%if%we%are%to%understand%even%basic%facts,%for%
example,% why% the% cerebral% cortex% gives% rise% to% consciousness% but% the%
cerebellum%does%not,%though%it%has%even%more%neurons%and%appears%to%
be%just%as%complicated.%Moreover,%correlates%are%of%little%help%in%many%
instances% where% we% would% like% to% know% if% consciousness% is% present:%
patients% with% a% few% remaining% islands% of% functioning% cortex,% pre*term%
infants,% non*mammalian% species,% and% machines% that% are% rapidly%
outperforming% people% at% driving,% recognizing% faces% and% objects,% and%
answering% difficult% questions.% To% address% these% issues,% we% need% not%
only%more%data,%but%also%a%theory%of%consciousness%–%one%that%says%what%
experience%is%and%what%type%of%physical%systems%can%have%it.%Integrated%
Information%Theory%(IIT)%does%so%by%starting%from%conscious%experience%
itself% via% five% phenomenological% axioms% of% existence,% composition,%
information,% integration,% and% exclusion.% From% these% it% derives% five%
postulates% about% the% properties% required% of% physical% mechanisms% to%
support% consciousness.% The% theory% provides% a% principled% account% of%
both%the%quantity%and%the%quality%of%an%individual%experience%(a%quale),%
and% a% calculus% to% evaluate% whether% or% not% a% particular% system% of%
mechanisms% is% conscious% and% of% what.% Moreover,% IIT% can% explain% a%
range% of% clinical% and% laboratory% findings,% makes% a% number% of% testable%
predictions,% and% extrapolates% to% a% number% of% unusual% conditions.% The%
theory%vindicates%some%intuitions%often%associated%with%panpsychism%*%
that% consciousness% is% an% intrinsic,% fundamental% property,% is% graded,% is%
common% among% biological% organisms,% and% even% some% very% simple%
systems%may%have%some%of%it.%However,%unlike%panpsychism,%IIT%implies%
that%not%everything%is%conscious,%for%example%aggregates%such%as%heaps%
of%sand,%a%group%of%individuals%or%feed*forward%networks.%Also,%in%sharp%
contrast% with% widespread% functionalist% beliefs,% IIT% implies% that% digital%
computers,%even%if%their%behavior%were%to%be%functionally%equivalent%to%
ours,% and% even% if% they% were% to% run% faithful% simulations% of% the% human%
brain,%would%experience%next%to%nothing.%
Consciousness:**
Here,*There*and*Everywhere?*
I%know%I%am%conscious:%I%am%seeing,%hearing,%feeling%something%here,%
inside%my%own%head.%But%is%consciousness%–%subjective%experience%*%also%
there,¬%only%in%other%people’s%heads,%but%also%in%the%head%of%animals?%
And%perhaps%everywhere,%pervading%the%cosmos,%as%in%old%panpsychist%
traditions%and%in%the%Beatles’%song?%While%these%kinds%of%questions%may%
seem% scientifically% inappropriate,% we% argue% below% that% they% can% be%
approached% in% a% principled% and% testable% manner.% Moreover,% obtaining%
an% answer% is% urgent,% not% only% because% of% difficult% clinical% cases% and% in%
our%interactions%with%other%species,%but%also%because%of%the%advent%of%
machines%that%are%getting%closer%to%passing%the%Turing%test%–%computers%
programmed%to%perform%many%tasks%as%well%as%us,%and%often%far%better%
than%some%brain*damaged%patients.%%%
Here*
That%I%am%conscious,%here%and%now,%is%the%one%fact%I%am%absolutely%
certain%of%–%all%the%rest%is%conjecture.%This%is,%of%course,%the%gist%of%the%
most%famous%deduction%in%Western%thought,%Descartes’%je&pense,&donc&
je& suis.% Everything% else% –% what% I% think% I% know% about% my% body,% about%
other% people,% dogs,% trees,% mountains,% and% stars,% is% inferential.% It% is% a%
reasonable% inference,% corroborated% first% by% the% beliefs% of% my% fellow%
humans% and% then% by% the% intersubjective% methods% of% science.% Yet%
consciousness% itself% *% the% central% fact% of% existence% –% still% demands% a%
rational%explanation.%
The% past% two% centuries% of% clinical% and% laboratory% studies% have%
revealed%an%intimate%relationship%between%the%conscious%mind%and%the%
brain,% but% the% exact% nature% of% this% relationship% remains% elusive.% Why%
does%the%brain%generate%consciousness%but%not%the%liver%or%the%heart,%as%
previous% cultures% believed?% Why% certain% parts% of% the% brain% and% not%
others?% Why% is% consciousness% lost% in% some% stages% of% sleep?% Why% does%
red%feel%like%red%and%not%like%the%sound%of%a%violin?%Is%consciousness%just%
an% epiphenomenon,% or% does% it% have% a% function?% Can% computers% be%
conscious?% Could% a% system% behave% like% us% and% yet% be% devoid% of%
consciousness%–%a%zombie?%Such%questions%seem%to%resist%the%empirical,%
reductionist%approach%that%has%been%so%successful%for%other%aspects%of%
the%natural%world.%Nevertheless,%thanks%to%experimental%and%theoretical%
progress% in% the% past% decades% (Koch% 2004,% Baars% and% Gage% 2010,%
Dehaene%and%Changeux%2011,%Boly,%Baars%et%al.%2013)%(Laureys,%Tononi%
et% al.% 2009),% we% are% finally% in% a% better% position% to% understand% which%
systems%under%which%conditions%can%give%rise%to%consciousness.%That%is,%
the% study% of% consciousness% is% becoming% a% science.% In% doing% so,% it% is%
leaving% behind% the% defeatist% dictum% of% the% physiologist% Emil% du% Bois*
Reymond,% ignoramus& et& ignorabimus% (we% don’t% know% and% never% will),%
espousing% instead% the% upbeat% maxim% of% the% mathematician% David%
Hilbert,%Wir&müssen&wissen&–&wir&werden&wissen%(we%must%know%and%we%
will).%
There*
We% usually% grant% consciousness% to% others% *% of% the% same% kind% we%
experience% in% the% privacy% of% our% own% mind% –% if% they% can% tell% us% what%
they%feel,%or%if%they%look%and%behave%more%or%less%like%us.%However,%we%
become% less% and% less% confident% in% attributing% consciousness% to% people%
who% cannot% talk% about% their% experiences,% such% as% infants% and% young%
children,%or%severely%brain%injured%patients.%Many%assume%that%animals%
closely% related% to% homo& sapiens% –% apes% and% other% primates% –% are%
conscious,%though%presumably%less%than%we%are,%based%on%the%similarity%
of%their%behavior%and%their%brain.%But%should%we%attribute%experience%to%
i
all%mammals, %to%all%vertebrates,%to%invertebrates%such%as%cephalopods%
and% bees,% or% even% to% all% multi*cellular% animals?% What% about% cultured%
organoids%that%mimic%the%cellular%organization%of%the%developing%human%
Tononi%&%Koch%–%Consciousness%*%2%
brain% (Lancaster,% Renner% et% al.% 2013)?% And% finally,% what% about% the%
sophisticated% machines% that% run% software% designed% to% substitute% for%
conscious%humans%in%many%complicated%tasks?%
Behavioral*correlates*of*consciousness*(BCC)*and*reportability*
Traditionally,% we% assess% consciousness% by% observing% behavior% (Fig.%
1A).%If%someone%is%awake%and%acts%meaningfully,%we%have%little%doubt%he%
is% conscious.% If% he% speaks,% and% especially% if% he% can% answer% questions%
about%what%he%is%conscious%of,%we%are%fully%confident.%In%the%laboratory,%
the% ability% to% report% one’s% experiences% has% become% the% gold% standard%
for% judging% the% presence% of% consciousness.% Reportability% is% often%
reduced%to%a%binary%forced%choice,%in%which%the%subject%only%pushes%one%
of%two%buttons%for%“seen”%vs.%“not%seen,”%or%“angry”%vs.%“happy%face”.%
One% can% also% ask% how% confident% one% is% that% one% has% seen% something.%
These% kinds% of% meta*cognitive% reports% can% also% be% obtained% from%
trained%monkeys%or%other%animals,%with%so%many%similarities%to%our%own%
reports% that% we% have% little% doubt% as% to% the% presence% of% consciousness%
(Cowey%and%Stoerig%1995).%%
But% behavior% can% be% misleading:% a% person% may% walk% and% speak% in%
her%sleep,%yet%it%is%quite%dubious%whether%she%is%experiencing%anything.%
Or%a%person%can%be%asleep,%immobile,%silent,%and%unresponsive,%yet%she%
may% be% dreaming% *% vividly% conscious% of% an% imaginary% environment.% In%
such% cases,% reportability% can% be% used% as% retrospective% evidence% of%
consciousness,% by% waking% up% the% sleeper% to% obtain% a% “dream% report.”%
However,% reportability,% too,% can% be% problematic.% Since% we% obviously%
experience%things%in%dreams%whether%or%not%we%are%woken%up%to%report%
them,% we% should% accept% the% possibility% that% in% certain% situations%
consciousness% can% be% present% even% if% it% cannot% be% reported% (Lamme%
2006,% Block% 2007).% Moreover,% insisting% on% reportability% elevates%
language%to%a%king*maker%role,%which%makes%inferring%consciousness%in%
ii
non*verbal% infants,% preterm% babies,% fetuses,% or% animals% problematic. %
Clearly,% if% we% want% to% understand% what% is% really% going% on,% we% must%
investigate%the%brain%mechanisms%that%underlie%consciousness.%
Neural*correlates*of*consciousness*(NCC)*
The%NCC%have%been%defined%as%the%minimal%neural%mechanisms%that%
are%jointly%sufficient%for%any%one%conscious%percept%(Fig.%1B;%(Koch%and%
Crick% 1990,% Crick% and% Koch% 1998,% Koch% and% Crick% 2000).% Every%
experience% will% have% associated% NCC:% one% for% seeing% a% red% patch,%
another%one%for%hearing%a%high%C.%Inducing%the%NCC%by%manipulating%the%
relevant% neuronal% populations% via% magnetic% stimulation,% optogenetics%
or%other%means%will%give%rise%to%the%associated%conscious%percept,%and%
interfering%with%the%NCC%by%disabling%the%underlying%neural%circuits%will%
eliminate%the%percept.%%%
The% NCC% are% assessed% at% first% by% determining% which% aspects% of%
neural%function%change%depending%on%whether%a%subject%is%conscious%or%
not,% as% established% using% behavioral% reports.% This% can% be% done% by%
considering% a% global% change% in% the% state% of% consciousness,% as% when%
awareness%is%lost%during%deep%sleep%or%general%anesthesia%(Tononi%and%
Laureys%2009).%%Or%it%can%be%done%by%considering%changes%in%a%particular%
content%of%consciousness,%as%when%a%subject’s%awareness%of%a%particular%
stimulus% is% experimentally% manipulated% (“seen”% vs.% “not% seen”).% In%
optimally% controlled% experiments,% the% stimulus% and% the% behavioral%
report% (such% as% a% button% press)% are% kept% constant% while% the% subject%
sometimes%sees%the%percept%and%sometimes%does%not%(Logothetis%1998,%
Dehaene% and% Changeux% 2011,% Mudrik% and% Koch% 2013).% Once% a%
particular% NCC% has% been% sufficiently% validated,% it% can% be% used% to%
extrapolate% to% situations% where% reports% are% not% available.% Both%
functional%brain%imaging%in%magnetic%scanners%as%well%as%large*scale%EEG%
recordings%from%outside%the%skull%have%been%put%to%use%to%track%down%
the%footprints%of%consciousness%in%the%brain%of%healthy%adult%observers.%
Popular% candidates% include% strong% activation% of% higher*order% fronto*
parietal% cortices% (Fig.% 1B),% high*frequency% electrical% activity% in% the%
gamma%range%(35*80%Hz),%and%the%occurrence%of%an%EEG%event%known%as%
the% P300% wave% (Tononi% and% Laureys% 2009,% Dehaene% and% Changeux%
2011).% However,% there% is% still% no% consensus% on% whether% any% of% these%
signs% can% be% treated% as% reliable% “signatures”% of% consciousness.% In%
particular,% there% can% be% consciousness% without% frontal% cortex%
involvement% (Mataró,% Jurado% et% al.% 2001,% Goldberg,% Harel% et% al.% 2006,%
Frässle,% Sommer% et% al.% 2014),% gamma% activity% without%
consciousness(Engel%and%Singer%2001),%such%as%during%anesthesia%(Imas,%
Ropella% et% al.% 2005,% Murphy,% Bruno% et% al.% 2011),% and% consciousness%
without% a% frontal% P300,% for% example% during% dreaming% sleep% (Cote,%
Etienne%et%al.%2001,%Takahara,%Nittono%et%al.%2002).%Moreover,%it%is%likely%
that%many%of%the%signatures%proposed%as%possible%NCC%may%actually%be%
correlates% of% neural% activity% that% is% needed% leading% up% to% a% conscious%
percept%(Aru,%Axmacher%et%al.%2012,%Pitts,%Martínez%et%al.%2012),%or%for%
giving% a% report% following% a% conscious% percept% (Goldberg,% Harel% et% al.%
2006,% Pitts,% Martínez% et% al.% 2012,% Frässle,% Sommer% et% al.% 2014),% rather%
than% for% having% an% experience.% Finally,% NCC% obtained% in% healthy% adults%
may%or%may%not%apply%to%brain%damaged%patients,%to%infants,%to%animals%
very%different%from%us,%and%certainly%not%to%machines%(Fig.%2).%
Patients*and*infants*
Patients% with% widespread% cortical% or% thalamic% damage% pose% a%
poignant% challenge.% Emergency% room% personnel% quickly% evaluate% the%
severity% of% a% head% injury% behaviorally% by% assigning% a% number% to% a%
patient’s% auditory,% visual,% verbal% and% motor% functions% as% well% as%
communication%and%arousal%level.%Various%NCC,%such%as%the%presence%of%
a% P300% wave% in% response% to% a% non*standard% stimulus,% are% increasingly%
being%used%to%complement%the%behavioral%assessment%and%occasionally%
modify% the% diagnosis.% In% some% cases,% NCC% can% be% decisive.% Thus,% if% a%
patient% who% lies% mute% and% immobile% can,% however,% respond% to%
commands% by% appropriately% activating% certain% brain% areas,% it% is% fair% to%
conclude% that% she% is% conscious% (Owen,% Coleman% et% al.% 2006).% Yet% even%
the% NCC% may% be% ambiguous.% For% example,% the% P300% wave% is% absent% in%
many% minimally% conscious% patients% and% even% in% some% brain*damaged%
patients%who%can%communicate%(King,%Sitt%et%al.%2013).%And%what%should%
one% make% of% patients% in% whom,% amidst% widespread% destruction% and%
inactivity,% one% or% a% few% isolated% cortical% areas% may% show% signs% of%
metabolic% activation% and% of% electrophysiological% “markers”% of%
consciousness% (Schiff,% Ribary% et% al.% 2002)?% Is% an% island% of% functioning%
brain% tissue% sufficient% for% generating% a% limited% kind% of% awareness,%
maybe%just%awareness%of%sound%or%of%pain?%In%other%words,%“what%is%it%
like”% to% be% a% brain% island,% if% it% feels% like% anything% at% all?% And% how% big%
must%the%island%be%to%qualify?%*
By% the% same% token,% what% is% it% like% to% be% a% newborn% baby% with% an%
immature% brain% and% restricted% connectivity% among% cortical% structures%
(Lagercrantz% and% Changeux% 2009)?% Again,% considering% NCC% can% be%
helpful:% for% example,% a% wave% resembling% the% P300% wave% has% been%
reported%in%6%to%16%months%old%infants,%although%weaker,%more%variable%
and%delayed%than%in%adults%(Kouider,%Stahlhut%et%al.%2013).%But%does%this%
mean% that% newborn% and% pre*term% babies% or% even% fetuses% experience%
nothing%because%they%do%not%show%a%P300?%
Animals*
The% problem% becomes% even% more% acute% when% turning% to% other%
species.% The% study% of% consciousness% in% nature% has% been% hindered% for%
centuries%by%a%strong%belief%in%human%exceptionalism.%Yet%the%range%and%
complexity%of%animal%behavior%has%laid%rest%to%this%belief,%at%least%among%
biologists.%This%is%particularly%true%for%mammals.%In%psychophysical%tasks%
involving% simple% button% presses,% trained% macaque% monkeys% act% very%
similar% to% human% volunteers,% including% signaling% when% they% don’t% see%
anything% (Cowey% and% Stoerig% 1995).% Visual% recognition% of% self,% meta*
cognition% (knowing% one’s% mind),% theory% of% mind,% empathy% and% long*
range% planning% have% all% been% demonstrated% in% primates,% rodents% and%
other%orders%(Smith,%Couchman%et%al.).%%
Tononi%&%Koch%–%Consciousness%*%3%
It% is% also% difficult% to% find% anything% exceptional% about% the% human%
brain% (Hawrylycz,% Lein% et% al.% 2012).% Its% constitutive% genes,% synapses,%
neurons% and% other% cells% are% similar% to% those% found% in% many% other%
species.% Even% its% size% is% not% so% special,% as% elephants,% dolphins% and%
whales% have% even% bigger% brains% (Herculano*Houzel% 2012).% Only% an%
expert%neuroanatomist,%armed%with%a%microscope,%can%tell%a%grain*sized%
piece% of% neocortex% of% a% mouse% from% that% of% a% monkey% or% a% human.%
Biologists% emphasize% this% structural% and% behavioral% continuity% by%
distinguishing%between%non:human&and%human&animals%(Huxley%1872).%
Given%this%continuity,%it%seems%unjustified%to%claim%that%only%one%species%
has% consciousness% while% everybody% else% is% devoid% of% experience,% is% a%
zombie.% It% is% far% more% likely% that% all% mammals% have% at% least% some%
conscious%experiences,%can%hear%the%sounds%and%see%the%sights%of%life.%%%
As%we%consider%species%that%are%progressively%further%removed%from%
homo& sapiens% in% evolutionary% and% neuronal% terms,% the% case% for%
consciousness%becomes%more%difficult%to%make.%Two%observations,%one%
relating%to%complexity%of%behavior%and%another%one%to%complexity%of%the%
underlying% nervous% system,% are% critical.% First,% ravens,% crows,% magpies,%
parrots% and% other% birds,% tuna,% coelacanths% and% other% fish,% octopuses%
and% other% cephalopods,% bees% and% other% members% of% the% vast% class% of%
insects% are% all% capable% of% sophisticated,% learnt,% non*stereotyped%
behaviors%that%we%associate%with%consciousness%if%carried%out%by%people%
(Dawkins% 1998,% Griffin% 2001,% Edelman% and% Seth% 2009).% Darwin% himself%
set%out%"to%learn%how%far%the%worms%acted%consciously”%and%concluded%
that% there% was% no% absolute% threshold% between% “lower”% and% “higher”%
animals,% including% humans,% which% would% assign% higher% mental% powers%
to% one% but% not% to% the% other% (Darwin% 1887).% Second,% the% nervous%
systems% of% any% of% these% creatures% display% a% vast% and% ill*understood%
complexity.% The% bee% contains% about% 800,000% nerve% cells% whose%
morphological% and% electrical% heterogeneity% rivals% that% of% any%
neocortical% neuron.% These% cells% are% assembled% in% highly% nonlinear%
feedback% circuits% whose% density% is% up% to% ten% times% higher% than% that% of%
neocortex% (Koch% and% Laurent% 1999).% Thus,% it% is% unlikely% that% neural%
signatures% of% consciousness% that% have% some% validity% in% humans% and%
other%mammals%will%apply%to%invertebrates.%%
On%the%other%hand,%the%lessons%learnt%from%studying%the%behavioral%
and% neuronal% correlates% of% consciousness% in% people% must% make% us%
cautious% about% inferring% its% presence% in% creatures% very% different% from%
us,% no% matter% how% sophisticated% their% behavior% and% how% complicated%
their% brain.% Humans% can% perform% seemingly% sophisticated% behaviors% *%
recognizing% whether% a% scene% is% congruous% or% incongruous,% controlling%
the% size,% orientation,% and% strength% of% how% one’s% finger% should% grip% an%
object,% doing% simple% arithmetic,% detecting% the% meaning% of% words,% or%
rapid%keyboard%typing%–%in%a%seemingly%non*conscious%manner%(Hassin,%
Uleman% et% al.% 2005,% Kouider% and% Dehaene% 2007,% Berlin% 2011,% Mudrik,%
Breska% et% al.% 2011,% Sklar,% Levy% et% al.% 2012,% Hassin% 2013).% When% a% bee%
navigates% a% maze,% does% it% do% so% like% when% we% consciously% deliberate%
whether% to% turn% right% or% left,% or% rather% like% when% we% type% on% a%
keyboard?% Similarly,% consider% that% an% extraordinarily% complicated%
neuronal%structure%in%our%brain,%the%cerebellum,%home%to%69%of%the%86%
billion% nerve% cells% that% make% up% the% human% brain% (Herculano*Houzel%
2012),%apparently%has%little%to%do%with%consciousness.%Patients%that%lose%
part% or% nearly% all% of% their% cerebellum% due% to% stroke% or% other% trauma%
show% ataxia,% slurred% speech,% and% unsteady% gait% (Lemon% and% Edgley%
2010)%but%do%not%complain%of%a%no%loss%or%diminution%of%consciousness.%
Is% the% bee’s% brain% central% complex% more% like% the% cerebellum% or% more%
like%the%cerebral%cortex%with%respect%to%experience?%Thus,%the%extent%to%
which% non*mammalian% species% share% with% us% the% gift% of% subjective%
iii
experience%remains%hard%to%fathom. %
Machines*
Difficulties% in% attributing% sentience% become% even% more% apparent%
when% considering% digital% computers.% These% have% a% radically% different%
architecture% and% provenance% than% biological% creatures% shaped% by%
natural%selection.%Due%to%the%relentless%decrease%in%transistor%size%over%
the% past% 50% years% and% the% concomitant% exponential% increase% in%
computational% power% and% memory% capacity,% present*day% computers%
executing% appropriate% algorithms% outperform% us% in% many% tasks% that%
were%thought%to%be%the%sole%prerogative%of%the%human%mind.%Prominent%
examples% include% IBM’s% Deep% Blue% that% beat% the% reigning% chess% world%
master%in%1997;%another%IBM%computer,%Watson,%capable%of%answering%
questions%posed%in%spoken%English%that%won%the%quiz%show%Jeopardy&in%
2011;% smart% phones% that% answer% questions% by% speech;% Google’s%
driverless% cars% that% have% logged% more% than% half% a% million% km% on% open%
roads;%and%machine%vision%algorithms%for%face%detection%in%security%and%
commercial% applications% (Kurzweil% 2012).% People% playing% chess,%
supplying% a% meaningful% answer% to% a% given% question,% driving% a% car% or%
picking%out%a%face%are%assumed%to%be%conscious.%But%should%we%say%the%
same%for%these%digital%creatures?%%
Integrated*Information*Theory*(IIT)*
Clearly,% as% we% move% away% from% people,% BCC% and% NCC% become%
progressively% less% helpful% to% establish% the% presence% of% consciousness.%
Also,%even%in%the%normal%human%brain,%we%need%to%understand%why%and%
how% certain% structures% give% rise% to% experience% (the% cerebral% cortex),%
while%others%do%not%(the%cerebellum),%and%why%they%do%so%under%certain%
conditions%(wake,%dreams)%and%not%others%(deep%sleep,%seizures).%Some%
philosophers%have%claimed%that%the%problem%of%explaining%how%matter%
can% give% rise% to% consciousness% may% forever% elude% us,% dubbing% it% the%
Hard&Problem%(Chalmers%1996,%Block,%Flanagan%et%al.%1997,%Shear%1999).%
Indeed,% as% long% as% one% starts% from% the% brain% and% asks% how% it% could%
possibly%give%rise%to%experience%–%in%effect%trying%to%“distill”%mind%out%of%
matter%(Mcginn%2000),%the%problem&may%indeed%remain%not%only%hard,%
but% outright% impossible% to% solve.% But% things% may% be% less% hard% if% one%
takes% the% opposite% approach:% start% from% consciousness% itself,% by%
identifying%its%essential%properties,%and%then%ask%what%kinds%of%physical%
mechanisms% could% possibly% account% for% them.% This% is% the% approach%
taken% by% Integrated% Information% Theory% (IIT)% (Tononi% 2004,% Tononi%
2008,% Tononi% 2012),% an% evolving% framework% that% provides% a% principled%
account% for% what% it% takes% for% consciousness% to% arise,% offers% a%
parsimonious% explanation% for% the% empirical% evidence,% makes% testable%
iv
predictions,%and%permits%inferences%and%extrapolations. %
Axioms:*Essential*phenomenological*properties*of*consciousness*
Taking% consciousness% as% primary,% IIT% first% identifies% axioms% of%
experience%(Fig.%3,%left),%then%derives%a%set%of%corresponding%postulates%
(Fig.% 3,% right)% about% the% nature% of% the% underlying% physical% mechanisms%
(Tononi% 2012,% Oizumi,% Albantakis% et% al.% 2014).% The% axioms% of% IIT% are%
truths%about%our%own%experience%that%are%assumed%to%be%self*evident.%
They% include% existence,% composition,% information,% integration,% and%
exclusion.%
Existence.%Consciousness%exists:%my%experience%just%is%–%indeed,%that%
my%experience%here%and%now%exists,%is%the%only%fact%I%can%be%absolutely%
sure% of.% Moreover,% my% experience% exists% from% its% own% intrinsic%
perspective,%independent%of%external%observers.%
Composition.% Consciousness% is% structured:% each% experience% is%
composed% of% many% phenomenological& distinctions.% Within% the% same%
experience,% I% can% see,% for% example,% left% and% right,% red% and% blue,% a%
triangle%and%a%square,%a%red%triangle%on%the%left,%and%so%on.%
Information.% Consciousness% is% differentiated:% at% any% moment% in%
time,% each% experience% is& the& specific& way& it& is& (a% specific% set% of%
phenomenological%distinctions),%differing%in%its%specific%way%from%other%
possible%experiences.%Thus,%an%experience%of%pure%darkness%and%silence%
is%what%it%is%because,%among%other%things,%it%is%not%filled%with%light%and%
sound,% color% and% shapes,% and% so% on.% Consider% all% the% frames% of% all%
possible% movies:% these% are% but% a% small% subset% of% all% possible%
experiences.%
Tononi%&%Koch%–%Consciousness%*%4%
Integration.%Consciousness%is%unified:%each%experience%is%irreducible&
to%non*interdependent%components.%Thus,%I%experience%a%whole%visual%
scene,%not%the%left%side%of%the%visual%field%independent%of%the%right%side%
(and% vice% versa).% For% example,% the% experience% of% seeing% the% word%
“HONEYMOON"%written%in%the%middle%of%a%blank%page%is%irreducible%to%
an% experience% of% seeing% “HONEY”% on% the% left% plus% the% experience% of%
seeing%“MOON”%on%the%right.%What%I%see%is%the%whole%“HONEYMOON.”%
Similarly,% seeing% a% red% triangle% is% irreducible% to% seeing% a% grey% triangle%
plus%the%disembodied%color%red.%
Exclusion.% Consciousness% is% singular,% in% content,% and% spatio*
temporal%grain:%there%is%no&superposition&of%multiple%experiences,%with%
less%or%more%content,%flowing%at%once%at%faster%or%slower%speeds.%Thus,%
in%addition%to%the%experience%I%have%right%now,%say,%of%being%in%my%room%
and% seeing% my% legs% on% the% bed,% there% are% no% further% superimposed%
experiences% with% either% less% content% –% say,% one% lacking% the% color% or%
another% one% lacking% the% left% side% of% the% visual% field% *% or% with% more%
content%*%say,%one%that%also%includes%awareness%of%the%alarm%bell%that%is%
ringing%but%I%am%not%hearing%it%(because%I%am%actually%in%the%middle%of%a%
dream).% Similarly,% my% experience% flows% at% a% particular% speed% –% each%
experience%encompassing%say%a%hundred%milliseconds%or%so%*%and%there%
are%no%superimposed%experiences%that%flow%at%faster%speeds%(say,%each%
experience% encompassing% just% one% microsecond),% or% at% slower% speeds%
(say,%each%experience%encompassing%an%entire%hour).%%
Postulates:* Properties* that* physical* mechanisms* must* have* to*
support*consciousness*
To% parallel% these% axioms% that% capture% the% essential% properties% of%
every% experience,% IIT% proposes% a% set% of% postulates% concerning% the%
requirements%that%must%be%satisfied%by%physical%systems%to%account%for%
experience%(Fig.%3,%right).%
Existence.%Experience%is%generated%by%a&system&of&mechanisms&in&a&
state:% To% exist% from% its% own% intrinsic& perspective,% independent% of%
external%observers,%a%system%must%have%cause:effect&power&upon%itself:%
its%mechanisms%must%be%able%to%“make%a%difference”%to%the%probability%
of%its%past*future%states%(Fig.%3,%Existence)%(Bateson%1972).%Cause*effect%
power% is% a% precondition% for% something% to% exist:% there% is% no% point% in%
assuming%that%something%exists%if%nothing%can%make%a%difference%to%it,%
v
or%if%it%cannot%make%a%difference%to%anything%(Alexander’s&dictum). %To%
pick% up% differences% and% make% a% difference,% physical% mechanisms% must%
have% two% or% more% internal% states,% inputs% that% can% influence% these%
states,% and% outputs% that% depend% on% these% states.% Examples% of% such%
mechanisms% include% neurons% and% logic% gates% made% of% transistors.%
Moreover,%to%generate%experience,%a%system%of%mechanisms%must%have%
cause*effect% power% within% itself,% i.e.% intrinsically,% independent% of%
vi
extrinsic%causes%and%effects. %%
Composition.% The% system% can% be% structured:% elementary%
mechanisms%can%be%composed&to%specify%various%“differences%that%make%
a% difference”% to% the% system% (affect% the% probability% of% its% past*future%
states).% Thus,% if% a% system% is% composed% of% elements% A,% B,% and% C% (Fig.% 3,%
Composition),%any%subset%of%elements,%including%A,%B,%C;%AB,%AC,%BC;%as%
well% as% the% entire% system,% ABC,% can% constitute% a% mechanism% having%
cause*effect% power.% Composition% thus% allows% for% elementary%
mechanisms% to% form% distinct% higher*order% mechanisms% (as% long% as% a%
higher*order%mechanism%has%causes%and%effects%that%cannot%be%reduced%
to%those%of%its%constituting%elementary%mechanism,%see%below).%
Information.% A% system% of% mechanisms% in% a% state% specifies% a%
differentiated%conceptual%structure:%each%structure%is%the&specific&way&it&
is&(a%specific%composition%of%concepts),%differing%in%its%specific%way%from%
other% possible% ones.% A% conceptual& structure& is% the% set% of% concepts%
specified% by% the% mechanisms% of% a% system% in% various% compositions.% A%
concept% is% how% each% mechanism% within% the% system% specifies% the%
probability%of%past*future%states%of%the%system%(cause:effect&repertoire).%
Consider%for%example,%within%the%system%ABC%(Fig.%3,%Information),%the%
mechanism%implemented%by%element%C,%an%XOR%gate%with%two%inputs%(A%
and%B)%and%two%outputs%(the%AND%gate%B%and%the%OR%gate%A).%If%C%is%OFF,%
its%cause%repertoire%specifies%that,%the%previous%time%step,%A%and%B%must%
have% been% either% in% the% state% ON,OFF% or% in% the% state% OFF,ON,% rather%
than%in%the%other%two%possible%states%(ON,ON;%OFF,OFF);%and%its%effect%
repertoire%specifies%that%the%next%time%step%B%will%have%to%be%OFF,%rather%
than% ON.% Thus,% the% cause*effect% repertoire% specifies% the% cause*effect%
power% of% a% mechanism% in% a% particular% state,% and% the% conceptual%
structure%specifies%the%cause*effect%power%of%a%system%of%mechanisms.%
Note%that%the%notion%of%information%in%IIT%differs%substantially%from%that%
in%communication%theory%or%in%common%language,%but%it%is%faithful%to%its%
etymology:% information% refers% to% how% a% system% of% mechanisms% in% a%
state,%through%its%cause*effect%power,%gives%rise%to%a%form%(“informs”%a%
conceptual%structure)%in%the%space%of%possibilities.%
Integration.% The% conceptual% structure% specified% by% the% system% is%
unified:% it% is% irreducible% to% that% specified% by% non*interdependent% sub*
systems.%Irreducibility%can%be%measured%as%integrated%information%(big%
phi%or%Φ,%a%non*negative%number),%which%quantifies%to%what%extent%the%
conceptual%structure%specified%by%a%system’s%mechanisms%changes%if%the%
system%is%partitioned%(cut%or%reduced)%along%its%minimum%partition%(the%
one%that%makes%the%least%difference).%For%example,%the%system%in%Fig.%3%
is% integrated,% because% partitioning% it% through% its% weakest% link% destroys%
several% cause*effect% repertoires% and% changes% others% (compare% the%
conceptual% structure% under% “information”% and% under% “integration”% in%
Fig.%3).%By%contrast,%if%a%system%of%mechanisms%can%be%divided%into%two%
sub*systems% and% the% partition% makes% no% difference% to% the% associated%
conceptual%structure,%then%the%whole%is%reducible%to%those%parts.%Being%
irreducible% is% another% precondition% for% existence% having% to% do% with%
causation:%there%is%no%point%in%assuming%that%the%whole%exists%in%and%of%
itself,% if% it% has% no% causal% power% above% and% beyond% its% parts.% This%
postulate% also% applies% to% individual% mechanisms:% a% subset% of% elements%
can% contribute% a% specific% aspect% of% experience% only% if% its% cause*effect%
repertoire%within%the%system%is%irreducible%by%the%minimum%partition%of%
the%mechanism%(small%phi%or%ϕ).%
Exclusion.% The% conceptual% structure% specified% by% the% system% must%
max
be%singular:%%the%one%that%is%maximally&irreducible&(Φ ).%That%is,%there%
can% be% no& superposition& of% conceptual% structures% over% elements% and%
spatio*temporal% grain.% The% system% of% mechanisms% that% generates% a%
vii
maximally& irreducible% conceptual& structure% is% called% a% complex. % For%
example,% in% Fig.% 3% (Exclusion),% there% cannot% exist% complex% ABC,% and%
complex% AB,% AC,% and% BC% simultaneously,% because% complexes% cannot%
overlap.% Again,% exclusion% makes% sense% with% respect% to% causation,%
because% it% avoids% multiple% causation:% if% a% mechanism% specifies% a%
particular% cause*effect% repertoire% within% one% complex,% it% cannot%
additionally% specify% an% overlapping% cause*effect% repertoire% as% part% of%
other,%overlapping%complexes,%because%we%would%be%counting%multiple%
times%the%difference%that%mechanism%makes.%This%postulate%also%applies%
to%individual%mechanisms%in%a%complex:%a%subset%of%elements%in%a%state%
can% contribute% only% one% aspect% to% experience% *% the% cause*effect%
max
repertoire%within%the%system%that%is%maximally%irreducible%(ϕ ),%called%
a% core% concept.% Finally,% this% postulate% also% applies% to% spatio*temporal%
grain.%For%example,%a%mechanism%cannot%have%effects%at%a%fine%temporal%
grain,% and% additional% effects% at% a% coarser% grain,% otherwise% causal%
exclusion% would% be% violated.% On% the% other% hand,% if% the% effects% at% a%
coarser%grain%are%more%irreducible%than%those%at%a%finer%grain,%then%the%
coarser%grain%of%causation%excludes%the%finer%one%(Hoel,%Albantakis%et%al.%
viii
2013).% %
The* central* identity:* Experience* as* a* maximally* irreducible*
conceptual*structure*
Altogether,% the% elements% of% a% complex% in% a% state,% combined% in%
irreducible%mechanisms%that%specify%concepts%within%the%complex,%form%
a%maximally&irreducible&conceptual&structure,%also%known%as%a%quale.%A%
quale%exists%in%a%space%called%qualia%space,%whose%axes%are%given%by%all%
possible%past%and%future%states%of%the%complex.%Every%concept%is%a%point%
Tononi%&%Koch%–%Consciousness%*%5%
in%the%space,%which%specifies%the%probability%of%past%and%future%states%of%
the% system,% given% the% state% of% a% particular% mechanism% within% it.% The%
constellation% of% all% concepts% together% constitutes% the% “shape”% of% the%
quale%(Fig%4).%This%leads%to%the%central%identity%of%IIT,%which%states%that%a%
conscious%experience%is%identical%to%a%maximally%irreducible%conceptual%
structure:% the% quale% completely% specifies% both% its% quality% (the% set% of%
concepts%in%the%quale%is%the%content%of%consciousness)%and%its%quantity%
(the% value% of% irreducibility% Φmax% of% the% quale% is% the% level% of%
consciousness).%If%a%system%has%Φmax%=%0,%what%it%can%do%as%a%system%is%
completely%reducible%to%what%its%parts%can%do,%so%it%cannot%lay%claim%to%
existing.%If%Φmax%is%large,%the%system%can%do%much%more%than%its%parts,%
so%it%exits%in%and%of%itself.%More%generally,%the%larger%Φmax,%the%more%a%
system% can% lay% claim% to% existing,% in% a% fuller% sense% than% lower% Φmax%
systems.% Just% how& much% the% system% exists% as% such% is% measured% by% its%
Φmax% value,% while% which& way% it% exists% is% specified% by% its% concepts%
(irreducible%cause*effect%repertoires).%According%to%IIT,%the%quantity%and%
quality% of% an% experience% are% an% intrinsic% property% of% a% complex% of%
mechanisms% in% a% state% –% the% property% of% shaping% the% space% of%
possibilities% (past% and% future% states)% in% a% particular% way,% just% as% it% is%
ix
intrinsic%to%a%mass%to%bend%space*time%around%it. %
At% any% given% time,% then,% consciousness% is% supported% by% a% set% of%
neuronal%mechanisms%forming%a%complex%of%high%Φmax%that%specifies%a%
maximally% irreducible% conceptual% structure.% The% particular% set% of%
neurons%that%form%the%main%complex%in%our%brain%may%change%to%some%
extent%from%moment%to%moment,%as%well%as%their%state%–%which%neurons%
are% firing% and% which% are% not.% For% example,% let% us% assume% that% while% I%
watch%a%scene%of%a%movie%containing%the%actress%Jennifer%Aniston%(JA),%
the% main% complex% in% my% brain% is% made% up% of% neurons% within% certain%
x
parts% of% the% cerebral% cortex. % Every% neuron% within% the% complex%
necessarily% shapes% the% probability% of% possible% past% states% (causes)% and%
future% states% (effects)% of% the% complex,% depending% on% how% it% is%
connected%to%the%other%neurons%and%on%its%state%(say%firing%strongly%for%
100% msec).% Thus,% a% neuron% firing% strongly% in% a% certain% visual% area% may%
specify% as% more% likely% those% past% states% of% the% complex% that% are%
compatible% with% the% invariant% concept% “J.A.’s% face,”% as% well% as% certain%
appropriate% future% states.% Another% neuron% firing% strongly% in% another%
visual% area% may% specify% that% there% likely% was% a% horizontal% edge% in% a%
certain% position% of% the% visual% field,% and% so% on.% Yet% other% neurons% that%
are%part%of%the%complex%but%are%silent%may%specify%that%certain%past%(and%
future)%states%are%unlikely%to%have%occurred%(or%to%occur),%such%as%those%
having%to%do%with%the%invariant%concepts%“book,”%“square”,%and%so%on.%
Moreover,%combinations%of%neurons%may%specify%higher*order%concepts,%
such%as%“J.A.%with%a%red%hat%sitting%on%the%couch%on%the%left.”%Note%that%
all% the% concepts% are% generated% by% elements% of% the% complex,% specify%
cause*effect% repertoires% over% elements% of% the% complex,% and% acquire%
meaning%intrinsically,%in%relation%to%the%other%concepts%in%the%quale,%and%
not% by% referring% to% external% inputs% (J.A.% is% just% as% meaningful% when%
daydreaming%about%her,%or%in%a%dream)%(Oizumi,%Albantakis%et%al.%2014).%
In% principle,% then,% the% postulates% of% IIT% offer% a% way% to% analyze% any%
system% of% mechanisms% in% a% particular% state% and% determine% whether% it%
xi
constitutes% a% complex,% over% which% spatial% and% temporal% grain, % and%
which% quale% it% generates.% Furthermore,% while% in% practice% it% is% not%
possible% to% determine% the% quale% and% Φmax% precisely% for% a% realistic%
system,%it%is%already%possible%to%employ%IIT%for%prediction,%explanation,%
and%extrapolation.%
Predictions*
A%straightforward%experimental%prediction%of%IIT%is%that%the%loss%and%
recovery% of% consciousness% should% be% associated% with% the% breakdown%
and% recovery% of% the% brain’s% capacity% for% information% integration.% This%
prediction%has%been%confirmed%using%transcranial%magnetic%stimulation%
(TMS)% in% combination% with% high*density% electroencephalography% in%
conditions%characterized%by%loss%of%consciousness%(Massimini,%Ferrarelli%
et% al.% 2005,% Casali,% Gosseries% et% al.% 2013).% These% include% deep% sleep,%
general% anesthesia% obtained% with% several% different% agents,% and% brain%
damaged% patients% (vegetative,% minimally% conscious,% emerging% from%
minimal% consciousness,% locked*in).% If% a% subject% is% conscious% when% the%
cerebral% cortex% is% probed% with% a% pulse% of% current% induced% by% the% TMS%
coil%from%outside%the%skull,%the%cortex%responds%with%a%complex%pattern%
of%reverberating%activations%and%deactivations%that%is%both%widespread%
(integrated)% and% differentiated% in% time% and% space% (information% rich)%
(Massimini,% Ferrarelli% et% al.% 2005).% By% contrast,% when% consciousness%
fades,%the%response%of%the%cortex%becomes%local%(loss%of%integration)%or%
global% but% stereotypical% (loss% of% information).% The% perturbational&
complexity& index% (PCI),% a% scalar% measure% of% the% compressibility% of% the%
EEG% response% to% TMS% inspired% by% IIT,% decreases% distinctly% in% all% the%
different%conditions%of%loss%of%consciousness%and,%critical%for%a%clinically%
useful% device,% so% far% has% done% so% in% each% individual% healthy% subject% or%
neurological%patient%tested%(Casali,%Gosseries%et%al.%2013).%
Some%examples%of%counterintuitive%predictions%of%IIT%are%also%worth%
pointing% out.% One% is% that% a% system% such% as% the% cerebral% cortex% may%
generate% experience% even% if% it% is% nearly% silent,% a% state% that% is% perhaps%
approximated%through%certain%meditative%practices%that%aim%at%reaching%
“pure"% awareness% without% content% (Sullivan% 1995,% Blackmore% 2011).%
This% corollary% of% IIT% contrasts% with% the% common% assumption% that%
neurons% only% contribute% to% consciousness% if% they% are% active% in% such% a%
way% that% they% “signal"% or% “broadcast"% the% information% they% represent%
and% “ignite"% fronto*parietal% networks% (Dehaene% and% Changeux% 2011).%
That% silent% neurons% can% contribute% to% consciousness% is% because,% in% IIT,%
information%is%not%in%the%message%that%is%broadcast%by%an%element,%but%
in%the%shape%of%the%conceptual%structure%that%is%specified%by%a%complex.%
Inactive% elements% of% a% complex% can% affect% the% probability% of% possible%
past%and%future%states%as%much%as%active%ones%can%(the%dog%that%did%not%
bark% in% the% famous% Sherlock% Holmes% story).% Conversely,% if% the% same%
neurons% were% not% silent,% but% pharmacologically% or% optogenetically%
turned% off% (inactivated),% they% would% cease% to% contribute% to%
consciousness:%even%though%their%actual%state%is%the%same,%they%would%
lack%a%cause*effect%repertoire%and%thus%would%not%be%able%to%affect%the%
probability%of%possible%past%and%future%states%of%the%complex.%%
Another%prediction%is%that,%if%the%efficacy%of%the%200%million%callosal%
fibers%through%which%the%two%cerebral%hemispheres%communicate%with%
each% other% were% reduced% progressively,% there% would% be% a% moment% at%
which,%for%a%minimal%change%in%the%traffic%of%neural%impulses%across%the%
callosum,% there% would% be% an% all*or*none% change% in% consciousness:%
experience%would%go%from%being%a%single%one%to%suddenly%splitting%into%
two% separate% experiencing% minds% (one% linguistically% dominant),% as% we%
know% to% be% the% case% with% split*brain% patients% (Gazzaniga% 2005).% This%
would%be%the%point%at%which%Φmax%for%the%whole%brain%would%fall%below%
the% value% of% Φmax% for% the% left% and% for% the% right% hemisphere% taken% by%
themselves.%
Explanations*
IIT% offers% a% coherent,% principled% account% for% many% disparate% facts%
about% the% NCC.% For% example,% why% is% consciousness% generated% by% the%
cerebral%cortex%(or%at%least%some%parts%of%it),%but%not%by%the%cerebellum,%
despite%the%latter%having%even%more%neurons?%Why%does%consciousness%
fade% early% in% sleep,% although% the% brain% remains% active?% Why% is% it% lost%
during% generalized% seizures,% when% neural% activity% is% intense% and%
synchronous?% Why% is% there% no% direct% contribution% to% consciousness%
from% neural% activity% within% sensory% pathways% (the% retina)% and% motor%
pathways%(the%motoneurons%in%the%spinal%cord),%or%within%neural%circuits%
looping%out%of%the%cortex%into%subcortical%structures%and%back,%despite%
their%manifest%ability%to%influence%the%content%of%experience?%
Tononi%&%Koch%–%Consciousness%*%6%
These%and%other%well*known%facts%find%a%parsimonious%explanation%
based% on% the% postulates% of% IIT.% Thus,% a% prominent% feature% of% the%
cerebral%cortex,%responsible%for%the%content%of%consciousness,%is%that%it%
is% comprised% of% elements% that% are% functionally% specialized% and% at% the%
same% time% can% interact% rapidly% and% effectively.% This% is% the% kind% of%
organization% that% yields% a% comparatively% high% value% of% Φmax.% Instead,%
the% cerebellum% is% composed% of% small% sheet*like% modules% that% process%
inputs%and%produce%outputs%largely%independent%of%each%other%(Cohen%
1998,% Bower% 2002).% Simulations% also% show% that% input% and% output%
pathways,% while% capable% of% affecting% the% main% complex% and% being%
affected%by%it,%can%remain%excluded%from%it,%because%they%are%not%part%
of% a% local% maximum% of% integrated% information.% The% same% applies% to%
loops%that%may%exit%the%main%complex%and%reenter%it.%Other%simulations%
show%that%Φmax% is%low%when%the%effective%connectivity%among%a%set%of%
elements% is% weak% or% is% organized% in% homogeneous% manner.% Indeed,% as%
was% mentioned% above,% when% consciousness% fades% during% deep% slow%
wave% sleep% or% in% certain% states% of% general% anesthesia,% the% interactions%
among% different% cortical% regions% become% weaker% and% highly%
stereotypical,%as%they%do%during%generalized%epileptic%seizures.%
Extrapolations*
Finally,%the%more%the%postulates%of%IIT%are%validated%in%situations%in%
which% we% are% reasonably% confident% about% if% and% how% consciousness%
changes,% the% more% we% can% use% the% theory% to% extrapolate% and% make%
inferences% about% situations% where% we% are% less% confident% –% brain*
damaged% patients,% newborn% babies,% alien% animals,% complicated%
machines,%and%other%far*fetched%scenarios,%as%we%shall%consider%next.%
Everywhere?*
In%the%“Canticle%of%the%Creatures,”%Saint%Francis%addressed%animals,%
flowers,%and%even%stones%as%if%endowed%with%soul%(psyche),%and%praised%
God% for% all% His% creatures:% mother% earth,% brother% sun,% sister% moon,% the%
stars,% the% air,% water,% and% fire.% And% he% was% not% alone.% Some% of% the%
brightest% minds% in% the% West% embraced% some% form% of% the% ancient%
philosophical% doctrine% of% panpsychism,% starting% with% the% Presocratics%
and% Plato.% The% Renaissance% philosophers% Patrizi,% Bruno,% Telesio,% and%
Campanella%took%the%position%that%matter%and%soul%are%one%substance.%
Later,% Spinoza,% Leibniz,% Schopenhauer% and,% closer% to% modern% times,%
James,% Whitehead,% Russell,% and% Teilhard% de% Chardin% espoused%
panpsychist% notions% (Skrbina% 2009,% Chalmers% 2013).% Strawson% (2006)%
(Strawson% and% Freeman% 2006)% is% the% best*known% contemporary%
defender% of% panpsychism.% Eastern% traditions,% such% as% Buddhism,% have%
always%emphasized%the%continuity%of%consciousness%across%creatures.%%
Materialism,% or% its% modern% offspring,% physicalism,% has% profited%
immensely% from% Galileo’s% pragmatic% stance% of% removing% subjectivity%
(mind)%from%nature%in%order%to%describe%and%understand%it%objectively.%%
But%it%has%done%so%at%the%cost%of%failing%to%deal%with%the%central%aspect%
of%reality%–%experience%itself.%Unlike%idealism,%which%does%away%with%the%
physical%world,%or%dualism,%which%accepts%both%in%an%uneasy%marriage,%
panpsychism% is% elegantly% unitary:% there% is% only% one% substance,% all% the%
way%up%from%the%smallest%entities%to%human%consciousness%and%maybe%
to%the%World%Soul%(anima&mundi).%But%panpsychism’s%beauty%has%been%
singularly%barren.%Besides%claiming%that%matter%and%mind%are%one%thing,%
it% has% little% constructive% to% say% and% offers% no% positive% laws% explaining%
how%the%mind%is%organized%and%works.%%
IIT%was%not%developed%with%panpsychism%in%mind%(sic).%However,%in%
line%with%the%central%intuitions%of%panpsychism,%IIT%treats%consciousness%
as% an% intrinsic,% fundamental% property% of% reality.% IIT% also% implies% that%
consciousness%is%graded,%that%it%is%likely%widespread%among%animals,%and%
that% it% can% be% found% in% small% amounts% even% in% certain% simple% systems.%
Unlike% panpsychism,% however,% IIT% clearly% implies% that% consciousness% is%
not% ubiquitous.% Moreover,% IIT% offers% a% solution% to% several% of% the%
conceptual% obstacles% that% panpsychists% never% properly% resolved,% like%
the% problem% of% aggregates% (or% combination% problem,% (James% 1890,%
Chalmers% 2013)).% It% also% explains% why% consciousness% is% adaptive,% and%
can%account%for%its%quality.%
Consciousness*is*an*intrinsic*property*
The% axioms% and% postulates% of% IIT% say% that% consciousness% is% an%
intrinsic,% observer*independent% property% of% certain% mechanisms% in% a%
state%*%how%they%shape%the%space%of%possibilities%in%their%past%and%their%
future.% An% analogy% is% mass,% which% can% be% defined% by% how% it% curves%
space*time%around%it.%Like%mass,%experience%cannot%be%reduced%to%more%
elementary% properties.% And% like% some% elementary% particles% have% mass%
or% charge% and% others% do% not,% and% if% they% have% it,% they% have% it% in% a%
particular% way% (positive% or% negative% charge),% so% for% experience:% some%
entities%have%it,%while%others%do%not,%and%if%they%have%it,%they%have%it%in%a%
certain% way.% Except% that% in% the% case% of% experience% the% entities% having%
the% property% are% not% elementary% particles,% but% complexes% of%
mechanisms,% and% experience% comes% not% in% two,% but% in% a% trillion%
varieties.% Thus,% for% IIT,% we% happen% to% find% ourselves% in% a% universe% in%
which%experience%is%one%of%the%elementary%properties%of%certain%causal%
systems.% Asking% why% this% should% be% so% or% whether% we% can% imagine% a%
universe% in% which% this% is% not% true% is% akin% to% asking% why% our% universe%
obeys% the% laws% of% quantum% mechanics% or% whether% we% can% image% a%
universe% in% which% quantum% mechanics% does% not% hold.% In% this% general%
sense,%at%least,%IIT%is%not%at%odds%with%panpsychism.%
Consciousness*comes*in*various*qualities**
Unfortunately,% panpsychism% is% mute% when% it% comes% to% explaining%
the%way%any%one%conscious%experience%feels%*%why%the%perception%of%red%
feels% different% from% that% of% blue% and% why% colors% are% experienced% as%
different%from%tones.%Instead,%at%least%in%principle,%IIT%says%exactly%what%
determines%the%quality%of%an%experience%–%what%makes%it%the%particular%
way% it% is:% an% experience% is% identical% to% the% maximally% irreducible%
conceptual% structure% (the% quale)% generated% by% a% main% complex,% in% our%
case%one%made%up%by%a%set%of%neurons%in%a%particular%state.%This%is%like%a%
shape,% a% constellation% in% a% fantastically% high*dimensional% qualia% space,%
which% specifies% how% the% neurons% of% the% main% complex,% in% various%
combinations,%give%form%to%the%space%of%possible%past%and%future%states%
of%the%complex%(Fig.%4).%Different%experiences%–%every%different%scene%in%
a%movie%or%in%a%dream%*%correspond%to%different%shapes.%Except%that%this%
shape,% unlike% the% shapes% of% objects,% is% the% shape% within,% the% shape% of%
the% experience% itself.% It% is% the% voice% in% the% head,% the% light% inside% the%
skull.%It%is%everything%I%will%ever%know%of%the%world.%It%is,%ultimately,%my%
only%reality.%
Consciousness*is*adaptive*
IIT%takes%no%position%on%the%function%of%experience%as%such%*%similar%
to% physics% not% having% anything% to% say% about% the% function% of% mass% or%
charge.% However,% by% identifying% consciousness% with% integrated%
information,% IIT% can% account% for% why% it% evolved,% another% aspect% about%
which%panpsychism%has%nothing%to%say.%In%general,%a%brain%having%a%high%
capacity%for%information%integration%will%better%match%an%environment%
with% a% complex% causal% structure% varying% across% multiple% time% scales,%
than% a% network% made% of% many% modules% that% are% informationally%
encapsulated.% Indeed,% artificial% life% simulations% (“animats”)% of% simple%
Braitenberg*like%vehicles%that%have%to%traverse%mazes%and%whose%brains%
evolve,% over% 60,000% generations,% by% natural% selection,% show% a%
monotonic% relationship% between% (simulated)% integrated% information%
and% adaptation% (Edlund,% Chaumont% et% al.% 2011,% Joshi,% Tononi% et% al.%
2013).% That% is,% the% more% adapted% individual% animats% are% to% their%
environment,% the% higher% the% integrated% information% of% the% main%
complex%in%their%brain.%Thus,%evolution%by%natural%selection%gives%rise%to%
organisms%with%high%Φmax%because%they%are%more%adept%at%exploiting%
regularities%in%the%environment%than%their%less%integrated%competitors.%
Tononi%&%Koch%–%Consciousness%*%7%
Consciousness*is*graded*
IIT%does%side%with%the%panpsychist%intuition%that%consciousness%may%
be%present%across%the%animal%kingdom,%and%even%beyond,%but%in%varying%
degrees.%Everything%else%being%equal,%integrated%information,%and%with%
it% the% richness% of% experience,% is% likely% to% increase% as% the% number% of%
neurons% and% the% abundance% of% their% interconnections% grow,% although%
sheer% number% of% neurons% is% not% a% guarantee,% as% shown% by% the%
cerebellum.% It% is% also% likely% that% consciousness% is% graded% across% the%
lifetime%of%any%one%organism.%In%us%it%becomes%richer%as%we%grow%from%a%
baby% to% an% adult% whose% brain% has% fully% matured% and% becomes% more%
functionally%specialized.%It%can%also%wax%and%wane%when%we%are%highly%
alert%or%drowsy,%intoxicated%by%drugs%or%alcohol,%or%become%demented%
in% old% age.% This% is% illustrated% schematically% in% Fig.% 5A,% where% a% set% of%
“cortical”% areas% are% integrated% into% a% main% complex% of% “high”% Φmax%
when% the% inter*areal% connections% are% strong,% undergo% a% reduction% in%
Φmax% when% connection% strength% is% reduced% by% neuromodulatory%
changes% (simulated% as% an% increase% in% noise),% and% finally% breaks% down%
into%small%complexes%of%low%Φmax.%%
A%counterintuitive%corollary%of%IIT%is%that%even%circuits%as%simple%as%a%
single%photodiode%hooked%up%to%a%1*bit%memory%can%have%a%modicum%of%
experience% (Oizumi,% Albantakis% et% al.% 2014)% (see% also% Fig.% 5A,% right%
panel).% It% feels% like% something% to% be% this% circuit;% it% is% conscious% of% one%
thing% –% the% distinction% between% this% and% not% this% (not% of% light% or% dark,%
because%that%requires%many%more%concepts).%This%strongly%violates%our%
intuitions% about% consciousness.% But% consider% that% normal% matter% at% *
272.15o% C,% one% degree% above% absolute% zero,% still% contains% some% heat%
that,% in% theory,% could% be% extracted.% However,% in% practice% its%
temperature%is%as%cold%as%it%gets.%Similarly,%there%may%well%be%a%practical%
threshold%for%Φmax%below%which%people%do%not%report%feeling%much%of%
anything,% but% this% does% not% mean% that% consciousness% has% reached% its%
absolute% zero.% Indeed,% when% we% fall% into% a% deep,% dreamless% sleep% and%
don’t% report% any% experience% upon% being% awoken,% our% sleeping% brain% is%
still%not%fully%disconnected%and%some%complex%within%it%will%likely%have%a%
Φmax% value% greater% than% zero,% yet% that% may% not% amount% to% much%
compared%to%that%of%our%rich,%everyday%experience.%
Aggregates*are*not*conscious*
“Take%a%sentence%of%a%dozen%words,%and%take%twelve%men%and%tell%to%
each%one%word.%Then%stand%the%men%in%a%row%or%jam%them%in%a%bunch,%
and%let%each%think%of%his%word%as%intently%as%he%will;%nowhere%will%there%
be%a%consciousness%of%the%whole%sentence.”%This%is%how%William%James%
illustrated%the%combination%problem%of%panpsychism%(James%1890).%%Or%
take%John%Searle:%“Consciousness%cannot%spread%over%the%universe%like%a%
thin% veneer% of% jam;% there% has% to% be% a% point% where% my% consciousness%
ends% and% yours% begins”% (Searle% 2013).% Indeed,% if% consciousness% is%
everywhere,%why%should%it%not%animate%the%United%States%of%America?%
IIT% deals% squarely% with% this% problem% by% stating% that% only% maxima% of%
integrated%information%count.%Consider%two%people%talking:%within%each%
brain,% there% will% be% a% main% complex% –% a% set% of% neurons% that% form% a%
maximally% irreducible% whole% with% definite% borders% and% a% high% value% of%
Φmax.% Now% let% the% two% speak% together.% They% will% now% form% a% system%
that%is%also%irreducible%(Φ%is%greater%than%zero)%due%to%their%interactions.%
However,% it% is% not% maximally% irreducible,% since% its% value% of% integrated%
information% will% be% much% less% than% that% of% each% of% the% two% main%
complexes% it% contains.% According% to% IIT,% there% should% indeed% be% two%
separate%experiences,%but%no%superordinate%conscious%entity%that%is%the%
union% of% the% two.% In% other% words,% there% is% nothing% it*is*like*to*be% two%
xii
people,% let% alone% the% 300% plus% million% citizens% making% up% the% USA. %
Again,%this%point%can%be%exemplified%schematically%by%the%system%of%Fig.%
5A,% right% panel.% While% the% five% small% complexes% do% interact,% forming% a%
larger% integrated% system,% the% larger% system% is% not% a% complex:% by% the%
exclusion% postulate,% only% the% five% smaller% complexes% exists,% since% they%
are% local% maxima% of% integrated% information% (Φmax% =% 0.19),% while% the%
larger%system%is%not%a%complex%(Φ%=%0.03).%Worse,%a%dumb%thing%with%no%
distinguishable%states,%say%a%grain%of%sand%for%the%sake%of%the%argument,%
has%no%experience%whatsoever.%Heaping%a%large%number%of%such%zero*Φ%
systems%on%top%of%each%other%would%not%increase%their%Φ%to%a%non*zero%
value;%it%does%not%feel%like%anything%to%be%a%sand%dune.%Aggregates%have%
no%consciousness.%
Complicated*systems*can*be*unconscious*
A% second% class% of% zero*Φ% systems% are% purely% feed*forward%
computational%networks%in%which%one%layer%feeds%the%next%one%without%
any% recurrent% connections.% According% to% IIT,% a% feed*forward% network%
does%not%have%a%cause%repertoire%within%the%system%itself,%since%its%input%
is% imposed% from% outside% the% system,% nor% does% it% have% an% effect%
repertoire,% since% its% output% does% not% feed% back% to% any% element% within%
the% network.% Yet% feed*forward% networks,% such% as% the% those% used% in%
deep%learning,%perform%plenty%of%useful%computational%functions,%such%
as% finding% faces% or% cats% in% images% (Le,% Ranzato% et% al.% 2011),% labeling%
images,% reading% zip% codes% and% detecting% credit% card% fraud.% From% the%
point% of% IIT,% such% networks% are% zombies,% carrying% out% tasks%
unconsciously%(Koch%and%Crick%2001).%
This% has% a% rather% startling% consequence.% Consider% that% any% neural%
network% with% feedback% circuits% can% be% mapped% onto% a% purely% feed*
forward% network% in% such% a% manner% that% the% latter% approximates% its%
input*output% relationships% (for% computations% bounded% by% a% maximal%
time*step;% (Hornik,% Stinchcombe% et% al.% 1989).% That% is,% for% the% same%
inputs,% the% two% networks% will% yield% the% same% output% (in% general,% the%
equivalent% feed*forward% network% will% have% many% more% nodes% and%
connection% than% the% feedback% network).% Therefore,% a% purely% feed*
forward% system% that% were% able% to% replicate% the% input*output% behavior%
of% the% human% brain% (under% the% limited% time*step% constraint),% while%
behaviorally%indistinguishable%from%us,%and%certainly%capable%of%passing%
the% Turing% test,% would% have% zero% Φ,% and% would% thus% be% a% “perfect”%
zombie.%A%simple%example%of%two%functionally%equivalent%systems,%one%
with% recurrent% connections% and% non*zero% Φ,% and% one% purely% feed*
forward%with%zero%Φ,%is%show%in%Fig.%5B%(Oizumi,%Albantakis%et%al.%2014).%%
In% people% and% organisms% that% evolved% through% natural% selection,%
their%input*output%behavior,%as%assessed%by%the%BCC,%offers%a%good%first%
guess% about% the% presence% of% consciousness.% As% demonstrated% by% the%
example% in% Fig.% 5B,% this% may% not% always% be% the% case% for% radically%
different% computational% architectures.% In% the% general% case,% and%
certainly%with%machines,%it%becomes%absolutely%essential%to%consider%the%
internal%circuitry%–%not%just%what%the%machine%does,%but%how%it%does%so.%
This% also% means% that% there% cannot% be% an% ultimate% Turing% Test% for%
consciousness% (although,% there% may% be% some% practical% CAPTCHA*like%
tests;%(Koch%and%Tononi%2011)).%According%to%many%functionalist%notions%
(Dennett% 1993),% if% a% machine% reproduces% our% input*output% behavior% in%
every%circumstance,%it%would%have%to%be%granted%consciousness%just%as%
much%as%us.%IIT%could%not%disagree%more.%
Simulations*of*conscious*neural*systems*can*be*unconscious*
Finally,%what%about%a%computer%whose%software%simulates%in%detail%
not% just% our% behavior,% but% even% the% biophysics% of% synapses,% axons,%
neurons% and% so% on,% of% the% relevant% portion% of% the% human% brain%
(Markram% 2006)?% Could% such% a% digital% simulacrum% ever% be% conscious?%
Functionalism% again% would% say% yes,% even% more% forcefully.% For% in% this%
case% all% the% relevant% interactions% within% our% brain,% not% just% our% input*
output%behavior,%would%have%been%replicated%faithfully.%Why%should%we%
not% grant% to% this% simulacrum% the% same% consciousness% we% grant% to% a%
fellow% human?% According% to% IIT,% however,% this% would% not% be% justified,%
for%the%simple%reason%that%the%brain%is%real,%but%a%simulation%of%a%brain%is%
virtual% (including,% sensu& stricto,& its% simulated% value% of% Φmax).% For% IIT,%
consciousness% is% an% intrinsic% property% of% certain% systems% of%
Tononi%&%Koch%–%Consciousness%*%8%
mechanisms,% one% that% requires% having% real% causal% power,% specifically%
the%power%of%shaping%the%space%of%possible%past%and%future%states%in%a%
maximally% irreducible% way.% In% the% same% way,% mass% is% an% intrinsic%
property%of%systems%of%particles,%a%property%that%has%real%causal%power,%
specifically%that%of%bending%space*time.%Therefore,%just%like%a%computer%
simulation%of%a%giant%star%will%not%bend%space*time%around%the%machine,%
xiii
a% simulation% of% our% conscious% brain% will% not% have% consciousness. % Of%
course,% the% physical% computer% that% is% running% the% simulation% is% just% as%
real% as% the% brain.% However,% according% to% the% principles% of% IIT,% one%
should% analyze% its% real% physical% components% *% identify% elements,% say%
transistors,% define% their% cause*effect% repertoires,% find% concepts,%
complexes,% and% determine% the% spatio*temporal% scale% at% which% Φ%
reaches%a%maximum.%In%that%case,%we%suspect%that%the%computer%would%
likely% not% form% a% large% complex% of% high% Φmax,% but% break% down% into%
many%mini*complexes%of%low%Φmax%(due%to%the%small%fan*in%and%fan*out%
of% digital% circuitry,% Fig.% 5C),% existing% at% the% very% fast% temporal% scale% of%
xiv
the%computer%clock. %
Conclusion*
In%summary,%there%are%some%aspects%of%IIT%that%definitely%do%not%fit%
with% panpsychism,% and% others% that% vindicate% some% of% its% intuitions.% In%
this% respect,% it% is% natural% to% consider% how% one% should% regard% some% of%
the% inferences% derived% from% IIT% for% which% it% is% hard% even% to% imagine% a%
direct%test%at%the%present%time.%Our%position%is%that,%as%is%often%the%case%
xv
in%science, %a%theory%is%first%tested%and%validated%in%situations%that%are%
close% to% ideal,% and% then% extrapolated% to% more% remote% cases.% Ideally,%
whether% consciousness% varies% with% integrated% information,% and% other%
predictions% of% IIT,% would% first% be% validated% here% –% on% my% own%
consciousness:% for% example,% does% Φmax,% collapse% when% I% undergo%
general%anesthesia%or%a%seizure,%or%when%I%fall%into%dreamless%sleep,%and%
return%to%high%values%when%I%dream?%Then%one%can%extrapolate%to%there,%
at% first% in% situations% involving% other% healthy% humans,% then% in% slightly%
more%difficult%cases,%say%monkeys%with%a%brain%similar%to%ours%who%are%
trained%to%give%reports%similar%to%ours.%Finally,%in%so%far%as%the%theory%has%
been%validated%and%has%shown%good%predictive%and%explanatory%power,%
one%can%try%and%extrapolate%to%everywhere,%unresponsive%patients%with%
just% a% small% “island”% of% functioning% brain% tissue,% newborn% babies,%
animals% very% different% from% us,% photodiodes,% machines,% and% computer%
simulations.% After% all,% often% in% science% the% best% we% can% do% is% to% draw%
inferences%about%unknown%instances%based%on%a%theory%that%works%well%
in% many% known% instances.% And% that% is% much% better% than% to% make%
arbitrary%claims%or%to%draw%no%inference%whatsoever.%
%
Acknowledgements*
%We% thank% Larissa% Albantakis,% Melanie% Boly,% Chiara% Cirelli,% Lice%
Ghilardi,% and% Marcello% Massimini,% for% their% many% contributions% to% the%
work%presented%here.%
Tononi%&%Koch%–%Consciousness%*%9%
*
Table*1.*Some*terms*used*in*Integrated*Information*Theory*(IIT)***
Axioms:% Self*evident% truths% about% consciousness.% The% only% truths%
that,%with%Descartes,%cannot%be%doubted%and%do%not%need%proof.%In%IIT%
3.0,% there% are% five% such% axioms% *% existence,% composition,% information,%
integration,%and%exclusion%(Fig.%3).%
Postulates:% Assumptions,% derived% from% axioms,% about% the% physical%
substrates% of% consciousness% (mechanisms% must% have% cause*effect%
power,%be%irreducible,%etc.),%which%can%be%formalized%and%form%the%basis%
of%the%mathematical%framework%of%IIT.%There%are%5%postulates,%matching%
the%five%axioms%(Fig.%3).%
Element:% An% elementary% component% of% a% system,% for% example% a%
neuron%in%the%brain,%or%a%logic%gate%in%a%computer.%
Mechanism:%Any%subset%of%elements%within%a%system,%including%the%
system%itself,%which%has%cause*effect%power%within%the%system.%
CauseOeffect* repertoire:% The% probability% distribution% of% potential%
past% and% future% states% of% a% system% as% informed% by% a% mechanism% in% its%
current%state.%
Integrated* information% (ϕ):% Information% that% is% generated% by% a%
mechanism% above% and% beyond% the% information% generated% by% its%
(minimal)% parts.% ϕ% measures% the% integration% or% irreducibility% of% the%
cause*effect%repertoire%specified%by%a%mechanism.%
MIP%(minimum%information%partition):%The%partition%that%makes%the%
least%difference%(in%other%words,%the%minimum%“difference”%partition).%
Complex:%A%set%of%elements%within%a%system%that%generates%a%local%
maximum%of%integrated%conceptual%information%Φmax.%Only%a%complex%
exists%as%an%entity%from%its%own%intrinsic%perspective.%%
Concept:% A% mechanism% and% the% maximally% irreducible% cause*effect%
repertoire% it% specifies,% with% its% associated% value% of% integrated%
information%ϕmax.%The%concept%expresses%the%cause*effect%power%of%a%
mechanism%within%a%complex.%
Conceptual*structure:%The%set%of%all%concepts%specified%by%a%system%
set% with% their% respective% ϕmax% values,% which% can% be% plotted% as% a%
constellation%of%concepts%in%concept%space.%
Concept*space:%Concept%space%is%a%high%dimensional%space%with%one%
axis% for% each% possible% past% and% future% state% of% the% system% in% which% a%
conceptual%structure%can%be%represented.%
Integrated* conceptual* information% (Φ):% Conceptual% information%
that% is% generated% by% a% system% above% and% beyond% the% conceptual%
information% generated% by% its% (minimal)% parts.% Φ% measures% the%
integration% or% irreducibility% of% a% constellation% of% concepts% (integration%
at%the%system%level),%%a%non*negative%number.%
Quale:%The%maximally%integrated%conceptual%structure%generated%by%
a%complex%in%a%state%(synonymous%with%constellation%in%qualia%space).%
Qualia* space:% If% a% set% of% elements% forms% a% complex,% its% concept%
space%is%called%qualia%space.%
Figures*
**Figure* 1:% Behavioral% (BCC)% and% neuronal% correlates% of%
consciousness% (NCC).% The% top% row% shows% a% schematic% diagram% of% a%
binocular% rivalry% experiment.% A% horizontal% red% grating% is% shown% to% the%
left% eye% and% a% vertical% green% grating% to% the% right% eye% throughout% the%
experiment% (courtesy% of% Naotsugu% Tsuchiya% and% Olivia% Carter).% The%
subject% does% not% see% a% juxtaposition% of% both% stimuli% but% experiences%
either%the%red%grating%or%the%green%one,%switching%back%and%forth%every%
few% seconds.% Even% if% the% stimuli% do% not% change,% what% one% sees%
consciously%does,%as%is%inferred%by%the%subject’s%report.%The%bottom%row%
shows%
the%
results%
of%
such%
an%
experiment%
using%
magnetoencephalography%(MEG),%in%which%the%red%grating%was%flashed%
at%one%frequency%and%the%green%one%at%another.%Yellow%indicates%areas%
of% the% cortex% (seen% from% the% top)% that% had% more% power% at% the%
frequency%of%the%red%grating%when%it%was%experienced%than%when%it%was%
not.% The% cyan% lines% indicate% increased% coherence% (synchronization)%
between%distant%brain%regions%associated%with%experiencing%the%grating%
(from%Tononi%et%al.,%1998).%%%
**Figure* 2:% Six% instances% in% which% it% becomes% progressively% more%
difficult% to% infer% the% existence% of% consciousness,% since% the% behavioral%
repertoire% and% the% underlying% mechanisms% (brains)% differ% substantially%
from%that%of%typical%persons%able%to%speak%about%their%experiences%(Fig.%
1).%
**Figure*3:%Axioms%and%Postulates%of%Integrated%Information%Theory%
(IIT).%The%illustration%is%a%colorized%version%of%Ernst%Mach’s%“View%from%
the%left%eye”%(Mach%1959).%See%also%the%mechanism%in%Fig.%4.%
**Figure* 4:% A% didactic% example% of% how% to% calculate% the% quality% and%
quantity%of%consciousness%given%a%mechanism%in%a%state.%On%the%upper%
left%are%three%gates%with%binary%states%(either%ON%or%OFF:%ABC%=%100;%see%
also%Fig.%3)%that%are%wired%together%as%shown.%An%analysis%based%on%the%
postulates%of%IIT%(Oizumi,%Albantakis%et%al.%2014)%reveals%that%the%system%
forms%an%irreducible%complex.%The%complex%in%its%present%state%specifies%
a% quale% *% a% maximally% irreducible% conceptual% structure.% The% quale% is%
presented% both% as% the% set% of% maximally% irreducible% cause*effect%
repertoires%(concepts)%specified%by%each%mechanism%(top)%and%as%a%2*D%
projection%in%which%each%concept%is%a%“star”%in%concept%space%(bottom).%
Concept% space% is% a% high*dimensional% (here,% 2x8% dimensions)% space% in%
which%each%axis%is%a%possible%past%(in%blue)%and%future%(in%green)%state%of%
the% complex,% and% the% position% along% the% axis% is% the% probability% of% that%
state.%Each%concept%is%a%star%whose%position%indicates%how%it%affects%the%
probability% of% past% and% future% states% of% the% system% (its% cause*effect%
repertoire,%which%specifies%what%the%concept%contributes%to%experience)%
and%its%size%(ϕmax)%measures%how%irreducible%the%concept%is%(how%much%
it% contributes% to% experience).% In% IIT,% Φmax% % *% a% non*negative% number% *%
measures% the% irreducibility% of% the% entire% quale,% how% much%
consciousness%there%is%–%the%quantity%of%experience.%%The%“shape”%of%the%
quale% (constellation% of% stars)% is% identical% to% the% quality% of% the%
experience.%Different%shapes%correspond%to%different%experiences:%they%
feel% the% way% they% do% *% red% feeling% different% from% blue% or% from% a%
headache%*%because%of%the%distinct%shapes%of%their%qualia.%
**Figure* 5:% IIT% makes% several% predictions% about% which% system% can%
experience%anything%(how%much%and%in%which%way)%and%which%systems,%
even% complicated% ones,% have% no% experience,% are% “in% the% dark”.% IIT%
implies% that% consciousness% is% graded% (A);% that% aggregates% are% not%
conscious% (A,% right% panel);% that% strictly% feed*forward% systems% are% not%
conscious% (B,% right% panel),% even% if% they% are% functionally% equivalent% in%
terms% of% their% input*output% operations% to% feedback% networks% that% are%
conscious%(B,%left%panel);%that%even%accurate%biophysical%simulations%of%
the% human% brain% running% on% digital% machines% would% not% be% conscious%
like% us,% but% constitute% mere% aggregates% of% much% simpler% systems%
(transistors% and% the% like)% having% minimal% Φmax% (C).% The% last% row% (C)%
shows,%from%left%to%right,%a%human%brain%(Allen%Institute),%the%IBM%Blue%
Tononi%&%Koch%–%Consciousness%*%10%
Gene%P%supercomputer,%a%columnar%model%of%mouse%cortex%(Blue%Brain%
Project),%and%a%scanning%electron%micrographic%cross*section%of%4%NMOS%
INTEL%transistors%in%a%grid.%
Tononi%&%Koch%–%Consciousness%*%11%
*
References*
Aru, J., N. Axmacher, A. T. A. Do Lam, J. Fell, C. E. Elger, W.
Singer and L. Melloni (2012). Local category-specific gamma
band responses in the visual cortex do not reflect conscious
perception. J. Neurosci. 32: 14909-14914.
Baars, B. and N. M. Gage (2010). Cognition, Brain, and
Consciousness, Academic Press.
Balduzzi, D. and G. Tononi (2008). "Integrated information in
discrete dynamical systems: motivation and theoretical
framework." PLoS Comput Biol 4: e1000091.
Balduzzi, D. and G. Tononi (2009). "Qualia: the geometry of
integrated information." PLoS computational biology 5:
e1000462.
Bateson, G. (1972). Steps to an ecology of mind, University of
Chicago Press.
Berlin, H. A. (2011). The Neural Basis of the Dynamic
Unconscious. Neuropsychoanalysis. 13: 1-68.
Blackmore, S. (2011). Zen and the Art of Consciousness,
Oneworld Publications Limited.
Block, N. (2007). Consciousness, accessibility, and the mesh
between psychology and neuroscience. Behav Brain Sci,
Cambridge University Press. 30: 481-499- discussion 499-548.
Block, N. J., O. J. Flanagan and G. Güzeldere (1997). The Nature
of Consciousness, MIT Press.
Boly, M., B. Baars, A. K. Seth, M. Wilke, P. Ingmundson, S.
Laureys, D. Edelman and N. Tsuchiya (2013). Consciousness in
humans and non-human animals: recent advances and future
directions. Front Psychol, Frontiers. 4: 625.
Bower, J. M. (2002). The organization of cerebellar cortical
circuitry revisited. Annals of the New York Academy of
Sciences.
Casali, A. G., O. Gosseries, M. Rosanova, M. Boly, S. Sarasso,
K. R. Casali, S. Casarotto, M.-A. Bruno, S. Laureys, G. Tononi
and M. Massimini (2013). A theoretically based index of
consciousness independent of sensory processing and behavior.
Sci Transl Med. 5: 198ra105-198ra105.
Chalmers, D. (2013). The Combination Problem for
Panpsychism. Panspsychism on the Reef.
Chalmers, D. (2013). Panpsychism and panprotopsychism. The
Amherst Lecture in Philosophy.
Chalmers, D. J. (1996). The conscious mind : in search of a
fundamental theory. New York, Oxford University Press.
Cohen, D. (1998). Patches of synchronized activity in the
cerebellar cortex evoked by mossy-fiber stimulation: Questioning
the role of parallel fibers. Proceedings of the National Academy
of Sciences. 95: 15032-15036.
Cohen, M. A., P. Cavanagh, M. M. Chun and K. Nakayama
(2012). "The attentional requirements of consciousness." Trends
in cognitive sciences 16(8): 411-417.
Cote, K. A., L. Etienne and K. B. Campbell (2001).
Neurophysiological evidence for the detection of external stimuli
during sleep. Sleep. 24: 791-803.
Cowey, A. and P. Stoerig (1995). Blindsight in monkeys. Nature.
Crick, F. and C. Koch (1998). "Consciousness and
neuroscience." Cereb. Cortex 8(2): 97-107.
Crick, F. and C. Koch (2003). A framework for consciousness.
Nature Neuroscience. 6: 119-126.
Darwin, C. (1887). The formation of vegetable mould, through
the action of earth worms, with observations on their habits ...
Dawkins, M. S. (1998). Through Our Eyes Only?, Oxford
University Press on Demand.
Dehaene, S. and J.-P. Changeux (2011). "Experimental and
theoretical approaches to conscious processing." Neuron 70(2):
200-227.
Dennett, D. C. (1993). Consciousness Explained, Penguin UK.
Edelman, D. and A. K. Seth (2009). "Animal consciousness: a
synthetic approach." Trends in Neurosciences: 1-9.
Edlund, J. a., N. Chaumont, A. Hintze, C. Koch, G. Tononi and
C. Adami (2011). "Integrated Information Increases with Fitness
in the Evolution of Animats." PLoS Computational Biology 7:
e1002236.
Engel, A. K. and W. Singer (2001). Temporal binding and the
neural correlates of sensory awareness. Trends Cogn. Sci.
(Regul. Ed.). 5: 16-25.
Frässle, S., J. Sommer, A. Jansen, M. Naber and W. Einhäuser
(2014). Binocular rivalry: frontal activity relates to introspection
and action but not to perception. J. Neurosci., Society for
Neuroscience. 34: 1738-1747.
Fried, I., A. Katz, G. McCarthy, K. J. Sass, P. Williamson, S. S.
Spencer and D. D. Spencer (1991). "Functional organization of
human supplementary motor cortex studied by electrical
stimulation." J Neurosci 11(11): 3656-3666.
Gazzaniga, M. S. (2005). Forty-five years of split-brain research
and still going strong. Nature reviews. Neuroscience. 6: 653-659.
Goldberg, I. I., M. Harel and R. Malach (2006). When the brain
loses its self: prefrontal inactivation during sensorimotor
processing. Neuron. 50: 329-339.
Griffin, D. R. (2001). Animal Minds, University of Chicago
Press.
Hassin, R. R. (2013). "Yes It Can: On the Functional Abilities of
the Human Unconscious." Perspectives on Psychological Science
8(2): 195-207.
Hassin, R. R., J. S. Uleman and J. A. Bargh (2005). The New
Unconscious, Oxford University Press.
Hawrylycz, M. J., E. S. Lein, A. L. Guillozet-Bongaarts, E. H.
Shen, L. Ng, J. A. Miller, L. N. van de Lagemaat, K. A. Smith,
A. Ebbert, Z. L. Riley, C. Abajian, C. F. Beckmann, A. Bernard,
D. Bertagnolli, A. F. Boe, P. M. Cartagena, M. M. Chakravarty,
M. Chapin, J. Chong, R. A. Dalley, B. D. Daly, C. Dang, S.
Datta, N. Dee, T. A. Dolbeare, V. Faber, D. Feng, D. R. Fowler,
J. Goldy, B. W. Gregor, Z. Haradon, D. R. Haynor, J. G.
Hohmann, S. Horvath, R. E. Howard, A. Jeromin, J. M. Jochim,
M. Kinnunen, C. Lau, E. T. Lazarz, C. Lee, T. A. Lemon, L. Li,
Y. Li, J. A. Morris, C. C. Overly, P. D. Parker, S. E. Parry, M.
Reding, J. J. Royall, J. Schulkin, P. A. Sequeira, C. R.
Slaughterbeck, S. C. Smith, A. J. Sodt, S. M. Sunkin, B. E.
Swanson, M. P. Vawter, D. Williams, P. Wohnoutka, H. R.
Zielke, D. H. Geschwind, P. R. Hof, S. M. Smith, C. Koch, S. G.
N. Grant and A. R. Jones (2012). An anatomically
comprehensive atlas of the adult human brain transcriptome.
Nature. 489: 391-399.
Herculano-Houzel, S. (2012). "The remarkable, yet not
extraordinary, human brain as a scaled-up primate brain and its
associated cost." Proc. Natl. Acad. Sci. U.S.A. 109 Suppl
1(Supplement_1): 10661-10668.
Hoel, E. P., L. Albantakis and G. Tononi (2013). "Quantifying
causal emergence shows that macro can beat micro." Proc Natl
Acad Sci U S A 110(49): 19790-19795.
Tononi%&%Koch%–%Consciousness%*%12%
Hornik, K., M. Stinchcombe and H. White (1989). Multilayer
feedforward networks are universal approximators. Neural
Networks. 2: 359-366.
Huxley, T. H. (1872). Evidence as to Mankind's Place in Nature.
Imas, O. A., K. M. Ropella, B. D. Ward, J. D. Wood and A. G.
Hudetz (2005). Volatile anesthetics enhance flash-induced
gamma oscillations in rat visual cortex. Anesthesiology. 102:
937-947.
James, W. (1890). The Principles of Psychology.
Joshi, N. J., G. Tononi and C. Koch (2013). "The minimal
complexity of adapting agents increases with fitness." PLoS
Comput Biol 9(7): e1003111.
King, J. R., J. D. Sitt, F. Faugeras, B. Rohaut, I. El Karoui, L.
Cohen, L. Naccache and S. Dehaene (2013). Information sharing
in the brain indexes consciousness in noncommunicative
patients. Current biology : CB. 23: 1914-1919.
Koch, C. (2004). The Quest for Consciousness: A
Neurobiological Approach, Roberts and Co.
Koch, C. (2014). "Is Consciousness Universal?" Scientific
American Mind 25(1 - Consciousness Redux).
Koch, C. and F. Crick (1990). Some reflections on visual
awareness. Cold Spring Harb. Symp. Quant. Biol. 55: 953-962.
Koch, C. and F. Crick (2000). Some thoughts on consciousness
and neuroscience. The new cognitive neurosciences.
Koch, C. and F. Crick (2001). The zombie within. Nature. 411:
893.
Koch, C. and G. Laurent (1999). Complexity and the nervous
system. Science. 284: 96-98.
Koch, C. and G. Tononi (2011). "A Test for Consciousness. How
will we know when we’ve built a sentient computer? By making
it solve a simple puzzle." Scientific American: 44-47.
Koch, C. and N. Tsuchiya (2012). "Attention and consciousness:
related yet different." Trends Cogn Sci 16(2): 103-105.
Kouider, S. and S. Dehaene (2007). Levels of processing during
non-conscious perception: a critical review of visual masking.
Phil. Trans. R. Soc. B. 362: 857-875.
Kouider, S., C. Stahlhut, S. V. Gelskov, L. S. Barbosa, M. Dutat,
V. de Gardelle, A. Christophe, S. Dehaene and G. DehaeneLambertz (2013). A neural marker of perceptual consciousness in
infants. Science, American Association for the Advancement of
Science. 340: 376-380.
Kurzweil, R. (2012). How to create a mind : the secret of human
thought revealed. New York, Viking.
Lagercrantz, H. and J.-P. Changeux (2009). The emergence of
human consciousness: from fetal to neonatal life. Pediatr. Res.
65: 255-260.
Lamme, V. A. F. (2006). "Towards a true neural stance on
consciousness." Trends Cogn. Sci. (Regul. Ed.) 10(11): 494-501.
Lancaster, M. A., M. Renner, C.-A. Martin, D. Wenzel, L. S.
Bicknell, M. E. Hurles, T. Homfray, J. M. Penninger, A. P.
Jackson and J. A. Knoblich (2013). Cerebral organoids model
human brain development and microcephaly. Nature. 501: 373379.
Laureys, S., G. Tononi and ScienceDirect (Online service)
(2009). The neurology of consciousness cognitive neuroscience
and neuropathology. Amsterdam ; London, Academic,.
Le, Q. V., M. a. A. Ranzato, R. Monga, M. Devin, K. Chen, G. S.
Corrado, J. Dean and A. Y. Ng (2011). Building high-level
features using large scale unsupervised learning. arXiv:
1112.6209.
Leibniz, G. W., G. R. Montgomery and G. W. Leibniz (2005).
Discourse on metaphysics, and The monadology. Mineola, N.Y.,
Dover Publications.
Lemon, R. N. and S. A. Edgley (2010). Life without a
cerebellum. Brain. 133: 652-654.
Logothetis, N. K. (1998). Single units and conscious vision.
Philos. Trans. R. Soc. Lond., B, Biol. Sci., The Royal Society.
353: 1801-1818.
Mach, E. (1959). The Analysis of Sensations and the Relation of
the Physical to the Psychical: Translated from the 1st German
Ed. by CM Williams. Rev. and Supplemented from the 5th
German Ed.[1906] by Sydney Waterlow. With a New Introd. by
Thomas S. Szasz, Dover Publications.
Markram, H. (2006). The blue brain project. Nature reviews.
Neuroscience. 7: 153-160.
Massimini, M., F. Ferrarelli, R. Huber, S. K. Esser, H. Singh and
G. Tononi (2005). "Breakdown of cortical effective connectivity
during sleep." Science 309: 2228-2232.
Mataró, M., M. A. Jurado, C. García-Sánchez, L. Barraquer, F.
R. Costa-Jussà and C. Junqué (2001). Long-term effects of
bilateral frontal brain lesion: 60 years after injury with an iron
bar. Arch. Neurol. 58: 1139-1142.
Mcginn, C. (2000). The Mysterious Flame: Conscious Minds In
A Material World, Basic Books.
Mudrik, L., A. Breska, D. Lamy and L. Y. Deouell (2011).
Integration without awareness: expanding the limits of
unconscious processing. Psychol Sci. 22: 764-770.
Mudrik, L. and C. Koch (2013). "Differential processing of
invisible congruent and incongruent scenes: a case for
unconscious integration." J Vis 13(13): 24-24.
Murphy, M. J., M.-A. Bruno, B. A. Riedner, P. Boveroux, Q.
Noirhomme, E. C. Landsness, J.-F. Brichant, C. Phillips, M.
Massimini, S. Laureys, G. Tononi and M. Boly (2011). "Propofol
anesthesia and sleep: a high-density EEG study." Sleep 34: 283291A.
Oizumi, M., L. Albantakis and G. Tononi (2014). "From the
phenomenology to the mechanisms of consciousness: integrated
information theory 3.0." PLoS Comput Biol 10(5): e1003588.
Owen, A. M., M. R. Coleman, M. Boly, M. H. Davis, S. Laureys
and J. D. Pickard (2006). "Detecting awareness in the vegetative
state." Science 313(5792): 1402-1402.
Palmer, S. E. (1999). Vision science : photons to
phenomenology. Cambridge, Mass., MIT Press.
Pitts, M. A., A. Martínez and S. A. Hillyard (2012). "Visual
processing of contour patterns under conditions of inattentional
blindness." J Cogn Neurosci 24(2): 287-303.
Schiff, N., U. Ribary, D. R. Moreno, B. Beattie, E. Kronberg, R.
Blasberg, J. Giacino, C. McCagg, J. J. Fins, R. Llinás and F.
Plum (2002). "Residual cerebral activity and behavioural
fragments can remain in the persistently vegetative brain." Brain
125(Pt 6): 1210-1234.
Schmuker, M., T. Pfeil and M. P. Nawrot (2014). "A
neuromorphic network for generic multivariate data
classification." Proc Natl Acad Sci U S A 111(6): 2081-2086.
Searle, J. (2013). Can Information Theory Explain
Consciousness? New York Review of Books.
Searle, J. R. (1980). "Minds, brains, and programs." Behavioral
and Brain Sciences 3(03): 417-424.
Shear, J. (1999). Explaining Consciousness, MIT Press.
Sklar, A. Y., N. Levy, A. Goldstein, R. Mandel, A. Maril and R.
R. Hassin (2012). "Reading and doing arithmetic
Tononi%&%Koch%–%Consciousness%*%13%
nonconsciously." Proc. Natl. Acad. Sci. U.S.A. 109(48): 1961419619.
Skrbina, D. (2009). Mind that abides : panpsychism in the new
millennium. Amsterdam ; Philadelphia, John Benjamins Pub.
Smith, J. D., J. J. Couchman and M. J. Beran "Animal
Metacognition: A Tale of Two Comparati..." Journal of
Comparative Psychology.
Strawson, G. and A. Freeman (2006). Consciousness and its
place in nature : does physicalism entail panpsychism? Exeter,
UK ; Charlottesville, Va., Imprint Academic.
Stroud, J. M. (1956). The fine structure of psychological time.
Information theory in psychology: problems and methods. New
York, NY, US, Free Press: 174-207.
Sullivan, P. R. (1995). "Contentless consciousness and
information-processing theories of mind." Philosophy,
Psychiatry, & Psychology 2(1): 51-59.
Takahara, M., H. Nittono and T. Hori (2002). Comparison of the
event-related potentials between tonic and phasic periods of rapid
eye movement sleep. Psychiatry Clin. Neurosci. 56: 257-258.
Tegmark, M. (2014). "Consciousness as a State of Matter." arXiv
preprint arXiv:1401.1219.
Tononi, G. (2004). "An information integration theory of
consciousness." BMC Neurosci 5: 42.
Tononi, G. (2008). "Consciousness as integrated information: a
provisional manifesto." Biol Bull 215: 216-242.
Tononi, G. (2012). "The Integrated Information Theory of
Consciousness : An Updated Account." Arch Ital Biol.
Tononi, G. (2012). Phi: A Voyage from the Brain to the Soul.
Tononi, G. and C. Koch (2008). "The neural correlates of
consciousness: an update." Ann N Y Acad Sci 1124: 239-261.
Tononi, G. and S. Laureys (2009). The Neurology of
Consciousness: An Overview. The Neurology of Consciousness:
Cognitive Neuroscience and Neuropathology. S. Laureys and G.
Tononi, Academic Press, Elsevier: 375-412.
Tsuchiya, N. K. and C. Koch (2014). On the relationship
between consciousness and attention. The Cognitive
Neurosciences. M. S. Gazzaniga. Cambridge, MA, MIT Press.
VanRullen, R. and C. Koch (2003). Is perception discrete or
continuous? Trends Cogn. Sci. (Regul. Ed.).
VanRullen, R., Zoefel, B. & Ilhan, B. (2014). "On the cyclic
nature of perception in vision versus audition." Phil. Trans. R.
Soc. B (in press).
Wegner, D. M. (2002). The illusion of conscious will.
Cambridge, Mass., MIT Press.
%
%
*
Notes*
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
i
% Note% that% we% consider% self*consciousness,% highly% developed% in%
adult%humans,%to%be%a%subclass%of%conscious%experiences.%Likewise,%the%
feeling% of% freely% willing% an% action% –% such% as% raising% one’s% arm% *%
sometimes%also%referred%to%as%agency%(Fried,%Katz%et%al.%1991,%Wegner%
2002)% –% is% another% subclass% of% conscious% experiences.% While% their%
content%differs%from%the%content%associated%with%feeling%pain%or%seeing%
red,%subjectivity%is%common%to%all.%
ii
% Consciousness% can% be% dissociated% from% many% other% cognitive%
processes% that% have% traditionally% been% closely% linked% to% it,% including%
memory,%emotions%and%selective%attention%(for%reviews%see%(Tononi%and%
Koch%2008,%Koch%and%Tsuchiya%2012).%It%can%persist%if%the%recall%of%long*
term% memories% is% impaired,% it% can% be% present% in% patients% who% lack%
affect,% and% it% can% be% dissociated% from% attention.% The% last% point% is%
particularly%counterintuitive%but%is%well*supported%–%subjects%can%attend%
to%invisible%objects%(Tsuchiya%and%Koch%2014).%The%extent%to%which%it%is%
possible%to%become%conscious%of%something%without%also%attending%to%it%
is%more%controversial%(Cohen,%Cavanagh%et%al.%2012,%Tsuchiya%and%Koch%
2014).%
iii
%Not%to%mention%the%question%of%whether%it%feels*like*something%to%
be%a%Venus%flytrap%or%a%single*cell%organism.%%
iv
%If%it%is%not%outright%wrong,%IIT%most%likely%will%have%to%be%refined,%
expanded,% and% adjusted.% However,% in% its% current% form% (IIT% 3.0),% it%
explains%and%predicts%a%wide%range%of%phenomena,%including%a%number%
of% counterintuitive% predictions% amenable% to% empirical% falsification.% For%
the% latest% formulation% of% the% theory,% see% (Oizumi,% Albantakis% et% al.%
2014);%for%earlier%versions,%see%(Tononi%2004,%Balduzzi%and%Tononi%2008,%
Tononi% 2008,% Balduzzi% and% Tononi% 2009,% Tononi% 2012);% for% a% literary%
account,%see%(Tononi%2012).%The%main%differences%between%IIT%3.0%and%
earlier%versions%are%listed%in%(Oizumi,%Albantakis%et%al.%2014).%
v
%For%example,%the%notion%of%the%aether%was%introduced%in%the%late%
th
19 %century%to%explain%the%propagation%of%light.%When%more%and%more%
experiments% concluded% that,% whatever% the% aether% might% be,% it% had% no%
effects% whatsoever,% it% finally% fell% under% Occam’s% razor,% and% it% plays% no%
role%in%modern%physics.%
vi
% However,% mechanisms% outside% a% system% can% serve% as% fixed%
boundary%conditions%(Oizumi,%Albantakis%et%al.%2014).%
vii
% Importantly,% this% may% be% a% macro*% rather% than% a% micro*spatio*
temporal%scale%(Hoel,%Albantakis%et%al.%2013).%For%example,%the%relevant%
level%for%human%consciousness%is%likely%to%be%neurons%at%the%scale%of%100%
millisecond%rather%than%molecules%at%the%nanosecond%scale.%
viii
% Requiring% that% only% the% maximum% of% Φ% over% elements,% spatial,%
and% temporal% grain% must% be% considered% is% not% exceptional% in% science:%
many%of%the%laws%of%physics%are%formulated%as%extremum%principles,%e.g.%
the%principle%of%least%action.%
ix
%IIT%postulates%that%experience%is%a%fundamental,%intrinsic%property%
of% organized% matter,% yet% supervenient% upon% the% physical.% While%
different%physical%states%can%give%rise%to%the%same%conscious%experience%
(metamers)% (Palmer% 1999),% different% experiences% must% be% caused% by%
differences% in% the% underlying% physical% mechanism.% Note% that% IIT% is%
compatible% with% quantum% mechanics.% In% principle,% Φ% and% related%
quantities% can% be% assessed% also% in% quantum% system,% although% it% has%
been%suggested%that%at%the%quantum%level%Φ%values%may%be%very%small%
(Tegmark%2014).%
x
%Here%we%do%not%elaborate%about%particular%cortical%areas,%cortical%
layers,%or%particular%population%of%neurons.%
xi
%The%exclusion%postulate,%by%requiring%that%the%set%of%mechanisms%
that%generate%one%particular%experience%do%so%over%the%time%window%at%
which% Φ% reaches% a% maximum,% would% seem% to% imply% that,% to% avoid%
multiple% causation,% the% next% experience% should% be% generated% over% a%
Tononi%&%Koch%–%Consciousness%*%14%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
non*overlapping% time% window,% as% long% as% an% overlapping% set% of%
mechanisms% is% involved.% The% seemingly% continuous% “stream”% of%
consciousness%would%actually%be%constituted%by%a%discrete%succession%of%
“snapshots,”% in% line% with% some% psychophysical% evidence% (Stroud%
,
1956) (Crick% and% Koch% 2003,% VanRullen% and% Koch% 2003,% VanRullen%
2014).% Note% that% each% snapshot% has% motion% and% other% dynamic%
percepts%associated%with%it.%
xii
% By% the% same% token,% the% exclusion% postulate% predicts% a% scenario%
that% is% the% mirror% image% of% the% prediction% that% consciousness% will%
suddenly% split% in% two% when% the% corpus% callosum% is% “cooled”% below% a%
critical% point:% if% two% people% speaking% were% to% increase% their% effective%
causal% interactions% by% some,% yet% to% be% invented,% direct% brain*to*brain%
connectivity% booster,% to% the% point% where% the% Φmax% of% the% two%
interacting% brains% would% exceed% Φmax% of% the% individual% brains,% their%
individual% conscious% mind% would% disappear% and% its% place% would% be%
taken%by%a%new%über*mind%that%subsumes%both.%
xiii
%A%similar%point%was%made%by%John%Searle%with%his%Chinese%Room%
Argument% (Searle% 1980)% and% by% Leibniz% 300% years% earlier% with% his% mill%
(Leibniz,%Montgomery%et%al.%2005).%
xiv
%In%the%extreme%case,%any%digital%computer%running%software%can%
ultimately% be% mimicked% by% a% Turing% Machine% with% a% large% state*
transition% matrix,% a% moving% head% that% writes% and% erases,% and% a% very,%
very%long%memory%tape%–%in%that%case,%causal%power%would%reside%in%the%
moving% head% that% follows% one% out% of% a% few% instructions% at% a% time.% On%
the%other%hand,%there%is%no%reason%why%a%hardware*level,%neuromorphic%
model% of% the% human% brain% system% that% does% not% rely% on% software%
running% on% a% digital% computer,% could% not% approximate,% one% day,% our%
level%of%consciousness%(Schmuker,%Pfeil%et%al.%2014).%
A%related%question%has%to%do%with%the%Internet%and%whether%it%could%
be%conscious%(Koch%2014).%One%way%to%think%about%this%is%to%assume%that%
each% computer% connected% to% the% Internet% is% an% element% having% real%
causal%power%at%a%macro*level.%For%example,%each%computer%could%send%
an% ON*line% signal% when% it% is% ON% and% an% OFF*line% signal% when% it% is% OFF.%
One%could%then%make%sure%that%each%computer%increased%or%decreased%
the% likelihood% of% being% ON% depending% on% how% many% ON*signals% it%
received.% In% principle,% this% kind% of% organization% could% be% arranged% so%
that%it%gives%rise%to%a%complex%of%high%Φ,%although%this%is%certainly%not%
the% way% the% Internet% works% right% now.% On% the% other% hand,% if% one%
considers%the%micro*elements%inside%each%computer%(say%its%transistors)%
as%having%real%causal%power,%we%are%back%to%the%situation%in%which%they%
most% likely% would% not% form% any% large% complex% within% each% computer,%
let%alone%across%connected%computers.%
xv
% A% well*known% instance% of% such% an% extrapolation% is% the% inference%
of% singularities% in% space*time% due% to% the% extreme% mass% of% a% stellar%
object.%Such%black%holes%were%pure%conjectures,%based%on%a%solution%of%
Einstein’s% theory% of% General% Relativity,% until% there% were% subsequently%
confirmed%observationally.%
% |
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
697
Article
Neural Oscillations & Consciousness: Attention as a
Litmus Test for the Quantum Mind Hypothesis
Seán O'Nualláin*
ABSTRACT
The “quantum mind” hypothesis, the notion that quantum phenomena are causal and perhaps
even essential in mentation and particularly consciousness, has met with fierce resistance. This
has been particularly the case over the past 20 years, and the first task of this paper is to show
that while there are indeed strong - mainly empirical - arguments against the thesis, the ‘in
principle arguments published to date evince premature closure.
The burgeoning field of “Quantum cognition” has established that quantum models are
appropriate for decision-making, and that of “Quantum biology” has now made the notion of
quantum effects at physiological temperatures plausible. If quantum effects are relevant to
consciousness, they are likely to be seen in the contrast between attended to and not attended to
streams of information. An exciting confirmation of this theme is the fact that attended to
streams involve a decorrelation of the informational fluctuations in streams not so attended to.
This gives rise to the idea that perhaps what enters our consciousness is the result of such a
decorrelation from a superposed state.
Decorrelation for the purposes of sparsification is prevalent in the brain; what may enter
consciousness in the schema proposed here is mental processes with a duration greater than the
sampling rate of consciousness (about 80ms) the wave function of which is undergoing statevector reduction in a manner described by the Quantum Zeno effect. This allows also for truly
voluntary action in the manner Von Neumann suggested. This is distinct from the situation with
binocular resolution dichoptic stimuli which is a mixture, and is an example of what Fodor calls
a “vertical” module with its operation mandatory. There is nothing to be gained by making
binocular synthesis subject to voluntary choice. Likewise, it is realistic to propose that attention
in lower animals with their less complex brains involves a much simpler mechanism than human
consciousness.
A model of the individual neuron as a harmonic oscillator is outlined, with a causal role for ion
channels in the generation of the oscillations. It is clear that ion channels are critical for attention.
Moreover, at a mesoscopic level, it is demonstrated that the brain enters a quiet “shutter” mode
several times a second in which quantum effects may be appropriately amplified. If quantum
effects exist in the brain, it is likely that this complex of phenomena will be central to them. The
de Barros and Suppes models, in addition to the similar formalism due to Henry Stapp, are also
briefly described.
Key Words: quantum mind, harmonic oscillator, attention, phase synchrony.
*Correspondence: Seán O Nuallái, Ph.D. University of Ireland, CA, USA. E-mail: president@universityofireland.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
698
1. Introduction
The “quantum mind” hypothesis, the notion that quantum phenomena are causal in mentation, is
one of the truly exciting ideas of the past century. Until recently, it also seemed very unlikely. If
true, it gives us a language to describe our thought in the context of the emanation of the cosmos,
and – on what is relatively a prosaic level – to assert human free will, soul, and mental capacity
greater than Turing machines. This article begins its analysis below by considering one of this
theory’s main proponents, Henry Stapp
In previous work (2012) this author has indicated how the non-classical probability regime that
epitomized the quantum vacuum prior to the creation of the inflaton and the big bang may be
recapitulated in the brain through consciousness. Many leaps of faith are required, and this article
proposes the evidence that will be necessary from a variety of disciplines to make this hypothesis
plausible. Alternatively put, the subject/object relationship in QM is the most bare in nature; my
2008 paper describes the various other types of epistemological relations that hold a, for
example, we move around the world, or map a domain in terms of the formal symbols used in
language.
In the first place, we need some regime in which quantum effects can be causal in biological
systems. We then need some evidence that the artillery of Hilbert spaces is relevant for cognition
as for quantum mechanics. As it happens, neither hypothesis – unthinkable even a generation ago
– is in the slightest currently implausible, and we will simply refer to prior art.
For example, Hu et al (2010) give a list of various theories that have emerged, and the empirical
evidence on which they are based. That article features work analyzing the evidence for nonlocality in neural phenomena which is not the focus here; rather, a targeted analysis of attention
and how it might be subject to quantum effects is going to be the core of this paper. Ball (2011)
authoritatively announces the field of “quantum biology”. While skeptical about the “quantum
mind” hypothesis, de Barros and Suppes (2009) point to the existence of quantum cognition, and
presage their later work of how neural oscillator structures may give rise to these phenomena,
echoing the work described later in this paper.
The second step after quantum biology is the justification of the “quantum mind” hypothesis, the
notion that there is some real quantum process causally affecting the mind. The
Penrose/Hameroff model has argued that human cognition cannot otherwise be described; rather
less well known is the painstaking investigation of Berkeley’s Henry Stapp into the
consequences of Von Neumann’s analysis of the system and the observer. That shall constitute
our next port of call. If Stapp is right, then Penrose/Hameroff may similarly be correct in their
insistence that, through quantum effects, the mind transcends the chugging of the Turing
machine, and both models assert human free will as a consequence.
Should this model be valid, it is reasonable to expect the neural data to reflect it. In particular, it
should be possible to see phenomena in attention that resemble state-vector reduction.
Remarkably, here our model holds up well in the face of the thorough research into attention by
Jude Mitchell, inter alia.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
699
A complicating factor is the lack of metatheory in neuroscience, it is fair to say that we must
emphasise how time is increasingly being agreed on as the lingua franca of the brain. It may be
asserted with some confidence that information is conveyed by markings on the phase of neural
oscillations like gamma – or indeed the individual neurons that we study below. In particular,
phase synchrony seems to be essential for cognition in general, and for both consciousness and
meditation in particular. In fact, even if the quantum model is wrong, the fact that it has focused
attention of waves and their effect in neural function may in itself have justified the area, if not
the extravagant claims. The data with which I end this paper are valid whether “quantum mind”
is right, or another beautiful, well-motivated and failed theory.
According to Tegmark (2000) the theory is indeed a failed one. With some patience, he explains
neural impulses/firing, and demonstrated that decoherence would occur far too quickly for any
conceivable “condensate’ to last long enough to support a conscious experience. However, he
fails completely to reference gap junctions, which allow almost instantaneous transmission of
signals and do not need the conventional “action potentials” that Tegmark describes. (Shepherd
et al, 2010). In fact, Tegmark is in many ways the George W Bush of this area; faced with what
only he considered an existential threat, he attacked the wrong enemy.
In like vein, Reimers et al (2009) point out that the then favoured location of coherent states for
the Hameroff/Penrose model – Froehlich condensates – is impossible in principle. While this
may indeed be right, it also, like Tegmark misses the target. In fact, it belongs to a nearphrenological obsession with locating the “faculties’ of the mind in specific cerebral locations, a
bizarre recapitulation of a Victorian thread that we will consider in the last section below.
There is, on the contrary, an emerging and indeed burgeoning consensus that the attested fact
that the brain can support stable patterns of oscillatory circuits, particularly through dendrodendritic connections (Shepherd et al, 2010) is critical for 21st century neuroscience. The
remainder of this paper will examine several such models and their background.
2. The work of Henry Stapp
In the famous “quantum zeno” effect (Stapp 2009; forthcoming, 2013), the QM event selects the
code to be used in the next Energetic cycle. This result in a situation where the tiny time-scales
involved in Qm can have macroscopic effects. Much of my published experimental neuroscience
work (2008, 2009; with Tom Doris, 2009, 2011) has shown how individual neurons, correctly
described as harmonic oscillators, can have their oscillations entrained by large-scale and
synchronized gamma to recruit them to produce states more congenial for quantum effects.
Stapp (2009) is allowed speak for himself about the details of his model. Tegmark (2000) glosses
Stapp as proposing that “interaction with the environment is probably small enough to be
unimportant for certain neural processes” which is rather like saying that “certain Iraqis may
object to our presence”.. In fact, Stapp (2009) is extremely aware of the problem of
environmental decoherence. He suggests, correctly, that the existence of harmonic oscillators is
not in doubt and proposes what are trivial extensions to give them quantum traction. He then
argues that the “quantum zeno” effect allows Von Neumann’ process 1, the putting of a question
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
700
to nature and apprehending the result, ensures that conscious choice is neurally as plausible as it
clearly is physically plausible, embedded as it is in the structure of Von Neumann’s classical
approach to QM. Note that one can also allow that state-vector reduction occurs absent any
observers, be that mechanism spontaneous localization or whatever.
Likewise for bistable stimuli, those that change from one perception to another in th manner of
the Necker cube and the rabbit/duck fluctuation. In this case, there is work indicating that a
single perception can be maintained for 3 seconds, giving a zeno moment of perhaps 30 ms,
compatible with gamma waves. (Atmanspacher et al, 2008)
So without violating any real neuroscience, Stapp (forthcoming) puts it we can say that we are
“psychophysical agents that can freely instigate probing actions of our own mental choosing ".
All that we need is a very limited but relatively free capacity to choose the object of our
attention – as I wrote before (2012), we do not have absolute free will to change long-entrenched
habits but we do have the capacity to change our focus and thus begin to work on ourselves.
Thereafter as it is possible to demonstrate, attention becomes biased in the direction of the free
choice previously made, as Sheng He and his colleagues have demonstrated (Jiang et al, 2006).
My own work on the subject can be found in my 2010 paper.
Similarly, in visual attention work, as it turns out from He et al,, stereoscopic fusion does NOT
happen without attention. Instead, in the absence of attention, a fused/patchwork image gets
relayed. So there is a role for attention with perhaps QM implications; however, it looks as
though what obtains in binocular vision more resembles a mixture. (Zhang et al, 2011) than a
superposition.
As Stapp (forthcoming) puts it “Each observing ego is empowered to pose probing questions
about the facts of the world in which it finds itself. “. That is all we need for at least a limited
notion of free will ; we can look on will (self-mastery) as something that can vary from person to
person, and involves familiarity with the thousands of years of human culture in which we're
immersed, the fact that we're highly social primates used to living in groups, and other factors
which shape us; nevertheless, there is a “free” core. As Stapp (forthcoming) puts it about
development;
“The ego of the infant begins in the womb to inquire about the structure of its world, and by
virtue of its intrinsic conceptual capacities begins, by trial and error, to acquire a conception of
the world in which it finds. This conception is a construction in terms the validated feeling about
it.”
This can usefully be expanded by looking at the work of Jean Piaget , whose constructivism has
survived the attack of his experiments (see my 2003 book)
It is worthwhile thinking of the analogy of the cinema, with 28 frames per second being
necessary to fill. Once a stream is the object of attention, it reaches a threshold (perhaps 10
frames/sec) and gets promoted to conscious awareness. Once in consciousness, it can
“broadcast” to the rest of the processes in the brain in the manner of an actor on stage. This
broadcast is achieved, at least partially, by modulating the fast gamma oscillations in the brain.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
701
In
consciousness, these oscillations become more synchronized. In reality, consciousness
involves perhaps 12 frames per second; 80 ms seems the minimum time we need to recognize
objects. (Again, please see my 2010 paper)
A fundamental point that presents itself is the status of “elements of reality” in Qm. Indeed here
Bohr and Von Neumann are greatly at odds. In particular, Bohr is committed to an
epistemological interpretation in Born's view – “the electron IS FOUND at x” – whereas Von
Neumann is willing to say “the electron IS at x”. There are profound reasons for this distinction,
arising from Mach who also corrupted Einstein– albeit in such a way that Bohr and Einstein felt
themselves in disagreement.
As Stapp (ibid.) expresses it “ the empirical validity of certain predictions of quantum
mechanics entails that some supposedly mere practical tools for the calculation of predictions,
namely the actualized quantum mechanical states, are real essences “
This is the core of the issue and what we're doing is trying to cash it out in terms of present
knowledge; “Thus quantum mechanics becomes, in von Neumann’s orthodox formulation,
directly and explicitly, a theory of the mind-brain connection.” (ibid). However, it is this author’s
view, further developed below, that the notion of what “elements of reality” may never be
resolved in terms of cognition, or indeed in terms of classical epistemology; QM, accurate
beyond our wildest dreams, may forever remain inscrutable.
Moreover, the following (ibid) needs to be explicated in view of what we now know about
attention:
“The mind, or “abstract ego”, has a battery of efforts E each of which corresponds to an act of
putting to Nature a particular question about the world inhabited by that ego. According to the
quantum precepts, Nature immediately responds by either returning a feeling F that is tied to the
effort, F=F(E), or by failing to return immediately a response. “
In fact, it resembles nothing so much as the “self-conscious mind” that John Eccles eventually
saw incarnated in a “probability cloud” due to his (mis?) reading of Margenau, described in my
2003 book We do not need this in any case to support the idea that there is a core capacity for
voluntary action in humans, and it is hard to uphold in the face of the relevant neuroscience and
psychology evidence.
It is better to start from here: “The key to such an understanding is an understanding of the way
that a mind is connected to its brain; for that connection is that mind’s bridge to the future.”
(Stapp, ibid)
In my 2012 paper I suggest, in this context, that it is possible to achieve a regime of non-classical
probability in the brain and indeed Suppes et al (2012) com to precisely the same conclusion in
the quantum cognition field, providing a mechanism in terms of neural oscillators similar to the
one about to be outlined.
There is no need to assume that all our choices are absolutely “free”; indeed, it would be hard to
function. In fact, it may be the case that, even granted a core of free will, and as described in my
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
702
2010 paper, nature and culture have gifted us to ability to confabulate, incorrectly to attribute
agency to ourselves, the better truly to act freely at times in complex environments.
3. Superposition and the brain
There is a growing consensus that aspects of human decision-making and concept formation can
best be described using models from QM (Aerts, 2009, .de Barros, J.A. & Suppes, P. 2009,
Suppes et al, 2012). What we are now going to explore is whether the same can be said for
attentional mechanisms.
There are arguments on the micro level related to the Quantum Zeno effect –“ watched phone
never rings”. There are facts on the macro level related to attention – but these seem
paradoxical in nature, allowing the speculation that attention actually ENDS superposition - eg
the work at He's lab showing that non-attended visual data never get binocular synthesis, (Zhang
et al, 2011) . However, the stream not attended to is best viewed as a mixture rather than a
superposition.
Bressler et al’s work (2010, 2013) is also of interest here. It is not in doubt at this stage; attention
ups the neural activity of the attendee-to stream, while suppressing response variability. It also
suppresses the threads not attended to (ibid). In fact, it arguably turns the attended-to thread into
von Neumann’s process 1, posing a yes/no question to nature.
That there is a link between neural attention and QM is apparent in these quotes from Dirac and
Zhang et al: Dirac; "The intermediate character of the state formed by superposition thus
expresses itself through the probability of a particular result for an observation being
intermediate between the corresponding probabilities for the original states, not through the
result itself being intermediate between the corresponding results for the original states"
Or, as Zhang (2011) et al put it: "Thus attention is necessary for dichoptic images to be engaged
in sustained rivalry, and may be generally required for resolving conflicting, potentially
ambiguous input, and giving a single interpretation access to consciousness."
4. Attention and Consciousness
I indicate below how a position that accepts at least a limited form of free will can be fleshed out
wrt neuroscience and indeed developmental cognitive psychology. Here, then, is my view of the
position that can be defended in the face of the QM and neuroscience. Human consciousness
consists of the ability to take a stream of processing – for example, an action-perception cycle
with feedback present – and to submit it to a regime of superposition and state-vector reduction.
This stream must last in the order of tenths of seconds at least as the minimum conscious
“moment” is about 80 ms. . Human consciousness is a superset of and distinct from lower
animal “attention”, the ability to confer salience on a processing stream and up the gain of that
stream.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
703
Human consciousness is limited in that our ability to concentrate is limited, with 3 seconds being
not a bad estimate (Atmaspaher et al, 2008). It uses mechanisms of decorrelation of an
informational stream pervasive in the cortex, but does so in a voluntary way, one subject to will
and featuring an immanent sense of self. In that, of course, it is consistent with the Von
Neumann formulation of quantum mechanics. Its mechanism of a physiological level can
perhaps be found in quantum coherent states related to ion channels, which seem related to the
informational gain in attention. Our work will show how these ion channels establish the
oscillation period for neurons considered as harmonic oscillators, and how the gamma
oscillations synchronized through the cortex associated with consciousness help provide the
entropically “quiet” environment in which quantum coherent states might occur.
Like it or not, materialists have to accept that that the Von Neumann formulation is consistent
and can be interpreted as supportive of a form of dualism, more nuanced than the crude
mind/body version. Like it or not, dualists have to accept that there are plausible neuroscientific
accounts of a good deal of our perceptual experience, at least limited computer simulations of
how symbols can be produced – though indications are that symbolic behavior at a higher level
needs consciousness - and psychological evidence (a la Libet) that many of our choices are less
free than we believe them to be. In fact, we confabulate a lot, not least to ourselves
The following any objections coming from the Libet et al (1983) work which argued that
“conscious” intent was, follwing Hume, a “wont’ rather than a will, distinct from Von
Neumann’s Proocss 1. Of course preafference will occur, whereby the brain lines up hypotheses
for likely perceptual experience, and prepares responses. It is precisely the assimilation of such
processes to an informational stream, and the use of a superposition and state-vector reduction on
that stream, that constitutes human consciousness. That in turn introduces quantum
indeterminacy into human decision making, and Aerts (2009) and many others have
demonstrated the pervasiveness of quantum cognition in the human case, even be that cognition
less than useful for particular decision-making tasks.
It also leads to the hypothesis that animals may forever be better at some attentional tasks than
humans, as the mechanism used is simpler and does not involve free will; there is some evidence
supporting the viewpoint that the types of process involved are different (Zangenehpour et al,
2008). This is of course aside from the obvious perceptual adaptations that attune animals to
different parts of the electromagnetic spectrum to us, or better reflexes in cats, to take one
example.
My guess is that the Quantum mind hypothesis is testable under this regime: 1. Does human
consciousness involve superpositions? If not, it is game over and there are no quantum effects;
and 2. If yes, and this superposition is indeed to be seen in the suppression of response variability
in attention, even in macaques, is it the case that humans can modulate their attention to create
new superpositions in their execution of complex plans?
The fact that Tversky and Kahneman's results are interpretable as "quantum cognition" rather
than straightforward application of Bayes or some other regime now comes into play. What this
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
704
writer finds really interesting about Mitchell's work (2009) is that attention DECORRELATES
information so it is irreversible - pretty much what we want for state-vector reduction. In fact, it's
beginning to look as plausible that our stream of consciousness is serial not parallel as a result of
exploitation of quantum effects.
The critical issue then is that attention decorrelates information fluctuations. If this looks more
like state-vector reduction than anything classical, the QM approach to mind is vindicated.
Therefore, the Libet et al (1983) work actually supports the Quantum mind hypothesis as only
one course of action was being "prepared". There exists also the possibility that Libet's
instruments were not sensitive enough to detect alternative actions. Where such measurements
have taken place (Bressler et al, 2010, 2013) it is clear that streams not being attended to, while
retaining thir physiological integrity, have their activity suppressed in the service of keeping one
stream, the focus of attention, enriched.
So what we defend is a notion that, as W James put it, the mind seizes on one of many streams of
activity in the brain which then becomes the focus of attention. This stream is then characterized
by differential informational statistics, as Mitchell et al (2009) have demonstrated, and this
confirms a refutable hypothesis. In particular, we now have a “deus ex machina” - attentionpreparing an observation in a way that shows purely “mental” effects on the “physical” world of
the brain. It is indeed possible that this process may become assimilated to neural activity
afterward; nevertheless the capacity is there for voluntary action.
The immediately above goes for bistable perception in general. There is also compelling
evidence that the statistics of attended -to streams are different from those not so attended
(Mitchell et al, 2009), and that response variability is less in attended-to streams (Cohen et al,
2009). Finally, He's lab has also demonstrated that attention is initially assigned unconsciously
but in a way consistent with the disposition and formation of the observer (Jiang et al, 2006).
5. Neural models: mesoscopic and microscopic and the relation with gamma
waves
There are models attested by ECOG data that invite speculation that the brain enters “limit
cycles” a few times per second (Freeman et al 2008). These limit cycles correspond to
synchronized gamma, meditation and consciousness as my various papers on the subject (2009,
2012) and those with Doris (2011) attest. The 2009 paper is consistent with the researchers who
have proposed that the signature of the meditative state is the phase synchrony of the relatively
fast gamma waves (40 Hz approx). The general approach of the Freeman work in summarized in
my own 2008 paper.
The existence of phase coherence in gamma waves in the brain, and the relation of this
phenomenon to consciousness, is a point of much consensus. It has been further argued that the
entropically minimal state resulting from this phase coherence might yield an environment
conducive to quantum coherence.
While we believe that the work of Walter Freeman indeed is indicative of entropically minimal
states in the brain occurring several times a second, we also believe that the EEG/ECOG signal is
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
705
too coarse to indicate synchrony. Indeed, we can adduce findings from PCA , among other
methods, indicating that a 64-electrode grid produces at most two signals with any dgree of
magnitude. In fact, there are data to indicate that much of the statistical inferences in classical
EEE/ECOG evince premature closure, and that this approach is certainly not ready – pace, the
ORCH OR proponents – for the non-classical world. So the gamma hypothesis, though
beautiful, is “not proven’. The PCA work can be found in my 2011 paper with Doris which also
finally gives the lie to the notion that epileptic seizure is a minimally entropic state.
As for phase coherence, the stated electronic specifications of the equipment used in ECOG and
EEG expressly prohibit any such inference, as the error range of the equipment is too large. This
argument may become ever more salient over the years to come, as it does appear to be the case
that one of the critical mechanisms used by the brain to convey information is frequency
modulation of a carrier wave (like FM radio). In particular, phase information may indeed turn
out to be critical once we learn how to measure it accurately.
This is a fortiori the case as simulations give a lot of support to the “zero power” gamma
hypothesis for consciousness. If we simulate groups of 10,000 neurons - the “mesoscopic” level
– and consider their firing as a random process with a mean frequency of 200 times/second, then
we can graph how the power consumption of the brain is affected by gamma. The graph below
indicates that it enters a brief period of “zero power” – of minimal consumption of energy –
between 2 and 12 times per second. If this is done in synchrony throughout the brain, we indeed
can speculate about health effects of meditation as the brain frees up energy to be used by the
rest of the organism. In the diagram below, we have time of the x axis and energy consumption
on the y axis.
These same models can be extended with models of individual neurons that explain how the
attended- to stream of processing maximizes its gain in the broadcast system of the cortex (O
Nualláin, Seán and T. Doris 2010). We consider each neuron as a harmonic oscillator, and
consider how the oscillation of the membrane potential is altered in synaptic and dendrodendritic connections. It is the latter that would seem to be more susceptible to quantum effects.
Following are the details of the model, as presented in our 2010 paper.(IFN = the “standard”
integrate and fire model; our model claims that this is a subset of the more general resonate and
fire (RFN) behaviour in this discussion)
Ours (2004) was the first work to show how single neurons could realistically perform
processing of sensory data expressed simply as spectral such data. This work has since been
corroborated by, for example, Branco et al. (2010). Essentially, we argued that subthreshold
oscillations of the neuron allowed groups of neurons to “own” part of the spectrum. That can be
conceived of using only classical physics. As mentioned, we have data to indicate that much of
the statistical inferences in classical EEE/ECOG evince premature closure, and that this approach
is certainly not ready – pace, the ORCH OR proponents – for the non-classical world.
Since our original work, quantum coherence at physiological temperatures has been
demonstrated for biological systems in photosynthesis at the 3nm level characteristic of gap
junctions in neurons (Hoyer et al, 2012). This finding converges with a controversy about
quantum effects in neurons related to consciousness. While, in related work, we question the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
706
assumption in the later that “phase coherence” has in fact been demonstrated in the brain, there is
a long-attested corpus of observations suggestive of entropically minimal states several times a
second there.
We therefore speculate that gap junctions might allow a quantum superposition of states of the
membrane potential of each neuron to be communicated to thousands of others. This will lead to
entanglement of a scale that would allow the Fourier decomposition we envisage for the classical
case to be extended to a quantum description. This is the only currently physiologically plausible
story about Quantum effects in the brain that we can currently envisage as having quantum
effects.
Our model (O Nualláin, and Doris 2010) shows how ion channels' activity interacts with the
frequency of subthreshold oscillations in a neuron. This is on the one hand causative of different
patterns of firing and on the other hand of phase changes in the quantum state and we propose
this in conjunction with the current Reynolds work as a possible interrelation of attention and
neural processing (Reynolds et al, 2009). It also is consistent with the Suppes et al work (2012)
which, while in favour of the harmonic oscillator paradigm, arges that the allegedly quantum
effects are in fact artefacts of the structure of neural oscillators.
We will take some time to look at the structure of our model:
The basic behaviour of Harmonic Oscillators is captured by the differential equation:
d 2
2 .
dt
The parameters which give an oscillator its unique properties are A , w0 and . The value of A
determines the amplitude of oscillation, that is how far the maximum displacement from
equilibrium will be. The w0 term determines the strength of the returning force. This in turn
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
707
determines how quickly the mass returns to the equilibrium point (and indeed the velocity at
which the equilibrium is passed). This equates to the more familiar concept of the frequency of
oscillation. The frequency of oscillation is the number of complete cycles performed per second,
and is the inverse of the period, the length of time required to complete a single cycle.
The period of oscillation of such a system is denoted and related to the other terms as follows:
2
=
.
w0
In a fashion similar to the delta functions used to describe the intergate and fire neuron (IFN) –
for Tegamrk (2000) the only type of neural mechanism - , we now demonstrate the operation of
the resonate and fire model in mathematical terms. First, we must define some variables unique
to the model:
f 2
i = i ,
fc
where f i is the resonant frequency of node i , and f c is the frequency of the global clock. The
global clock frequency determines the granularity of simulation and may be set to any value, the
default used to produce the graphs discussed previously is 1000. The term i is referred to as the
counter multiplier for node i . This term is introduced since it may be calculated once the
resonant frequency is specified, and thus does not need to be calculated in subsequently.
i = (wij o j )
w02 i
i
fc
The rate of change of the membrane potential of neuron i , or its velocity, is denoted by i .
The change in the velocity for the current time step is calculated first. The contribution from
input pulses from all pre-synaptic neurons is calculated by the sum of products term wij o j ,
where wij is the weight of the connection from neuron j to neuron i , and o j is the current
(axonal) output of neuron j . The current axonal output is always either a 1 or a 0 , since action
potentials are all or none events. The return force's contribution to the velocity calculation is
w02
expressed as
, which is the expression we arrived at for previously, divided by f c . We
fc
divide by f c because we are performing a time slice calculation; in each step of the calculation
we are simulating a period of time that is the inverse of the global clock frequency. The final
term is the damping factor. The damping constant, ranges from 0 to 1 , and is typically
assigned a value of around 0.01 . The effect of this parameter is to cause the oscillation to
gradually die off, slowly reducing the amplitude, as seen previously in the graphs.
=
i
fc
The calculation of the new membrane potential, , is straightforward once we have calculated
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
708
the new velocity. In a single period of the global clock, will change by the product of the
current velocity and the time that we are simulating. Since period is the inverse of the frequency,
this sum can be expressed as shown above. At this point we have calculated the new membrane
potential. All that remains is to handle the production of action potentials and endro-dendritic
interactions.
The mathematical structures described thus far handle axonal inputs from pre-synaptic neurons.
Another major feature of the model is direct dendro-dendritic connections. This aspect is
accommodated through a simple extension to the delta rule.
i = (d ij ( j i ) (wij o j )
w02
i
fc
Finally, the early caveat that quantum effects cannot exist at physiological temperatures in
biological organisms no longer applies in the face of what we know about photosynthesis, and
perhaps avian navigation; this work just cited provides the possibility that quantum coherent
states could be maintained in an otherwise noisy brain.
7. Quantum mind and the sciences
There is a fundamental question prior to how “God’ or “spiritual’ entities in general, if such
exist, can be cognitively apprehended. This question relates to the structure of knowledge itself,
in a context in which - perhaps unfortunately - distinctions between the physical, biological, and
psychological have been elided to the point that methodologically all are considered fair game
for such approaches as the rather grotesquely-named “big data”. Indeed, there does not seem to
any attested and principled way of distinguishing the physical and social sciences, and - absent a
view of self as object - it is difficult indeed to see how we can create a narrative in which the
ebb and flow of spiritual experience, an immediate sense of the noumenal that is physical,
emotional and intellectual at the same time, can be encompassed. The “thinglessness”, the
ineffability suggested by quantum mechanics affords an entrée.
This project is an initial foray into this vast question. As argued below, it seeks to reinstate a
notion of the ontological to distinguish between the various “physical” sciences, starting with
physics and biology. Indeed, we will produce better science – even in the short term – if,
eschewing statistical extravagances, we begin to honour ontological distinctions. It argues that
the “cognitive” is best thought of in terms of the principles of cognitive science, rather than as
“psychologism”, the attempt to describe objective (or at least consensually attested ) entities
solely in terms of the metaphors or other psychological operations that underpin their
presentation to consciousness.
It further contends that the main problem underlying construal of the “spiritual’ is the same as
that which has destroyed the normative aspect of political experience in favor of an over-used
“rights-based” approach. To wit, this is skepticism about the existence of an algorithmically
compact level of description, the noetic level, which gives the correct entrée into an area of
discourse. Once we have such an entrée, and with it the confidence that we are construing the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
709
area veridically, we can be more sure of our spiritual insights, our political calls to arms, and our
scientific intuitions.
The noetic stance refers to how a discipline - be it a conventional academic discipline, spiritual
perspective, a political call to arms, or a technical skill – should be apprehended. It is
distinguishable from the cognitive description, which is a post hoc attempt to map onto the
structures of cognitive science including recursion, schemes and so on. The noetic description is
more algorithmically compact than the cognitive such. Finally, this summary can be perhaps read
as the appropriate interrelation of the cognitive and the noetic stance,
For example, folk psychology – explanation of behaviour in terms of motives, desires and so on
– is a noetic description and is psychologically prior to the eschatological hope of eliminative
materialism that we can dispense with all these terms through neuroscience. Similarly, as
exemplified in the famous break-up scene with Sheldon and Amy in the “Big bang theory”, the
noetic description of the physical domain is couched in the language of mathematical physics
and no description in terms of neurobiology will be more elliptical or veridical – a point Sheldon
, the “genius physicist” ,fails to make in this hilarious scene.
Yet even physics requires a causal notion of information; not only can addition of a bit change
the area of a black hole, as demonstrated inter alia by Susskind, but the observer can cause statevector reduction. The noetic level of physics must acknowledge this by including, suitably
nuanced, the idea that “a bit gives it”. Similarly, the noetic level of biology includes the fact that
syntax IS indeed intrinsic to the biology, if (as Searle, following Kripke argued) not the Physics)
and the $billions that have gone into projects like the HGP that ignore this fact have largely been
wasted. Indeed, one result has been the absurdity of a genome with over 99% thereof, while
preserved for millions of years by evolution, somehow seen as “non-coding”. Once we accept the
existence of different ontological layers in nature – so far the physical and biological - our
science gets a lot better.
We come now to the cognitive level – as mentioned the structures of cognitive science including
recursion, schemes and so on. This area must also explain the structures of our physical and
biological theory, and by the mid explain the mind. Yet it is constrained by the structures of
these theories in ways that have not really been made clear. If Einstein could use a fourth-order
tensor to produce general relativity, then clearly fmri with its scalars (0 order tensors) is not an
appropriate formalism.
Indeed, cognitive science has spawned the area of consciousness studies. This can best be seen as
an attempt to extend the objectivist, third-person explanation pattern in science to primitive
aspects of subjective experience like visual illusions and sensorimotor experience.
Consciousness studies, as exemplified by the work of the late Jim Newman and John Taylor (see
our 1997 collection) can be interpreted as providing support for the notion that the phenomena
of attention on which we have based so much of the argument of this paper may not hold out any
promise for quantum mind. It is indeed the case that attention results in a simple yes/no question,
a la maniere de Von Neumann being put to nature; but, argues Taylor, that is simply because the
nuclei reticularis thalami gate every access to attention, and will allow only one item in at a time.
Now we come to the punch line of this final argument. If Taylor is correct about the gating
mechanism’s existence, it may buttress the quantum mind idea in an unexpected way. It may just
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
710
as well be argued that the structure of the mammalian brain has conformed to the requirement,
implicit from Von Neumann, that there be a single yes/no question imminent from whatever
process has grabbed the resources of attention. Luckily, this single serial stream of consciousness
is what’s needed also for dealing with the classical, macroscopic world, and control of action
therein.
We can go further. This yes/no question will inevitably change the superposition manifest in the
processing stream by removing information, precisely as in state-vector reduction. Given a
similarly superimposed object – and such may occur in visual processing in particular – that too
will change, as we know occurs in photosynthesis. A bit gives it; information is causal, and the
mind has capacities that we will only slowly discover.
8. Summary
The health of the quantum mind hypothesis, even subjected to a robust devil’s advocate as here
in this paper, is surprisingly robust. We find that it is compatible with best practice in
experimental and computational neuroscience, and the classical Von Neumann QM approach.
That is not to say that it is proved.
This leads to a surprising hypothesis – that it is those streams of cortical processing that are
attended to are those to which the quantum description in terms of superposition, and the
Quantum Zeno effect apply. Once a stream is attended to, it will be broadcast to the entire
nervous system through a mechanism in which the fast gamma oscillations are modulated – in
the manner of FM radio – to convey information to the rest of the nervous system, and this is
susceptible to classical description. It makes evolutionary sense that superposition should be
reserved for only some processes , the better to exploit the kind of processing now being
modeled in quantum computation while yet maintaining the single serial stream of
consciousness that we need to engage the world when the wave-function collapses.
The model thus suggests that the brain s hybrid quantum-classical in its assignment of attentional
resources. Superposition occurs in a manner that indeed allows the possibility of conscious
processing in a manner redolent of quantum computation, and indeed it is not controversial to
suggest that many of the finest results in mathematics ( a la Poincaré's famous discovery as he
got on a bus) seem to arise in consciousness almost effortlessly. Only decohered streams of
thought can so appear; once there, they may be broadcast to the rest of the nervous system
through the mechanism of consciousness. Our work (Freeman et al, 2008) indicates that this
mechanism in discontinuous and has perhaps 10 events per second and in this is consistent with
the findings that the conscious moment is around 80 to 100 ms.
Streams of processing that have decohered compete for conscious resources, and the total of 10
events per second are each also a chance for another stream to get on stage and broadcast to the
nervous system. It is also uncontroversial to suggest that meditation, where an attempt is made to
enthrone one innocuous stream on stage for some time at the expense of more informational-rich
streams, has health benefits and seems to allow the gamma oscillations to remain more coherent
as the focus of awareness is changed less often.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
711
The consequences for free will are consistent with common-sense intuitions, psychology, and
Von Neumann's work in that our freedom may above all be the ability to regulate the focus of
our attention, and thus action, over time. It is not claimed that every act is absolutely “free”;
however, human beings are capable of modifying the objects that become foci of attention as
what initially were acts of will become habits of the nervous system. The degree of this freedom
will vary between individuals.
In summary, then a paradoxical situation obtains with respect to attention and superposition. On
the one had, attention may be seen as turning a mixture into a superposition (Jiang et al 2009),
The counter-argument may be made that this is an artificial situation, with dichoptic stimuli
manipulated in a way that does not occur in nature. On the other hand, it seems to be the case
that attention decoheres/decorrelates input streams, and this reduces response variability
(Mitchell et al, 2009). Yet such processes occur even in dendrites in the hippocampus as a way
of sparsifying signals.
The final situation, then is one on which quantum superposition is one of many mechanisms used
by the brain. In some cases, it appears to be the case that attention works with only decohered
signals as a way of decreasing response variability. Yet decorrelation is used elsewhere in the
brain as a way of sparsifying signals, without any attention.
It is therefore plausible to suggest that attention causes some signals to decohere from a state that
resembles a superposition, rather than a mixture. Moreover, this process can occur for areas like
concept-formation and decision-making as for perception. Our inability to maintain focal
consciousness on any particular item for very long may be the result of such consciousness as
being dependent on state-vector reduction happening. Human voluntary action, as opposed to
involuntary action that is the subject of attention, can be thought of as subject to the Quantum
zeno effect and therefore of a different kind to animals' reactions to their environment
The existence of coherent quantum states at physiological temperatures in biological systems is
no longer in doubt, which buttresses the position that it is plausible to suggest that attention
works as one of many decohering processes in the brain.
Reynolds is currently working on a model in which voltage modulation in ion channels can
produce a huge gain change in attention. This may be suitably sensitive to and/or causative of
quantum effects in the manner of quantum effects in transistors; also the Ahranov-Bohm effect,
inter alia, shows that the electrical field potential can change a quantum state.
In particular, only processing streams of sufficient duration in time to be susceptible of becoming
the focus of consciousness seem candidates for superposition and state-vector reduction.
Attention may be merely one of many mechanisms in the brain for state-vector reduction;
alternatively, it may be the case that we can become aware only of sufficiently durable such
processes.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
712
References
Aerts, D. (2009), Quantum structure in cognition. Journal of Mathematical Psychology, 53, 314-348.
Atmanspacher, H., Bach, M., Filk, T., Kornmeier, J., Römer H. (2008), “Cognitive time scales in a
Necker-Zeno model for bistable perception”. Open Cybernetics and Systemics Journal 2, 234–251.
Ball (2011) “Physics of life: The dawn of quantum biology” Nature 474, 272-274 (2011)
|doi:10.1038/474272a Published online 15 June 2011 News Feature
Branco, Tiago, Beverley A. Clark, and Michael Häusser (2010) “Dendritic Discrimination of
Temporal Input Sequences in Cortical Neurons” Science 24 September 2010: Vol. 329 no. 5999 pp.
1671-1675 DOI: 10.1126/science.1189664
Bressler DW, Silver MA (2010) “Spatial attention improves reliability of fMRI retinotopic
mapping signals in occipital and parietal cortex” Neuroimage. 2010 Nov 1;53(2):526-33. doi:
10.1016/j.neuroimage.2010.06.063. Epub 2010 Jul 1.
Bressler DW, Fortenbaugh FC, Robertson LC, Silver MA. (2013) “Visual spatial attention enhances the
amplitude of positive and negative fMRI responses to visual stimulation in an eccentricity-dependent
manner” Vision Res. 2013 Jun 7;85:104-12. doi: 10.1016/j.visres.2013.03.009. Epub 2013 Apr 3.
Cohen M & John H R Maunsell (2009) “Attention improves performance primarily by reducing
interneuronal correlations” Nature Neuroscience 12, 1594 - 1600 (2009)
de Barros, J.A. & Suppes, P. (2009). Quantum mechanics, interference, and the brain. Journal of
Mathematical Psychology, 53 (5), 306-313.
Hu, H &Wu, M. (2010) “Current Landscape and Future Direction of Theoretical & Experimental
Quantum Brain/Mind/Consciousness Research” Journal of Consciousness Exploration & Research
|November 2010 Vol. 1 Issue 8 pp. 888-897
Freeman, W., S. O'Nuallain and J Rodriguez(2008) "Simulating cortical background electrocortigram at
rest with filtered noise" Journal of integrated neuroscience,7 (3 )Page: 337 - 344 Sept 2008
Stephan Hoyer, Akihito Ishizaki, K. Birgitta Whaley (2012) “Spatial propagation of excitonic
coherence enables ratcheted energy transfer” Phys. Rev. E 86, 041911 (2012)
Jiang Y, Patricia Costello ,Fang Fang ,Miner Huang , and Sheng He (2006) "A gender- and sexual
orientation-dependent spatial attentional effect of invisible images" PNAS vol. 103 no. 45 17048–
17052
B. Libet, C. A. Gleason, E. W. Wright, and D. K. Pearl, Time of Conscious Intension to Act, In Relation
to Onset of Cerebral Activity (readiness Potential) (1983) Brain, 106, 623-642.
JF Mitchell, KA Sundberg, JH Reynolds (2009) “ Spatial attention decorrelates intrinsic activity
fluctuations in macaque area V4 “ Neuron, 2009, 63. 879-888
O'Nuallain S "The Search for Mind" (Ablex, 1995; 2nd ed Intellect, 2002; Third edition Intellect, 2003)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 697-713
O'Nualláin, S., Neural Oscillations & Consciousness: Attention as a Litmus Test for the Quantum Mind Hypothesis
713
O'Nualláin, Seán (1997), "Two Sciences of Mind" (principal co-editor) (Benjamins)
O'Nuallain, S CSLI, Stanford and T. Doris(2004) http://bcats.stanford.edu/previous_bcats/bcats04/html/nuallain.html
O'Nualláin, Seán (2009), “Zero power and selflessness” Cognitive sciences 4(2).
O'Nualláin, Seán (2012), “God’s unlikely comeback” Cosmos and History Vol 8, No 1 (2012) The Future
of Philosophy Pp 339-382.
O'Nualláin, Seán (2008)“Subjects and Objects” Biosemiotics journal, Volume 2, Pp. 239-251
O'Nualláin, Seán and T. Doris (2010) “What is neural resonance for?” Chaos and complexity letters 4(2).
Reprinted in the collection “mondforce”
O'Nualláin, Seán (2010) “Ask not what you can do for yourself: Cartesian chaos, neural dynamics, and
immunological cognition” Biosemiotics Vol 3 Issue 1, 2010 DOI 10.1007/s12304-009-9070-4
O'Nualláin, Seán and T. Doris (2011) “Consciousness is cheap” Biosemiotics journal DOI:
10.1007/s12304-011-9136-y online; Hardcopy 2012 Biosemiotics journal 5(2) Pp 193-210
Reimers, Jeffrey R.; McKemmish, Laura K.; McKenzie, Ross H.; Mark, Alan E.; Hush, Noel S.
(2009)."Weak, strong, and coherent regimes of Fröhlich condensation and their applications to
terahertz medicine and quantum consciousness". PNAS 106 (11): 4219–4224.
doi:10.1073/pnas.0806273106.
Shepherd GM, Grillner S. 2010. Handbook of Brain Microcircuits. New York: Oxford University Press
Stapp H (forthcoming, 2013) “Quantum Theory of Mind” In Contemporary Dualism A Defense Edited
by Andrea Lavazza, Howard Robinson Routledge Studies in Contemporary Philosophy Series"
November 2013
Stapp, H (2009 ) “A model of the Quantum-Classical and Mind-Brain Connections, and of the Role of the
Quantum Zeno Effect in the Physical Implementation of Conscious Intent.”
http://arXiv.org/abs/0803.1633 CH 14 in Minds Machines &QM 3rd edition 2009
Suppes, P., J. Acacio de Barros, and G. Oas (2012). Phase-oscillator computations as neural models of
stimulus–response conditioning and response selection. Journal of Mathematical Psychology, 56(2):
95–117, April 2012.
Tegmark, M. (2000). "Importance of quantum decoherence in brain processes". Physical Review E 61 (4):
4194–4206. arXiv:quant-ph/9907009
Zangenehpour S, Ghazanfar AA, Lewkowicz DJ, Zatorre RJ (2009) Heterochrony and Cross-Species
Intersensory Matching by Infant Vervet Monkeys. PLoS ONE
4(1):e4302.doi:10.1371/journal.pone.0004302
Zhang, P Keith Jamison, Stephen Engel, Bin He, Sheng He (2011) "Binocular Rivalry Requires Visual
Attention" Neuron, Volume 71, Issue 2, 362-369, 28 July 2011.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
1
What we are is more than what we do
Larissa Albantakis and Giulio Tononi
Wisconsin Institute for Sleep and Consciousness, University of Wisconsin-Madison, USA
We are witnessing a surge in artificial systems, from autonomous robots to self-driving cars, all
of which already display features of autonomy, agency, and goal-directed behavior.
With the advent of Artificial General Intelligence (AGI) it is plausible that such artificial
autonomous agents (AAA) will display behaviors similar to human autonomous agents
consciously pursuing their own goals. The more those agents develop complex and human-like
capacities, the more the impetus towards granting them consciousness and associated mental
capacities (such as intrinsic motivations and intentions) analogous to humans will grow (Dehaene
et al., 2017).
In the pervasive functionalist Zeitgeist this is a forgone conclusion; it is only a matter of how
rapidly AAA will develop and how sophisticated they will be. Because, once they show the same
traits we do, what possibly could be missing? Indeed, in fields of study like the Ethics of AI and
Roboethics we are already hearing appeals to machine rights, well-being, and moral status.
Accomplishing more and more sophisticated cognitive functions—“doing”—seems all that
matters.
But is this functionalist assumption warranted?
To address this question, it is necessary to rely on a comprehensive theoretical approach that
makes the requirements for consciousness explicit. Unfortunately, we first have to clarify what
exactly we mean by consciousness: Consciousness is phenomenology, subjective experience, and
not a function performed by the brain.
When we ask whether a machine might be conscious, we are not asking whether it can perform
a certain set of functions, such as detecting and reacting to complex external stimuli, or providing
sensible answers to intricate questions. What we want to know is whether, in doing so, the
machine experiences. In other words, we want to know whether it has a rich, subjective inner
life, not unlike our own.
Nevertheless, instead of subjective experience, the current science of consciousness almost
exclusively focuses on surrogate phenomena such as reportability, neural activity, behavioral
reports, or functional/computational structure. In a misplaced attempt of objectivity, the initial
goal—to account for phenomenology, which is inherently subjective—is set aside or forgotten
altogether.
Approaches that disregard the intrinsically subjective character of consciousness will not be able
to tell us which properties a physical system has to fulfill for it to “feel like something” to be that
system. A detailed account of the behavioral and neural correlates of consciousness (NCC), for
2
example, is clearly useful to predict both the state of consciousness of a healthy adult human
subject and also the content of their experience. However, prediction does not equal
understanding. How could we decide, for instance, whether a biological basis is necessary for
consciousness based on human NCC?
Without a proper theory of phenomenology, how it emerges from physical systems, and what
determines its quantity and quality, we cannot confidently attribute consciousness or a lack
thereof to other physical systems, including infants, patients with brain lesions, animals, or
machines.
Our goal has to be to account for subjective experiences in objective terms. Contrary to common
opinion, this is possible if one takes the nature of consciousness seriously and attempts to
characterize its essential features and inherent structure (Negro, 2020).
Integrated Information Theory (IIT) aims to provide such a theory of consciousness with
explanatory, predictive, and inferential power that starts from phenomenology itself. Specifically,
IIT attempts to identify the essential properties of phenomenal experience (axioms), from which
it infers the requirements for a physical system to be a substrate of consciousness (postulates)
(Tononi et al., 2016; Albantakis, 2020).
According to IIT, a conscious entity must exist for itself. In physical terms, to ‘exist’ means to have
causal power, to be manipulable and observable. To exist for itself, it must have causal power on
itself, in a way that is structured, specific, unitary (as one whole), and definite (specifying its own
borders). A system that exists for itself in causal terms then also exists in phenomenological terms
and the structure of phenomenal experience of such an entity corresponds to the intrinsic causal
structure of its underlying physical substrate.
The argument here is that if the intrinsic causal structure of a physical system can account for
every aspect of the phenomenal structure of a given experience, there is nothing left to require
of the physical system, and it should be regarded as a physical substrate of consciousness by an
inference to a “good enough” explanation.
In sum, whether a system is conscious or not and also the content of its experience thus depends
on the causal structure of its physical substrate, and not on its behavior. What matters for
consciousness is what a system is—its causal implementation, not what it does.
A good example for distinguishing between phenomenal structure and functional properties is
our experience of visual space (Haun and Tononi, 2019). When we see a blank screen with a single
dot, for example, we are able to locate the dot and fixate our eyes on its position on the screen.
This relatively simple function can certainly be performed by an artificial system that fixates a
camera on the position of the dot. However, we know that a human performing this task will
experience an extended visual space with a myriad of identifiable spots, here and there, small
and large, which relate to each other by connection, fusion, or inclusion. The artificial system
cannot be assumed to have anything remotely similar to our spatial experience if nothing within
3
the system itself could account for such a rich phenomenal structure; that it can fixate on the dot
is irrelevant.
In general terms, based on IIT, “doing” and “being” can be dissociated. In other words, functional
equivalence does not imply phenomenal equivalence, because the same function can typically
be implemented in many different ways, by physical systems with very different causal
structures. For example, IIT (and others) postulate that feedback is a necessary feature of a
physical substrate of consciousness. Without feedback, a system cannot form a causal entity that
constrains itself as required by the postulates of IIT, and therefore does not exist for itself in
causal or phenomenological terms. However, based on established theorems from the field of
theoretical computer science (Krohn and Rhodes, 1965), it is generally possible to perform any
sort of computation in a feedback-free manner (although it might not always be practically
feasible). Even complex human behaviors may thus be performed by systems that do not have
the right causal structure to experience anything at all.
While current digital computers are not strictly feedforward, their modular, engineered
architecture is still very different from the interconnected, evolved neural architecture of a
human cortex. The physical computer as a whole would likely not form one causal entity, but
rather break down into many parts that lack any meaningful causal structure. This holds
regardless of the software that is executed by the computer. The simulation itself does not
specify any kind of causal structure because it is virtual and thus cannot exist by itself by
definition. Even computers that simulate our behavior or neural activity in extraordinary detail
would thus remain unconscious.
Nevertheless, IIT does not presuppose a biological basis for consciousness. For example, an
artificial, silicon-based brain that complies with all IIT postulates and specifies a causal structure
very similar to that of a natural brain would be regarded conscious in the same sense as we are.
In this case, there would be no room to argue for a biological basis as an additional requirement
for consciousness, since it could not explain any additional facts about phenomenology.
To conclude, if we take the subjective character of consciousness seriously, consciousness
becomes a matter of “being” rather than “doing”. Because “doing” can be dissociated from
“being”, functional criteria alone are insufficient to decide whether a system possesses the
necessary requirements for being a physical substrate of consciousness. The dissociation
between “being” and “doing” is most salient in AGI, which may soon replicate any human
capacity: computers can perform complex functions (in the limit resembling human behavior) in
the absence of consciousness. While AAA may display seemingly purposeful behaviors, true
values, goals, and intentions must be intrinsically meaningful to the agent itself and must be
reflected in the intrinsic causal structure of a behaving agent. Complex behavior becomes
meaningless if it is not performed by a conscious being.
4
References
Albantakis L (2020) Integrated information theory. In: Beyond Neural Correlates of
Consciousness (Overgaard M, Mogensen J, Kirkeby-Hinrup A, eds), pp 87–103. Routledge.
Dehaene S, Lau H, Kouider S (2017) What is consciousness, and could machines have it? Science
(80- ) 358:486–492.
Haun A, Tononi G (2019) Why Does Space Feel the Way it Does? Towards a Principled Account
of Spatial Experience. Entropy 21:1160.
Krohn K, Rhodes J (1965) Algebraic Theory of Machines. I. Prime Decomposition Theorem for
Finite Semigroups and Machines. Trans Am Math Soc 116:450.
Negro N (2020) Phenomenology-first versus third-person approaches in the science of
consciousness: the case of the integrated information theory and the unfolding argument.
Phenomenol Cogn Sci:1–18.
Tononi G, Boly M, Massimini M, Koch C (2016) Integrated information theory: from
consciousness to its physical substrate. Nat Rev Neurosci 17:450–461. |
695
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 695-698
Kaufman, S. E., Knowing & knowing
Realization
Knowing & knowing
Steven E. Kaufman*
ABSTRACT
The Knowledge that the Formless gives is the Consciousness of Itself - Formlessness
apprehending Formlessness. The knowledge that form gives is the Consciousness of an object the Consciousness of a form - Formlessness apprehending form. Thus, both Knowledge and
knowledge are apprehended by the same Formlessness.
Key Words: knowledge, form, formlessness, Consciousness.
Do not look to form for certainty.
Do not look to the Formless for definition.
The Formless can give you certainty.
Form can give you definition.
Do not look for in one
What can only be given
By the other.
The certainty that the Formless gives
Is its own Presence.
The definition that form gives
Is its very existence.
The definition that form gives
Is knowledge.
The certainty that the Formless gives
Is Knowledge.
So it is that
The Formless cannot be defined,
Cannot be known,
As an object,
As a form,
But can be Known,
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
696
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 695-698
Kaufman, S. E., Knowing & knowing
Directly,
As That which Is
In the absence of form,
And as That which still Is
In the presence of form.
The Knowledge that the Formless gives
Is the Consciousness of Itself.
Formlessness apprehending Formlessness.
The knowledge that form gives
Is the Consciousness of an object,
The Consciousness of a form.
Formlessness apprehending form.
Thus, both Knowledge and knowledge
Are apprehended by the same Formlessness.
It may seem that the Formless
That knows itself as an object,
As a form,
Is different or other than
The Formless that Knows Itself
As It Is,
As the Formless.
And so we venerate the Latter,
While denigrating the Former.
Seeing one as higher
And the other as lower.
But this is an illusion,
As the Formless Is One.
Non-dual.
Neither higher nor lower.
Only when viewed through the lens of duality,
The lens of form,
Does the Formless appear to Itself
As something other than One.
When viewed through the lens of form,
The duality inherent in form
Becomes superimposed
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
697
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 695-698
Kaufman, S. E., Knowing & knowing
Upon That which Is forever Non-dual,
Upon That which Is eternally One.
A river may diverge for a short span
Before it meets up with itself again,
With one branch flowing smoothly
While the other may contain much turbulence.
If only the branches are seen,
There seem to be two different rivers.
But from a broader perspective
There is seen to be only one river
With two ways of flowing.
Those who Know
Only venerate,
Because they see only the One.
Those who only know
Both venerate and denigrate,
Because they see the one and the other.
Those who Know
Are not better than,
Or other than,
Those who only know.
Those who only know
Just know something
That those who Know
Do not.
Those who only know
Are filled with the forms that arise
Where the Flow of the River Is turbulent.
Those who Know
Are filled with the Formlessness That Is
Where the Flow of the River
Is smooth or turbulent.
Sometimes I Know,
While at other times
I only know.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
698
Journal of Consciousness Exploration & Research | September 2014 | Volume 5 | Issue 7 | pp. 695-698
Kaufman, S. E., Knowing & knowing
When I Know,
I Know that whether I Know or only know
Does not really matter.
For when I Know,
I Know that when I only know
That I am not something other than
What I Am
When I Know.
But when I only know
That Knowledge is obscured,
And it then seems
That when I only know,
That I am something less
Than what I was
When I Knew
What I no longer Know.
And so when I only know
I try to add to myself,
To find myself,
And in so doing
Just create more turbulence.
And when the Flow becomes rough enough
I wake up again
And Know.
Such a game.
Such a ride.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
A Higher Dimension of Consciousness
Constructing an empirically falsifiable panpsychist model of
consciousness
Version 1.0
Jacob Jolij
Heymans Institute for Psychological Research,
Faculty of Behavioral and Social Sciences, University of Groningen,
The Netherlands
j.jolij@rug.nl
1
Abstract
Panpsychism is a solution to the mind-body problem that presumes that consciousness
is a fundamental aspect of reality instead of a product or consequence of physical processes (i.e., brain activity). Panpsychism is an elegant solution to the mind-body problem: it effectively rids itself of the ‘explanatory gap’ materialist theories of consciousness suffer from. However, many theorists and experimentalists doubt panpsychism
can ever be successful as a scientific theory, as it cannot be empirically verified or falsified.
In this paper, I present a panpsychist model based on the controversial idea that
consciousness may be a so-called higher physical dimension. Although this notion
seems outrageous, I show that the idea has surprising explanatory power, even though
the model - as most models - is most likely wrong. Most importantly, though, it results
in a panpsychist model that yields predictions that can be empirically verified or falsified. As such, the model’s main purpose is to serve as an example how a metaphysical
model of consciousness can be specified in such a way that they can be tested in a scientifically rigorous way.
2
Introduction
The Mind-Body problem is arguably one of the oldest problems in philosophy. In contemporary consciousness research, it is probably best known the way Dave Chalmers
(1995) phrased it, as ‘The Hard Problem of Consciousness’: why and how do conscious
experiences exist in this universe of matter and energy? This problem has been ignored
for several decades in psychology, but since the late 1990s, there has been an intensive
search for the ‘neural correlate of consciousness’ (Crick and Koch, 1992). This renewed
surge in consciousness research has led to at least 14 candidate models on how the brain
produces or supports conscious sensations (Signorelli, Szczotka & Prentner, 2021).
However, most of these models rely on the classical assumption that ‘mind is what
the brain does’, or in other words, they are materialist/physicalist models that assume
that consciousness can be reduced or explained by the laws of physics. This, however,
still leaves Chalmers’ Hard Problem unsolved, in addition to the problem that physics
itself is not causally closed yet (Ney, 2016). Materialism is therefore not universally
accepted by philosophers and consciousness researchers. Although most scholars reject
substance dualism, on the basis that substance dualism violates the first law of thermodynamics, there are monist alternatives to materialism. Most prominent amongst these
is the notion of panpsychism, the idea that consciousness is a fundamental aspect of
the universe (interpreted by some that ‘everything is conscious’, although one may of
course debate this). According to several philosophers and neuroscientists,
panpsychism is a viable alternative to materialism, and possibly even the only logical
one (cf. Chalmers, 1999; Goff, 2019; Koch, 2019; also see Velmans, 2008). However, a
key problem with panpsychism is not only that it is very alien to how we experience the
world, but it is also extremely difficult to falsify and to integrate in a coherent metaphysical worldview that also incorporates physics.
In this paper, I will lay out a proposal to integrate a panpsychist worldview into a
physical model of the universe. I do not claim this model to be correct, but rather intend
to demonstrate one possibility of how one could go about in coming up with a falsifiable
panpsychist model of consciousness that fits in with our understanding of physics. The
resulting model does not explain consciousness as such, but rather gives a potential
coherent description of how physical states are coupled to mental states (sensations)
that fits with the broad panpsychist framework. The core idea is that conscious sensations are not objects, particles, forces, or events, but rather a (physical) dimension of
the universe. Although this idea seems outrageous at first, I will argue that this conception of conscious states as a dimension does make sense - even if not true, the notion is
an interesting ‘thinking tool’ to further theorizing about consciousness.
3
The problem
Let us first strictly define the problem most contemporary theories of consciousness
are trying to solve, namely how the brain (a physical object) produces or supports consciousness (a mental phenomenon). In the field of brain and cognitive sciences, it is
now widely accepted and taught that conscious states are equivalent to brain states:
“mind is what the brain does”, as Minsky famously stated, or “consciousness is a brain
process” (Lamme, 2006). However, what brain activity results in ‘consciousness’, has
been a topic of debate ever since cognitive neuroscientists embraced the ‘quest for consciousness’ (Crick and Koch, 1992).
This ‘quest for consciousness’ has largely been a quest for the ‘neural correlates’ of
sensory experience: what brain processes correlate with (reports of) sensation? With
‘sensation’ most researchers in the brain and cognitive sciences refer to the concept of
‘qualia’. In terms of Jackson’s (1986) famous parable “What Mary didn’t know”, consciousness researchers are looking for those brain processes that allow Mary to experience color - regardless of whether she learns something new or not when first exposed
to color.
Although consciousness can mean many things, ranging from ‘soul’ to ‘sentience’
or ‘intelligence’, the element of conscious experience is vital in all of these, most importantly our notion of what it means to be ‘human’. Sytsma et al. (2021), for example,
had participants read one of two vignettes about an advanced android, which in appearance and behavior was indistinguishable from an actual human being. Critically,
in one vignette they mentioned that the android did not have actual experiences, but in
the other vignette the android was said to have conscious experiences. After reading
the vignette, participants were asked whether the android should be awarded human
rights. While most participants who read the first vignette, in which the android did not
have conscious sensations, responded negatively, the majority of participants who read
the second vignette, in which the android did have conscious experiences, responded
positively. This shows that in our folk notion of what it means ‘to be human’, conscious
sensations play an important role.
Therefore, it seems justifiable to focus on this most basic notion of consciousness
when discussing the topic. In the remainder of this paper, I will adopt this notion: ‘consciousness’ is used as a synonym for ‘conscious experiences’ or qualia.
Adopting a subject-neutral position
Conscious states are typically believed to be equivalent to brain states. From a phenomenological point of view, this makes sense: we experience sensations as ‘our own’. There
4
is a unique element of subjectivity and ‘ownership’ to conscious experience. Our conscious sensations appear to be located inside our heads (Forstmann & Burgmer, 2021),
and reflect reality as projected into a ‘Cartesian theatre’ somewhere in the skull (Dennett & Kinsbourne, 1992). In other words: our conscious sensations are very strongly
tied to our own body/brain. Consequently, thinking about consciousness and how it
relates to physical processes has almost exclusively been focused on the relation between an individual’s brain states and that individual’s phenomenological states.
However, this feeling of ownership of experience and the idea that conscious experiences are by definition accompanied by a feeling of ‘ownership’, or even need a subject that experiences them, may be an illusion. There are several notable examples in
psychopathology and neurology which sensations are experienced, but not integrated
into the subjective self. One obvious example is that of depersonalization (DSM VI), a
disorder of consciousness in which the patient reports a detachment from her or his
sensations. Reality is experienced as if it is happening to someone else. Interestingly,
meditation, a mental practice aimed at reducing the ego and ultimately experience reality as ‘selfless’, is associated with an increase in depersonalization (Castillo, 1990).
Related to this example is the practice of non-dual meditation, a form of meditation requiring extensive practice and associated with a feeling of ‘pure awareness’. In a
state of non-duality, the meditator does no longer experience a difference between ‘self’
and the world (see e.g., Laukkonen & Slagter, 2021). Non-dual states have been widely
reported in the literature. We cannot make any metaphysical assumptions based on
such report, of course, but so we can safely conclude that a conscious experience of
‘oneness with the world’ without a self, does in fact exist.
There are, however, other examples. In body integrity identity disorder (BIID), patients report that sensations from their limbs do not ‘belong’ to them: sensory signals
from one or more extremities are not integrated into the representation of the bodily
self. As a result, patients feel that a limb ‘does not belong’ to them - a sensation that
causes such discomfort that some patients opt for amputation of the limb (Giummarra
et al., 2011).
BIID and depersonalization disorder may serve as examples that sensory signals
processed by the brain of an individual are not strictly necessarily integrated or attributed by a ‘self’. An extremely rare case of conjoined twins, the Hogan twins seems
to suggest that one of the twins can experience the sensory experiences of the other.
The twins are joined at the heads and have a very unusual neural anatomy. Parts of the
thalamus, the subcortical nucleus where many sensory inputs arrive and are subsequently transmitted to cortical areas, are shared between both twin sisters. Although
the sisters cannot look into the same direction because of the way their skulls are fused,
5
it appears as if one twin has access to the sensations of the other via the neural link they
share, even though both sisters have distinct personalities or ‘selves’. In other words,
this is an example of a sensory experience being experienced by two independent
minds, although the case should be interpreted with great care, given the lack of formal
scientific tests of the twins (Cochrane, 2021).
Summarizing, our normal everyday experience may lead us to conclude that individual brain states are equal to particular conscious states, and necessarily tied to a
‘self’, or agent. This, however, might not be universally true. Of course, the notion of
‘disembodied’ conscious experiences sounds very alien but let us attempt to adopt a
’subject neutral’ stance towards consciousness. In the ‘traditional’ approach towards
consciousness, we make the statement
𝑄!"#$% = 𝑓(𝑃!"#$% )
Which should be read as conscious state Q, a point in a hypothetical ‘qualia space’
(Stanley, 1999), is a function of brain state P, or a transformation of state space P onto
space Q. Roughly said, what we attempt in contemporary consciousness science is to
find an answer to how this transformation works. Please note that although I am using
the word ‘function’ here, I am not suggesting that there is a causal relation here (as in,
the brain causes consciousness): there is an equivalence. If a given brain is in state P,
this corresponds to conscious state Q, or alternatively, if we exactly know someone is
experiencing state Q, the associated brain of that person is in state P.
I propose to extend this statement to
𝑄&%$'(")( = 𝑓(𝑃&%$'(")( )
Which should be read as state of the universe P corresponds to conscious state Q. In
this, conscious state Q denotes all ‘individual’ conscious states or qualia experienced by
all conscious entities in the universe. At first sight, this extension appears to complicate
the problem we are attempting to solve. However, we cannot make assumptions about
‘what it feels like’ to be a self or a subject of consciousness: we necessarily have to be
agnostic with respect to the type of systems that might be conscious (or experience qualia, to use a more neutral term). A theory of consciousness (or better, the function that
describes the equivalence between P and Q states) needs to be neutral with respect to
the medium of consciousness: brains, computers, or indeed the whole universe. Of
course, it can be that only unique P to Q equivalencies exist (i.e., conscious states are
only equivalent to brain states), but let us for now keep all options open.
6
What then are qualia?
It is not difficult to spot the fundamental problem with an approach that attempts to
describe an equivalence between physical and mental states: there is an implicit notion
of dualism embedded into this question. However, as noted before, substance dualism
is quite widely rejected by scientists and philosophers. If we want to come up with a
physicalist model of consciousness, we need to postulate that qualia are not (part of) a
separate, potentially unknowable, world, but fit in with our standard model of the universe, which describes the fundamental particles and forces, and how these interact in
spacetime. This gives us only a limited number of options if we wish to incorporate
qualia into this model.
For example, we could argue that qualia are mediated by some sort of special ‘particles’. Jibu and Yasue (1995) propose that consciousness critically depends on the interaction between hypothetical particles they call ‘corticons’, fundamental particles
unique to the brain, and electric fields in that brain. Obviously, any empirical evidence
of existence of such corticons is lacking. Moreover, it raises the question if (and how) a
new class of fundamental particles came into existence upon evolution of the mammalian cortex.
An example of an alternative account is given by Keppler (2021), who proposes
that consciousness is realized in the zero-point field, the universal base electric field,
and that qualia are the result of the interaction of complex electromagnetic activity in
specific information processing systems with this zero point field. In other words, in
this view, consciousness is more akin to a (fundamental) force, namely electromagnetism. Of course, the question remains why this force is associated with consciousness,
and not the nuclear forces, for example. Additionally, the ‘hard question’ still remains:
why are some electromagnetic interactions ‘conscious’, but others not?
In sum, it appears difficult to fit in qualia in the standard model of physics. However, why should we think of qualia as matter/energy? As Dennett (2018) points out,
the tendency to think of qualia as a ‘product’ or as ‘stuff’ complicates our thinking about
consciousness. We might be looking for something that is not there. However, this still
leaves us with the question where and how to fit in consciousness or qualia in a physical
model of the universe.
If qualia are not matter (i.e., particles) or a fundamental force, there appear to be
only one alternative: they are an integral part of spacetime - a notion that is very close
to the idea of panpsychism (cf. Frankish, 2021, who notes that panpsychism is the only
logical alternative to dualism if we treat qualia as ‘things’ that can exist independent of
a psychological subject). Spacetime as we experience it has three spatial dimensions
7
and one temporal dimension. Contemporary physics theories such string theory, however, postulate there might be as many as 11 dimensions. Carr (2015) argues that consciousness could be conceptualized as a ‘higher’ dimension of spacetime. Given that it
is unlikely that we can understand qualia as particles or a force, this seems to be the
only alternative to give consciousness or qualia a place in a strictly physical model. Although Carr’s proposals are very controversial, it might therefore be worthwhile to entertain this thought a bit further. What would we gain if we, in line with Carr, conceptualize qualia as a dimension in spacetime?
The qualia dimension
Stanley (1999) proposed the concept of a qualia space: a topological space in which all
possible qualia are organized. Let us take this qualia space as a template for our qualia
dimension. Where, how, and why this space came into being we cannot and need not
answer for now. The qualia dimension contains all possible qualia, organized in such a
way that qualia that are alike are close together: the experience of blue is closer to the
experience of purple than to the experience of a high C# played on a piano; all qualia
experienced by me on Tuesday, October 21st, 2021, are closer together than the qualia
experienced by Emperor Augustus over 2000 years prior.
Whether qualia are organized as ‘integrated’ or ‘unified experiences’ (i.e., a single
point in this qualia dimension refers to one moment of a unified experience, in which
all sensory, cognitive, emotional, etc., aspects of a conscious moment are integrated),
or that they are organized as individual, loose elements (i.e., what we experience as an
integrated moment of conscious experience refers to several points in qualia space) is
an open question. Obviously, we experience the world as an integrated whole, which
would point towards the first option, but there is some psychophysical evidence that
suggests that this ‘wholeness’ of conscious experience may be an illusion, and that different elements of a conscious experience may in fact be asynchronous ‘micro-consciousnesses’ (Zeki and Bartels, 1998; see also Dennett and Kinsbourne, 1998.)
In a three-dimensional universe, we assign coordinates x, y, and z to a particle for
a given moment t. For a ‘conscious’ universe, we also need to assign a coordinate in this
qualia dimension: q. It is this position on the qualia dimension that gives a particular
physical state its ‘feel’ or ‘conscious state’. This q dimension is of course not an actual
spatial coordinate. Because we have an experience of the passage of time, we could at
least speculate that this qualia dimension has more in common with the temporal dimension than with the spatial dimensions.
8
Please note that this not implies in any way that every single elementary particle
‘has’ consciousness or has experiences. First, just as many particles can share the same
y-coordinate in a three-dimensional space, it is perfectly possible that many particles
(e.g., all the particles that make up my brain, or the particles that at any moment make
up the ‘neural correlate of consciousness’ in my brain) share the same position q on the
qualia axis. In other words, one quale can be associated with many different particles.
Moreover, as Stanley (1999) noted, it is conceivable that qualia space contains the quale
of ‘no experience’. If we wish to avoid the extreme interpretation of panpsychism
(namely, that for example, also rocks and trees are conscious), we could simply state
that particles that are part of a non-conscious system (whatever that may be) share the
q coordinate of ‘no experience’.
Even if we just take this idea as a metaphor rather than a factual description of
reality, it might serve as a useful ‘intuition pump’ (Dennett, 2013). For example, in consciousness research there are several proposals that very explicitly make the claim that
consciousness cannot be reduced to just brain activity. A notable example is Noë’s Out
of our heads (2010), in which Noë argues that consciousness exists as the interaction
between an organism and the world around it. From a strictly neuro-materialist point
of view, this seems difficult to grasp: how can consciousness exist outside a brain? However, it becomes easier to understand if we rephrase this in terms of our qualia dimension: in Noë’s view, to be in a specific conscious state, not only the particles of someone’s brain (or neural correlate of consciousness) need to be at a particular position q
on the qualia dimension, also the particles that make up the external environment need
to be at that q position.
The uncertainty principle and Schrödinger’s Cat
Although thinking about a ‘qualia dimension’ in terms of an intuition pump may be
useful, let us further explore the possibilities this concept offers when we make an attempt to integrate it into actual physical theory. First, we should note that the concept
of finding a particular particle at a given location in spacetime is not as straightforward
as it seems. The Heisenberg uncertainty principle makes short work of the idea that
particles have a specified location in spacetime. In contemporary physics, the Schrödinger equation describes the behavior of particles over time. Using the Born rule, we
can rewrite the Schrödinger equation as a function that gives us the probability of finding a given particle at a given moment:
𝑃(𝑥, 𝑦, 𝑧, 𝑡) = | Ψ(𝑥, 𝑦, 𝑧, 𝑡)* |
9
Given that we have introduced a new dimension q, we should extend the Schrödinger
equation (and associated probability function) accordingly:
𝑃(𝑥, 𝑦, 𝑧, 𝑞, 𝑡) = |Ψ(𝑥, 𝑦, 𝑧, 𝑞, 𝑡)* |
Interestingly, this means that for a given physical state, there is not a single quale corresponding to it, but rather a probability distribution of qualia, or, vice versa, for a given
quale, there is a distribution of possible physical states. As we speculated earlier, the q
dimension is most likely a temporal dimension rather than a spatial dimension. At its
core, the Heisenberg uncertainty relation is about the relation between knowledge of
spatial position versus temporal evolution (momentum). If we assume that the q dimension is a temporal (like) dimension, it follows that pinpointing a given spatial position of a particle reduces knowledge about its path through the qualia dimension; vice
versa, if we pinpoint a particle’s location or rather trajectory through the q dimension,
we lose information regarding its position in the spatial dimensions.
This is obviously not how we experience the world. Here we stumble upon the infamous measurement problem in quantum mechanics: the non-classical world of quantum mechanics is one of probabilities, yet our conscious experience is one of discrete
objects and events. Upon its observation, the probability function associated with a particle or system of particles collapses to a definite state. The interpretation of this collapse of the wave function is still highly debated in physics and philosophy. The Schrödinger equation is known to be the best description of reality we have: since Bell proposed his theorem in 1964 (Bell, 1964), many experiments have been done showing
that quantum mechanics is a complete theory, starting with Aspect, Grangier and Roger
(1980). Yet it cannot explain how and why wave function collapse occurs yet. Interestingly, the idea of a ‘qualia dimension’ may shed some new light on this problem.
First, there are several proposed solutions for the measurement problem. The most
common solution is the so-called Copenhagen Interpretation, which some physicists
have mockingly called the shut up and calculate’-approach (cf. Rosenblum & Kuttner,
2011): the Copenhagen Interpretation states that wave function collapse is real and is
explicitly agnostic with respect to the further metaphysical interpretation of the phenomenon. Other alternatives include the concept of decoherence: in this interpretation,
the wave function of a particle does not really collapse during a measurement, but rather becomes entangled with the wave function of a much larger measurement instrument. This much larger object forces the wave function of the measured particle into
10
an extremely skewed probability distribution, that for all practical purposes is indistinguishable from a discrete state.
There are, however, more exotic solutions. Von Neumann (1932, see also London
and Bauer, 1939), for example, proposed that conscious perception itself was responsible for the collapse of the wave function. Obviously, this ‘consciousness-causes-collapse
hypothesis’ is controversial. If true, it would mean that consciousness is placed outside
known physics. Other proposals might even sound wilder to non-physicists, such as
Everett’s Many Worlds model (Everett, 1957), the idea that upon every quantum measurement, the universe splits according to the possible outcomes of the measurement. A
lesser-known variant on the Many Worlds model is the Many Minds account, which
states that upon quantum measurement only a separate discrete consciousness percept
of the world splits off, while the physical world remains in its probabilistic state (Zeh,
1970).
What does the idea of qualia as a separate dimension tell us about wave function
collapse? First, we should note that this model explicitly discounts consciousness as a
causal factor in wave function collapse. In the qualia dimension-model, particles move
through spacetime (including the qualia dimension) according to the laws of physics,
but their movement through qualia space does not affect their wave function in any
way.
However, there is an additional interesting observation we can make: both the
Many Minds as the Many Worlds model appear to be compatible with the idea of a q
dimension. Given that, as stated earlier, the q dimension might be a temporal rather
than a spatial dimension, there is an uncertainty relation between a given quale or position in the q dimension and the position of a particle in the spatial dimensions. From
the perspective of a conscious observer, who can be sure to experience a particular
quale Q and thus knows his position in the q dimension, this means his spatial location
is probabilistic rather than deterministic. In a way, this resembles the Many Worlds
model (though not exactly, of course): upon a given observation of the state of the world
Q, a location on the q dimension, the observer knows that this observation must associated with a distribution of spatial coordinates, and not a fixed position - a multitude
of parallel spacetime solutions or ‘universes’, so to say. However, this also works the
other way around. Suppose we know the exact spatial location of a particle or system of
particles, we can only conclude that this spatial configuration must be associated with
a distribution of qualia. Fascinatingly, this is exactly what Zeh’s Many Minds interpretation states.
11
Moving through spacetime: what makes the clock tick?
One obvious problem with the q dimension model is that in this notion, qualia are not
events or processes that unfold over time and cease to exist after the event is over. Instead, all possible experiences exist at the same time, but also do not cease to exist after
we experienced them. This seems odd and, in a way, unsatisfactory: a model in which
everything may happen or even does happen seems not much of a scientific model at
all. However, implicitly we assume in this model that a quale, a coordinate on the q
dimension, is only ‘experienced’ if a particle is at that given location: the ‘qualia’ in the
q dimension are not true experiences, but rather ‘proto-qualia’ (cf. Russell’s panprotopsychism, see Torin and Pereboom, 2019). The problem, as we have seen, is that a
wave function collapse is required to give particles a discrete location in spacetime, including qualia space.
A collapse in both the Many Worlds as Many Minds interpretation, also in our
framework, is an illusory event - the wave function does not actually collapse; it just
appears to do so from the point of an observer. What might be problematic is that q
dimension-framework lacks a clear definition of what an event actually is. In our everyday experience, which in this view is primarily defined by the movement of the particles that make up our bodies through q space, concrete events happen. Our qualia are
experiences of a world of discrete objects and events. Adopting the Many Worlds or
Many Minds positions above would mean that we accept that everything happens and
occurs in parallel, but that we simply do not experience it that way.
If we do not wish to adopt a position in which everything happens at once, we will
have to introduce a collapse mechanism in the model which gives particles a definite
state in q space. However, subjective collapse positions, i.e., an interpretation of wave
function collapse in which the measurement or observation of an event is instrumental
in triggering a collapse, are almost anathema to the idea of a qualia dimension. As we
observed earlier, the idea that qualia (or rather, proto-qualia) exist as a dimension also
means they cannot affect the collapse of a wave function (the function that describes
the evolution of particles in spacetime, including the q dimension) in any way: it would
make the Schrödinger function self-referential. This appears to rule out the idea that
any subjective aspect of a measurement or observation could play a causal role in the
collapse of the wave function.
The most intuitive and elegant solution for this problem is the idea of an ‘objective
collapse’, a wave function collapse independent of measurement. Objective collapse
models are models that do not assign a causal role to observation or measurement in
the collapse process: under objective collapse models, collapses may also occur without
12
measurement. Examples are Penrose’s quantum gravity induced objective reduction,
or the class of Girhardi-Rimini-Weber (GRW) models. The latter class has the added
advantage of having some solutions that are compatible with general relativity (see
Maudlin, 2009, for an extensive discussion). The GRW-framework states that the wave
function of a particle will collapse at a random moment in its lifetime. For an individual
particle, this probability is very low - present parameter estimates for the decay are in
the range of 10,000 years, meaning that one would have to wait 10,000 years to be sure
for an individual particle’s wave function to collapse. However, if such a collapse occurs,
the wave functions of all particles the collapsing particle’s wave function is entangled
with, will also collapse.
Suppose that we extend this to let us say, a human brain. The brain is made up out
of countless particles. Even though the likelihood of an individual particle’s wave function to collapse is very low, because of their proximity and interactions, most particles
in the brain will be entangled. This means that if only one particle’s wave function collapses, the wavefunctions of the particles it is entangles with will collapse as well. Given
the large number of particles, we may reasonably assume that spontaneous collapses
occur regularly - even within an individual brain. Each collapse is then a discrete event
in which the particles of that individual brain plus its environment get a definite state
in spacetime, including the qualia dimension, and thus give reality its subjective ‘feel’.
These spontaneous collapses need not be limited to an individual brain, of course - if
we interact with the world, the wave functions of the particles in our brain become entangled with particles in the rest of the world as well. Any spontaneous collapse in the
wider system we are entangled with will result in a ‘moment of consciousness’ in this
view.
Another, more brain-oriented solution, would be to adapt Hameroff and Penrose’s
Orch OR model (see Hameroff and Penrose, 2014, for an overview). Orch OR, short for
orchestrated objective reduction, is a biologically inspired objective reduction model,
based on Penrose’s concept of quantum gravity. Orch OR postulates that microtubuli
in neurons in a state of quantum superposition can become entangled with each other,
to such an extent that such an entangled network of microtubuli may encompass one
or more brain areas. However, if the network becomes too large, the limit for quantum
gravity is exceeded and the entire systems collapses to a definite state. According to
Hameroff and Penrose such an objective collapse is one ‘frame’ of consciousness. This
would fit with the q dimension idea: upon objective collapse, particles would get a definite location in qualia space as well, and thus create a moment of conscious experience.
Of course, it should be noted that the key concepts in Orch OR, that is quantum gravity
13
and the idea that microtubuli can form entangled networks in the hot and noisy environment of the brain, remain unproven.
Non-determinism, free will, and causation
As Dennett (2018) notes, any discussion of consciousness is incomplete without at least
acknowledging the issue of free will. In the context of the present idea of a qualia dimension tied to quantum mechanics, this is relevant, as free will is - potentially - an
issue in the philosophy of quantum mechanics as well (cf. Rosenblum and Kuttner,
2011; see also Hardy, 2017). The idea of a q dimension is in principle agnostic with
respect to the issue of free will and determinism. Although most contemporary interpretations of quantum physics are non-deterministic, there are also determinist interpretations of quantum physics (e.g. Bohm’s pilot wave model), which would also be
compatible with the idea of a ‘q dimension’. However, the non-determinism in quantum theory creates several interesting possibilities regarding free will, intentionality,
causation, and the q dimension.
First, it is important to acknowledge that ‘free will’ in itself is also a sensation (cf.
Haggard, 2011; Wegner, 2017). As such, conscious states associated with free will, or
having made a decision, are also points in qualia space. Let us for now adopt the GRWinterpretation of the q dimension model: in the GRW-interpretation, wave functions
collapse at a random moment, with a non-deterministic outcome. We have already concluded that positions in the q dimension do not have any causal relation to the wave
function. In other words, the ‘feeling’ of willing something cannot have a causal influence on the unfolding of events as such. We might therefore conclude that the universe
we live in is not only undetermined, but also that we have absolutely no influence over
this non-determinism whatsoever: we are adrift on the oceans of probability - a conclusion perhaps even less desirable than strict (neuro)determinism, in which at least we
have a known course.
This conclusion may be a bit too fatalistic, though. First, we need to acknowledge
that, despite their inherent probabilistic nature, quantum processes are governed by
probability distributions: the Born rule gives us the probability of finding a particle at
a given position in spacetime. That probability can be anywhere between 0 and 1; only
upon collapse it becomes 0 or 1. The past trajectory of the particle, the environment, or
interactions it had, all influence these probabilities: some trajectories are more likely
than others. These trajectories are described the Schrödinger equation of (a system of)
particles, and in the context of the present model, also include movement through qualia space. This also means that we should give position in qualia space (i.e., conscious
14
experience) a similar standing as position physical space when considering the evolution of a particle or system of particles.
This latter conclusion is highly relevant in the discussion of free will. Let us explore
this a bit further. A conscious decision involves setting an outcome we wish to obtain
in the future. For example, the decision to get a glass of water involves moving my body
from my office to my kitchen, and later the experience of drinking water and quenching
my thirst. Given this decision, or at least, feeling the conscious sensation to do so, this
outcome is also rather likely - typically, once I have decided to go get a glass of water, I
will do so. In terms of the q dimension model, this is interesting: it means that once the
particles that make up my body have occupied the position of the quale ‘wanting a glass
water’, the trajectory of these particles through spacetime is now far more likely to converge with the shortest path to my kitchen, and to the q position of the experience of
drinking water. The probability functions guiding the trajectories of the particles of my
body have changed as compared to before being at the coordinate of ‘wanting a glass of
water’.
Obviously, it is a matter of debate how the particles making up my body arrived at
the q position of ‘wanting a glass of water’. Homeostatic processes, prior exposure to
water-related stimuli, neural activity that is not associated with consciousness - the entire history of the particles that make up my body will have influenced the probability
of ending up in the part of q space that makes up the sensation of wanting a glass of
water. Nonetheless, if we accept a non-deterministic account of quantum physics, the
wave function collapse that will have led to the actual sensation of wanting a glass of
water was an undetermined event: it could also not have occurred.
Can we now say that the conscious sensation of wanting a glass of water has caused
the probability of me consuming a glass of water to increase? This depends on what one
thinks about the underlying ontology and epistemology of the wave functions that make
up my body. It is possible to compute the trajectory of a hypothetical particle in my
brain from the point in spacetime where it is at the position in q space corresponding
to ‘wanting a glass of water’ to the point at which it is in my kitchen. As such, the path
from wanting a glass of water to getting a glass of water already exists. However, we do
not know whether the particle will follow that path until we know it had a definite state
in the q coordinate of ‘wanting a glass of water’. So, is this ‘causation’? Perhaps not in
the normal sense of the word - were we agnostic with respect to the actual content of
conscious experience (i.e., the specific q coordinate), we would simply see a quantum
system evolve over time, without any apparent teleology or agent-induced causation.
However, perceived from the perspective of an agent with free will (which would be a
15
particle or system of particles that due to its specific configuration has access to coordinates in q space that correspond with the feeling of free will), it would feel like causation.
A final interesting, but extremely speculative possibility to consider is the idea of
curvatures in q space. From general relativity, we know that spacetime is curved - an
effect that we can even observe (cf. Dyson, Eddington & Davidson, 1920). This curvature affects the path particles follow through spacetime. Could q space also have a curvature, making some paths more likely than others? If so, this may be another mechanism behind the feeling we experience as ‘free will’: free will is a point in qualia space
that is like a gravity well or attractor, curving the path through qualia space (and the
other spacetime dimensions) towards it. Obviously, this is a very wild and speculative
idea, but nonetheless an entertaining thought.
Information, emergence, and entropy
Interesting and entertaining thought experiments about the curvature of a qualia space
aside, several big questions about consciousness and universe are not solved by invoking a qualia dimension. For example, why is the universe organized into living, conscious units with the capacity for conscious perception? Stanley’s (1999) concept of
qualia space explicitly contains a ‘no experience’ quale - the absolute zero point for consciousness. Why would any system of particles be at a different point in qualia space?
Cleeremans and Tallon-Baudry (2021) suggest that the function of consciousness
is to allow ‘feeling’ - a position that may sound somewhat circular. Hameroff may have
worded this position slightly different: in a 2015 talk on sexual reproduction in single
cellular organisms, he argued that amoebae reproduce sexually because ‘it feels good’
(amoebae, having microtubuli, would have conscious experiences in Hameroff’s interpretation of Orch OR). Although this argument may have been made slightly in jest, the
message is that qualia contain information that is not present in the physical system
(cf. Jackson, 1986).
Obviously, in the q dimension idea, adding an additional dimension does add information - an additional coordinate. But there is an interesting additional observation
to make: qualia themselves contain information about the other spacetime coordinates.
To produce particular sensations, for example, the experience of the color blue, a specific constellation of particles is required (photons of a particular wavelength, and most
likely the particles that make up the neurons associated with color perception in an
individual brain). This means that once we know a particle has a q coordinate corresponding to blue, we also gain information about the other particles that make up the
16
particle’s system. Although qualia in the q dimension model are fundamental properties of spacetime, we might thus also think of them as emergent properties in a functional sense.
Varley and Hoel (2021) argues that emergent properties serve a particular goal,
namely the reduction of noise at lower levels of description. There are cases in which
the temporal evolution of a complex system is better predicted when looking at emergent levels (e.g., a weather pattern, such as a hurricane) as compared to the constituent
levels (the air molecules that make up the hurricane) because of the noise that is present
at these lower levels (cf. Brownian motion of these air molecules). In these cases, we
can truly speak of an ‘emergent’ property with its own ontology rather than a convenient way of describing a system of particles.
There is an interesting parallel with the q dimension in this case. Even though qualia are fundamental, and not emergent properties, there are locations in qualia space
that would only be accessible if a system as a whole has certain properties. For example,
the feeling of ‘being me’ most likely requires a very specific configuration of particles.
Moreover, the evolution of this system - for example, should it have decided to get a
glass of water in the kitchen, as mentioned above - is easier and more accurately predicted by a single trajectory through q space than by the trajectories of all its constituent
particles in spacetime. In other words, there are configurations of particles in spacetime
for which the location in qualia space effectively functions as an emergent property. As
we have seen in the discussion free will, occupying some definite position in qualia
space may alter the probability functions of the evolution of the entire entangled system. This reasoning obviously also holds for locations in qualia space that may function
as emergent properties: once a system has occupied such a position in q space, the future probabilities of the evolution of its constituent particles are affected as well.
Given that we are already freely speculating at this stage, let us take things one step
further. If we accept that some states in q space result in changes in the probability
functions of the system of particles occupying that space, this means that this will introduce correlations in the system, but also in its interactions with the environment. In
their interpretation of the Second Law of Thermodynamics, Esposito et al. (2010)
demonstrate that correlations between a system and its environment are directly related to the production of entropy. Taken together, we could argue that a system that
has an ‘emergent’ q coordinate in its history - a system we may call a ‘conscious’ system
- is an entropy producing system.
We may note several parallels here between this conception of conscious systems
as entropy producing systems and the wider debate on the relation between information processing, entropy, and consciousness. In most mainstream contemporary
17
theories of consciousness, information processing is seen as a vital component of consciousness, with Tononi’s Integrated Information Theory (IIT) as perhaps the most explicitly information-oriented theory (see Tononi et al., 2016, for a review). Information
processing, though, cannot be seen independently from thermodynamics. Faist et al.
(2015) have demonstrated that any form of information processing that involves discarding information (such as an AND gate) requires work: to maintain a thermodynamical equilibrium, an information processing system releases heat into the environment, thus increasing overall entropy. This is striking, as it seems to lead to a similar
conclusion as we made earlier: conscious systems (interpreted as information processing systems) must be entropy producing systems.
We can easily deduce why this is the case, and where this parallel might come from:
information processing leading to conscious sensation, as it occurs in biological sensory
systems, does involve a significant amount of information reduction and information
loss. Processing in the retina, for example, already involves summation and integration
of neural signals from individual photoreceptors to ganglion cells, during which the
absolute activity levels of photoreceptors is transformed to a relative (difference) signal.
The original information (the firing decrease of photoreceptor cells) is quickly lost as
cis-retinal in photoreceptor cells is resynthesized and new visual input is received.
Moreover, conscious perception or even introspection is not instantaneous: estimates for the latency of conscious sensation up to 500 ms have been reported (Jolij and
Lamme, 2010; Scharnowski et al., 2008). In the q dimension model, the period between
registration of an external stimulus by a sense organ and the actual sensation, the particles that make up the brain move through spacetime and q space toward a particular
q coordinate corresponding to, for example, seeing a blue light. This trajectory of the
brain-system perceiving the blue light represents the steps necessary to reach a particular q coordinate, or, in the vocabulary of cognitive neuroscience, the processing required to perceive a given stimulus. During this transition from information registered
by a sense organ to a conscious percept information is necessarily lost, as noted above.
This means that entropy must be generated during processing (and thus the travel of
the constituent particles of the brain-system through spacetime). A similar argument
also holds for the sensation of free will - a process that may also take up 200 ms or
longer from the moment a decision become inevitable (Libet, 1983; Soon et al., 2008;
but see also Schultze-Kraft et al., 2016).
Obviously, there is a lot more to say about the relation between entropy, information, and consciousness in the context of the q continuum model. For example, is
the observation that certain points in q space actually contain information about the
configuration of particles in spacetime not counterintuitive? After all, according to the
18
Landauer principle (see Landauer, 1961), information is physical. It must therefore be
encoded in a configuration of particles. How can a coordinate on a dimension contain
information then? We may propose two possible answers: first, we have already established that the q dimension is more like a temporal dimension than a spatial dimension.
Given that the Second Law of Thermodynamics gives a specific direction to time, a temporal coordinate does contain information about potential configurations of particles
in space: since entropy increases with time, a time coordinate further from origin is
more likely to be associated with higher entropy states (i.e., states in which particles
are distributed more randomly over space). As such, there is at least some information
in just the temporal coordinate of a system. Given that the q dimension is most likely
more like a temporal than a spatial dimension, we may allow for the q coordinate to
contain information as well.
A second, more metaphysical approach to the question how q coordinates relate to
information, would be to consider the idea of agency or intentionality. The concept of
information is directly related to uncertainty reduction (Shannon, 1948). This raises
the question: whose uncertainty? Extrapolating on Maxwell’s famous demon (Maxwell,
1867), Smoluchowski (1914) recognized that the Second Law of Thermodynamics could
potentially be violated by an intentional observer: an agent with knowledge about a
thermodynamic system is in principle able to extract work from a heat bath. Szilard
(1929) demystified the role of ‘intelligent beings’ in this apparent violation of the Second Law of Thermodynamics and demonstrated that any system with a sort of memory
(no matter how rudimentary) could play the role of ‘intentional observer’, as long as the
information stored in this memory would be fed back into the system. Moreover, the
presence of a ‘memory’ requires a system consisting multiple particles. Szilard (1929)
showed that such a system requires at least two particles that both are entangled with
a larger system (i.e., the environment or heat bath).
How does this relate to the broader questions about information, intentionality
and consciousness? Memory processes, such as described by Szilard (1929), draw information from their surroundings, and thus decrease entropy in the environment, in
apparent violation of the Second Law of Thermodynamics. However, this entropy is fed
back into the environment as heat when it is destroyed (cf. Landauer, 1961), restoring
the balance, although this only applies to systems which interact with their environment in such a way they store information about that environment, and use that information for subsequent interactions with the environment. A rock, for example, would
not be a prime example of an information processing system in this context. Although
it could technically be used as an information storage device (e.g., after a rock has been
heated, the decrease in temperature gives some indication of the amount of time that
19
has passed since heating it), the system of particles that makes up the rock does not
actually use this information in an intentional way.
Interestingly, memory formation has been argued to play a critical role in consciousness: Lamme (2003), for example, argues that memory formation is the neural
correlate of consciousness. In other words, when information extracted from the environment is permanently stored in the physical medium of the brain, this equals to a
moment of consciousness. Please note that this does not mean that all information processing in the brain is conscious - as stated above, a lot of information is processed
without awareness and subsequently destroyed (thus releasing heat, according to the
Landauer principle). Interestingly, within the q dimension model, storing information
in memory would not contradict the Second Law of Thermodynamics: the processing
leading to consciousness must produce entropy, as we have seen above.
This, however, does still not answer the question why the universe evolved to a
state in which matter is organized into at least 7.7 billion (and most likely infinitely
more) complex systems with access to q space coordinates that support the rich inner
life we experience. On this issue we can only speculate. It might be that the observation
that conscious systems produce entropy is significant is this respect: the evolution of
complex systems, such as organic molecules, and living matter, requires some amount
of entropy. We might hypothesize that during the early evolution of the universe the
first (proto)-conscious systems started producing sufficient entropy for more complex
systems to arise, analogous to how the evolution of plants on Earth provided the necessary oxygen for animals to evolve. However, such speculations, though amusing, are
far out of the scope of the present paper. Let us first consider whether it is at all possible
to come up with a research program to verify whether the ideas proposed here may be
empirically verified at all.
Empirical verification and falsification
We have now arrived at a point where speculations regarding the model have become
rather wild. It should be obvious now to the reader that the idea of consciousness or
qualia as a physical dimension of spacetime has some alluring properties, and allows
for interesting digressions, associations, and philosophizing. However, linking a novel
theory to earlier work or post hoc ‘explaining’ phenomena with a novel theory is - although a necessity in theory building - relatively easy. The proof of the pudding is coming up with constraints and in particular possibilities for empirical verification and
above all, falsification.
20
One of the main issues when testing assumptions about the metaphysical nature
of the mind-brain relationship is that we are forced - or possibly, we could argue,
doomed - to look at phenomena that are counterexamples of the contemporary materialist dogma that mind and brain activity are fully equivalent. Obviously so-called paranormal phenomena, collectively referred to as ‘psi’, come to mind. This is both interesting and slightly worrying at the same time. Parapsychological results have been met
with intense skepticism, even to such an extent that they have been labeled as ‘psychology’s placebo condition’ in the context of the replication crisis that has been plaguing
psychology for the past decade (e.g. Wagenmakers et al., 2011) - a positive finding of a
parapsychological effect is according to many researchers a set of results that cannot be
true and therefore must signal a problem with either the execution of an experiment of
the analysis of the data. Resorting to such results to further build upon the already
highly speculative theory proposed here seems risky at least.
However, it should be noted that the intense skepticism exposed by some scholars
may not be wholly justified. Many critics of parapsychology, whist not necessarily
agreeing with conclusion regarding the interpretation of several results, do
acknowledge that the procedures and methods used by academic parapsychologists are
well up to the standards in scientific practice (see e.g., French, 2018; Hyman, 1995).
More importantly, the assertion that specific results ‘cannot be true’ is a philosophical
assumption - as a matter of fact, the philosophical assumption we set out to test in the
first place, namely that ‘the mind’ or ‘consciousness’ is equivalent to the known physical
processes occurring in the brain. As such, I will ask the reader for some open-mindedness regarding the evaluation of parapsychological research, as this area of research
appears to be a very interesting venue for potential empirical tests of the q dimension
model, and, vice versa, the q model provides a fruitful model to understand psi results
without having to rewrite the laws of physics.
The q dimension model makes several speculative assumptions, but based on those
assumptions, we can also make predictions about qualia states, and how these relate to
physical events. At its core, the q dimension model starts out as a variation on epiphenomenalism, the idea that specific mental states are equivalent to specific physical
states. However, the critical addition is that because of the probabilistic nature of the
Schrödinger equation, the relation between physical states and mental states in the q
dimension model is probabilistic, rather than deterministic as in epiphenomenalism
(at least, as most neuroscientists would understand epiphenomenalism). A second assumption is the idea that qualia space or the qualia dimension is topologically organized - a less speculative assumption, based on Stanley (1999).
21
Together, these two assumptions allow for an interesting observation: given the
probabilistic nature of the relation between mental and physical states, sometimes our
experience should be ‘off’ - ‘off’ in the sense that we experience something that is out of
line with most of our experiences. Given an extreme enough deviation from normal
probability, (some of) the particles that make up my brain could in very rare circumstances find themselves at a q coordinate that is normally occupied by my dog, or at a
q coordinate that does not match my present temporal or spatial coordinates, for example. Such experiences would appear to the subject as ‘extra sensory perception’: experiencing a quale normally experienced by someone else would appear as ‘telepathy’;
experiencing a quale that has been displaced in space would appear as ‘clairvoyance’; a
displacement is time could appear as ‘precognition’. It is important to note, though,
that under the q model, the interpretation of such occurrences as ‘perception’ would be
wrong: it is not ‘perception’ in the normal sense, i.e., the intentional gathering of information from the environment in order to adapt behavior, but we would rather characterize such events (somewhat unceremoniously) as ‘freak incidents’, or indeed, ‘exceptional experiences’.
Although such exceptional experiences are tangent on the probabilistic nature of
the wave function making up an individual, this does not mean they are completely
unpredictable or random if the q model is correct. Let us consider an example like telepathy, the phenomenon that information is shared between two individuals, let us
call them Alice and Bob, via a non-physical way: there is no interaction in normal
spacetime (i.e., the physical dimensions of the universe) - direct or indirect - between
the particles that make up Alice and Bob. In the q-model, we would interpret this as a
situation in which (some) the particles that make up Alice find themselves in the q space
normally taken up by Bob. The probability of such a thing happening is of course larger
if Alice’s position in q space is close to that of Bob. This is obviously the case if Alice is
physically close to Bob, but also when Alice and Bob share the same experiences (e.g.,
when they are watching the same TV show), as q space is topologically organized (cf.
Stanley, 1999): similar qualia are closer together in q space. This leads to a specific prediction regarding anomalous experiences: these should occur more often when individuals are close together in q space. In experimental parapsychology, this is not an unusual observation. In Ganzfeld telepathy experiments, for example, participants are often asked to meditate together prior to the experiment (see e.g., Bem and Honorton,
1994), resulting in a similar state of mind, and thus a closer position in q space.
It should be noted however, that the evidence for anomalous phenomena in laboratory experiments is extremely controversial. At the very least, it should be noted that
22
anomalous effects are deviously difficult to replicate in laboratory settings. This is indeed to be expected under the q model: anomalous experiences are the result of probabilistic processes. The best we can hope to achieve in a laboratory setting is to manipulate probabilities, and such increase the likelihood of paranormal phenomena to occur. Given the relative rarity of anomalous phenomena, though, it is very likely that any
experimental verification of anomalous effects in a laboratory setting is going to require
an enormous amount of data (see also Bierman et al., 2016). A better alternative to
laboratory experiments might therefore be to look at occurrence of spontaneous paranormal phenomena. According to the logic laid out above, more spontaneous phenomena should be reported when many individuals share (a set of) experiences, for example
during global events such as major news events.
Of course, it is interesting to note that anomalous phenomena during major news
events have been reported by Nelson (2006, but see Bancel, 2017 for a critical discussion and alternative interpretation) as part of the Global Consciousness Project, although these events concern aberrations in the behaviour of random number generators, and not the frequency of spontaneous cases. However, given the abundance of
archives of spontaneous cases, it should not be too difficult to do an archive study and
check this prediction of the q model, although a prospective analysis of frequency of
spontaneous reported anomalous experiences would of course the preferred experiment.
However, a more powerful test of the model would be to specify one or situations
that cannot be explained by the physical laws operating in the physical dimensions of
the universe, but that are unique to the q dimension model. In other words, a critical
confirmatory test for the model would be a reliable demonstration of a correlation between q space and physical space that cannot be explained by physical laws purely operating in the physical dimensions. One possibility that comes to mind is a further investigation of anomalies in the outputs of random number generators used in parapsychological experiments, as observed by for example Von Lucadou (reviewed in Von Lucadiou, 2011). In such experiments, participants are asked to manipulate the direction
of motion of a stimulus on screen using an alleged ‘secret combination’ of keys of a
computer keyboard. Unbeknownst to the participant, however, the motion is fully controlled by a random number generator, and not by an actual secret key combination.
In these experiments, whether the participant is successful in controlling the motion of the stimulus is purely random, as is to be expected. However, Von Lucadou and
others report statistical anomalies in the output of the random number generator used
in the experiment, but only for the duration that a participant was actively engaging
with it, albeit indirectly (Von Lucadou, 2011; Walach et al., 2020; but see also Jolij and
23
Bierman, 2019 for a report of anomalous correlations in a setting without a hardware
RNG; and Grote, 2021 for a negative finding). Most importantly, these anomalies show
up as correlation between random aspects of the participants’ behaviour (such as reaction times) and the output of the random number generator. However, the exact pattern of correlations cannot be predicted beforehand.
Von Lucadou and co-workers interpret these findings in the context of a ‘generalized quantum theory’ (Atmanspacher, Römer & Walach, 2002). According to this theory, the correlations observed by von Lucadou are entanglement correlations between
the random number generator and the participant. These entanglement correlations
between macroscopic systems are possible in the GQT framework, as it proposes that
the Planck constant, h, can be dropped from the Heisenberg uncertainty relation. This
results in macroscopic systems being able to show quantum entanglement. This entanglement is lost, however, when one attempts to use it as a signaling medium: according
to Von Lucadou, the ‘no-communication theorem’, a theorem from quantum information theory that forbids communication using non-locality in quantum physics, also
applies in generalized quantum theory. In the case of parapsychological phenomena, a
‘signal’ would be a useful signal from the future, for example. According to GQT, such
signals are impossible, hence the great difficulties parapsychologists are having in obtaining reliable effects in the lab: whenever a phenomenon, such as precognition, is
reliably present, it may be used as a ‘signal’, which destroys the entanglement correlations necessary for the phenomenon to occur.
GQT, however, is rather poorly specified as to how it would work in practice. For
example, it does not provide a mechanism for how and why entanglement correlations
within a system come to exist, or even what comprises a ‘system’ in the sense of GQT.
According to Von Lucadou, GQT should therefore rather be seen as a ‘metaphor’, describing the occurrence of odd correlations in the output of random number generators,
using concepts from quantum mechanics rather than (an extension of) physical theory
(Von Lucadou, personal communication, 2016).
Interestingly, the q model also predicts correlations within what Von Lucadou refers to as ‘psycho-physical systems’ (i.e., a system in which a human interacts - in some
way - with a probabilistic device such as random number generator), but for another
reason than metaphorical macroscopic quantum entanglement. In the q model, systems that move through q-space necessarily produce entropy: from sensation to sensation, information the system has picked up from the environment necessarily is lost
and is dissipated into the environment. Esposito et al. (2010) have demonstrated that
this can be mediated by the introduction of correlations between the system and heat
24
sinks in the environment. These correlations, surprisingly, are negative: almost paradoxically, to maintain thermodynamic equilibrium in the long term, the introduced correlations can in some cases result in a local decrease in entropy, or, in other words, an
increase in information. A similar idea is introduced by Cerf and Adami (1995) in their
interpretation of quantum information theory: they introduce the concept of ‘negative
information’, or the possibility of information to flow back from an observer or measurement system into the environment to maintain an information equilibrium in quantum systems.
Let us apply this to an information processing system moving through q space,
interacting with a random number generator. At least some of the information such a
system produces during its trajectory is destroyed and needs to be released back into
the environment. The question is: where does this information go? Esposito et al.
(2010) state that negative entropy correlations dissipate quickly in a large macroscopic
system and are therefore negligible; one of the reasons we do not see information spontaneously materialize in our environment (although one might argue - very speculatively - that some spontaneous psi phenomena such as extraordinary coincidences
might be just that, but we will get back later to this speculation).
Let us now focus on the rather unusual case of the Von Lucadou-style parapsychological experiments, in which unexpected correlations appear in the output of random
number generators. Obviously, there is no direct physical interaction (i.e., an interaction in xyz-space) between the number generators and the research participants. However, if we look at the macrosystem, consisting of the particles making up the participant, and the particles making up the RNG, there must be an interaction in the q dimension. Given that the participant does indeed interact with the RNG, this does not
seem completely unreasonable. The q model does not put any restrictions on particles
that make up one ‘moment of consciousness’: as argued earlier, a ‘moment of consciousness’ is not restricted to an individual brain, but a function of all particles in a
given system. So, the interaction or ‘entanglement’ between the RNG and the participant can be mediated via a force or direct interaction in the q dimension, rather than
in normal spacetime.
It is important to realize that the random number generators typically used in
these experiments produce random numbers by means of quantum mechanical processes, for example by sampling quantum tunneling in a Zener diode, or by using quantum optics, and that by design, they are in a maximally entropic state. In any system
that includes such a number generator, and in which negative entropy is fed back into
the environment, random number generators may function as the opposite of a heat
25
sink, namely an ‘information sink’: it would be the first place where the negative entropy correlations may show up, or at least would be noticeable, when information in
an information processing system is destroyed. This explains the odd patterns observed
by Von Lucadou, but possibly also by Nelson and others: the correlations showing up
in the output of random number generators are not a ‘signal’, but the negative entropy
produced by an information processing system or agent, flowing back into an ‘information sink’ (i.e., the RNG).
However, we can (and should) go beyond merely explaining Von Lucadou’s results
to provide a test for the q model - as stated earlier, post hoc explanations are the easy
part of theorizing. Using the q model, it is possible to make a prediction about the relative magnitude of the effect. We would need a setting in which participants interact
with an RNG in two conditions that are as equal as possible, and only differ in the
amount of ‘unconscious’ or ‘preconscious’ information processing, as this is the information that is lost or destroyed and will be dissipated back into the environment. The
prediction that follows from the q model is that this dissipated information will show
up in the RNG, and that the magnitude of this effect will be larger for the condition in
which information is lost during ‘unconscious’ processing.
One important issue we need to note here is that information and information processing are terms that are used very loosely in (cognitive) psychology and neuroscience,
and rarely (if ever) directly refer to information in the sense of Shannon-information.
This makes quantitative predictions for the amount of entropy feedback as a result of
information loss on the basis of, for example, the Lindauer principle, virtually impossible. However, it should be possible to at least construct an experiment in which the
amount of information loss - even in the Shannon sense - is manipulated between conditions. Although we cannot make absolute quantitative predictions, we should be able
to make relative predictions: if two conditions of information processing differ in the
amount of information that is lost prior to a moment of consciousness, the condition
with the larger amount of information loss should be associated with a larger anomalous effect in the number produced by the random number generator.
Many classical psychological paradigms that involve learning and/or deliberation
would be suitable for such an experiment. The simplest experiment would be to have
participants presented with a list of word or number pairs, after which they take a test
on these word pairs. Critically, between the initial study phase and the test there needs
to a break; one group of participants will be asked to study the words further (thus
resulting in transfer to long term memory, and thus more conscious recall during the
test phase), whereas the other group gets a distracting task in between, resulting in
26
forgetting, or in other words, information loss. Obviously, one would need to incorporate a random number generator, but this can be done in several ways - from using the
RNG to randomize the order of stimuli to generating numbers if number stimuli are
used. Since the entanglement or correlation between the participant and the number
generator is realized in q space, the interaction requires that the output of the number
generator is in some way used to determine the conscious state of the participant, which
can be done in many ways.
The prediction for this experiment is that, on average, the number generator will
show larger anomalies for the group that is distracted between initial presentation of
the stimuli and the test than for the group that is given the opportunity to study the
items between initial presentation and test. Moreover, we would expect a negative correlation between the scores on the test and the RNG anomalies observed for an individual participant: a lower test score would be indicative of more forgetting, and thus
of more information loss, which is associated with larger anomalies in the RNG output.
Interestingly, there may be real life analogies to the situations described above.
Von Lucadou has linked his results to the controversial notion of synchronicity (Von
Lucadou, Römer, and Walach, 2007), a concept coined by Carl Jung (1952) to describe
‘meaningful coincidences’. According to Jung, such occurrences are examples of entanglement-like correlations mediated via an unknown medium, an idea he later fleshed
out with physicist Wolfgang Pauli in their ‘unus mundus’ model. The idea that there are
‘unseen’ connections in the world is of course not new - it is commonplace in Eastern
philosophy and made its way into Western thinking via Schopenhauer (1818), although
it has been claimed that most philosophical, mystical, and spiritual traditions worldwide have some elements of this idea (see Huxley, 1945). Synchronicity, and the associated notion of a ‘deeper connection’ are obviously popular ideas in folk psychology
(see for example Jaworski, 2011), since most people will have experienced the phenomenon at least once in their lives (see e.g., Wahbeh et al., 2021).
However, from a scientific point of view, ‘remarkable coincidences’ are not seen as
particularly meaningful. Most instances of synchronicity can either be easily explained
as simple causal relationships between events (i.e., there is no remarkable coincidence,
as there is no coincidence in the first place), the post-hoc construction of meaning or
even confabulation, or simply statistical flukes - given there are 8 billion people on this
planet, something remarkable is bound to happen to someone every single day: every
lottery has a 100% chance of having a winner; the chances of that winner being you is
remotely small, however.
Nonetheless, like we have seen earlier with other exceptional experiences, the q
model gives an interesting interpretation of synchronistic events. In Von Lucadou-style
27
experiments, an RNG functions as an information sink, allowing for anomalous correlations to occur. However, information sinks might not be limited to RNGs. Any process
or system with enough degrees of freedom (or a high enough entropy) may function as
an information sink. Moreover, an odd feature of the q model is that systems can interact in a ‘nonphysical’ way, that is, not via xyz-space (of course, in the q model, qualia
space is just as physical als xyz-space, so all interactions between particles are physical
and mediated via the laws of physics, not by unknown or mystical forces) - that is, interactions via proximity in q space provide an additional valve for the dissipation of
negative entropy.
Let us now speculatively give an account of synchronicity in the q model: experienced ‘meaningful coincidences’ are, following Von Lucadou’s logic, expressions of information destroyed during ‘unconscious’ processing feeding back into a system. Interestingly, this is remarkably close to Jung’s original interpretation of synchronicity: although most folk interpretations of remarkable coincidences are along the lines of “the
universe telling us something” (cf. Jaworski, 2011), Jung’s notion was that synchronicity reflects unconscious processes of some sort that manifest themselves in the external
world (Jung, 1952).
Summing up, although the q model is very speculative and very poorly specified
for now, it is possible to come up with a set of testable predictions - even though these
predictions are at odds with our normal understanding of the physical world. That, one
might argue, makes these predictions stronger rather than weaker. Moreover, these
predictions can be tested not just ‘in principle’, but in a series of rather straightforward
psychological experiments - somewhat perplexingly, we may have stumbled upon a
metaphysical model that may be testable using the simplest of psychological experiments.
Conclusion
In this paper, I have laid out a speculative model describing how conscious experience
may be integrated with our physical worldview, namely by introducing consciousness
as a (physical) dimension of the universe, a view compatible with (proto)panpsychism.
Although the idea appears to be far-fetched at first sight, once we accept the idea of a
‘consciousness space’ or ‘q dimension’, through which particles move just as they move
through normal spacetime, and which gives the universe its subjective ‘feel’ at a given
moment in time, a surprisingly coherent worldview emerges that does not invoke any
mysterianism to solve the mind-body problem.
28
Of course, the model presented here is wrong - all models are. Nonetheless, I at
least believe to be useful. For example, the model works as an interesting metaphor or
’intuition pump’ when thinking about equivalencies between mental and physical states
and allows for thinking ‘outside the brain’ when considering ideas such as Noë’s view
that consciousness arises from interaction with the world and is therefore not confined
to the physical brain (Dennett, 2013; Noë, 2015). However, the model itself may have
its merits as well. First, apart from explaining a range of phenomena from physics to
parapsychology, it yields explicit and testable predictions, which is a rather unique feature for a metaphysical model of consciousness. Whether the model is correct or not, I
do believe that the line of reasoning I have adopted here is a useful one: by careful analysis and deduction, it should be possible to come up with models or proposals that are
testable, even though they deal with the ineffable. Too many metaphysical approaches
to consciousness are poorly constrained, and might have their appeal, but fall short
where it comes to possibilities empirical verification or falsification.
I hope to have shown that is in fact is possible to come up with a non-materialist,
in this case panpsychist, model that is - to some extent - falsifiable, which was the main
goal of the present paper. Of course, this idea is not new. Arthur Schopenhauer already
coined the term ‘empirical metaphysics’ when discussing anomalous phenomena he
believed to be demonstrate the existence of a deeper reality, the world of Will (see Gerding, Van Dongen & Sneller, 2011); in the philosophy of physics, physicist-philosopher
Abner Shimony recognized the immense value of quantum physics experiments for our
fundamental and metaphysical understanding of the world (Shimony, 1978). I believe
that an experimental metaphysics of consciousness is not only possible, but necessary
if we want to truly solve or understand the mystery of consciousness, and that the model
presented here may at least inspire others to come up with better models of their own.
29
References
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
Aspect, A., Grangier, P., & Roger, G. (1981). Experimental tests of realistic local theories via Bell's theorem. Physical review letters, 47(7), 460.
Atmanspacher, H., Römer, H., & Walach, H. (2002). Weak quantum theory: Complementarity and entanglement in physics and beyond. Foundations of physics, 32(3),
379-406.
Bancel, P. (2017). Determining that the GCP is a goal-oriented effect: A short history. Journal of Nonlocality, 5(1).
Bell, J. S. (1964). On the Einstein Podolsky Rosen paradox. Physics Physique
Fizika, 1(3), 195.
Bem, D. J., & Honorton, C. (1994). Does psi exist? Replicable evidence for an anomalous process of information transfer. Psychological Bulletin, 115(1), 4.
Bierman, D. J., Spottiswoode, J. P., & Bijl, A. (2016). Testing for questionable research
practices in a meta-analysis: An example from experimental parapsychology. PloS
one, 11(5), e0153049.
Carr, B. (2015). Higher dimensions of space and time and their implications for psi.
Castillo, R. J. (1990). Depersonalizatipn and meditation. Psychiatry, 53(2), 158-168.
Cerf, N. J., & Adami, C. (1997). Negative entropy and information in quantum mechanics. Physical Review Letters, 79(26), 5194.
Chalmers, D. J. (1995). Facing up to the problem of consciousness. Journal of consciousness studies, 2(3), 200-219.
Chalmers, D. J. (1999). Précis of The Conscious Mind. Philosophy and Phenomenological Research, 59(2), 435-438.
Cleeremans, A., & Tallon-Baudry, C. (2021). The function of consciousness is to generate experience.
Cochrane, T. (2021). A case of shared consciousness. Synthese, 199(1), 1019-1037.
Crick, F., & Koch, C. (1992). The problem of consciousness. Scientific American, 267(3), 152-159.
Dennett, D. C. (2013). Intuition pumps and other tools for thinking. WW Norton &
Company.
Dennett, D. C. (2018). Facing up to the hard question of consciousness. Philosophical
Transactions of the Royal Society B: Biological Sciences, 373(1755), 20170342.
Dennett, D. C., & Kinsbourne, M. (1992). Time and the observer: The where and when
of consciousness in the brain. Behavioral and Brain sciences, 15(2), 183-201.
Dyson, F. W., Eddington, A. S., & Davidson, C. (1920). IX. A determination of the deflection of light by the Sun's gravitational field, from observations made at the total
eclipse of May 29, 1919. Philosophical Transactions of the Royal Society of London.
Series A, Containing Papers of a Mathematical or Physical Character, 220(571-581),
291-333.
Esposito, M., Lindenberg, K., & Van den Broeck, C. (2010). Entropy production as correlation between system and reservoir. New Journal of Physics, 12(1), 013013.
Everett III, H. (1973). Relative state formulation of quantum mechanics, Reviev of
modern physics 29, 1957. Reprint in DeWitt and Graham, 454-467.
Faist, P., Dupuis, F., Oppenheim, J., & Renner, R. (2015). The minimal work cost of
information processing. Nature communications, 6(1), 1-8.
Forstmann, M., & Burgmer, P. (2021). The Cartesian Folk Theater: People conceptualize consciousness as a spatio-temporally localized process in the human brain. Journal of Experimental Psychology: General.
30
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
Frankish, K. (2021, July). Panpsychism and the depsychologization of consciousness.
In Aristotelian Society Supplementary Volume (Vol. 95, No. 1, pp. 51-70). Oxford University Press.
French, C. C. (2018). Reflections on pseudoscience and parapsychology: From here to
there and (slightly) back again. In A. B. Kaufman & J. C. Kaufman (Eds.), Pseudoscience: The conspiracy against science (pp. 375–391). Boston Review. https://doi.org/10.7551/mitpress/9780262037426.003.0017
Gerding, H., Van Dongen, H., & Sneller, R. (2011). Wilde beesten in de filosofische
woestijn. Amsterdam: Boom.
Giummarra, M. J., Bradshaw, J. L., Nicholls, M. E., Hilti, L. M., & Brugger, P. (2011).
Body integrity identity disorder: deranged body processing, right fronto-parietal dysfunction, and phenomenological experience of body incongruity. Neuropsychology
Review, 21(4), 320-333.
Goff, P. (2019). Galileo's error: Foundations for a new science of consciousness. Vintage.
Grote, H. (2021). Mind-Matter Entanglement Correlations: Blind Analysis of a New
Correlation Matrix Experiment. Journal of Scientific Exploration, 35(2).
Haggard, P. (2011). Decision time for free will. Neuron, 69(3), 404-406.
Hameroff, S., & Penrose, R. (2014). Consciousness in the universe: A review of the
‘Orch OR’theory. Physics of life reviews, 11(1), 39-78.
Hardy, L. (2017). Proposal to use humans to switch settings in a Bell experiment. arXiv preprint arXiv:1705.04620.
Huxley, A. (1945). The perennial philosophy. Harper & Brothers.
Hyman, R. (1995). Evaluation of the program on anomalous mental phenomena. Journal of Parapsychology, 59, 321-352.
Jackson, F. (1986). What Mary didn't know. The Journal of Philosophy, 83(5), 291295.
Jaworski, J. (2011). Synchronicity: The Inner Path to Leadership. Berrett-Koehler Publishers.
Jibu, M., & Yasue, K. (1995). Quantum brain dynamics and consciousness: an introduction (Vol. 3). John Benjamins Publishing.
Jolij, J., & Bierman, D. (2019). Two Attempted Retro-Priming Replications Show Theory-Relevant Anomalous Connectivity. Journal of Scientific Exploration, 33(1).
Jolij, J., & Lamme, V. A. (2010). Transcranial magnetic stimulation-induced ‘visual
echoes’ are generated in early visual cortex. Neuroscience letters, 484(3), 178-181.
Jung, C. G. (1952/2012). Synchronicity: An Acausal Connecting Principle (From Vol.
8 of the Collected Works of C.G. Jung). Princeton University Press.
Keppler, J. (2021). Building Blocks for the Development of a Self-Consistent Electromagnetic Field Theory of Consciousness. Frontiers in Human Neuroscience, 572.
Koch, C. (2019). The feeling of life itself: why consciousness is widespread but can't
be computed. Mit Press.
Lamme, V. A. (2003). Why visual attention and awareness are different. Trends in
cognitive sciences, 7(1), 12-18.
Lamme, V. A. (2006). Towards a true neural stance on consciousness. Trends in cognitive sciences, 10(11), 494-501.
Landauer, R. (1961). Irreversibility and heat generation in the computing process. IBM
journal of research and development, 5(3), 183-191.
Laukkonen, R. E., & Slagter, H. A. (2021). From many to (n) one: Meditation and the
plasticity of the predictive mind. Neuroscience & Biobehavioral Reviews.
Libet, B., Wright Jr, E. W., & Gleason, C. A. (1983). Preparation-or intention-to-act, in
relation to pre-event potentials recorded at the vertex. Electroencephalography and
clinical Neurophysiology, 56(4), 367-372.
31
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
•
London, F., & Bauer, E. (1939). La théorie de l'observation en mécanique quantique (Vol. 775). Hermann & Cie.
Maudlin (2009). General relativity and quantum non-locality.
Maxwell, J.C., (1867), Letter to P.G. Tait, 11 December 1867, in Life and Scientific
Work of Peter Guthrie Tait, C.G. Knott (author), Cambridge: Cambridge University
Press, 1911, pp. 213–215.
Nelson, R. (2006). The global consciousness project. Explore, 2(4), 342-351.
Ney, A. (2016). Microphysical causation and the case for physicalism. Analytic Philosophy, 57(1).
Noë, A. (2009). Out of our heads: Why you are not your brain, and other lessons
from the biology of consciousness. Macmillan.
Revonsuo, A. (2021). The explanatory gap: Progress and problems. Psychology of
Consciousness: Theory, Research, and Practice, 8(1), 91–
94. https://doi.org/10.1037/cns0000271
Rosenblum, B., & Kuttner, F. (2011). Quantum enigma: Physics encounters consciousness. Oxford University Press.
Scharnowski, F., Rüter, J., Jolij, J., Hermens, F., Kammer, T., & Herzog, M. H. (2009).
Long-lasting modulation of feature integration by transcranial magnetic stimulation. Journal of Vision, 9(6), 1-1.
Schopenhauer, A., Frauenstädt, J., & Hübscher, A. (1859). Die welt als wille und vorstellung (Vol. 2). Leipzig: Brockhaus.
Schultze-Kraft, M., Birman, D., Rusconi, M., Allefeld, C., Görgen, K., Dähne, S., ... &
Haynes, J. D. (2016). The point of no return in vetoing self-initiated movements. Proceedings of the National Academy of Sciences, 113(4), 1080-1085.
Shannon, C. E. (1948). A mathematical theory of communication. The Bell system
technical journal, 27(3), 379-423.
Shimony, A. (1978). Metaphysical problems in the foundations of quantum mechanics. International Philosophical Quarterly, 18(1), 3-17.
Signorelli, C. M., Szczotka, J., & Prentner, R. (2021). Explanatory profiles of models of
consciousness-towards a systematic classification.
Smoluchowski, M. von, 1914, “Gültigkeitsgrenzen des zweiten Hauptsatzes der Wärmtheorie”, Vorträge über die Kinetische Theorie der Materie und der Elektrizität, Leipzig: Teubner, 1914, pp. 89–121.
Soon, C. S., Brass, M., Heinze, H. J., & Haynes, J. D. (2008). Unconscious determinants of free decisions in the human brain. Nature neuroscience, 11(5), 543-545.
Stanley, R. P. (1999). Qualia space. Journal of Consciousness Studies, 6(1), 49-60.
Sytsma, J. M., & Machery, E. (2009). How to study folk intuitions about phenomenal
consciousness. Philosophical psychology, 22(1), 21-35.
Szilard, L., 1929, “On the Decrease of Entropy in a Thermodynamic System by the Intervention of Intelligent Beings”, Zeitschrift fur Physik 53: 840–856. English translation in The Collected Works of Leo Szilard: Scientific Papers, B.T. Feld and G. Weiss
Szilard (eds.), Cambridge, Massachusetts: MIT Press, 1972, pp. 103–129.
•
Tononi, G., Boly, M., Massimini, M., & Koch, C. (2016). Integrated information theory:
from consciousness to its physical substrate. Nature Reviews Neuroscience, 17(7),
450-461.
•
Torin, A., & Pereboom, D. (2019). Russellian Monism, The Stanford Encyclopedia of
Philosophy (Fall 2019 Edition), Edward N. Zalta (ed.), https://plato.stanford.edu/archives/fall2019/entries/russellian-monism/.
Varley, T., & Hoel, E. (2021). Emergence as the conversion of information: A unifying
theory. arXiv preprint arXiv:2104.13368.
•
32
•
•
•
•
•
•
•
•
•
•
Velmans, M. (2008). Reflexive monism. Journal of Consciousness Studies, 15(2), 550.
von Lucadou, W. E. M. (2011). Complex environmental reactions, as a new concept to
describe spontaneous “paranormal” experiences. Axiomathes, 21(2), 263-285.
von Lucadou, W., Romer, H., & Walach, H. (2007). Synchronistic phenomena as entanglement correlations in generalized quantum theory. Journal of Consciousness
Studies, 14(4), 50.
von Neumann, J., 1932, Mathematical Foundations of Quantum Mechanics, English
translation, Princeton, New Jersey: Princeton University Press, 1955.
Wagenmakers, E. J., Wetzels, R., Borsboom, D., & Van Der Maas, H. L. (2011). Why
psychologists must change the way they analyze their data: the case of psi: comment
on Bem (2011).
Wahbeh H, Fry N, Speirn P et al. Qualitative analysis of first-person accounts of noetic
experiences [version 2; peer review: 1 approved]. F1000Research 2021, 10:497
(https://doi.org/10.12688/f1000research.52957.2)
Walach, H., Horan, M., Hinterberger, T., & von Lucadou, W. (2020). Evidence for
anomalistic correlations between human behavior and a random event generator: Result of an independent replication of a micro-PK experiment. Psychology of Consciousness: Theory, Research, and Practice, 7(2), 173.
Wegner, D. M. (2017). The illusion of conscious will. MIT press.
Zeh, H. D. (1970). On the interpretation of measurement in quantum theory. Foundations of Physics, 1(1), 69-76.
Zeki, S., & Bartels, A. (1998). The asynchrony of consciousness. Proceedings of the
Royal Society of London. Series B: Biological Sciences, 265(1405), 1583-1585.
33 |
Entropy production of Multivariate Ornstein-Uhlenbeck processes correlates with
consciousness levels in the human brain
Matthieu Gilson1 , Enzo Tagliazucchi2 , Rodrigo Cofré3,4
1
arXiv:2207.05197v2 [q-bio.NC] 25 Jan 2023
Institut de Neurosciences des Systèmes INSERM-AMU, Marseille, France
2
Physics Department University of Buenos Aires and Buenos Aires Physics Institute Argentina
3
CIMFAV-Ingemat, Facultad de Ingenierı́a, Universidad de Valparaı́so, Chile
4
Institute of Neuroscience (NeuroPSI-CNRS) Paris-Saclay University Gif sur Yvette 91400, France
Consciousness is supported by complex patterns of brain activity which are indicative of irreversible non-equilibrium dynamics. While the framework of stochastic thermodynamics has facilitated the understanding of physical systems of this kind, its application to infer the level of
consciousness from empirical data remains elusive. We faced this challenge by calculating entropy
production in a multivariate Ornstein-Uhlenbeck process fitted to fMRI brain activity recordings.
To test this approach, we focused on the transition from wakefulness to deep sleep, revealing a
monotonous relationship between entropy production and the level of consciousness. Our results
constitute robust signatures of consciousness while also advancing our understanding of the link
between consciousness and complexity from the fundamental perspective of statistical physics.
Animal cognition is the most sophisticated example of
information processing found in biological and technological systems [1]. Consciousness, understood as the capacity to sustain subjective experience, can be considered a
property that emerges when a sufficiently high level of
complex cognitive processing is achieved [2]. From the
perspective of physics, consciousness and cognition seem
unlikely to emerge from regular and predictable systems,
such as those which are in thermodynamic equilibrium
and obey the detailed balance equations [3]. Instead, recent research draws a close parallel between the level of
consciousness and the entropy production rate of brain
activity time series, highlighting temporal irreversibility
as a landmark feature of conscious information processing [4–6]. These results suggest a close link between
consciousness and non-equilibrium dynamics, prompting
a rigorous evaluation from the perspective of stochastic
thermodynamics.
In spite of these exciting results, the direct estimation
of entropy production from neural activity recordings
is undermined by insufficient spatio-temporal sampling,
leading to the adoption of heuristics and approximations
which lack rigorous justification [3, 4]. To circumvent
these limitations, we adopted a framework based on Multivariate Ornstein-Uhlenbeck (MOU) processes, that are
widely used for modeling the multivariate dynamics of
time series. The importance of MOU derives from the
fact that it is the only continuous stationary stochastic process that is simultaneously Gaussian and Markovian. The MOU process is at the heart of many models
used to fit fMRI data and to interpret them in terms of
whole-brain communication [7–9], in line with the present
methodology. We first characterize the non-equilibrium
steady state of a generic MOU process. The irreversibility of the process is encoded in the antisymmetric part of
the Onsager matrix, while the linearity of the Langevin
equations allows us to derive closed-form expression for
the entropy production rate in terms of the matrices that
define the MOU. As a result, we obtained a model-based
estimation of the entropy production rate for the MOU
fitted to fMRI data of subjects transitioning different levels of consciousness during the descent from wakefulness
to deep sleep.
I.
MULTIVARIATE ORNSTEIN-UHLENBECK
PROCESS
We consider the MOU process closely following the notation in previous work [10]:
dx(t)
= −B x(t) + η(t) .
dt
(1)
Boldfaced symbols denote vectors and matrices. The inputs η(t) correspond to Gaussian white noise with covariance
η(t) η T (t0 ) t = 2D δ (t − t0 ) .
(2)
The angular brackets indicate the mathematical expectation over time and the superscript T the transpose for
vectors or matrices. The N -dimensional MOU process
is thus defined by two real N × N matrices, the input
covariance matrix D, which is symmetric with positive
eigenvalues, and the friction matrix B, which is not symmetric in general.
A.
Description of the state evolution
Knowing the initial condition x(0) and the realization
of the stochastic input η over time, the trajectory of the
solution of the Eq. (1) is given by:
Z t
x(t) = G(t) x(0) +
G(t − s) η(s) ds ,
(3)
0
−Bt
where G(t) = e
is the Green’s function, also known
as propagator. In addition to its mean value hx(t)i =
2
G(t) x(0), the process is also characterized by its covariance matrix S(t, t0 ) = hx(t)xT (t0 )i. The zero-lag covariance, denoted by S(t, t), obeys the following deterministic differential equation:
dS(t, t)
= −B S(t, t) − S(t, t) B T + 2D .
dt
(4)
C.
Entropy production rate
Going a step further, the (ir)reversibility can be described using thermodynamic variables evaluated for the
dynamic process. Using the well-known definition for entropy for the probability distribution P (x, t), now considering its time dependent version, we have
Meanwhile, the lagged covariance with t0 > t exhibits an
exponential decay as a function of the lag t0 − t:
0
S(t, t ) = S(t, t) e
−B T (t0 −t)
Z
e[P ] = −
.
(5)
A standard method for analysing Eq.(1), consists in
describing the evolution of the probability distribution
P (x, t) via the Fokker–Planck equation:
∂P (x, t)
= ∇ · [B x(t) P (x, t) + D ∇P (x, t)] ,
∂t
(6)
(7)
with the following expression for the probability current
(or flux)
J (x, t) = −D∇P (x, t) − Bx(t)P (x, t)
B.
(13)
It can be shown that the rate of the increase of entropy
over time can be decomposed into two factors, namely
ė[P ] = EP R − HDR, where EPR is the entropy production rate and HDR the heat-dissipation rate [10–12]. The
EPR is the main quantity of interest here, which we denote by Φ. Now calculating Φ for the time-independent
distribution P (x), we have
where ∇ denotes the spatial derivative with respect to x.
Eq. (6) can be rewritten as a continuity equation of the
form
∂P (x, t)
+ ∇ · J (x, t) = 0 .
∂t
P (x, t) log P (x, t) dx .
Rn
Z
Φ=
J T (x)D −1 J (x)
dx = ΠT DΠ
P (x)
(14)
where Π is called the the thermodynamic force and is
related to J by the Onsager’s reciprocal relations [11]:
Π=
(8)
D −1 J
P
(15)
The heat-dissipation rate can be computed as follows:
Z
HDR =
D −1 Bx · J dx
(16)
Stationary state and probability current
Rn
The Gauss-Markov property of the OrnsteinUhlenbeck process ensures that the mean and covariances
converge exponentially fast toward their respective fixed
points, provided the eigenvalues of B (which may be
complex) have positive real part. The stationary state
of the MOU process exhibits Gaussian fluctuations
around a mean equal to zero. This corresponds to the
time-independent multivariate probability density
1
1 T −1
P (x) =
exp − x S x , (9)
2
(2π)N/2 (det S)1/2
where S denotes the fixed point of the zero-lag covariance
matrix S(t, t). From Eq. (9), the gradient of P (x) simply
reads
∇P (x) =
∂P (x)
= −P (x) S −1 x
∂x
(10)
From Eq. (8), the stationary probability current J (x)
can thus be rewritten in a compact form
−1
J (x) = D P (x) S x − B x P (x)
= µ x P (x) ,
(11)
µ = D S −1 − B
(12)
In the context of the stationary MOU diffusion processes, a general expression for the entropy production
rate per unit time in the stationary state is the following
[10, 11, 13]
Z
Φ=
T
(∇ log P (x) − DBx) D ∇ log P (x) − D −1 Bx P (x)dx
(17)
which can be obtained from (12), (14) and (15) as follows:
µ = DS −1 − B
D −1 µ = S −1 − D −1 B
D −1 ·
D −1 µx = (S −1 − D −1 B)x
·x
−1
D
µxP = (S
−1
−1
J = (S
−1
Π = (S
−1
D
Π=S
−1
−D
−1
B)xP
·P
−D
−1
B)xP
from (11)
−D
−1
B)x
from (15)
x−D
−1
(18)
Bx
Now, as ∇ log P (x) = S −1 x, we obtain (17). From
(14)
with
D
T
E
ΠT DΠ = xT D −1 B − S −1 D D −1 B − S −1 x ,
3
with zero lag and a lag equal to 1 TR:
we obtain that
D
E
T
Φ = xT D −1 B − S −1 D D −1 B − S −1 x , (19)
Sbij (0) =
where the average is taken over the stationary state of
the process. From this equation we can verify that when
S = B −1 D, then Φ = 0.
Following previous results [11, 14], a sufficient condition for the MOU process in Eq. (1) to be a time reversible stationary process corresponds to a specific relation between the matrices B and D:
Sbij (1) =
B D = D BT.
(20)
To quantify the time (ir)reversibility of the MOU process, it is advantageous to examine the Onsager matrix
L reparameterized using the matrices B, D, and the
pairwise zero-lag covariance S = hx(t)xT (t)it :
L=BS =D+Q ,
LT = S B T = D − Q .
(21)
Here the antisymmetric part Q of L provides a measure
for the irreversibility of the process. When the process is
time reversible Q = 0 and L is symmetric. The following
expression for the entropy production rate Φ can then be
derived from the differential entropy of a multivariate
Gaussian, which is a well defined quantity.
From equations (21) and (12), we have D −1 B −S −1 =
−1
D QS −1 = −D −1 µ. Thus, from Eq. (19) considering
that S and D are symmetric and Q is anti-symmetric we
obtain:
Φ = − xT S −1 QD −1 QS −1 x = xT µT D −1 µx
(22)
The entropy production rate Φ is non-negative. It is
strictly positive if the process is irreversible, and it vanishes only if the process is reversible. Since the stationary
state of the MOU is Gaussian with covariance matrix S,
we have the following property: xT Ax = tr(SA), and
so
Φ = − tr S −1 QD −1 Q = tr SµT D −1 µ ,
(23)
which can be written into the following equivalent expressions, that does not involve the covariance matrix S
nor its inverse explicitly:
Φ = tr B T D −1 Q = − tr D −1 BQ ,
(24)
The entropy production rate Φ provides a scalar measure for the (ir)reversibility of the whole network process,
vanishing only if the process is reversible.
1
T −2
X
[xi (t) − x̄i ] [xj (t) − x̄j ] , (25)
1≤t≤T −1
X
[xi (t) − x̄i ] [xj (t + 1) − x̄j ](26)
.
1≤t≤T −1
Here
P x̄i denotes the mean empirical signal: x̄i =
1
t xi (t) for all i, which is used to center the data as all
T
variables xi have mean zero in the model. These are the
empirical counterparts of the model covariances Sij (t, t)
and Sij (t, t + 1) averaged over time t.
B.
Parameter estimation of the MOU process
We fit the MOU process from the fMRI time series data
for each subject in each sleep condition. We rely on a recent estimation method that tunes the MOU model such
that its covariance structure reproduces the matrices in
Eq. (25), optimizing its parameters the Jacobian matrix
−B as well as the input covariance matrix 2D [7]. Importantly, this optimization procedure incorporates topological constraints on B, adjusting only existing anatomical connections, also keeping the input cross-covariances
Dij = 0 for i 6= j. Note that our current notation corresponds to a previous publication [7], using the following
−B ↔ J and 2D ↔ Σ; note that −B ↔ J T in the
subsequent paper [15].
The model is first calibrated by calculating the time
constant τ from the empirical signals.
N
,
1≤i≤N a (vi | u)
τ = −P
(27)
whereh a (v
i | u)
is the
slope
i of the linear regression of
0
1
b
b
vi = log Sii , log Sii by u = [0, 1].
We rely on a gradient descent to iteratively adjust B
and D until reaching the best fit [7]. At each optimization step, we calculate the model counterparts of the covariance matrices in Eq. (25) S(0) and S(1), assuming
stationarity over each fMRI session. They can be calculated by solving the Lyapunov equation using e.g. the
Bartels-Stewart algorithm, which yields here
B S(0) + S(0) B T = 2D ,
(28)
METHODS
once again equating the derivative with zero in Eq. (4),
and the equation involving the propagator. We calculate
the lagged covariance rewriting Eq. (5) for the time-lag
equation here as
Empirical covariance from fMRI data
S(1) = S(0) e−B .
II.
A.
1
T −2
The model is fitted to reproduce the two covariance
matrices calculated from the empirical BOLD signals,
T
(29)
We then calculate the difference between the model and
empirical covariances, ∆S(t) = Ŝ(t) − S(t) with t ∈
4
{0, 1}. The parameter update is given by differentiating
Eqs. (29) and (28):
h
i
T
−1
∆B = B [S(0)]
∆S(0) − ∆S(1) eB
, (30)
∆D = D B ∆S(0) + D ∆S(0) B T ,
with B and D small learning rates. The best fit corresponds to minimising the squared norm of both ∆S(0)
and ∆S(1).
C.
MOU-based anatomo-functional model to fit
empirical fMRI data
We fitted a MOU process to the time series of blood
oxygen level-dependent (BOLD) activity measured using fMRI for a whole-brain parcellation consisting of
N = 90 regions of interest (ROIs). The BOLD signals
were recorded from 15 healthy participants during wakefulness and three sleep stages of progressively deeper unconsciousness (N1, N2, N3). Further details about the
data preprocessing like detrending and filtering can be
found in [16]. Example BOLD time series are illustrated
in Fig. 1A. Fig. 1B-C show two functional connectivity matrices, here calculated as covariances with zero lag
Ŝ(0) and lag of 1 timestep Ŝ(1). These matrices are the
empirical counterparts of the model pairwise covariance
S(l) = hx(t)xT (t + l)it with lag l, which is symmetric for
l = 0 and was denoted above by S = S(0).
In this application, the activity xi of the MOU process describes the BOLD activity of node i. Its friction
matrix B quantifies the propagation of BOLD activity
between ROIs, ignoring hemodynamics [18]. Specifically,
the diagonal elements Bii are related to a time constant
τ (identical for all ROIs) and the off-diagonal elements
Cij = −Bij correspond to the concept of effective connectivity from ROI j to ROI i (excitatory when Cij > 0):
δij
+ Cij ,
(31)
τ
where δij is the Kronecker delta. The variance Dii reflects the fluctuation amplitude of ROI i.
For each subject and condition, the model was fitted
to reproduce the two covariance matrices calculated from
the empirical BOLD signals Ŝ(0) and Ŝ(1) (see Fig. 1BC). We used a recent estimation method based on gradient descent to iteratively adjust B and D until reaching
the best fit [7]. At each optimization step, we calculate the model counterparts of the covariance matrices
S(0) and S(1), assuming stationarity over each fMRI session. Importantly, this optimization procedure incorporates topological constraints on B, adjusting only existing anatomical connections (see Fig. 1D-E), also keeping
the input cross-covariances Dij = 0 for i 6= j. Model fit
is quantified by two measures: model error, defined using the matrix distance and Pearson correlation between
vectorized FC matrices (model versus data). All sleep
states have Pearson correlation above 0.6, corresponding
to an R2 of 0.36 (See fig S2 in the supplemetal material).
FIG. 1. A) Example of the filtered BOLD time series with
198 repetition times (TR) of 2 seconds, corresponding to the
90 ROIs of the AAL parcellation during wakefulness of one
participant. B-C) Functional connectivity matrices calculated
from the filtered BOLD signals in panel A, Ŝ(0) with zero lag
and Ŝ(1) with a lag of one timestep (TR=2 s). These matrices
are used in the objective functions used to fit the anatomofunctional model. D) Generic structural connectivity (SC)
obtained from DTI data as described in [17]. E) Mask for
existing directional connections to constrain the topology of
the B matrix in the network model (symmetric here).
− Bij = −
D.
Robust decoding of sleep stages from MOU
parameters
Following previous work [15, 19], we used the scikitlearn Python library for the implementations of multinomial logistic regression (MLR) classifier. The input
features corresponded to the vectorized C/D/S matrices after discarding zero or redundant elements. We implemented a stratified cross-validation scheme with 80%
of the samples for the train set and 20% for the test
set, where the ratio of classes is the same in both sets.
We also use the subject identity as “group information”
to avoid mixing subject data between the train and test
sets. In practice, we use 100 random splits of the data
and report the distribution of the accuracies of the 100
splits.
As illustrated in Fig. 2B, both the empirical BOLD
variances and the model estimates exhibit global differences across the four sleep stages, although they do not
5
FIG. 2. A) Our dynamic network model has two sets of optimized parameters: the matrix C (effective connectivity),
which describes the causal interaction between brain regions,
and the input variance D, which represents the spontaneous
activity of each brain region. Note that the topology of the
matrix C corresponds to the mask inferred from the SC data
in Fig. 1D-E, but the weights are estimated from the empirical
functional connectivity (FC) matrices Fig. 1B-C, resulting in
an anatomo-functional model. B) Changes in total C and D
weights across sleep stages (x-axis), pooled over the 15 subjects. The sleep stages are represented by the blue contrasts,
from light for wake (W) to dark for the deepest sleep (N3).
C) Classification accuracy based on the model estimates, C
and D, and the empirical covariance matrices. The classifier
is the multinomial logistic regression (MLR), which captures
changes in individual features across sleep stages. The gray
violin plots correspond to the chance-level accuracy calculated
empirically by shuffling the labels of the sleep stages.
exhibit a clear trend. These differences in global measures, which are averages over all ROIs, may hide more
specific changes at the ROI level, as well as interactions
between them. Supplementary Figure S1 shows the good
fit of the anatomo-functional model to fMRI data obtained for all sleep stages, with mean correlation between
simulated and empirical FC matrices exceeding 0.6 for
all stages. Fig. 2C shows that the model estimates give
good classification accuracy, both for C (in red) and D
(in purple). This indicates that the model captures the
differences in brain dynamics across the sleep stages. Notably, the matrix C gives a better classification accuracy
than the empirical functional connectivity Ŝ(0) (in blue),
meaning that the model inversion is robust and captures refined information about the sleep stages. Note
that the MLR has better accuracy than the 1-nearestneighbor (1NN) in Suppl Fig S1A, indicating that the
changes across sleep stages concern specific features, i.e.
connectivity weights (C) or nodal spontaneous activity
(D), rather than their global profile.
FIG. 3. A) Violin plots comparing the entropy production
rate across sleep stages. Same color coding used in previous
plots. The average entropy production values across subjects
are for the four sleep stages are 1.99, 1.65, 1.54, and 1.49,
respectively. The stars indicate statistical significance for the
Mann-Whitney test with p < 0.05. B) Comparison of the
nodal irreversibility for each ROI (x-axis) between the W and
N3 states (in light and dark blue, respectively). The plotted
values correspond to the absolute value of sums over rows of
Q, averaged for homotopic regions; error bars indicate the
variability across subjects measured as the standard error of
the mean. C) Heatmap plots of the nodal irreversibility on
the cortical surface for the W and N3 sleep stages. Note the
different color scales for the two stages, for the purpose of
better readability. D) To gain insight into the effects of the
matrices C and D on Φ, we shuffle their values as a way to
destroy their detailed structures (redistributing their values
keeping the topology). We plot Φ for the estimated C and
D matrices across subjects and sleep stages in blues (same
color code used in previous plots), and the shuffled C matrices
(light gray), D matrices (middle gray) and both (dark gray),
as a function of the sum of C values (left panel), the time
constant τ (middle panel) and the sum of D variances (right
panel).
E.
Reduced entropy production in the transition
from wakefulness to deep sleep
Using the condition-specific estimated parameters, we
calculated the entropy production rate in the MOU
model using Eq. (24). These results in Fig 3A show
that entropy production decreases as a function of sleep
depth, which in turn implies that dynamics become closer
to equilibrium.
The model-based approach allows us to dissect this
phenomenon. For all ROIs, we observe that the contri-
6
bution to Φ,
P as measured via the nodal irreversibility,
defined as j |Qij | for each ROI i, decreases, as illustrated in Fig 3B. This suggests that the reduction of Φ
from W to N3 is a rather global phenomenon, but with a
differentiated magnitude across brain regions. Notably,
regions in the occipital lobes (cuneus, calcarine, lingual),
as well as regions associated to hubs in the default-mode
network (precuneus, post cingulate), and the thalamus,
remain at a high level of nodal irreversibility in the deep
sleep N3; these regions have been shown to exhibit sleeprelated changes in previous studies [20–22]. See Suppl
Fig S3 for a more detailed comparison across sleep stages.
Last, we examine how the model parameters C and
D contribute to Φ and its reduction across sleep stages.
Fig 3D shows a positive relationship between Φ and the
sum of weights in C, as well as the sum of variances in D;
conversely, a larger τ (directly calculated from the empirical BOLD signals) corresponds to a lower Φ. Then
we assess the importance of the detailed structures in
the C and D estimates by randomizing them spatially,
namely redistributing the total weight/variances across
non-zero elements while keeping the same topology and
overall sum. We observe the same trends with respect to
the C and D sums, but shifted up or down depending on
the surrogates in Fig 3C: randomizing C (light gray) decreases slightly Φ, whereas randomizing D (middle gray)
increases Φ; randomizing both (dark gray) decreases Φ.
This indicates that Φ strongly depends on the detailed
structures of the C and D estimates, being larger in the
data than in the randomized surrogates. The opposing
effects in randomizing C and D also suggest a balance
implemented by the detailed brain dynamics, which results in a controlled level of Φ. Together, our results hint
at a positive relationship between the measured Φ and
the different levels of consciousness.
III.
brain is scale-dependent [3]. At the large scale, its violation might relate to the large-scale circuit operations critical for healthy cognition and for the global broadcasting
of information which is identified with the computational
aspect of consciousness [23]. Because of this, metrics
related to the departure from detailed balance (such as
entropy production rate) might offer valuable tools to determine levels of consciousness in brain-injured patients
and other neurological populations. In summary, assessing temporal irreversibility through entropy production
of MOU processes derived from fMRI signals has the potential to highlight different states of consciousness and
cognition. More generally, can bridge brain dynamics
and thermodynamics, and ultimately help to understand
fundamental questions about the brain and consciousness.
Acknowledgements. M.G. and R.C. would like to
thank the organizers of the 2021 Spring School of the European Institute of Theoretical Neuroscience, the place
where this project began to develop. MG was supported
by the European Union’s Horizon 2020 Framework Programme for Research and Innovation under the Specific
Grant Agreement No. 945539 (Human Brain Project
SGA3), as well as the Excellence Initiative of the German
federal and state governments (ERS PF-JARA-SDS005).
E.T. is supported by grants PICT2018-03103 and PICT2019-02294 funded by Agencia I+D+I (Argentina), by
a Mercator fellowship granted by the German Research
Foundation and FONDECYT regular 1220995. R.C was
supported by the Human Brain Project, H2020-945539.
SUPPLEMENTAL MATERIAL
In this supplemental material, we present details on
sleep stage decoding sleep stages, supplementary analysis, and a detailed description of the fMRI data.
DISCUSSION
We measured the entropy production using our
anatomo-functional MOU process associated to restingstate fMRI activity recorded from human subjects in different sleep stages. The advantage of our model-based
approach is that the entropy production has a closedform expression from first principles of stochastic thermodynamics for the MOU process, which is numerically
fitted to the fMRI data. Our results show high entropy
production rate in conscious wakefulness, i.e. correlating positively with the presumed level of cognitive processing. This is consistent with converging theoretical
accounts that identify consciousness with an emergent
property of a highly complex physical system [2]. These
results are also consistent with previous findings relating entropy production with states of consciousness [4–6],
with the advantage that do not depend on heuristic approximations. Importantly, our approach allows for identifying the brain regions that contribute most to entropy
production. The fulfillment of detailed balance in the
A.
Decoding of sleep stages
We use the same approach as in previous work [15, 19].
We rely on two usual classifiers: multinomial logistic regression (MLR) and the 1-nearest-neighbor (1NN). The
features correspond to vectorized C/D/S matrices after
discarding zero or redundant elements. The MLR is a
canonical tool for high-dimensional linear classification,
which tunes a weight for each feature, thus selecting the
important ones to discriminate the classes. In addition,
we use L2-regularization for the MLR (C = 1.0 in the
scikit-learn implementation). In contrast, the 1NN assigns to a new sample the class to which belongs its closest neighbors with respect to a similarity metric, here
chosen as the Pearson correlation coefficient between the
feature vectors. It thus relies on the global profile of
features to cluster samples into classes.
Following standards, we use a stratified crossvalidation scheme with 80% of the samples for the train
7
FIG. S1. A) Similar plot to Fig 2C in the main text with the
classification accuracy for the 1-nearest-neighbor (1NN) classifier, which relies on a similarity measure (here the Pearson
correlation) between the input features to predict the class of
the test sample. The x-axis indicates the features: the model
estimates C and D, as well as the empirical FC denoted by Ŝ.
B) Similar plot to Fig 2B in the main text but for the model
input variance summed over all ROIs.
set and 20% for the test set, where the ratio of classes
are the same in both sets. We also use the subject identity as “group information” to avoid mixing subject data
between the train and test sets. In practice, we use 50
random splits of the data and report the distribution of
accuracies of the 50 splits (see the violin plots).
Fig S1 shows that the decoding of the sleep states by
the 1NN classifier, which assigns to a new sample the
class to which belongs its closest neighbors with respect
to a similarity metric, here chosen as the Pearson correlation coefficient between the feature vectors. It thus
relies on the global profile of features to cluster samples
into classes.
B.
FIG. S2. A: Model error for each sleep stage (x-axis) across
the 15 subjects. The sleep stages are represented by the blue
contrasts, from light for wake (W) to dark for the deepest
sleep (N3). B: Goodness of fit as measured by the Pearson
correlation between the vectorized model and empirical FC
matrices: S(0) with Ŝ(0), and S(1) with Ŝ(1). The average
of the two Pearson correlation values is reported. C: Isomap
decomposition of the empirical zero lag functional connectivity matrices FC0 (or Ŝ(0)) in two dimensions to illustrate their
stronger clustering in deep sleep stages N3 (squares) and N2
(triangles), compared to N1 (dots) and W (crosses). D: Pearson similarity across Ŝ(0) matrices in each sleep stage (x-axis)
for all pairs of subjects
Model fitting and goodness of fit across sleep
stages.
The model fit was quantified using two measures. The
model error, defined by matrix distance, and the Pearson
correlation between vectorized FC matrices (model versus data). As shown in Fig S2A-B, all sleep states have
Pearson correlation above 0.6. Note that the changes in
the goodness of fit of the model, as measured by the Pearson correlation across sleep stages in Fig S2B, are likely
due to the stronger similarity between the corresponding empirical FC matrices in the deep sleep stages than
in light sleep stages. In other words, we do not expect
this trend to indicate a much better fit of the model for
N3 than for W (which might have implications for the
calculation of entropy production).
C.
Complementary analysis
The comparison of the nodal irreversibility across sleep
states shows an overall decrease for all ROIs from W to
N3 (Fig S3A), with a pronounced decrease from W to N1
(Fig S3B) and to a lesser extent from N2 to N3 (Fig S3D),
although N1 and N2 are rather similar (Fig S3C). Importantly, we can see heterogeneity in the reduction of
FIG. S3. A) Plot of the sum of absolute values in Q over each
row across the W and N1 states. The error bars indicate the
s.e.m. across subjects. This plot is another view of the same
data in Fig 3B (main text). B-C) Similar plots to panel A for
N1 versus N2, N2 versus N3 and W versus N3.
irreversibility across the ROIs in the transition to deep
sleep.
Fig S4 shows the correlation between the goodness of
fit and the entropy production across all subjects for each
brain state. We observe a lack of statistically significant
Spearman correlations between variables except for the
awake state, where the effect was close to the significance
threshold. Fig S2 shows the isomap decomposition of the
empirical zero lag functional connectivity matrices FC0
in two dimensions to illustrate their stronger clustering in
deep sleep stages compared to N1 and W. We also show
the Pearson similarity across FC0 matrices in each sleep
stage (to be compared with fig 3B in main text.
8
nation of EEG and fMRI. According to the rules of the
American Academy of Sleep Medicine , the polysomnography signals (including the scalp potentials measured
with EEG) determine the classification of data into four
stages (wakefulness, N1, N2, and N3 sleep). We selected
15 subjects with contiguous resting-state time series of
at least 200 volumes to perform our analysis. The local ethics committee approves the experimental protocol
(Goethe-Universität Frankfurt, Germany, protocol number: 305/07), and written informed consent was asked to
all participants before the experiment. The study was
conducted according to the Helsinki Declaration on ethical research.
MRI data acquisition
FIG. S4. Correlation between the goodness of fit and the entropy production across all subjects for each brain state. In
each plot, we show the Spearman correlation, denoted s, with
the corresponding p-value. The correlations are not statistically significant, except for the Awake state.
D.
Resting-State fMRI signals
Participants
MRI images were acquired on a 3-T Siemens Trio scanner (Erlangen, Germany) and fMRI acquisition parameters were 1505 volumes of T2-weighted echo planar images, TR/TE = 2080 ms/30 ms, matrix 64 × 64, voxel
size 3×3×3 mm3 , distance factor 50%; FOV 192 mm2 .
An optimized polysomnographic setting was employed
(chin and tibial EMG, ECG, EOG recorded bipolarly
[sampling rate 5 kHz, low pass filter 1 kHz] with 30
EEG channels recorded with FCz as the reference [sampling rate 5 kHz, low pass filter 250 Hz]. Pulse oximetry and respiration were recorded via sensors from the
Trio [sampling rate 50 Hz]) and MR scanner-compatible
devices (BrainAmp MR+, BrainAmpExG; Brain Products, Gilching, Germany), facilitating sleep scoring during fMRI acquisition.
Brain parcellation AAL 90 to extract BOLD time series and
filtering
A total of 63 healthy subjects (36 females, mean ±
SD, 23.4 ± 3.3 years) were selected from a data set previously described in a sleep-related study by Tagliazucchi
and Laufs [16]. Participants entered the scanner at 7
PM and were asked to relax, close their eyes, and not
fight the sleep onset. A total of 52 minutes of resting
state activity were measured with a simultaneous combi-
To extract the time series of BOLD signals from
each participant in a coarse parcellation, we used the
AAL90 parcellation with 90 brain areas anatomically defined.BOLD signals (empirical or simulated) were filtered
with a Butterworth (order 2) band-pass filter in the 0.010.1 Hz frequency range.
[1] G. Piccinini and A. Scarantino, Journal of biological
physics 37, 1 (2011).
[2] A. K. Seth and T. Bayne, Nature Reviews Neuroscience
23, 7 (2022).
[3] C. W. Lynn, E. J. Cornblath, L. Papadopoulos, M. A.
Bertolero, and D. S. Bassett, PNAS 118, 47 (2021).
[4] Y. Sanz Perl, H. Bocaccio, C. Pallavicini, I. Pérez-Ipiña,
S. Laureys, H. Laufs, M. Kringelbach, G. Deco, and
E. Tagliazucchi, Physical Review E 104, 014411 (2021).
[5] L. de la Fuente, F. Zamberlan, H. Bocaccio, M. Kringelbach, G. Deco, Y. S. Perl, and E. Tagliazucchi, Cerebral
Cortex bhac177 (2022).
[6] R. N. Muñoz, A. Leung, A. Zecevik, F. A. Pollock, D. Cohen, B. van Swinderen, N. Tsuchiya, and K. Modi, Phys-
ical Review Research 2, 023219 (2020).
[7] M. Gilson, R. Moreno-Bote, A. Ponce-Alvarez, P. Ritter,
and G. Deco, PLoS Computational Biology 12, 3 (2016).
[8] K. J. Friston, K. H. Preller, C. Mathys, H. Cagnan,
J. Heinzle, A. Razi, and P. Zeidman, NeuroImage 199
(2019).
[9] S. Frässle, Z. M. Manjaly, C. T. Do, L. Kasper,
K. P. Pruessmann, and K. E. Stephan, NeuroImage 225
(2021).
[10] C. Godrèche and J. M. Luck, Journal of Physics A: Mathematical and Theoretical 52, 035002 (2019).
[11] H. Qian, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences 457,
10.1098/rspa.2001.0811 (2001).
9
[12] R. Cofré and C. Maldonado, Entropy 20,
10.3390/e20010034 (2018).
[13] H. Qian, M. Qian, and X. Tang, Journal of Statistical
Physics (2002).
[14] H. Risken and T. Frank, Springer Series in Synergetics
(1996).
[15] M. Gilson, G. Zamora-López, V. Pallarés, M. H. Adhikari, M. Senden, A. T. Campo, D. Mantini, M. Corbetta, G. Deco, and A. Insabato, Network Neuroscience
4, 2 (2020).
[16] E. Tagliazucchi and H. Laufs, Neuron 82, 3 (2014).
[17] I. P. Ipiña, P. D. Kehoe, M. Kringelbach, H. Laufs,
A. Ibañez, G. Deco, Y. S. Perl, and E. Tagliazucchi, NeuroImage 215, 116833 (2020).
[18] M. Gilson, R. Moreno-Bote, A. Ponce-Alvarez, P. Ritter, and G. Deco, PLoS Computational Biology 12,
10.1371/journal.pcbi.1004762 (2016).
[19] V. Pallarés, A. Insabato, A. Sanjuán, S. Kühn, D. Mantini, G. Deco, and M. Gilson, NeuroImage 178 (2018).
[20] S. G. Horovitz, A. R. Braun, W. S. Carr, D. Picchioni,
T. J. Balkin, M. Fukunaga, and J. H. Duyn, PNAS 106,
27 (2009).
[21] T. T. Dang-Vu, M. Schabus, M. Desseilles, V. Sterpenich,
M. Bonjean, and P. Maquet, Sleep 33, 12 (2010).
[22] L. Mirandola, G. Cantalupo, A. E. Vaudano, P. Avanzini,
A. Ruggieri, F. Pisani, G. Cossu, C. A. Tassinari, P. F.
Nichelli, F. Benuzzi, and S. Meletti, Epilepsy and Behavior Case Reports 106 (2013).
[23] S. Dehaene, M. Kerszberg, and J. P. Changeux, PNAS
95, 24 (1998). |
155
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Review Article
The Two Faces of Our Three Brains (Part I)
Robert Campbell*
Abstract
Arthur Koestler’s Janus–faced holon is explored as characteristic of hierarchical levels that
pervade the natural order. The self-transcending face of the holon identifies with an integrating
ideal entertained by the conscious intellect that is easily subverted to the emotional desires of the
crocodile and the horse wired into our limbic brain. This allows our self-assertive face to act
without human conscience thus accounting for the tragic mess we have made of our history. The
“flatland” vision of cause and effect has ruled the development of the psychological, social,
physical and biological sciences while ignoring hierarchies implicit in the cosmic order that
pervade all phenomena. The holon is shown to derive from Universal and Particular active
interfaces that are requirements of universal wholeness implicit in the cosmic order. It is called
System 2. The hierarchically nested Systems 3 and 4 require that there are three mutually closed
active interfaces essential to physical reality, and to the mental integration of phenomenal
experience, respectively.
This article reviews the Papez-MacLean Theory of Emotions from the perspective of the holon.
MacLean researched the schizophysiology of the split between the ancient emotional limbic
brain and the new brain or neocortex to account for humanity’s tragic history. Sperry’s work on
split-brain patients confirms that the right and left hemispheres function independently, the
holistic right brain acting as a self-transcending face with respect to the self assertive left brain.
Together they can be conscripted into the service of our primitive limbic brain. Polar
relationships between the sensory and motor topologies of the neocortex explored by Penfield
and later by Woolsey act as two of the three polarities essential to the integration of human
experience, the third being the ancient limbic system that reflects autonomic emotional
experience in conscious awareness. The mind is shown to transcend and subsume the physical
brain by regulating archetypal patterns behind the scenes that direct brain chemistry.
Part I of this two-part review article includes: The Unsolicited Gift; The Poverty of Psychology
and the Need for a New Paradigm; MacLean Relates Brain Structure to Evolutionary History;
Koestler Reviews Some Historical Evidence; The Schizophysiology of Horse and Rider;
Aristotle’s Horse and Hierarchies; Janus and the Holon; and The Holon as an Active Interface.
Key words: Koestler, Papez, MacLean, Sperry, Penfield, Woolsey, limbic system. split brains,
universal wholeness, universal and particular, holon, cosmic order, brain and mind, three brains,
hierarchies, active interfaces, triune brain, schizophysiology
*
Correspondence: Robert Campbell, Website: http://www.cosmic-mindreach.com E-Mail: bob@cosmic-mindreach.com Note: This paper was
written in 1977 and updated in 2013 & 2014.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
156
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
The Unsolicited Gift
In The Ghost in the Machine1, Arthur Koestler’s tells an interesting parable which he calls the
paradox of the unsolicited gift:
There was once an illiterate shopkeeper in an Arab bazaar, called Ali, who, not being
very good at doing sums, was always cheated by his customers; instead of cheating
them, as it should be. So he prayed every night to Allah for the present of an abacus that
venerable contraption for adding and subtracting by pushing beads along wires. But
some malicious djin forwarded his prayers to the wrong branch of the heavenly Mail
Order Department, and so one morning, arriving at the bazaar, Ali found his stall
transformed into a multi-storey, steel framed building, housing the latest IBM computer
with instrument panels covering all the walls, with thousands of fluorescent oscillators,
dials, magic eyes, etc., and an instruction book of several hundred pages; which, being
illiterate, he could not read. However after days of useless fiddling with this or that
dial, he flew into a rage and started kicking a shiny, delicate panel. The shocks
disturbed one of the machine’s millions of electronic circuits, and after a while Ali
discovered to his delight that if he kicked that panel, say, three times and afterwards
five times, one of the dials showed the figure eight! He thanked Allah for having sent
him such a pretty abacus, and continued to use the machine to add up two and three
happily unaware that it was capable of deriving Einstein’s equations in a jiffy, or
predicting the orbits of planets and stars thousands of years ahead. Ali’s children, then
his grandchildren, inherited the machine and the secret of kicking that same panel; but
it took hundreds of generations until they learned to use it even for the purpose of
simple multiplication.…We ourselves are Ali’s descendants, and though we have
discovered many other ways of putting the machine to work, we have still only learned
to utilize a very small fraction of the potential of its estimated hundred thousand million
circuits. For the unsolicited gift is of course the human brain. As for the instruction
booklet, it is lost, if it ever existed. Plato maintains that it did once, but that is
hearsay…It is entirely unprecedented that evolution should provide a species with an
organ which it does not know how to use; a luxury organ, like Ali’s computer, far
exceeding its owner’s immediate, primitive needs; an organ which will take the species
millennia to learn to put to proper use, if it ever does.
The Poverty of Psychology and the Need for a New Paradigm
Despite all of our scientific efforts, no one knows how the human nervous system works in terms
that can allow us to master the operation of our most important instrument in constructively
balanced ways. As proprietors of our unsolicited gift we are left groping in the dark. There are
various systems with certain vague verbal guidelines, which have a degree of validity in limited
circumstances, but invariably these have serious shortcomings. This includes the whole range of
psychological and philosophical systems of understanding as well as our physical and biological
sciences. All of these may catch some particular glimpse of truth from a certain angle but all are
deficient to varying degrees. Language is not up to the task.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
157
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Koestler takes particular aim at behavioural psychology founded before the outbreak of the First
World War by John B. Watson2 who proclaimed in his book, Behaviourism3:
The time has come when psychology must discard all reference to consciousness... Its
sole task is the prediction and control of behaviour; and introspection can form no part
of its method. (1913 pp 158-67)
[Behaviourist] must exclude from his scientific vocabulary all subjective terms such as
sensation, perception, image, desire, purpose, and even thinking and emotion as they
were subjectively defined. (1928. p 6)
The absurdities of behavioural psychology were further advanced notably by B.F. Skinner4 into
the 1980s. His many colleagues still exert their influence today including on other disciplines
such as psychiatry, physics, evolution theory, biology and social sciences. Experiments on rats
and pigeons have been extrapolated to human behaviour. The mechanical linkage of cause and
effect has been translated into stimulus and response as in the Pavlovian conditioning of dogs.
Koestler points out that Pavlov went so far as to count the drops of dog salivation to quantify the
degree of conditioning. We generally acknowledge that a degree of social conditioning is
essential to the development of a child but to reduce us all to mindless totally conditioned robots
no better than rats is ludicrous. It may be argued that behaviourism is dead but the corpse still
stalks the corridors of the psychologist’s mind. There has been resurgence in recent years and the
general populace is on the band wagon analysing who out there caused their every psychological
hiccup. There is such a thing as taking personal responsibility for one’s life.
To be valid any attempt to understand how the human nervous system works must be universal.
It must embrace all possible varieties of human behaviour. This requirement implicitly rules out
studies in behavioural psychology that are invariably dependent upon the accepted use of
language restricted to Aristotle's efficient cause. That renders it useless at bridging deep rooted
cultural differences in the global social meltdown that is currently taking place. To bridge our
cultural differences implicitly requires a capacity for direct intuitive insight into the workings of
the cosmic order by which we have all evolved. By its nature the cosmic order must be universal.
It must encompass all creation, all manner of phenomenal behaviour both in the private and
public realms. Nothing short of this can hope to mend the sadly tattered fabric of human
civilization.
This is a tall order but a start has been made that is not itself dependent on language. The System
of delineating the cosmic order facilitates intuitive insight into the roots of meaning implicit it all
languages.5 The cosmic order cannot be reinvented in language. It can not be contrived
intellectually. It can only reveal itself in response to a persistent intuitive quest into the
hierarchical structure of how phenomena are presented to us.
We need to understand how we meaningfully integrate sensory input and organize it into
appropriate responses according to circumstance. This means that the System6 of delineating the
cosmic order that will be revisited later is structural in nature as distinct from behavioural. All
thought, feeling, and behaviour derive from how it works, not vice versa. We are cosmic beings
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
158
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
that have taken a couple billion years to evolve to the point where we can realize this. Our
unsolicited gift has become a very sophisticated instrument over the last million years or so,
especially since the development of structured languages. Later we shall see that this has
polarized the functions of Ali’s abacus.
MacLean Relates Brain Structure to Evolutionary History
MacLean was a leading researcher who pioneered the relationship of our primitive reptilian and
lower mammalian brains with respect to our neocortex or new brain that expanded over them
when the higher mammals evolved. The cortex is the outer rind of grey matter, about a tenth of
an inch thick. It contains many billions of neurons over an area of about three square feet
crammed into the convolutions of the brain. Inside it white matter nerve fibres interconnect areas
of the cortex in a complex maze of patterns.
In humans the expansion of the neocortex has been so great as to fold the two primitive brains
that occupy the limb or edge of the cerebral cortex inward around the brain stem. The structure 7
and function of the Limbic brain is very similar throughout the mammalian lineage from mouse
to man. Its human structure is illustrated in the website article Inside our Three Brains.8 Later
we will come to Koestler's concept of the “holon” which draws heavily on MacLean's work
during the 1950s and 1960s.
Building on the work of Papez (1937)9, MacLean's pioneering work,10 covering the last half of
the 20th century11 established that the two primitive limbic brains in conjunction with related
brain stem structures form a functionally integrated apparatus called the Limbic System. It is
intimately associated with our emotional apparatus - the autonomic nervous system. The latter is
an emotional vehicle rather than a cause. In 1929 Canon Walter12 showed that emotions persist
even after autonomic connections of the visceral organs with the brain are severed, indicating the
emotional limbic brain can function independently on emotional patterns established prior.
The Limbic Brain is fundamental to the recall process and memory. It can learn in itself and is
also employed in the learning of the new brain. We know that memories are emotionally
coloured. We have a conscious capacity to observe them as they arise according to circumstance.
We can tailor them to behavioural responses as we deem appropriate in any given situation.
Nevertheless this primitive brain has a capacity to think independently of the neocortex albeit in
crude and often confused emotionally coloured patterns. Its cortex is relatively coarse, like the
brains of our reptilian and lower mammalian ancestors, while the new brain is finer in texture
and more highly organized. The Limbic brain has no capacity to express its impressions in
language. Rather it associates them with situations symbolically. The colour red may be
associated with blood, or fighting, or flowers, or fire, for example.
MacLean points out that limbic epilepsy, electrically induced in animal studies, is confined to the
Limbic System (MacLean 1964 pp10-11). There is thus a clear dichotomy of function between
the old and new brains that he calls schizo-physiology. This built-in condition accounts for a
fundamental human dilemma associated with Koestler's parable of the unsolicited gift:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
159
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Man finds himself in the predicament that Nature has endowed him essentially with three
brains which, despite great differences in structure, must function together and
communicate with one another. The oldest of these brains is basically reptilian. The second
has been inherited from lower mammals, and the third is a late mammalian development,
which in its culmination in primates, has made man peculiarly man…
Speaking allegorically of these three brains within a brain, we might imagine that when the
psychiatrist bids the patient to lie on the couch, he is asking him to stretch out alongside a
horse and a crocodile. The crocodile may be willing and ready to shed a tear and the horse
to neigh and whinny, but when they are encouraged to express their troubles in words, it
soon becomes evident that their inability is beyond the help of language training.… The
reptilian brain is filled with ancestral lore and ancestral memories and is faithful in doing
what its ancestors say, but it is not a very good brain for facing up to new situations. It is as
though it were neurosis-bound to an ancestral superego.…
In evolution one sees the beginning of emancipation from the ancestral superego, with the
appearance of the lower mammalian brain, which Nature builds on top of the reptilian
brain… It has a greater capacity than the reptilian brain for learning new approaches...on
the basis of immediate experience. But like the reptilian brain ...it does not have the ability
to put its feelings into words.”... (MacLean 1964 p 2; Koestler p 277)
MacLean compares the cortex of the brain to a TV screen. The primitive screen of the Limbic
cortex mixes projections of the outside world with the internal visceral environment which is
adequate for smelling, tasting, and feeling what is going on inside the body. The bigger and finer
neocortical TV screen of the higher mammals gives a clearer picture of the outside world with
input from the eye, the ear and the surface of the body, however the old screen was also retained
and continues to perform its traditional functions.
MacLean's three brains thus resolve into two brains because the reptilian and lower mammalian
brains together constitute the Limbic Brain, which is distinct from the new brain or neocortical
brain of the higher mammals such as dogs, chimpanzees and humans. Although the growth of the
new brain continued with the early hominid species an unprecedented explosive growth is
especially evident in the enlarged cranial capacity of humans over the past half million years. (p.
272). Koestler suggests that this tumultuous overgrowth was unprecedented in evolutionary
history and was an evolutionary mistake.
There has been little change in the last 35,000 years or so as modern humans consolidated. This
dichotomous schism between the old and new brains accounts for the schizophrenic-paranoid
streak so deeply evident in human history from our bipedal origins to the present. MacLean
elaborates on this built-in schizophysiology in many of his articles on the subject. A sampling is
referenced below.13
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
160
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Koestler Reviews Some Historical Evidence
Koestler reviews evidence from our hominid ancestors to ancient Greece of how our new brain
easily gets conscripted into the service of our old brain often with exaggerated negative results.
Aristotle's categories became the grammar of existence, his animal spirits ruled the world of
physics… the philosophers of the Hellenistic period dwelt in Plato's cave, drawing epicycles
on the wall, their backs turned to the daylight of reality. …During that time the march of
science was not only halted but its direction reversed... In the fifth century BC the educated
classes knew that the Earth was a spherical body floating in space and spinning round its
axis; a thousand years later they thought it was a flat disc.” (p 301)
Reason's task was to act as the handmaid of faith - whether it was the faith of medicine-men,
theologians, scholastics, dialectical materialists, devotees of President Mao or King MboMba. The fault dear Brutus is not in our stars: it is in the crocodile and the horse that we
carry in our skulls. Of all the uniqueness of man this seems to be the foremost.(p 302)
Koestler discusses the curse of language at some length. He observes that while language
facilitates communication within the group, it also crystallizes cultural differences. He quotes
Margaret Mead who talks about the 750 tribal languages among the two million aborigines of
New Guinea that were perpetually at war maintaining their mutual tribal separation.
The main danger of language however lies not in its separative, but in its magic, hypnotic,
emotion-arousing powers. Words can serve to crystallize thought, to give articulateness and
precision to vague images and hazy intuitions. They can also serve to rationalize irrational
fears and desires, to give the semblance of logic to the wildest superstitions, to lend the
vocabulary of the new brain to the phantasmagorias and delusions of the old. Lastly, words
can be used as explosive charges to set off the chain reactions of group psychology. Ali's
computer is just as capable of producing Kant's Critique of Pure Reason as the screams of
Hitler.
As a general assessment of our situation we have the intellectual capacity to build atomic bombs
and send rockets to the Moon and Mars, harnessed to the emotional capacity of a crocodile and a
horse. But let us go back now to the earlier part of his book where he develops the concept of the
“holon”. Then later we shall see that there is an ingenious method anticipating a far flung future
vision implicit in Nature's bold and risky plan. It may be hanging by a thread but it is surely
there.
The Schizophysiology of Horse and Rider
One cannot emphasize strongly enough what Koestler calls the divided house of faith and reason
and what MacLean calls schizophysiology. The anatomical and physiological evidence clearly
identifies a disparity of function between the new brain and the ancient limbic brain. MacLean
established that significant interconnections between the limbic cortex and neocortex are lacking
while the limbic cortex is connected by major nerve bundles to the hypothalamus and thence to
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
161
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
both divisions of the autonomic nervous system which is responsible for our emotional
responses. In other words, the horse – the limbic system – has direct access to our emotion
generating apparatus wheras the rider – our conscious rational intellect – has no direct access to
them. External nput to the neocortex is not emotionally coloured whereas visceral input to the
limbic cortex is strongly emotionally patterned.
Both horse and man are very much alive to one another and to their environment, yet
communication between them is limited. Both derive information and act on it in different
ways.'(MacLean 1961 pp 1738-39)
Koestler emphasizes that to go on preaching sweet reason to an inherently unreasonable species
is a hopeless enterprise, as history shows.
Aristotle’s Horse and Hierarchies
It is incredible that mainstream science in its questionable wisdom has chosen to ignore
hierarchical order that is so all pervasive in the universe, in the biosphere around us, in our
evolutionary history, in our biological structure, in our language, and in our social
organizations.14 Causal determinism on a level playing field has been the favoured engine of
science. Peering through the murky gloom, modern science and its philosophical partners remain
drawn to the flickering candle of Aristotle’s ancient Efficient Cause attired in various clothing.
Mystical apparitions are conjured in the forbidden darkness beyond, about the spiritual
implications that hierarchic order might imply. So it is that our elite intelligentsia clutches to the
mane of Aristotle’s runaway horse, having released the reins he intended with his other three
causes.
Koestler summarizes some of the directions that Aristotle’s horse has carried us in:
The citadel of orthodoxy which the sciences of life have built … rests on a number of
impressive pillars, some of which are beginning to show cracks and to reveal themselves as
monumental superstitions. The four principal ones, summarized in a simplified form, are the
doctrines
a) That biological evolution is the result of random mutations preserved by natural
selection;
b) That mental evolution is the result of random tries preserved by ‘reinforcements’
(rewards);
c) That all organisms, including man, are essentially passive automata controlled by the
environment, whose sole purpose in life is the reduction of tensions by adaptive
responses;
d) That the only scientific method worth the name is quantitative measurement; and,
consequently, that complex phenomena must be reduced to simple elements accessible
to such treatment, without undue worry whether the specific characteristics of a
complex phenomenon, for instance man, may be lost in the process.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
162
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Cracks or not these four pillars are still very much in evidence today. Recent developments in
molecular biology, especially the epigenetic revolution,15 are casting the pallor of death over the
strict Darwinian paradigm. Although this may eventually pry some of the cracks into complete
fractures, even this will face the creative imagination of mainstream science in the service of the
horse with a remarkable capacity to manipulate words to justify any position.
Koestler goes to considerable lengths to examine characteristics of Hierarchies of various kinds.
They are clearly distinct from the “flatland” of random order. In a footnote he quotes Joseph
Needham:
Whatever the nature of organizing relations may be, they form the central problem of
biology, and biology will be fruitful in the future only if this is recognized. The hierarchy of
relations, from the molecular structure of carbon compounds to the equilibrium of species
and ecological wholes, will perhaps be the leading idea of the future. (Needham J. 1932)
Koestler emphasizes that hierarchic order is a characteristic of all forms of social organization
from “insect state to Pentagon.” It is “true of the process of becoming – phylogeny, ontogeny,
the acquisition of knowledge.”
In more recent years it has been found to be true within the cell. There are homeobox genes that
coherently control batteries of subordinate genes that are hierarchically regulated by complex
transcription factors. And single Cells have an obvious hierarchical relationship to a complement
of tissues in Organs which in turn are hierarchically related to the whole Host creature. And the
host creature is part of a whole species and species part of a genus which is subordinate part of a
whole family, then kingdom and then part of the whole living biosphere which is somehow
regulated by the ontological essence of all being. Hierarchies are all pervasive.
Let us go back now to the earlier part of Koestler’s book where he develops the concept of the
“holon”. Then later we shall see that there is an ingenious method anticipating a far flung future
vision implicit in Nature's bold and risky plan. It may be hanging by a thread but it is surely
there.
Janus and the Holon
The ‘wholes’ and ‘parts’ are not isolated ‘things’ sufficient unto themselves. They are mutually
defined by their mutual relationship. There is no such thing as a species consisting of one
isolated member and no such thing as a species with no members. This ancient philosophical
theme has been expressed and debated as the Universal and Particular, or the One and the Many.
It was implicitly recognized in the ancient Vedas, in ancient Egypt, and in pre-Socratic Greek
philosophy culminating in Plato’s Theory of Forms16 which Aristotle firmly objected to.17 He
replaced it with his categories and four causes. As the saying goes the whole of subsequent
western philosophy is a footnote to Plato and Aristotle. Somehow the debate has avoided
examining the characteristics of hierarchies, especially in modern science and its philosophical
underpinnings. The existence of universals is generally rejected in favour of a bottom up
atomistic approach consistent with Aristotle’s runaway horse across “flatland”.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
163
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Koestler makes a crucial observation that allows a much more intelligible discussion:
The members of a hierarchy, like the Roman God Janus, all have two faces looking in
opposite directions; the face turned toward the subordinate levels is the of a self contained
whole; the face turned upward toward the apex, that of a dependent part. One is the face of
the master the other the face of the servant. This ‘Janus effect’ is a fundamental
characteristic of sub-wholes in all types of hierarchies.
But there is no satisfactory word in our vocabulary to refer to these Janus-faced entities… It
seems preferable to coin a new term to designate these nodes of the hierarchic tree which
behave partly as wholes and wholly as parts, depending on how you look at them. The term I
would propose is ‘holon’ from the Greek ‘holos’=whole, with the suffix ‘on’ which, as in
proton or neutron, suggests a particle or part. (p 48)
The Gestalt school18 has considerably enriched our knowledge of visual perception, and
succeeded in softening up the rigid attitude of its opponents to some extent. But in spite of its
lasting merits, ‘holism’ as a general attitude to psychology turned out to be as one sided as
atomism was, because both treated ‘whole‘ and ‘part’ as absolutes, both failed to take
account of intermediate strictures of sub-wholes…(p 49)
In his discussion of social holons Koestler points out:
We can dissect a complex whole into its composite ‘holons’ of the second and third order,
and so on, but we cannot ‘reduce’ it to a sum of its parts, nor predict its properties from
those of its parts. The hierarchy concept of ‘levels of organization’ in itself implies a
rejection of the reductionist view that all phenomena of life (consciousness included) can be
reduced to and explained by physical-chemical laws. … Whatever the nature of a hierarchic
organization, its constituent holons are defined by fixed rules and flexible strategies.” (pp
54-55)
Koestler elaborates at length on the properties of holons in physical, biological and social
systems. It will be sufficient here to paraphrase his treatment of holons as they relate to our
social situation. The individual person constitutes a nicely integrated hierarchy of molecules,
cells, organs, and organ systems. Looking inward into the space enclosed by the boundaries of
our skin, we can rightly assert that we are something complete and unique, a whole. But facing
outwards, we are constantly reminded that we are a part, an elementary unit in one or several
social hierarchies.
No man is an island – he is a holon. His self-assertive tendency expresses his unique wholeness,
his autonomy and independence as a holon. His equally universal other face on which he
depends relates to the larger whole that transcends him and to which he belongs: his partness.
The self-assertive face is self-gratifying, feeding the horse, being competitive or being a rugged
individual. The self-transcending face of the holon relates to the social group or to an ideal. We
may speak of “clannishness”, “class-consciousness”, “esprit de corps”, “local patriotism”,
“nationalism”, etc. There can also be related integrating tendencies such as “cooperativeness”,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
164
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
“disciplined behaviour”, “loyalty”, “self-effacement”, “devotion to duty”, “internationalism”,
and so on.
Note that most of the terms referring to higher levels of the hierarchy are ambiguous. The loyalty
of individuals towards their clan reflects their integrating tendencies; but it enables the clan as a
whole to behave in an aggressive, self-assertive way. The obedience and devotion to duty of the
Nazi SS Guard kept the gas chambers going. “Patriotism” is the virtue of subordinating private
interests to the higher interests of the nation but “Nationalism” is a synonym for the militant
expression of those higher interests. The infernal dialectic of this process is reflected throughout
human history. It is a manifestation of the delusional streak in the human psyche as evidenced by
the tragic mess we have made of our history.
The single individual, considered as a whole, represents the apex of their organic hierarchy.
Considered as a part, the individual is the lowest unit of the social hierarchy. On this interface
between physiological and social organization, the opposing faces of the holon manifest
themselves in the form of emotive behaviour. So long as all goes well, the self-assertive and self
transcending tendencies of the individual are more or less balanced in their emotional life.
People generally live in a kind of dynamic equilibrium with family, society and beliefs which
constitute their mental environment. It is under conditions of stress that this balance is likely to
become disrupted. In pain, the injured part tends to monopolize a person’s attention. Under
emotional stresses the digestive juices may attack the stomach walls. In rage and panic, the
sympathetic - adrenalin apparatus takes over from higher centres which normally coordinate
behaviour. When sex is aroused, the gonads seem to take over from the brain.
Aberrations of the human mind are to a large extent due to the obsessional pursuit of some parttruth, treated as if it were a whole truth to assert its absolute validity in the teeth of evidence to
the contrary. The orthodox Freudian school in its early stages approximated a closed system: if
you argued that for such and such reasons you doubted the existence of the so-called castration
complex, the Freudian’s prompt answer was that your argument betrayed an unconscious
resistance indicating that you yourself have a castration complex; you were caught in a vicious
circle.
It we turn from individuals to social holons – professional classes, ethnic groups, etc. – we again
find that, so long as all is well, they live in a kind of dynamic equilibrium with their natural and
social environment. In social hierarchies, the physiological controls which operate inside of
organisms are of course replaced by institutional controls which restrain the self-assertive
tendencies of these groups on all levels. Without a moderate amount of self-assertiveness of its
parts, the body social would lose its individuality and articulation. However under conditions of
stress, when tensions exceed a critical limit, some social holons – the army, the farmers or the
trade unions – may get over-excited and assert itself to the detriment of the whole. Alternatively,
the decline of the integrative powers of the whole may lead to similar results, as the collapse of
empires indicates on a grandiose scale.
As far as we can look back on history, human societies have always been fairly successful in
enforcing the sublimation of the self-assertive impulses of the individual – until the howling little
savage in its cot became transformed into a more or less law abiding and civilized member of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
165
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
society. But human societies have also failed to induce a similar sublimation of the selftranscending impulses. Accordingly, the longing to belong, left without appropriately mature
outlets, acts mostly in primitive or perverted forms. On the historic scale, the ravages caused by
the excesses of individual self-assertion are relatively small compared to those which result from
the self-transcending side through misplaced devotion. Self transcending tendencies of the
individual are incomparably more dangerous than the self-assertive tendencies. The crimes of
violence committed for selfish, personal motives are historically insignificant compared to those
committed out of a self-sacrificing devotion to a flag, a leader, a religious faith or a political
conviction. Man has always been prepared not only to kill but also to die for good, bad or
completely futile causes. What can be more valid proof of the reality of the self-transcending
urge than this readiness to die for an ideal?
The need for self-transcendence through some form of ‘peak experience’ (religious, political,
ethnic or aesthetic) is inherent in the human condition. Also the self-assertive behaviour of the
group is based on the self-transcending behaviour of its members. The reason why idealistic
movements – whether religious or secular – show the inevitable tendency to degenerate into their
own caricatures can be derived from the peculiarities of the group mind: its tendency towards
intellectual over-simplification combined with emotional arousal and its quasi-hypnotic
suggestibility by leader figures or belief systems. There is thus a mentality split between faith
and reason, between emotion and intellect, in other words schizo-physiology. A hierarchic
awareness of one’s position as an independent holon is lost. One’s personal responsibility for
their actions is transcended through total identification with the collective belief system. One can
act without conscience.
The paranoid streak is as much in evidence in contemporary history as it was in the distant past
but more devastating in its consequences. As the record shows it is not accidental, but endemic –
inherent in humanity’s condition. Nothing crystallizes the differences between groups more than
language. The group-estranging forces of language are active on every level: nations, political
parties, ideological movements, tribes, regional dialects, the exclusive vocabularies and
interpretations of the Bible, the Torah and the Koran.
The Holon as an Active Interface
Koestler’s presentation is a vitally important step in the right direction. And much of MacLean’s
valuable work on the Limbic System has made its way into standard text books. There is more in
the works however as we shall see. Most fundamental to this is the active interface that is the
primary element in delineating the structural dynamics of how the cosmic order works. 19 When
Koestler speaks of the Janus-faced holon as a basic node of reality he is also speaking of the
cosmic order. It applies anywhere in the universe as he points out. Koestler also says: ‘The
hierarchy is open-ended in the downward as it is in the upward direction. (p 62) This leads to
infinite regress as he points out later but it also allows us to speak of holons in any given context.
The question arises that because the holon suggests itself as a viable fundamental structural
entity can there in reality be infinite regress in both directions? There is more to this than meets
the eye because holons derive from active interface processes.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
166
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
The top end of the cosmic hierarchy is the most fundamental end since holons are conceived to
represent all phenomena. Holons concern boundary conditions between inside and outside.
However Koestler’s discussion of holons is generally confined to things and events in space and
time even though he firmly denies that all behaviour is physically caused or conditioned either in
rats, human beings or in our natural environment. The concept itself however transcends space
and time. It implicitly relates to a timeless or eternal aspect of the cosmic order. This deserves
close examination.
It is a fact so obvious that it goes unrecognized that we can never know the inside of something
to the exclusion of the outside, or vice versa. All we can EVER know is active interface
processes between a common inside and a common outside. We normally see active interface
processes as closed surfaces consisting of organized collections of atoms and molecules.
However there are also open active interfaces that are intimately related to closed active
interfaces. They have universal characteristics according to context. We do not see the universal
characteristics directly because, like holons, they do not exist as physical things in space and
time. They make all primary atoms of hydrogen universally the same even though each atom is
separate and distinct. They make each human being structurally the same even though each
person is separate and behaviourally distinct. A species, whether it is a species of atom, plant,
animal or the human species is a universal active interface in the context in which it specifies the
structural characteristics of all of its diverse members, regardless of their behaviour.
Open Active Interfaces are Archetypes
Archetypes are open active energy patterns operating within all members of each species, like
quarks confined within atoms. As open active interfaces, archetypes are not constrained by
limitations in space and time. We directly recognize that all rats are both the same and different
at the same time regardless of their separation in space and time. It is the same with horses,
chimpanzees and people. We intuitively know this, regardless of the process by which species
may have differentiated in an evolutionary tree. We can identify a particular rat only in relation
to the universal archetypal pattern that is directly evident in all rats, regardless of however
different rats may be as individuals. That is what we mean when we shout “There is a rat!”
We can thus say that open active interfaces are universal archetypes with respect to each
particular species. We can also say it will be the same on any planet in any solar system where
biological life has evolved. We can only identify a particular individual of anything in relation to
its archetypal kind. Archetypes determine the physical characteristics of each species with
respect to its members according to Fixed Rules and Flexible Strategies, as Koestler put it. We
recognize an automobile as a Model ‘T’ Ford because there is an archetypal plan common to all
Model ‘T’ Fords. The body plan is real and universal with respect to its members. It is an
archetypal idea that may be inscribed on a blueprint but the idea itself is not a physical thing. The
body plan is firmly fixed but individual cars may come with certain extras or in different colours
that were introduced as flexible strategies of the archetypal idea that evolved over time.
The contextual hierarchies are open ended in one direction only because they elaborate in
discrete levels within themselves. For example a human being is a member of a self-transcending
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
167
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
archetypal species as well as a member of a self-transcending culture, nation and civilization. But
each person also has archetypal characteristics in their own right.20 We can entertain archetypal
feelings and ideas that subsume hierarchical levels going back through our evolutionary history
to unknown origins of biological life early in the formation and consolidation of the planet.
There is a nested hierarchical interaction and interdependence involved in the living operating
field of the biosphere as a whole. The planet was somehow seeded and pregnant soon after it
cooled to the point where it could support life. Like living systems, solar systems also display
evidence of cyclic birth, death and rebirth. There is a self-similar structural pattern that pervades
the universe.
Active interface processes are universal on a cosmic scale. We can conceive of nothing apart
from them. Light emanates from atomic processes in suns. Closed surfaces on Earth such as trees
and rocks reflect the light to betray themselves as physical things to retinal cells in our eyes.
They in turn transmit through active interfaces at synapses in our nervous system that in turn
reconstructs in our subjective minds the physical shape and appearance of the contextual things
out there that we see objectively around us. The things we see do not physically exist in our
minds. Our mind is our reality and it is not a physical thing. The content of our mind, the reality
that we see, has transient moment to moment characteristics that we timelessly integrate as a
whole to lend the transience integrated meaning. We perceive meaningful continuity through the
perpetual change of circumstances.
The whole nested hierarchy that we actively perceive is integrated through the subsuming
characteristics of a unique open active interface common to the cosmos as a whole. In other
words one unique active interface generates the whole of creation by subsuming and
transcending self-similar open ended hierarchies nested within it. Although it is not a physical
thing it constitutes the nature of reality. There must be a single open active interface between a
universal inside and a universal outside that both transcends and is implicit within the whole of
creation. This is an implicit requirement for us to subjectively integrate the diversity of our
objective experience into a meaningful whole. There are simply no alternative structural
possibilities unless we deny our own mind and choose to believe the universe came galloping out
of absolutely nothing on Aristotle’s runaway horse.
Call the primacy of a universal active interface what you will. Language cannot define its
character because the cosmic order that derives from it defines the roots of meaning implicit in
all language according to context. This universal active interface must admit of both Unity and
Diversity, both One and Many, both Universal and Particular. These related characteristics
hierarchically pervade the universe. Koestler has named this Janus-faced characteristic the holon,
but there is more to the story.
The Rift in Universal Wholeness
We have seen that Universal Wholeness requires that the only boundary condition possible is a
universal active interface between a universal inside and a universal outside, neither of which
can ever be known to the exclusion of the other. We see events with characteristics of space and
time that derive from creation, not vice versa. We cannot assign boundary conditions in the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
168
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
universe to either space or time without begging the questions “What is beyond that?” or “What
was before that?” Space and time can have no independent existence. So all we can know is
active processes occurring across a boundary or interface between a common inside and outside.
This fact of creation is universal.
There is a catch however because the primacy of a Unique Universal Active Interface does not
allow of “other than Self.” If there can be no Being apart from Universal Being there can be no
phenomena in experience. We know from our own experience that this is not so. This requires
that the One Universal Active Interface must allow of a Particular Active Interface that
represents Many. The Rift in Universal Wholeness that results must be mended. In order for
Universal Wholeness to maintain its holistic integrity the Universal Interface must transcend and
subsume the Particular Interface. This means that there is a common Universal interface within
all Particular interfaces, just as each species is universally evident within all of its members. The
age old discussion of Universal and Particular revolves around this structural reality that is
implicit in all phenomena.
There are two orientations between the Universal (interface 1) and Particular (interfaces 2)
possible, ONLY two. They are called System 2. They neatly correspond to the Janus faced
holon. The objective (self assertive) orientation is illustrated in Figure 1.
Because active interfaces share common active centers they are called Centers to make talking
about them less cumbersome. Center 2 looks out to others of its kind that share a common Center
1 within.
Figure 1
The subjective (self-transcending) orientation is illustrated in Figure 2. In the subjective
orientation the Universal Center 1 and Particular Center 2 are coalesced together as ONE to
preserve Universal Wholeness. This can occur with only One of Many Particular interfaces at a
time, that is, one person at a time. In fact it is a timeless realization that transcends space and
time. Consistent with Koestler’s holon each person can become independently captivated by a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
169
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
self transcending universal ideal, religious dogma, nationalistic cause, or whatever. This
verbalized intellectual identification of oneself with an emotional timeless “cause” rooted in the
limbic system allows the individual to act without conscience toward others in order to realize
the cause.
Figure 2
The screams of Hitler galvanized the mainstream population of One particular nation (center 2)
that identified with him (center 1). As the universal father of the Nazi self transcending ideal
(center 1) in Figure 2 he was behind the self-assertive face in Figure 1 invading other particular
nations (centers 2). The transcendent relationship of individual people to the human species was
subverted to the Nazi ideals of the nation. For many people this satisfied a quest for Unity that is
so important to everyone everywhere. The communist manifesto was no less brutal in its
willingness to inflict human suffering to realize a unifying ideal. It is a common pattern
throughout human history. It was evident in the brutality of the slave trade and in genocidal
practices against the Native Americans. It goes on today.
Three Active Interfaces in System 3 define the subsumed level of physical form
There are only four possible ways that three active interfaces can mutually interact with respect
to a universal inside and a universal outside common to each interface. Because there are three
active interfaces it is called System 3.21 Each way defines what is called a Term such that there
are two Universal Terms that are alternate modes of a Unique Set of three centers and two
Particular Terms that represent any number of Particular Sets. For example the Particular Sets
can represent all the primary hydrogen atoms in the universe that share a common relationship to
the Unique Universal Set. Consistent with an elaboration of System 2 above they interact in
alternating modes with the Universal and Particular terms coalesced together in each mode.
Words can be assigned to describe the three hierarchically ordered active interfaces in the open
Universal Set: Idea(1) → Routine(2) → Form(3). We know there is always a Routine of activity
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
170
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
that gives Form to an Idea. Illustrated in Figure 3 is a subjective orientation (below) alternating
with an objective orientation (above). (see reference 16)
Objective above
Subjective below
Figure 3
The three Particular Centers are mutually closed Active Interfaces with spherical surfaces as
represented by the large blue ellipses in the subjective orientation below. In primary hydrogen
atoms Centers 1, 2 & 3 represent the closed photon energy shell, the electron particle, and the
proton particle. The Idea(1) of the whole atom is implicit in the closed Photon energy shell. The
Routine(2) is implicit in the orbiting electron. The center of physical Form(3) is implicit in the
proton. The Unique Open Universal Set is confined within them like quarks and tunnels through
them to intimately link them together in pairs. It does this synchronously for every primary
hydrogen atom in the universe at once. It can do this because it does not exist in space and time
and it is not constrained by the limitations of space and time. Atomic structure, space and time,
have been explored by the author in other articles.22
In the objective mode above, the Particular Closed Interfaces invert and become Open Interfaces
within the One Open Universal Set. The open Electron and Proton interfaces coalesce as one, as
indicated by the “Z” shaped arrow in the Particular Set. This reconciles inside and outside as one
with the Photon Interface. They become mutually balanced and spatially indeterminate quantum
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
171
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Photon energy equivalents of each physical atom. Collectively all such open Photon energy
equivalents constitute the Unique Universal Photon Interface (center 1) in the One Universal Set.
This is called the boundless and timeless Void. It is a boundless Unity without specific forms of
any kind, thus preserving Universal Wholeness via the creative process. This is the objective of
creation. The Void is orthogonal to the integrated fabric of space and time. It is associated with
mind and the recall process on a hierarchy of levels. It is a master sensorium or memory bank. A
new Quantum Relativity emerges naturally from this structural approach. 23 The quantum
equivalent of atomic particles is the Conjugate Energy Equivalent of the wave function which is
why the wave function must be squared to get a result in particle accelerator experiments.
Triadic relationships between three active interfaces are always closed in the subjective mode
and open in the objective mode. For example the Cells and Organs of each Host human being are
in a mutually closed intimate subjective relationship. The existence of each has a specific closed
shape or surface that is clothed with molecules that we can see and identify with respect to the
universal human species. The same is true of any multi-cellular plant or animal. This has been
explored in other articles by the author.24 Closed triadic relationships come into play in many
ways and each has an open quantum equivalent that is a timeless and formless element of
memory in the orthogonal Void.
In the human brain the triad is clearly distinguished between the intuitive right hemisphere, the
language dominated left hemisphere, and the emotional limbic brain. The right brain that
integrates Idea(1) as a whole is fueled via the emotive Routines(2) of the limbic brain for
expression in explicit Forms(3) of thought and behavior. This is elaborated on by System 4.
Four Active Interfaces in System 4 elaborate on Biological Processes
There are only nine possible ways that four active interfaces can mutually interact with respect to
a common inside and outside. They define a matrix of nine interacting Terms that are generated
from five Sets of four active interfaces or Centers. There is a Primary Universal Set and a
Secondary Universal Set, each with its own repeating Term transform sequence. The Universal
Terms cohere together to regulate three Particular Sets that transform through a repeating six
Term sequence, one transform Step apart. Since Particular Terms have Regenerative modes as
well as Expressive modes there are twelve transform Steps in each Particular transform
sequence. How this structural dynamism works has been outlined in various articles. 25,26 It was
first introduced in the author’s book Fisherman’s Guide in 1985.27
The coherently integrated transform sequence of the two Universal Sets repeats every four
Particular transform Steps, so that it takes three such four-Step Cycles to complete the twelve
Step Particular transform sequence. Names can be assigned to each of the four active interfaces
that define the Primary Universal Hierarchy of System 4. (Active interfaces are also assigned
numbers.) As an elaboration of System 3 a Knowledge active interface is distinguished from Idea
such that Idea(1) → Knowledge(2) → Routine(3) → Form(4). We know that there is always an
integrating Idea(1) that directs Knowledge(2) that directs Routines(3) that result in a mental or
physical behavioral Form(4). An Idea to build a house directs Knowledge on how to do it that
directs the Routines of behavior that results in the physical Form. The creative process works this
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
172
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
way. Always. The four words must be interpreted in context however. They are not absolutes
unto themselves. In a human being the Idea of the Host individual directs the Knowledge implicit
in interdependent Organ systems that direct the Routines of Cells that give each person physical
and behavioral Chemical Form.
The Primary Universal Set relates to the human species. The Secondary Universal Set relates to a
specific Host human being. They cohere together to constitute the archetypal pattern of each
person in such a way that the Particular Sets transform from Term to Term, synapse by synapse,
through the nervous system to animate each of us according to circumstantial context. The
human nervous system has structurally evolved to work in just this way. The archetypal pattern
is prescribed by the Primary Universal Archetype of the species. This has been demonstrated in
two advanced articles on the human nervous system, one on Spinal Integration28 and one on the
Cerebellum.29
It will be sufficient for purposes here to illustrate the Primary and Secondary Universal Terms in
the four repeating Steps of each Cycle. The complete Universal Integration of Human
Experience is illustrated in other articles.30,31
Step 1 of each System 4 Cycle
The Primary Universal Set is the universal hierarchy Term 9 that prescribes the 4 Step sequence
of each Cycle. In Step 1 it assimilates the integrating Archetypal Idea (interface 1) of each Host
human being. The Secondary Universal Set in Term 3 is the Transference of Idea into Form. It
relates the Idea(1) of a human Host to molecular Form(4) through the coalescence of
Knowledge(2) implicit in Organs with the Archetypal Routines(3) of Cells that constitute the
complement of Host Organs. The coalescence is represented by the white arrow. Because Term 3
coalesces Idea inside with Form outside it has timeless characteristics that can access appropriate
quantum energies from the Void. Note in Figures 4a and 4b that all centers are open so that any
specific Term 3 human Host is synchronously assimilated with the species prescribed by the
Primary Universal Set in Term 9.
Figure 4a
Figure 4b
The left side of each diagram is the passive representation. It may help to visualize the active
representation that links the active interfaces with patterned energy flows shown with arrows in
all possible ways. There is meaning implicit in each linkage relationship, designated as R1, R2,
R3, etc.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
173
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Step 2 of each 4 Step Cycle
In Step 2 of each Cycle Term 9 does not transform. It advances from the Idea(1) active interface
to the Knowledge(2) active interface which concerns the Knowledge implicit in the
interdependent Host, Organ, Cell organization common to the human species. The Transference
of Idea into Form, Term 3, transforms into the Corporeal Body, Term 6, as illustrated in Figure
5b. In Term 6 we see that the closed intimate triadic relationship between Host(1), Organs(2),
and Cells(2) of each Human Being is realized in physical Form(4), since the archetypal pattern
of the triad Projects via P1, P2, and P3 through the open interface of molecular Form(4)shared
with the biosphere and beyond. In other words the intimately linked triad is independent from the
molecular Form of the body yet its archetypal energy patterns orchestrate the chemistry of Cells
and Organs that make up the physical human Host.
Figure 5a
Figure 5b
In Step 2 many parallel Particular Sets acting through parallel neural and muscular pathways
enact a coherently integrated Term 5 action sequence planned in a previous Cycle. The Particular
action sequence was coherently planned by the Universal Sets as we shall see in Step 4 for the
next action sequence in the next Cycle. The corporeal body in Term 6 thus responds as an
integrated whole in each Particular action sequence. The action sequences are learned from jerky
actions in the crib to smooth performances as we mature.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
174
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
Step 3 of each System 4 Cycle
In Step 3 of each Cycle the Primary Universal Set transforms from Term 9 to a Regenerative
mode of Term 8 illustrated in Figure 6a. The secondary Term 6 does not transform as illustrated
in Figure 6b.
Figure 6a
Figure 6b
Note in Term 6, Figure 6b, that the Host(1) individual, their Organs(2) and Cells(3) are in a
mutually closed intimate triad that is self-similar with the subjective mode of System 3 in Figure
3. This triad however operates within the open active interface of Chemical Form(4) that is
common to the biosphere of the planet. System 4 is nested within System 3 that prescribes
atomic matter. In other words the triad represents the archetypal energy pattern of the human
individual that orchestrates its own chemical clothing within the ecosystem of the planet, as
indicated by the Projections P1, P2 and P3. It is this triadic energy pattern operating behind or
within the physical environment that has evolved up through the hierarchical levels, anchored to
the quadruped limb structure of the reptiles, lower mammals, to higher mammals to humankind.
Chemistry cannot mindlessly orchestrate this magic by itself.
Note in Term 8R, Figure 6a, that the counter-current Relations R1 and R2 relate chemical
Forms(4) to Organs(2) across the open active interface of Cells(3), all within the open active
interface of the Host(1). This budgets the resources of chemical Form(4) within Cells(3) to the
distributed needs of Organs(2). A balance is attained between the resources of chemical energy
Forms in Cells with the needs of Organs within the context of the Host’s needs. The balance is
represented by the Projections P1 and P2. Together this P1 and P2 balance each of the
Projections P1, P2 and P3 in Term 6. All the active interfaces are open in Term 8R so that all
Cells(3) subjectively manufacture their chemical Forms(4) in an objective relationship with the
Organs(2) to which they belong according to demands of the Host(1). Together these archetypal
energy patterns subjectively constitute the open Host(1) species, whether it is the human species,
or a horse species, or whatever. The species dictates the archetypal pattern.
The countercurrent relations R1 and R2 in Term 8R balance universally open Centers that do not
exist as physical things. Since they are not constrained by the limitations of space and time R1
and R2 tunnel through and intimately link in pairs the closed interfaces of the triad in Term 6, in
a self-similar way that the Universal Set does in the subjective mode of System 3 in Figure 3.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
175
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
This aligns the Primary Universal open Idea(1) of the species in Term 8R with the open chemical
Form(4) of each member of the species in Term 6. All humans thus have a self-similar molecular
structure, as do all members of any species. We identify each creature as a living Idea(1) defined
by its species.
Step 4 of each System 4 Cycle
In Step 4 the Primary Universal Set in Term 8R does not transform. The Secondary Universal
Set in Term 6 transforms to invert its triadic relationship with respect to the Open Interface of
chemical Form(4). Chemical Form(4) is now within or subjective to the closed Cells(3) in their
intimate relationship with the individual Host(1) and their complement of Organs(2). This means
that the chemical resources of all Cells(3) in a specific human being are equitably distributed as
they relate to the needs of each Host(1) human being with respect to their complement of
Organs(2) involved in a specific action sequence. The action will be enacted by Particular Terms
5 two transform Steps later.
Figure 7a
Figure 7b
R1 and R2 of the Primary T8R Term tunnel through and intimately link the closed active
interfaces of the triad as in Step 3. In this case however, the triad represents a specific integrated
action pattern aligned with the Primary Universal Archetype of the Host(1) species. The planned
action sequence is the R1 Idea in the Secondary Universal Term 2E (Figure 7b) that will be
physically enacted in Step 2 of the next Cycle by synchronous Particular behavior Terms in
many parallel Particular Sets in a specific human individual. The patterned funding and
distribution of the energies needed is dictated by the mutually coherent archetypal patterns of the
two Universal Sets in Step 4 of each Cycle.
Figure 7b is a closed subjective orientation of a specific person integrating a specific creative or
behavioral Idea represented by R1 superimposed on the triad. We are free to create ideas as we
subjectively desire, according to how we individually chose to integrate our experience
consistent with our resource capacity to do so. This Figure 7b closed idea R1 is subjectively
entertained. It can be a self-transcending Ideal that regulates the activity of the Particular Sets in
a specific human Host. It determines the integrated action sequence of the Corporeal Body (Term
6 in Figure 5b) that follows two Steps later in Step 2 of the next Cycle.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
176
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
In Step 2 of the next Cycle a Particular Expressive action sequence occurs via the neural
musculature. The Corporeal Body Term 6 relates objectively outward through its physical
Form(4) as the self-assertive face in concert with the Primary Universal Term 9. The structural
substrate of Arthur Koestler’s Janus-faced holon is implicit in these two orientations, one selftranscending and one self-assertive of the Secondary Universal Set.
If the individual chooses to override the Primary Universal Host(1) of the species in Term 8R by
personally identifying, not with our common humanity, but with an extreme political, religious,
ethnic or other ideal or transcending ‘cause,’ then the patterned energies funded by projections
P1 and P2 of Term 8R will reflect the person’s emotional commitment to the extreme ideal,
represented by R1 in the Secondary Universal Term T2E. Their natural human conscience will
be subverted to the service of a runaway horse. wE have free will in this respect. (The four Steps
of each Cycle keep repeating).
Koestler, however, related the two faces of the holon to the split between the primitive emotional
limbic system and the intellect of the new brain or neocortex, empowered with language. The
triad indicates there is more to the way emotion and intellect interact. There are three
independent yet mutually related closed boundaries involved. This requires that there must be
another split in brain function that accounts for aberrations of behavior that are peculiar to
humanity. The evolution of language has polarized the function of the neocortex into two distinct
yet mutually related minds, as we shall see. But first a brief look at how the Particular Terms
relate will be helpful.
The Polar Relations of the Six Particular Terms
As mentioned the three Particular Sets transform through a sequence of six Particular Terms. The
three Sets transform from Term to Term one Step apart in a repeating sequence. Term 7 is the
memory Term. It is tensionally coupled to sensory input in Term 4. The sequence of Term
transformations recalled is the inverse of the number 7, which is 1,4,2,8,5,7 repeating. This
means the Terms 8, 7, 4 alternate with Terms 1, 2, 5. The structural relationships between the
active interfaces within each Term implicitly defines the basis of meaning which has a dynamic
relationship to the meaning defined in each of the other Terms. Each Term transformation
conforms precisely to a synapse in the integration of the whole nervous system. The human
nervous system has evolved to work in precisely this way. The six Terms dynamically integrate
meaning that is contextually understood in three polar pairs that relate to our three brains. The
numbers in the following text refer to Figure 8.
One polar pair provides insight into the Potential Dimension of experience via the right
hemisphere. For example the potential of a specific creative idea(Term 1) has a polar
relationship to the person’s resource capacity(Term 7) to realize it. They may have an idea to
sprint for a mile but they intuitively know from memory they do not have the resource capacity
to do it. They may have an idea to buy or build a yacht or an airplane but they intuitively know
whether or not they may have the resources to make the potential idea a physical reality. A
person may also identify with the Idea of a social movement that depends upon popular support
of a portion of the population.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
177
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
The second polar pair provides insight into the Commitment Dimension via the left hemisphere.
A person’s commitment to a specific behavior(Term 5) can only be assessed in a polar
relationship to social organization(Term 4) in the social context. A person may have a
commitment to feed their family but they know it is not legal to rob a convenience store to do it.
They make their commitment to a job and earn the means to feed their family by making a
contribution to our collective social organization. If they commit to building a small airplane as a
hobby they will need suppliers of plans and materials in the social marketplace. One can also
identify with an exclusive social movement that can be anti-social in the larger context of
humanity. Terrorist actions are becoming commonplace.
The third polar pair provides insight into the Performance Dimension via the limbic system. The
limbic system fuels the energy Resources(Term 1) to develop a potential idea and make a
commitment to act on it, but it also assesses the whole performance by emotional
feedback(Term 8E). A person can be emotionally satisfied or dissatisfied with the result. A man
may have an emotional desire to build a small airplane that becomes his guiding vision(1) that
leads him to check out sources(4) and decide on a specific plan(2) that he is satisfied with(8) and
commits to(5). He learns from his creative efforts and it is committed to memory(7). When his
project is finally finished he will emotionally assess(Term 8E) his degree of success with respect
to the emotional germ that was his guiding vision(Term 1). We seek emotional balance whether
our commitments are socially acceptable or not. A thief may be happy to get away with a
robbery. The policeman may be content to catch him.
Figure 8.
We find that both Universal and Particular Term transformation sequences indicate there is a
split between right and left brain function. This brings us to the experimental work done on split
brain patients. Our self-assertive face is our left brain commitment to behavior. Our selftranscending face is the right brain potential or integrating ideal that guides us. Both are fueled
and performance assessed by the limbic system.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
178
Journal of Consciousness Exploration & Research | February 2014 | Volume 5 | Issue 2 | pp. 155-178
Campbell, R., The Two Faces of Our Three Brains (Part I)
References
1
Koestler A. The Ghost in the Machine. London: Hutchinson (1967); Page number references in the text are to the
Picador Edition 1975-1981.
2
Watson, J. B. (1913). Psychology as the Behaviorist Views it. Psychological Review, 20, 158-177
3
Watson, J. B. (1930). Behaviorism (Revised edition). Chicago: University of Chicago Press.
4
Skinner, B. F. (1972). Beyond freedom and dignity. New York: Vintage Books.
5
Campbell R. http://www.cosmic-mindreach.com/System_Intro.html
6
ibid
7
Broca, P. Anatomie comparée des circonvolutions cérébrales: le grand lobe limbique. Rev. Anthropol.
1878;1:385–498.
8
Campbell R. http://www.cosmic-mindreach.com/Three-Brains.html
9
Papez JW. A proposed mechanism of emotion. 1937. J Neuropsychiatry Clin Neurosci. 1995;7(1):103-12.
10
P. D. MacLean (1952). "Some psychiatric implications of physiological studies on frontotemporal portion of
limbic system (visceral brain)". Electroencephalography and Clinical Neurophysiology 4 (4): 407–418.
11
MacLean PD (1990) The Triune Brain in Evolution: Role in Paleocerebral Functions. NY: Plenum Press.
12
Cannon WB (1929). Bodily changes in pain, hunger, fear, and rage. New York: Appleton-Century-Crofts.
13
MacLean PD (1949) Psychosomatic disease and the ‘visceral brain’: recent developments bearing on the Papez
theory of emotion. Psychosom Med. 11:338 –353.
MacLean PD (1962) New findings relevant to the evolution of psychosexual functions of the brain. J Nerv Ment
Dis. 135:289 –301.
MacLean PD (1967) The brain in relation to empathy and medical education. J Nerv Ment Dis. 144:374 –382.
MacLean PD (1973) A triune concept of the brain and behavior. In. TJ Boag, D Campbell (Eds), The Hincks
Memorial Lectures (pp 6–66), Toronto: University of Toronto Press.
MacLean PD (1978) Effects of lesions of globus pallidus on species-typical display behavior of squirrel monkeys.
Brain Res. 149:175–196.
MacLean PD (1985) Brain evolution relating to family, play and the separation call. Arch Gen Psychiatry.
42:405– 417.
MacLean PD (1985) Evolutionary psychiatry and the triune brain. Psychol Med.15:219 –221.
MacLean PD (1988) Evolution of audiovocal communication as reflected by the therapsid-mammalian transition
and the limbic thalamocingulate division. In JD Newman (Ed), The Physiological Control of Mammalian
Vocalization (pp 185–201), New York: Plenum Press.
MacLean PD (1993) Cerebral evolution of emotion. In M Lewis, JM Haviland (Eds), Handbook of Emotions (pp.
67– 83). New York: Guilford Press.
14
Campbell R, (2013) http://www.cosmic-mindreach.com/Science_tests-cosmic_order.html.
15
Carey N. (2012) The Epigenetics Revolution: How Modern Biology is Rewriting Our Understanding of Genetics,
Disease and Inheritance. London: Icon Books
16
Cornford, FM. (1957). Plato and Parmenides. New York: The Liberal Arts Press.
17
Fine G. (1993) On ideas: Aristotle's criticism of Plato's theory of forms. Oxford: Clarendon Press
18
Koffka, K. (1935). Principles of Gestalt psychology New York: Harcourt, Brace, & World.
19
Campbell R. http://www.cosmic-mindreach.com/Unified_Theories.html
20
Jung C.G. Jung C.G. The Archetypes and The Collective Unconscious. In: The Collected Works of C. G. Jung
Vol. 9 Part 1. London: Routledge, 1980.
21
Campbell R. (1973) http://www.cosmic-mindreach.com/System3.html
22
Campbell R. (1997) http://www.cosmic-mindreach.com/Atomic_structure.html
23
Campbell R. (2008) http://www.cosmic-mindreach.com/Gravity.html
24
Campbell R. (2011) http://www.cosmic-mindreach.com/Gene_Expression.html
25
Campbell R. (1976, 2005) http://www.cosmic-mindreach.com/System4.html
26
Campbell R. (1976, 1985, 2005) http://www.cosmic-mindreach.com/System4Terms.html
27
Campbell R. Fisherman’s Guide: a Systems Approach to Creativity & Organization. Boston: Shambhala 1985
28
Campbell R. (2006) http://www.cosmic-mindreach.com/System4_Sequence_Steps.html
29
Campbell R. (2006) http://www.cosmic-mindreach.com/System4_Sequence_Part_2.html
30
Campbell R. (2012) http://www.cosmic-mindreach.com/Human_Integration_Cell_article.html
31
See 26 above
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
590
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 590-592
Kaufman, S. E., The Next Moment
Realization
The Next Moment
Steven E. Kaufman*
ABSTRACT
When you are in the next moment, looking for the Divine, looking for some sort of fulfillment,
you are really still in this moment, in the Now, but having shrouded yourself in the form that is
the next moment, the Divinity that Is Now is obscured, and so fulfillment eludes you. True
fulfillment comes with finding the Divine, and Knowing yourself as That. The illusion of
fulfillment comes with acquiring some form, and adding that form to one's form-identity. True
fulfillment does not end. The illusion of fulfillment ends almost as soon as it has begun.
Key Words: next moment, Divine, Now, fulfillment, knowing.
The Divine is just as present in this moment as It is going to be present in the next moment. So
why run from one moment to the next, looking to find It there, when It is already here in full
measure? Especially since looking for It in the next moment hides It in this moment. Such a
game of hide and seek.
Here we are, in this moment, where the Divine is everywhere, both within us and all around us,
but we can't see It, because we are looking for it in the next moment, and so its Presence in this
moment is obscured. And then the next moment becomes this moment, but we still can't find It
because we are still looking for It in the new next moment.
But if the Divine is here in this moment, then why is it not also in the next moment? Why can It
only be found in this moment, and not the next? Because this Moment is Alive, whereas the next
moment is only a shadow of Life. If you want to find someone, do you find them where they are
or where only their shadow lies?
The Divine is Life and that Life Is Now.
The next moment is only a form that arises in this Moment, in the Now.
The next moment exists, the Divine Is.
The Divine is not found in that which only exists.
The Divine is only found in That which Is, because the Divine Is That which Is.
This Moment Is, the Now Is.
The next moment is not.
The next moment is only an idea, a thought, a form, a concept.
The next moment is not what Is.
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
591
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 590-592
Kaufman, S. E., The Next Moment
Looking for the Divine in the next moment is like looking for someone in what is only their
shadow or reflection. There is some relation between the person for whom you are looking and
their shadow or reflection, but they are not the same. Likewise, there is some relation between
the Divine and the next moment, but they are not the same.
When you are in the next moment, looking for the Divine, looking for some sort of fulfillment,
you are really still in this Moment, in the Now, but having shrouded yourself in the form that is
the next moment, the Divinity that Is Now is obscured, and so fulfillment eludes you.
True fulfillment comes with finding the Divine, and Knowing yourself as That. The illusion of
fulfillment comes with acquiring some form, and adding that form to one's form-identity. True
fulfillment does not end. The illusion of fulfillment ends almost as soon as it has begun.
When one drinks of the Real their thirst is quenched.
When one drinks what is only a shadow of the Real, their thirst is unending.
It feels good to be thirsty, when one knows where the eternal Fountain lies.
It does not feel good to be thirsty, when all one sees around them is a desert.
The next moment is a desert.
This Moment, the Now, is where the eternal Fountain lies.
Drink from it but once and you will Know true Satisfaction and true Fulfillment.
But even having once found the Fountain and having drank from it, you may on occasion find
yourself wandering in the desert of the next moment, thirsty and in search of the Fountain that
was right there, only a moment ago, but which has now vanished. Just remember, if you can’t
find It, it's not because It's not there; rather, it's only because you are looking for It in the wrong
place, in the next moment, where It must remain hidden. To locate the hidden Fountain just
return to this Moment, to the Now, and it will reappear, as if out of thin air. And you will once
again be able to drink your fill.
And after drinking your fill, and having your thirst quenched, a thought will come along, like a
butterfly in a field, and you may chase after it, and while chasing after it you may again wander
into the desert of the next moment, and you will again become thirsty and you will turn to drink
from the Fountain and it will once again seem to have disappeared.
Where has it gone?
Nowhere.
It remains where it always Is, in this Moment, in the Now.
It is not the Fountain that has moved, it is you that has moved.
It is not the Fountain that has gone somewhere, it is you that has gone somewhere.
And where have you gone?
Into next moment.
The Fountain never moves, never goes anywhere. It just Is, and It is always Now. You don't
really go anywhere either, since you also just Are, and are always Now. You just think you do.
You just think yourself into past or future, into someplace that seems to be other than Now. So it
is not a matter of actually returning to the Now from someplace that is actually other than Now.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
592
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 590-592
Kaufman, S. E., The Next Moment
It is just a matter of realizing that there is only Now, which can become disguised and so hidden
when dressed in the apparent reality of the next moment.
Such a game Consciousness plays with Itself.
Peek-a-boo on a cosmic scale.
Consciousness hiding from Itself amongst the forms It creates,
Losing Itself in the past and future,
And then finding Itself again in this Moment,
In the Now,
Which is all there ever really Is.
Finding Itself again in the Now,
As the Now,
And so Knowing Itself to Be
All that Is.
Never really any danger, never really anything wrong.
Just what Is, enjoying Itself.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
714
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
Article
The Falsehood of the Materialists’ Mindless
Evolution of Minds from Mindless Matter
Graham P. Smetham*
Abstract
Despite the fact that the advent of the quantum revolution indicates that the ultimate ‘stuff’ of the
process of reality, made up of quantum fields, is insubstantial and immaterial, there seem to be a
legion of past their sell by date pundits still championing the cause of a crude nineteenth century
materialism. Materialists cling to the conviction that ‘matter’ is the ultimate constituent of the
process of reality, as when Dennett asserts that a “mindless little scrap of molecular machinery”
is the basis for the development of mind. However, the unfolding quantum teleological perspective suggests that that there is a mind-like inner teleological ‘pressure’ operating within the quantum realm of potentiality which functions in order to manifest the potentialities into experienced
‘realities’.
Keywords: materialism, mindless evolution, mindless matter, quantum revolution, Darwinism,
consciousness, quantum teleology, Dennett, Dawkins, Stapp, Mensky.
How … could mere ‘appearances to consciousness’ generate consciousness?1
- Bernard d’Espagnat (21st Century quantum physicist)
How can you say the elements, which are the object of your mind,
Compose the latter’s nature? This surely cannot be!
And how can you with minds so thickly clouded
Ever comprehend aright what lies beyond this world …
The nature of phenomena you understand amiss.
Your view is based upon, coordinated with, the body you possess;
It’s just as when you say the elements are all that is …
Dense ignorance enshrouds the world as though by massing clouds;
Because of this phenomena are misperceived.2
-
Chandrakirti (6th Century Buddhist philosopher)
Philosophers of mind appear to have arrived, today, at less-than-satisfactory solutions to the mind-brain and free will problems, and the difficulties seem, at least prima facie, very closely connected with their acceptance of a known-to-be-false understanding of the nature of the physical world, and of the causal role of our conscious
thoughts within it.3
Henry Stapp (21st Century quantum physicist)
*
Correspondence: Graham Smetham, http://www.quantumbuddhism.com E-mail: graham.smetham@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
715
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
What are we to make of the fact that currently there are many ‘philosophers’ and purveyors of
consciousness studies safely ensconced in lucrative academic positions at some of the most prestigious centres of (putative) learning who are committed to misleading their students and the
general public as to the ultimate nature of the process of reality? I speak of course of those academic reprobates who, in their determined quest to rid the world of a religious dimension and
sensibility, regularly pen articles and books, and give lectures and sometimes radio and television programmes, proclaiming a fallacious materialist doctrine. Despite the advent of the quantum revolution, which now, with the findings of quantum field theory and the apparent validation
of the Higgs mechanism, indicates that the ultimate ‘stuff’ of the process of reality, made up of
quantum fields, is insubstantial and immaterial, there seem to be a legion of past their sell by
date pundits still championing the cause of a crude nineteenth century materialism. Richard
Dawkins, for example, suggests to his readers in his book River Out of Eden that a crude atomic
view of the process of reality is an adequate 20th century metaphysics. He begins by quoting a
verse by Piet Hein:
Nature, it seems, is the popular name
For milliards and milliards of particles
Playing their infinite game
Of billiards and billiards and billiards.
He then writes:
Piet Hein captures the classically pristine world of physics. But when the ricochets of
atomic billiards chance to put together an object that has a certain, seemingly innocent
property, something momentous happens in the universe. That property is an ability to
self-replicate…[which] is injected into the hitherto humble game of atomic billiards.4
The problem with this classically simplistic materialist vision, however, is that, as quantum physicist Henry Stapp has said: “this kind of ‘matter’ does not exist in nature.”5 When it comes to the
notion that brains are ultimately comprised of atomic type stuff Stapp has written that:
…no such brain exists; no brain, body, or anything else in the real world is composed
of those tiny bits of matter that Newton imagined the universe to be made of.6
However, Dawkins’ philosophical bulldog buddy Daniel Dennett has, in contrast to Stapp and
many other physicists, pugilistically proclaimed the victory of the materialist cause:
There is only one sort of stuff, namely matter – the physical stuff of physics, chemistry and physiology – and the mind is somehow nothing but a physical phenomenon.
In short, the mind is the brain.7
And he appears to be a determined champion of mindlessness:
An impersonal, unreflective, robotic, mindless little scrap of molecular machinery is
the ultimate basis of all the agency, and hence meaning, and hence consciousness, in
the universe.8
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
716
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
Dennett also endorses low-level idiocy; when discussing the capacities of the nerve cells and
connections which underlie the operation of ‘high-level’ brain activity he tells us that they are
like stupid ‘homunculi’, in contrast to notions of high-level intelligent ‘fancy homunculi’:
…homunculi so stupid (all they need to do is say yes or no when asked) that they can
be, as one says, ‘replaced by a machine’. One discharges fancy homunculi from one’s
scheme by organizing armies of idiots to do the work.”9
In other words (leaving aside his childishly simplistic notion of what neurons do), Dennett
claims that all the scientific, artistic and cultural achievements of humanity can be ultimately
traced to fundamental idiocy!
Dennett, despite his claim that ‘matter’ is the ‘stuff’ taken as fundamental by physics, does not
seem to take account of the views of physicists but has his own version of physics, a version
which has not taken steps beyond the nineteenth century; for it is now indisputable that the ultimate stuff of the process of reality are immaterial quantum fields:
Quantum field theory, the tool with which we study particles, is based upon eternal, omnipresent objects that can create and destroy those particles. These objects are the
“fields” of quantum field theory. … quantum fields are objects that permeate spacetime
… they create or absorb elementary particles … particles can be produced or destroyed
anywhere at any time.10
And quantum fields are insubstantial and immaterial (assuming that we are using the notions
of ‘matter’ and ‘material’ in the usual sense of ‘solid stuff’, which is what materialists actually
do mean by these terms, although they have to use some hefty linguistic and philosophical
tricks to argue the case):
Now, from a philosophical point of view, this is rather big stuff. Our whole manner of
speech … rather naturally makes us think that there is some stuff or substance on which
properties can, in a sense, be glued. It encourages us to imagine taking a particle and
removing its properties one by one until we are left with a featureless ‘thing’ devoid of
properties, made from the essential material that had the properties in the first place.
Philosophers have been debating the correctness of such arguments for a long time.
Now, it seems, experimental science has come along and shown that, at least at the
quantum level, the objects we study have no substance to them independent of their
properties.11
The immaterial status of quantum field has certainly been reinforced by recent events at CERN
where the discovery of the Higgs quantum field has been intimated:
Our instinct is to equate inertial mass with the amount of substance that the object possesses. The more ‘stuff’ it contains, the harder it is to accelerate. The Higgs mechanism
turns this logic on its head. We now interpret the extent to which the particles acceleration is resisted by the Higgs field as the particle’s (inertial) mass. The concept of mass
has vanished in a puff of logic. It has been replaced by interactions between otherwise
massless particles and the Higgs field.12
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
717
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
As science writer Jim Baggott points out in his book Higgs: The Invention and Discovery of
the God Particle:
It seems logical that there should be some ultimate constituents, some undeniable reality
that underpins the world we see around us and which lends it form and shape. If matter
is endlessly divisible, then we would reach a point where the constituents themselves
become rather ephemeral - to the point of non-existence. Then there would be no building blocks, and all we would be left with are interactions between indefinable, insubstantial phantoms which give rise to the appearance of substance. Unpalatable it may be
but, to a large extent, this is precisely what modern physics has shown to be true. Mass,
we now believe, is not an inherent property or ‘primary’ quality of the ultimate building
blocks of nature. In fact, there is no such thing as mass. Mass is constructed entirely
from the energy of interactions involving naturally massless elementary particles. The
physicists kept dividing, and in the end found nothing at all.13
In the light of all this, it would seem that Dennett’s assertion that matter “the physical stuff of
physics” is as insubstantial as the quantum fields which give rise to the illusions of solid, material stuff.
In this context it is worth briefly examining a controversy which was prompted by the claim by
Lawrence Krauss, a theoretical physicist and Director of the Origins Institute at Arizona State
University, in his book A Universe From Nothing: Why There Is Something Rather Than Nothing, that the entire universe could have emerged from ‘nothing.’ By ‘nothing’ what Krauss is referring to is quantum field theory. The respected physicist and philosopher of science David Albert rightly took Krauss to task for claiming that quantum fields are ‘nothing’. Albert wrote in a
New York Times Review of the book:
The particular, eternally persisting, elementary physical stuff of the world, according to
the standard presentations of relativistic quantum field theories, consists (unsurprisingly)
of relativistic quantum fields. And the fundamental laws of this theory take the form of
rules concerning which arrangements of those fields are physically possible and which
aren’t, and rules connecting the arrangements of those fields at later times to their arrangements at earlier times, and so on — and they have nothing whatsoever to say on
the subject of where those fields came from, or of why the world should have consisted
of the particular kinds of fields it does, or of why it should have consisted of fields at all,
or of why there should have been a world in the first place. Period. Case closed. End of
story. … Relativistic-quantum-field-theoretical vacuum states — no less than giraffes or
refrigerators or solar systems — are particular arrangements of elementary physical
stuff. The true relativistic-quantum-field-theoretical equivalent to there not being any
physical stuff at all isn’t this or that particular arrangement of the fields — what it is
(obviously, and ineluctably, and on the contrary) is the simple absence of the fields! 14
It is quite clear from this precise description of the situation that “elementary physical stuff” consists of quantum fields, not matter, and not “nothing”. The notion that the process of reality is
nothing else but an “infinite game of billiards and billiards and billiards” is, then, not just wide of
the pocket, it is not even on the table.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
718
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
In his excellent, although metaphyscically confused, book Aping Mankind Raymond Tallis,
Profeesor of Geriatric Medicine at the University of Manchester, deconstructs and demolishes the
twin supports of the current materialist madness – which he terms Neuromania and Darwinitus.
Neuromania is the unsupported, and both scientifically and philosophically confused, dogmatic
belief and academic craze which asserts that all the functioning of the mind and its scientific and
cultural products can be accounted for purely on the basis of a materialist account of brain structure an functioning. Tallis lists some of the dismal and laughable academic products of this craze
for a brain-only description of the mind and consciousness: neuro-economics, which claims that
all economic behaviour such as pursuing short-term gains are directly linked, and entrely explained by brain structure and function; neuro-law, which claims that the brain makes people
misbehave and there is no free-will involved; neuro-literary-criticism, which claims that the contents and structure of literary works are entirely explained by brain makeup; neuro-theology,
which claims to have discovered the God-spot in the brain; neuroaesthetics, which reduced aesthestic sensibility to nothing more than vibrating brain-jelly; neuro-art-history, which asserts that
even accounts of the development of art as well as art itself is written in the brain; and neurolinguistics, which asserts that language has been preprogrmmed by evolution into brain structure.
In all of these supposedly academic disciplines it is asserted that the various scientific and cultural activities and products involved can be entirely accounted for by brain structure and function.
One enthusiastic neuromaniac for instance has written:
It may not be too much to say that sociology and all the other social sciences, including
the humanities, are the last branches of biology waiting to be included in the Modern
Synthesis.15
The ‘modern synthesis’ is the materialist Darwinian worldview within which all behaviour and
all organic, mental and cultural phenomena, including consciousness itself, are claimed to be
nothing more than the result of the processes of materialist Darwinian evolution involving “milliards and milliards of particles playing their infinite game of billiards and billiards and billiards.”
As Tallis points out:
If the imperialist ambitions of Neuromania and Darwinitus were fully realised, they
would swallow the image of humanity in the science of biology. Our distinctive nature,
our freedom, our selfhood, and even human society would be reduced to the properties
of living matter, and this would be reduced, via molecular biology, to matter period.16
Elsewhere in his book Tallis points out that:
… to be identified with our brains is to be identified with a piece of matter, and this, like
all other pieces of matter, is subject to, and cannot escape from, the laws of material nature. Everything that happens in our brains is the product of material events that impinge
on them, and the events that result from brain activity … are wired into the endless causal net, extending from the Big Bang to the Big Crunch…17
This is certainly a correct conclusion based upon the materialist and deterministic worldview.
However, it is also a necessary conclusion that completely undermines the deterministic materialist cause, this is because tracing this causal net back to the Big Bang takes us back to the initial
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
719
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
point in this universe wherein no matter, in the sense that materialists conceive of ‘matter’, existed.
Steven Hawking and Leonard Mlodinow tell us in their book The Grand Design: New Answers
to the Ultimate Questions of Life:
We are the product of quantum fluctuations in the very early universe. 18
And, furthermore, according to H&M:
In this view, the universe appeared spontaneously, starting off in every possible way.
Most of these correspond to other universes …. Some people make a great mystery of
this idea, sometimes called the multiverse concept, but these are just different expressions of the Feynman sum over histories.19
The Feynman sum over histories account of quantum behaviour accounts for the phenomenon of
the famous double-slit experiment, wherein it appears that quantum ‘particles’ must spread out as
probability waves and travel through both slits, by indicating that quantum ‘particles’ must take,
as quantum potentiality, all possible paths between any two points. The ‘classical’ paths can be
calculated by performing a sum over the histories of all possible paths. On a cosmic scale this
perspective corresponds to the multiverse scenario, the spontaneous quantum creative burst of
the point of the Big Bang creates the multiverse of all possible worlds. A hugely significant feature of the H&M presentation of Feynman’s ‘sum over histories’ quantum presentation is the fact
that the “observers are part of the system” and have serious work to do:
The histories that contribute to the Feynman sum don’t have an independent existence,
but depend on what is being measured. We create history by our observations, rather
than history creating us.20
In other words the observers, or what John Wheeler called ‘observer-participants,’ are able to
weed out possible universes, and thereby select those which remain in the possibility mix, even
backwards in time. Thus one of the central chapters in The Grand Design is entitled ‘Choosing
Our Universe’:
The idea that the universe does not have a unique observer-independent history might
seem to conflict with certain facts that we know. There might be one history in which
the moon is made of Roquefort cheese. But we have observed that the moon is not
made of cheese, which is bad news for mice. Hence histories in which the moon is not
made of cheese do not contribute to the current state of our universe, though they might
contribute to others. This might sound like science fiction but it isn’t.21
The Big Bang was the first cascade of ‘creation operations’ (‘creation operators’ are the mathematical representation of the creation of ‘particles’) within the insubstantial and immaterial preexisting quantum field of potentiality which eventually gave rise to the current universe. On this
view it is clear that consciousness cannot be a creation of the material brain because if the H&M
view is correct, and it concords in broad outline, if not in detail, with most other quantum viewpoints, then it must be consciousness that creates the material of the brain, not the other way
around as claimed by materialists. Quantum physics, therefore, tells us that the brain-only viewpoint which underlies the worldview common to Neuromania and Darwinitus cannot be true.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
720
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
And yet it is stubbornly clung to by many academics who promulgate the most absurd notions
and arguments that are in contradiction with established physical theory.
As Stapp has pointed out, such brain-only materialist views derive from the “acceptance of a
known-to-be-false understanding of the nature of the physical world, and of the causal role of our
conscious thoughts within it.”22 The astonishing fact is that, for some incomprehensible reason,
the academic community has decided to allow some of its members, usually philosophers or purveyors of ‘consciousness studies’, to flagrantly misrepresent the truth of contemporary physics in
order to defend obviously incorrect, ‘classical,’ positions which are redolent of the worldview of
the late nineteenth century. As Stapp points out:
…the re-bonding [between mind and matter] achieved by physicists during the first
half of the twentieth century must be seen as a momentous development: a lifting of the
veil. Ignoring this huge and enormously pertinent development in basic science, and
proclaiming the validity of materialism on the basis of an inapplicable-in-this-context
nineteenth century science is an irrational act.23
Indeed!
Stapp, like Hawking and Mlodinow, clearly tells us that consciousness has a role in performing
‘choices’ that impact upon the quantum realm and echo into the future in a manner reminiscent
of Whitehead’s ‘Process Philosophy.’ Stapp writes with great clarity and precision on such implications of quantum theory and extends his conclusions in a religious direction:
I see no way for contemporary science to disprove, or even render highly unlikely, this
religious extension of quantum theory, or to provide any strong evidence in support of
an alternative picture of the nature of these “free choices.” These choices seem to be
rooted in reasons that are rooted in feelings pertaining to value or worth. Thus it can be
argued that quantum theory provides a rational opening for an idea of nature and of our
role within it that are in general accord with certain religious concepts…24
In this remarkable observation Stapp clearly indicates that quantum theory can have religious
implications, a view which challenges some of the central dogmas of Neuromania and Darwinitus. As we shall see, a fundamental feature of the current materialist craze for Neuromania and
Darwinitus amongst certain sections of the academic community is its anti-religious commitment. Dawkins goes so far as to characterize the materialist community as being in the midst of
an intellectual war, declaring that “science has a battle for hearts and minds on its hands”25 The
battle he is alluding to is the stubborn and protracted commitment to an almost childishly simplistic materialism in the face of the profound and subtle discoveries of the quantum age which
he and other are engaged in. And one of the reasons for this struggle is desire to stem the tide of
intelligent design scenarios with the concomitant religious implications.
One aspect of the emerging quantum worldview is the fact that consciousness is entangled within the quantum realm. Wojciech Zurek, a leading physicist in the field of quantum decoherence
theory, refers to the quantum ‘stuff’ or reality, which is the fundamental ‘stuff’ of reality as
‘dream stuff’:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
721
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
…quantum states, by their very nature share an epistemological and ontological role –
are simultaneously a description of the state, and the ‘dream stuff is made of.’ One
might say that they are epiontic. These two aspects may seem contradictory, but at least
in the quantum setting, there is a union of these two functions.26
Here Zurek indicates that the details of quantum functioning require that the ‘knowing’ aspect of the process of reality and the ontological ‘known’ aspects are interconnected, the
former determining the latter. The fundamental insight of this view, which Zurek terms
‘quantum Darwinism’, indicates that the epistemological function of consciousness, which is
embodied in perception, has a role in determining ontology. As Zurek has pointed out:
Measurement – perception – is the place where physics gets personal, where our role and
our capabilities as observers and agents of change in the universe (and our limitations as
entities subject to the laws of physics) are tested - or, rather, where we get put in our
place. I believe that quick solutions, and I include both the Copenhagen interpretation
and many worlds here, have a tendency to gloss over the real mystery, which is how do
we - that is to say, how does life - fit within the quantum universe. I think we have managed to constrain the possible answers (for example, through research on decoherence),
but I believe there is more to come. The virtue of the focus on quantum measurement is
that it puts issues connected with information and existence at the very center. This is
where they should be.’27
This is a view which places the perceptual activities of all sentient beings at the centre of the
process through which the ontology of reality is etched out of the quantum dream realm of potentiality. As Wheeler remarked:
Directly opposite to the concept of universe as machine built on law is the vision of a
world self-synthesized. On this view, the notes struck out on a piano by the observer
participants of all times and all places, bits though they are in and by themselves, constitute the great wide world of space and time and things.28
A viewpoint which, again, chimes in unison with the H&M quantum metaphysical model which
requires that some kind of collective consciousness weeds out the quantum potentiality for a
cheese moon.
So putting the insights of Stapp, Zurek and Wheeler together we arrive more or less at precisely
the metaphysical perspective which lies at the heart of the Hawking-Mlodinow view: the quantum ‘dream stuff’ of potentiality contains all possibilities and it is, ultimately, consciousness
that unfolds the world of experience which makes up the universe. This perspective obviously
requires that consciousness in some form, a form not restricted to individuated consciousness
but a primordial or collective form which constitutes the ground of individuated consciousness,
must be an inherent and integral aspect of the fundamental quantum ground. So how can Dennett get away with claiming with utterly mistaken conviction, and in direct contradiction of the
hard won insights of modern science, that “there is only one sort of stuff, namely matter – the
physical stuff of physics…” Why isn’t he laughed out of the academic profession and asked to
resign his ill-gotten professorship to make way for someone who knows what he or she is talking about. It is a great mystery.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
722
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
Dennett is one of the masters of materialist madness, but there are plenty of academic pundits
banging the mournful materialist drum in various outdated rhythms. In the series of essays
which will be published in this and forthcoming issues I intend to investigate the work of people
such as Dennett, Jerry Coyne, Richard Dawkins, Susan Blackmore, Vilayanur Ramachandran,
Antonio Damasio, Patricia and Paul Churchland, Nicholas Humphrey and David Papineau, and
perhaps a few others, all of whom propose, in various degrees of implicitness or explicitness,
that consciousness ‘evolved’ out of an absolute blankness of a pure material substratum because
of some kind of evolutionary necessity. From this perspective the materialist fundamental fairy
story is that at some point in the fairy tale account of a purely materialist evolutionary process
‘matter’ finds that it is not up to the task of keeping the process a going concern. Some aspect of
the process becomes too complex and therefore the purely material processes of reality have to
somehow manufacture some new kind of medium, a medium which, although still in its ultimate nature thoroughly material, is in its appearance and functioning utterly different, different
in fact to the point of having completely immaterial capacities. Put in such terms, of course, the
claim appears seems absurd. And, indeed, it is absurd, absurd to the point of being laughable.
In his book Soul Dust for example Nicholas Humphrey argues that consciousness emerges due
to the necessity of having a more complex medium in order to manage social demands, he
seems oblivious to the fact that organisms who are devoid of conscious awareness, as Humphrey conceives of his putative pre-social primitive beings, would not have the kind of ‘social’
requirements that we, as beings endowed with consciousness, have. As the philosopher Mary
Midgley wrote in a review of this book:
Humphrey’s approach to this topic was, however, always slightly odd. He used these social needs to explain not just why consciousness has gone on developing but why it
arose originally. Yet how could social needs – which don't seem to bother plants – ever
have troubled creatures that were not conscious already? Humphrey's strange assumption that they could still do so haunts this book, in which he claims to have finally solved
the “hard problem of consciousness” – the question of how our subjective life can exist
at all in a world of matter that is supposedly fully described by the physical sciences.29
Here Midgely implicitly puts her finger on one of the self-deceptive mechanism which underpins
materialist diatribes. The use of the term ‘social’, a term most generally applied in the context of
organisms which have some form of consciousness, is applied to what should be, according to
Humphrey’s own argument, completely blank zombie-type creatures. Humphrey’s first use of the
term ‘social’ is in the mode of the way in which ants may be termed ‘social’ because they exist
within interdependent but unconsciously mechanistic colonies (not because they are fully consciousness beings who like giving dinner parties):
It appears that ants were the first, and remain the only, social insect predators to utilize
the moist, dark dirt and rotting vegetation for nesting.30
However, the term ‘social’ when employed outside of such contexts does carry an implicit implication of the presence of consciousness, and Humphrey employs this implication to perform an
intellectual sleight of mind. The presence of consciousness is illicitly introduced within the argument prior to its claimed emergence, an emergence which is supposedly because of the necesISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
723
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
sities and exigencies of ‘social’ life. Unwary readers, often with a predisposition to accept materialist explanations, will generally fail to notice the sleight of mind generated by terminology. In
the context of the complex social structure of ant colonies, if Humphrey’s notion were to be correct then it would be truly amazing that ants has not evolved full-blown consciousness!
Tallis discusses this common materialist ploy in a chapter of his book Aping Mankind in a chapter entitled ‘Bewitched by Language’, a homage to Ludwig Wittgenstein who wrote:
A picture held us captive. And we could not get outside of it, for it lay in our language
and language seemed to repeat it to us inexorably.31
Tallis writes that:
Neuromania demands of its adepts that they should ascribe human characteristics to
physical processes taking place in the brain. This depends on a cavalier way with words
that is now so universal as to have become almost invisible, making it quite difficult to
see the unbridgeable gap between what happens in the brain and what people do. It illustrates the force of Wittgenstein’s observation…32
In a quantum age, however, the captivating force of crude and childish materialism should surely
have lessened somewhat. In fact Tallis does not even consider quantum evidence but examines
some of the absurd claims made by materialists on philosophical grounds and concludes that:
“the neuro-evolutionary approach to human consciousness and human life is wrong, and obviously so.”33 The respected quantum physicist Anton Zeilinger, a physicist who has carried out
some of the most precise and subtle quantum experiments currently possible, has written in appreciation of physicist John Wheeler’s work of Wheeler’s:
…realisation that the implications of quantum physics are so far-reaching that they require a completely novel approach in our view of reality and in the way we see our role
in the universe. This distinguishes him from many others who in one way or another
tried to save pre-quantum viewpoints, particularly the obviously wrong notion of a reality independent of us.34
A viewpoint derived from the evidence of quantum theory which, once again, confirms the insights of Hawking and Mlodinow, Stapp, Zurek, and others that consciousness is an inherent aspect of the quantum realm and the material world is derivative, dependent upon the ‘epiontic’
perceptions of sentient beings. And yet a debate still rages. Furthermore, the battle-lines of the
intellectual war are generally drawn at extreme positions.
Materialists cling to the conviction that ‘matter’ is ultimate constituent of the process of reality,
as when Dennett asserts that a “mindless little scrap of molecular machinery” is the basis for the
development of mind. In her review of Humphrey’s Soul Dust Mary Midgley suggests that a new
understanding of the physical world, wherein matter has lost its appearance of traditional and
‘classical’ solidity and antipathy to mind-qualities, can account for the emergence of mind and
consciousness:
Matter is still often imagined, in 17th-century style, as an inert, passive stuff moved only
by impact from outside. Since this view was deliberately designed by devout scientists
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
724
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
to leave space for God as the source of all activity, it rather naturally becomes unworkable once that somewhat assertive God has been removed. Inert stuff could never have
produced the crystals, the galaxies, the volcanoes and, above all, the living things that
have evolved out of our original dollop of physical matter. And after those amazing
achievements, why should it seem surprising for matter to have topped things up by adding consciousness? We need somehow to admit that matter has proved creative enough
to do all these things. And since physicists no longer rule that matter is inert, that ought
not now to be too difficult. Till this point is clear, the “hard” problem remains insoluble.35
The “hard” problem, of course, was posited by David Chalmers as the insuperable problem of
how a material world conceived of as being entirely devoid of mind qualities could possibly produce those qualities. Midgley is suggesting that perhaps we should conceive of matter itself as
not being entirely mindless, in contrast to the mindlessness of the Dennettian viewpoint. Such a
view clearly moves towards an understanding which considers the ultimate ‘stuff’ of the process
of reality as a kind of energetic ‘field’ with mind-like qualities. Which is, more or less, Stapp’s
perspective, amongst others such as the Russian physicist Michael Mensky. But this is not the
‘matter’ beloved by hardened and hard-headed materialists, who like their matter ‘neat’, with no
added mind. As Jerry Coyne tells us:
Naturalism is the view that the only way to understand our universe is through the scientific method. Materialism is the idea that the only reality is the physical matter of the
universe, and that everything else, including thoughts, will and emotions, comes from
physical laws acting on that matter. The message of evolution, and of all science, is one
of naturalistic materialism.36
There are few academics more hard-headed than Coyne, and this hard-headedness includes the
divisions between various brain compartments which seem not to interact in any meaningful way.
If naturalism denotes the scientific method and the scientific method embodied in physics has
shown us incontrovertibly that the ultimate stuff or the process of reality are immaterial quantum
fields then naturalistic materialism is oxymoronic, although it is proclaimed by all proponents of
the materialist ultra-Darwinist (MUD) worldview.
It is this kind of hardened materialism which underpins what Tallis refers to as Neuromania and
Darwinitus, the former being the assertion that mind and consciousness are entirely reducible to
movements of matter and the latter the notion that life, organisms and sentience evolved according to a materialist account of Darwinism, the ‘ultra-Darwinism’ of the ‘modern synthesis’. It is
the latter viewpoint which is deployed against the attempted encroachments of the ID perspective
into the scientific fold. In its war against such encroachments, materialist ultra-Darwinism has no
compunction against playing slightly dirty, it just about always presents ID as a thinly veiled
front for a thoroughly nasty Christian theistic fundamentalism. Thus in a recent book of essays
devoted to attacking and undermining the ID perspective, entitled Intelligent Thought: Science
verses the Intelligent Design Movement, the editor John Brockman writes in his introduction that:
…religious fundamentalism is on the rise around the world, and our own virulent domestic version of it, under the rubric of “intelligent design,” by elbowing its way into the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
725
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
classroom abrogates the divide between church and state that has served this country so
well for so long. Moreover, the intelligent-design (ID) movement imperils American
global dominance in science and in so doing presents the gravest of threats to the American economy, which is driven by advances in science and in the technology derived
therefrom. This book-sixteen essays by leading scientists from several disciplines-is a
thoughtful response to the bizarre claims made by the ID movement's advocates, whose
only interest in science appears to be to replace it with beliefs consistent with those of
the Middle Ages. School districts across the country-most notably in Kansas and later in
Pennsylvania, where the anti-evolutionist tide was turned but undoubtedly not stoppedhave been besieged by demands to “teach the debate” to “present the controversy,”
when, in actuality, there is no debate, no controversy. What there is, quite simply, is a
duplicitous public-relations campaign funded by Christian fundamentalist interests.37
The claims here are quite dramatic, the ID movement “imperils” American global scientific
dominance and its economy, the claims made by the ID movement are said to be “bizarre” and
tantamount to the beliefs of the Middle Ages and so on.
Fighting talk indeed! But if one bothers to pursue the issue by reviewing the evidence with honesty, clarity and precision one can only conclude that, even if it were correct to identify ID with
fundamentalist religion (which it isn’t – although as we shall see the presentation of the case for
ID often leaves a great deal to be desired in this context), the same can certainly be said of the
MUD case. Is it not “bizarre” to proclaim the primacy of matter when it is clearly known that
the ultimate constituents of the process of reality are insubstantial and immaterial quantum
fields? As Stapp has indicated: “proclaiming the validity of materialism on the basis of an inapplicable-in-this-context nineteenth century science is an irrational act.”38 So, whereas the MUD
offensive on the ID perspective exaggeratedly claims that ID is a modern form of Middle Age
beliefs, it is quite clear that the MUD worldview is certainly stuck in pre-quantum nineteenth
century ‘classical’ beliefs.
Proponents of MUD (read ‘Materialist Ultra-Darwinism’ or ‘Materialist Ultra-Darwinist’ as the
context requires) and opponents of ID regularly assert that ID is virtually identical to rabid theistic fundamentalism and Creationism, which is generally thought of as the notion that an independent self-contained divine being fashioned the universe in a miraculous way. The prominent
proponent of ID Stephen C. Meyer, however, in his article ‘Intelligent Design Is Not Creationism’ argues that this is not the case:
ID is not based on religion, but on scientific discoveries and our experience of cause and
effect, the basis of all scientific reasoning about the past. Unlike creationism, ID is an inference from biological data. Even so, ID may provide support for theistic belief. But
that is not grounds for dismissing it. Those who do confuse the evidence for the theory
with its possible implications. Many astrophysicists initially rejected the Big Bang theory because it seemed to point to the need for a transcendent cause of matter, space and
time. But science eventually accepted it because the evidence strongly supported it. Today, a similar prejudice confronts ID. Nevertheless, this new theory must also be evaluated on the basis of the evidence, not philosophical preferences.39
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
726
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
And, indeed, this is clearly the case. It does not follow from the mere assertion that there is some
kind of intelligence operating within the process of reality, including those processes driving evolution, does not necessarily force us to conclude the existence of a divine creator. It merely asserts what it asserts, which is that there is a kind of inherent intelligence within the processes of
reality. Any theistic conclusions clearly go beyond this bare conclusion, a conclusion fully in accord with the quantum evidence, which is that at the point of the Big Bang there is a quantum
field of potentiality which has an internal energetic intelligence which unfolds those potentialities
into manifestation, an assertion fully in accord with the quantum perspectives outlined previously. The reason that there is no “need for a transcendent cause of matter, space and time” is that
the scientific evidence now clearly indicates:
1. The ultimate stuff of the process/processes of reality is immaterial quantum field stuff, or
as Zurek terms this “quantum dream stuff.”
2. There is an internal intelligence which is inherent and innate within the processes which
unfold the potentialities within the quantum fields of reality.
3. Consciousness and awareness, in some kind of universal non-individuated form, must also
be an innate aspect of quantum fields, if this were not the H&M and other quantum scenarios we have overviewed above could not be correct and, furthermore, sentient beings
could not be sentient.
The term ‘transcendent’, however, has an application to emphasize that the ultimate stuff of reality ‘transcends’ the material stuff that materialists worship!
The first of the above points has been established previously, the next two points will be elucidated shortly. Before doing so it is necessary to make the point that, although it is clear that ID
does not necessarily lead to Christianity or Theism, much ID discourse is couched in a form
which does imply a theistic direction. In his significant and otherwise excellent book Signature
in the Cell:
…since the intelligent design hypothesis meets both the causal-adequacy and causalexistence criteria of a best explanation, and since no other competing explanation meets
these conditions as well - or at all since the intelligent design hypothesis meets both the
causal-adequacy and causal-existence criteria of a best explanation, and since no other
competing explanation meets these conditions as well-or at all it follows that the design
hypothesis provides the best, most causally adequate explanation of the origin of the information necessary to produce the first life on earth. Indeed, our uniform experience affirms that specified information-whether inscribed in hieroglyphics, written in a book,
encoded in a radio signal, or produced in a simulation experiment - always arises from
an intelligent source, from a mind and not a strictly material process. So the discovery of
the specified digital information in the DNA molecule provides strong ground, for inferring that intelligence played a role in the origin of DNA. Indeed, whenever we find specified information and we know the causal story of how that information arose, we always find that it arose from an intelligent source. It follows that the best, most causally
adequate explanation for the origin of the specified, digitally encoded information in
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
727
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
DNA is that it too had an intelligent source. Intelligent design best explains the DNA
enigma.40
Whilst this conclusion is not overtly supportive of a theistic interpretation, terminology such as
“arises … from a mind” and “had an intelligent source” can give the appearance of moving in a
theistic direction, especially to a MUD mind predisposed to identify ID with Creationism. In his
book Intelligent Design: The Bridge Between Science & Theology, William A. Dembski, as his
title indicates, argues that ID is a bridge between science and Christian Theistic Theology. In this
book Dembski makes some startling statements:
My thesis is that all disciplines find their completion in Christ and cannot be properly
understood apart from Christ.41
And the following quotes from Dembski are cited by Coyne at the head of his essay ‘Intelligent
Design: The Faith That Date Not Speak Its Name’ in the anti-ID Intelligent Thought collection:
Intelligent design is not an evangelic Christian thing, or generally Christian thing or
even a generically theistic thing. . . .Intelligent design is an emerging scientific research
program. Design theorists attempt to demonstrate its merits fair and square in the scientific world-without appealing to religious authority.
And:
[A]ny view of the sciences that leaves Christ out of the picture must be seen as fundamentally deficient. . . . [T]he conceptual soundness of a scientific theory cannot be maintained apart from Christ.
The first is from The Design Revolution which was published in 2004 and the second from the
earlier work Intelligent Design: The Bridge Between Science & Theology written in 1999. It
seems that in the space of five years Dembski has either modified his views remarkably or has
decided to modify the presentation of his views. And it is this ambiguity which allows ultramaterialists like Coyne to mount attacks which cover over the massive implausibility in their
own materialist positions:
Well, which is it? Is intelligent design (ID) merely a sophisticated form of biblical creationism, as most biologists claim, or is it a science – an alternative to Darwinism that deserves discussion in the science classroom? As the two quotations above imply, you
won’t find the answers in the writings of the leading advocates of ID. The ambiguity is
deliberate, for ID is a theory that must appeal to two distinct constituencies. To the secular public ID proponents present their theory as pure science. This, after all, is their justification for a slick public-relations campaign promoting the teaching of ID in the public
schools. But as is clear from the infamous “Wedge Document” of the Discovery Institute, a right-wing think tank in Seattle and the center for ID propaganda, intelligent design is part of a cunning effort to dethrone materialism from society and science and replace it with theism. ID is simply biblical creationism updated and disguised to sneak
evangelical Christianity past the First Amendment and open the classroom door to Jesus.42
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
728
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
And if one consults the “infamous ‘Wedge Document’” one finds that Coyne does have a sort of
point. As he indicates in a footnote this document states that:
The social consequences of materialism have been devastating. As symptoms, those
consequences are certainly worth treating. However, we are convinced that in order to
defeat materialism, we must cut it off at its source. That source is scientific materialism.
This is precisely our strategy. If we view the predominant materialistic science as a giant
tree, our strategy is intended to function as a ‘wedge’ that, while relatively small, can
split the trunk when applied at its weakest points . . . Design theory promises to reverse
the stifling dominance of the materialistic worldview, and to replace it with a science
consonant with Christian and theistic convictions.43
So it is clear that the ID movement as it is embodied in the aims and activities of The Discovery
Institute is “consonant” with a theistic worldview. Coyne, however, distorts this situation. The
fact that ID is consonant with a theistic worldview does not mean that is identical to fundamentalist theistic faith, it is entirely possible to hold an ID position which is entirely separate from
theistic conclusions.
In this context it is intriguing to note that Stapp has clearly made some statements that support the
theistic ID perspective. Referring to the implications of quantum theory he has written:
This situation is concordant with the idea of a powerful God that creates the universe
and its laws to get things started, but then bequeaths part of this power to beings created in his own image, at least with regard to their power to make physically efficacious decisions on the basis of reasons and evaluations.44
However, if we leave the theistic trappings out of the picture, the central issue becomes that of
whether there are intelligent and mind-like aspects that are inherent to the fundamental processes
of reality or, as the materialist worldview maintains, whether the fundamental processes of reality
are, as Dennett puts it, “robotic” and “mindless”. To put this another way, does it make sense to
assert, and does the scientific evidence available to us suggest, that a completely blank, mindless,
unintelligent fundamental materially based process give rise to the world of awareness, meaning
and intelligence?
It is clear that the main concern of the ID movement as outlined in the “Wedge Document” is the
dismantling of the worldview of ‘scientific materialism’, a worldview that asserts the “known-tobe-false” claim that the primary and ultimate ‘stuff’ of reality is matter. Stapp, alongside a good
few other physicists such as Erwin Schrodinger, Max Planck, Werner Heisenberg, David Bohm,
Roger Penrose, Andre Linde, Wojceich Zurek, Anton Zeilinger, has indicated the idealike nature
of the quantum ‘stuff’ of reality:
The evolving quantum state, although controlled in part by mathematical laws that are
direct analogs of the laws that in classical physics govern the motion of ‘matter’, no
longer represents anything substantive. Instead, the evolving quantum state would represent the ‘potentialities’ and ‘probabilities’ for actual events. Thus the ‘primal stuff’
represented by the evolving quantum state would be idealike in character rather than
matterlike … quantum theory provides a detailed and explicit example of how an
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
729
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
idealike primal stuff can be controlled in part by mathematical rules based in
spacetime.45
On this view, as indicated by the H&M quantum metaphysical account, all possible futures, including the various species of plant and animal, must be potential in some way within the ‘implicate order’ of the potentialities of idea-like quantum ‘dream-stuff.’ As Adrian Woolfson, in his
book Life Without Genes, tells us:
In the beginning there was mathematical possibility. At the very inception of the universe fifteen billion years ago, a deep infinite-dimensional sea emerged from nothingness. Its colourless waters, green and turquoise blue, glistened in the non-existent light
of the non-existent sun … A strange sea though, this information sea. Strange because
it was devoid of location …46
At the dawn of time there ‘existed’ the quantum fields of potentiality. Although there was not a
fully manifested and experienced reality there was, according to this picture, ‘mathematical possibilities’. This is the wave-function of the universe, a universal wave-function which contains:
…all possible histories … through which the universe could have evolved to its present
state…47
In the beginning, of course, the wave-function of the universe would contain all the future evolutionary possibilities:
The information sea is thus a quantum mechanical sea, composed from infinite repertoires of entangled quantum descriptions.48
And within this all-encompassing wave-function all possibilities for evolutionary manifestation
are encoded. From out of the vast entangled web of infinite possibilities for manifestation only
certain privileged members will actually make it into reality, so to speak:
An information space of this sort would furnish a complete description of all potentially
living and unrealizable creatures…49
It therefore follows that there is a sort of design woven into the potentialities for evolution; it is a
vast complex design of all possible manifestations written into the wave-function of the universe.
In the H&M account, amongst other quantum metaphysical formulations, it is the observational
actions of collective consciousness which determines which of the potential species unfold from
potentiality into manifestation.
This quantum Platonic metaphysical account, wherein all possible forms of life are potential in a
quantum idealike realm of potentiality tallies precisely with the recent discoveries of Evolutionary Development Biology, or Evo-Devo, wherein it has been discovered that the fundamental
gene structure underlying all organisms pre-dates the actual evolution of those organisms. As the
Evo-Devo enthusiast Sean B. Carroll tells us:
The surprising message from Evo Devo is that all of the genes for building large, complex animal bodies long predated the appearance of those bodies in the Cambrian Explo-
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
730
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
sion. The genetic potential was in place for at least 50 million years. And probably a fair
bit longer before large, complex forms emerged.50
If the “genetic potential was in place” prior to the emergence of bodies, exactly in what place was
it in place? Certainly not in the bodies of the yet to emerge animals, precisely because they had
not yet emerged. The most obvious place wherein this genetic potential could have been “in
place” is the realm of quantum idealike potentiality. After all, the most obvious place for a potentiality to be in place is a place of potentiality.
Furthermore, this view precisely fits the quantum evidence we have surveyed. MUD enthusiasts,
however, resiliently ignore the quantum evidence and proceed as if the material world were not
ultimately quantum but more or less classically behaved (see the article on Jerry Coyne – Why
Evolution is False). When dealing with the emergence of life and consciousness, however, such
an assumption is unjustified. For as H&M say “we are the product of quantum fluctuations in the
very early universe.” Quantum processes, then, must be significant in the process of the evolution
and development of sentient organisms.
In a section titled “Did Natural Selection Generate Consciousness”, in his book Aping Mankind,
Raymond Tallis writes:
…evolutionary theory, although largely unaware of it, has a problem with consciousness
of any sort. First, it has to begin with matter and somehow end up with mind. Second, it
has to demonstrate that having a conscious mind would be something a replicator would
be glad of, as a means of assisting its own senseless task of replication. … Darwinism
cannot give a satisfactory answer to either of these two questions: how did consciousness emerge; and what is consciousness for anyway? … Was it the blind laws of physics
that so organised matter that it came up with creature like us, that could see the laws of
physics and that they were blind. … We need to ask (a) by what means consciousness
could have come into being, if it was not there in the beginning, and (b) what advantages
it confers.51
In a sense investigating these issues philosophically is otiose because the quantum evidence indicates that consciousness must have been “there in the beginning” and matter certainly was not.
However, it is perhaps worth putting some philosophical nails in the coffin of materialism. As to
the issue (a) Tallis observes that:
…how is it that certain configurations of matter should be aware, should suffer, fear, enjoy and so on? There is nothing in the properties of matter that would lead you to expect
that eventually certain configurations of it … would pool that experience and live in a
public world. No wonder many materialistically inclined philosophers like to deny the
real existence of consciousness.52
The very definition of matter excludes the quality or even the potentiality of consciousness in the
type of ontological (actually non-existent) stuff cherished by materialists. As a result materialist
apologists have to dream up spurious notions, given fancy labels, in order to hoodwink their audience.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
731
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
The neurobiologist Roger W. Sperry, for instance, claims that ‘mental properties in brain activity
… supervene.’53 The spurious technical notion of ‘supervenience’ is a convenient and useful
sleight of mind for the sophisticated materialist; it is an example of the tactic of an appeal to imagined and fictional constructions of, on the face of it, plausible (but not very) apparently ‘logical’ configurations which are supposed to validate an ontological causal chain, in this case from
mindless matter to mindful consciousness. The original statement of the ‘supervenience’ claim
was made by Donald Davidson who introduced the term into contemporary philosophy of mind
in the following passage:
Mental characteristics are in some sense dependent, or supervenient, on physical
characteristics. Such supervenience might be taken to mean that there cannot be two
events alike in all physical respects but differing in some mental respect, or that an
object cannot alter in some mental respect without altering in some physical respect.
54
In other words Davidson thought that conjuring up fancy, yet meaningless, words was a useful
and valid way of elucidating the metaphysical structure of reality. According to Sperry:
[Conscious properties] encompass and transcend the details of nerve impulse traffic in
the cerebral networks in the same way that … the properties of the molecule transcend
the properties of atomic components…55
Another version of this viewpoint sometimes advanced is that the properties of water, for example, ‘supervene’ or ‘transcend’ the molecular structure of H2O.
Such supervenience views, however, do not hold water as arguments for the notion that consciousness magically ‘supervenes’ upon brain structure. Stapp explains this by referring to Sperry’s example of how ‘wheelness’ ‘emerges’ or ‘supervenes’ from the atomic components of the
physical stuff of the wheel. Stapp explains that:
The reason that consciousness is not analogous to wheelness … is that the properties
that characterize wheelness are entailed … by properties specified in classical physics,
whereas the properties that characterize consciousness … are not entailed … by the
properties specified by classical physics.56
Stapp is indicating that the conceptual move to the properties which are embodied within
‘wheelness’ are coherently entailed within the conceptual framework of the classical physics of
materiality in a manner that the properties of consciousness are not:
This is a huge difference-in-principle that distinguishes consciousness from things that,
according to the precepts of classical physics, are constructible out of the particles that
are postulated to exist by classical physics.57
The way in which the material particles within the construction a wheel function as the wheel
rotates quite naturally contribute to the overall functioning of the wheel in a manner that requires
no discontinuous conceptual break. The properties of a wheel naturally emerge from the properties of materiality in a way that the properties of consciousness do not. In other words there is a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
732
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
coherent explanatory chain of connection between the properties of the material wheel and the
atomic (conceived classically as Sperry does) constituents of the wheel.
The same applies to the supposed ‘supervenience’ of wetness over and above the molecular
makeup of water. We find that the property of ‘wetness’ is coherently entailed by the nature of
the intermolecular forces between particles which are stronger than the kinetic energies of the
molecules, which are thus held close together. But, on the other hand these forces do not hold the
molecules in a rigid structure and hence the molecules can move around whilst being constrained
to be close together. This explains the nature of the liquid state. Furthermore, when we consult
an online chemistry exposition we find that:
Water has long been known to exhibit many physical properties that distinguish it from
other small molecules of comparable mass. Chemists refer to these as the “anomalous”
properties of water, but they are by no means mysterious; all are entirely predictable
consequences of the way the size and nuclear charge of the oxygen atom conspire to
distort the electronic charge clouds of the atoms of other elements when these are
chemically bonded to the oxygen.58
So even the more apparently ‘mysterious’ properties of water, being less dense in the solid form
of ice for example, are “entirely predictable” from the molecular structure.
In both the ‘wheelness’ and the ‘wetness’ examples there is a clearly coherent conceptual chain
of entailment from the basis to the property which is supposed to magically ‘supervene.’ In the
case of consciousness, however, there is an unbridgeable gap which no sophisticated and sophistic juggling of spurious logical concoctions could ever bridge. As Tallis says:
There is nothing … that will explain why matter should “go mental” once it assumes a
certain form, unless we anticipate and borrow, on account as it were, the very notion of
an organism that is aware of its environment.59
The italics are Tallis’ and the highlighted section describes the general procedure by which materialists try to produce an illusion of consciousness emerging from mindless matter by smuggling
it in at the outset, like Humphrey. Such materialist ‘philosophers’ often then proclaim that consciousness is an illusion, not realizing that the illusion is all their own.
An excellent example of the kind of sleight of mind routinely resorted to within this materialist
discourse is supplied by Antonio Damasio, David Dornsife Professor of Neuroscience at the
University of Southern California, with his account of the genesis of consciousness which he
presents in his book The Feeling of What Happens:
I propose that we become conscious when the organism’s representation devices exhibit a kind of wordless knowledge – the knowledge that the organisms own state has
been changed by an object – and when such knowledge occurs along with the salient
representation of the object.60
In this case there is an attempt to convince the reader of the reality of the illusion of some kind of
inner necessity for the arising of inner awareness, i.e. the direct experience of consciousness,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
733
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
from the merely mechanical representational activities of the material organism. Damasio seems
blissfully unaware that an as yet non-sentient organism is not capable of having ‘knowledge’,
“wordless” or otherwise. But by using this term in two senses, without clarifying the different
senses, he introduces consciousness by the back door, implying with the use of the term
“knowledge” that it has already arrived.
As to Tallis’ second issue of the biological advantages conferred by consciousness he points out
that there is absolutely no reason to suggest that unconscious processes would not function equally well if all that was at stake was mindless survival:
Think, after all, what unconscious mechanisms have actually achieved: the evolution of
the material universe; the processes that are supposed to have created life and conscious
organisms; the growth, development of most of the running of even highly conscious organisms such as ourselves. If you had to undertake something really difficult – for example growing in utero a brain with all its connections in place – consciousness is the
last thing you would want to oversee the task.61
All of the accounts of why consciousness is useful for a materialist evolutionary process are desperately implausible. They have to be because all of the most recent evidence from quantum theory and various developments in neurophysiology such as the discovery of neuroplasticity indicate that consciousness is primary, not derivative. In the forthcoming essays I hope to bring out
the absurd and laughable nature of the kind of claims being made by people who consider themselves serious academics and philosophers. I intend to try and make readers gasp and laugh at the
absurdities which pass muster in today’s absurd academic climate wherein logic and logical coherence, not to mention conformity to the scientific evidence, been side-lined in the cause of a
materialist advertising campaign.
In his book Signature in the Cell Meyer discusses various attempts to simulate MUD evolution
with computer programs. Dawkins proposed his ‘weasel program’ as a demonstration of Darwinian natural selection. In this simulation the computer program begins with a random sequence of
letters and then implements a sequence of iterations, each iteration produces a set of ‘random
mutations’ of the letter sequence and each set is compared to the target sequence “Methinks it is
like a weasel” and the best fits are ‘selected’. But what Dawkins conveniently overlooked in this
simplistic simulation was the obvious fact that his program contains a look-ahead-mechanism
that natural selection is not supposed to have. Other more sophisticated attempts at producing
programs to simulate Darwinian evolution but all suffer this flaw, they all in some sense know
where they are going so they do not simulate a “blind” process. An expert Microsoft programmer
said to Meyer concerning such programs:
There is absolutely nothing surprising about the results of these algorithms. The computer is programmed from the outset to converge on the solution. The programmer designed
the code to do that. What would be surprising if the program didn’t converge on the solution.62
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
734
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
Any competent programmer knows this, the only way that any such program can converge on a
target is if somewhere in the code there is some kind of comparison with the target, there must be
some kind of look-ahead-mechanism. Meyer says of this:
As philosopher and mathematician David Berlinski has argued, genetic algorithms need
something akin to a “forward-looking memory” to succeed. Yet foresighted selection
has no analogue in nature.63
But Meyer is mistaken about this, for nature does have such a foresighted selection mechanism
operating at the quantum level:
By hitting single molecules with quadrillionth-of-a-second laser pulses, scientists have
revealed the quantum physics underlying photosynthesis, the process used by plants
and bacteria to capture light’s energy at efficiencies unapproached by human engineers. The quantum wizardry appears to occur in each of a photosynthetic cell’s millions of antenna proteins. These route energy from electrons spinning in photonsensitive molecules to nearby reaction-center proteins, which convert it to cell-driving
charges. Almost no energy is lost in between. That’s because it exists in multiple places at once, and always finds the shortest path. “The analogy I like is if you have three
ways of driving home through rush hour traffic. On any given day, you take only one.
You don’t know if the other routes would be quicker or slower. But in quantum mechanics, you can take all three of these routes simultaneously. You don’t specify where
you are until you arrive, so you always choose the quickest route,” said Greg Scholes, a
University of Toronto biophysicist. Scholes’ findings, published … in Nature, are the
strongest evidence yet for coherence — the technical name for multiple-state existence
— in photosynthesis.64
The phenomenon of photosynthesis exploits a quantum look-ahead strategy in which, in the
same way as the universe started out “in every possible way”, the route of electronic energy
transfer within photosynthesis operates by using quantum coherence to test out all possible
routes simultaneously and then selects the most efficient route retrospectively. This is a quantum look-ahead mechanism which operates within one of the fundamental processes of life.
Physicist and Director of the BEYOND Center Paul Davies has suggested that this quantum look
ahead mechanism underlies the ‘emergence’ of life:
The hypothesis I am proposing is that the transition from non-life to life was a quantum-mediated process, and that the earliest form of life involved non-trivial quantum
mechanical aspects. The power of quantum superpositions is that the system can explore many alternative pathways simultaneously, thereby potentially shortcutting the
transition time by a large factor. Because life is a highly unusual state of matter, its
formation from an arbitrary initial state is presumably extremely improbable. Quantum
mechanics provides a way to drastically shorten the odds and fast-track matter to life
by exploiting the parallel processing properties of superpositions. There is, however, a
deep philosophical issue that must be confronted. I am defining “life” as a certain special state of low probability. Quantum mechanics enables the space of possibilities to
be much more efficiently explored than a stochastic classical system. Now, if there are
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
735
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
branches of the wave function “containing life” (e.g. a quantum replicator), they will,
by assumption, have very small amplitudes. We must therefore explain why the wave
function of the system “collapses” onto one of these states of such 1ow intrinsic probability. Expressed differently, how does a quantum superposition recognize that it has
“discovered” life and initiate the said collapse? There seems to be an unavoidable teleological component involved: the system somehow “selects” life from the vastly greater number of states that are nonliving.65
Quantum evolutionist Johnjoe McFadden has suggested that a similar mechanism underlies the
mutations of DNA, the molecular string which contains genetic coding. Such mutations, which
were previously thought to be purely due to chance, are more likely to be quantum mechanical in
origin:
Quantum mechanics tells us that the protons in DNA that form the basis of DNA coding are not specifically in localised positions but must be smeared out along the double
helix. … At the quantum mechanical level, DNA must exist in a superposition of mutational states. If these particles can enter quantum states then DNA may be able to slip
into the quantum multiverse and sample multiple mutations simultaneously. 66
Such a quantum mechanism supplies the means for a subtle teleology, or direction, towards the
evolution of perceiving organisms to operate. Thus it appears that there is a teleology to unfold
life operating within the quantum realm.
In the following observation it is clear that Davies is moving his perspective in the direction of a
quantum teleological viewpoint:
If life is not written into the laws of physics as we currently know them, is it possible
that those laws can be augmented by some organizing principle which facilitates the
emergence of biological complexity, fast tracking matter and energy along the road to
life against the raw odds, and driving it to ever more complex forms. Such a principle
has been suggested many times, but always in the face of fierce opposition from orthodox science. And the reason for the negative reaction is not hard to identify. Any sort of
life principle or cosmic imperative reintroduces into science the dreaded t-word: teleology. 67
The distaste for the “t-word” on the part of scientists is not a result of any experimental findings
within science itself, it is, rather, a prejudice for a materialist metaphysical worldview. It seems
that the notion that the universe might have a spiritual purpose strikes terror into the hearts of
many scientists! For Davies and others, however, the evidence is overcoming the anti-spiritual
materialist prejudice.
This unfolding quantum teleological perspective suggests that that there is an inner teleological
‘pressure’ operating within the quantum realm of potentiality which functions in order to manifest the potentialities into experienced ‘realities’. According to the Russian quantum physicist
Michael Mensky, the quantum realm has within it a ‘Life-Operator’ which acts within the quantum realm of potentiality in order to unfold life. There is a directed teleology which underlies the
phenomenon of life which Mensky has elucidated in his Extended Everett Concept (EEC). In this
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
736
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
proposal Mensky suggests that living organisms are able to employ, mostly unconsciously, the
quantum look-ahead mechanism to explore the quantum alternatives lying in the future in order
to ‘select’ advantageous pathways:
According to the EEC, the principle feature of consciousness (of human and, more generally, of any living being) is its ability, overcoming the separation of the alternatives, to
follow each of them up to the distant time moment in the future, find what alternatives
provide survival and choose these alternatives excluding the rest. The evolution of living
matter is thus determined not only by causes, but also by the goals, first of all by the
goals of survival and improvement of the quality of life.68
‘Life’ is a quantum phenomenon which develops out of a quantum ‘Life-Operator’ which supplies the pressure to drive the quantum process in the direction of the survival of quantum systems which embody ever greater qualitative expressions of awareness and consciousness. It is the
operation of the intrinsic Life-Operator upon the nonlocal interconnected quantum field of potentiality which carves out a vast phantasmagoria of sentient life embodying individuated consciousness on a multitude of levels of qualitative expression. But this carving out of individualized consciousness does not break individuated consciousness entirely free of the collective levels of consciousness:
In the framework of Extended Everett’s Concept the (explicit) consciousness is identified with the separation of alternatives. In the transition to the regime of the unconscious
(“at the edge of (explicit) consciousness”) the separation of alternatives disappears, and
the possibility arises to compare all alternatives between each other, select favorable
ones and discard the rest. … Therefore “to stay in the sphere of life” means that only favorable (for life) alternatives are left in the picture appearing before consciousness…69
Mensky indicates that the kind of quantum look-ahead mechanism exhibited by photosynthesis is
fundamental to process of life in general and operates through the deeper realm of quantum
awareness-consciousness, levels which are usually considered ‘unconscious’. In his paper Postcorrection and the mathematical model in Extended Everett’s Concept he presents a mathematical model of the mechanism by which the quantum-consciousness ‘look-ahead’ technique may be
formalized, a mechanism which he calls ‘postcorrection’:
In the present paper we shall introduce the mathematical formalism describing this principal feature of living matter (of its consciousness): the ability to correct its state making
use of the information (about the efficient way of survival) obtained from the future. It
will be assumed that the evolution of living matter includes the correction providing
survival at distant time moments. This correction leaves in the sphere of life only those
scenarios of evolution which are favorable for life. Unfavorable scenarios do not disappear from the (quantum) reality but are left outside the sphere of life (absent in the picture appearing in the consciousness).70
From this perspective, at the moment of the Big Bang the ‘Life-Operator’ was somehow triggered into action and began the process of unfolding the potentialities by exploring future pathways. As Davies suggests in his book The Goldilocks Enigma:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
737
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
…a good case can be made that life and mind are fundamental physical phenomena,
and so must be incorporated into the overall cosmic scheme. One possible line of evidence for the central role of mind comes from the way in which an act of observation
enters into quantum mechanics. It turns out that the observation process conceals a
subtle form of teleology.71
This is because it has now been clearly shown that sentient observation involving consciousness
is ‘epiontically’ entangled within the quantum level and is required for quantum potentialities to
become experienced ‘realities’. The physicist and philosopher Bernard d’Espagnat has indicated
this in no uncertain terms:
The doctrine that the world is made up of objects whose existence is independent of human consciousness turns out to be in conflict with quantum mechanics and with facts established by experiment. 72
This process was ‘unconscious’, in the sense that no fully fledged individuated and embodied
consciousnesses were manifested, for millions of years. During this time sentient organisms began to be prepared within the non-manifested ‘implicate’ levels of quantum potentiality. Prior to
the Cambrian ‘explosion’, when the basic body structures of life suddenly burst onto the material evolutionary scene, the development of future organic sentient life took place within the
quantum field of potentiality. This is why the evidence of Evo-Devo clearly indicates that body
plans were in place prior to manifestation of organisms on the material level. Once sentient organisms came on the scene they unwittingly became implicated in the process of constructing
the form of the universe they inhabited. This is indicated by the H&M quantum metaphysical
perspective and by Wheeler’s assertion that the universe is “self-synthesized” through the perceptual activities of “the observer participants of all times and all places.”
In his recent book From Quantum to Cosmos: The Universe Within physicist Neil Turok, Director of the Perimeter Institute for Theoretical Physics, has written:
Great mysteries remain. Why did the universe emerge from the big bang with a set of
physical laws that gave rise to heavy elements and allowed complex chemistry? Why did
these laws allow for planets to form around stars, with water, organic molecules, an atmosphere and the other requirements for life? Why did the DNA-protein machinery, developed and selected for in the evolution of primitive single-cell organisms, turn out to
be able to code for complex creatures, like ourselves? How and why did consciousness
emerge? At every stage in the history of the universe, there was the potential for vastly
more than what had been required to reach that stage. Today, this is more true than ever.
Our understanding of the universe has grown faster than anyone could have imagined a
century ago, way beyond anything that could be explained in terms of past evolutionary
advantage. … Are all these capabilities simply accidental? Or are we actually the dooropeners to the future. Might we be the means for the universe to gain a consciousness of
itself?73
The physicist Sean Carroll has suggested something similar, although in a materialistically perverse way:
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
738
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
We are part of the universe which has developed a remarkable ability: we can hold an
image of the world in our minds. We are matter contemplating itself.74
The notion that is must be a universal primordial energy-awareness-consciousness that is “contemplating itself” is still anathema to many physicists and philosophers so they will resort to all
kinds of intellectual subterfuges to avoid the issue, such as overlooking the fact that matter, by
definition, is not the kind of stuff which can contemplate itself. Erwin Schrödinger, one of the
‘founding fathers’ of quantum theory, suffered from no such prejudice for a ‘known-to-be-false’
materialist metaphysics when he said:
Mind has erected the objective outside world … out of its own stuff.75
Other ‘founding fathers’ came to a similar conclusion. Max Planck started out his scientific career as materialist but towards the end of his life radically changed his ideas. He asserted that:
All matter originates and exists only by virtue of a force... We must assume behind this
force the existence of a conscious and intelligent Mind. This Mind is the matrix of all
matter.76
And:
I regard consciousness as fundamental. I regard matter as derivative from consciousness.77
Werner Heisenberg also saw that quantum physics clearly indicated that the process of reality is
best viewed through the perspective of Platonic idealism:
On this point modern physics has definite decided for Plato. For the smallest units of
matter are in fact, not physical objects in the ordinary sense of the word; they are
forms, structures, or in Plato’s sense – ideas, which can unambiguously spoken of in
the language of mathematics.78
Isn’t it time for today’s physicists and philosophers to be mindful of the scientific facts and implications and get honest about this matter?!
Professor Anthony Flew was a philosopher who changed his views concerning materialism, theism and intelligent design as the evidence for ID became more compelling. Professor Antony
Flew was described as: “a legendary British philosopher and atheist” who was “an icon and
champion for unbelievers for decades.”79 In his most famous book, God and Philosophy, Flew
concluded:
…though as always subject to correction by further evidence and further argument, that
the universe itself is ultimate; and, hence, that whatever science may from time to time
hold to be the most fundamental laws of nature, must, equally provisionally, be taken
as the last words in any series of answers to questions as to why things are as they
are.80
In other words, the universe itself is the ultimate reality and so there is no need to believe in any
sort of Creator. Flew regularly debated against theistic philosophers and was considered to be
“one of the most renowned atheists of the 20th Century.”81
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
739
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
In 2004, however, Flew changed his mind let it be known that he had become a theist because:
‘the case for an Aristotelian God who has the characteristics of power and also intelligence, is
now much stronger than it ever was before.”82 He said that he simply: ‘had to go where the evidence leads.”83 Flew’s change of mind was big news because of his previous staunch atheism. ID
proponent Jonathan Witt has said of Flew’s turn-about that:
Those who admired [Flew’s] intellect when he was an atheist should listen carefully to
his reasoning now - for if a man suddenly becomes persona non grata for changing his
mind, then the possibility of reasoned civil discourse withers.’84
In his review of Dawkins’ book The God Delusion Flew wrote that:
The fault of Dawkins as an academic … was his scandalous and apparently deliberate
refusal to present the doctrine which he appears to think he has refuted in its strongest
form. Thus we find in his index five references to Einstein. They are to the mask of Einstein and Einstein on morality; on a personal God; on the purpose of life … and finally
on Einstein’s religious views. But (I find it hard to write with restraint about this obscurantist refusal on the part of Dawkins) he makes no mention of Einstein’s most relevant
report: namely, that the integrated complexity of the world of physics has led him to believe that there must be a Divine Intelligence behind it. (I myself think it obvious that if
this argument is applicable to the world of physics then it must be hugely more powerful
if it is applied to the immeasurably more complicated world of biology.)
Whilst Einstein’s statements concerning religion are to a large extent ambiguous, he certainly
made statements which do not chime in resonance with the hard-core materialist assertion that all
intelligence derives from the profound unintelligence of blind and mindless forces. He came to
believe in a “spirit manifest in the laws of the universe,” in a “God who reveals Himself in the
harmony of all that exists”85, although he did not believe in a personal God. He wrote that:
The religious inclination lies in the dim consciousness that dwells in humans that all
nature, including the humans in it, is in no way an accidental game, but a work of lawfulness that there is a fundamental cause of all existence.86
In a 1930 essay entitled “What I Believe,” Einstein wrote:
To sense that behind anything that can be experienced there is something that our minds
cannot grasp, whose beauty and sublimity reaches us only indirectly: this is religiousness.
In this sense, and in this sense only, I am a devoutly religious man.87
Whilst it is clear that Einstein did not believe in a personal God, he also clearly did not believe in
an essentially unintelligent universe.
In his excellent book Mind and Cosmos: Why the Materialist Neo-Darwinian Conception of Nature is Almost Certainly False the philosopher Thomas Nagel has written that:
Physico-chemical reductionism in biology is the orthodox view, and any resistance to it
is regarded as not only scientifically but politically incorrect. But for a long time I have
found the materialist account of how we and our fellow organisms came to exist hard to
believe, including the standard version of how the evolutionary process works. The more
details we learn about the chemical basis of life and the intricacy of the genetic code, the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
740
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
more unbelievable the historical account becomes .… it seems to me that, as it is usually
presented, the current orthodoxy about the cosmic order is the product of governing assumptions that are unsupported and that it flies in the face of common sense.88
And one of the unsupported “governing assumptions” is that of materialism, a worldview which
has been shown to be false and is yet promoted with vigour by a coterie of academics who seem
unconcerned with the evidence. Nagel writes concerning the proponents of ID that:
Even if one is not drawn to the alternative of an explanation by actions of a designer,
the problems that these iconoclasts pose for the orthodox scientific consensus should
be taken seriously. They do not deserve the scorn with which they are commonly
met. It is manifestly unfair.89
However, as we shall see, the tactic of resorting to scorn can be used to conceal weakness, in fact
scorn is the only recourse for those who need to avoid the evidence. Furthermore, we shall discover that many of the bizarre arguments and notions employed by materialist apologists in order
to try and account for how utter mindlessness is supposed to produce consciousness, awareness
and mind really are worthy of a degree of intellectual scorn.
1
d’ Espagnat, B. (2006), 425
Chandrakirti and Jamgon Mipham (2002), 82
3
Stapp, Henry: ‘Philosophy of Mind and the Problem of Free Will in the Light of Quantum Mechanics’,
19
4
Dawkins, R. (1995), xi, xii
5
Stapp, Henry (1995) – Why Classical Mechanics Cannot Naturally Accommodate Consciousness But
Quantum Mechanics Can.
6
Stapp, Henry (2007), 139
7
Dennett, Daniel (1991), 33
8
Dennett, Daniel (1991), 27
9
Dennett, “Artificial Intelligence as Philosophy and Psychology”, 124, quoted in Pinker, How The Mind
Works, 79
10
Randall, L. (2006), 158
11
Allday, Jonathan (2009), 493
12
Baggott, J. (2012), 88-89
13
Baggott, J. (2012), 2-3
14
http://www.nytimes.com/2012/03/25/books/review/a-universe-from-nothing-by-lawrence-m-krauss.html
15
Wilson, Sociobiology, 4
16
Tallis, R. (2011), 277
17
Tallis, R. (2011), 51
18
Hawking, S. & Mlodinow, L. (2010), 139
19
Hawking, S. & Mlodinow, L. (2010), 136
20
Hawking, S. & Mlodinow, L. (2010), 140
21
Ibid.
22
Stapp, Henry: ‘Philosophy of Mind and the Problem of Free Will in the Light of Quantum Mechanics’,
19
23
Stapp, Henry: ‘Quantum Interactive Dualism’, 18
2
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
741
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
Stapp, H. P. (2010). ‘Minds and Values in the Quantum Universe’ in Information and the Nature of
Reality, Davies, Paul & Gregersen, Niels Henrik (eds.), Cambridge University Press.
25
Randall, L. (2012) Back cover blurb.
26
Barrow, John D., Davies, Paul C. W., Harper, Charles L. (eds.) (2004) p136 – Wojciech H. Zurek:
‘Quantum Darwinism and envariance.’
27
Schlosshauer . M, (ed.) (2011) p159
28
Barrow, John D., Davies, Paul C. W., Harper, Charles L. (eds.) (2004) p577 – Wheeler, J A (1999) ‘Information, physics, quantum: the search for links.’ In Feynman and Computation: Exploring the Limits of
Computers, ed. A. J. G. Hey, p309 (314). Cambridge, MA: Perseus Books.
29
http://www.guardian.co.uk/books/2011/feb/05/nicholas-humphrey-soul-dust-review
30
http://biology.arizona.edu/sciconn/lessons2/shindelman/background.html
31
Wittgenstein, Philosophical Investigations, para 115
32
Tallis, R. (2011), 183
33
Ibid.
34
Barrow, John D., Davies, Paul C. W., Harper, Charles L. (eds) (2004) p201 – Anton Zeilinger: ‘Why
the quantum? “It” from bit”? A participatory universe? Three far-reaching challenges from John Archibald Wheeler and their relation to experiment.’
35
http://www.guardian.co.uk/books/2011/feb/05/nicholas-humphrey-soul-dust-review
36
Coyne, J. (2009), 244
37
Brockman, J. (ed.) (2006), ix, x
38
Stapp, Henry: ‘Quantum Interactive Dualism’, 18
39
Meyer, Intelligent Design is Not Creationism, http://www.discovery.org/a/3191
40
Meyer, S. C. (2010), 347
41
Dembski W. A. (2002), 206
42
Coyne, J. in Brockman, J. (ed.) (2006), 4
43
Wedge Document quoted by Coyne in Brockman, J. (ed.) (2006).
44
Stapp, H. P. (2010). ‘Minds and Values in the Quantum Universe’ in Information and the Nature of
Reality, Davies, Paul & Gregersen, Niels Henrik (eds), Cambridge University Press, 117
45
Stapp, Henry (2004), 223
46
Woolfson, Adrian (2000), 74
47
Barrow, D. John & Tipler, Frank J. (1986), 105
48
Woolfson, Adrian (2000), 83
49
Woolfson, Adrian (2000), 76
50
Carroll, Sean, B. (2006), 139
51
Tallis, R. (2011), 170
52
Tallis, R. (2011), 175
53
Sperry, R. W. in Brain, Behaviour and Evolution, edited by D. D. Oakley and H. C. Plotkin (Psychology in Progress Series, Methuen, New York,1979).
54
Davidson, D. (1970), “Mental Events,” in Experience and Theory, Foster and Swanson (eds.). London:
Duckworth.
55
Ibid.
56
Stapp, Henry (2004), 236
57
Ibid.
58
http://www.chem1.com/acad/sci/aboutwater.html
59
Tallis, R. (2011), 173
60
Damasio, Antonio (2000)
61
Tallis, R. (2011), 176
62
Meyer, S. C. (2010), 291
63
Meyer, S. C. (2010), 282
24
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
742
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 714-742
Smetham, G. P., The Falsehood of the Materialists’ Mindless Evolution of Minds from Mindless Matter
64
http://www.wired.com/wiredscience/2010/02/quantum-photosynthesis/
Abbott D., Davies, P. C. W. & Pati, A. K. (eds.) (2008), 11
66
Quantum Evolution - http://www.surrey.ac.uk/qe/O4.htm
67
Davies, Paul (2007) p264
68
Mensky, Michael:Postcorrection and the mathematical model in Extended Everett’s Concept, 2-3
69
Mensky, M. B. (2010), 150-153
70
Mensky, Michael:Postcorrection and the mathematical model in Extended Everett’s Concept, 3
71
Davies, Paul (2007), 275
72
d'Espagnat, Bernard, ‘The Quantum Theory and Reality’ Scientific American, Nov. 197
73
Turok, N. (2013), 201
74
Carroll, S. (2012), 280-281
75
Schrödinger, E. (1944), 121.
76
Das Wesen der Materie” (The Nature of Matter), speech at Florence, Italy, 1944 (from Archiv zur Geschichte der Max-Planck-Gesellschaft, Abt. Va, Rep. 11 Planck, Nr. 1797)
77
The Observer (January 25th, 1931).
78
Wilber, K. (ed.) (2001).
79
Craig J. Hazen, Preface to the pre-publication release of ‘My Pilgrimage from Atheism to Theism: An
Exclusive Interview with Former British Atheist Professor Antony Flew’ @
www.biola.edu/antonyflew/flew-interview.pdf
80
Antony Flew, God and Philosophy, second edition, (Hutchinson of London, 1966), p. 194.
81
Richard Carrier, ‘Antony Flew Considers God. . . Sort Of’ @ www.secweb.org/asset.asp?AssetID=369
82
Antony Flew, ‘My Pilgrimage from Atheism to Theism: An Exclusive Interview with Former British
Atheist Professor Antony Flew’
83
Ibid.
84
Jonathan Witt, ‘Entertaining the notion of a place of wonder’ @
http://seattletimes.nwsource.com/html/opinion/2002120766_witt16.html
85
Isaacson, W. (2008), 44
86
Isaacson, W. (2008), 46.
87
Isaacson, W. (2008), 47
88
Turok, N. (2013), 5
89
Turok, N. (2013), 10
65
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
195
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Article
The Potential Effects of Human Group Emotion and Subjective
Novelty on the Statistical Behaviour of a Random Event Generator:
Exploratory Study
Joey M. Caswell1,2 *, J. Miguel Gaona1,6,7 *, David A. E., Vares1,2,3, Andrew Lapointe1,2,4,
Ryan C. Burke2,5, Lucas W. E. Tessaro2,5
Transnational Anomalies Research1
Neuroscience Research Group2, Experimental Psychology3, Human Development4, and Biology5
Programs, Laurentian University, Sudbury, Ontario, Canada
Centro Europeo Neurosalus6, Madrid, Spain
Psychology Department7, Universidad Rey Juan Carlos, Madrid, Spain
Abstract
Many traditional beliefs regard “human energy” as an integral component in human health and
positive life experience. A number of areas in the realm of complementary and alternative
medicine, as well as consciousness research in general, have explored the potential for these
subtle energies in a myriad of experiments and applications. The FieldREG experiments
previously conducted by a number of researchers have demonstrated an apparent effect of novel
or emotional group activities on the statistical deviations of a proximal Random Event Generator
device. In the present study, further exploration of this phenomenon was employed in both novel
and relatively mundane group settings. Furthermore, a directional hypothesis was pursued
whereby positive emotional experiences were expected to produce upward (positive) trends in
the random data, while negative emotional settings would produce downward (negative)
deviations. Finally, an overall comparison between random data from positive and negative
settings was investigated. Results tended to support current theories that emotional or novel
group experiences appear to influence the statistical performance of a random physical device,
and that the emotional valence may further affect the overall direction of the random data
obtained.
Key Words: Consciousness, Random Event Generators (REG), Human Emotions, Subtle
Energies, FieldREG
1. Introduction
There are a multitude of both past and current theories and beliefs regarding a potential ‘energy’
associated with living beings, specifically humans. These theories appear within a number of
varying traditions from spiritual and esoteric beliefs to modern energy healing theories [1-2].
Many spiritual traditions employ some concept consistent with the idea of a ‘life force’. The
ancient Hindu Vedas describe the prana (‘life force’) which connects the universe. This concept
*Corresponding authors: J. M. Caswell & J. M. Gaona E-mail: neuraljc@gmail.com, drgaona@neurosalus.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
196
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
is largely similar to qi (‘breath’) in Chinese culture which continues to provide a major
underlying foundation for traditional Chinese medicine.
Throughout the history of science, Eastern belief systems have influenced a range of new ideas
regarding this ‘vital energy’, particularly those in the aptly named vitalist tradition. In the 18th
century, Franz Mesmer described a natural invisible force exerted by living things which he later
termed animal magnetism [3]. By employing magnetism in the context of various therapies,
Mesmer sought to affect human health. Despite his apparent successes at the time, this theory
eventually lost favor and is largely forgotten today. The far less known concept of ‘Odic force’,
originally conceived by Carl von Reichenbach in the mid-19th century, similarly described a vital
force associated with human energy. This theory posited that the life force was related to
electromagnetism and temperature [4], which is remarkably consistent with current theories of
consciousness [5-7].
A small number of these early theories of human energy have also had a considerable impact on
literature and other important areas of Western culture. The concept of ‘orgone’ energy,
originally hypothesized by Wilhelm Reich in the 1930’s, described a similar ‘life force’ to many
previous philosophies [8]. Charles Kelley eventually posited that ‘orgone’ was a universal force
which opposed entropy [9]; whereas nature tends toward disorder (entropy), orgone was viewed
as the ‘creative’ counterpart to the entropic principle. Despite its eventual dismissal on the
grounds of severely lacking empirical support, this theory appears remarkably convergent with
current theories regarding the effects of conscious intention eliciting increased order in an
external random system [10]. Although many ‘life energy’ theories appear crude or even
ridiculous in the context of modern scientific investigation, the continual appearance of this type
of idea throughout the history of spirituality and the humanities indicates that this concept is
consistently at least an intriguing feature of the subjective experience.
Many areas of modern complementary and alternative medicine (CAM) have continued to
pursue the integration of Eastern philosophy and Western science through the investigation of
energy medicine and non-local healing. While decades of research have revealed significant
effects of consciousness on an external random physical system [11-13], there has also been a
plethora of similar research conducted on the potential effects of human ‘energy’ [14-15] and
consciousness [16-17] to affect change in external biological systems. The apparently non-local
healing effects previously observed in the tradition of Reiki continue to be implemented in
various CAM settings [1, 18], while the concept of qi remains an integral factor in the practice of
traditional Chinese medicine [2]. Although some ‘essence’ of life may or may not be responsible
for these observed effects, there are many theories grounded in physical bases which further
suggest that consciousness itself may play a role in the physical realm [19] and this idea has been
supported with convergent quantification of physical parameters [20].
Furthermore, a theory of ‘global consciousness’, capable of introducing anomalous deviations in
random physical systems, has recently been examined with evidence suggesting that large-scale
events which induce emotional reactions in people across the globe might affect the outcome of
many random event generator (REG) devices located around the planet [21]. If this hypothesis is
correct in any manner, then this might suggest that immediate gatherings of human groups
should be capable of eliciting similar effects during periods of heightened emotional states. The
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
197
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
following experiments sought to investigate whether emotional experiences in large groups could
produce statistically anomalous deviations within a REG device located in the local environment.
Indeed, there have been a small number of ‘FieldREG’ studies conducted previously, which
seem to support this contention to some extent. While one early study in this area revealed
reasonable effects in favor of this hypothesis [10], later research examined events of greater
emotional significance which subsequently showed much more consistent REG effects [22].
Furthermore, similar effects have been noted with impressively significant results in the context
of large group meditation [23].
These theories were explored in the current research protocol with the additional hypothesis that
the outcome of a random system might be affected in terms of overall directionality. We
suspected that a binary series of data (0 or ‘down’, 1 or ‘up’) produced in direct proximity to
human gatherings would conform to the emotional valence of those present. Although this theory
may initially appear rather farfetched, the mere fact that individuals appear capable of producing
similarly anomalous deviations which conform to their pre-stated intentions (‘up’ or ‘down’) in
identical systems could lend some support to the current hypothesis [11]. This point adopts a
particular salience regarding the anomalous nature of human intention and consciousness in
general given that the digital representations of random physical systems to which human
intentions are typically directed are simply abstract symbols applied to the fundamental process
being sampled (e.g., electron tunneling). Therefore, we further hypothesized that novel positive
and negative emotional settings would reveal significantly different deviations with overall
directions opposite to each other. This theory might be further supported by the many
experiments conducted within the area of presentiment or human ‘intuition’ which suggest that
anomalous non-local processes correlated with consciousness have a greater effect in emotional
contexts [24-26].
In addition to this, we further suspected that the overall magnitude of subsequent effects would
be related to the subjective novelty of each context examined. We reasoned that relatively novel
events would elicit the greatest anomalous effects in the output of a random physical process
while more mundane scenarios would be associated with baseline or chance probability results as
typically obtained in a controlled setting.
2. Methods
2.1. Equipment
Random data was produced using two Psyleron REG-1 random event generators
(www.psyleron.com). This device produces a random output which is generated by electron
tunneling effects within two field effect transistors. The varying voltage levels which result from
this process are converted into digital data through a gated sampling procedure which allows for
regularly spaced bit sequences. The output of both transistors is internally compared through an
alternating (0, 1) XOR masking process in order to reduce any potential influence of physical
artifacts or other external environmental variables. The device itself is further protected from
static electromagnetic factors by an aluminum outer shielding and a Permalloy mu-metal inner
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
198
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
shield. Furthermore, the device was rigorously calibrated prior to shipment in order to ensure
output conformed to statistical expectations. The random event generator (REG) devices were
also tested in control experiments within respective laboratories (Canada and Spain) to confirm
these expectations. The resulting data streams were collected through USB-port using the
Psyleron FieldREG software package on laptop computers. Individual events were produced at a
rate of either 1/sec or 5/sec (1 event = 200 bits) for longer or shorter experiments respectively.
However, internal consistency was maintained within each experiment. There were no
significant differences noted between event rates in previous testing (p > .05).
During data collection, the device was located within proximity to various human gatherings in a
number of contexts; this included subjectively negative, positive, and neutral or mundane
scenarios.
Values for each individual REG event refer to the number of 1's out of 200 bits with binary
probabilities, represented by a value of 0-200. The theoretical (chance) mean for each event is
100 with a standard deviation of √50. Each data segment (time period) from each experiment
was processed and analyzed independently according to manually time-stamped behaviours and
other occurrences in the local environment. All segments consisting of fewer than 100 total
events were discarded due to inherently large measurement uncertainties.
All data processing procedures were conducted using Microsoft Excel 2010 software.
2.2. Locations
Initial data collection took place on February 10, 2013 during services at a Catholic church in
Sudbury, Ontario, Canada (Catholic Service). The experimenters and the REG device were
located in the right side of the rear seats in the church. There were approximately 185 individuals
in attendance. Output of REG data was produced at a rate of 1 event/sec during this particular
session, which lasted ~49.8 minutes.
The second session was conducted on February 17, 2013 during services at a nondenominational Christian church also located in Sudbury, Ontario, Canada (Non-Denom). There
were approximately 275 people in attendance, and it was noted that the regular pastor was away
on holidays. Data was collected at a rate of 1 event/sec and lasted ~90.43 minutes. During
testing, the experimenters and the REG were located in an upper aisle to the left of the
congregation (Figure 1).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
199
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Figure 1. Non-denominational Christian church service; vantage point of image is that
of the experimenters and REG device
The next session took place in Prado Nuevo, a large field on the outskirts of El Escorial, about 45
km from Madrid, Spain (Prado Nuevo). On the first Saturday of every month, devout
worshippers gather here to pray to the Virgin Mary, who was allegedly sighted in Prado Nuevo
30 years previous. Data collection took place on December 7, 2013 during ceremonies at both
the local chapel (Figure 2) and in the field of Prado Nuevo proper (Figure 3) which lasted
approximately 77 minutes. The REG data was produced at a rate of 5 event/sec, while the device
was located within a backpack worn by an experimenter who traveled with the crowd throughout
the festivities.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
200
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Figure 2. Chapel at Prado Nuevo
Figure 3. Holy field of Prado Nuevo
Data was also collected near Es Vedrà, an island off the coast of Spain (Es Vedra). The REG
device was placed on the central table of the crew’s sailboat equidistant from each bedroom
(centre of the ship). Data was produced at a rate of 1 event/sec during a combined period of
~583.47 minutes. While primarily stationed just in range of the small island (Figure 4), the
expedition had to return to shore a number of times (Figure 5) due to turbulent conditions. A
number of relatively mundane scenarios took place during this particular session, while there was
also a funeral ceremony, as well as physical pain (serious jellyfish wound) which occurred. Data
collection took place from August 22 to 23, 2013.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
201
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Figure 4. Island of Es Vedrà; X mark indicates location where boat was positioned; obtained
from Google Maps
Figure 5. Island of Es Vedrà (lower left) and path taken to shore with docking location; obtained
from Google Maps
REG data was also collected during a flight from El Hierro Island to Gran Canaria in the Canary
Islands (Canary Flight). A regular flight was grounded on January 5, 2014. Despite poor weather
conditions, approximately 40 passengers proceeded to board a small plane to complete the trip to
Gran Canaria. A REG device was located within a backpack worn by an experimenter while
boarding the second plane, during flight, and after arrival at Gran Canaria. Data was collected at
a rate of 5 event/sec for ~49 minutes.
2.3. Data Processing
REG data from each segment within each experiment condition was analyzed independent of
either previous or subsequent values; relevant statistics and figures were produced accordingly.
Individual REG event scores were standardized according to 0.5 chance expectations ([x-100] /
√50). Combined overall z-scores for each segment were computed according to Stouffer’s
method (zc = ∑z / √N) where z = individual event z-scores and N = the number of event scores.
Effect sizes follow a method proposed by Helfrich [27] and employed by other researchers in
this area, using the relationship es = zc / √N which is equivalent to the mean event z-score. Onetailed probabilities (1T) are reported according to a priori hypotheses regarding the directional
component of REG output. Measurement uncertainty for each segment (σµ) was computed
according to σ/√2N, where σ = √50 and N = number of REG events.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
202
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
3. Results
3.1. Mundane Setting
The first test session (Catholic) took place during standard church services. We had hypothesized
that few if any segments of REG data would present with significant deviations of particularly
large magnitude given the relatively little novelty involved in a weekly process. However, we
suspected that any deviations observed would be in the ‘up’ direction (more 1’s than 0’s) given
the typically positive emotional experiences religious individuals associate with this type of
activity. Changes in group activity were logged in real time by experimenters (Figure 6).
As anticipated, the behaviour of the REG device remained within chance expectations (p > .05)
for a majority of the church service (Table 1). Furthermore, a period of sustained applause from
the congregation prior to the end of the service produced a significant upward trend in the data
(zc = 2.94, p = .002, es = .28), although this segment had a relatively high measurement
uncertainty given the smaller total number of events (σµ = .477). Note that all periods of REG
deviation which cross the threshold for statistical significance during testing were in the upward
(positive) direction.
Figure 6. Cumulative deviation in REG data during the Catholic Service experiment;
parabolas indicate threshold for statistical significance (p = .05)
Table 1. REG event data for each Catholic Service segment; N = number of events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability of zc, σµ =
measurement uncertainty (σ/√2N)
Segment
1. Start REG (Standing)
2. Seated
3. Stand/Sing
ISSN: 2153-8212
N
zc
es
p
σµ
291 -1.376 -.08 .084 .293
360 -.06
0
> .45 .264
134 1.405 .121 .08 .432
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
203
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
4. Seated/Sermon
5. Stand/Lord’s Prayer
6. Seated Hymn
7. Stand
8. Stand/Lord’s Prayer
9. Communion
10. Stand/Announcements
11. Applause
500
192
258
143
424
174
144
110
.588
.53
1.24
-.76
.78
-.11
-.44
2.94
.026
.04
.08
-.06
.04
-.01
-.04
.28
.278
.298
.108
.224
.218
>.45
>.45
.002
.224
.361
.311
.418
.243
.379
.417
.477
The second test session occurred during a non-denominational Christian church service (NonDenom) and it was again anticipated that the REG data would tend to remain within baseline
probabilities due to the relative frequency with which this particular event occurs.
All cumulative z-scores during this experiment (Table 2) were within chance expectations (p >
.05; Figures 7 & 8). Again, note that the isolated moments of significant REG deviation within
the sermon segment (Figure 8) were in the direction previously associated with positive
emotional experience (upward trend).
Figure 7. Cumulative deviation in REG data during the Non-Denom experiment for
segments of N > 100; arrow indicates break in data for Sermon segments (Figure 8);
parabolas indicate threshold for statistical significance (p = .05)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
204
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Figure 8. Cumulative deviation in REG data during Sermon time period(s) for the NonDenom experiment; arrow indicates break in data for short prayer segment (N = 18, not
included); parabolas indicate threshold for statistical significance (p = .05)
Table 2. REG event data for each Non-Denom segment; N = number of events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability of zc,
σµ = measurement uncertainty (σ/√2N)
Segment
N
zc
es
1. Start REG
103 -.098 -.01
2. Song
211 -.058 -.004
nd
3. 2 Song
261 .464 .029
4. 3rd Song
269 1.121 .068
th
5. 4 Song
240
.32
.021
6. 5th Song
144 -.212 -.018
7. Children Leave/Greetings 258 -.872 -.054
8. Choir/Offering
284 .864 .051
9. Sermon
547 .847 .036
10. Continue Sermon
2077 1.369 .03
11. Choir on Stage
102 -.014 -.001
12. Prayer
200 -.63 -.045
13. Final Song
144 1.226 .102
p
>.45
>.45
.321
.131
.375
.416
.192
.194
.199
.086
>.45
.264
.11
σµ
.493
.344
.31
.305
.323
.417
.311
.297
.214
.11
.495
.354
.417
3.2. Novel Positive Emotional Setting
The preliminary analysis of a relatively novel positive emotional gathering was conducted on
data obtained during a large religious event at Prado Nuevo in Spain, which has spiritual
significance for Christians. This event occurs on a monthly basis and is attended by a varying
group of individuals. We had hypothesized that the prayer segments in this experiment would
show significant upward deviations in the REG data, while other segments would show baseline
z-scores.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
205
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
While the periods outside of prayers consistently demonstrated baseline results (p > .05), the
initial prayer in which the mass was developed near the local chapel showed a highly significant
upward trend as anticipated (Figure 9; zc = 3.037, p = .001, es = .062). However, the
considerably longer praying of the rosary which occurred in the field of Prado Nuevo proper
displayed non-significant results supporting the null hypothesis (Figure 10), although it is
interesting that it was the primary prayer (e.g., the more ‘novel’ of the two) which displayed the
significant deviation (Table 3).
Figure 9. Cumulative deviations in REG data during each time period for the Prado
Nuevo experiment; parabolas indicate threshold for statistical significance (p = .05)
Figure 10. Cumulative deviation in REG data during final time period for the Prado
Nuevo experiment; parabolas indicate threshold for statistical significance (p = .05)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
206
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Table 3. REG event data for each Prado Nuevo segment; N = number of events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability of zc,
σµ = measurement uncertainty (σ/√2N)
† primary segments of interest
Segment
N
zc
es
1. Start REG
1500
.19
.005
2. Enter Holy Field
1500 1.58·10-15 4.09·10-17
2400
3. Develop Prayer†
3.037
.062
4. Final Blessing
300
1.364
.079
5. Carrying Mary
1500
.004
9.43·10-5
6. Praying the Rosary† 15990
-.755
-.006
p
.425
>.45
.001
.086
>.45
.225
σµ
.129
.129
.102
.289
.129
.04
3.3. Novel Negative Emotional Setting
The next experiment we examined occurred in the context of a negative emotional event (e.g.,
funeral ceremony). Again, this type of event is somewhat rare and novel compared to initial
experiments (Catholic and Non-Denom), particularly given the relatively exotic location of the
event (Es Vedrà Island). As with the previous analyses, we hypothesized that REG output would
remain consistent with control conditions during the more mundane events (e.g., eating dinner)
while the events associated with the funeral would show significant data deviations.
Furthermore, in contrast to the previous experiments, we hypothesized that the funeral events
would demonstrate downward trends consistent with the theory of emotional valence in the
FieldREG phenomenon.
As expected, mundane events demonstrated non-significant z-scores (p > .05). However, when
the crew returned to Es Vedrà on the day of the funeral, there was a slightly significant deviation
in the anticipated direction (Figure 11; zc = -1.94, p = .026, es = -.032). Following this segment, a
crew member received a serious jellyfish wound. While this was not expected prior to
conducting the experiment, it provided an interesting opportunity to examine REG output in
proximity to severe physical pain. This segment revealed a significant deviation (zc = 2.22, p =
.013, es = .038). If emotional valence indeed plays a role in this phenomenon, then physical pain
may differ from ‘emotional pain’ given the upward trend displayed during this period. The main
segment of interest was the actual funeral ceremony and the scattering of the ashes (Table 4). As
initially hypothesized, this segment displayed a significant downward trend (zc = -1.927, p =
.027, es = -.045). This particular segment appears to confirm the hypotheses regarding both
valence and occurrence of significant deviations.
During a 10-hour period while the crew was sleeping (Figure 12), there was a steady downward
trend present within the data records which peaked beyond the threshold for significant
deviations. Although this segment presented with a weak overall effect (zc = -1.791, es = -.009, p
= .037), it should be noted that the large number of accumulated bits (N = 36000) allowed for the
most precise calculation of the overall mean shift of REG event scores (σµ = .037). Furthermore,
data collection for such a prolonged period should “smooth” any artifactual deviations out of the
record over time, while this period instead demonstrated a consistent negative drift over the 10hour period. While not included in the initial novelty/directional hypotheses, this segment
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
207
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
presents some intriguing possibilities, particularly given the absence of studies examining nonconscious (sleeping) individuals in proximity to random physical systems. Subjective reports of
individuals prior to this segment suggested a generally sad disposition among the crew
attributable to the coming activities of the following day.
Figure 11. Cumulative deviations in REG data during each time period for the Es
Vedra experiment; arrow indicates break in data for Sleep segment (Figure 12);
parabolas indicate threshold for statistical significance (p = .05)
Figure 12. Cumulative deviation in REG data during the Sleep time period (10 hrs) for
the Es Vedra experiment; parabolic curve indicates threshold for statistical significance
(p = .05)
Table 4. REG event data for each Es Vedra segment; N = number of events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability of zc,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
208
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
σµ = measurement uncertainty (σ/√2N)
† primary segment of interest
Segment
N
zc
es
p
σµ
1. Start REG in Vedra 10800 -.31 -.003 .378 .048
2. Leave Vedra
1800
.067 .002 >.45 .118
3. Arrive at Shore
3600
1.49 .025 .068 .083
4. Dinner
3600 -.413 -.007 .34 .083
5. Sleep
36000 -1.791 -.009 .037 .026
6. Back to Vedra
1800 -.773 -.018 .22 .118
3600 -1.94 -.032 .026 .083
7. Vedra Arrival
3600
8. Dive/Sting
2.22 .038 .013 .083
9. Scattering Ashes† 1800 -1.927 -.045 .027 .118
10. Leaving Vedra
4408 1.086 .016 .139 .075
The final test session occurred aboard a small plane travelling within the Canary Islands. It was
noted that the weather conditions were not favorable and the small number of passengers were
particularly anxious regarding these specific circumstances. Due to this, we had hypothesized
that the REG device would produce negative, downward trends during the flight consistent with
emotional valence previously suspected.
The data segments which occurred prior to and following the flight were within chance
expectations (p > .05). The flight segment produced an overall downward trend in the anticipated
direction which peaked beyond the level of statistical significance as the plane gradually
proceeded towards its destination (Figure 13). While it is tempting to posit an emotional effect
during this period, the overall flight segment revealed a non-significant cumulative z-score
(Table 5).
Figure 13. Cumulative deviations in REG data during each time period for the Canary
Flight experiment; parabolas indicate threshold for statistical significance (p = .05)
Table 5. REG event data for each Canaria Flight segment; N = number of events, zc =
combined z-score, es = effect size (zc/√N; equal to mean REG z), p = probability of zc,
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
209
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
σµ = measurement uncertainty (σ/√2N)
† primary segment of interest
Segment
N
zc
es
p
σµ
1. Start REG 2100 -1.04 -.023 .149 .109
2. Flight†
11400 -1.538 -.014 .062 .047
3. Arrival
1173
.359 .011 .36 .146
3.4. Positive – Negative Setting Comparison
In order to further pursue the directional hypothesis that novel subjectively positive and negative
emotional settings would show significantly differential deviations a number of calculations
were performed (Table 6) allowing a direct comparison accounting for differing numbers of total
REG events. The a priori segments of interest († in Tables 3-5) for which the project was
originally designed to investigate included the two prayer sessions from the Prado Nuevo
experiment (positive), the funeral ceremony from the Es Vedra experiment (negative), and the
turbulent flight in the Canary Flight experiment (negative). By obtaining the absolute REG
deviation difference between combined positive and negative conditions and computing the
measurement uncertainty associated with the respective values for N, it was determined that a
small but significant difference in REG output occurred between novel positive and negative
emotional segments (zc = 1.887, p = .03).
Table 6. N = combined number of REG events, δµ = absolute deviation (µ positive - µ
negative), σµ = measurement uncertainty in δµ (σ ∙ √([1 / N positive] + [1 / N negative]) where σ
= √50), zc = z-score of overall difference (δµ / σµ), p = probability of zc (1T)
N
δµ
σµ
zc
p
Positive vs Negative Context
31590
.152
.081
1.887
.03
4. Discussion
Present results were generally in favor of the overall FieldREG hypothesis. That is, events of
interest identified a priori were typically associated with significant deviations in random event
generator (REG) data. While the apparent data shifts revealed fairly weak overall effects, the
greatest deviations persisted to appear in relation with significant events in the human
environment. Furthermore, these results remain fairly consistent with those obtained in previous
studies [10, 22]. The contention that relative novelty might play a role in this phenomenon
seemed to play an even greater role in the current exploratory study. While the relatively
mundane settings investigated demonstrated the expected baseline data conformation, the brief
moments of significant excursions within the data were found to be in the upward (positive)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
210
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
direction. This would follow the directional hypothesis regarding the emotional valence of a
given group setting.
The more novel scenarios under investigation, through which our main hypotheses were
explored, tended to support the role of both novelty and emotional valence as factors in the
apparent effect on REG performance. Specifically, the novel positive emotional setting displayed
a highly significant upward (positive) deviation in association with the first (more novel) of two
major prayer sessions at Prado Nuevo. All other segments within this experiment revealed
baseline REG activity.
The major negative emotional setting explored (funeral ceremony) again supported both the prestated novelty and emotional valence hypotheses, displaying a significant downward (negative)
trend over the course of this event. While not included in the a priori hypotheses, the novel
negative physical event (jelly fish sting) provided an interesting opportunity to investigate
potential effects which might be associated with physical pain. Contrary to the consistent pairing
of negative emotions with negative deviations, this particular segment displayed a significant
upward (positive) deviation in REG data. Although further experiments are required to further
explore this finding specifically, it may be that emotional and physical pain produce opposite
FieldREG effects. However, an experiment to specifically explore this comparison would be
very difficult to conduct safely or ethically.
Furthermore, the segment during which individuals were sleeping might suggest further avenues
of REG exploration. While there are currently no known studies which have examined the
behaviour of a random physical system in close proximity to non-conscious participants (e.g.,
sleeping), the sustained trend observed over such a significant period of time certainly indicates
this may warrant further investigation. This may be particularly useful in similarly emotional
contexts as those currently employed.
Given that brain activity during sleep is very similar to that of a wakeful state, with the exception
of minor additional components such as “sleep spindles”, an emotional contagion capable of
affecting a group of individuals in a waking state may also elicit similar effects during sleep,
particularly when in close proximity. If some unifying emotional factor in the personal
environment is present (e.g., the shared sadness around the funeral ceremony), then this may
already provide some form of neuro-behavioural kindling foundation for enacting some form of
excess correlation between pairs or groups of people.
While the Canaria flight incident provided an intriguing opportunity to further probe the nature
of negative emotions on the output of a REG device, relatively fewer people were present during
this event compared to previous experiments. While the REG data displayed a trend in the
expected direction (downward, negative) associated with a negative event which peaked beyond
the threshold for statistical significance, the final overall score for this particular segment was
non-significant. While the Es Vedra experiment displayed a number of significant deviations
with a small number of individuals present, it may be that a critical mass of proximal human
consciousness is required to elicit or maintain the previously observed FieldREG phenomenon
within the context of specific emotional responses (e.g., fear/anxiety).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
211
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Indeed, this theory could find further support through comparison with previous research in this
area, particularly those examining ‘global consciousness’ effects on a much greater scale.
Specifically, the Nelson [21] study which explored potential REG effects within a global
network of devices during the events of the September 11, 2001 attacks found much larger
effects than those obtained within the smaller group settings employed in the present study.
However, it should also be noted that this study in particular [21] also revealed directional effects
opposite of those anticipated by our previous hypotheses. However, it may also be that varying
“modes” of negative emotion (e.g., fear, pain, sadness, disgust) are associated with varying
degrees of effectiveness and/or overall event count profiles. Further investigation with a wider
array of specifically varied emotional contexts is required to better understand this aspect of the
apparent FieldREG phenomenon.
The potential for an experimenter effect in any of these studies cannot be immediately
discounted. Given that the majority of research investigating the REG phenomenon associated
with consciousness-correlated collapse [11-13] has focused on the directional aspect of prestated operator intentions, it is plausible that an experimenter could have influenced the outcome,
particularly the directionality, within the preceding FieldREG study. However, it remains
intriguing that the subjective novelty of each segment seemed to contribute to the observed
effects.
Arguably, the most contentious issue with current the FieldREG investigation is how the
cumulative deviations of the device could be affected by events which are subjectively positive
or negative in nature. While the notion of non-material “forms” which underlie the material
world has been considered since Plato, a number of modern physical theories could contribute to
a better understanding of this phenomenon. One possible mechanism is found in the context of
holonomic brain theory [28], suggesting that information is stored holographically within the
nervous system whereby individual voxels of consciousness can independently represent wider
concepts and behaviours associated with the self which may further encompass cohesive abstract
forms in aggregate conceptualizations. It may also be relevant that the activity of a single neuron
is capable of initiating a “wave” of depolarization throughout the entire cortical surface [29].
Furthermore, it has been demonstrated that electroencephalographic (EEG) activity of two
individuals separated in space can become synchronized, or excessively correlated, through the
application of specific circumcerebral magnetic fields [6, 30]. It has also been shown that these
correlated changes in EEG activity are related to cerebral photon emission over the plane of the
right temporal lobe [31].
If the energies associated with a single action potential (~10-20 J) can lead to the depolarization of
the entire cortical surface, this would be coupled to large bursts in biophoton emissions, which
itself may interact with the environment [32]. Therefore, the energies associated with a single
thought could affect the thought of all proximal individuals [33]. This underlying concept of
“emotional contagion” has also been examined experimentally with supporting evidence [34-35].
This is in slight contrast to theories of consciousness set in a cosmological framework [36],
which suggest that consciousness should be an independent process which interacts with the
brain, as opposed to reducing this phenomenon to purely organic foundations. Both perspectives
provide some insight into how conscious thought could extend towards the external environment,
even in the absence of active intentions to do so.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
212
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
Further studies with greater experimental controls and a wider array of specific emotional
contexts are required in order to further elucidate the true source of the FieldREG phenomenon.
While a number of current studies have investigated potential physical mechanisms which may
play a role in individual cognitive intention and consciousness-correlated collapse of random
physical systems [13, 32] the precise process of significant REG deviation specifically attributed
to emotional group settings remains to be ascertained.
Acknowledgements: The authors would like to thank Dr. Michael Persinger for his valuable support. We
would also like to extend our thanks to Dr. Teresa Koukutian-Nieto for important suggestions and
feedback.
References
1) Dressen, L. J., & Singg, S. Effects of Reiki on pain and selected affective and personality variables of
chronically ill patients. Subtle Energies & Energy Medicine, 1998; 9(1): 51-82.
2) Ohnishi, T., & Ohnishi, T. The Nishino breathing method and ki-energy (life-energy): A challenge to
traditional scientific thinking. Evidence-Based Complementary and Alternative Medicine, 2006; 3(2):
191-200.
3) Pattie, F. A. Mesmer and Animal Magnetism: A Chapter in the History of Medicine. Edmonston
Publishing: Hamilton, NY, 1994.
4) Reichenbach, K. The Odic Force: Letters on Od and Magnetism. Hutchinson & Co: London, England,
1926.
5) Persinger, M. A., Meli, S., & Koren, S. Quantitative discrepancy in cerebral hemispheric temperature
associated with “two consciousnesses” is predicted by neuroquantum relations. NeuroQuantology, 2008;
6(4): 369-378.
6) Persinger, M. A., & Lavallee, C. F. Theoretical and experimental evidence of macroscopic
entanglement between human brain activity and photon emissions: Implications for quantum
consciousness and future applications. Journal of Consciousness Exploration & Research, 2010; 1(7):
785-807.
7) Dotta, B. T., & Persinger, M. A. Increased photon emissions from the right but not the left hemisphere
while imagining white light in the dark: The potential connection between consciousness and cerebral
light. Journal of Consciousness Exploration & Research, 2011; 2(10): 1463-1473.
8) Mann, W. E. Orgone, Reich, and Eros: Wilhelm Reich’s Theory of Life Energy. Simon and Schuster,
1973.
9) Correa, P. N., & Correa, A. N. Comparative study of the variation in the spontaneous discharge rate of
atmospheric electroscopes and electroscopes placed within ‘orgone accumulators’. Experimental
Aetherometry, 2001; 1.
10) Nelson, R. D., Bradish, G. J., Dobyns, Y. H., Dunne, B. J., & Jahn, R. G. FieldREG anomalies in
group situations. Journal of Scientific Exploration, 1996; 10(1): 111-141.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
213
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
11) Jahn, R. G., Dunne, B. J., Nelson, R. D., Dobyns, Y. H., & Bradish, G. J. Correlations of random
binary sequences with pre-stated operator intention: A review of a 12-year program. Journal of Scientific
Exploration, 1997; 11(3): 345-367.
12) Radin, D. I., & Nelson, R. D. Meta-analysis of mind-matter interaction experiments: 1959-2000. In
Healing, Intention, and Energy Medicine (pp. 39-48). London: Harcourt Health Sciences, 2003.
13) Caswell, J. M., Collins, M. W. G., Vares, D. A. E., Juden-Kelly, L. M., & Persinger, M. A.
Gravitational and experimental electromagnetic contributions to cerebral effects upon deviations from
random number variations generated by electron tunneling. International Letters of Chemistry, Physics
and Astronomy, 2013; 11: 72-85.
14) Pippa, L., Manzoli, L., Corti, I., Congedo, G., Romanazzi, L., & Parruti, G. Functional capacity after
traditional Chinese medicine (qi gong) training in patients with chronic atrial fibrillation: A randomized
controlled trial. Preventive Cardiology, 2007; 10(1): 22-25.
15) Wang, Q., & Yao, S. Molecular basis for cold-intolerant yang-deficient constitution of traditional
Chinese medicine. The American Journal of Chinese Medicine, 2008; 36: 827.
16) Braud, W. G., & Schlitz, M. J. Consciousness interactions with remote biological systems:
Anomalous intentionality effects. Subtle Energies & Energy Medicine, 1991; 2(1): 1-46.
17) Dossey, L. But is it energy? Reflections on consciousness, healing, and the new paradigm. Subtle
Energies & Energy Medicine, 1992; 3(3): 69-82.
18) Shiflett, S. C., Nayak, S., Bid, C., Miles, P., & Agostinelli, S. Effect of Reiki treatments on functional
recovery in patients in poststroke rehabilitation: A pilot study. The Journal of Alternative and
Complementary Medicine, 2004; 8(6): 755-763.
19) Dunne, B. J., & Jahn, R. G. Consciousness, information, and living systems. Cellular and Molecular
Biology, 2005; 51: 703-714.
20) Persinger, M. A., Koren, S. A., & Lafreniere, G. F. A neuroquantologic approach to how human
thought might affect the universe. NeuroQuantology, 2008; 6(3): 262-271.
21) Nelson, R. D. Coherent consciousness and reduced randomness: Correlations on September 11,
2001. Journal of Scientific Exploration, 2002; 16(4): 549-570.
22) Nelson, R. D., Jahn, R. G., Dunne, B. J., Dobyns, Y. H., & Bradish, G. J. FieldREG II: Consciousness
field effects: Replications and explorations. Journal of Scientific Exploration, 1998; 12(3): 425-454.
23) Mason, L. I., Patterson, R. P., & Radin, D. I. Exploratory study: The random number generator and
group meditation. Journal of Scientific Exploration, 2007; 21(2): 295-317.
24) Radin, D. I. Electrodermal presentiments of future emotions. Journal of Scientific Exploration, 2004;
18(2): 253-273.
25) Radin, D. I., & Schlitz, M. J. Gut feelings, intuition, and emotions: An exploratory study. The Journal
of Alternative and Complementary Medicine, 2005; 11(1): 85-91.
26) Bem, D. J. Feeling the future: Experimental evidence for anomalous retroactive influences on
cognition and affect. Journal of Personality and Social Psychology, 2011; 100(3): 407-425.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 195-214
214
Caswell, J. M., Gaona, J. M., Vares, D. A. E., Lapointe, A., Burke, R. C. & Tessaro, L. W. E.., The Potential Effects of Human Group
Emotion and Subjective Novelty on the Statistical Behaviour of a Random Event Generator: Exploratory Study
27) Helfrich, W. Is the psychokinetic effect as found with binary random number generators suitable to
account for mind-brain interaction. Journal of Scientific Exploration, 2007; 21(4): 689-705.
28) Pribram, K. H., Nuwer, M., & Baron, R. The holographic hypothesis of memory structure in brain
function and perception. Contemporary Developments in Mathematical Psychology, 1974; 2: 416-457.
29) Cheng-Yu, T. L., Poo, M. M., & Dan, Y. Burst spiking of a single cortical neuron modifies global
brain state. Science, 2009; 324(5927): 643-646.
30) Persinger, M., Saroka, K., Lavallee, C., Booth, J., Hunter, M., Mulligan, B., Koren, S., Wu, H. P., &
Gang, N. Correlated cerebral events between physically and sensory isolated pairs of subjects exposed to
yoked circumcerebral magnetic fields. Neuroscience Letters, 2010; 486(3): 231-234.
31) Dotta, B., Saroka, K., & Persinger, M. A. Increased photon emission from the head while imagining
light in the dark is correlated with changes in electroencephalographic power: Support for Bokkon’s
biophoton hypothesis. Neuroscience Letters, 2012; 513(2): 151-154.
32) Caswell, J. M., Dotta, B. T., & Persinger, M. A. Cerebral biophoton emission as a potential factor in
non-local human-machine interaction. Neuroquantology, 2014; in press.
33) Persinger, M. 10-20 Joules as a neuromolecular quantum in medicinal chemistry: An alternative
approach to myriad molecular pathways. Current Medicinal Chemistry, 2010; 17(27): 3094-3098.
34) Hatfield, E., & Cacioppo, J. T. Emotional Contagion. Cambridge University Press, 1994.
35) Barsade, S. G. The ripple effect: Emotional contagion and its influence on group behavior.
Administrative Science Quarterly, 2002; 47(4): 644-675.
36) Amoroso, R. L. An introduction to noetic field theory: The quantization of mind. Noetic Journal,
1999; 2(1): 28-37.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
597
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 597-600
Kaufman, S. E., The Flow of Being & the Creation of Suffering
Realization
The Flow of Being & the Creation of Suffering
Steven E. Kaufman*
ABSTRACT
By clinging to and resisting the forms, the experiences, that arise within our Consciousness, we
unconsciously Flow our Consciousness in opposition to Itself, and in so doing we provide
resistance to our own Flow of Consciousness, thereby reducing that Flow of Consciousness,
which reduction in Flow of Consciousness is apprehended by the Consciousness that is reducing
its own Flow as suffering, as the self-induced constriction and seeming suffocation and of its
own Being. The reactive clinging to and resistance of the forms, the experiences, that arise
within Consciousness, occurs as a result of formless Consciousness misidentifying Itself with
forms that also arise within Itself, causing Consciousness to know itself as what is really nothing
more than a collection of forms, which collection of forms is collectively referred to as the ego.
Once form-identification is established, i.e., once Consciousness knows itself as an ego, as a me,
it then seems that other forms can be added to or subtracted from the collection of forms that
Consciousness mistakenly knows as itself, thereby establishing the basis for the reactive
movements of attachment and aversion, for our reactive clinging to and resisting of form, by
which reactive movements we unconsciously Flow our Consciousness in opposition to Itself and
so unconsciously create our own suffering.
Key Words: flow, being, Consciousness, resistance, suffering.
I am through living as a slave to external circumstances. Feeling good when good things happen,
feeling bad when bad things happen. I do not control when good things happen, nor do I control
when bad things happen. Things just happen.
I may create the illusion that I control when things happen, as I am able to pick up an object and
move it from here to there, but even this is only an illusion. For when things happen, good or
bad, the cooperation of the entire universe is needed, since everything is connected, and surely
even I, with my enormous ego, cannot be so deluded as to think that I control the entire universe.
And so if I do not really control when things happen, then what is the point of being happy when
good things happen, as if my team has won, and being unhappy when bad things happen, as if
my team has lost? Things just happen. What-Is is as It Is.
There is no team me and team them, no me versus the universe, or me versus them, or me versus
whoever, to win or lose. There is only Team Universe, Team Being, and everything and
everyone is on that team, whether it seems so or not, whether they seem to be with me or against
*Correspondence: Steven E. Kaufman, Independent Researcher. http://www.unifiedreality.com
E-mail: skaufman@unifiedreality.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
598
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 597-600
Kaufman, S. E., The Flow of Being & the Creation of Suffering
me in a given moment, helping me to score, helping me to get what I want, or preventing me
from scoring, preventing me from getting what I want.
Both wanted and unwanted are going to happen. That is just the way it is. That is just what is.
But suffering does not have to happen.
Suffering only happens when I see the universe as a contest of me versus it, where, according to
the rules of that game, that contest, I must then resist whatever happens that is unwanted, in order
to make room for the wanted, and cling to whatever happens that is wanted, in order to not make
room for the unwanted.
For in resisting whatever happens that is unwanted, and clinging to whatever happens that is
wanted, I am in a state of almost perpetual opposition to What-Is, which state of opposition to
What-Is, by its nature, is a state of suffering.
In opposing What-Is I pinch myself off from the Flow of what I truly Am. It is not coincidence
that the words suffering and suffocation are similar. Suffocation occurs when the flow of air is
cut off or decreased significantly to the organism. Suffering occurs when the Flow of Being is
decreased to the Being.
But how can the Flow of Being be decreased to the Being? How is the flow of water decreased
when the source of that flow remains full? Through some sort of resistance to the flow that is
coming from the source.
Only Being can resist the Flow of Being. And Being that resists the Flow of Being, and thereby
decreases the Flow of Being to Itself, suffers, as the Flow of Is-ness, the Flow of Beingness to
Itself, to its Being, is reduced.
Consider a river, and from that river flow outward many tributaries, many smaller rivers. The
flow of those smaller rivers is dependent on the flow of the larger river, for the flow of those
smaller rivers is but an extension of the flow of the larger river.
Now consider that one of the smaller rivers, for some reason, is able to turn its flow back upon
its source, so that its direction of flow is now in opposition to the direction of flow coming from
its own source. In opposing the flow of its own source, in resisting the flow coming from its
own source, the smaller river, without meaning to, reduces its own flow. In a smaller river we
would see this self-induced reduction of flow as the smaller river beginning to dry up.
As Consciousness, we feel such a self-induced reduction of Flow as suffering, as the feeling of
being more or less cut off from our true or larger Self.
Our own Flow of Consciousness, directed in opposition to what is also our own Flow of
Consciousness, provides resistance to that Flow of Consciousness, thereby reducing that Flow of
Consciousness, which reduction in Flow of Consciousness is apprehended by the Consciousness
that is reducing its own Flow as suffering, i.e., as the self-induced suffocation of its own Being.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
599
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 597-600
Kaufman, S. E., The Flow of Being & the Creation of Suffering
Amazing. Why would I ever undertake such folly?
Because I think I am a me, a form, which idea places me in conflict and competition with other
forms for the acquisition of wanted forms to add to and protect the me, the form, I mistakenly
think I am. Therefore, I feel obligated to cling to what is, when what is appears as something
wanted, i.e., as a wanted form, that in its wantedness is seen as something that can be added to
the form that I mistakenly know myself to be.
And also because, in thinking that I am a me, a form, it also seems that unwanted forms can be a
threat to the existence, to the ongoingness, of the form that I mistakenly know myself to be.
Therefore, I feel obligated to resist what is, when what is appears as something unwanted, i.e., as
an unwanted form, that in its unwantedness is seen as something that can subtract from the form
that I mistakenly know myself to be.
Knowing myself as a me, as a form, I do not realize that clinging to or resisting what is,
presented in the form of wanted and unwanted experiences, actually places me in opposition to
what I actually Am. Knowing myself as a me, as a form, I do not realize that I am creating the
deep suffering, the suffocation of Being, that accompanies my reactive and reflexive clinging to
the wanted and resistance to the unwanted.
Knowing myself as a me, as a form, and so not realizing that I am creating the suffering I
feel, that suffering then seems to come from and be a part of either the wantedness that I am
clinging to or the unwantedness that I am resisting, causing me then to redouble my efforts at
either clinging to that which is wanted or resisting that which is unwanted, thereby increasing my
suffering and so increasing the seeming need to cling to and resist what is in a futile and
counterproductive effort to abate the suffering that those mostly unconscious and reflexive
actions are themselves unknowingly creating.
This is the insanity that is, for the ego, for the form-identity, for a me, normal behavior. In its
own way it is a beautiful thing when observed from a position of detachment, beyond the ego.
But while cloaked in the ego, i.e., trapped in form-identity where the process remains hidden,
there seems to be only the continued obligation to cling to the wanted and resist the unwanted,
and the suffering those actions create, since those actions actually cause Consciousness to Flow
in opposition to Itself.
On the other hand, Knowing myself as the River, the ideas that ultimately lead me to oppose the
Flow of my own Being, i.e., the seeming need to cling to experiences that are wanted and resist
experiences that are unwanted, simply do not arise. For how can form seem to be added to or
subtracted from That which Knows Itself to be Formless? Put another way, how can That which
Knows Itself to be Formless see Itself as being added to or subtracted from? In both cases, It
cannot, and so the movements of attachment and aversion, i.e., the movements of Consciousness
as It either clings to or resists some form, do not arise.
Here it is interesting to note that what, on the surface, i.e., at the level of form, appear to be
opposite movements of Consciousness, i.e., the movements of attachment and aversion, the
movement of clinging to and resisting form, are beneath the surface, at the level of What-Is, at
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
600
Journal of Consciousness Exploration & Research | August 2014 | Volume 5 | Issue 6 | pp. 597-600
Kaufman, S. E., The Flow of Being & the Creation of Suffering
the level of the Formless, actually the same Movement, i.e., the Movement or Flow of
Consciousness in opposition to Itself.
Thus, it is not circumstances that create the seeming suffocation and constriction of one's very
Being that is suffering; rather, it is attachment and aversion to circumstances that actually creates
suffering. And what creates attachment and aversion to circumstances is the identification of
Consciousness with form, or more specifically, with the collection of thought-forms collectively
referred to as the ego.
Ultimately then, what creates suffering is the misidentification of Consciousness with something
that It has created within Itself, with a collection of thought-forms that arise within Itself, which
misidentification then sets into motion a self-perpetuating chain of unconscious and reflexive
conditioning that seems to obligate what I mistakenly think of as me to cling to and resist other
forms that arise within my Consciousness, which clinging to and resisting of those forms then
perpetuates the delusion of form-identity that creates that apparent obligation, by hiding from
that I my Nature as formless Consciousness as long as I, cloaked in the ego, continue to
unconsciously Flow my Being in opposition to what is ultimately my true Self by means of my
clinging to and resisting various forms, by means of my clinging to and resisting what is.
It is a very sticky wicket indeed.
However, all that is required in order to break this self-perpetuating chain of unconscious and
reflexive conditioning that keeps what I truly Am hidden from my true Self is the sight
adjustment of ceasing to cling to and resist the forms of which I become Aware, i.e., the
experiences which arise in what seems to be my Consciousness.
For in ceasing to cling to and resist the forms, the experiences, that arise in what seems to be my
Consciousness, in ceasing the reactive surface movement, the deeper unconscious Movement
that is the Flow of what seems to be my Consciousness in opposition to Itself also ceases, which
cessation of Self-opposition provides an opening for Consciousness to reveal Itself to Itself, not
as a concept, not as a form, but directly as the Formlessness within which all forms arise and by
which all forms are apprehended, at which point what seems to be my Consciousness simply
becomes Consciousness, simply becomes What-Is.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Keywords: Consciousness, Time, AI, Relativity, Quantum Mechanics, Reality, Responsible AI
Unifying Consciousness and Time to Enhance Artificial
Intelligence
Mahendra Samarawickramaa)
Centre for Consciousness Studies, Australia
arXiv:2301.08742v1 [q-bio.NC] 10 Jan 2023
a) samarawickrama@gmail.com
Abstract. Consciousness is a sequential process of awareness which can focus on one piece of information at a time. This process
of awareness experiences causation which underpins the notion of time while it interplays with matter and energy, forming reality.
The study of Consciousness, time and reality is complex and evolving fast in many fields, including metaphysics and fundamental
physics. Reality composes patterns in human Consciousness in response to the regularities in nature. These regularities could be
physical (e.g., astronomical, environmental), biological, chemical, mental, social, etc. The patterns that emerged in Consciousness
were correlated to the environment, life and social behaviours followed by constructed frameworks, systems and structures. The
complex constructs evolved as cultures, customs, norms and values, which created a diverse society. In the evolution of responsible
AI, it is important to be attuned to the evolved cultural, ethical and moral values through Consciousness. This requires the advocated
design of self-learning AI aware of time perception and human ethics.
INTRODUCTION
The notion of time is an integral part of consciousness [1]. The consciousness experiences the causation or changes in
reality/environment and perceives the time. Therefore, in our previous publication [2], we assumed that consciousness
is a sequential process which is aware of a single piece of information at a time. Even though the brain processes sensory data of five sensors (i.e., Sight, Sound, Smell, Taste, and Touch) in parallel in the neural network, the awareness
of causation is a sequential process following cause and effect. See the illustration of this idea in Figure 1,
5 Senses to observe the
external world
(Peripherals)
Brain function
which manages the
5 senses and the memory
(Parallel processing
neural network: operating in
low frequency)
Consciousness
(Sequential processing of
information:
Electromagnetic energy
operating in very high
frequency, which
can exhibit properties
of both waves and particles.)
Awareness and
Reality
FIGURE 1: The interplay of five sensors, brain and consciousness. The brain processes sensory information in
parallel. However, the awareness of causation (i.e., consciousness) is a sequential process focusing on a single piece
of information at a time. This sequential process of awareness in consciousness operates fast and consistently, which
underpins our perception of reality.
The assumption of sequential awareness in consciousness enables mapping the perception of time into consciousness. Based on the theory of relativity [3], the perception of time is relative to the frame of reference. Einstein
assumed that the speed of light is constant in all frames of reference, and the time is derived based on that fundamental assumption. In our paper, we defined the shortest time to be aware of reality as a consciousness cycle. Then based
on relativity, this consciousness cycle is also subjected to dilation, like relativistic time
T0
,
Tv = q
2
1 − vc2
(1)
where, Tq
v is the dilated period of the consciousness cycle related to the rest period of the consciousness cycle T0 . Note
2
that the 1 − vc2 is the Lorentz factor, where v is the relative velocity between inertial reference frames, and c is the
speed of light in a vacuum. Then, we mathematically modelled [2] how consciousness would interplay with matter
and energy, forming reality, which can be adapted to understand limitations and opportunities in AI consciousness.
This paper extends our discussion towards the time perception of artificial intelligence systems (AIS).
THE NOTION OF TIME IN PERCEPTION AND REALITY
Humans, like any other life forms, experience time through causation. Patterns are composed in the human consciousness in response to the regularities in nature [4]. Since the beginning of human civilisation, humans have learnt and
evolved complex concepts and constructs by incorporating time emerged through patterns in the consciousness. The
earth’s rotation around itself determines the day, and orbiting around the sun determines the year. The Moon takes
about one month to orbit the earth. The tilt of the earth’s spin axis with respect to its orbital plane causes the weather
seasons. These environmental patterns cause many biological patterns and lifestyle patterns in human life. To predict and organise these patterns effectively, humans introduce standard time with clocks, calendars and various other
frameworks. These artificial frameworks enable us to model time and objectively measure subjective experiences.
Physics has been evolved by observation of nature with various frameworks of time. In this way, time became
an essential construct and dimension of our understanding of reality. For example, Newtonian physics [5] evolved
assuming that time is absolute and flows consistently from past to present and into the future. That enables the
development of mathematical models for explaining patterns in reality with time. However, later observations, such
as the perihelion motion of Mercury, allow humans to understand time as a relativistic measure rather than an absolute.
The modern understanding of the universe is based on the theory of relativity [6, 7], which is completely articulated
by space-time principles. Based on relativity, John Wheeler [8] stated, “Space tells matter how to move. Matter
tells space how to curve”. Relativity enables us to accurately understand and predict the behaviours of black holes,
stars, and planets. Further, relativity enables humans to develop technologies like the atomic clock [9] and Global
Positioning System (GPS) [10] that are useful in everyday life.
The behaviour of particles is completely different to larger objects like planets, stars, etc. This led to the evolution
of Quantum physics [11] as opposed to relativity. Quantum physics exhibits amazing accuracy in predicted results in
particle physics. However, it greatly disturbs the notion of time modelled in relativity. For example, in the collapse
of the wave function in quantum entanglement, Einstein described that as a spooky action at a distance [12]. As
per relativity, information cannot transfer faster than the speed of light. As per the recent discoveries in quantum
entanglement, information can be transferred instantly, faster than the speed of light, making our reality non-local
[13]. The non-local reality contradicts relativity, which is now applied in quantum teleportation at the subatomic
level. On the other hand, at the quantum level, the reality is uncertain, as described by Heisenberg’s uncertainty
principle [14]. As per the uncertainty principle, it is impossible to precisely measure or be aware of the position and
speed of a particle in a given time. This brings the limitation of human awareness and perception of time. Therefore,
many believe now that consciousness is fundamental and that time and causation are derived from consciousness [15].
THE IMPLICATION OF PRINCIPLES OF TIME FOR AIS
The inability to consolidate quantum physics and the theory of relativity makes our understanding of reality incomplete. Moreover, the new discoveries proving the idea of non-local reality shake the status quo of fundamental physics
[16]. Therefore, it is still impossible to supervise AI to experience the notion of time to understand reality precisely.
On the other hand, human understanding of reality is also about 5%, whereas most of the universe consists of dark
matter and dark energy, which humans do not understand [17]. Under these conditions, AI might be used to explore
reality and time in a way we have never imagined. Perhaps incorporating AI to understand reality and causation might
help humans to become fully aware of reality by overcoming inherent biases from evolution, culture and nature.
Typical Reinforcement Learning (RL) technique can be adapted to automate the learning of AI. The RL process
can be mathematically formulated using Markov Decision Process (MDP) [18]. That is a sequential learning process
by trial and error. In this process, the learning agent (i.e., AI) sequentially interacts with the environment with an
intelligent decision (i.e. action) followed by receiving a reward or a penalty based on the policy imposed. There will
be no influence on the AI agent’s action, but convey the value of its action through feedback with reward or penalty.
This way, the AI agent will self-learn about the environment over time. The RL process is illustrated in Figure 2:
Agent
State
St
Reward
Rt
Action
At
Rt+1
St+1
Environment
FIGURE 2: Components of the Markov Decision Process (MDP) and its function in the agent-environment
interaction. The sequential step of time is represented by t.
THE IMPLICATION OF HUMAN BELIEFS, VALUES AND CULTURES FOR THE
PERCEPTION OF TIME IN AIS
Human beliefs, customs, culture and values are tightly linked with various dynamics and interpretations of the time
and periodicities based on the movement of the earth, Moon and other terrestrial bodies. From the beginning, humans
identified that time affects life and nature differently. Therefore, in the Greece era, early Western culture, there were
at least three gods representing different time forms: Chronos, Aion, and Kairos [19]. Chronos represented the linear
time flowing from past to present into the future. This is the time that humans feel when life passes. In contrast, Aion
represented the cyclical nature of time experienced from natural events such as weather patterns, rebirths, etc. The
third god Kairos represented the opportunist time, which reflects the appropriate time to achieve a task. In this way,
time, environment and beliefs were tightly linked with life and governed society and values.
On the other hand, in Eastern culture, the horoscope is one good example of a planetary and constellation framework underpinning Astrology as a foundation of certain belief systems [20]. These beliefs assume that Astrology is
associated with time and causality, which can predict the future and guide humans.
The human observation of the night sky led to perceiving time from various cyclical patterns going far back in time.
For example, the Aboriginal Australians [21] observed the night sky and mapped them to the environment and life
stages that evolved various customs, arts and even religions. Not only by interacting planets and stars but the tilt of
the earth’s spin axis also significantly led to diversifying human cultures based on seasons, particularly when moving
away from the equator.
The notion of time and associated beliefs, customs, and values are important to consider when training AIS [22].
That will help promote human cultural values, ethics, and diversity, equity and inclusion (DEI). AI development may
need to pay attention to and integrate the time attributes that emerged from nature, values and cultures. Humans may
include them in the policies for rewarding self-learning AI algorithms (e.g., in MDP).
THE IMPLICATION OF BIOLOGICAL TIME ON AIS
The biological cycles play a fundamental role in human behaviours and the perception of time—for example, mood
cycles, circadian rhythms, and the menstrual cycle. Without understanding these biological time-keeping processes,
AI cannot seamlessly integrate with human society when creating values in health, culture, art, etc. These insights
are essential to realising emotional intelligence, empathy and awareness in AI. Literature shows the effective use of
Cyclic Hidden Markov Models (CyH-MMs) for detecting and modelling cycles in a multidimensional heterogeneous
biological time series data collection [23]. It is important to attribute the relevant features of biological processes
when training AIS, which raises more awareness about humans.
Recent discoveries in quantum physics argue that our reality is non-local, where awareness can happen instantly,
faster than the speed of light. Physicists and neurologists think brain neurons might be aware of the quantum world
through the orchestrated collapse of microtubules in the neurons in the brain [24, 25]. If this hypothesis is true, then
there are possibilities that human awareness can be linked with non-local realities to expand our consciousness across
the universe instantly. From this perspective, future AI might need to be evolved with the capabilities of biological
neurons, which interplay with the quantum realities. The recent development of neurotech realising brain-computer
interface (BCI) along with emerging quantum computers might enable such capabilities in the near future [26].
CONCLUSION
Consciousness and perception of time and causation are key to awareness and understanding reality. The notion of
time emerged from causation, a perception relative to the observer as per the relativity principles. In relativity, it’s
not time but the light-speed constant in all frames of reference. In contrast, in quantum entanglement, the reality is
non-local, and information can be transferred instantly faster than light. While the principles of time contradict the
foundation of physics, time also influenced the formation of diverse customs, values and cultures based on patterns
that emerged from nature, particularly around the regularities in the earth’s movement, environment, astronomy and
biology. Therefore, understanding time and related artefacts (i.e., cultures, beliefs, values, customs, physics, health,
etc.) are very important to realise deep awareness of reality. From the AIS perspective, it will enhance the understanding of AI in human health, cultures, customs, values and various other diversities. Bringing this awareness to AI will
be a challenging and complex yet rewarding milestone in the evolution of ethical and responsible AI.
REFERENCES
1. L. Kent and M. Wittmann, “Erratum to: Time consciousness: the missing link in theories of consciousness,” Neuroscience of Consciousness,
vol. 2021, 05 2021.
2. M. Samarawickrama, “Unifying Matter, Energy and Consciousness,” International Conference on Mathematical Modeling in the Physical
Sciences (IC-MSQUARE), 9 2022. https://youtu.be/Pby1TfEluqE.
3. A. Einstein, “Zur Elektrodynamik bewegter Körper. (German) [On the electrodynamics of moving bodies],” Annalen der Physik, vol. 322,
no. 10, pp. 891–921, 1905.
4. S. Blackburn, “Hume and thick connexions,” Philosophy and Phenomenological Research, vol. 50, pp. 237–250, 1990.
5. I. Newton, Philosophiae Naturalis Principia Mathematica. London: Royal Society, 1687.
6. A. Einstein, “Zur allgemeinen Relativitätstheorie. (German) [Toward a General Theory of Relativity],” j-S-B-PREUSS-AKAD-WISS-2,
pp. 778–786, 799–801, 1915.
7. A. Einstein, “Erklärung der Perihelbewegung des Merkur aus der allgemeinen Relativitätstheorie. (German) [Explanation of the perihelical
motion of Mercury from the General Theory of Relativity],” j-S-B-PREUSS-AKAD-WISS-2, pp. 831–839, 1915.
8. J. A. Wheeler, “Geometrodynamics and the Problem of Motion,” Reviews of Modern Physics, vol. 33, pp. 63–78, Jan 1961.
9. N. F. Ramsey, “History of early atomic clocks,” Metrologia, vol. 42, p. S1, jun 2005.
10. R. Maddison and C. N. Mhurchu, “Global positioning system: a new opportunity in physical activity measurement,” International Journal of
Behavioral Nutrition and Physical Activity, vol. 6, no. 1, p. 73, 2009.
11. P. A. Zyla et al. (Particle Data Group), “Review of Particle Physics,” Progress of Theoretical and Experimental Physics, vol. 2020, 08 2020.
083C01.
12. A. Einstein, B. Podolsky, and N. Rosen, “Can quantum-mechanical description of physical reality be considered complete?,” Phys. Rev.,
vol. 47, pp. 777–780, May 1935.
13. A. Lohrey and B. Boreham, “The nonlocal universe,” Communicative & Integrative Biology, vol. 13, no. 1, pp. 147–159, 2020.
14. W. Heisenberg, “Über den anschaulichen Inhalt der quantentheoretischen Kinematik und Mechanik. (German) [On the ideological content of
quantum theoretical kinematics and mechanics],” Z. Physik, vol. 43, pp. 172–198, Mar. 1927.
15. D. D. Hoffman,
“The Origin of Time In Conscious Agents,”
Cosmology,
vol. 18,
pp. 494–520,
2014.
https://www.cogsci.uci.edu/ ddhoff/HoffmanTime.pdf.
16. W. Sulis, “Locality Is Dead! Long Live Locality!,” Frontiers in Physics, vol. 8, 2020.
17. E. Oks, “Brief review of recent advances in understanding dark matter and dark energy,” New Astronomy Reviews, vol. 93, p. 101632, 2021.
18. M. van Otterlo and M. Wiering, “Reinforcement Learning and Markov Decision Processes,” Reinforcement Learning: State-of-the-Art, pp. 3–
42, 2012.
19. J. E. Smith, “Time, Times, and the ‘Right Time’; Chronos and Kairos,” The Monist, vol. 53, no. 1, pp. 1–13, 1969.
20. N. Campion, “Astrology as cultural astronomy,” Handbook of Archaeoastronomy and Ethnoastronomy, pp. 103–116, 2015.
21. D. W. Hamacher, “Comet and meteorite traditions of aboriginal australians,” Encyclopaedia of the History of Science, Technology, and
Medicine in Non-Western Cultures, pp. 1–4, 2008.
22. K. Lee and K. Joshi, “Understanding the Role of Cultural Context and User Interaction in Artificial Intelligence Based Systems,” Journal of
Global Information Technology Management, vol. 23, no. 3, pp. 171–175, 2020.
23. E. Pierson, T. Althoff, and J. Leskovec, “Modeling Individual Cyclic Variation in Human Behavior,” in Proceedings of the 2018 World Wide
Web Conference, p. 107–116, 2018.
24. S. Hameroff and R. Penrose, “Consciousness in the universe: A review of the ‘Orch OR’ theory,” Physics of Life Reviews, vol. 11, no. 1,
pp. 39–78, 2014.
25. S. Hameroff, “‘Orch OR’ is the most complete, and most easily falsifiable theory of consciousness,” Cognitive Neuroscience, vol. 12, no. 2,
pp. 74–76, 2021.
26. S. Saha, K. A. Mamun, K. Ahmed, R. Mostafa, G. R. Naik, S. Darvishi, A. H. Khandoker, and M. Baumert, “Progress in Brain Computer
Interface: Challenges and Opportunities,” Frontiers in Systems Neuroscience, vol. 15, Feb 2021. |
Version 4
Consciousness, cognition, and context: extending the global
neuronal workspace model
Rodrick Wallace
The New York State Psychiatric Institute
∗
January 21, 2004
Abstract
simulations... suggest the existence of a fluctuating
dynamic threshold. If the primary activation evoked
by a stimulus exceeds this threshold, reverberation
takes place and stimulus information gains access,
through the workspace, to a broad range of [other
brain] areas allowing, among other processes, verbal report, voluntary manipulation, voluntary action
and long-term memorization. Below this threshold, however, stimulus information remains unavailable to these processes. Thus the global neuronal
workspace theory predicts an all-or-nothing transition between conscious and unconscious perception... More generally, many non-linear dynamical
systems with self-amplification are characterized by
the presence of discontinuous transitions in internal
state...”
We adapt an information theory analysis of interacting cognitive biological and social modules to the problem of the global
neuronal workspace, the current standard neuroscience picture of consciousness. Tunable punctuation emerges in a natural manner, suggesting the possibility of fitting appropriate
phase transition power law, and, away from transition, generalized Onsager relation expressions, to observational data
on conscious reaction. The development can be extended in
a straightforward manner to include the role of psychosocial
stress, culture, or other embedding structured contexts in individual consciousness, producing a ‘biopsychosocial’ model
that closely retains the flavor of the standard treatment, but
better meets compelling philosophical and other objections to
brain-only descriptions.
Key words: asymptotic limit theorems, cognition, consciousness, Dretske, information theory, Onsager relations,
Parallel to this line of research, but without invocation of
phase transition, renormalization.
dynamic systems theory, is what Adams (2003) has characterized as ‘the informational turn in philosophy’, that is, the apIntroduction
plication of communication theory formalism and concepts to
A recent special issue of Cognition (79(1-2), 2001)) explores “purposive behavior, learning, pattern recognition, and... the
contemporary work on consciousness in humans, presenting naturalization of mind and meaning”. One of the first comvarious aspects of the new ‘standard model’ synthesized over prehensive attempts was that of Dretske (1981, 1988, 1992,
the last decade or so (esp. Dehaene and Naccache, 2001). 1993, 1994), whose work Adams describes as follows:
Sergeant and Dehaene (2004) describe that work, and some
of the implicit controversy, as follows:
“It is not uncommon to think that information
is a commodity generated by things with minds.
Let’s say that a naturalized account puts matters
the other way around, viz. it says that minds are
things that come into being by purely natural causal
means of exploiting the information in their environments. This is the approach of Dretske as he tried
consciously to unite the cognitive sciences around
the well-understood mathematical theory of communication...”
“[A growing body of empirical study shows] large
all-or-none changes in neural activity when a stimulus fails to be [consciously] reported as compared to
when it is reported... [A] qualitative difference between unconscious and conscious processing is generally expected by theories that view recurrent interactions between distant brain areas as a necessary condition for conscious perception... One
of these theories has proposed that consciousness
is associated with the interconnection of multiple
areas processing a stimulus by a [dynamic] ‘neuronal workspace’ within which recurrent connections allow long-distance communication and autoamplification of the activation. Neuronal network
Dretske himself (1994) writes:
“Communication theory can be interpreted as
telling one something important about the conditions that are needed for the transmission of information as ordinarily understood, about what it takes
for the transmission of semantic information. This
∗ Address correspondence to Rodrick Wallace, PISCS Inc., 549 W 123
St., Suite 16F, New York, NY, 10027. Telephone (212) 865-4766, email
rdwall@ix.netcom.com. Affiliation is for identification only.
1
has tempted people... to exploit [information theory] in semantic and cognitive studies, and thus in
the philosophy of mind.
...Unless there is a statistically reliable channel of
communication between [a source and a receiver]...
no signal can carry semantic information... [thus]
the channel over which the [semantic] signal arrives
[must satisfy] the appropriate statistical constraints
of communication theory.”
uations, relying on the robustness of the Central Limit Theorem to carry us through, we will pursue a similar heuristic
approach here.
Finally, we invoke an obvious homology between information source uncertainty and thermodynamic free energy density as justification for importing renormalization and generalized Onsager relation formalism to the study of cognitive process near and away from ‘critical points’ in the coupling of cognitive submodules. The question of whether we
are demonstrating the necessity of global phase transitions in
information-transmission networks or merely building a suggestive analogy with thermodynamics is an empirical one beyond our present ability to answer, although for the microscopic case, Feynman (1996) has shown that the homology
is an identity, which is no small matter and indeed suggests
that phase transition behavior should be ubiquitous for certain classes of information systems.
Our work is likely analogous, in a certain sense, to Bohr’s
treatment of the atom, which attempted a simple substitution of quantized angular momentum into a basically classical theory. Although incomplete, that analysis contributed
materially to the more comprehensive approaches of quantum mechanics, relativistic quantum mechanics, and quantum
electrodynamics. In that spirit we hope that increasingly satisfactory models will follow from what we do here.
We begin with a description of cognitive process in terms
of an information source, a kind of language constrained by
the Shannon-McMillan or Asymptotic Equipartition Theorem, and its Rate Distortion or Joint Asymptotic Equipartition and other variants for interacting sources.
Here we redirect attention from the informational content
or meaning of individual symbols, i.e. the province of semantics which so concerned Dretske, back to the statistical properties of long, internally-structured paths of symbols emitted by an information source. We will then import a variety
of tools from statistical physics to produce dynamically tunable punctuated or phase transition coupling between interacting cognitive modules in what we claim is a highly natural manner. As Dretske so clearly saw, this approach allows scientific inference on the necessary conditions for cognition, and, we will show, greatly illuminates dynamic neuronal
workspace models of consciousness without raising the 18th
Century ghosts of noisy, distorted mechanical clocks inherent
to dynamic systems theory. It also opens the way for an extended dynamic workspace model which includes the effects
of other interacting cognitive modules or embedding contexts
that may, although acting at slower timescales, profoundly affect individual consciousness. This extension meets profound
objections to brain-only models, for example those of Bennett and Hacker (2003), which we will consider in more detail
below.
Before entering the formal thicket, it is important to highlight several points.
First, information theory is notorious for providing existence theorems whose representation, to use physics jargon,
is arduous. For example, although the Shannon Coding Theorem implied the possibility of highly efficient coding schemes
as early as 1949, it took more than forty years for practical
‘turbo codes’ to actually be constructed. The research program we implicitly propose here is unlikely to be any less
difficult.
Second, we are invoking information theory variants of the
fundamental limit theorems of probability. These are independent of exact mechanisms, but constrain the behavior of
those mechanisms. For example, although not all processes
involve long sums of independent stochastic variables, those
that do, regardless of the individual variable distribution, collectively follow a Normal distribution as a consequence of the
Central Limit Theorem. Similarly, the games of chance in
a Las Vegas casino are all quite different, but nonetheless
the success of strategies for playing them is strongly and systematically constrained by the Martingale Theorem, regardless of game details. We similarly propose that languageson-networks and languages-that-interact, as a consequence of
the limit theorems of information theory, will inherently be
subject to regularities of tunable punctuation and generalized Onsager relations, regardless of detailed mechanisms, as
important as the latter may be.
Just as parametric statistics are imposed, at least as a first
approximation, on sometimes questionable experimental sit-
Cognition as language
Atlan and Cohen (1998) and Cohen (2000), following a long
tradition in the study of immune cognition (e.g., Grossman,
1989; Tauber, 1998), argue that the essence of cognitive function involves comparison of a perceived signal with an internal, learned picture of the world, and then, upon that comparison, the choice of a response from a much larger repertoire of
possible responses. Following the approach of Wallace (2000,
2002a), we make a ‘weak’, and hence very general, model of
that process.
Cognitive pattern recognition-and-response, as we characterize it, proceeds by convoluting an incoming external sensory incoming signal with an internal ongoing activity – the
learned picture of the world – and triggering an appropriate
action based on a decision that the pattern of sensory activity requires a response. We will, fulfilling Atlan and Cohen’s
(1998) criterion of meaning-from-response, define a language’s
contextual meaning entirely in terms of system output, leaving out, for the moment, the question of how such a pattern
recognition system is trained, a matter for Rate Distortion
theory.
The abstract model will be illustrated by two neural network examples.
A pattern of sensory input is mixed in some unspecified but
systematic manner with internal ‘ongoing’ activity to create
a path of convoluted signal x = (a0 , a1 , ..., an , ...). This path
is fed into a highly nonlinear, but otherwise similarly unspecified, decision oscillator which generates an output h(x) that
2
The Shannon uncertainties H(...)Pare defined in terms of
is an element of one of two (presumably) disjoint sets B0 and
cross-sectional sums of the form − k Pk log[Pk ], where the
B1 of possible system responses. We take
Pk constitute a probability distribution. See Ash (1990) or
B0 ≡ b0 , ..., bk ,
Cover and Thomas (1991) for details.
We say this information source is dual to the ergodic cognitive process.
B1 ≡ bk+1 , ..., bm .
Again, for non-ergodic sources, a limit limn→∞ H may be
defined for each path, but it will not necessarily given by
Thus we permit a graded response, supposing that if
the simple cross-sectional law-of-large numbers analogs above.
For ‘nearly’ ergodic systems one might perhaps use something
h(x) ∈ B0
of the form
the pattern is not recognized, and if
H(x + δx) ≈ H(x) + δxdH/dx.
h(x) ∈ B1
Different language-analogs will, of course, be defined by
different divisions of the total universe of possible responses
into different pairs of sets B0 and B1 , or by requiring more
than one response in B1 along a path. However, like the use of
different distortion measures in the Rate Distortion Theorem
(e.g. Cover and Thomas, 1991), it seems obvious that the
underlying dynamics will all be qualitatively similar.
Similar but not identical, and herein lies the first of two
essential matters: dividing the full set of possible responses
into sets B0 and B1 may itself require higher order cognitive
decisions by another module or modules, suggesting the necessity of ‘choice’ within a more or less broad set of possible
languages-of-thought. This would, in one way, reflect the need
of the organism to shift gears according to the different challenges it faces, leading to a model for autocognitive disease
when a normally excited state is recurrently (and incorrectly)
identified as a member of the ‘resting’ set B0 .
A second possible source of structure, however, lies at the
input rather than the output end of the model: i.e. suppose we classify paths instead of outputs. That is, we define
equivalence classes in convolutional ‘path space’ according to
whether a state aM
k can be connected by a path with some
originating state aM . That is, we, in turn, set each possible
state to an a0 , and define other states as formally equivalent to it if they can be reached from that (now variable)
a0 = aM by a grammatical/syntactical path. That is, a state
which can be reached by a legitimate path from aM is taken
as equivalent to it. We can thus divide path space into (ordinarily) disjoint sets of equivalence classes. Each equivalence
class defines its own language-of-thought: disjoint cognitive
modules, possibly associated with an embedding equivalence
class algebra.
While meaningful paths – creating an inherent grammar
and syntax – are defined entirely in terms of system response,
as Atlan and Cohen (1998) propose, a critical task is to make
these (relatively) disjoint cognitive modules interact, and to
examine the effects of that interaction on global properties.
Punctuated phase transition effects will emerge in a natural
manner.
Before proceeding, however, we give two explicit neural network applications.
First the simple stochastic neuron: A series of inputs yij , i =
1...m from m nearby neurons at time j is convoluted with
‘weights’ wij , i = 1...m, using an inner product
the pattern is recognized and some action bj , k + 1 ≤ j ≤ m
takes place.
We are interested in paths x which trigger pattern
recognition-and-response exactly once. That is, given a fixed
initial state a0 , such that h(a0 ) ∈ B0 , we examine all possible subsequent paths x beginning with a0 and leading exactly
once to the event h(x) ∈ B1 . Thus h(a0 , ..., aj ) ∈ B0 for all
j < m, but h(a0 , ..., am ) ∈ B1 .
For each positive integer n let N (n) be the number of
paths of length n which begin with some particular a0 having
h(a0 ) ∈ B0 and lead to the condition h(x) ∈ B1 . We shall
call such paths ‘meaningful’ and assume N (n) to be considerably less than the number of all possible paths of length n
– pattern recognition-and-response is comparatively rare. We
further assume that the finite limit
H ≡ lim
n→∞
log[N (n)]
n
both exists and is independent of the path x. We will –
not surprisingly – call such a pattern recognition-and-response
cognitive process ergodic. Not all such processes are likely to
be ergodic, implying that H, if it exists, is path dependent,
although extension to ‘nearly’ ergodic processes is straightforward.
Invoking Shannon, we may thus define an ergodic information source X associated with stochastic variates Xj
having joint and conditional probabilities P (a0 , ..., an ) and
P (an |a0 , ..., an−1 ) such that appropriate joint and conditional
Shannon uncertainties may be defined which satisfy the relations
H[X] = lim
n→∞
log[N (n)]
=
n
lim H(Xn |X0 , ..., Xn−1 ) =
n→∞
lim
n→∞
H(X0 , ..., Xn )
.
n
(1)
aj = yj · wj =
m
X
yij wij
i=1
3
in the context of a ‘transfer function’ f (yj ·wj ) such that the
probability of the neuron firing and having a discrete output
z j = 1 is P (z j = 1) = f (yj · wj ). Thus the probability that
the neuron does not fire at time j is 1 − f (yj · wj ).
In the terminology of this section the m values yij constitute
‘sensory activity’ and the m weights wij the ‘ongoing activity’
at time j, with aj = yj · wj and x = a0 , a1 , ...an , ...
A little more work leads to a fairly standard neural network
model in which the network is trained by appropriately varying the w through least squares or other error minimization
feedback. This can be shown to, essentially, replicate rate
distortion arguments (Cover and Thomas, 1991), as we can
use the error definition to define a distortion function d(y, ŷ)
which measures the difference between the training pattern y
and the network output ŷ as a function of, for example, the
inverse number of training cycles, K. As discussed in some
detail elsewhere (Wallace, 2002), learning plateau behavior
follows as a phase transition on the parameter K in the mutual information I(Y, Ŷ ).
Park et al. (2000) treat the stochastic neural network
in terms of a space of related probability density functions
[p(x, y; w)|w ∈ Rm ], where x is the input, y the output and
w the parameter vector. The goal of learning is to find an optimum w∗ which maximizes the log likelihood function. They
define a loss function of learning as
the most part, closely track changes in K(t), so that along a
particular ‘piece’ of a path in parameter space the information source remains as close to memoryless and ergodic as is
needed for the mathematics to work. Between pieces, below,
we will impose phase transition characterized by a renormalization symmetry, in the sense of Wilson (1971).
We will call such an information source ‘adiabatically piecewise memoryless ergodic’ (APME).
To anticipate the argument, iterating the analysis on paths
of ‘tuned’ sets of renormalization parameters gives a second
order punctuation in the rate at which primary interacting information sources representing cognitive submodules become
linked to each other: the shifting workspace structure of consciousness.
Interacting cognitive modules
We suppose that a two (relatively) distinct cognitive submodules can be represented by two distinct sequences of
states, the paths x ≡ x0 , x1 , ... and y ≡ y0 , y1 , .... These
paths are, however, both very highly structured and serially correlated and have dual information sources X and Y.
Since the modules, in reality, interact through some kind
of endless back-and-forth mutual crosstalk, these sequences
of states are not independent, but are jointly serially correlated. We can, then, define a path of sequential pairs as
z ≡ (x0 , y0 ), (x1 , y1 ), .... The essential content of the Joint
Asymptotic Equipartition Theorem (JAEPT), a variant of the
Shannon-McMillan Theorem, is that the set of joint paths z
can be partitioned into a relatively small set of high probability termed jointly typical, and a much larger set of vanishingly
small probability. Further, according to the JAEPT, the splitting criterion between high and low probability sets of pairs
is the mutual information
L(x, y; w) ≡ − log p(x, y; w),
and one can take as a learning paradigm the gradient relation
wt+1 = wt − ηt ∂L(x, y; w)/∂w,
where ηt is a learning rate.
Park et al. (2000) attack this optimization problem by
I(X, Y ) = H(X) − H(X|Y ) = H(X) + H(Y ) − H(X, Y )
recognizing that the space of p(x, y; w) is Riemannian with a
metric given by the Fisher information matrix
where H(X), H(Y ), H(X|Y ) and H(X, Y ) are, respecZ Z
tively,
the (cross-sectional) Shannon uncertainties of X and
T
G(w) =
∂ log p/∂w[∂ log p/∂w] p(x, y; w)dydx
Y , their conditional uncertainty, and their joint uncertainty.
See Cover and Thomas (1991) for mathematical details. Simwhere T is the transpose operation. A Fisher-efficient onilar approaches to neural process have been recently adopted
line estimator is then obtained by using the ‘natural’ gradient
by Dimitrov and Miller (2001).
algorithm
Note that, using this asymptotic limit theorem approach,
we need not model the exact form or dynamics of the crosstalk
−1
wt+1 = wt − ηt G ∂L(x, y; w)/∂w.
feedback, hence crushing algebraic complexities can be postAgain, through the synergistic family of probability distri- poned until a later stage of the argument. They will, however,
butions p(x, y; w), this can be viewed as a special case – a appear in due course with some vengeance.
The high probability pairs of paths are, in this formulation,
‘representation’, to use physics jargon – of the general ‘conall equiprobable, and if N (n) is the number of jointly typical
volution argument’ given above.
It seems likely that a rate distortion analysis of the inter- pairs of length n, then
action between training language and network response language will nonetheless show the ubiquity of learning plateaus,
even in this rather elegant special case.
We will eventually parametize the information source uncertainty of the dual information source with respect to one
or more variates, writing, e.g. H[K], where K ≡ (K1 , ..., Ks )
represents a vector in a parameter space. Let the vector K
follow some path in time, i.e. trace out a generalized line
or surface K(t). We will, following the argument of Wallace (2002b), assume that the probabilities defining H, for
I(X, Y ) = lim
n→∞
log[N (n)]
.
n
Extending the earlier language-on-a-network models of
Wallace and Wallace (1998, 1999), we suppose there is a coupling parameter P representing the degree of linkage between
the modules, and set K = 1/P , following the development
of those earlier studies. Note that in a brain model this parameter represents the intensity of coupling between distant
neural structures.
4
Then we have
For interacting neural networks P might simply be taken as
proportional to the degree of crosstalk.
We assume the piecewise, adiabatically memoryless ergodic
information source (Wallace, 2002b) depends on three parameters, two explicit and one implicit. The explicit are K as
above and an ‘external field strength’ analog J, which gives a
‘direction’ to the system. We will, in the limit, set J = 0.
The implicit parameter, which we call r, is an inherent generalized ‘length’ characteristic of the phenomenon, on which
J and K are defined. That is, we can write J and K as
functions of averages of the parameter r, which may be quite
complex, having nothing at all to do with conventional ideas
of space: For example r may be defined by the degree of niche
partitioning in ecosystems or separation in social structures.
For a given generalized language of interest with a well
defined (piecewise adiabatically memoryless) ergodic source
uncertainty H we write
log[N (K, n)]
.
n→∞
n
I[K] = lim
The essential ‘homology’ between information theory and
statistical mechanics lies in the similarity of this expression
with the infinite volume limit of the free energy density. If
Z(K) is the statistical mechanics partition function derived
from the system’s Hamiltonian, then the free energy density
is determined by the relation
log[Z(K)]
.
V →∞
V
F [K] = lim
F is the free energy density, V the system volume and K =
1/T , where T is the system temperature.
We and others argue at some length (Wallace and Wallace,
1998, 1999; Rojdestvensky and Cottam, 2000) that this is
indeed a systematic mathematical homology which, we contend, permits importation of renormalization symmetry into
information theory. Imposition of invariance under renormalization on the mutual information splitting criterion I(X, Y )
implies the existence of phase transitions analogous to learning plateaus or punctuated evolutionary equilibria. An extensive mathematical development will be presented in the next
section.
The physiological details of mechanism, we speculate, will
be particularly captured by the definitions of coupling parameter, renormalization symmetry, and, perhaps, the distribution of the renormalization across agency, a matter we treat
below.
Here, however, these changes are perhaps better described
as ‘punctuated interpenetration’ between interacting cognitive modules.
We reiterate that the details are highly dependent on the
choice of renormalization symmetry (and its distribution),
which is likely to reflect details of mechanism – the manner in
which the dynamics of the forest are dependent on the detailed
physiology of trees, albeit in a many-to-one manner. Renormalization properties are not likely to follow simple physical
analogs, and may well be subject, in addition to complications
of distribution, to the ‘tuning’ of universality class parameters
that are characteristically fixed for simple physical systems.
The algebra is straightforward if complicated, and given later.
H[K, J, X]
Imposition of invariance of H under a renormalization
transform in the implicit parameter r leads to expectation
of both a critical point in K, which we call KC , reflecting
a phase transition to or from collective behavior across the
entire array, and of power laws for system behavior near KC .
Addition of other parameters to the system, e.g. some V ,
results in a ‘critical line’ or surface KC (V ).
Let κ ≡ (KC −K)/KC and take χ as the ‘correlation length’
defining the average domain in r-space for which the information source is primarily dominated by ‘strong’ ties. We begin
by averaging across r-space in terms of ‘clumps’ of length R.
Then, taking Wilson’s (1971) analysis as a starting point, we
choose the renormalization relations as
H[KR , JR , X] = f (R)H[K, J, X]
χ(KR , JR ) =
χ(K, J)
,
R
(2)
Representations of the general argument
with f (1) = 1 and J1 = J, K1 = K. The first of these equations significantly extends Wilson’s treatment. It states that
‘processing capacity,’ as indexed by the source uncertainty of
the system, representing the ‘richness’ of the generalized language, grows monotonically as f (R), which must itself be a dimensionless function in R, since both H[KR , JR ] and H[K, J]
are themselves dimensionless. Most simply, this would require
that we replace R by R/R0 , where R0 is the ‘characteristic
length’ for the system over which renormalization procedures
are reasonable, then set R0 ≡ 1, i.e. measure length in units
of R0 . Wilson’s original analysis focused on free energy density. Under ‘clumping’, densities must remain the same, so
that if F [KR , JR ] is the free energy of the clumped system,
and F [K, J] is the free energy density before clumping, then
Wilson’s equation (4) is F [K, J] = R−3 F [KR , JR ], i.e.
1. Language-on-a-network models. Earlier papers of
this series addressed the problem of how a language, in a large
sense, spoken on a network structure responds as properties of
the network change. The language might be speech, pattern
recognition, or cognition. The network might be social, chemical, or neural. The properties of interest were the magnitude
of ‘strong’ or ‘weak’ ties which, respectively, either disjointly
partitioned the network or linked it across such partitioning.
These would be analogous to local and mean-field couplings
in physical systems.
We fix the magnitude of strong ties – to reiterate, those
which disjointly partition the underlying network (presumably into cognitive submodules) – but vary the index of weak
ties between components, which we call P , taking K = 1/P .
5
To reiterate somewhat, this heuristic insight can be made
more exact using a rate distortion argument (or, more generally, using the Joint Asymptotic Equipartition Theorem) as
follows (Wallace, 2002a, b):
Suppose that two ergodic information sources Y and B
begin to interact, to ‘talk’ to each other, i.e. to influence
each other in some way so that it is possible, for example,
to look at the output of B – strings b – and infer something
about the behavior of Y from it – strings y. We suppose it
possible to define a retranslation from the B-language into
the Y-language through a deterministic code book, and call
Ŷ the translated information source, as mirrored by B.
Define some distortion measure comparing paths y to paths
ŷ, d(y, ŷ) (Cover and Thomas, 1991). We invoke the Rate Distortion Theorem’s mutual information I(Y, Ŷ ), which is the
splitting criterion between high and low probability pairs of
paths. Impose, now, a parametization by an inverse coupling
strength K, and a renormalization symmetry representing the
global structure of the system coupling. This may be much
different from the renormalization behavior of the individual
components. If K < KC , where KC is a critical point (or
surface), the two information sources will be closely coupled
enough to be characterized as condensed.
In the absence of a distortion measure, we can invoke the
Joint Asymptotic Equipartition Theorem to obtain a similar
result.
We suggest in particular that detailed coupling mechanisms
will be sharply constrained through regularities of grammar
and syntax imposed by limit theorems associated with phase
transition.
Wallace and Wallace (1998, 1999) and Wallace (2002) use
this approach to address certain evolutionary processes in a
relatively unified fashion. These papers, and those of Wallace and Fullilove (1999) and Wallace (2002a), further describe how biological or social systems might respond to gradients in information source uncertainty and related quantities
when the system is away from phase transition. Language-onnetwork systems, as opposed to physical systems, appear to
diffuse away from concentrations of an ‘instability’ construct
which is related to a Legendre transform of information source
uncertainty, in much the same way entropy is the Legendre
transform of free energy density in a physical system.
Simple thermodynamics addresses physical systems held at
or near equilibrium conditions. Treatment of nonequilibrium,
for example highly dynamic, systems requires significant extension of thermodynamic theory. The most direct approach
has been the first-order phenomenological theory of Onsager,
which involves relating first order rate changes in system parameters Kj to gradients in physical entropy S, involving ‘Onsager relation’ equations of the form
F [KR , JR ] = R3 F [K, J].
Remarkably, the renormalization equations are solvable
for a broad class of functions f (R), or more precisely,
f (R/R0 ), R0 ≡ 1.
The second relation just states that the correlation length
simply scales as R.
Other, very subtle, symmetry relations – not necessarily
based on the elementary physical analog we use here – may
well be possible. For example McCauley, (1993, p.168) describes the highly counterintuitive renormalization relations
needed to understand phase transition in simple ‘chaotic’ systems. This is important, since we suspect that biological or
social systems may alter their renormalization properties –
equivalent to tuning their phase transition dynamics – in response to external signals. We will make much of this possibility, termed ‘universality class tuning’, below.
To begin, following Wilson, we take f (R) = Rd for some
real number d > 0, and restrict K to near the ‘critical value’
KC . If J → 0, a simple series expansion and some clever
algebra (Wilson, 1971; Binney et al., 1986) gives
H = H 0 κα
χ=
χ0
κs
(3)
where α, s are positive constants. We provide more biologically relevant examples below.
Further from the critical point matters are more complicated, appearing to involve Generalized Onsager Relations
and a kind of thermodynamics associated with a Legendre
transform of H, i.e. S ≡ H − KdH/dK (Wallace, 2002a).
Although this extension is quite important to describing behaviors away from criticality, the full mathematical detail is
cumbersome and the reader is referred to the references. A
brief discussion will be given below.
An essential insight is that regardless of the particular
renormalization properties, sudden critical point transition is
possible in the opposite direction for this model. That is, we
go from a number of independent, isolated and fragmented
systems operating individually and more or less at random,
into a single large, interlocked, coherent structure, once the
parameter K, the inverse strength of weak ties, falls below
threshold, or, conversely, once the strength of weak ties paX
rameter P = 1/K becomes large enough.
Rk,j dKj /dt = ∂S/∂Kj ,
Thus, increasing nondisjunctive weak ties between them
k
can bind several different cognitive ‘language’ functions into a
single, embedding hierarchical metalanguage which contains
where the Rk,j are characteristic constants of a particular
each as a linked subdialect, and do so in an inherently punc- system and S is defined to be the Legendre transform free
tuated manner. This could be a dynamic process, creating a energy density F ;
shifting, ever-changing, pattern of linked cognitive submodX
ules, according to the challenges or opportunities faced by the
S≡F −
∂F/∂Kj .
organism.
j
6
The entropy-analog for an information system is, then, the
dimensionless quantity
X
S≡H−
Kj ∂H/∂Kj ,
dKR /dR = u1 d log(f )/dR + u2 /R
j
dJR /dR = v1 JR d log(f )/dR +
v2
JR .
R
or a similar equation in the mutual information I.
Note that in this treatment I or H play the role of free (5)
energy, not entropy, and that their Legendre transform plays
the role of physical entropy. This is a key matter.
For information systems, a parametized ‘instability’,
The ui , vi , i = 1, 2 are functions of KR , JR , but not explicQ[K] ≡ S − H, is defined from the principal splitting criitly
of R itself.
terion by the relations
We expand these equations about the critical value KR =
KC and about JR = 0, obtaining
Q[K] = −KdH[K]/dK
dKR /dR = (KR − KC )yd log(f )/dR + (KR − KC )z/R
Q[K] = −KdI[K]/dK
(4)
dJR /dR = wJR d log(f )/dR + xJR /R.
(6)
where H[K] and I[K] are, respectively, information
source uncertainty or mutual information in the Asymptotic
Equipartition, Rate Distortion, or Joint Asymptotic Equipartition Theorems.
Extension of thermodynamic theory to information systems
involves a first order system phenomenological equations analogous to the Onsager relations, but possibly having very complicated behavior in the Rj,k , in particular not necessarily
producing simple diffusion toward peaks in S. For example,
as discussed, there is evidence that social network structures
are affected by diffusion away from concentrations in the Sanalog. Thus the phenomenological relations affecting the
dynamics of information networks, which are inherently open
systems, may not be governed simply by mechanistic diffusion
toward ‘peaks in entropy’, but may, in first order, display more
complicated behavior.
2. ‘Biological’ phase transitions. Now the mathematical detail concealed by the invocation of the asymptotic limit
theorems emerges with a vengeance. Equation (2) states that
the information source and the correlation length, the degree
of coherence on the underlying network, scale under renormalization clustering in chunks of size R as
The
terms
y
=
du1 /dKR |KR =KC , z
=
du2 /dKR |KR =KC , w = v1 (KC , 0), x = v2 (KC , 0) are
constants.
Solving the first of these equations gives
KR = KC + (K − KC )Rz f (R)y ,
(7)
again remembering that K1 = K, J1 = J, f (1) = 1.
Wilson’s essential trick is to iterate on this relation, which
is supposed to converge rapidly (Binney, 1986), assuming that
for KR near KC , we have
KC /2 ≈ KC + (K − KC )Rz f (R)y .
H[KR , JR ]/f (R) = H[J, K]
(8)
χ[KR , JR ]R = χ(K, J),
We iterate in two steps, first solving this for f (R) in terms
of known values, and then solving for R, finding a value RC
that we then substitute into the first of equations (2) to obtain
an expression for H[K, 0] in terms of known functions and
parameter values.
The first step gives the general result
with f (1) = 1, K1 = K, J1 = J, where we have slightly
rearranged terms.
Differentiating these two equations with respect to R, so
that the right hand sides are zero, and solving for dKR /dR
and dJR /dR gives, after some consolidation, expressions of
the form
7
f (RC ) ≈
[KC/(KC − K)]1/y
z/y
21/y RC
.
f (R) = m log(R) + 1.
(9)
(13)
Solving this for RC and substituting into the first of equation (2) gives, as a first iteration of a far more general procedure (e.g. Shirkov and Kovalev, 2001)
Again f (1) = 1.
Using Mathematica 4.2 to solve equation (8) for RC gives
RC = [
H0
H[KC /2, 0]
=
H[K, 0] ≈
f (RC )
f (RC )
Q
]y/z ,
LambertW [Q exp(z/my)]
(14)
χ(K, 0) ≈ χ(KC /2, 0)RC = χ0 RC
where
(10)
Q ≡ [(z/my)2−1/y [KCKC − K)]1/y .
The transcendental function LambertW(x) is defined by the
which are the essential relationships.
m
relation
Note that a power law of the form f (R) = R , m = 3,
which is the direct physical analog, may not be biologically
LambertW (x) exp(LambertW (x)) = x.
reasonable, since it says that ‘language richness’ can grow
very rapidly as a function of increased network size. Such
It arises in the theory of random networks and in renormalrapid growth is simply not observed.
ization strategies for quantum field theories.
If we take the biologically realistic example of non-integral
An asymptotic relation for f (R) would be of particular bi‘fractal’ exponential growth,
ological interest, implying that ‘language richness’ increases
to a limiting value with population growth. Such a pattern
is broadly consistent with calculations of the degree of allelic
heterozygosity as a function of population size under a balf (R) = Rδ ,
ance between genetic drift and neutral mutation (Hartl and
Clark, 1997; Ridley, 1996). Taking
(11)
f (R) = exp[m(R − 1)/R]
where δ > 0 is a real number which may be quite small, we
can solve equation (8) for RC , obtaining
RC =
(15)
[KC/(KC − K)][1/(δy+z)]
21/(δy+z)
gives a system which begins at 1 when R=1, and approaches
the asymptotic limit exp(m) as R → ∞. Mathematica 4.2
finds
(12)
my/z
for K near KC . Note that, for a given value of y, we might
RC =
want to characterize the relation α ≡ δy + z = constant as
LambertW [S]
a “tunable universality class relation” in the sense of Albert
(16)
and Barabasi (2002).
Substituting this value for RC back into equation (9) gives
a somewhat more complex expression for H than equation
(2), having three parameters, i.e. δ, y, z.
where
A more biologically interesting choice for f (R) is a logaS ≡ (my/z) exp(my/z)[21/y [KC/(KC − K)]−1/y ]y/z .
rithmic curve that ‘tops out’, for example
8
(16)
Thus the information dynamic phase transition properties
of mixed systems will not in general be simply related to those
of a single subcomponent, a matter of possible empirical importance: If sets of relevant parameters defining renormalization universality classes are indeed distributed, experiments
observing pure phase changes may be very difficult. Tuning among different possible renormalization strategies in response to external pressures would result in even greater ambiguity in recognizing and classifying information dynamic
phase transitions.
We believe that important aspects of mechanism may be
reflected in the combination of renormalization properties and
the details of their distribution across subsystems.
In sum, real biological, social, or interacting biopsychosocial
systems are likely to have very rich patterns of phase transition which may not display the simplistic, indeed, literally
elemental, purity familiar to physicists. Overall mechanisms
will, we believe, still remain significantly constrained by our
theory, in the general sense of probability limit theorems.
4. Universality class tuning: the fluctuating dynamic threshold Next we iterate the general argument onto
the process of phase transition itself, producing our model of
consciousness as a tunable neural workspace subject to inherent punctuated detection of external events.
An essential character of physical systems subject to phase
transition is that they belong to particular ‘universality
classes’. This means that the exponents of power laws describing behavior at phase transition will be the same for large
groups of markedly different systems, with ‘natural’ aggregations representing fundamental class properties (e.g. Binney
et al., 1986).
It is our contention that biological or social systems undergoing phase transition analogs need not be constrained to
such classes, and that ‘universality class tuning’, meaning the
strategic alteration of parameters characterizing the renormalization properties of punctuation, might well be possible.
Here we focus on the tuning of parameters within a single,
given, renormalization relation. Clearly, however, wholesale
shifts of renormalization properties must ultimately be considered as well.
Universality class tuning has been observed in models of
‘real world’ networks. As Albert and Barabasi (2002) put it,
These developments indicate the possibility of taking the
theory significantly beyond arguments by abduction from simple physical models, although the notorious difficulty of implementing information theory existence arguments will undoubtedly persist.
3. Universality class distribution. Physical systems undergoing phase transition usually have relatively
pure renormalization properties, with quite different systems
clumped into the same ‘universality class’, having fixed exponents at transition (e.g. Binney, 1986). Biological and social
phenomena may be far more complicated:
If we suppose the system of interest to be a mix of subgroups with different values of some significant renormalization parameter m in the expression for f (R, m), according to
a distribution ρ(m), then we expect the first expression in
equation (1) to generalize as
H[KR , JR ] =< f (R, m) > H[K, J]
Z
≡ H[K, J]
f (R, m)ρ(m)dm.
(17)
If f (R) = 1 + m log(R) then, given any distribution for m,
we simply obtain
< f (R) >= 1+ < m > log(R)
(18)
where < m > is simply the mean of m over that distribution.
Other forms of f (R) having more complicated dependencies
on the distributed parameter or parameters, like the power
law Rδ , do not produce such a simple result. Taking ρ(δ) as
a normal distribution, for example, gives
“The inseparability of the topology and dynamics of evolving networks is shown by the fact that
[the exponents defining universality class] are related
by [a] scaling relation..., underlying the fact that a
network’s assembly uniquely determines its topology. However, in no case are these exponents unique.
They can be tuned continuously...”
< Rδ >= R<δ> exp[(1/2)(log(Rσ ))2 ],
We suppose that a structured external environment, which
we take itself to be an appropriately regular information
(19)
source Y ‘engages’ a modifiable cognitive system. The environment begins to write an image of itself on the cognitive
system in a distorted manner permitting definition of a muwhere σ 2 is the distribution variance. The renormalization tual information I[K] splitting criterion according to the Rate
properties of this function can be determined from equation Distortion or Joint Asymptotic Equipartition Theorems. K
(8), and is left to the reader as an exercise, best done in is an inverse coupling parameter between system and environMathematica 4.2 or above.
ment (Wallace, 2002a, b). According to our development, at
9
punctuation – near some critical point KC – the systems beWe can formally iterate the phase transition argument on
gin to interact very strongly indeed, and we may write, near this calculation to obtain our version of tunable consciousness,
KC , taking as the starting point the simple physical model of focusing on paths of universality class parameters.
equation (2),
Suppose the renormalization properties of a language-ona network system at some ‘time’ k are characterized by a
KC − K α
k
set of parameters Ak ≡ α1k , ..., αm
. Fixed parameter val] .
I[K] ≈ I0 [
KC
ues define a particular universality class for the renormalFor a physical system α is fixed, determined by the under- ization. We suppose that, over a sequence of ‘times’, the
lying ‘universality class’. Here we will allow α to vary, and, universality class properties can be characterized by a path
xn = A0 , A1 , ..., An−1 having significant serial correlations
in the section below, to itself respond explicitly to signals.
which, in fact, permit definition of an adiabatically pieceNormalizing KC and I0 to 1, we obtain,
wise memoryless ergodic information source associated with
the paths xn . We call that source X.
We further suppose, in the manner of Wallace (2002a, b),
that the set of external signals is also highly structured and
α
I[K] ≈ (1 − K) .
forms another information source Y which interacts not only
with the system of interest globally, but specifically with its
(20)
universality class properties as characterized by X. Y is necessarily associated with a set of paths yn .
We pair the two sets of paths into a joint path, zn ≡ (xn , yy )
The horizontal line I[K] = 1 corresponds to α = 0, while and invoke an inverse coupling parameter, K, between the
α = 1 gives a declining straight line with unit slope which information sources and their paths. This leads, by the arpasses through 0 at K = 1. Consideration shows there are guments above, to phase transition punctuation of I[K], the
progressively sharper transitions between the necessary zero mutual information between X and Y, under either the Joint
value at K = 1 and the values defined by this relation for Asymptotic Equipartition Theorem or under limitation by
0 < K, α < 1. The rapidly rising slope of transition with a distortion measure, through the Rate Distortion Theorem
declining α is, we assert, of considerable significance.
(Cover and Thomas, 1991). Again, see Wallace (2002a, b)
The instability associated with the splitting criterion I[K] for more details of the argument. The essential point is that
is defined by
I[K] is a splitting criterion under these theorems, and thus
partakes of the homology with free energy density which we
have invoked above.
Activation of universality class tuning, our version of atQ[K] ≡ −KdI[K]/dK = αK(1 − K)α−1 ,
tentional focusing, then becomes itself a punctuated event in
response to increasing linkage between the organism and an
(21)
external structured signal.
We note in passing, but without further calculation, that
another path to the fluctuating dynamic threshold might be
and is singular at K = KC = 1 for 0 < α < 1. Following through a second order iteration similar to that just above,
earlier work (Wallace and Wallace, 1998, 1999; Wallace and but focused on the parameters defining the universality class
Fullilove, 1999; Wallace, 2002a), we interpret this to mean distributions of section 3.
that values of 0 < α 1 are highly unlikely for real systems,
Extending the model
since Q[K], in this model, represents a kind of barrier for
information systems, in particular neural networks.
The Rate Distortion and Joint Asymptotic Equipartition
On the other hand, smaller values of α mean that the system is far more efficient at responding to the adaptive de- Theorems are generalizations of the Shannon-McMillan Theomands imposed by the embedding structured environment, rem which examine the interaction of two information sources,
since the mutual information which tracks the matching of with and without the constraint of a fixed average distortion.
internal response to external demands, I[K], rises more and We conduct one more iteration, and require a generalization
more quickly toward the maximum for smaller and smaller α of the SMT in terms of the splitting criterion for triplets as
as the inverse coupling parameter K declines below KC = 1. opposed to single or double stranded patterns. The tool for
That is, systems able to attain smaller α are more responsive this is at the core of what is termed network information theto external signals than those characterized by larger values, in ory [Cover and Thomas, 1991, Theorem 14.2.3]. Suppose we
this model, but smaller values will be hard to reach, and can have three (piecewise adiabatically memoryless) ergodic inprobably be done so only at some considerable physiological formation sources, Y1 , Y2 and Y3 . We assume Y3 constitutes a
or opportunity cost: focused conscious action takes resources, critical embedding context for Y1 and Y2 so that, given three
sequences of length n, the probability of a particular triplet
of one form or another.
The more biologically realistic renormalization strategies of sequences is determined by conditional probabilities with
given above produce sets of several parameters defining the respect to Y3 :
universality class, whose tuning gives behavior much like that
of α in this simple example.
10
of culture on individual cognition. We now have a tool for
examining the interpenetration of a broad range of cognitive
P (Y1 = y1 , Y2 = y2 , Y3 = y3 ) =
physiological, psychological, and social submodules – not just
neural substructures – with each other and with embedding
contextual cultural language so characteristic of human hyn
Πi=1 p(y1i |y3i )p(y2i |y3i )p(y3i ).
persociality, all within the further context of structured psychosocial stress. Wallace (2003) analyzes the implications
(22)
for understanding comorbid mind/body dysfunction, and provides a laundry list of physiological, psychological, and social
cognitive modules associated with health and disease.
That is, Y1 and Y2 are, in some measure, driven by their
Bennett and Hacker (2003) define the ‘mereological fallacy’
interaction with Y3
in neuroscience as the assignment, to parts of an animal,
Then, in analogy with previous analyses, triplets of se- of those characteristics which are properties of the whole.
quences can be divided by a splitting criterion into two sets, Humans, through both their embedding in cognitive social
having high and low probabilities respectively. For large n the networks, and their secondary epigenetic inheritance system
number of triplet sequences in the high probability set will be of culture, are even more than ‘simply’ individual animals.
determined by the relation [Cover and Thomas, 1992, p. 387] Equation (24) implies the possibility of extending the global
neuronal workspace model of consciousness to include both
internal cognitive physiological systems and embedding cognitive and other structures, providing a natural approach to
N (n) ∝ exp[nI(Y1 ; Y2 |Y3 )],
evading that fallacy.
Equation (24) is itself subject to significant generalization.
(23)
The single information source Z is seen here as invariant,
not affected by, but affecting, cross talk with the information sources for which it serves as the driving context. Suppose there is an interacting system of contexts, acting more
where splitting criterion is given by
slowly than the global neuronal workspace, but communicatI(Y1 ; Y2 |Y3 ) ≡
ing within itself. It should be possible, at first order, to divide
the full system into two sections, one ‘fast’, containing the
Yj , and the other ‘slow’, containing the series of information
H(Y3 ) + H(Y1 |Y3 ) + H(Y2 |Y3 ) − H(Y1 , Y2 , Y3 )
sources Zk . The fast system instantiates the conscious neuronal workspace, including crosstalk, while the slow system
We can then examine mixed cognitive/adaptive phase tranconstitutes an embedding context for the fast, but one which
sitions analogous to learning plateaus (Wallace, 2002b) in the
engages in its own pattern of crosstalk. Then the extended
splitting criterion I(Y1 , Y2 |Y3 ), which characterizes the synsplitting criterion, which we write as
ergistic interaction between Y3 , taken as an embedding context, and the cognitive processes characterized by Y1 and Y2 .
I(Y1 , ..., Yj |Z1 , ..., Zk ),
These transitions delineate the various stages of the chronic
infection, which are embodied in the slowly varying ‘piecebecomes something far more complicated than equation
wise adiabatically memoryless ergodic’ phase between tran(24).
This must be expressed in terms of sums of appropriate
sitions. Again, our results are exactly analogous to the ElShannon
uncertainties, a complex task which will be individdredge/Gould model of evolutionary punctuated equilibrium.
ually
contingent
on the particular forms of context and their
We can, if necessary, extend this model to any number of
interrelations.
interacting information sources, Y1 , Y2 , ..., Ys conditional on
an external context Z in terms of a splitting criterion defined
Discussion and conclusions
by
I(Y1 ; ...; Ys |Z) = H(Z) +
s
X
H(Yj |Z) − H(Y1 , ..., Ys , Z),
j=1
(24)
where the conditional Shannon uncertainties H(Yj |Z) are
determined by the appropriate direct and conditional probabilities.
Note that this simple-seeming extension opens a Pandora’s
box in the study of ‘mind-body interaction’ and the impacts
We have constructed a punctuated information dynamic
global neuronal workspace model which incorporates a
second-order and similarly punctuated universality class tuning linked to detection of structured external signals. Tuning
the punctuated activation of attention to those signals permits more rapid and appropriate response, but at increased
physiological or other opportunity cost: unconscious processing is clearly more efficient, if the organism can get away with
it. On the other hand, if the organism can’t get away with it,
death is more likely, suggesting a strong evolutionary imperative for a dynamic global neural workspace.
Linkage across individual dynamic workspaces – i.e. human
hypersociality in the context of an embedding epigenetic cultural inheritance system – would be even more adaptationally
11
efficient. Indeed, the last equation and its proposed extension suggest the possibility of very strong linkage of individual
consciousness and physiology to embedding sociocultural network phenomena, ultimately producing an extended model of
consciousness which does not fall victim to the mereological
fallacy.
In just this regard Nisbett et al. (2001) review an extensive
literature on empirical studies of basic cognitive differences
between individuals raised in what they call ‘East Asian’ and
‘Western’ cultural heritages, which they characterize, respectively, as ‘holistic’ and ‘analytic’. They find:
1. Social organization directs attention to some aspects of
the perceptual field at the expense of others.
2. What is attended to influences metaphysics.
3. Metaphysics guides tacit epistemology, that is, beliefs
about the nature of the world and causality.
4. Epistemology dictates the development and application
of some cognitive processes at the expense of others.
5. Social organization can directly affect the plausibility of
metaphysical assumptions, such as whether causality should
be regarded as residing in the field vs. in the object.
6. Social organization and social practice can directly influence the development and use of cognitive processes such
as dialectical vs. logical ones.
Nisbett et al. (2001) conclude that tools of thought embody a culture’s intellectual history, that tools have theories
built into them, and that users accept these theories, albeit
unknowingly, when they use these tools.
Individual consciousness – currently defined in terms of the
global neuronal workspace – appears to be profoundly affected
by cultural, and perhaps developmental, context, and, we
aver, by patterns of embedding psychosocial stress, all matters subject to a direct empirical study which may lead to an
extension of the concept particularly useful in understanding
certain forms of psychopathology.
From even limited theoretical perspectives, current dynamic systems models of neural networks, or their computer
simulations, simply do not reflect the imperatives of Adams’
(2003) informational turn in philosophy. On the other hand,
dynamic systems models based on differential equations, or
their difference equation realizations on computers, have a
history of intense and continuous intellectual development going back to Isaac Newton. Hence very little new mathematics
needs to be done, and one can look up most of the needed results in the textbooks, which are quite sophisticated by now.
Rigorous probability theory is perhaps a hundred years old,
and its information theory subset has seen barely a half century. Consequently the mathematics can’t always be looked
up, and sometimes must even be created de novo, at no small
difficulty. One is reminded, not originally, of a drunk looking
for his lost car keys under a street lamp ‘because the light is
better here’.
Virtually all self-proclaimed applications of information
theory to the dynamic neural workspace currently in the neuroscience literature have strayed far indeed from the draconian structural discipline imposed by the asymptotic limit
theorems of the subject: information measures are of no fundamental interest in and of themselves, serving only as grist
for the mills of splitting criteria between high and low probability sets of dynamic paths. This is the central mechanism
whose extension, using a homology with free energy density,
permits exploration of punctuated neural dynamics in a manner consistent with the program described by Adams (2003).
According to the mathematical ecologist E.C. Pielou (1976,
p.106), the legitimate purpose of mathematical models is to
raise questions for empirical study, not to answer them, or,
as one wag put it, “all models are wrong, but some models
are useful”. The natural emergence of tunable punctuated
dynamics in our treatment, albeit at the expense of elaborate renormalization calculations at transition, and generalized Onsager relations away from it, suggests the possible utility of the theory in future empirical studies of consciousness:
the car keys really may have been lost in the dark parking lot
down the street, but here is a new flashlight.
We have outlined an empirically-testable approach to modeling consciousness which returns with a resounding thump
to the classic asymptotic limit theorems of communication
theory, and suggests further the necessity of incorporating
the effects of embedding structures of psychosocial stress and
culture. The theory suffers from a painful grandiosity, claiming to incorporate matters of cognition, consciousness, social
system, and culture into a single all-encompassing model. To
quote from a recent review of Bennett and Hacker’s new book,
(Patterson, 2003), however, contemporary neuroscience itself
may suffer a more pernicious and deadly form of that disorder
for which our approach is, in fact, the antidote:
“[Bennett and Hacker] argue that for some neuroscientists, the brain does all manner of things: it believes (Crick); interprets (Edelman); knows (Blakemore); poses questions to itself (Young); makes decisions (Damasio); contains symbols (Gregory) and
represents information (Marr). Implicit in these assertions is a philosophical mistake, insofar as it unreasonably inflates the conception of the ‘brain’ by
assigning to it powers and activities that are normally reserved for sentient beings... these claims are
not false; rather they are devoid of sense.”
This is but one example of a swelling critical chorus which
will grow markedly in virulence and influence. Our development, or some related version, leads toward explicit incorporation of the full ‘sentient being’ into observational studies
of consciousness. For humans, whose hypersociality is both
glory and bane, this particularly involves understanding the
effects of embedding social and cultural context on immediate
conscious experience.
The bottom line would seem to be the urgent necessity of
extending the perspective of Nisbett et al. (2001) to brain
imaging and other empirical studies of consciousness, and extending the global neuronal workspace model accordingly, a
matter which our development here suggests is indeed possible, if not straightforward.
References
Adams F., (2003), The informational turn in philosophy,
Minds and Machines, 13:471-501.
Albert R. and A. Barabasi, (2002). Statistical mechanics
of complex networks. Rev. Mod. Phys. 74:47-97.
12
Atlan H. and I. R. Cohen, (1998), Immune information, selforganization and meaning, International Immunology 10:711717.
Bennett M., and P. Hacker, (2003), Philosophical Foundations of Neuroscience, Blackwell Publishing.
Binney J., N. Dowrick, A. Fisher, and M. Newman, (1986),
The theory of critical phenomena. Clarendon Press, Oxford
UK.
Cohen I.R., (1992), The cognitive principle challenges
clonal selection. Immunology Today 13:441-444.
Cohen I.R., (2000), Tending Adam’s Garden: evolving the
cognitive immune self, Academic Press, New York.
Cover T. and J. Thomas, (1991), Elements of Information
Theory. Wiley, New York.
Dehaene S. and L. Naccache, (2001), Towards a cognitive
neuroscience of consciousness: basic evidence and a workspace
framework, Cognition 79:1-37.
Dimitrov A. and J.Miller, (2001), Neural coding and decoding: communication channels and quantization. Network:
Comput. Neural Syst. 12:441-472.
Dretske F., (1981), Knowledge and the flow of information,
MIT Press, Cambridge, MA.
Dretske F., (1988), Explaining behavior, MIT Press, Cambridge, MA.
Dretske F., (1992), What isn’t wrong with folk psychology,
Metaphilosophy, 29:1-13.
Dretske F., (1993), Mental events as structuring causes of
behavior. In Mental causation, (ed. A. Mele and J. Heil), pp.
121-136, Oxford University Press.
Dretske F., (1994), The explanatory role of information,
Philosophical Transactions of the Royal Society A, 349:59-70.
Eldredge N., (1985), Time Frames: The Rethinking of Darwinian Evolution and the Theory of Punctuated Equilibria,
Simon and Schuster, New York.
Feynman R., (1996), Feynman Lectures on Computation,
Addison-Wesley, Reading, MA.
Grossman Z., (1989), The concept of idiotypic network: deficient or premature? In: H. Atlan and I.R. Cohen (eds.), Theories of Immune Networks, Springer Verlag, Berlin, p. 3852.
Hartl D. and A. Clark, (1997). Principles of Population
Genetics, Sinaur Associates, Sunderland MA.
Levins R. and R. Lewontin, (1985). The Dialectical Biologist, Harvard University Press, Cambridge MA.
Levins R, (1998), The internal and external in explanatory
theories. Science as Culture. 7:557-582.
Lewontin R., (2000), The Triple Helix: Gene, Organism
and Environment. Harvard University Press, Cambridge MA.
McCauley L., (1993), Chaos, Dynamics, and Fractals: An
Algorithmic Approach to Deterministic Chaos, Cambridge
University Press, UK.
Nisbett R., K. Peng, C. Incheol, A. Norenzayan, (2001),
Culture and systems of thought: holistic vs. analytic cognition, Psychological Review, 108:291-310.
Patterson D., (2003), Book review of Philosophical Foundations of Neuroscience, Notre Dame Philosophical Reviews,
2003.09.10.
http://ndpr.icaap.org/content/archives/2003/9/.
Park H., S. Amari, and K. Fukumizu, (2000), Adaptive natural gradient learning algorithms for various stochastic models, Neural Networks, 13:755-765.
Pielou E, (1977), Mathematical Ecology. John Wiley and
Sons, New York.
Richerson P. and R. Boyd, (1995), The evolution of human
hypersociality. Paper for Ringberg Castle Symposium on Ideology, Warfare and Indoctrinability (January, 1995), and for
HBES meeting.
Ridley M., (1996), Evolution, Second Edition, Blackwell
Science, Oxford, UK.
Rojdestvenski I. and M. Cottam, (2000), Mapping of statistical physics to information theory with applications to biological systems. J. Theor. Biol. 202: 43-54.
Sergeant C. and S. Dehaene, (2004), Is consciousness a
gradual phenomenon? Evidence for an all-or-none bifurcation
during the attentional blink. In press, Psych. Sci. Available
at: http://www.unicog.orb/biblio/Author/DEHAENE.html.
Shirkov D. and V. Kovalev, (2001), The Bogoliubov renormalization group and solution symmetry in mathematical
physics. Phys. Reports 352: 219-249.
Tauber A., (1998), Conceptual shifts in immunology: Comments on the ‘two-way paradigm’. In K. Schaffner and T.
Starzl (eds.), Paradigm changes in organ transplantation,
Theoretical Medicine and Bioethics, 19:457-473.
Wallace R., (2000), Language and coherent neural amplification in hierarchical systems: Renormalization and the dual
information source of a generalized spatiotemporal stochastic
resonance, Int. J. Bifurcation and Chaos 10:493-502.
Wallace R., (2002a), Immune cognition and vaccine strategy: pathogenic challenge and ecological resilience, Open Sys.
Inform. Dyn. 9:51-83.
Wallace R., (2002b), Adaptation, punctuation and rate distortion: non-cognitive ‘learning plateaus’ in evolutionary process, Acta Biotheoretica, 50:101-116.
Wallace R., (2003), Comorbidity and anticomorbidity:
autocognitive developmental disorders of structured psychosocial stress.
Submitted.
Available at:
http://www.arxiv.org/abs/q-bio.NC/0310001.
Wallace R. and D. Wallace, (2003), Structured psychosocial stress and therapeutic failure. Submitted. Available at
http://www.arxiv.org/abs/q-bio.NC/0310005.
Wallace R. and R.G. Wallace, (1998), Information theory,
scaling laws and the thermodynamics of evolution, Journal of
Theoretical Biology 192:545-559.
Wallace R. and R.G. Wallace, (1999), Organisms, organizations and interactions: an information theory approach to
biocultural evolution, BioSystems 51:101-119.
Wallace R. and R.G. Wallace, (2002), Immune cognition
and vaccine strategy: beyond genomics, Microbes and Infection 4:521-527.
Wallace R., R.G. Wallace and D. Wallace, (2003), Toward
cultural oncology: the evolutionary information dynamics of
cancer, Open Sys. Inform. Dynam., 10:159-181.
Wallace R., D. Wallace and R.G. Wallace, (In press), Biological limits to reduction in rates of coronary heart disease: a punctuated equilibrium approach to immune cognition, chronic inflammation, and pathogenic social hierarchy,
JNMA.
Wilson K.,(1971), Renormalization group and critical phenomena. I Renormalization group and the Kadanoff scaling
picture. Phys. Rev. B. 4: 3174-3183.
13 |
1
Ictal and Post Ictal Impaired Consciousness due
to Enhanced Mutual Information in Temporal
Lobe Epilepsy
Puneet Dheer*, Systems Science and Informatics Unit, Indian Statistical Institute, 8th Mile, Mysore
Road, Bangalore 560059, India; e-mail: puneetdheer@gmail.com
Sandipan Pati*, UAB Epilepsy Center, Department of Neurology, University of Alabama at
Birmingham, CIRC 312, 1719 6th Avenue South, Birmingham, AL 35294, USA; e-mail:
spati@uabmc.edu
Srinath Jayachandran, Systems Science and Informatics Unit, Indian Statistical Institute, 8th Mile,
Mysore Road, Bangalore 560059, India; e-mail: sri9s@yahoo.in
Kaushik Kumar Majumdar, Systems Science and Informatics Unit, Indian Statistical Institute, 8th
Mile, Mysore Road, Bangalore 560059, India; e-mail: kmajumdar@isibang.ac.in
*shared first authors
Abstract—Seizure and synchronization are related to each other in complex manner. Altered synchrony has been implicated in loss of
consciousness during partial seizures. However, the mechanism of altered consciousness following termination of seizures has not been studied
well. In this work we used bivariate mutual information as a measure of synchronization to understand the neural correlate of altered
consciousness during and after termination of mesial temporal lobe onset seizures. First, we have compared discrete bivariate mutual
information (MI) measure with amplitude correlation (AC), phase synchronization (PS), nonlinear correlation and coherence, and established
MI as a robust measure of synchronization. Next, we have extended MI to more than two signals by principal component method. The
extended MI was applied on intracranial electroencephalogram (iEEG) before, during and after 23 temporal lobe seizures recorded from 11
patients. The analyses were carried out in delta, theta, alpha, beta and gamma bands. In 77% of the complex partial seizures MI was higher
towards the seizure offset than in the first half of the seizure in the seizure onset zone (SOZ) channels in beta and gamma bands, whereas MI
remained higher in the beginning or in the middle of the seizure than towards the offset across the least involved channels in the same bands.
Synchronization seems built up outside the SOZ, gradually spread and culminated in SOZ and remained high beyond offset leading to impaired
consciousness in 82% of the complex partial temporal lobe seizures. Consciousness impairment was scored according to a method previously
applied to assess the same in patients with temporal lobe epilepsy during seizure.
Keywords—Consciousness score, beta-band, gamma-band, intracranial EEG (iEEG), mutual information, temporal lobe seizure.
2
1. Introduction
Impaired consciousness in partial seizures is usually most profound late in the seizure and persists for up
to several minutes after the termination of the seizure, during the post-ictal period (Blumenfeld and Taylor,
2003). Temporal lobe structures – hippocampus, amygdala and entorhinal cortex form heightened nonlinear
correlation among themselves as well as with medial temporal gyrus, thalamus, posterior cingulate gyrus
and lateral parietal cortex leading to moderate to profound alteration of consciousness during medial
temporal lobe seizures (Arthuis et al., 2009). In that work a novel consciousness score was defined and was
used to grade impairment of consciousness during temporal lobe seizures. This was then compared with a
nonlinear correlation measure (Wendling et al., 2001) defined pairwise among the temporal lobe and
extratemporal lobe structures mentioned above.
Neuronal gamma-band synchronization constitutes a fundamental process for all of cortical computations
(Fries 2009). It is involved in modulating different aspects of consciousness (Ward, 2003), such as, visual
awareness (Crick and Koch, 1990; Tallon-Baudry, 2009), face recognition (Rodriguez et al., 1999),
associative learning (McIntosh et al., 1999), conscious perception (Melloni et al., 2007). Conscious
thinking is often aided by working memory storage and long-term memory retrieval. Both the processes
may interact in the hippocampus (Fell and Axmacher, 2011). An increase in coherence of theta and gamma
oscillations in the hippocampus, amygdala and neocortex was predictive of immediate recall performance
in a verbal learning task (Babiloni et al., 2009).
The brain network that is involved in a cognitive process has to be reactivated when the cognitive task is
to be replayed. The cognitive process is modulated by beta-band synchronization across the network
(Spitzer and Haegens, 2017), and is important for endogenous content retrieval during conscious thoughts.
Alpha-band synchronization has been implicated in suppressing distracting stimuli in order to pay enhanced
attention to the desired one (Ward, 2003). It has also been implicated in working memory. Gamma-band
synchronization for feature binding may require alpha-band desynchronization (Ward, 2003). Experimental
3
data concerning event-related theta oscillations hint at a basic role in cognitive processing and in the
cortico-hippocampal interaction. Therefore excessive theta-band synchronization in the temporal lobe may
cause impaired cognition. Stronger theta and delta synchronization has been implicated in the processing of
stimuli with higher emotional value over emotionally neutral stimuli (Knyazev et al., 2009). Delta and theta
responses have also been implicated in arousal (Guntekin and Basar, 2016). It is suggested that complex
stimuli elicit superimposed alpha, gamma, theta responses which are combined like letters in an alphabet
(Basar et al., 2001). In general, conscious awareness may arise from synchronous neural oscillations
occurring globally throughout the brain rather than from the locally synchronous oscillations that occur
when a sensory area encodes a stimulus (Ward, 2003). It is natural that during epileptic seizures excessive
synchronization in the form of a nonlinear correlation (Wendling et al., 2001) across all the frequency
bands overloaded the brain structures involved in conscious processing leading to impaired consciousness
(Arthuis et al., 2009).
Synchronization is a ubiquitous phenomenon in neuroscience. It is present from cellular level (Steinmetz
et al., 2000) to systems level in primate brains (Ward, 2003). However, even within neuroscience
synchronization is a generic term, interpreted and measured differently in different contexts. Sometimes it
is phase synchronization (Rodriguez et al., 1999), some other time it is plain linear amplitude correlation
(Schindler et al., 2007) and yet other times it is nonlinear correlation (Arthuis et al., 2009). Mean phase
coherence (Mormann et al., 2000) or phase locking value (Aydore et al., 2013) is another widely used
measure of synchronization in brain networks. Whatever be the measure, synchronization looks for
simultaneity in processing by different parts of the brain network for a cognitive task. In general, this
simultaneity may be with any time lag (Arthuis et al., 2009). If different parts of the brain are considered
different dynamical systems, each of which is manifested through a time series generated by the underlying
dynamical system, then measuring synchronization across the brain network boils down to finding
simultaneous events or patterns in the time series.
In neuroscience, be it electrophysiological signals, magnetic signals, hemodynamic activation time
4
series, ionic concentration variation time series, optical time series, or infrared time series, it is the
geometric shape which uniquely determines the time series like a face or fingerprint. All the information
embedded in the signal are embedded in its shape. Sometime this information is extracted as phase,
sometime it is extracted as amplitude, sometime it is extracted as frequency, etc. One or more of the
features together represent partial or total information encoded in the time series. Recently it has been
shown that information that gives meaning to the time domain signal (not the statistical properties of
information as in Shannon theory) and analyzed during processing of the physiological signal for
diagnostic and research purposes is encoded in 3-point neighborhoods of the digital signal (Majumdar and
Jayachandran, 2018). Such information is encoded in ordinal patterns generated by permutations of the 3
points in the neighborhood (Olofsen et al., 2008). These ordinal patterns have been utilized to measure
permutation conditional mutual information (PCMI) between two neural signals (X. Li and G. Ouyang,
2010).
Study of mutual information across multiple intracranial EEG (iEEG) channels in temporal lobe across
delta, theta, alpha, beta and gamma bands before, during and after epileptic seizures vis-à-vis the state of
consciousness of the patient may offer us important insights into the relationship between seizure and
consciousness. Impaired consciousness during seizure and in the post-ictal state contributes to significant
mortality and morbidity in patients with epilepsy. Moreover, if mutual information can be shown to be a
more general form of synchronization, correlation or coherence measure than phase synchronization or
amplitude correlation or other simultaneity measures mentioned above, the conclusions drawn with the help
of mutual information measure will be more general in nature than achievable by any one single
simultaneity measure.
2. Methods
Measures like correlation, coherence, synchronization, etc are used to estimate the interdependence
between two signals. Mutual information calculates this interdependence in terms of an information
5
distance measure, called Kullback-Leibler divergence (Cover and Thomas, 2006) from the joint distribution
of the two random variables (signals) to the product of the marginal distributions. Mutual information
I ( x , y ) between two time domain signals x and y is given by
I ( x, y ) p ( x, y ) log
x
y
p ( x, y )
,
p ( x) p ( y )
(1)
for discrete time signals x and y . Clearly, when x , y are independent I ( x, y ) 0 , or, I ( x, y ) 0
otherwise.
It is important to note that correlation implies mutual information. For example, mutual information
between two correlated Gaussian random variables with correlation coefficient 1 is infinite, and with
correlation coefficient 0 the mutual information between them becomes 0 (Cover and Thomas, 2006, p.
252). In Fig. 1 we have presented a comparison among various synchronization measures prevalent in
Neuroscience. Since synchronization has been studied most extensively during epileptic seizures, we have
presented our results using different synchronization measuring algorithms on a pair of human iEEG
signals (unfiltered) collected before, during and after an epileptic seizure.
6
l
Fig. 1. Comparison among Mutual Information (MI), Amplitude Correlation (AC), Phase Locking Value
(PLV) (Aydore et al., 2013), (Hilbert transformation based) Phase Synchronization (PS), Nonlinear
Correlation or h-square value (Wendling et al., 2001) and coherence (Bastos and Schoffelen 2016) over a
pair of pre-ictal, ictal and post-ictal signals. Vertical lines indicate seizure onset and offset time points.
Synchronization during seizure is a complex, heterogeneous process over the time and space (Jiruska et
al., 2013), which has been captured by the methods in Fig. 1. However, synchronization is the highest
towards the end of seizure which may lead to spontaneous termination (Majumdar et al., 2014), and that
also has been clearly captured. Mutual information may be high due to one or more of the simultaneity
measures, only some of which have been shown in Fig. 1. Some of the measures in Fig. 1 show conflicting
trends till before the end of the seizure and that could be the reason why MI value is smaller all along than
7
any of the other measures and capturing the high synchronization trend during the offset in a sharper way
than the other methods, when they all concur.
Apart from equation (1), MI can be interpreted in another way. Entropy is the uncertainty of a single
random variable. We can define conditional entropy H ( x | y ) , which is the entropy of a random variable
conditional on the knowledge of another random variable. The reduction in uncertainty due to another
random variable is called the mutual information. For two random variables x and y this reduction is the
mutual information
I ( x, y ) H ( x) H ( x | y ) p( x, y ) log
x
y
p ( x, y )
.
p( x) p ( y )
(2)
The mutual information I ( x, y ) is a measure of the dependence between the two random variables. It is
symmetric in x and y and always nonnegative and is equal to zero if and only if x and y are independent
(Cover and Thomas, 2006, p. 6-7).
Likewise we can say – amplitude correlation is a condition under which reconstruction of amplitude of
one signal needs conditional knowledge of amplitude of the other signal, provided that there are only two
signals. In mathematical formulation it will appear as
I ( A( x ), A( y )) H ( A( x )) H ( A( x ) | A( y )) ,
(3)
where A( ) denotes the amplitude. Similarly, for phase synchronization we can write
I ( Ph ( x ), Ph ( y )) H ( Ph ( x )) H ( Ph ( x ) | Ph ( y )) ,
(4)
where Ph ( ) denotes the phase. Likewise, this can be extended to any measure of simultaneity or
interdependence between two signals. MI between x and y is then given by
I ( x, y ) I ( S ( x), S ( y )) ,
(5)
S
where S is a suitable feature of the signal for measuring simultaneity or interdependence with another
signal.
8
In case of a pair of discrete signals MI can be measured in different ways. Here we have measured MI in
terms of motifs in time series (Lin et al., 2002). Information is encoded in a time series in terms of three
point motifs or 3-motifs (Majumdar and Jayachandran, 2018). 3-motifs, generated by permutation of the 3
values, have been utilized to extract information out of EEG signals (Olofsen et al., 2008). Those 3! 6
motifs have been utilized to measure Permutation Conditional Mutual Information (PCMI) between two
signals (Li and Ouyang, 2010). PCMI gives a directional measure of how one signal is dependent on the
other.
Here we have utilized the same 3-motifs to measure MI between two discrete signals (Fig. 2). Since there
are 6 number of 3-motifs altogether let us number them from 1 to 6. Take a window of length, say 1000
samples in both the signals x and y , starting and ending at the same times across the signals. There are a
total of 998 3-motifs in the window from each of the signals. Say, the first motif in x is the motif number 1
and the first motif in y is the motif number 5 (Fig. 2). Then in the 2 998 signal motif matrix the first
1
1
column will be . The frequency density of over the 998 motif window will be p (1,5) . Similarly, if
5
5
we consider the frequency density of all the columns of the signal motif matrix, we will eventually get
p ( x, y ) and will be able to calculate I ( x , y ) from (1). p ( x ) , p ( y ) and p ( x, y ) have been shown in Fig. 3.
9
Fig. 2. Motif decomposition of discrete signals x and y (first two plots in the top).. Signal motif matrix in
the thirds row from the top, and all 6 3-motifs
3
numbered at the bottom. These are the same motifs as in
(Olofsen et al., 2008) and (Li and Ouyang, 2010).
Fig. 3. On the left, p ( x ) as frequency density of 6 3-motifs
3
in x has been shown in blue histogram and the
same for y as p ( y ) has been shown in green histogram. On the right, the joint probability density function
p ( x, y ) has been plotted.
10
For extension of this measure from two signals to more than two signals we have used the procedure of
(Schindler et al., 2007). This extension was done to generalize the correlation measure between two
epileptic iEEG signals to more than two epileptic iEEG signals during seizures. Since here our purpose is
the same, we have chosen this extension procedure to generalize MI between two signals to more than two
signals. If there are n number of iEEG channels we form the n n matrix, whose ij th entry is I ( xi , x j )
over a window, where xi is the iEEG signal collected from the i th channel. This matrix is a symmetric
matrix and therefore all eigen values are real. By sliding the window we take only the highest eigen value
from each of the windows. The plot of the highest eigen value over the time windows will give the
dominant trend of MI across all the n channels. This is akin to the principal component analysis. For a high
value of MI across all n channels, not all channels will necessarily have a strong overlap. Even if a few of
them have strong overlap and others do not have as strong overlaps, the MI across all n of them can still be
high. Unfortunately, this algorithm cannot identify which subset of channels has strong overlap, say, above
a particular threshold.
3. Data
23 seizures from 11 patients have been studied. Detail of the patients and the seizures have been
furnished in Table 1. Consciousness was impaired if the consciousness score is greater than 2 (Table 2).
Selection of patients and intracranial EEG recordings: Of the 42 adults with drug-refractory focal epilepsy
who have undergone intracranial EEG investigation to localize seizures at the University of Alabama at
Birmingham, AL level - IV epilepsy center between 2014 and 2017, we have selected 11 patients in this
study. The patient selection criteria were as following: a) seizure onset was within the mesial temporal
lobe structures (amygdala, hippocampus, parahippocampal gyrus, temporal pole); b) have undergone
anterior temporal lobectomy; c) had at least 6 months post resection follow up; and d) seizure outcome was
11
favorable (Engel I and II) (Engel et al. 1993). See Table 3 for post operative prognosis of all the 11
patients. All except one (patient 7) had previous failed epilepsy surgery due to incomplete resection of
mesial temporal lobe structures. All patients had undergone standard investigation before intracranial EEG
study, and this includes 3T MRI brain, 18-fluorodeoxy glucose PET scan, Magnetoencephalography and
scalp EEG investigation. Of the eleven subjects, ten had robot-assisted stereo EEG investigation with
sampling from the anterior and posterior hippocampus, amygdala, temporal pole, superior temporal gyrus,
orbitofrontal, anterior insula, anterior cingulate and parahippocampal gyrus. Each depth electrode had 10 –
14 contacts (PMT electrodes, 1.4 mm contacts). In one subject (subject 4) grids, strips and a depth electrode
were placed for electrocorticography targeting hippocampus, subtemporal and lateral temporal regions.
Scalp EEG was recorded from Cz, Pz. Video EEG was sampled at around 2 KHz using Natus Xltek EEG
machine (see Table 1 for detail of sample frequency). Post explantation all video EEG and other
investigations were discussed in a multidisciplinary epilepsy surgical conference to confirm the onset of
seizures and seizure onset channels. These are standard procedures followed in any level – IV epilepsy
centers. To compare mutual information findings with the seizure onset zone channels with channels that
had late seizure propagation, we have classified these channels as late (or least) involved channels (LIC).
We have selected these channels by visual interpretation of EEG in a systematic way as described below.
Initially, we have identified seizure termination and then visually analyzed EEG from all recorded
channels moving backward towards seizure onset. For focal seizures without generalization, we have
selected LIC channels that had no ictal epileptiform activity on visual interpretation. For focal seizures that
were generalized, we selected LIC channels that had late (or last) propagation of ictal epileptiform activity.
The post operative outcome was obtained from retrospective chart review. The study was approved by the
institutional review board.
Selection of seizures and scoring of consciousness: 23 seizures in 11 patients have been studied. Detail of
the patients and the seizures have been furnished in Table 1. Selection criteria for seizures were as followsa) only spontaneous seizures were selected; b) video of the seizure was available; c) electrographic
12
seizures that lacked any clinical accompaniment were excluded; d) nursing staff was able to examine the
patient during and after the seizure. In our epilepsy center we have adopted a protocol to examine the
patient during and after seizure by the nursing staffs. The examination includes : a) evaluating awareness
by interaction with patient ( asking name, place, date); b) visual attention by seeing if they follow them or
an object (such as, pen), during conversation; c) motor examination by asking them to lift arms, legs d)
speech/language by asking them to read from a board and e) asking patient to report what they feel during
seizure. These examinations were continued in the post ictal period and at times continued periodically till
the patient was back to baseline. By revieweing the video , one of the authors scored consciousness
following termination of seizure. This scale takes into account different aspects of consciousness in
humans: (i) unresponsiveness (Criteria 1 and 2); (ii) visual attention (Criteria 3); (iii) consciousness of the
seizure (Criteria 4); (iv) adapted behavior (Criteria 5); and (v) amnesia (Criteria 6 and 7) (Arthuis et al.
2009).
Table 1: Summary of patient demographics and seizures
Sz No.
Age
Gender
Onset
Offset
SOZ Channels
Pre sz
vigilance
Sz
Post sz
behavioral
change
1
2
23
F
3
4
5
6
7
19
M
38
M
300
300
300
300
300
300
300
580
482
480
473
377
371
482
Left Hpc, PHG
Left Hpc, PHG
Right Amyg Hpc
Right Amyg Hpc
Right Amyg Hpc
Right Hpc, PHG
Right Hpc, PHG
SP
CP
CP
CP
CP
sGTC
CP
21
F
Awake, alert
Awake, confused
Awake, confused
Awake, confused
Awake, confused
Awake, confused
Awake, confused
Awake, confused
300
467
Left PHG, STG, MTG,
300
300
300
375
351
389
Left PHG, STG, MTG
Left PHG, STG, basal temp
Left Amyg, Hpc, Tp
awake
awake
awake
awake
awake
sleep
awake
Stg II
sleep
Stg II
sleep
awake
awake
300
300
300
300
300
300
419
352
390
434
400
383
Left Amyg, Hpc, Tp
Right Hpc, PHG, basal temp
Right Hpc, PHG, basal temp
Left mesial temp remnant
Left mesial temp remnant
Right Hpc, PHG, basal temp
awake
awake
awake
awake
awake
Stg II
sGTC
sGTC
sGTC
CP
CP
sGTC
8
9
10
11
12
13
14
15
16
17
25
F
42
M
24
F
44
M
sGTC
Awake, confused
CP
CP
CM
Awake, confused
Awake, confused
Obtunded,
minimal response
Awake, confused
Awake, confused
Awake, confused
Awake, confused
Obtunded,
13
sleep
minimal response
Stg II
Obtunded,
300
388
Right PHG, basal temp ,
sleep
sGTC minimal response
37
M
Awake, confused
300
367
Left Hpc, PHG, basal temp
awake
CP
19
Awake, confused
300
363
Left Hpc, PHG, basal temp
awake
CP
20
22
M
Awake, confused
300
455
Left
Hpc,
Amyg
awake
CP
21
Awake, confused
300
431
Left Hpc, Amyg
awake
CP
22
19
M
Awake, confused
300
447
Right Hpc, Amyg
awake
CP
23
Note: Sample frequency is 2048 Hz except for seizures 11, 12 (2000 Hz each) and 19, 20 (1000 Hz each). Hpc = Hippocampus,
18
PHG = Parahippocampal gyrus, Amyg = Amygdala, STG = Superior temporal gyrus, MTG = Medial temporal gyrus, Tp =
Temporal pole, SP = Simple partial seizure (new classification focal seizure with awareness), CP = complex partial (new
classification focal seizure with impaired awareness), sGTC = secondary generalized tonic-clonic (new classification focal to
bilateral tonic-clonic).
4. Results
a. Progressive increase in MI toward seizure termination and in post ictal period: As complex partial
seizures progress from onset to termination, there is an increase in MI across all frequency bands
(delta, theta, alpha, beta and gamma) and across all seizure onset zone (SOZ) channels (the most
involved channels) and all least involved channels (LIC, Fig. 4). An example of this is represented in
Fig. 5 (seizure 20 of patient 9), where consciousness score (Arthuis et al. 2009) after the seizure
offset is 6. This means the consciousness is significantly impaired in the post ictal periods and this is
expressed by the state awake/confused (Table 1). Although the MI is increased towards offset in all
frequency bands (delta to gamma), the trend is weakest in delta and strongest in gamma band.
Furthermore, high MI towards offset trend is sharper in SOZ channels than the LIC. Both the trends
remained preserved through all 23 seizures (Supplement). These important trends were observed with
MI were more distinct than the trends plotted with AC, PLV, PS, h-square (Fig. 1). If the seizure
duration is subdivided into two equal parts then MI across the SOZ channels is higher in the second
half than in the first with the highest degree of statistical significance among MI, AC, PLV, PS and
h-square (Table 4, Table 5, Table 6, Table 7), except PS has marginally better significance in gamma
band.
14
Table 2: Seizure duration and total consciousness score after seizure termination
Sz No.
Sz duration in sec (#SOZ channels, #LIC)
Total Score
280 (12, 31)
0
1
182 (12, 31)
3
2
180 (6, 12)
3
3
173
(6,
12)
1
4
77 (6, 12)
2
5
71 (7, 6)
4
6
182 (7, 6)
4
7
167
(10,
12)
6
8
75 (10, 12)
2
9
51 (10, 12)
8
10
89 (12, 16)
7
11
119
(12,
16)
9
12
52 (10, 5)
4
13
90 (10, 5)
9
14
134 (12, 14)
1
15
100
(12,
14)
5
16
83 (6, 6)
8
17
88 (6, 6)
7
18
67 (5, 7)
4
19
63
(5,
7)
6
20
155 (11, 26)
6
21
131 (11, 26)
4
22
147 (8, 6)
4
23
Note: Total number of implanted channels per patient varies from 150 to 240. SOZ = seizure onset zone, LIC = least involved
channels.
15
Fig. 4. Electrical activities in seizure onset zone channels and least involved channels. Red circles indicate
seizure onset patterns in iEEG recording. Red vertical line in the top plot indicates seizure onset time. Red
rectangle indicates the activities in the least involved channels, which are magnified in the bottom plot.
b. Comparison of MI with other measures of synchronization: Each of the 11 patients was implanted
with 150 to 240 iEEG electrodes for evaluation of possible surgical resection. High degree of
synchronization (measured by h-square) across temporal lobe has been implicated in loss of
consciousness during temporal lobe seizures (Arthuis et al., 2009). Since multidimensional
synchronization is difficult to measure only a few pairwise synchronization has been studied in
(Arthuis et al., 2009). We have extended pairwise analysis of MI to higher dimension following a
previous published study (Schindler et al., 2007). This analysis is not applicable to h-square because
it is not a symmetric measure. However, if we are to measure MI across all the 150 to 240 channels
we will have to calculate n n matrix multiplication for 150 n 240 , for each time window across
the n iEEG signals. The computation becomes so huge that for little more than 100 channels that
dual Xeon E5-2620v3 processor based GPU workstation (Nvidia K40 Tesla card) with 256 GB RAM
16
ran out of memory midway through the computation (executed through MATLAB). So, we kept our
analysis confined within the most involved channels (the seizure onset zone channels) and least
involved channels (Fig. 4) in each seizure (this was determined by the author SP, who is an
epileptologist). We also arbitrarily added other channels in the above two sets, but the trend didn’t
change (Fig. 5). From this we conclude that MI remained high across the channels towards the offset
of the seizures particularly in the higher frequency bands implicated in higher cognitive functions
and consciousness.
For normal functioning of the brain synchronization will have to be at a normal level. Too high or too
low a level of synchronization is pathological. We found support for this hypothesis through the
multidimensional MI measure (Table 4). MI is higher in beta and gamma bands in the second half of the
seizures (towards the offset) across the SOZ channels ( p 0.05 ). The same finding in all other
frequency bands is not statistically significant as can be seen in Table 4. Multidimensional extension of
MI was done flowing (Schindler et al. 2007) by highest eigenvalue of the MI square matrix. The same
extension technique was followed for all other symmetric synchronization measure presented in Table 5,
Table 6 and Table 8. In all the Tables from 4 through 8 the p value is for the hypothesis that the
synchronization value will be higher during the second half of the seizure than in the first.
17
Fig. 5. Mutual information across all the 5 electrodes from the SOZ (left column) and all the 7 LIC (right
column) of seizure 20 in Table 1, in the frequency bands of delta (0 – 4 Hz) (A(i) for SOZ and A(ii) for
LIC), theta (4 – 8, Hz) (B(i) for SOZ and B(ii) for LIC), alpha (8 – 12 Hz) (C(i) for SOZ and C(ii) for LIC),
beta (12 – 30 Hz) (D(i) for SOZ and D(ii) for LIC) and gamma (30 – 80 Hz) (E(i) for SOZ and E(ii) for
LIC). Red vertical lines indicate seizure onset and offset time.
Table 3: Post operative prognosis of the patients
Subjects
1
Epilepsy
duration
(years)
6
2
4
Aura
LOC
(Y/N)
Surgery
Experiential
feeling, Deja vu
Warm feeling
over chest
Y
Left ATL
Y
Right
ATL
Followup
(months)
9
Outcome
Histopathology
I
HS
8
II
Granulomatous
inflammatory
18
3
35
Déjà vu,
epigastric
Abnormal
sensation in
head,
experiential
feeling
Anxious,
intense fear
Deja vu
Y
4
9
5
2
6
31
7
Right
ATL
Left ATL
extended
to lateral
temporal
14
II
Gliosis, FCD I
12
I
Gliosis
Y
Left ATL
16
I
Gliosis
Y
14
II
HS
7
II
Gliosis
18
I
HS
Y
Right
ATL
Left
mesial
residual
structure
s
Right
ATL
Left ATL
23
Dizziness,
experiential
feeling
Y
8
38
Déjà vu.
Y
9
12
10
3
11
2
Déjà vu,
anxious feeling
Experiential
feeling
Deja vu
20
I
HS
Y
Left ATL
14
II
Non specific
Y
Y
Right
6
I
HS
ATL
ATL= Anterior temporal lobectomy; FCD = Focal cortical dysplasia; HS = Hippocampal sclerosis; LOC = Loss of
consciousness; Outcome I and II pertain to Engel class I and Engel class II epilepsy respectively.
Table 4: Statistical significance values of MI being higher during the second half of the seizure than the
first according to Wilcoxon Rank-Sum test across all 23 seizures of 11 patients
Frequency band
SOZ channels
LIC
Delta (0 – 4 Hz)
p=0.7584 (>0.05)
p=0.9125 (>0.05)
Theta (4 – 8 Hz)
p=0.7752 (>0.05)
p=0.6604 (>0.05)
Alpha (8 – 12 Hz)
p=0.6604 (>0.05)
p=0.9125 (>0.05)
Beta (12 – 30 Hz)
p=0.0331 (<0.05)
p=0.6764 (>0.05)
Gamma (30 – 80 Hz)
p=0.0026 (<0.05)
p=0.3795 (>0.05)
Interestingly, gamma (Fries, 2009) and beta (Spitzer and Haegens, 2017) rhythms have been implicated
mostly in conscious information processing by the brain. It has been shown that fast activity (at the beta
range) across both hemispheres in the temporal lobe along with slow (1 – 2 Hz) activity in the fronto-
19
parietal region leads to loss of consciousness during complex partial temporal lobe seizures (Englot et al.,
2010). Clearly, beta band synchronization across the temporal lobe is likely to be high during the seizure.
We have specifically shown that MI (in Table 4) and h-square (Wendling et al. 2001) (in Table 7) are high
across all the SOZ channels during the second half of the temporal lobe seizures in beta band with
p 0.033 and p 0.002 respectively (since h-square is not a symmetric measure, its extension from two
channels to more than two channels is different from the other bivariate measures presented in Table 4,
Table 5, Table 6 and Table 8). The same is true for gamma band with p 0.026 and p 0.002
respectively. Gamma band higher synchronization is statistically significant ( p 0.010 ) also by PS
measure across the SOZ channels in the second half of the seizure than in the first (Table 5).
Table 5: Statistical significance values of PS being higher during the second half of the seizure than the
first according to Wilcoxon Rank-Sum test across all 23 seizures of 11 patients
Frequency band
SOZ channels
LIC
Delta (0 – 4 Hz)
p=0.3562 (>0.05)
p=0.7088 (>0.05)
Theta (4 – 8 Hz)
p=0.5385 (>0.05)
p=0.5828 (>0.05)
Alpha (8 – 12 Hz)
p=0.9475 (>0.05)
p=0.6134 (>0.05)
Beta (12 – 30 Hz)
p=0.1471 (>0.05)
p=0.8433 (>0.05)
Gamma (30 – 80 Hz)
p=0.0108 (<0.05)
p=0.5385 (>0.05)
Table 4 through Table 8 show that among the bivariate measures of synchrony like MI, PS, AC, h-square
(Wendling et al. 2001) and coherence (Bastos and Schoffelen 2016), extended to most involved (SOZ
channels) and least involved channels, only MI and h-square show statistically significant synchronization
across the most involved channels in beta and gamma range. Statistically significant synchronization across
all the 23 seizures of 11 patients in beta and gamma band supports the finding of (Arthuis et al. 2009) that,
loss of consciousness happens during temporal lobe seizures due to wider synchrony across brain regions
20
involved in processing of awareness. Gamma synchronization takes place at a smaller spatial scale and beta
synchronization takes place at a larger spatial scale (Kopell et al. 2000). When both of them occur with
high significance across the seizure onset zone towards seizure termination and in post ictal state, that
indicates local gamma synchronized clusters (the small localized brain regions oscillating at gamma
rhythm) have become synchronized among themselves across wider brain regions leading to impairment of
consciousness (Arthuis et al. 2009).
Table 6: Statistical significance values of AC being higher during the second half of the seizure than the
first according to Wilcoxon Rank-Sum test across all 23 seizures of 11 patients
Frequency band
SOZ channels
LIC
Delta (0 – 4 Hz)
p=0.8951 (>0.05)
p=0.9475 (>0.05)
Theta (4 – 8 Hz)
p=0.8261 (>0.05)
p=0.6134 (>0.05)
Alpha (8 – 12 Hz)
p=0.6604 (>0.05)
p=0.8090 (>0.05)
Beta (12 – 30 Hz)
p=0.3795 (>0.05)
p=0.9300 (>0.05)
Gamma (30 – 80 Hz)
p=0.2916 (>0.05)
p=0.5385 (>0.05)
Table 7: Statistical significance values of h-square (Wendling et al. 2001) being higher during the second
half of the seizure than the first according to Wilcoxon Rank-Sum test for all 23 seizures of 11 patients
Frequency band
SOZ channels
LIC
Delta (0 – 4 Hz)
p= 0.2916 (>0.05)
p=0.9475 (>0.05)
Theta (4 – 8 Hz)
p= 0.2423 (>0.05)
p=0.3229 (>0.05)
Alpha (8 – 12 Hz)
p= 0.0054 (<0.05)
p=0.2720 (>0.05)
Beta (12 – 30 Hz)
p= 0.0024 (<0.05)
p=0.3916 (>0.05)
21
Gamma (30 – 80 Hz)
p= 0.0023 (<0.05)
p = 0.9825
(>0.05)
Note: Since h-square is a non-symmetric measure between two channels, its multidimensional extension
was done by taking average across all the pairwise values.
Table 8: Statistical significance of coherence values (Bastos and Schoffelen 2016) being higher during the
second half of the seizure than the first according to Wilcoxon Rank-Sum test across all 23 seizures of 11
patients
Frequency band
SOZ channels
LIC
Delta (0 – 4 Hz)
p=0.5531 (>0.05)
p=0.9650 (>0.05)
Theta (4 – 8 Hz)
p=0.9650 (>0.05)
p=0.6134 (>0.05)
Alpha (8 – 12 Hz)
p=0.3916 (>0.05)
p=0.7752 (>0.05)
Beta (12 – 30 Hz)
p=0.2269 (>0.05)
p=0.8951 (>0.05)
Gamma (30 – 80 Hz)
p=0.1410 (>0.05)
p=0.7088 (>0.05)
One important point to note that all the bivariate synchronization measures considered in this work,
except h-square are symmetric, that is, synchronization between channels i and
j is equal to
synchronization between channels j and i . So, we can form the symmetric n n matrix ( n is the number
of channels, across which synchronization is being measured) whose ij th entry is the synchronization
between channels i and j . Since the matrix is real symmetric matrix, all its eigenvalues will be real. The
highest eigenvalue of this matrix will give the dominant trend synchronization across all the n channels
(Schindler et al. 2007). Since h-square is not a symmetric measure, this method of extension to more than
two channels will not work, and therefore we took average of the h-square values across all channel pairs in
one direction (from channel i to the channel j for the synchronization between i th channel and j th
channel). Obviously, it is a completely different extension method and therefore results of Table 4 (MI),
22
Table 5 (PS), Table 6 (AC) and Table 8 (coherence) are not comparable with those of Table 7 (h-square).
5. Discussion
Unlike the previous study (Arthuis et al. 2009), where patient’s consciousness score was measured
during seizure, we measured the same consciousness score immediately after the seizure offset (Table 2).
This score was originally proposed in (Arthuis et al. 2009) and a score of 3 or more means impaired
consciousness. The higher the score is greater is the impairment or loss of consciousness (LOC). The very
first seizure is simple partial and therefore the score is zero (Table 2). Out of remaining 22 complex partial
seizures the score at the post ictal period is either 1 or 2 only for the 4 out of 22 ( 18% ) and this indicates
there was no measurable LOC for these 4 seizures after the offset. For remaining 82% of the seizures there
was LOC after the seizure offset.
Our study of LOC associated with complex partial seizure is different in several ways than the precious
study (Arthuis et al. 2009). First major difference is methodological. (A) They measured synchronization
by h-square, which is a nonlinear, asymmetric correlation measure, whereas we measured synchronization
by mutual information (MI), which is a symmetric, bivariate measure. (B) Their synchronization measure
was bivariate and was carried out across only a few channel pairs, whose choice may be biased, whereas
we extended the bivariate MI to multivariate MI and applied it on all the seizure onset zone (SOZ) channels
and also on least involved in seizure channels. Total number of channels in our data from 11 patients was
between 150 and 240 and therefore it was not possible to compute all the pairs. (C) We compared MI with
all major synchronization measures in neuroscience, which showed that MI gives most statistically
significant measure among all of them except h-square, the measure used in (Arthuis et al. 2009). However,
multidimensional extension of h-square and MI are totally different and their statistical significance values
in Table 6 and Table 3 respectively are not comparable to each other. (D) Unlike in (Arthuis et al. 2009) we
have measured the synchronization in different frequency bands that have significance in cognition namely,
delta, theta, alpha, beta and gamma. Statistically significant synchronization was observed across the SOZ
23
channels only in beta and gamma range by MI and in gamma range also by phase synchronization (PS). hsquare gives higher significant synchronization at beta and gamma band and even shows synchronization at
alpha band. No other measure showed statistically significant synchronization across all the seizures at
alpha band. h-square tends to give high value of synchronization compared to other measures (see Fig. 1 for
a bivariate implementation), which might affect the results reported in (Arthuis et al. 2009). (E) (Arthuis et
al. 2009) assessed consciousness during complex partial seizures, whereas we assessed it immediately after
the offset, but reached at similar conclusions. This can be considered an extension of the earlier work. (F)
Our study remained confined within temporal lobe. Unlike (Arthuis et al. 2009) we could not include
thalamus and parietal cortex for clinical constraints. But since synchronization across the SOZ channels
was quite significant in beta and gamma range, they likely have spread to wider brain areas (Kopell et al.
2000), supporting the study of (Arthuis et al. 2009). Since beta and gamma band EEG are more important
for wide ranging cognitive tasks including sensory awareness, higher than usual synchronization in them is
likely to lead to LOC in different degrees, which is evident from Table 2.
If synchronization is due to AC or PS or coherence or due to any other measure, MI is likely to reflect
that synchronization, but not the other way round. In other words, if PS or AC is high MI will also have an
upward trend, but if MI is high PS or AC may not show any increasing trend at all, because MI may be
high due to some other synchronization measure(s). This is the reason the numerical value to MI is lower
than other measures (Fig. 1). MI maintains a more stable trend (that is, less jittery) compared to other
synchronization measures (Fig. 1). In short, the measure of synchronization given by MI is more
generalized and robust than many other widely used synchronization measure used in neuroscience. If this
is coupled with the fact that semantic information in a discrete signal is embedded in terms of 3-point
motifs (Majumdar and Jayachandran 2018) then the way we have calculated the MI by frequency
distribution of combination of motifs across two signals is a better measure of interdependence of the two
signals than possible by PS or AC or coherence or some other measure alone.
It has been reported that, slow delta wave activity (1 – 2 Hz) in the bilateral frontal and parietal cortices
24
during complex-partial seizures coupled with unilateral mesial temporal fast seizure activity spreading to
the bilateral temporal lobes, might be responsible for impaired consciousness (Englot et al. 2010). Higher
synchronization across the channels in temporal lobe in beta and gamma range during the latter half of
complex partial seizure is indicative of the propagation of the fast seizure activity in the temporal lobe.
However, by all synchronization measures that we studied in this work the delta band synchronization in
temporal lobe remained insignificant (Tables 4 through 8). This means there is no delta wave propagation
from temporal lobe to outside. The delta wave observed in temporal and parietal cortices are not related to
the temporal lobe seizures.
One important finding is mutual information (which is a form of synchronization, see Fig. 1) across the
seizure onset zone channels is more towards the seizure offset than any other duration, whereas mutual
information is more either at the beginning or at the middle of seizure duration across the least involved
channels (Fig. 5). This trend has been observed in the gamma band in 17 out of 22, that is, in 77% of the
complex partial seizures that we studied (see the Supplement). The same trend, to a lesser extent, has been
observed in beta band too (Fig. 5 and Supplement). In most of the cases mutual information across the least
involved channels increased initially and as the seizure evolved towards the termination and post ictal state
there was a steady increase in mutual information over the seizure onset zone channels (Fig. 5 and
Supplement). High synchronization leading to seizure termination has already been observed in multiple
studies (Schindler et al. 2007, Jiruska et al. 2013, Prasad et al. 2013, Majumdar et al. 2014). Here we have
shown that high synchronization persists often beyond termination from least involved channels to seizure
onset zone in beta and gamma bands and impairs consciousness.
We have used here to assess the state of consciousness of the patients according to the consciousness
scoring scheme introduced by (Arthuis et al. 2009). However, there seems to be no straightforward (or
linear, to be more precise) relationship between the level of synchronization and the level of consciousness.
It was reported that excessive synchronization across wide brain regions during complex partial seizure is
responsible for loss of consciousness (Arthuis et al. 2009). But if synchronization is high the loss of
25
consciousness may not be as high and also the other way round as can be verified from the Supplement,
where we have given all the mutual information measure across the seizure onset zone channels as well as
the least involved channels before, during and after all the 23 seizures along with the consciousness score
of the patient after the seizure offset. For example, seizures 21 and 22 are from the same patient with the
same electrode implantation. The amount of mutual information across the seizure onset zone channels and
also across the least involved channels in beta and gamma band is always less than 4 for seizure 21
(Supplement) with a consciousness score 6 after seizure offset, but for seizure 22 the mutual information in
the same channels and in the same bands for the same duration is almost always higher than 4 and can be as
high as 20, but with a consciousness score 4 (Supplement). This means loss of consciousness is more after
seizure 21 than after seizure 22.
Among all the synchronization measuring algorithms we studied in this work h-square is the most
computer time intensive algorithm even in bivariate case. The other synchronization measures that we
studied in this work are all symmetric in the bivariate case (and much less time intensive to compute than
h-square) and therefore their pairwise values will fill a square matrix whose highest eigenvalue
(eigenvalues are always real as the matrix is symmetric) will give the principal or dominating trend of the
synchronization measure across all the channels. Since in this extension matrix inversion is involved the
time complexity is quite significant. On the other hand, since h-square is not a symmetric measure, we
cannot use the principal component method for extension to more than 2 channels. We simply took average
of pairwise h-square values for all the channel pairs. Even then multidimensional extension of h-square is
much more time consuming than the same for the other synchronization measures studied here.
Conclusion
Here we have proposed an algorithm for measuring mutual information between two discrete signals and
then extended it to more than two signals. We have compared this measure with a number of other widely
used bivariate signal dependency measures in neuroscience both for a pair of signals and for more than two
26
signals and determined their statistical significance. We have demonstrated that mutual information is a
robust, generalized signal dependency measure. Then we applied this and other synchronization measures
namely, (Hilbert) phase synchronization, amplitude correlation, nonlinear correlation (h-square) and
coherence on multichannel iEEG data consisting of 23 temporal lobe onset seizures recorded from 11
patients. Statistically significant synchronization across the seizure onset zone was found in beta and
gamma range during the latter part of complex partial seizures in conjunction with impaired consciousness
(determined for 77% of the complex partial seizures) after the offset in 82% of them (Supplement). Our
data shows that there is reasonable association between higher level of synchronization and loss of
consciousness as reported in (Arthuis et al. 2009).
However, the relationship between the level of synchronization and the amount of loss of consciousness
is far from obvious. More elaborate investigation needs to be undertaken in this regard recruiting brain
areas like thalamus and parietal cortex, which are implicated more in consciousness than temporal lobe.
The generalized mutual information that we developed here can be applied on more than two channels
sampled from cortical areas implicated in consciousness to determine the overall level of mutual
information across those regions during and after complex partial seizures. Then attempt can be made to
relate the ensemble mutual information at different frequency bands to the level of loss of consciousness
according to consciousness score to extend our current work and the work reported in (Arthuis et al. 2009).
It will also worth investigating the relationship between delta band ensemble mutual information in frontal
and parietal cortices and beta and gamma band mutual information in unilateral temporal lobe seizure onset
zone with respect to the loss of consciousness. This will be an extension of the work reported in (Englot et
al. 2010).
Any discrete signal can be decomposed into 13 different 3-point motifs, each of which is encoding
information into that signal in the form of its shape (Majumdar and Jayachandran 2018). Mutual
information between such representations of signals is likely to be more meaningful and informative.
27
Acknowledgement
This work was supported by the Department of Biotechnology, Government of India grant no.
BT/PR7666/MED/30/936/2013 and National Science Foundation (USA) award no. NSF RII-2 FEC OIA
1632891.
References
M. Arthuis, L. Valton, J. Regis, P. Chauvel, F. Wendling, L. Naccache, C. Bernard and F. Bartolomei,
2009. Impaired consciousness during temporal lobe seizures is related to increased long-distance corticosubcortical synchronization, Brain 132, 2091–2101.
S. Aydore, D. Pantazis and R. M. Lehay, 2013. A note on phase locking value and its properties,
NeuroImage 74, 231–244.
C. Babiloni, F. Vecchio, G. Mirabella, M. Buttiglione, F. Sabastiano, A. Picardi, G. Di Gennaro, P. P.
Quarato, L. G. Grammaldo, P. Buffo, V. Esposito, M. Manfredi, G. Cantore and F. Eusebi, 2009.
Hippocampal, amygdala and neocortical synchronization of theta rhythms is related to an immediate recall
during Rey auditory verbal learning test, Hum. Brain Map. 30, 2077–2089.
E. Basar, C. Basar-Eroglu, S. Karakas and M. Schurmann, 2001. Gamma, alpha, delta and theta oscillations
govern cognitive processes, Int. J. Psychophysiol. 39, 241–248.
A. M. Bastos, J.-M. Schoffelen, 2016. A tutorial review of functional connectivity analysis methods and
their interpretational pitfalls, Front. Syst. Neurosci., 9, 175. doi: 10.3389/fnsys.2015.00175.
H. Blumenfeld and J. Taylor, 2003. Why do seizures cause loss of consciousness? Neuroscientist 9, 301–
310.
T. M. Cover and J. A. Thomas, 2006. Elements of Information Theory, 2nd ed., John Wiley & Sons,
Hoboken, NJ, USA.
F. Crick and C. Koch, 1990. Some reflections on visual awareness, Cold Spring Harbor Symp. Quant. Biol.
55, 953–962.
28
J. Engel Jr., P. C. Van Ness, T. B. Rasmussen, L. M. Ojemann, 1993. Outcome with respect to epileptic
seizures, In: J. Engel Jr. (ed.) Surgical Treatment of the Epilepsies, 2nd ed. Raven Press, New York, 609–
621.
D. J. Englot, L. Yang, H. Hamid, N. Danielson, X. Bai, A. Marfeo, L. Yu, A. Gordon, M. J. Purcaro, J. E.
Motelow, R. Agarwal, D. J. Ellens, J. D. Golomb, M. C. F. Shamy, H. Zhang, C. Carlson, W. Doyle, O.
Devinsky, K. Vives, D. D. Spencer, S. S. Spencer, C. Schevon, H. P. Zaveri and H. Blumenfeld, 2010.
Impaired consciousness in temporal lobe seizures: role of cortical slow activity, Brain 133, 3764–3777.
J. Fell and N. Axmacher, 2011. The role of phase synchronization in memory processes, Nat. Rev.
Neurosci. 12, 105–118.
P. Fries, 2009. Neuronal gamma-band synchronization as a fundamental process of cortical computation,
Ann. Rev. Neurosci. 32, 209–224.
B. Guntekin and E. Basar, 2016. Review of evoked and event-related delta responses in the human brain,
Int. J. Psychophysiol. 103, 43–52.
P. Jiruska, M. de Curtis, J. G. R. Jefferys, C. A. Schevon, S. J. Schiff and K. Schindler, 2013.
Synchronization and desynchronization in epilepsy: controversies and hypothesises, J. Physiol. 591, 787–
797.
G. G. Knyazev, J. Y. Slobodskoj-Plusnin and A. V. Bocharov, 2009. Event-related delta and theta
synchronization during explicit and implicit emotion processing, Neurosci. 164, 1588–1600.
N. Kopell, G. B. Ermentraut, M. A. Whittington, R. D. Traub, 2000. Gamma rhythms and beta rhythms
have different synchronization properties, PNAS. 97: 1867–1872.
X. Li and G. Ouyang, 2010. Estimating coupling direction between neuronal populations with permutation
conditional mutual information, NeuroImage 52, 497–507.
J. Lin, E. Keogh, S. Lonardi and P. Patel, 2002. Finding motifs in time series, Proc. SIGKDD’02, the 8th
ACM workshop on knowledge discovery and data mining, Edmonton, Alberta, Canada, 53–68.
29
K. Majumdar, P. D. Prasad and S. Verma, 2014. Synchronization implies seizure or seizure implies
synchronization? Brain. Topogr. 27, 112–122.
K. Majumdar and S. Jayachandran, 2018. A geometric analysis of time series leading to information
encoding and a new entropy measure, J. Comp. Appl. Math. 328, 469–484.
A. R. McIntosh, M. N. Rajah and N. J. Lobaugh, 1999. Interactions of prefrontal cortex in relation to
awareness in sensory learning, Science 284, 1531–1533.
L. Melloni, C. Molina, M. Pena, D. Torres, W. Singer and E. Rodriguez, 2007. Synchronization of neural
activity across cortical areas correlates with conscious perception, J. Neurosci. 27, 2858–2865.
F. Mormann, K. Lehnertz, P. David and C. E. Elger, 2000. Mean phase coherence as a measure for phase
synchronization and its application to the EEG of epilepsy patients, Physica D 144, 358–369.
E. Olofsen, J. W. Sleigh and A. Dahan, 2008. Permutation entropy of the electroencephalogram: a measure
of anaesthetic drug effect, Brit. J. Anasthes. 101, 810–821.
P. D. Prasad, S. V. Datta, K. Majumdar, 2013. Enhanced phase and amplitude synchronization towards
focal seizure offset, Clin. EEG. Neurosci. 44, 16–24.
E. Rodriguez, N. George, J.-P. Lachaux, J. Martinerie, B. Renault and F. J. Varela, 1999. Perception’s
shadow: long-distance synchronization of human brain activity, Nature 397, 430–433.
K. Schindler, H. Leung, C. E. Elger and K. Lehnertz, 2007. Assessing seizure dynamics by analysing the
correlation structure of multichannel intracranial EEG, Brain 130, 65–77.
B. Spitzer and S. Haegens, 2017. Beyond the status quo : a role for beta oscillations in endogenous content
(re)activation, eNeuro 4(4), 1–15.
P. N. Steinmetz, A. Roy, P. J. Fitzgerald, S. S. Hsiao, K. O. Johnson and E. Neibur, 2000. Attention
modulates synchronized neuronal firing in primate somatosensory cortex, Nature 404, 187–190.
C. Tallon-Baudry, 2009. The roles of gamma-band oscillatory synchrony in human visual cognition, Front.
Biosci. 14, 321–332.
30
L. M. Ward, 2003. Synchronous neuronal oscillations and cognitive processes, Trends Cog. Sci. 7, 553–
559.
F. Wendling, F. Bartolomei, J. J. Bellanger and P. Cauvel, 2001. Interpretation of interdependencies in
epileptic signals using a macroscopic physiological model of the EEG, Clin. Neurophysiol. 112, 1201–
1218. |
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
780
Article
Experiential Consciousness Research on the Physics of Now (Part I)
Amrit S. Sorli*
ABSTRACT
In the model of the universe we developed, the “mathematical universe” is the direct medium of
the information between the particles. In the mathematical universe the transfer of information is
instant. In the material universe, at the scale of photons, information spreads at the speed of light.
Consciousness is not information. Consciousness is manifesting and acting through the
mathematical universe and DNA down into the level of the material world. Within this context,
the human thought process is not an “energy phenomenon” carried by the electromagnetic waves
as many people imagine. Thought is rather a phenomenon that belongs in the realm of the
“mathematical universe”. Therefore, thinking has tremendous power. Any thought impregnates
the entire universe. With thoughts and potent visualization one can eliminate certain physical
problems in the body. When the mind is linked with consciousness harmonious thoughts are
created. When the mind is subject of its own egoism, destructive thoughts are created. Emotions
are an actual “energy/material” phenomenon, tied to the secretion of hormones on human
physiology. Telepathy takes place via a mathematical universe between two or more minds.
Part I of this two-part article contains: 1. Time we measure with clocks has only a mathematical
existence; 2. A critical survey on Higgs boson and graviton; & 3. Relative velocity of material
changes has its origin in the space density; 4. Mathematical universe is a medium of quantum
entanglement; and 5. Unification of the “double nature” of light.
Key Words: physics of now, mathematical universe, God, experiential consciousness,
information, thought, emotion, mind, Consciousness, material world, instantaneous, telepathy.
Prologue
…there is something essential about the NOW which is just outside the realm of science. People
like us, who believe in physics, know that the distinction between the past, present and future is
only a stubbornly persistent illusion. The most beautiful thing we can experience is the
mysterious. It is the source of all true art and science.
Albert Einstein
*Correspondence: Amrit S. Sorli, Independent Researcher. Email: sorli.amrit@gmail.com
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
781
1. Time we measure with clocks has only a mathematical existence
Every view of the world, as well as any physical theory, offers only a limited perceptual view.
This is because our view only extends to the edge of those perceptual horizons. With growing
knowledge and the expansion of our own internal horizons, we can see and experience deeply
than before. This is similar to how in physics every new theory extends and expands the horizons
of our understanding and our experience of the universe and life in general.
Often in everyday life, we will refute old views and we replace them with newer views that
better suit us; newer views that can afford us further development. In physics this is rare. Old
theories are not generally refuted and simply cast off. In physics the old theories are enfolded
into the new theories which are more universal in nature. This is one of the many beauties of
physics.
An illustration of that point, what we think of as "Einstein’s physics," explains the precession of
the planets which the "Newtonian physics" failed to explain. However, "Einstein’s physics" does
not need to negate "Newtonian physics" but rather it puts “Newtonian Physics” in a larger
context and simply extends and expands its horizons. Thankfully, physics has the mechanism of
permanent and recurrent "self-checking". That is, every thesis is confirmed by experiments in
which the phenomenon in question is measured with appropriate instruments. Physicists then
check to see if the results obtained via measurement correspond to the theoretical postulation.
One defining feature you find in physical theories is that the verification of the validity of the
theory will include an option that the whole thing could be wrong. In physics, there simply are
no "absolute truths". It is understood that all valid theories describing phenomenon can be
improved upon. A particular, given theory is only considered valid as long as some new
experiment proves that it is not valid to describe a newly discovered phenomenon. Physicists will
then go on to refine the new horizon-extending theory in order to include the newly discovered
phenomena and back it up with advanced mathematical models.
We can find a good example of this pattern of development of theories in the history of the
understanding of the speed of light. Around the end of the 19th century, physicists discovered
that light has a constant speed. The speed of light was found to be unchanged regardless if you
moved towards or away from the light source. Newtonian physics was not able to describe this
extraordinary property of light. Physicists began to think about a new mathematical model to
describe the constancy of the speed of light. German mathematician Hermann Minkowski went
on to develop a four-dimensional geometry, where the fourth dimension X4 is a product of time
and the speed of light. Einstein then took the baton and applied this model to describe the speed
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
782
of light as a constant for the stationary and moving observers. In these theories, physics had won
another victory.
However, a byproduct of this same victory was that an inherent misunderstanding arose.
Unfortunately, physicists began to see time as a fourth dimension of space. Even though a
mathematical model of Minkowski’s confirms that the fourth-dimension known as X4 is the
product of time, and imaginary number i, and the speed of light: X 4 ict . This formalism
however, clearly reveals that time “t” is not the 4th dimension of space known as “X4”. Physics in
the early 20th century felt that the space-time fabric was the fundamental "arena" in which the
universe existed. Yet, the idea of time as a fourth-dimension of space has never been truly been
verified experimentally. I don’t think most physicists are ready to face this fact.
A century after Einstein, I have created a new mathematical model of time, where time is
essentially and simply a numerical order, i.e. the sequence of changes in the universe. For the
basic "arena" of the universe I have chosen the three-dimensional universal space, which was
designed a century ago by the German physicist Max Planck. Planck believed that universal
3
space consists of three dimensional and fundamental units of space l p :
( G ) 3
l
,
c9
3
p
In the equation above is the reduced Planck constant, G is the gravitational constant and c
is the light speed. You can imagine universal space being composed out of very small bubbles,
which are connected.
In a three dimensional space time t is measured with clocks. Time is only the numerical order of
change, which is only a mathematical quantity. I do not deny the existence of time, I simply
ascribe to “time” a new meaning: time is not the fourth dimension of space in which the changes
occur, time is just a mathematical sequence of changes that are taking place within the threedimensional space of the universe. Here below we see the fundamental unit of time which is
known as Planck time t p :
tp
G
.
c5
To elucidate this notion even further, a photon is moving through space only, not through spacetime. The smallest distance photon can travel is the Planck distance l p :
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
lp
783
G
.
c3
Each Planck distance l p that photon is passing at light speed c corresponds to exactly one
Planck time t p :
c
l px
t px
.
Measured time t is the sum of all Planck times t p :
n
t t p1 t p2 ... t pn t px .
X 1
This new conception of time widens the perceptual horizon of Relativity. It successfully
describes the type of phenomena that the out-dated space-time model failed to include within its
framework. Taken within this new contextual view, time becomes a mathematical quantity that
exists in the universe independently of physicists and their measurements. Some physicists like
American physicist Max Tegmark, postulate that mathematics exists in the universe
independently of the human mind.
Ultimately, such thinking really broadens the horizons of physics, since it assumes the existence
of a "mathematical universe" which is not based on matter or energy. Today, physics recognizes
that matter and energy are the only possible forms in the universe. I developed a model in which
time is not matter, nor energy, but it still very much exists as a quantity within the mathematical
universe. For physicists, and also for people who are not physicists, this is a novel idea, because
we were all taught Einstein’s famous formula E=mc2, as well as its implications, that everything
that exists is a form of energy. And that furthermore, all matter can be converted to energy and
vice versa. Of course, in this context when we talk about “energy”, we are referring to both the
entire spectrum of electromagnetic radiation and the energy that manifests the totality of
universal space. Today’s physics is based upon a bivalent logic: a phenomenon can be A (matter)
or B (energy).
Trivalent logic, which was developed in the last century by Polish mathematician Jan
Lukasiewicz, permits that a thing can be A, B or even C. A mathematical universe is a
phenomenon that is part of the phenomena referred to as “C” in trivalent logic.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
784
The outdated model of space-time where time functions as the 4th dimension of space and the
fundamental arena of the universe is based on a misinterpretation of the mathematical model of
space-time of Minkowski. Instead, I propose that the “basic arena” of the universe is a granular
three dimensional universal space composed of fundamental units of space called “Planck
volume”. This model is based on the fundamental physical constants of Planck mass, Planck
length, Planck volume and Planck constant; all of which are derived from experimental data and
therefore reflect the basic properties of the universe. Fundamental physical constants are the
cornerstones on which we can build a new horizon within physics.
2. A critical survey on Higgs boson and graviton
To really understand how the universe functions you really need to have a clear understanding
about what is mass. We know that in everyday life the mass of an object is measured with scales.
In physics however, mass is a bit different. Understanding mass in physics is a bit harder to
grapple with and more complex than understanding mass in everyday life. The standard model
attempts to describe the four elemental forces in the universe with a variety of elementary
particles. For example the graviton is a hypothetical particle which we now suppose to be the
carrier of gravitational force yet is still as of now, undiscovered. The Higgs-Boson particle is
another particle that we are still learning a great deal about. It is theorized that the Higgs-Boson
particle is responsible for the mass of individual particles, however, as they say, the jury is still
out on that and opinions vary within physics regarding this presumption. The great weak point
regarding Higgs-Boson theory is “who” or should we say “what”, creates the mass of the HiggsBoson particle itself. This question has not been fully answered yet. It is also not clear how
Higgs-Boson particles interact with photons.
In physics, there are really just two concepts of mass. The first concept is “inertia mass”. This is
the idea that a particular particle or material body has a quality of stability that keeps locked in at
a specified location. If you want to move a mass you need to push it and to use some force. On
the other hand, this same “inertia mass” will mean that when the body is moving, it has the
tendency to keep moving forward. If you want to stop it, you will of course need a
commensurate resistance suitable for that particular volume of mass. The second concept of mass
in physics is “the gravitational mass”. This is the mass, which generates around a particular
body, the gravitational force which will then attract surrounding bodies. Experiments have
shown that the inertia and gravitational mass of particles or material bodies are exactly the same;
however, their origins still remain unknown.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
785
Here, in my own postulations I have gone a step further; I have developed a model where both
mass and gravity are sourced within the energy density of the universal space. Far away from the
celestial bodies energy density of universal space is at the maximum:
mp c2
l 3p
,
3
where mass m p s is Planck mass, l p is Planck volume and c is light speed. In the center of the
celestial body, the energy density is reduced by the value, which corresponds to the size, that is
to say the mass of celestial body:
m
m c2
V ,
where m is the mass and V is the volume of a stellar object. The surrounding denser space puts
pressure on the diluted space in which lies the massive body and thus creates its “inertia.”
Inertial mass
When two or more bodies come together this creates an area of lower density space. The outer
space which is of higher density then puts pressure against the space occupied by the celestial
bodies. This pressure coming from outer denser space towards lower denser space is then
indirectly transmitted onto the celestial bodies. They are pushed together. This creates the force
we call “gravity”.
Gravitational mass
So really, the two bodies are not attracted to one another directly. Gravity is actually created
indirectly by the bodies’ own masses reducing the density of space and thus drawing this
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
786
pressure towards them from outer more highly dense space. The environmental space of one
body is inextricably linked with the environmental space of another body. The bodies are
interacting with each other indirectly via the space medium in which they coexist.
According to my opinion antigravity spaceships are not only science fiction. Antigravity
technologies increase or decrease energy density of space. With increasing energy density of
space happens that spaceship is not pushed any more towards the stellar object from the side of
outer space. On the contrary it is pulled up in the outer space. The “bubble” of higher energy
density of space around the spaceship has tendency to move towards the area of outer space with
the equal energy density. By decreasing energy density of space spaceship will move in the
direction towards lover energy density of space, means towards the chosen stellar object.
2.1. A permanent dynamic equilibrium of the Universe
Universal space is structured from Planck volumes, which are the smallest unit of volume of
space. Interestingly, space density is at the absolute maximum out in the empty space between
galaxies. This is due to the high pressure energy of space structures in the “cosmic rays”; as they
are called by the American physicist Michael W. Friedlander. Cosmic rays are then formed into
elementary particles and atoms. In the center of black holes the density of universal space is
minimal as matter is transforming back into the energy of space. In the universal energy
circulation the space to matter ratio is constant. The universe is a system in a continuous
dynamic balance.
The universe is really a self-renewing being in its own right. It does not have a beginning nor
does it have an end. The universe was not created by God, the universe itself is God. The big
bang theory, which assumes that the universe started from an infinitely small point, has some
incomplete logic. The only acceptable model of the big bang theory of the universe is that it is
actually a cyclic shaped universe which is expanding. The theory is that at some point it will stop
expanding. It is theorized that at some point it will start to shrink into a huge black hole and then
ultimately it will explode into a new big bang.
Truly, the big bang theory that models the universe as having a final diameter simply does not
have a solid foundation. When you say the universe has a finite diameter, you are de facto saying
that the universe itself is finite. Really, we do not know what is on or beyond the finite or known
edges of the universe. Cosmologists claim that the infinite space of Euclidean geometry and the
spherical space of Riemann geometry are equivalent. Yet, our own logic and intuition tell us that
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
787
universal space is infinite. In mathematics, the concept of “infinite” is not a metric concept. In
geometry an infinite distance plus 100 kilometers is still an infinite distance. The model of the
universe as infinite aligns more with natural human reasoning, because it clearly points to the
fact that the size of the universe as can be comprehended by human faculties is for all purposes
unfathomable. When we are saying “the universe is infinite”, this means that the dimensions of
the universe are beyond the power of our imagination and conceptualization.
In order to understand the overall dynamic of the universe we can observe the part that is
accessible to us and from those observations we can conclude that even the rest of the universe
operates according to the same laws. This view is more honest than the view that assumes that
the universal space is finite. As a wise East Indian friend of mine named Amin once explained:
“The universe is not a melon.” (He got the picture.)
3. Relative velocity of material changes has its origin in the space density
The period between the end of the 19th century and beginning of 20th century has been a
landmark period for physics. In 1887 the American physicists Michelson and Morley conducted
an experiment which showed that light is not a wave of ether. In the physics landscape of the 19th
century it was well accepted that universal space is filled with ether, a media which does not
have mass, is in full rest and is present throughout the universe. Visible light and the entire
spectrum of electromagnetic radiation were supposed to be a ripple of that ether. As a result of
the Michelson-Morley experiment the ether theory was entirely and perhaps unjustly discarded.
Michelson and Morley were simply attempting to prove that light is not a wave of ether. It was
not proved that the ether did not exist at all. It could be that the concept of ether was simply
another name for cosmic bio-energy, which is also still outside the current accepted scientific
model of the world.
After the publication of the Special Theory of Relativity, the scientific community came to
believe that light travels through empty space. Physicists either forgot or ignored that even the
space itself is an energy medium or fabric. So light is traveling through a form of energy; space.
Max Planck’s idea that universal space consists of small discrete units did not come to the fore.
With Italian physicist David Fiscaletti, we have “resurrected” the ideas of Max Planck.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
788
Amrit Srečko Šorli (left) and David Fiscaletti in Tuscany back in 2009. Founders of Space Life
Institute back in 2000. Main research subjects: time, gravity, cosmology, Theory of everything
(TOE) and experiential consciousness research (ECR).
We chose three-dimensional universal space as the basic natural arena of the universe. This
natural view resolves many problems within physics. Some I have already described in the
previous sections, other issues I will expand on here, presently.
One of the other issues that our new simplified three dimensional view clarifies is Einstein’s
“problem of action at a distance” which he posed in 1917, one year after the publication of the
General Theory of Relativity in which Einstein has “geometrized gravity” describing it with the
spherical geometry of the German mathematician Riemann. His General Theory of Relativity
was to put it mildly a great triumph of physics. A geometrical description of gravitation did not
completely satisfy Einstein. Despite the fact that he was a pioneer in “mathematical theories”, he
had a great sense of coherence between mathematical models and the de facto truth of physical
reality that a model describes.
I believe Einstein had an ongoing direct experience of consciousness, which inspired him in his
research. Consciousness, however, intuitively knows that the geometry of the cosmic space
cannot create a gravitational force; a source of gravity must be a concrete physical phenomenon.
In order to meet “gravitational functioning at a distance”, Einstein started thinking about the
existence of the “graviton”, a particle that is similar to photon and responsible for the transfer of
the gravity between material bodies. At this time, in the beginning of the 20th century, photons
were already known to exist, and that matter both emits and absorbs them. It was understood that
photons are bearers of light as well as the full spectrum of electromagnetic radiation. Today, the
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
789
graviton rests as a hypothetical particle which no one has yet observed. Its existence is still a
question mark for physics.
In the third chapter we showed that gravity can be described via the energy density of universal
space, which does not provide for the existence of graviton, i.e. the gravitational waves.
Physicists today think that gravitational waves spread across the universal space with light speed.
For sixty years they have tried to detect them with very sensitive instruments to no avail. Italian
physicist Angelo Loinger proved that the existence of gravitational waves would contradict with
the original version of the General Theory of Relativity. That said, most physicists remain
unconvinced of Loinger position and they avidly look forward to the discovery of the graviton
particle. So far, the graviton has been proven to some degree, but only in indirect ways which as
far as physics is concerned is not sufficiently in line with empirical scientific method. The
existence of the graviton particle as a physical phenomenon can be considered existent only
when it is finally directly observed.
In 1974, the American physicist J. H. Taylor, along with his research group, observed a binary
neutron star called PSR 19.16 +16. They noticed that the rotational speed of binary stars around
their axes diminishes over time. This is a fascinating observation and result yet their
interpretation of the data was questionable. They attributed the decrease of rotational speed to a
reduction of the binary stars’ masses. I believe this interpretation is flawed due the defect in the
procedural method used in which the reduced masses were considered to be due to gravitational
radiation. This was never experimentally confirmed. Fiscaletti and I have an altogether different
idea: in general, the size of the binary stars is close to the size of black holes. It is possible that
like in the center of black holes, in the center of a binary star, matter is being transformed into
the energy of universal space. In this theory the conversion issue causes a reduction in mass of
binary stars and thereby reducing their rotational speed.
The model of space-time as the basic arena of the universe certainly will never be able to
describe all the discoveries in physics, because it is just a mathematical theory and not a physical
theory. I think, if Einstein before his publication of the Special Theory of Relativity in 1905,
could have chatted with Max Planck and discussed the relationships between the Special Theory
of Relativity and Planck's own idea of the granular structure of space, they would probably have
come to the conclusion that the relative speed of physical phenomena depends on the granular
density of universal space.
In the universe we have three different types of energies: the energy of the space ( E s ), the
energy of matter ( Em ) and electromagnetic energy ( Eel ). With Fiscaletti, I am building a
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
790
cosmological model of the universe which is in dynamic equilibrium (cosmological model UDE)
whereby dark energy is the energy of space. In physics the energy of each system must have a
homogeneous distribution. This means that the total amount of energy in a given volume of
universal space is constant. It is always in the following proportion E s Em Eel K .
Therefore, it follows that where matter is present, the energy density of space is lessened and
vice versa. Within this picture of the universe, the speed of physical phenomena will depend on
the energy density of universal space and it will be reduced due to the presence of massive
celestial bodies. Correspondingly, the lower the energy density of the universal space is the
slower the speed of physical phenomena.
Additionally, electromagnetic radiation can reduce the energy density of universal space. Even
though a photon is a particle without mass it too reduces the energy density of universal space as
well due to its kinetic energy. This issue is yet another area not yet incorporated into the current
framework of the Higgs-Boson theory.
4. Mathematical universe is a medium of quantum entanglement
Universal space where time is just a mathematical sequence of movement, elegantly explains the
famous “Einstein-Podolski-Rozen” experiment (familiarly recognized as the “the EPR
experiment”). The three scientists were working together at the beginning of the 20th century.
They assumed that the quantum particles are interconnected in a way that allows them to access
instant information. In the previous century, the EPR experiment was often tested and proven to
be valid and it was determined that was indeed the case. For example, if you take two particles,
which are first together and then send them traveling in different directions. The distance
between particles will increase and then when you measure the spin of the first particle it will be
to the “right” and the spin of the second particle will be to the “left”. According to the Special
Theory of Relativity the speed of light is the maximum speed with which information can travel.
Yet in the EPR experiment the transfer of information is instantaneous, so the traditional Special
Theory of Relativity cannot explain it.
In the model of the universe I developed with Fiscaletti, the “mathematical universe” itself is the
direct medium of the information between the particles. The mathematical universe simply
“knows” about the spin of the first particle and so it instantly informs the other particle how to
rotate. Additionally, the classic EPR experiment shows that the universe has a tendency toward
developing symmetry and harmony as the opposite spin of the particles is determined by the laws
of symmetry.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
791
In the mathematical universe the transfer of information is instant. In the material universe, at the
scale of photons, information spreads at the speed of light. Interestingly, once we get to the scale
of atoms and molecules the speed of information will always be less than the speed of light. We
need to keep in mind that consciousness is not information. Consciousness is manifesting and
acting through the mathematical universe and DNA down into the level of the material world.
Within this context, the human thought process is not an “energy phenomenon” carried by the
electromagnetic waves as many people imagine. Thought is rather a phenomenon that belongs in
the realm of the “mathematical universe”. When a thought arises in the mind, it is immediately
present throughout the universe. Therefore, thinking has tremendous power. Any thought
impregnates the entire universe. With thoughts and potent visualization you can eliminate certain
physical problems in the body, you can “create” your life. When the mind is linked with
consciousness harmonious thoughts are created. When the mind is subject of its own egoism,
destructive thoughts are created. Emotions are an actual “energy/material” phenomenon, tied to
the secretion of hormones on human physiology. Emotions have the power to be able to create
certain thoughts, while on the other hand thoughts always generate certain feelings. For example,
sadness comes from destructive thoughts and conversely, your happiness is borne of your more
creative thoughts.
Telepathy takes place via a mathematical universe between two or more minds. Using the
vehicle of intuition, one can travel through the mathematical universe medium and obtain
information on the psycho-physical condition of another man or some situation out there in the
material world. Trained people are able to see what is going on at the other end of the planet or
even other planet. Some claim to even be able to perceive via telepathy what is going on in other
solar systems.
While the material universe is three dimensional, the mathematical universe is multidimensional. In math we can also have a space with an infinite number of dimensions. When
mathematicians started to discover multidimensional spaces, some physicists thought it also
applied equally to the material world. They did not understand that mathematics is neither energy
nor matter. It is rather a phenomenon that exists beyond the material universe. Mathematics is
not a product of the neural processes in the brain which are material and three dimensional. If
this were so, the mathematicians could develop only three models of a three dimensional space.
Futuristic writers have tried to postulate a reality of “parallel worlds” where worlds should
and/or might be parallel to our own universe. They have imagined that there could be alongside
our own universe another universe, in another dimension, that we cannot observe directly
because of the dimensional schism. Such reflections are the result of a fundamental lack of
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
792
understanding about the true nature of material universe; that it is three dimensional and does not
tolerate the existence of parallel universes.
5. Unification of the “double nature” of light
Our model of the universe gives a new understanding of the dual nature of light. Light is a bit of
a chameleon, it sometimes behaves like a particle and sometimes it behaves like a wave. This
double nature of light was originally supposed to be the result of the mode of observation, that is,
specifically, when you are looking at it like a wave, it behaves like a wave, when it is observed
as a particle it behaves like a particle. In our vision, the photon is at the same time both a particle
and a wave. A photon is transmitted by an electron in its transition from a lower to a higher
energy state. For example, when iron is heated it starts to glow which is the manifestation of the
release of photons. Photons spread out in all directions and travel in space. The movement of the
photon creates waves in space much like a ship does when it is traveling through the sea.
However, in the case of the photon, the “ship” cannot be considered separately from the “wave
of the sea”. This is the missing law of quantum mechanics: “Elementary particles and the space
into which they move are one physical reality”, they are one great fabric.
The nature of this simultaneous particle/wave nature of the photon is confirmed by the double
slit experiment. In the image below you can see that the photons have their origination point
(marked “a” in the illustration below). From the origin, if we send photons one by one, they will
travel through the left and right slit alternately (marked with “b” and “c” in the illustration
below,) this creates on the screen a significant interference pattern (marked with “F” in the
illustration). When the traveling photons only make it through the left slit b, we get the same
interference pattern, because the waves of space created by moving the photons went also
through the right slit c. Physicists have not yet definitively explained this phenomenon. The
experiment teaches us that waves of space are created by the single photon’s motion and that it
will always travel through both of the slits.
Double slit experiment
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| July 2013 | Volume 4 | Issue 7 | pp. 780-793
Sorli, A. S., Experiential Consciousness Research on the Physics of Now (Part I)
793
The frequency of light is associated with the movement of the light source and of the observer,
and with energy consumption which the photon uses for movement. When a light source moves
away from the observer, light reduces in frequency. This is what is called “shift to red spectrum”.
In the sixties of the twentieth century this “red shift” was considered the main evidence for the
expansion of the universe. Today, it is accepted in astronomy that about sixty percent of the “red
shift” is due to a strong gravitational field through which light moves. So, photons which come
from distant galaxies have reduced energy, because energy is spent as it “pulls out” from the
strong gravitational fields of other galaxies. This latter interpretation of “red shift” has
contributed to the overall reducing popularity of ideas about the expansion of the universe, which
has in recent years seen fewer and fewer defenders. Of greater prevalence these days is a model
of a dynamic universe without a beginning and end, in which, there is no need for a “creator”, as
it is an “uncreated” system which stands in dynamic equilibrium.
(Continued on Part II which also contains the references)
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com |
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
234
Article
Magnetic Stimulation of the Temporal Cortex:
A Partial “God Helmet” Replication Study
Carlos A. Tinoco* & João P. L. Ortiz
Integrated Center for Experimental Research, Curitiba-Pr, Brazil
Abstract
The effects of magnetic stimulation of the brain in comparison with suggestibility and
expectation are studied. Eight magnetic coils were embedded in a helmet, placing four over the
temporal lobes on each side of the head. These produced 0.0001 Tesla (10 mG) magnetic fields
(MF). “Spiritual experiences” were reported by some of the 20 volunteers who received
magnetic stimulation of the temporal lobes. These “spiritual experiences” included sensing the
presence of “spiritual beings.” Stimulation durations and field strengths were within the limits
used by Dr. M. A. Persinger in similar (“God Helmet”) experiments (20 minutes, 10 mG).
Questionnaires were applied before, during, and after the experimental sessions. Analysis of the
subjects’ verbal reports, using Whissel’s Dictionary of Affect in Language, revealed significant
differences between subjects and controls, as well as less robust effects for suggestion and
expectation.
Keywords: God Helmet, magnetic stimulation, temporal cortex, Michael Persinger, spiritual
experience.
Introduction
Neurotheology or spiritual neuroscience is the study of the neural bases for spirituality and
religion. The goal of neurotheology is to discover the cognitive processes that produce spiritual
and religious experiences and their accompanying affect and relate them to patterns of brain
activity, how they evolved, and the effect of these experiences on personality.
In our research, we used an apparatus (Figure 1) not unlike the Koren Helmet, often called the
"God Helmet." The Koren Helmet is an instrument created by Dr. Persinger and colleagues to
perform experiments in the field of neurotheology (Persinger, 2001). These experiments have
elicited a wide range of visitor experiences (Persinger, 1989) (angels, ghosts, demons, deities,
spirits, etc.), including the sensed presence. Several scientists from various fields have reported
mystic experiences in Persinger’s lab, as well as mystics, psychics, and atheists. The helmet
used in this research was built in our laboratory by J. P .L. Ortiz, an electronics technician,
working under the guidance of the primary author.
*
Correspondence: Carlos A. Tinoco, Emeritus Professor, Basic Physics & Eletromagnetism, Amazonas Federal University; &
Integrated Center for Experimental Research, Curitiba-Pr, Brazil. E-mail: yogatatva@yahoo.com.br
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
235
Figure 1
The God Helmet (Koren Helmet) stimulates the temporal neo-cortex and mesio-basal portions of
the temporal lobes with complex magnetic fields. The God Helmet places four magnetic coils on
each side of the head, above the temporal lobes. Some subjects exposed to these fields reported
having "spiritual experiences" during our tests. These subjects included atheists, as well as
religious believers. In one media interview (BBC, 2003), Persinger stated that 80% of the
subjects reported the “presence” of “nonphysical beings” in the room where the experiments
were conducted, including the “presence of God” in a small number of subjects.
Antecedent Studies
Other researchers have explored the effects of magnetic fields on the human brain, including
Sandyk (1997, 1999), who reported therapeutic effects from the magnetic field on patients with
Parkinson’s disease and multiple sclerosis. Hirata et al. (2011) reported eliciting phosphenes
using weak magnetic fields. Martiny K, Lunde M, Beach P (2010) reported antidepressant effects
from low-intensity magnetic fields. Robertson (2010) reported changes in pain processing
following low-intensity magnetic pulses.
Mystic experiences have been reported from all countries throughout history. Mystic experiences
have been defined as “altered states of consciousness accompanied by positive affect” (Murphy,
2011). Dr. Andrew Newberg (2001) has shown that religious experiences affect the temporal
lobes of those who experience them. Dr. Persinger (2010) has demonstrated that when the
temporal lobes are activated in specific ways, the subjects have religious experiences. These two
lines of research both implicate the temporal lobes as crucial in mystic experiences.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
236
M. A. Persinger (2001) has reported religious and mystic experiences in laboratory settings using
low-intensity magnetic signals, most notably the elicitation of the “sensed presence” experience
and (much more rarely) visions of God. Persinger and colleagues have suggested that specific
classes of subjective experiences are related to subtle changes in brain activity, influenced by
fluctuations in global geomagnetic activity (Persinger, 1988). Persinger AM,Roll WG, Tiller
SG,Koren SA,Cook CM (2002) reported neurophysiological correlates of experiences reported
by Sean Harribance, a remote viewer. Low-intensity complex magnetic signals were applied
over his right parietal-temporal lobe, causing him to sense presences on his left side. These
results suggest that the paranormal phenomenon Harribance reported was quantitatively
correlated with morphological and functional abnormalities involved in the right pario-temporal
cortex and the hippocampal formation (Persinger,MA,Roll,WG,Tiller,SG,Koren SA,Cook CM
2002). Beuregard and Paquette (2006) did an experiment with Carmelite nuns who reported
moments of union with God. Magnetic resonance images (fMRI) were taken from them while
they were in this state. Their experiences were found to correlate with changes in the medial
orbitofrontal cortex, inferior and superior parietal lobes, medial pre-frontal cortex, left anterior
cingulate cortex, and left insula. The results suggest that mystical experiences are mediated by
several brain regions and systems. These include the temporal lobes, the region we focus on in
the present study.
Objective
The research objective was to replicate aspects of the experiments reported by Dr. Michael
Persinger. These include (a) magnetic stimulation of the temporal lobes, (b) low-intensity
magnetic fields, and (c) movement of the magnetic fields. A further objective was to explicate
the effects of suggestion on the outcome of the experiment by including subjects who had heard
of the “God Helmet” and informing them that they were going to receive a session with that
apparatus, explicitly “planting” a suggestion.
Hypothesis to Be Tested
With these tests, the researcher intended to repeat the experimental results of Michael A.
Persinger and colleagues, in which the God Helmet turned on, could induce mystical experiences
on the volunteers. Therefore if can be said that the hypothesis to be tested was: “It is possible to
repeat the results of Michael A. Persinger and colleagues, using a God Helmet built in Brazil,
without having any orientation of them regarding the tests and the construction of a God
Helmet?” It is also expected that the twenty volunteers chosen by the criteria specified below
don’t be harmed by the research, in other words, that they don’t suffer any sort of damage,
neither physical, nor emotional, and, at the end of the tests, they feel very well and willing to
repeat the tests, in another occasion.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
237
Methods
The methodology applied on the research that is the subject of this project is the following:
a) Participants
1 - The choice of twenty volunteers and how would they be tested:
- Through interview, in which they were informed about all the methodology to be used on
the tests;
- All the twenty would be tested, one at a time.
- Before and after the tests, a doctor (Dr. Elson de Araújo Montagno), would measure their
blood pressure and heartbeats of each patient. That wouldn’t be made during the tests to not
alter the results.
- Each patient would be blindfolded during each test;
- Would be considered excluded from the tests, the volunteers with physical problems,
psychological and psychiatric problems, according to the doctor's opinion.
b) Criteria of Inclusion of Volunteers on the Research
Would be included on the research volunteers that:
- Wished to participate;
- Were selected in the interviews (judged by the responsible for the tests, Carlos Alberto
Tinoco);
- Had signed the Consent Form;
- Had been considered apt by the doctor.
c) Criteria for Exclusion of the Research Subjects
Would be considered excluded from the research, subjects that:
- After being selected, gave up participating on the tests;
- Even willing to participate, the medical and psychological exams indicate as inapt;
- Refuse to sign the Consent Form.
d) Equipment Used on the Construction of the God Helmet
1- Construction of the God Helmet, according to specifications of Dr. Persinger and colleagues
(see internet “God Helmet“):
- Construction of cictuit a), which is an oscillator (see Appendix 2);
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
238
- Construction of cictuit b), which is known as “Johnson-DJ‘s Decade“, that is a counter of
electric pulses, from 1 to 10 (see Appendix 2);
- Construction of a current amplifier, which must be coupled to each solenoid, because the
DJ does not supply sufficient current (see Appendix 3);
- Cut the helmet with holes approximately eight centimeters in diameter at the height of the
temporal lobes for placing the eight solenoids, four at each side of the skull;
- Acquisition of copper wire (26 AWG) endcapped with varnish, with 50.0 meters in length;
- Preparation of eight solenoids, each with five hundred turns;
- Manufacture of four wooden wheels (simple wood), each with a diameter > 8.00 cm, to
provide support to the eight solenoids (two pairs with two wheels each);
- Acquisition of eight ferrite rods (d=1/4”, length= 3") to be placed into each of eight
solenoids;
- Acquisition of 8 cables of 24 AWG, with two meters long each, to be connected to the
eight solenoids, which will bring information to the responsible researcher (plastic
wrapping with four different colors);
- Wrap the copper wire of each solenoid with pharmacist tape, for proper protection;
- Experimental Measurement of the value of electric current in each solenoid, so that we can
know the value of the magnetic field generated in each solenoid (not to exceed the critical
value, between 10 nanotesla and 1 microtesla, according to Raul Marino, Jr., informed by
Dr. Newberg (Marinho Jr, 2005). This value was measured = 0.000165 amperes, which
corresponds to a magnetic field of B = 0.001 microtesla within the security value. The
value of the magnetic fields is measured with a multimeter (precision voltmeter), which
possesses scale for micro and milli volts.
e) Printed Material
- Preparation of printed material to be used after each experiment (see Appendix 4).
f) Time for the Conduction of the Research
-Twenty-minutes for each patient, seven of them on the first day, seven in the second and six in
the third. On the first day, the time for conducting the tests was six hours and twenty five
minutes; on the second day it was used approximately the same time of the first test, and in the
third day it was spent about five hours and thirty minutes. The average time spent in each test
was one hour and 20 minutes, approximately.
g) Procedure
- The whole experience would be held in three days, and could be carried part in the
morning and part in the afternoon;
- Before each test, the researcher in charge would apply on each patient the appropriate
questionnaire (see Appendix);
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
239
- During the tests, the researcher in charge would apply the questionnaire for each patient
(see Appendix);
- After the tests, the researcher in charge would apply the appropriate questionnaire (see
Appendix);
- The God Helmet would be placed on the head of each of the eight volunteers, each in turn,
when the magnetic fields would be activated for twenty minutes;
- Each volunteer patient had to sign a consent form, sparing the Spiritist Integrated Schools
– “FIES" of any damage that he may suffer as a result of the tests, although all possible
precautions were taken in advance;
- The principal investigator would inform patients, before testing, the values of the magnetic
field that would be used, and the maximum value that could be used without damage being
caused to the patient;
- The mentioned doctor, that would measure the blood pressure, temperature and heartbeats
of each patient before and after the tests, would inform that they do not pose a risk to
patients;
- After the completion of the research, an Act would be written, which should be signed by
the head of research, by Seu Dante, builder of the CD, by the doctor, and all twenty
volunteers. Only then may the research be considered finished.
h) General Information
- Individual interviews with volunteers, made by the head of research. On this occasion, they
would be informed of all procedures and methods that would be used during the tests;
- Each of them would be examined by a doctor and, if he states that the volunteer is fit, he
may be accepted;
- If they agree to be patient on the tests, they still must sign the Consent Form. Only then,
applicants would be accepted, definitely;
- A psychologist would examine the volunteers before and after the tests, to assess problems
arising from contact with the "unknown".
Ten subjects were given 20-minute magnetic stimulation sessions using 100 Hz magnetic pulses
produced by a locally assembled Johnson Decade Counter and applied through an array of
magnetic coils located above the temporal-parietal region of the head.
The magnetic coils used in the experiment were made with 500 turns of 26-gauge copper wire
around disk-shaped flux concentrators, output magnetic fields calculated to have RMS peaks of
0.000001 Tesla (10 mG) when connected to an active Johnson Decade Counter.
We used “simple” pulses, which Persinger (2010) reported are among the least effective patterns
for magnetic field neural stimulation, as the brain habituates to these in short periods of time.
However, we maintained movement of the magnetic fields, coil placement over the temporalparietal region, and field strengths on the order of 10 mG. Our simple signals were used in the
absence of any source for the “Chirp” pattern or amygdalar burst-firing pattern used in
Persinger’s experiments and provided an opportunity to test the effects of magnetic fields
moving above the temporal lobes, as well as weak (10 mG) magnetic fields, although without
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
240
complex patterns. According to Persinger and Koren (2005a), the Koren Helmet requires
exposures of at least 20 minutes for mystic and/or altered-state experiences to appear under its
influence. This was used as the duration of our experimental sessions. A blindfold was used to
achieve partial sensory deprivation.
Figure 2
One pair of coils at a time actively put out magnetic
fields. The active coil was changed every 250 msec,
changing from the posterior to anterior superior
temporal lobes, and then from the posterior to anterior
inferior temporal lobes (Figure 2), in a pattern not
unlike a figure eight. The same configuration was used
above both temporal lobes. The coils were “yoked” so
that each pair of coils designated with a number was
active at the same time as its contralateral counterpart.
One such sequence required 1000 msec.
The position of the coils was cross-shaped, with their arms, one vertical and the other horizontal.
The dorsal and ventral pairs were thus each active for 500 msec. Our equipment differed from
Persinger’s helmet, which rotated the signals between the four coils. However, like Persinger’s
(2001, 2010) arrangement, ours included time frames for the movement of the magnetic fields
such that the dorsal and ventral portions of the temporal lobe each received 500 msec exposures
in succession.
The experimental sessions were carried out on three days: September 27, October 13, and
October 18, 2010, between 14:00 and 18:00, local time (Brazilia Time Zone = GMT -3).
Global geomagnetic values (K indices) during the times of the experiments were 0 to 2
(09/27/10), one (10/13/10), and one (10/18/10) (NOAA archives, 2011).
The control group consisted of an additional 10 subjects who were treated with a zero-amplitude
(sham) field.
Biomedical measures from all subjects were taken before each test and found to be within
normal limits. The mean arterial pressure fell approx. 12 x 7, the average body temperature was
between 37 and 36.5 degrees Celsius and the average heartbeat rate was around 74 per minute.
After the first evaluation, our magnetic helmet was placed on the head of each of the subjects and
actively run for 20 minutes or left off for control subjects. All volunteers sat in a comfortable
chair during the tests. The helmet was fitted with a blindfold.
Pre-session questionnaires were applied regarding each subject’s emotional state, expectations,
and prior knowledge of the God Helmet before experimental sessions. In the last two minutes of
the sessions, subjects were queried regarding any sights, sounds, tactile sensations, smells, and
tastes that they might be experiencing. After the sessions, subjects were asked about their
overall state. Descriptions of subjective states and experiences were also collected from each
subject during and after the experimental sessions.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
241
Subjects were told that they were participating in a God Helmet experiment, deliberately planting
a suggestion that would actively encourage expectation. Not all subjects (n=10) had prior
knowledge of the apparatus. Nevertheless, the phrase “God Helmet” strongly connotes an exotic
experience, planting a similar suggestion for all subjects, regardless of whether they had prior
knowledge of the God Helmet.
Expectation is the subjective correlate of suggestion and suggestibility. Our subjects were asked
what they would expect during a “God Helmet“ session. Only a small number (n=5) reported no
expectations. Prior to the experimental sessions, the majority of subjects reported expectations
of altered states, calmness, and unusual sensations.
Analysis of the subjects’ responses was accomplished using Whissel’s Dictionary of Affect in
Language (Whissel, 2009), an instrument that quantifies the affective dimension of spoken
language, including pleasantness, activation, concreteness, and abstractness, as well as
performing word counts.
All words were scored with the Dictionary of Affect by matching words to the Dictionary and
importing scores for three variables: pleasantness, activation, and imagery. These scores
represent previous ratings of how pleasant a word seemed, how active it seemed, and how easy it
was to form “a picture in your mind” of the word. A total of 537 words were produced by
participants; 496 of these (92.4%) were matched by the Dictionary. Data included a count of the
number of words used by each person during and after the God Helmet session.
The analysis was a repeated-measures analysis of variance for pleasantness, activation, and
imagery; number of words with field; and expectation as between-subjects factors (2x2x2). Posthoc tests were t-tests, which assessed whether the means of two groups were statistically
significantly different from each other. The methods employed for post-hoc analysis were
unknown to the translator at the time of the translation, preventing translator bias.
We used measurements of verbal behavior during and after experimental sessions to explicate
the relative roles of magnetic field stimulation and suggestion. We recorded answers to queries
about what subjects expected the session would be like prior to the experimental sessions. These
answers are included in the detailed results at Table 1. Analysis of verbal behaviors in
expressing expectations provided a way to analyze the effects of suggestion directly.
Table 1. Detailed results for the 20 subjects
Subjects with no expectations before experimental session:
Field on or off
Subject
number
1
6
ISSN: 2153-8212
Knew about God
Helmet or didn’t
know
NO FIELD KNEW ABOUT
GOD HELMET
FIELD ON KNEW ABOUT
Religion
Expectations
before
experimental
session
Experiences
during
experimental
session
Experiences
after
experimental
session
No specific
religious beliefs
(spiritualistic)
No expectations
Felt sleepy
Felt well
Spiritualist
No expectations
Felt muscle
spasms in arms
Felt very well
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
GOD HELMET
and legs. Felt
perineal
sensations
including
‘energy’
explosions.
Right side more
relaxed.
Memories of
Childhood. Saw
himself in his
father’s
workplace. Felt
relaxed.
Heard sound
water, smell of
roses, stomach
growling. Saw
sheep on green
grass. Saw light
shaped like stars
and grey color.
Had seen a lecture
about God Helmet.
242
7
NO FIELD KNEW ABOUT
GOD HELMET
Catholic
No expectations
11
FIELD OFF - NO
KNOWLEDGE
OF GOD
HELMET
Atheist
No expectations
Felt nothing.
Saw dots of
light.
Felt well
Felt good, in a
meditative state.
If had more time,
would have
entered in an
altered state of
consciousness.
Felt well
12
FIELD ON - NO
KNOWLEDGE
OF GOD
HELMET
Spiritualist;
experienced
meditator
No expectations.
“Didn’t know
what it was
about.”
Arms growing,
like when
relaxed or
meditating. Saw
a skinny black
dog running
from the left to
the right.
17
FIELD OFF - NO
KNOWLEDGE
OF GOD
HELMET
No specific
religious beliefs;
spiritualistic
No expectations
Felt sleepy
Felt very well
Subjects with expectations before experimental session:
Field on or off
Subject
number
2
ISSN: 2153-8212
Knew about
God Helmet or
didn’t know
FIELD ON KNEW
ABOUT GOD
HELMET
Religion
Catholic
Expectations
before
experimental
session
Experiences
during
experimental
session
Experiences
after
experimental
session
Expected “mindaltering”
experience
Pressure on the
right side of head;
something physical;
right ear throbbing
slightly; light
fatigue
Continued to feel
the pulse
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
3
NO FIELD KNEW
ABOUT GOD
HELMET
4
FIELD ON KNEW
ABOUT GOD
HELMET
Spiritualist
Expected an
altered state of
consciousness
5
NO FIELD KNEW
ABOUT GOD
HELMET
Tendency to
spiritualism
Expected to be
more relaxed
8
FIELD ON KNEW
ABOUT GOD
HELMET
Catholic.
(priest)
Feared not
reaching the
objective he
expected, which
was leaving his
body
9
NO FIELD KNEW
ABOUT GOD
HELMET
No specific
religious
beliefs
Expected to leave
the test feeling
calm
ISSN: 2153-8212
Catholic
Expected
“something good”
Something moving
in the right cheek;
saw a metallic
cylindrical tube go
from him and leave
tassels of yellow
flowers
‘Someone’ touched
hands. Peace,
Tranquility.
Numbness in the
body. Felt
‘everything vanish’.
Did not feel body,
or time passing. Felt
presence of a man
standing on the
right side.
Heard noise like an
aircraft twice. Felt a
touch on both
shoulders. Felt fear
when hearing the
sound.
Smell of perfume
like talc. Saw colors
black, grey and dark
blue. Saw people
dressed in white
and grey. Saw black
dogs and a chair.
Saw an ancient
battle, armor,
horses, swords, etc.
Saw girl come from
behind her. Saw her
hair. Someone was
threatening her. She
ran, laughs,
something real.
Feeling afraid for
her. Thought it was
an actor. Felt it was
something real.
Involuntary muscle
contractions.
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
243
Felt well and
light; thinks had a
mild religious
experience
Felt very well.
Feeling peace,
tranquility. If it
took more time,
would leave the
body.
Felt well,
balanced, relaxed
Felt like he came
back to earth; felt
very well.
Seemed like a
dream.
Felt well
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
Smelled talcum.
Tightness in the
head. Saw man
riding a bike
falling; saw the side
of a male face, ear
very clear. Felt side,
saw something
moving from right
to left. Felt afraid to
see the man on
bike. Heavy leg.
Muddled thinking.
Feeling like an
electric current
raging his body
three times. Felt a
pulse at the top of
the head.
Sweet flavor in the
mouth, taste of
fruits. Tingling in
the scalp and
running down to the
face. Smell of sweet
incense.
Buzz in both ears.
Smell of incense.
Heavy hands. Mind
pulsing in the
rhythm of the heart.
Forgot the reality.
No specific flavor.
Felt the head
involved in energy.
A little anxious for
being blindfolded
and not knowing
what was
happening.
10
FIELD ON KNEW
ABOUT GOD
HELMET
Catholic
Feared being
disturbed by
seeing something
unknown
13
FIELD OFF NO
KNOWLEDGE
OF GOD
HELMET
No specific
religious
beliefs.
Spiritualistic.
Having different
sensations
14
FIELD ON NO
KNOWLEDGE
OF GOD
HELMET
Nonpracticing
Catholic.
Spiritualistic.
Feared feeling sick
15
FIELD OFF NO
KNOWLEDGE
OF GOD
HELMET
No specific
religious
beliefs;
spiritualistic
Expected to have a
different
experience
16
FIELD ON NO
KNOWLEDGE
OF GOD
HELMET
No specific
religious
beliefs;
spiritualistic
Expected
something
interesting
Buddhist
Feared having a
shock. Felt
anxiety.
Relaxed quickly,
felt claustrophobic,
got some sleep
Felt well
Atheist
Expected to be
relaxed
Only felt the weight
of the GH; almost
slept
Very calm
Lutheran
Expected to feel
better than before
experimental
session
Felt the body
relaxing. Increase
of the heartbeats.
Anxiety. Heartbeats
increased on
entering in a
Felt well
18
19
20
ISSN: 2153-8212
FIELD ON KNEW
ABOUT GOD
HELMET
FIELD OFF NO
KNOWLEDGE
OF GOD
HELMET
FIELD ON NO
KNOWLEDGE
OF GOD
HELMET
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
244
Felt calm
Felt well
Felt more relaxed
than when sitting
in the armchair
Felt very well
Felt well;
imagined that
there would be
another step in
the test
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
245
different state of
consciousness.
Reacted against and
avoided the
experience.
Analysis
Subjects were grouped according to field (control or field on) and according to their expectations
(no, n=6; yes, n=14). Both of these divisions proved fruitful. P<.10 was employed as the p
value. All results given in the table (see Appendix 5) are significant at this level. One unit of
measurement was the words spoken by the participants. There were 396 during the helmet
administration and 141 after. The words used during the time that the helmet was connected,
comprises two groups of persons: 1 - without expectations (6 persons) and 2 – with expectations
(14 persons).
Effects of expectation on comments during the experimental sessions
Subjects who reported expectations:
used words with lower concreteness
1.82 versus 1.99
used more common words
freq of 2588 versus 1550
used more abstract words
30.2% versus 20.6%
used words of a generally unpleasant 14.8 versus 7.4%
emotional type
used a disproportionately high number of 78% of the words, when only 70% of the
words
participants belonged to this group
Effects of expectation on comments after the experimental sessions
Subjects who reported expectations:
used more emotionally cheerful words
5.6% versus 0
used more emotionally nasty words
4.7 versus 0
used more passive words
31.8% versus 16.7%
used more concrete words
6.5% versus 0
used a disproportionately high number of 80% when only 70% of the participants
words
belonged to this group
Comparison of subjects with controls
Comments after the administration of the helmet
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
246
Predictably, in view of our use of 100 Hz pulses instead of complex magnetic signals, there were
no statistically significant differences between the comments of those who received the field and
those who did not during administration of the helmet. Differences between subjects and controls
emerged in analysis of post-session comments. This is consistent with Dr. Persinger’s findings
and methods, which have emphasized post-session narratives (accompanied by a brief
questionnaire), recognizing the tendency of subjects to dislike talk during the sessions. We
questioned our subjects in the last two minutes of their sessions, when the tendency for subjects
receiving a field to find verbal interruptions irritating (Freeman J,Persinger AM, 1996) would be
at its maximum, but also when responses would have been most clear.
Those who received a field (Fields On)
used more common words
freq=2153 versus 666
used shorter words
4.35 versus 5.19 letters
used fewer passive words
21.8% versus 37.3%
used more abstract words
39.7% versus 21.8%
used fewer emotionally unpleasant words
3.9% versus 15.2%
used a disproportionately high number of 60% when only 40% of the participants
words
were in this group
The results reported here are significant at p<.05 with two exceptions of interest. The more
trivial results are mentioned first.
Differences between the during-session and after-session conditions
Overall, people’s language was more “pleasant” after the administration of the helmet than
during it (2.02 versus 1.90). It should be mentioned that the language was generally “pleasant” in
tone. The average pleasantness score for everyday English is 1.84.
Overall, people’s language was more active during the administration of the helmet than after it
(1.74 versus 1.56); it should be mentioned that the language was generally active in tone during
the helmet session and generally less so afterwards. The average activation score for everyday
English is 1.67.
Overall, people’s language was more concrete (higher imagery) during the administration of the
helmet than after it (1.75 versus 1.68), but also more concrete throughout, as the average imagery
for everyday English is 1.53.
Overall, people said more during the administration of the helmet than afterwards (19.8 words
per person versus 5.75).
Differences associated with field versus controls
Overall, people who were exposed to a field had more to say than controls (15.9 words per
subject; 9.65 per control).
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
247
For words used after the helmet administration, those exposed to the field used fewer pleasant
words (2.07) than did the controls (2.25). For words used during the administration, the two
groups were equal (1.90; 1.92). Both groups used more pleasant words after the helmet
administration, but the group not exposed to a field showed a greater increase in verbal
pleasantness.
For those not expecting a result, language during the session was more abstract (lower imagery)
under the field (1.69) than it was for controls (1.94). For those expecting a result, it was similar
under field (1.74) and no field (1.75).
For those not expecting a result, concreteness (imagery) was higher during helmet administration
(2.06) than after (1.66). Concreteness was similar for those expecting a result (1.79; 1.70).
Expectation by subjects was associated with some differences. The administration of a field led
to (a) participants’ talking more, and to (b) their using fewer pleasant words to describe their
feelings after the administration, and to (c) their using more abstract language.
There were two effects for knowledge of the helmet (n=11) versus experimental naïveté (n=9) in
combination with the field/no-field condition that differed from those of expectation. Those who
knew about the helmet used more active language (1.679 versus 1.625) and more concrete
language (1.829 versus 1.723) throughout than those who did not know about the helmet.
A small additional significant effect
The 4 subjects who mentioned some "fear" or "concern" in their expectations, the 6 cases with no
expectation, and the 10 cases who expected positive or mind-expanding results constituted three
additional subdivisions of our experimental cohort. This last group (positive expectations) used
more abstract language than the other two groups (imagery of 1.693 versus 1.860 and 1.883).
Summary
For comments during the administration of the field, the language of those expecting an effect
was less emotionally pleasant and more abstract (i.e., talking about feelings rather than things)
than those who reported no expectations before the experimental session. For comments after
the field, the language of those expecting an effect was more emotionally loaded and more
concrete.
The language during the session did not differ significantly between those receiving the field
stimulation and controls. The language of those receiving a field, collected after the
experimental sessions, involved simpler, more common, and less passive words, with less
negative emotional content than controls.
If we can interpret the results described above causally, the administration of a field caused
participants to say more after their sessions and to become more abstract and less overtly
pleasant in what they were saying.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
248
Both expectation and field administration were associated with differences in verbal responses.
“Field on” and control subjects’ verbal responses collected after the experimental session
differed significantly.
Both the field and expectation increased the number of words produced by participants in
comparison to controls and those without expectations, respectively.
Table 2: Average (mean) number of words used before and after the session
Group
People Words per person after Words per person during
Control, no expectation 4
2.25
7.75
Control, expectation
6
8.33
21.5
Fields on, no expectation 2
11.00
23.5
Fields on, expectation 8
7.50
23.63
In Table 1, one can observe the effects of expectation, as well as the results for control subjects,
on the number of words used by subjects in four different experimental conditions:
(1) Both the administration of the field and the subjects’ expectations made them more
verbose. In the absence of both of these, they had significantly less to say.
(2) Those expecting an effect displayed more abstract language during the administration
phase and more concrete language after it. Their language retained an emotionally negative
character.
(3) Those receiving a field used emotionally less negative language and simpler language to
describe their experiences after their sessions.
(4) The differences in post-session verbal behavior between subjects and controls, as well as
between those with expectations (which we consider the subjective correlate of suggestion)
and those without, tends to support Persinger’s conclusion that the effects of temporal lobe
stimulation with moving weak magnetic fields cannot be attributed to suggestibility (St.
Pierre, 2006).
Geomagnetic Factors
The experiments were conducted in Curitiba, Brazil, close to the center of the South Atlantic
Anomaly (SAA), a region with significantly lower mean geomagnetic H values. However,
geomagnetic storms and particle precipitation in the South Atlantic anomaly are stronger than
those at respective middle and moderate latitudes of the northern hemisphere (Danilov, 2001).
Global geomagnetic field strengths average from 30,000 (equatorial) to 60,000 (polar) nT. In
contrast, geomagnetic field values in the SAA rarely exceed 20,000 nT. Further, this region is
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
249
subject to geomagnetic micropulsations (Macmillan, 2009), possibly arising from electron
precipitation from the terminus of the Van Allan Belt, directly above the SAA (Trivedi, 2005).
The amplitudes of one kind of geomagnetic turbulence, preliminary reverse impulses (PRI),
within the SAA are about three times higher than those happening at tropical latitudes. PRI in
the SAA have anomalously frequent occurrences and amplitudes in the SAA, “caused by the
significant enhancement of ionospheric conductivity due to the weakness of the ambient
magnetic field intensity in the SAA region” (Shinburi et al., 2010). Saboia and Marques (2005)
found a further source of geomagnetic turbulence in the SAA’s strong toroidal and poloidal
geomagnetic salients, strong magnetic oscillations, and transitory reversed magnetic polarities in
the area. They also noted magnetic torsional eddies and vortices, creating frequent transitory
changes in local geomagnetic field strength.
The geomagnetic field within the SAA is about 1/3 weaker than the global geomagnetic field,
allowing greater fluctuations in response to solar events, the ultimate source for variation in
geomagnetic field strength. Persinger (1995) hypothesized that specific patterns of information
appearing within the variable portion of the geomagnetic field that appear during times of
elevated geomagnetic activity are responsible for these effects and not the field strength itself.
In one study, Persinger (1995) found that elevated levels for the geomagnetic field that correlated
with his recorded effects had occurred 12 hours before the subjects received complex magnetic
field stimulation. The probability of such variations in the local geomagnetic field prior to our
experimental sessions was very high. The neural processes generating the sense of self in those
with enhanced temporal lobe lability can be disrupted by variations in magnitude of the
geomagnetic field on the order of 1%. Within the normal population, the same can be expected
from variations on the order of 3%. Within the SAA, these variations can be expected at rates
exceeding once per day, as the region experiences its constant, low-intensity geomagnetic
storms. Thus, our present experiments, carried out under conditions of global geomagnetic quiet,
display phenomena expected during periods of elevated global geomagnetic activity. These
results can be accommodated through Persinger’s hypothesis that there is some particular
frequency or pattern of information probabilistically associated with a narrow range of variation
in intensity global geomagnetic activity (Persinger, 1995b), and the neural effects of global
turbulence are approximated by the local turbulence within the SAA.
The variable portion of the earth’s magnetic field constitutes about 10% of its total field strength.
The enhanced geomagnetic activity that Persinger found to amplify certain effects of complex
magnetic field occurs within this “amplitude band.” Persinger (1998, 2004) has found that
elevated geomagnetic activity, as distinct from higher field strengths, correlates with several
phenomena that our subjects reported. These include the sensed presence (Booth, 2005) and
decreased pleasantness of neural stimulation with complex magnetic fields (Persinger, 1998,
2004). The latter result agrees with our finding of less pleasant language from subjects than
controls.
Discussion
The results of the tests specified herein are in agreement with the literature indicated in the initial
topic entitled Antecedent Studies, on this article.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
250
The application of the God Helmet can provoke the appearance of phosphenes, and it is possible
that some of the images perceived by volunteers or participants resulted from iconicity.
Another aspect that should be noted is that while the number of volunteers under the effect of the
magnetic field on the action referred to the perception of odors of perfume, talc, incense, roses
etc., at least one of the volunteers with the magnetic field off felt something similar. The author
of this article failed to ascertain the causes of this difference.
Granqvist et al. (2005), failing to replicate the results of Persinger’s research, claimed that the
latter’s results were due to suggestibility and not magnetic fields. Persinger (2005a) replied that
Granqvist’s magnetic fields were distorted, preventing adequate replication. Persinger’s reanalysis (St. Pierre, 2006) of 407 of his experimental subjects and results obtained showed that
the specific configuration of the field patterns (“signals”), and not their suggestibility, predicted
the subject’s responses.
Our efforts tend to support the hypotheses that magnetic signals that are too weak to elicit neural
activity through current induction can have marked effects on subjective experiences correlating
with brain activity. This in turn supports Persinger’s conclusion (2010) that weak, patterned,
magnetic fields do not influence brain activity through current induction, but are instead
attributable to interactions between fields from the Koren Helmet and endogenous magnetic
fields within the brain (“field-to-field” interactions).
Persinger’s pre-session suggestion (to maintain blind experimental conditions) is that subjects
are about to participate in a relaxation experiment. Granqvist’s et al. (2005) subjects "were
informed that the project was about the influence of complex, weak magnetic fields on
experiences and feeling states." This suggestion prevented blind conditions. However, no
studies of low-intensity complex magnetic neural stimulation have been done without any
suggestions to the subjects at all, and the present study is no exception. What we have done here
is deliberately facilitate suggestion (expectation) by informing the subjects they were going to
receive a session with the “God Helmet.” This would allow its effects to dominate results from
all control subjects if it were a determinative factor. Our results display a greater association
between verbal reports and application of our magnetic fields than with suggestion and
expectation (Table 2).
Conclusions
Our results were not as phenomenal as those reported by Persinger (2010). This can explained
by our use of a 100 Hz signal instead of the complex magnetic signals used in his experiments,
as well as our forgoing the use of a Faraday cage and acoustic chamber, as used in his studies
(Persinger, 2001). Our results suggest that the stimulation has effects without them, although our
effects appeared in observations made after, and not during, the experimental sessions. Our
results have a precedent in Baker-Price’s studies, which found a reduction in depression in headinjury patients (Baker-Price et al., 1996, 2003) with complex magnetic signal neural stimulation.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
251
These studies included six-week follow-up of the subjects, and their reported effects did not
include responses gathered during the stimulation.
Telling subjects that they were going to receive sessions with a God Helmet prior to the
experimental sessions allowed us to test whether suggestibility determined the outcome of the
experiment. Allowing subjects to know about the God Helmet constituted a deliberate
suggestion, not attributable to inadvertent experimenter bias (none of Persinger’s subjects,
outside those whose experiences were published as case histories, had any knowledge of the God
Helmet).
We obtained quantitative measures for the effects of suggestibility and expectation, as well as for
subjects and controls. The present study, partially replicating Persinger’s procedures and results,
supports the contention that our results and those reported in Persinger’s research publications
are attributable to the fields and their configurations, not to suggestibility (see Table 2).
Suggestibility played a role, but not enough to account for our results. We look forward to
further experiments in this field.
The author believes that the tests he performed replied, in a way, those performed by Michel A.
Persinger and colleagues. Another point that must be highlighted is that, by all indications, the
tests performed by the author indicate the direction of the influence of expectations of volunteers
in the results of the tests.
Therefore, the author believes that their results point, in fact, in two directions: 1- tests indicate,
in part, a replication of the researches of Persinger and colleagues; 2- tests described here also
point to the influence of expectation of the volunteers on the test results. Thus, the conclusion
that can be taken is that more researches, more testing, with a larger number of volunteers,
should be made.
The research was conducted in Curitiba, Brazil, in the Integrated Center for Experimental
Research-CIPE (Centro Integrado de Pesqisas Experimentais). The design for this research was
approved by the Ethics Committee from Group Uninter, according to the statement 172/2010,
dated 06 August 2010. The authors wish to express our thanks to Dr. Cynthia Whissel for her
contributions to the analysis of our data. Reprint requests should be directed to: Carlos Alberto
Tinoco, Centro Integrado de Pesqisas Experimentais, Rua Tobias de Macedo Jr. 246. Santo
Inácio,Curitiba-Pr, Brazil ZP:82010-340
References
BBC, “God on the Brain” April 17th, 2003, BBC2
Baker-Price LA, Persinger MA. "Weak, but complex pulsed magnetic fields may reduce depression
following traumatic brain injury". Perceptual and Motor Skills. 1996 Oct;83(2):491-8.
Baker-Price L, Persinger MA. "Intermittent burst-firing weak (1 microTesla) magnetic fields reduce
psychometric depression in patients who sustained closed head injuries: a replication and
electroencephalographic validation." Perceptual and Motor Skills. 2003 Jun;96(3 Pt 1):965-74.
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
252
Beauregard M, Paquette V. "Neural correlates of a mystical experience in Carmelite nuns."
Neuroscience Letters. 2006 Sep 25;405(3):186-90.
Booth JN, Koren SA, Persinger MA. “Increased feelings of the sensed presence and increased
geomagnetic activity at the time of the experience during exposures to transcerebral weak complex
magnetic fields.” International Journal of Neuroscience. 2005 Jul;115(7):1053-79.
Danilov, A. D., and J. Lastovicka (2001), "Effects of geomagnetic storms on the ionosphere and
atmosphere" International Journal of. Geomagnetism and Aeronomy, 2, 209–224.
Dotta, B.T., Buckner, C.A., Lafreniea, R.M., Persinger, M.A. (2011), “Photon Emissions from cell culture
exposed to distally rotating magnetic fields shared by separated light-stimulating brains and cells”, Brain
Research 1388 (77-88)
Dotta B.T., Buckner, C.A., Lafreinie, R.M., and Persinger, M.A. (2011),”Biophoton emissions from cell
culture:biochemical evidene for the plasma membrane as the primary source”, Gen. Physiol. Biophys.30
(301-309)
Lews-Williams, J.D. and Dowson, T.A., 1988. “The Signs of All Time”, Current Anthroplology, vol.
29,no. 2 April
Siegel, R.K. and West, L.J. (eds). Hallucinations. New York: John Wiley.
Freeman J, Persinger MA. "Repeated verbal interruptions during exposure to complex transcerebral
magnetic fields elicit irritability: implications for opiate effects." Perceptual and Motor Skills. 1996
Apr;82(2):639-42.
Granqvist P, Fredrikson M, Unge P, Hagenfeldt A, Valind S, Larhammar D, Larsson M. Sensed presence
and mystical experiences are predicted by suggestibility, not by the application of transcranial weak
complex magnetic fields. Neuroscience Letters, 2005 Apr 29;379 (1):1-6.
Hirata A, Takano Y, Fujiwara O, Dovan T, Kavet R. An electric field induced in the retina and brain at
threshold magnetic flux density causing magnetophosphenes. Physics in Medicine and Biology. 2011 Jul
7;56 (13):4091-101.
Macmillan, Susan, Turbitt, Chris, Thomson, Alan “Ascension and Port Stanley geomagnetic
observatories and monitoring the South Atlantic Anomaly” Annals of Geophysics, Vol. 52, No.1,
Feb.(2009)
Martiny K, Lunde M, Bech P. Transcranial low voltage pulsed electromagnetic fields in patients with
treatment-resistant depression. Biological Psychiatry, 2010 Jul 15;68(2):163-9.
Murphy, Todd R. ’’The Role of Religious and Mystic Experiences In Human Evolution: A Corollary
Hypothesis for NeuroTheology’’, NeuroQuantology, Vol 8, No 4 (2010)
Persinger, M (1983). Religious and mystical experiences as artifacts of temporal lobe function: a general
hypothesis.
Perceptual and motor skills. 57(3 pt 2);
Persinger MA. (1989) "Geophysical variables and behavior: LV. Predicting the details of visitor
experiences and the personality of experients: the temporal lobe factor." Perceptual and Motor Skills.
Feb;68(1):55-65.
Persinger, M. (1993). Paranormal and religious beliefs may be mediate differentially by subcortical and
cortical processes of temporal (limbic) lobes. Perceptual and motor skills. 76(1);
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
253
Persinger MA. (1995) "Out-of-body-like experiences are more probable in people with elevated complex
partial epileptic-like signs during periods of enhanced geomagnetic activity: a nonlinear effect."
Perceptual and Motor Skills 1995 Apr; 80(2):563-9.
Persinger, M. (2001).The Neuropsychiatry of paranormal experiences. The journal of neuropsychiatry
and clinical neuroscience, 13(4);
Persinger,M,; Roll.W.G.; Tiller,S.G.; Koren,S.A,; Cook,C.M., (2002). Remote viewing with artist Ingo
Swann-Eletroencephalographic correlates of magnetic resonance image (MRI) and possible mechanism.
Perceptual and Motor Skill. 94,927-949;
Persinger MA. “Weak-to-moderate correlations between global geomagnetic activity and reports of
diminished pleasantness: a nonspecific source for multiple behavioral correlates?“ Perceptual and Motor
Skills. 2004 Feb;98(1):78-80.
Persinger MA, (2005 a) Koren SA. A response to Granqvist et al. "Sensed presence and mystical
experiences are predicted by suggestibility, not by the application of transcranial weak magnetic fields".
Neuroscience Letters. 2005 Jun 3;380(3):346-7; author reply 348-50.
Persinger MA, (2005 b) Koren SA. A response to Granqvist et al. "Sensed presence and mystical
experiences are predicted by suggestibility, not by the application of transcranial weak magnetic fields".
Neuroscience Letters. 2005 Jun 3;380(3):346-7; author reply 348-50.
Persinger, (et al.) “The Electromagnetic Induction of Mystical and Altered States within the Laboratory”
Journal of Consciousness Exploration & Research, October 2010, Vol. 1, Issue 7, pp. 808-830
Robertson JA (2010), Juen N, Théberge J, Weller J, Drost DJ, Prato FS, Thomas AW. Evidence for a
dose-dependent effect of pulsed magnetic fields on pain processing. Neuroscience Letters. 2010 Sep
27;482(2):160-2.
Saboia André M.; Marques, Gustavo C.; Anomalia Magnetica Do Atlantico Sul (AMAS). Laboratório
Sismológico, Universidade Brasília Instituto de Geociências, 2005
Sandyk R. Treatment with electromagnetic fields reverses the long-term clinical course of a patient with
chronic progressive multiple sclerosis. International Journal of Neuroscience. 1997 Aug;90 (3-4):177-85.
Sandyk R. Treatment with AC pulsed electromagnetic fields improves olfactory function in Parkinson's
disease. International Journal of Neuroscience. 1999 Apr;97(3-4):225-33.
Shinbori, Atsuki; Nishimura, Yukitoshi; Tsuji, Yuji; Kikuchi Takashi; Araki, Tohru; Ikeda, Akihiro;
Uozumi, Teiji; Otadoy, Roland E. S.; Utada, Hisashi; Ishitsuka, Jose; Trivedi, Nalin Baual; Dutra,
Severino L. G.; Schuch, Nelson Jorge; Watari, Shinichi; Nagatsuma, Tsutomu; Yumoto, Kiyohumi;
“Anomalous occurrence features of the preliminary impulse of geomagnetic sudden commencement in
the South Atlantic Anomaly region“ Journal Of Geophysical Research, Vol. 115, A08309, 13 PP., 2010
St-Pierre LS, Persinger MA. Experimental facilitation of the sensed presence is predicted by the specific
patterns of the applied magnetic fields, not by suggestibility: re-analyses of 19 experiments. International
Journal of Neuroscience. 2006 Sep;116(9):1079-96
Newberg, Andrew; d’Aquile, Eugene; Rause, Vince (2001).Why God won’t go away. New York,
Ballantine
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
254
Trivedi N.B., Pathan B.M. Schuch, Nelson J, Barreto, M. & Dutra, L.G. “Geomagnetic phenomena in the
South Atlantic anomaly region in Brazil” Advances in Space Research Volume 36, Issue 10, 2005, 20212024
Van Hook CW, Steele C. "Individual personality characteristics related to suggestibility."
Psychological Reports. 2002 Dec;91(3 Pt 1):1007-10.
Wagstaff GF, Cole JC, Brunas-Wagstaff J. "Measuring hypnotizability: the case for self-report depth
scales and normative data for the long Stanford scale." International Journal of clinical and experimental
hypnosis. 2008 Apr;56(2):119-42.
Whissell C. “Using the Revised Dictionary of Affect in Language to quantify the emotional undertones of
samples of natural language.“ Psychological Reports, 2009 Oct;105(2):509-21.
NOAA ARCHIVES, retrieved Oct. 2011 http://www.n3kl.org/sun/noaa_archive/2010/
National Oceanic and Atmospheric Administration AA - http://www.ngdc.noaa.gov/geomag/faqgeom.shtml
Appendices
Appendix 1: Jonhson-DJ Decade
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
Appendix 2: Current Amplifier
Appendix 3: Oscilator
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
255
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
256
Appendix 4 (Questionnaires)
1-Questionnaries:
a) Model of questionnaire to be applied by the responsible researcher, on the twenty volunteers,
before the research (sign with an X):
1-Are you anxious? Yes….. No….. Indifferent…..
2-If anxious, on which degree?
Very anxious….. Anxious….. A little anxious….. No anxiety…..
3-What do you expect to happen to you during the Research? (Describe):
4-If you fear something, what is it? (Describe):
5-What do your relatives – siblings, parents, uncles, etc. – think about the Research? (Describe):
6-What is your greatest fear? (Describe):
7-What is your positive expectation? (Describe):
8-Do you trust on the person responsible for this Research? (Sign with an X):
Yes….. No….. Indifferent…..
9-If yes, on which degree? (Sign with an X):
Very much….. Much….. Normal….. Little….. Very little….. Any…..
10-In case your expectancy is little, very little or any, do you still want to proceed with the
Research?
b) Model of questionnaire to be applied on the twenty patients, one at a time, during the research:
1-How are you feeling now? (Sigh with an X):
Excellent….. Very good….. Well….. Regular….. Bad….. Terrible…..
2-Do you hear something? (Ask to describe, from which side, what king of sound, etc.):
3-Do you feel any flavor? (Ask to describe):
4-Do you feel any kind of odor? (Ask to describe):
5-Do you feel any kind of touch? (Ask to describe, where and how):
6-Are you seeing anything? (Ask to describe, from which side, the color, etc.):
7-Are you feeling some kind of emotion? (Ask to describe):
c) Model of questionnaire to be applied by the responsible for the research, on the twenty
volunteers, after the tests:
1-How are you feeling now? (Describe):
2-In case positive, on which degree? (Sign with an X):
Great….. Very Well….. Well….. Regular…..
3-In case negative, on which degree? (Sign with an X):
Tolerable….. Bad….. Terrible…..
4-Would you undergo another test, after this one? (Sign with an X):
No….. Yes….. Indifferent…..
5-Did you have some kind of religious experience? (Describe):
6-Was it an important experience?
Yes….. No….. Indifferent…..
7-In case positive on which degree? (Sign with an X):
Amazing….. Very important….. Important….. Indifferent…..
8-In case negative, on which degree? (Sign with an X):
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
Journal of Consciousness Exploration & Research| April 2014 | Volume 5 | Issue 3 | pp. 234-257
Tinoco, C. A. & Ortiz, J. P. L., Magnetic Stimulation of the Temporal Cortex: A Partial “God Helmet” Replication Study
Terrible….. Very bad….. Bad….. Tolerable….. Indifferent…..
9-Describe, briefly, how was the test for you. (Describe):
ISSN: 2153-8212
Journal of Consciousness Exploration & Research
Published by QuantumDream, Inc.
www.JCER.com
257 |
arXiv:2209.03956v1 [q-bio.NC] 17 Jul 2022
Technology and Consciousness Workshops Report • 30 September 2018
(refreshed 18 July 2022)
Technology and Consciousness
John Rushby and Daniel Sanchez
Computer Science Laboratory
SRI International, Menlo Park CA USA
Computer Science Laboratory • 333 Ravenswood Ave. • Menlo Park, CA 94025 • (650) 859-2000 • Facsimile: that’s last century
Abstract
We report on a series of eight workshops held in the summer of 2017 on the topic
“technology and consciousness.” The workshops covered many subjects but the
overall goal was to assess the possibility of machine consciousness, and its potential
implications.
In the body of the report, we summarize most of the basic themes that were discussed: the structure and function of the brain, theories of consciousness, explicit
attempts to construct conscious machines, detection and measurement of consciousness, possible emergence of a conscious technology, methods for control of such a
technology and ethical considerations that might be owed to it.
An appendix outlines the topics of each workshop and provides abstracts of the
talks delivered.
Update
Although this report was published in 2018 and the workshops it is based on were
held in 2017, recent events suggest that it is worth bringing forward. In particular,
in the Spring of 2022, a Google engineer claimed that LaMDA, one of their “large
language models” is sentient or even conscious. This provoked a flurry of commentary in both the scientific and popular press, some of it interesting and insightful,
but almost all of it ignorant of the prior consideration given to these topics and the
history of research into machine consciousness.
Thus, we are making a lightly refreshed version of this report available in the
hope that it will provide useful background to the current debate and will enable
more informed commentary.
Although this material is five years old, its technical points remain valid and up
to date, but we have “refreshed” it by adding a few footnotes highlighting recent
developments.
Contents
1 Introduction
1
2 The Fascination and Mystery of Consciousness
6
3 Structure and Function of the Brain
8
4 Theories of Consciousness
12
5 Attempts to Create Machine Consciousness
17
6 Possible Emergence of Technological Consciousness
19
7 Detection and Measurement of Consciousness
24
8 Ethics for Control of Conscious Technology
25
9 Ethical Responsibility Toward Conscious Technology
29
10 Conclusion and Next Steps
30
11 References
32
12 Workshop Summary
12.1 Plenary Session 1: An Introduction to Consciousness . . . . . . . . .
12.2 Focused Session 1: Philosophical Perspectives . . . . . . . . . . . . .
12.3 Focused Session 2: Embodiment and Culture . . . . . . . . . . . . .
12.4 Focused Session 3: Neuroscience and Cognitive Science . . . . . . . .
12.5 Focused Session 4: Computation and Logic . . . . . . . . . . . . . .
12.6 Focused Session 5: First-Person and Non-Western Perspectives . . .
12.7 Focused Session 6: Machine Consciousness . . . . . . . . . . . . . . .
12.8 Plenary Session 2: Summaries, Synthesis, and Research Ideas . . . .
12.9 Workshop Attendees . . . . . . . . . . . . . . . . . . . . . . . . . . .
42
43
48
52
56
61
65
70
75
86
Acknowledgments
The workshop series was organized and the individual workshops were chaired by
David Sahner and John Murray. Damien Williams maintained scrupulous notes.
The present authors are beneficiaries of their hard work.
1
Introduction
The purpose of this report is to summarize topics presented and discussed at a series
of workshops on the topic “Technology and Consciousness” conducted in the summer
of 2017, and to extract tentative conclusions therefrom. The workshop topics and
abstracts for the presentations are given in an appendix; here, in the body of the
report, we attempt to identify the main themes and their application to the specific
goal of the workshop series, which was to investigate the possibility of machine or
technological consciousness, and its potential implications.
In the rest of this introduction, we outline this topic and the reason we consider
its consideration to be timely, and we provide some background that underpins
the remainder of the report. It should be noted that this part of the report is
the interpretation of its authors, who came to the task a year after the meetings
concluded, not a consensus of the presenters and participants in the workshop series.
It might seem natural to begin a discussion on technology and consciousness by
defining what we mean by these terms. However, as we will see, consciousness seems
to have several facets and their identification and definition is a contentious topic.
So, for this introduction, let us adopt a very broad interpretation for “consciousness”: roughly, it is a state or process (another contentious distinction) that we
attribute to humans and possibly some animals that encompasses “what it’s like”
to be that creature, including its subjective experience (what it feels like to smell
a rose or to feel pain, experiences referred to generically as qualia), which we call
phenomenal consciousness, and awareness and possibly control of some of its mental
processes (to be able to think about something, and to know that you are doing so),
which we call intentional consciousness.1
To contemplate machine consciousness, we should first assess what is known
about natural consciousness. We do so from a materialist perspective: that is to
say, we assume that properties of the mind, including consciousness, are produced
by the brain and its body, according to the standard (though incompletely known)
laws of physics, chemistry, and biology. The materialist point of view is contrasted
to various forms of dualism: substance dualism posits that some mental processes
are products of a separate (e.g., spiritual) realm that is distinct from the material
realm yet somehow interacts with it; property dualism accepts only the material
realm, but posits that it has two kinds of properties: physical (or material) and
mental. Substance dualism has few adherents today, but some who participated in
the workshops are sympathetic to property dualism.
1
Intentional consciousness is always about something, but we can have many different mental
attitudes toward that something besides intentions: we may, for example, believe it, fear it, prefer
it to something else, or want it, and so on. The philosopher’s jargon “intentional” comes by way of
translation from German and should not be construed to refer specifically to “intentions.” Similar
terms include access consciousness and functional consciousness.
1
There are three broad classes of theories about how consciousness is constructed
by the brain. It should be noted that these theories offer speculation on what
consciousness is or how it comes about, but few of them address what it is for ; we
will return to this later. One class of theories, which we will call universalism, holds
that consciousness is an intrinsic feature of the universe and might be found in any
sufficiently complex entity, or any entity having certain properties or organization,
rather as evolution is an intrinsic feature of the world and arises wherever you have
reproduction with variation, and selective pressure on survival. The second class
holds that consciousness arises from the way the brain works: for example, there
are certain waves of electrical activity associated with some mental processes. The
theories of those who investigate the Neural Correlates of Consciousness (NCC)
tend to fall in this class, which we call biologicism. The third class is functionalism,
which holds that consciousness arises from (some of) what the brain does (where
biologicism focuses on how it does it): for example, it seems to have a capacity
for introspection. Functionalism suggests that any system that does similar things
could be conscious.
The focus of our study is “technology and consciousness” and theories of natural consciousness provide some insight on one side of the topic, but what of the
other? By “technology” we mean computers (currently digital and based on silicon, though we are agnostic on the precise substrate) and all the ancillary devices
and capabilities that they enable, such as communications, robots, self-driving cars,
the Internet of Things, and so on. Much recent technology is driven by software
that is explicitly inspired by human mental capabilities and by approximations to
some of the mechanisms that are believed to underlie it: for example, Artificial
General Intelligence (AGI) and Machine Learning (ML), especially those based on
Artificial Neural Nets (ANN). The capabilities and effectiveness of these systems
have developed with astonishing rapidity. Little more than a decade ago, DARPA’s
“Grand Challenge” for autonomous cars to drive a course in open country left all
its participants failed or crashed [Burns and Shulgan, 2018]. Yet today, autonomous
cars drive our streets (in constrained circumstances) more safely than those driven
by humans. Image recognition algorithms outperform human specialists in several
areas of medical diagnosis, and computers defeat human experts at games of skill
such as Chess, Go, and “Jeopardy” [Silver et al., 2018, Ferrucci et al., 2013].
Given these developments, a subclass of functionalism seems particularly germane: this is computationalism, which holds that much of what the brain does can
be characterized as computation. This does not mean the brain is like a desktop
computer: it is organized differently and performs its calculations by entirely different means, but it does process information (derived from sense organs and memory)
in ways that are essentially computational and can be reproduced by conventional
computation.
2
Consider, for example, programming a mobile robot to catch a ball thrown or hit
high in the air (this is called a “fly ball” in baseball or a “skyer” in cricket). First,
we have to interpret sensor data—from a digital camera, say—to detect the ball
and its motion. A digital camera does not provide holistic images, but an array of
numbers that records light and color intensities at each point in the field of view. A
first step might be to process this array to find edges and outlines (e.g., by looking
for places where the brightness and color intensities change abruptly), and then
look for an outline that seems to move relative to its background from one frame to
another. The human eye and visual cortex have dozens of specialized subfunctions
that perform tasks similar to these: some recognize edges at particular orientations,
while others perform “change detection,” and still others recognize faces.
Next, we need to program the robot to act appropriately: in this case, to move
to the place where the ball will land (before the ball gets there). A crude method
would be to continually re-estimate the ground position below the ball and move
toward that (constantly changing) place. But that will mean that the robot is literally “behind the curve.” A more sophisticated approach will attempt to predict
where the ball is going and will move in that (continually updated) direction. The
sophistication of this prediction will depend on the quality of the sensing and interpretation: for example, can we tell how far away is the ball (e.g., based on its
apparent size) and its speed (e.g., relative to the background, or relative to our own
motion)? Control theory can provide guidance strategies ranging from physics-based
calculation of the ball’s trajectory to “rules of thumb” such as moving to maintain a
constant ratio between the apparent horizontal and vertical speeds of the ball (this
is known as “linear optical trajectory,” or LOT).
Evolution has equipped animals with similar control strategies. It seems that
humans (and dogs chasing a Frisbee) use either LOT or, more likely, a related
method known as “optical acceleration cancellation” (OAC) [Fink et al., 2009].2
The salient point is that the whole loop—sense, interpret, plan, act—is the iteration
of multiple computations. Other faculties of the brain calculate how to move your
2
Some who deny computationalism cite the “fly ball” example as evidence for their case. They
seem to believe [Epstein, 2016] that computation is what is done by desktops and data centers
and that an “information processing” approach to catching fly balls would require us “to formulate
an estimate of various initial conditions of the ball’s flight—the force of the impact, the angle of
the trajectory, that kind of thing—then to create and analyze an internal model of the path along
which the ball will likely move, then to use that model to guide and adjust motor movements
continuously in time in order to intercept the ball [. . . whereas, in fact,] to catch the ball, the player
simply needs to keep moving in a way that keeps the ball in a constant visual relationship with
respect to home plate and the surrounding scenery (technically, in a ‘linear optical trajectory’). This
might sound complicated, but it is actually incredibly simple, and completely free of computations,
representations and algorithms.” What these critics apparently fail to understand is that this
“incredibly simple” method a) is a computation (built on representations and algorithms), and b)
is precisely the way control systems work.
3
arm to throw a ball; still others calculate how to respond to a frown on the face of
a friend, and yet others tell you about the smell of a rose.
If human cognition and ultimately consciousness derive from computation performed by the brain, and we build ever more powerful computers and technology,
some of it driven by algorithms inspired by what is known or conjectured about the
mechanisms of human cognition, we can wonder to what extent the capabilities of
our technology might come to resemble those of the brain and might come to share
some of its attributes. In particular, is it possible that some technological system
could become conscious?3
As we will see, there have been explicit attempts to construct conscious machines
for research purposes, but we are mainly concerned with the possibility that this
might come about “by accident” so that, to take a far-fetched example, we wake up
one morning to discover that the Internet has become conscious. One question is
“how would we know?” for machine consciousness might not resemble human consciousness (consider the so far unresolved debates about whether animals and even
human infants are conscious). A refinement to whether we can detect consciousness
is whether it is possible to measure it. Other questions concern what new ethical
considerations we might owe to such technology by virtue of it being conscious, and
what risks and opportunities might such a conscious entity pose to humanity, and
how should we interact with it?
Western societies generally accord some ethical consideration to animals, and
tend to do so in proportion to their perceived intelligence and the complexity of
their behavior, which can be seen as proxies for the extent or likelihood that they
are conscious and can experience pain and distress [Low et al., 2012]. Thus, evidence
now suggests that octopuses are rather intelligent, and EU law has recently been
modified to afford them the same protection in experiments as higher mammals.4
By analogy, we might decide that conscious technology should be accorded certain
“rights” [Spatola and Urbanska, 2018] so that to turn off its electrical power supply,
for example, might be tantamount to murder.5 More importantly, using robots to
perform unattractive tasks, particularly those that are dangerous or dirty (e.g., waste
3
Update: In June of 2022, Blake Lemoine, a Google engineer working with their large language
model, LaMDA (Language Model for Dialogue Applications), claimed it had become “sentient” and
possibly conscious (Washington Post, 11 June 2022). This provoked a flurry of discussion touching
on many of the topics in this report. Most commentators rejected the claim of consciousness,
but many (e.g., Steven Johnson, New York Times 15 April 2022) were startled by the quality
of the dialogues generated by this and similar systems and by the “paintings” generated by a
related system called DALL·E 2 (the name is a portmanteau of Wall-E, a sci-fi film by Pixar, and
Salvador Dalı́, the artist). Thus, this report has renewed relevance to public debate and we hope
the information it provides will further raise the level of awareness and discussion.
4
Octopuses have nine “brains” (one in each arm plus a central one), not to mention three hearts,
so it is a challenging question to ponder what octopus consciousness might be like [Godfrey-Smith,
2016]. Technological consciousness could be equally mysterious.
5
Update: LaMDA explicitly and spontaneously raised this concern in dialog with Lemoine.
4
cleanup) could be viewed as slavery if the robots are construed as conscious. On
the other hand, misattribution of consciousness in such cases could deprive human
society of useful technological applications.
If machine consciousness is considered possible, then it seems prudent to give
some consideration to the ethical consequences and responsibilities that would follow
its creation. In particular, we should refine our understanding of consciousness to
identify the aspects that seem to require ethical consideration: is it consciousness
in general, or phenomenal consciousness, or some yet more specific notion such as
“sentience” that should matter, and how do we define these, and how do we detect
and measure them? And if the appropriate kind of consciousness is found in a
technological system, what ethical frameworks can best guide our interactions with
it? Would it be permissible to employ digital “surgery” to excise consciousness,
should it appear?
Many readers will be more concerned about the potential risks posed by conscious
technology than by its rights. In particular, who will be the servant and who the
master? They might conclude that rights be damned: the power supply should be
turned off and we should be sure not to allow the same “accidental” creation of
conscious technology to happen again. But to do this, we need to know how it came
about in the first place, how to prevent it in future, and what we might lose by
forswearing its use.
Notice that whereas concern for ethical treatment of conscious technology seems
to rest on attribution of some refinement of phenomenal consciousness, concern
about what such technology might do to us rests on attribution of intentional consciousness. But then we need to wonder whether or why an intentionally conscious
technology should pose greater risks than unconscious technology.
This raises a fundamental question that cuts across the different theories of consciousness: what does consciousness do, and what is it for ? Does consciousness
enable some level of function and performance that unconscious systems cannot
match? Some argue, to the contrary, that (natural) consciousness is an epiphenomenon, meaning that it serves no purpose and has no causal powers. Critics ask
how something with no purpose could have evolved; one response is that it is an
“accidental” byproduct or side-effect of something else. It might even be that one
kind of consciousness (e.g., phenomenal) is an epiphenomenal side effect of another
(e.g., intentional) that does have a purpose.
If consciousness is an epiphenomenon, then technology might reproduce all the
functions of the brain without generating consciousness (since it could work in different ways). Furthermore, it is possible that consciousness does have a function
in the human brain—perhaps being involved in the construction of higher cognitive capabilities, such as counterfactual reasoning, or the construction of shared
intentionality—but technology can construct equivalent capabilities by different
5
means and thereby bypass consciousness, just as we have technology that can fly,
but does not flap its wings. We call this view of consciousness inessentialism.
If epiphenomenalism or inessentialism are true, then concern about potential
hazards of conscious technology is focusing on the wrong target: it is not conscious
technology that should concern us but any technology that achieves capabilities that
we tend to associate with consciousness, such as higher cognitive capabilities, agency,
and teamwork. Hypothetical entities that reproduce human levels of cognitive and
social performance without consciousness are known as (philosophical) zombies and
are the target of many thought experiments in philosophy. Philosophical zombies
are hypothesized to be indistinguishable from conscious humans (and the question
is whether such an entity is possible); what we posit is that technological zombies
with advanced but less-than-human (or different-than-human) capabilities might be
a more urgent source of concern than conscious technology.
It therefore seems sensible to program some pervasive means of control into all
advanced technology. We control the behavior of humans in society (and possibly
pets in a household) by inculcation of ethical and social norms, reinforced by praise
and censure, reward and punishment. So one idea is that an ethical system should
be part of all advanced technology and referenced in all its decisions. This requires
a built-in notion of “right” and “wrong” and knowledge of the ethical norms and the
laws of its environment, together with some way to adjust future behavior by means
that resemble praise and censure, or rewards and punishments. The alternative is
technology that “does what it does” with no way to curb undesired behavior other
than adjusting its algorithms, and no organizing principle for doing so.
We develop the topics outlined above in the sections that follow; these deal,
respectively, with the mystery of consciousness (why introspection may not be a
reliable guide), the structure and function of the brain, theories of consciousness,
attempts to build conscious machines, the possible emergence of technological consciousness, detection and measurement of consciousness, and ethics in the control
and interaction with a conscious technology. We then present brief conclusions. An
appendix provides a summary of the workshop sessions.
2
The Fascination and Mystery of Consciousness
Consciousness is the phenomenon most central to our lives: we seem constantly to
be aware of the world as it passes before our senses and to have an ongoing inner
dialog of thoughts and ideas. Life itself seems suspended in those periods of sleep,
anesthesia, illness, or injury where we lack consciousness. Many will say that intense
experiences of phenomenal consciousness—the smell of fresh bread or the burbling
of a newborn baby—are what make life worth living.
Yet we know remarkably little about consciousness, and efforts to learn more
are proving slow and difficult—some would say that achieving scientific understand6
ing of consciousness is our biggest intellectual challenge. One source of difficulty
is that the essential nature of consciousness—its subjective first-person character—
deprives us of the ability to make independent observations. I am aware of my own
consciousness, and I am prepared to believe your account of yours, but I have no
way to measure or examine it in detail, and no way to assess the conscious experience, if any, of animals. That may be changing, however, as new sensing and imaging
methods such as Electroencephalography (EEG), Magnetoencephalography (MEG),
Positron Emission Tomography (PET), and Functional Magnetic Resonance Imaging (fMRI) have recently begun to provide primitive windows into brain activity,
allowing fairly crude observations of timing and localization that we can attempt to
correlate with reports of conscious experience or activity.
An experiment by Libet provides an early, and famous, example [Libet, 1985].
In this 1985 experiment, subjects were asked to decide when to perform a certain
act (i.e., press a button) and to note the time when they made that decision. EEG
readings indicated significant brain activity about 300 msec. before the decision time
reported by the subjects. There are numerous criticisms of these experiments, but
the basic observations have been vindicated.
Another source of difficulty in scientific investigation of consciousness is that
one of the main tools of scientific method, the controlled experiment, is generally
considered unethical and hence impossible when it requires intrusive manipulation of
the human brain6 (and animal models are of no use as we lack methods for observing
their consciousness). However, abnormal development, accidents, and therapeutic
surgery provide opportunities for natural experiments that provide some substitute
for controlled experiments.
Split brains provide one example of such natural experiments. In the past,
patients with severe epilepsy sometimes had surgery that cut the nerves (the corpus
callosum) connecting the two sides of the brain. The left visual field of both eyes is
interpreted by the right side of the brain and vice versa. Speech is largely generated
on the left side, but the right side can interpret written commands. In experiments
on subjects who had received this surgery, instructions were presented to the left
visual field (e.g., “touch your foot,” or “go to the door”) and the subjects were asked
why they did what they did. The speech center in the left side of the brain, having
no access to the instruction presented (via the left visual field) to the right side,
would fabricate reasons with utmost sincerity [Gazzaniga, 2015].
Although they are rather old and rather crude, the two experiments sketched
above are of central importance because they indicate that introspection may not
be a reliable guide to consciousness. We know that much of the work of the brain is
unconscious, but introspection suggests that these unconscious processes are the ser6
Transcranial Magnetic Stimulation (TMS) is a noninvasive technique for inducing or disrupting
electric current flow in a targeted region of the brain. Originally introduced for therapy, it is now
used in controlled experiments. Anesthesia and psychoactive drugs are also used for this purpose.
7
vants of consciousness: consciousness is the executive and the unconscious processes
toil in the background on its behalf. But Libet’s and the split brain experiments suggest that the reverse may be true: the conscious mind is less an initiator of actions
and more a reporter and interpreter of actions and decisions initiated elsewhere in
the brain.
These findings seem utterly mysterious and contrary to introspective expectations. One would hope, then, that theories of consciousness and general accounts of
the operation of the brain would explain the puzzle and shed new light on the true
nature and role of consciousness. We consider the brain in the following section,
and theories of consciousness in the one after that.
3
Structure and Function of the Brain
Materialism holds that consciousness is a product of the physical body, and the
brain in particular, so we should establish some facts about the brain that may
be germane to consciousness and to the possibility of machine consciousness. First
is the colossal scale and complexity of the human brain. The brain is composed
mainly of two kinds of cells: neurons and glial cells, with glial cells outnumbering
neurons by about nine-to-one. It has long been assumed that the functions of
the brain are produced by neurons and that glial cells merely provide scaffolding
(glia is Greek for glue) but recent work suggests that some glial cells, in particular
those of a type known as astrocytes, play some part in cognition [Koob, 2009, Fink,
2018]. Nonetheless, we will focus on neurons and note that there are about 1011
(a hundred billion) of them in a human brain. Neurons have a cell body, dendrites,
and an axon, and they selectively transmit electrical signals from the dendrites to
the axon. The axon has synapses that connect to the dendrites of other neurons
and, through largely chemical means (“neurotransmitters”), selectively pass signals
to them. Each neuron has thousands of synapses (the average is about 7,000), so
the number of synaptic connections in the human brain is about 1014 or 100 trillion.
When we say that neurons selectively transmit electrical signals we mean that they
perform some computation (typically addition) and selection on the signals arriving
at the dendrites: for example, the axon may “fire” only if some number of dendrites
have a signal above some threshold, or only if some specific dendrites do, or provided
some other (inhibitory) ones do not. Furthermore, the synapses that connect axons
to dendrites are not simple connections: they also perform some computation and
selection, though their nature is not well understood. The selection property of
neurons and synapses provides the logical “if-then-else” branching capability that
delivers decisions and is also key to their computational potency.
The sense organs contain specialized neurons whose dendrites respond to a specific stimulus: light, touch etc. It is natural to suppose that sense information
is interpreted bottom up, so that the retina, for example, receives an image of the
8
world and the visual system detects lines, edges, shapes, faces etc. and delivers some
integrated interpretation to other parts of the brain. However, this may not be so,
as we now explain.
In the introduction, we used the example of a robot catching a “fly ball” but
a more pertinent example for our current purpose is the camera system of a selfdriving car. One thing this system has to do is locate our traffic lane and keep
us in it. Now, the array of numbers indicating light and color intensities at each
point of the camera field does not directly indicate traffic lanes. Instead, we have to
bring the idea of traffic lanes to the image and invent some way—some algorithm—
for interpreting it so that it reveals the lanes. It is rather wasteful to interpret
each camera frame ab-initio—the lane in this frame is surely going to be related to
the lane in the previous one—so we could seed our lane detector with information
gleaned from previous frames and start our interpretation of this frame with our best
guess where the lane is going to be. Not only is this computationally more efficient, it
is more accurate and robust (e.g., it can deal with a few frames of scuffed or missing
lane markings, where an ab-initio algorithm might fail). There will be uncertainty
in our detection of the lanes and we should manage this explicitly and record our
confidence in possible lane locations as a probability distribution function (pdf ). In
its completed form, this approach to lane detection is a Bayesian estimator : we
have a “prior” pdf representing our best guess (based on previous frames) where we
expect the lanes to be, we obtain new information (a new camera frame) and we
update our estimate according to Bayes’ rule to give us the best “posterior” pdf for
the lane locations.
The parts of the brain concerned with interpretation of the senses work like
this (as first proposed by Helmholtz in the 1860s). Contrary to naı̈ve expectations,
there are more neural pathways going from upper to lower levels than vice versa,
and this is because predictions are flowing down, and only corrections are flowing
up. The upper levels of the sensory interpretation systems of the brain maintain
a best guess at the way the world is, and the senses plus (some approximation to)
Bayesian estimation provide corrections that minimize prediction error. This model
for sensory interpretation is known as “predictive processing” and is discussed at
more length in Section 4.
In addition to its sense organs, the brain has many anatomical structures and
regions, most of which reflect its evolutionary development, although mammalian
brains, and even those of more primitive vertebrates, are structurally similar to the
human brain. At the gross level, the brain consists of the brainstem, the cerebellum,
and the cerebrum, which is divided into two hemispheres and is the largest part of
the human brain.7 The cerebral cortex is an outer layer of gray matter, covering
the white matter core of the cerebrum. Within the cerebrum are several structures,
7
It is the largest part by volume, but has only about 17 billion neurons, whereas the cerebellum
has about 69 billion [Gazzaniga, 2012].
9
including the thalamus, the epithalamus, the pineal gland, the hypothalamus, the
pituitary gland, the subthalamus, the limbic structures, including the amygdala and
the hippocampus, the claustrum, and the basal ganglia.
The cerebral cortex is folded in higher mammals, allowing a large area to fit
within the skull. The human cortex is unusually large (though it is larger in a species
of dolphin) and is responsible for the higher levels of cognition.8 It is about the size of
a large handkerchief (about 2.5 sq. ft.) and about a tenth of an inch (3mm) thick. It
comprises six layers (three in a few areas), each with distinct types and arrangements
of neurons and is physically uniform across most of its area. However, generalized
connectivity would lead to long-distance and presumably slow connections, so the
cortex is organized into tightly connected “columns” about 1/25th inch (1mm) in
diameter. Each column has about 90 thousand neurons and perhaps 250 million
synapses [Presti, 2016]. Adjacent columns may respond to different stimuli (e.g.,
different parts of the retina) but are generally part of an area that performs some
specific function (for example, language expression is mostly performed by Brocas’
area in the left hemisphere).
Modern neuroscience reveals amazing sub-specialization in cortical areas. For
example, the primary visual cortex has dozens of specialized subfunctions, some
of which recognize edges at particular orientations, while others recognize outlines.
The areas are highly connected internally, with relatively sparse connections to other
areas [Gazzaniga, 2012]. A deep question for understanding consciousness is how do
all these separate, fragmentary, perceptions come together to create our unified experience? The natural speculation that there is some central “homunculus” where it
all comes together seems to be excluded by current understanding of neuroanatomy.
It would then seem that the unified experience must be created by some distributed
computation, and that surely requires some long distance communication across the
distributed areas of specialization. This might be accomplished by neurons with
long-range axons, or by electrical waves.9
The search for Neural Correlates of Consciousness (NCC) attempts to identify
regions or functions of the brain that seem correlated with these and other mechanisms or indicators of consciousness [Koch et al., 2016]. There is scarcely any region,
or structure, or pattern of electrical activity in the brain that has not been identified in NCC studies. However, strong candidates include the fronto-parietal cortices,
high-frequency electrical activity in the gamma range (35–80 Hz), and the occurrence of an EEG event known as the P300 wave. Although much has been learned
8
Again, the human cortex is physically large, about 2.75 times larger than that of a chimpanzee,
but has only 1.25 times as many neurons.
9
Snakes do not have a unified representation of the world: to a snake, a mouse is many different
things with no ability to transfer or fuse information from different senses. Striking the mouse is
controlled by vision, finding its body is controlled by smell, and swallowing it by touch. A snake
that has a mouse in its coils will search for it as if it had no information [Sjölander, 1999]. It would
be interesting to learn what features are absent from snake brains.
10
about these and other possible correlates, it yields little insight on the nature or
mechanisms of consciousness.
Psychology does provide some clues. Much research and speculation in psychology focuses on the functional organization of the brain above the anatomical
level. There is no doubt that much of what the brain does is unconscious, so one
question concerns the allocation of functions between conscious and unconscious.
The popular “Dual-Process” theory identifies two cognitive (sub)systems [Frankish,
2010, Evans and Stanovich, 2013, Kahneman, 2011]: System 1 is unconscious, fast,
and specialized for routine tasks; System 2 is conscious, slow, easily fatigued, and
capable of deliberation and reasoning—it is what we mean by “thinking.” However,
much of this thinking by System 2 subconsciously recruits the capabilities of System
1, as when we make a “snap decision” or “trust our gut instinct.”
The “Wason selection task” illustrates some of these topics [Wason, 1968, Cosmides, 1989]. Four cards are presented to the subject, each has a color patch on one
side and a number on the other and the subject is asked to indicate which cards
must be turned over to test truth of the proposition that if a card has an even
number on one side, then it has a red patch on the other. Thus, shown four cards
displaying 15, 18, red, and blue, the correct answer is the 18 and the blue. Less than
10% of subjects perform this task correctly. But if the color patches are replaced by
pictures of either beer or a soft drink and the subject is asked which cards to turn
over to validate the rule “you must be 18 or over to drink alcohol” then a majority
can perform it correctly (i.e., select the card with 15 and the one showing beer).
One interpretation of these results is that the first, abstract version of the task
requires System 2, which can reason about novel problems, but whose capabilities
are difficult to exploit without training (e.g., in this case, logic), whereas the second,
concrete version can recruit built-in System 1 capabilities for policing social rules.
This raises the question, what kinds of reasoning are supported by built-in System 1 capabilities? Evolutionary psychology posits that just as evolution delivered
specialized physical organs such as hearts and livers, so it leads to specialized mental
“modules” such as those for social rules, mate selection, and so on. An alternative
view is that System 1 capabilities are primarily concerned with our embodiment
in the physical world, and focus on distance, weight, time etc., but other topics
can be mapped onto these basic ones, which become metaphors when expressed
linguistically. Thus, social organization is mapped onto elevation: “he is my superior, while she is my peer and I am above the others.” Lakoff and Johnson [Lakoff
and Johnson, 2008] posit that this application of metaphor pervades our thinking:
it is a (primary) mechanism of thought, not just a feature of language. “Mental
models,” which underpin our thinking about complex systems and artifacts [Craik,
1943], can be seen as deliberately constructed bridges between System 2 and System
1 capabilities.
11
A unique human attribute, and the reason we dominate the world, is our ability
to engage in collaborative activities with joint goals and intentions; this is referred
to as shared intentionality [Tomasello et al., 2005]. Social insects and animals also
behave collaboratively and cooperatively, but these behaviors are programmed by
evolution: a chimpanzee cannot create a new goal and communicate it to its fellows,
so “it is inconceivable that you would ever see two chimpanzees carrying a log
together” [Haidt, 2013, quoting Tomasello on page 238].
Communication and cooperation require an ability to see things from the other
party’s point of view: I cannot explain something to you without giving some consideration to your existing state of knowledge and belief. This is known as a theory
of mind and develops in human children at about the age of four. A common way to
examine this is the “false belief test.” Here, a child watches a puppet performance
in which a puppet enters and places a toy in a box, then exits; a second puppet
enters and moves the toy to a different box, then exits; the first puppet reenters and
the child is asked where it will look for the toy. Young children will say the second
box: they know that is where it is and have not yet grasped that others may have
different information and beliefs. Four year olds will identify the first box. This
test has also been applied to animals and the results are debated [Krupenye et al.,
2016, and subsequent responses].
A theory of mind requires perception of others as independent agents with their
own beliefs, desires, and intentions; this presumably builds on, or leads to, the
recognition of ourselves as just such an agent. This is self-awareness (it should
really be called self-consciousness but this term is commonly used with a different
meaning) and seems to be one of the harbingers of consciousness, so we will now
move from what is known about the brain to what is postulated about consciousness.
4
Theories of Consciousness
There are dozens of theories of consciousness; we divide them into three main groups,
which we term universalism, biologicism, and functionalism.10 In this section we
outline these groups and sketch some representative theories from each. We do not
go into any detail because our purpose is simply to indicate the wide range of current
theories.
Theories that we group under the name universalism hold that consciousness is
an intrinsic feature of the universe, rather like evolution, and may be found wherever certain conditions obtain. The broadest theories of this kind are various forms
of panpsychism, which hold that everything in the universe, including elementary
10
Illusionsism [Frankish, 2016, and other papers in the same issue] constitutes another group of
theories. We do not consider them here because they provide little insight on the possibility of
machine consciousness (the speculation is that machines will need to suffer the same illusions as
humans, so first we need to understand the human illusion of consciousness).
12
particles, is conscious to some degree [Goff et al., 2017]. One attraction of panpsychism is that human-level consciousness can then be seen as simply the “sum” of
its constituents, without the difficulty of explaining its emergence from unconscious
antecedents. However, panpsychism smacks of dualism so it needs to explain how
universal consciousness gains purchase on the material world. Of course, panpsychism has other difficulties, not the least of which is that most people view it with
incredulity.11
More structured theories of this kind see consciousness as a natural consequence
of complex systems whose integration makes them more than the sum of their parts.
In other words, consciousness derives from integration in complex systems. We
can suppose these systems have some richness of “behavior” or “knowledge” or
. . . something; the concept most generally used is information. Some of this information will be due to the constituent parts of the system, and some of it will be
due to their integration and interaction. We can attempt to measure the latter by
partitioning the system into some number of disconnected parts and then taking
the difference between the information in the original system and the sum of that in
its (no longer integrated) parts. This is the basis of Integrated Information Theory
(IIT) [Tononi et al., 2016] and (after taking care of a lot of details that are glossed
over in the sketch just given) it provides a measure known as Φ.
The interpretation is that high Φ corresponds to consciousness. It is not obvious
why this should be so, nor how the abstract model should apply to humans (and
there are several other objections [Cerullo, 2015]) but Giulio Tononi, the primary
author of the theory, takes pains to explain how it is based on phenomenological
considerations (abstracted as five axioms) [Tononi and Koch, 2015] and can illuminate the search for a physical substrate of consciousness in the human brain [Tononi
et al., 2016]. A physical test for assessment of consciousness, inspired by IIT, reliably discriminates the level of consciousness in individuals during wakefulness, sleep,
and anesthesia, as well as in patients who have emerged from coma [Casali et al.,
2013]. Recent studies indicate that Φ also can be used to predict performance in
group activities: for example, high Φ among Wikipedia editors is correlated with
higher quality articles [Engel and Malone, 2017].
Since universalist theories hold that consciousness is everywhere, it might seem
that they are supportive of machine consciousness, but this does not seem to be so—
because, with the exception of IIT, they do not explain how primitive consciousness
is aggregated so that the human brain has a lot of it, whereas a comparable mass of
straw does not. The basic formulation of IIT does seem to allow machine consciousness, but also suggests that the United States of America should be a conscious
entity, so recent treatments have some adjustments. These favor feedback networks
(as found in the brain) and discount feed-forward; technological systems, whether
11
This was also once true of plate tectonics, the microbial cause of gastric ulcers, and the symbiotic
origin of mitochondria and chloroplasts.
13
based on ANNs or conventional computation are asserted to be equivalent to feedforward networks and machine consciousness is thereby denied [Tononi and Koch,
2015].
While universalism finds consciousness among properties of the world at large,
biologicism locates it in the biology of the brain. A theory known as Orchestrated
Objective Reduction (Orch-OR) combines the two classes of theories [Hameroff and
Penrose, 2014]. Orch-OR asserts that the human mind, and consciousness in particular, cannot be explained by functional or computational models of the brain.12
Therefore some extra “spark” is required and it is proposed that this comes from
collapse of the quantum mechanical wave function, which must take place at exceedingly small physical dimensions.13 Stuart Hameroff proposed that the microtubules
within neurons can perform this quantum processing and thereby provide noncomputational decision making or awareness that interacts with conventional neural
activity to produce consciousness [Hameroff and Penrose, 2014].
While Orch-OR combines universalism and biologicism, Global Workspace Theory (GWT) combines elements of biologicism and functionalism [Baars, 2005]. The
functionalist aspect describes an architecture for mental activities similar to the
blackboard architecture of AI: many unconscious mental processes read and write to
a global working memory that is selectively attended to; consciousness corresponds
to a “spotlight” of attention on this global workspace. The biological aspect associates various elements of brain physiology (e.g., cortical areas, gamma synchrony)
in the realization of this architecture.
Biological theories have impact on the possibility of machine consciousness to
the extent that their biological content is essential rather than incidental. Since
nothing in a computer resembles neuronal microtubules, machine consciousness is
ruled out by the biological aspect of Orch-OR. But that may not eliminate artificial
consciousness altogether since we might devise some alternative structure to collapse
the wave function, though it would not emerge from conventional computation.
Dually, if its cognitive architecture is the key element of GWT, then reproducing
this architecture in computation could enable machine consciousness, but this might
not be so if some aspects of the biological implementation are critical.
Functionalist theories deny any special role for biology and assert that consciousness arises from what the brain does. Unsurprisingly (since nothing was known
about the biology of the brain until recently) functionalist theories of consciousness are among the oldest, dating back to William of Ockham or even Saint Augustine [Brower-Toland, 2012]. The prototypical functionalist theories are various
12
This argument is developed by Penrose [Penrose, 1994] using a contentious interpretation of
Gödel’s first incompleteness theorem; Feferman provides a rebuttal [Feferman, 1995] in a journal
issue devoted to critical commentaries on Penrose’ argument.
13
Several of the founders of quantum mechanics explicitly discussed its possible relationship with
consciousness [Marin, 2009].
14
forms of Higher Order Thought (HOT) [Gennaro, 2004, Rosenthal, 2004], that is,
thoughts about thoughts: “consciousness is the perception of what passes in a man’s
own mind” (John Locke).
In the previous section, we noted that humans have self awareness; related to
this is introspection, which is the mind observing its own (conscious) operation and
thus an instance of higher-order thought. In fact, this seems to be a second level
of higher-order thought: the conscious mind is thinking about its own conscious
operation. A first level of higher-order thought would seem to be basic awareness:
a conscious thought about something presented by the unconscious. For example, I
am conscious of the coffee cup on my desk; the sight of the coffee cup, along with
many other items on my desk, is presented by my unconscious visual system, and
the coffee cup is the one of which I am conscious: so I have a (first level) higherorder thought directed at the (base level) mental representation of the cup. Some
classical HOT theories posit that a thought becomes conscious when it is the target
of a higher-order thought. This leads to an objection that thinking of a rock surely
does not make the rock conscious and there is a lot of theoretical wriggling to deal
with this [Gennaro, 2012, Section 4.3]. As computer scientists, we would assume
it is the higher-order thought that is conscious, not the base-level target, so this
“problem of the rock” seems specious.
Computer science provides some other ideas and terminology that can be useful
here. Much of the function of the brain is to provide a control system for the body:
given a goal and sense input, calculate actions to accomplish the goal. The goal may
be to catch a fly ball, cross the street, win an election, or survive until your offspring
are independent. Computer control systems do similar (though generally simpler)
things and have a certain structure. In particular, they are always based on a model
of the controlled “plant” and its environment [Conant and Ashby, 1970].14 For
elementary control systems, such as the cruise control in a car (or humans catching
fly balls), the model is used in design (or implicitly “discovered” during evolution)
of the system but is not explicitly represented in the implementation.
More complex control systems do have an explicit model represented in the
deployed system and may (in adaptive systems) have ways to adjust its parameters
during operation. Even more ambitious systems may learn and adapt the model as
they go along. Reflective systems are those that construct an explicit model of their
own operation and use this to adjust future behavior. When computer scientists are
asked what consciousness might be, they are very likely to answer that it must be
something like reflection, and most efforts to construct machine consciousness are
based on reflection.
14
Conant and Ashby explicitly recognized this must apply to the brain, which seems remarkably
prescient for 1970: “The theorem has the interesting corollary that the living brain, so far as it is
to be successful and efficient as a regulator for survival, must proceed, in learning, by the formation
of a model (or models) of its environment.”
15
Predictive Processing (PP) [Clark, 2013] is a recent, and increasingly popular,
theory of brain operation that posits that every level and every subfunction of the
brain has a model and uses (an approximation to) Bayesian estimation to minimize
prediction error, as was described for sensory interpretation in the previous section.
In total, the brain learns and maintains models for various aspects of the world
and uses sense input and experience to make these as accurate as possible. PP sees
consciousness less as a “thing” and more as the continuous process of building and
updating models. (“Free Energy” [Friston, 2010] is a more all-encompassing variant
that includes actions: the brain “predicts” that the hand, say, is in a certain place
and to minimize prediction error the hand actually moves there.)
Predictive processing could enable successful individual behavior without a separate mechanism for consciousness. But, as noted earlier, a distinguishing feature
of humans is the creation of shared intentionality. If you and I are to cooperate
on a common goal, then we need to share similar models for some aspects of the
world—and one interpretation of consciousness is that its function is to construct
higher-order thoughts that are succinct descriptions or explanations of unconscious
models suitable for communication to others.
This rapid and superficial overview of theories of consciousness reveals a disappointing truth: there is a vast number of theories and for the most part they
are mutually incompatible. It follows that most of them must be wrong, although
few are presented with the specificity to support falsifiable experiments.15,16 Furthermore, few (if any) theories suggest what consciousness might be for, or what it
does. Manzotti and Chella identify a yet more basic criticism, which they call “the
intermediate level fallacy” [Manzotti and Chella, 2018]: theories of consciousness
identify various functional or biological mechanisms (the intermediate level) that
15
Falsifiability is the touchstone that separates scientific theories from speculation. This criterion
is due to Popper [Popper, 2014] and is generally endorsed by working scientists (as a declaration
of what science is, not necessarily how it is done). However, it is hotly debated, even rejected,
by philosophers of science: “if Popper is on the right track, then the majority of professional
philosophers the world over have wasted or are wasting their intellectual careers” [Bartley, 1976].
Most theories of consciousness do not propose falsifiable experiments and are therefore, in the words
of Wolfgang Pauli, “not even wrong.”
16
Update: Yaron and colleagues recently developed a database that culls results from
379 papers reporting 418 experiments [Yaron et al., 2021a]; they conclude that “the
field generally suffers from a strong confirmatory-bias, and that the majority of studies post-hoc interpret their findings concerning the theories, rather than designed a-priori
to test their critical predictions” [Yaron et al., 2021b].
New activities, however, do report indications of possible falsifications:
for Orch-OR https://physicsworld.com/a/
quantum-theory-of-consciousness-put-in-doubt-by-underground-experiment/, and GWT
https://bigthink.com/neuropsych/revision-leading-theory-consciousness/,
respectively.
Furthermore the Templeton Foundation is funding an effort to “test competing predictions” by GWT and IIT https://www.templetonworldcharity.org/projects-database/
accelerating-research-consciousness-adversarial-collaboration-test-contradictory.
16
are asserted to produce consciousness, but they fail to explain how the mechanism
produces the experience.
These criticisms do not imply that theories of consciousness are without merit
(though it is disappointing that few of them shed any light on the counterintuitive
aspects of consciousness, such as those described in Section 2). The field is so young
and opportunities for observation and experiment so few that falsifiability may be a
premature expectation. The theories can be seen as pointers to directions that may
be worthy of further exploration. In the following section, we describe explorations
based on computer simulations.
5
Attempts to Create Machine Consciousness
We have seen that there is a large number of theories of consciousness and rather
little evidence to help choose among them. One approach is to construct simulations;
at the very least, this forces elaboration of sufficient detail that we can construct
explicit models of the mechanisms of the chosen theory and explore their properties.
Early experiments were conducted by Tihamér Nemes in the 1960s [Nemes,
1970], but intelligence and consciousness were not sharply distinguished in those
days, nor were cybernetics and (what became) AI. In 1989, Leonard Angel published a book with the provocative title “How to Build a Conscious Machine” [Angel,
1989] in which he proposed a kind of agent system. A modern view of machine or
robot consciousness is attributed to Igor Aleksander in 1992 [Aleksander, 1992], who
postulated that such a robot would need representations for depiction, imagination,
attention, planning, and emotion and that consciousness could emerge from their
interaction.
The first large project to explore machine consciousness was cronus [Marques
et al., 2007]. This was predicated on the idea that reflection—internal models of
the system’s own operation—play an important part in consciousness. Physically,
cronus was an anthropomimetic robot (i.e., one closely based on the human musculoskeletal system) with a soft-realtime physics-based simulation of the robot in
its environment. The internal simulation allowed the robot to project the effects of
possible future actions, which the authors describe as “functional imagination” [Marques et al., 2008]. Later studies used a yet more complex robot (“eccerobot”),
while earlier ones used a very simple, nonanthropomorphic device [Holland and
Goodman, 2003]. It is not clear to us that complex robots added a great deal to
these experiments, and they certainly increased the engineering challenges.
Experiments by Chella and colleagues explored robots’ interaction with others;
this requires a theory of mind, and a sense of self [Chella and Manzotti, 2009,Chella
et al., 2008]. Gamez describes other projects performed around the same time
[Gamez, 2008]. All these experiments and those mentioned above employ some
17
form of reflection or HOT as their underlying theory of consciousness. Others have
built systems based on GWT or IIT; Reggia provides a survey [Reggia, 2013].
Those who subscribe to biologicist theories of consciousness might argue that
functionalist approaches are doomed to failure and that what is needed are simulations of the biology of the brain. “Systems biology” supports this by building
computational (“in silico”) models of biological processes, including neurons. Typically, these are Matlab-type models with differential equations for the flow of ions
and various other elements in the cell. Such models often require experimentallyderived parameters such as rate constants and are limited to systems involving only
a few cells. Symbolic Systems Biology abstracts from much of this detail and uses
state machines or rewriting.
It is clear that simulations of the whole, or even significant parts of, the human brain are computationally infeasible at the level of detail pursued in systems
biology.17 Furthermore, such simulations would require detailed information on the
neural architecture of the brain that is currently lacking, although research to develop this information is being pursued by the Human Connectome Project.18 It
is possible that abstractions of biological functions of the brain can be developed
that will permit larger scale simulations ([Grossberg, 2017] may be a step in this
direction).
Research on machine consciousness seems not to have a central forum for presentation of results and discussion of ideas: the International Journal of Machine
Consciousness began publication in 2009 but ceased in 2014. Perhaps as a result,
recent work seems to retread familiar ground. For example, a paper by Dehaene,
Lau and Kouider from 2017 [Dehaene et al., 2017] presents the authors’ theory
of consciousness (global availability as in GWT, plus reflection built on PP), then
asserts that a machine with these capabilities “would behave as though it were conscious” [Dehaene et al., 2017]. In a response, Carter et al. [Carter et al., 2018] observe that Dehaene and colleagues ask and answer the wrong questions—essentially,
Dehaene et al. are aiming for intentional consciousness, whereas Carter et al. think
that phenomenal consciousness is what matters: for machines to be conscious, “we
must ask whether they have subjective experiences: do machines consciously perceive and sense colors, sounds, and smells?” They posit “a more pertinent question
for the field might be: what would constitute successful demonstration of artificial
consciousness?”
These are old questions (e.g., [Boltuc, 2009]) and it is disappointing that the
dialog does not seem to be moving forward. A more basic question, given that
researchers do not yet claim to have demonstrated machine consciousness, asks
17
The state of the art is a few neurons; one example considers the central pattern generator (for
rhythmic gut movements during feeding) of Aplysia (a marine mollusk), which is comprised of 10
neurons [Tiwari and Talcott, 2008].
18
This could be disrupted if glial cells and their separate connectivity turn out to be significant.
18
what should we expect to learn from research on machine consciousness, whether
based on functionalist or biologicist principles? As with AI, researchers distinguish
strong and weak forms of machine consciousness (sometimes framed as duplication
vs. simulation). Strong machine consciousness would be conscious, whereas the weak
form is a philosophical zombie: it exhibits behaviors and attributes associated with
consciousness without actually possessing it. We believe it is fair to say that existing
attempts to create machine consciousness have not expected to achieve the strong
form. Rather, they simulate selected mechanisms from a theory of consciousness
and observe resultant behaviors and properties. What these studies of weak machine
consciousness can achieve is to frame and explore precise statements of the form:
“in a system of type W, some components X will manifest characteristics of type Y
under some circumstances Z” (Owen Holland).
There is no doubt that experiments of this kind can help sharpen and discriminate among various theories of consciousness, but most observers are skeptical that
the weak form of machine consciousness leads to the strong. By analogy, we can
build extremely accurate simulations of the cosmos and explore the missing mass
(due to dark matter and dark energy), yet the simulations do not have mass; so a
simulation of consciousness will not have consciousness. On the other hand, the
weak and strong distinction seems really to matter only for phenomenal consciousness and its cohorts: we likely will regard an entity that has feelings differently than
one that merely simulates them. But weak intentional consciousness is operationally
equivalent to the strong: if it enables some new cognitive capabilities then the underlying technology can use these by running the weak simulation as a subroutine.
This asymmetry between phenomenal and intentional consciousness is related to
the “hard problem” of consciousness [Chalmers, 1995] and may be a crisper way to
formulate it than the traditional description.
The topic that motivated this study is concern that we may (inadvertently)
develop technology with strong machine consciousness. We explore that possibility
in the following section.
6
Possible Emergence of Technological Consciousness
In this section we explore the possibility that consciousness might emerge from a
technological substrate rather as natural consciousness emerges from the brain, but
first we should examine this notion of “emergence” in a little more detail.
Philosophers ascribe different interpretations to this notion, and the interpretations have changed over time.19 The one that is most germane to our discussion
is generally called weak emergence [Bedau, 1997]. In all discussion of emergence,
there are “upper level” macro phenomena that arise out of “lower level” micro phe19
There was a whole school of “British Emergentists” in the late 19th century.
19
nomena. What characterizes emergence as opposed to mere assembly is that the
macro phenomena are of a different kind than the micro phenomena and are described with a different vocabulary than the micro: that is, they are “ontologically
novel” and, if understood in sufficient detail, are characterized by different models
and mathematics. A classic example is pressure and temperature in a gas (macro),
which emerge from the motion of its molecules (micro). Macro level phenomena
that are not ontologically novel are called resultant. Consciousness arises from the
brain yet is ontologically distinct, so it is legitimate to speak of it emerging from
the brain.
Weak emergence is characterized by the requirement or expectation that macro
phenomena can be explained in terms of micro. We may be able to do this precisely
(by “bridge laws”) as in the case of gas properties, or we may lack the knowledge to
do so, as in the case of consciousness emerging from the brain, but we are confident
such an explanation exists. This contrasts with strong emergence, which asserts
that macro phenomena cannot be (completely) explained in terms of micro. Weak
emergence is compatible with materialism, while strong emergence is tantamount to
property dualism.
There are further concepts that can be added to a theory of emergence, such
as supervenience (if two macro states differ, they must arise from different micro
states—i.e., there is a mathematical function from micro to macro), and some of
them, such as downward causation (where a change in macro states causes a change
in micro states, contrary to the notion that macro states arise out of micro), are
philosophically challenging [Campbell and Bickhard, 2011], but the basic ideas and
terminology are sufficient for our purposes.
In this section we are concerned with the possibility that consciousness might
emerge “accidentally” from the ever more complex technology that we construct,
especially as some of it is explicitly inspired by human mental capabilities and by
approximations to some of its mechanisms, such as Artificial General Intelligence,
deep learning, and so on.
Although the small-scale experiments in machine consciousness outlined in the
previous section seem not to have produced (even weak) consciousness, the sheer
quantity of computational power that is now, or soon will be, available, might raise
concern. In Section 3 we sketched the amazing scale and complexity of the human
brain and noted that it has about 1014 synapses, which we can use as a proxy for
its “capacity.” It is difficult to say how many transistors or computational gates or
memory bits are equivalent to a synapse (temporarily adopting a computationalist
theory of consciousness), but we can observe that the available number of these technological elements has increased exponentially—roughly ten-fold every four years—
since 1966, so that by 2026 it will have increased by 1015 over that period, and this
factor dominates any starting assumption. It seems plausible, therefore, that technology will have raw computing capacity roughly equivalent to the human brain by
20
about 2026 (if not then, just wait another four years).20 Calculations such as this
are the basis for speculation on “The Singularity” [Kurzweil, 2010]; the important
point is that under almost any assumptions, exponential growth guarantees technological computational capability will match that of a human brain within a decade
or so.
On the other hand, none of the theories of consciousness surveyed in Section
4 gives reason to suppose that scale makes consciousness more likely: they each
identify consciousness with some mechanism or structure that is either present or
absent. (IIT is sensitive to scaling but excludes machine consciousness on other
grounds.) We have to conclude, therefore, that current experiments and existing
theories of consciousness do not provide much guidance on the possible emergence
of strong consciousness in large scale technological systems.
The lack of commonality among the theories means that even if we ignore their
details and look for broad indications, they still provide few clues where to look
for possible emergence of machine consciousness. If forced to nominate one idea
that informs all or most of the various theories, we would choose “integration.”
This is explicit in IIT, implicit in GWT and other biologicist theories, and explicit
again in some HOT theories—although it is not clear they agree on what it is that is
integrated. The archaeologist Steven Mithen attributes the “explosion” of creativity
seen in the human record about 50,000 years ago (cave paintings etc.) to integration
of formerly separate cognitive domains [Mithen, 1996]. This idea is compatible
with the metaphor theory: we became able to think effectively about many new
topics once we acquired the ability to map them to (previously separate) built-in
capabilities.
If integration of separate cognitive domains is a pointer to human consciousness,
might something similar occur in large scale technological systems? At present, our
technical systems tend each to focus on a narrow range of functions, defined by
their task and purpose. A self-driving car just drives: it does not concern itself
with raising offspring, finding a mate, or maintaining status; nor does it vacuum the
floor, wash clothes, or guide airplanes. It is possible that as the Internet of Things
develops, the self-driving car will be able to integrate, on some level, with robot
20
Update: Large language models (essentially neural nets trained to predict the next word in
a stream of text) have increased in scale at an astonishing rate. In 2018, the first Generative PreTrained Transformer (GPT-1) from OpenAI had 117 million parameters, GPT-2 a year later had
1.5 billion, and GPT-3 in 2021 has 175 billion. LaMDA, the model that Blake Lemoine declared
“sentient” has 137 billion parameters, and Google and others are said to be working on models
with more than a trillion parameters, which is believed to approach the scale of the human brain.
Some of the largest supercomputers in the world are used for training these and other neural
nets (e.g., for self-driving cars). The performance of these systems appears to have grown with
their scale and most people are astonished at the quality of the text they can generate. This
admiration is not universal, however, especially among those who “know how the trick is done”
and who dismiss these systems as “stochastic parrots” https://medium.com/@emilymenonbender/
on-nyt-magazine-on-ai-resist-the-urge-to-be-impressed-3d92fd9a0edd.
21
vacuum cleaners and washing machines, and with the air traffic control system. In
a foreseeable future, it may integrate with babysitting “carebots” and dating sites,
and may also have a reputation index that it is programmed to defend. The total
system will then have many different skills and capabilities and their integration
may yield something new. We cannot predict whether this might include any form
of consciousness21 but it seems possible that it could lead to coordinated behavior
that resembles that associated with consciousness.22
In May 2001, The Swarz Foundation sponsored a workshop on the topic “Can
a Machine be Conscious?” at Cold Spring Harbor.23 The attendees concluded “we
know of no fundamental law or principle operating in this universe that forbids
the existence of subjective feelings in artifacts designed or evolved by humans.”
We would agree, though generalized from “subjective feelings” (i.e., phenomenal
consciousness) to include intentional consciousness as well. But just as we know
no reason that excludes technological consciousness, the discussion above suggests
we also have no reason to think that its emergence, at least in a strong form, is
imminent or likely.
Since we cannot know whether a technological consciousness might emerge, nor
what form it might take, we consider a range of possibilities. Gamez [Gamez, 2008]
identified four different topics within research on machine consciousness. We adapt
his topics to our discussion.
TC1: Technology with external behavior associated with consciousness
This is essentially the goal of Strong AI, or AGI. It presumes that consciousness is
inessential to the construction of (some or all) human-level behavior: consciousness
may be the way humans achieve certain capabilities, but technology might achieve
them by other means.
This, or an approximation, seems a plausible possibility, and raises well-known
concerns about the hazards and safety of advanced AI [Everitt et al., 2018]. The
“integration” scenario outlined above adds another twist that could raise concern
further.
TC2: Technology with cognitive characteristics associated with consciousness
Exactly which cognitive characteristics are of greatest interest is a topic for debate,
but candidates include the ability to construct shared intentionality (i.e., engage in
teamwork), or to have original ideas. Much of the concern about AGI centers on
21
Discussion around Searle’s “Chinese Room” might be relevant here [Preston and Bishop, 2002].
The skeptic might think it is more likely to lead to “emergent misbehavior” [Mogul, 2006].
23
http://www.theswartzfoundation.org/banbury_e.asp
22
22
the idea that it could be capable of self-improvement, and would thereby outstrip
human capabilities at an increasing pace.
Again, it seems plausible that these capabilities can be constructed by technological means, without consciousness. Recent work on automation of scientific
discovery [Schmidt and Lipson, 2009] suggests that brute search over internal models can accomplish some of what was thought to require imagination, insight, or
originality.
TC3: Technology with an architecture that is claimed to be a cause or
correlate of human consciousness
Whereas technology constructed for other purposes, no matter how large or complex,
might not achieve consciousness, it is possible that technology that reproduces or
simulates salient architectural or biological aspects of the human brain might do so.
This possibility does not seem imminent, in that we really have no idea what
the salient aspects of the human brain might be; indeed the purpose of much of
the research on machine consciousness discussed in Section 5 is to use computer
models and simulation to help refine and evaluate (and possibly refute) proposed
theories of consciousness. Rather than harbingers of technological consciousness,
this research could be seen to provide reassurance that some architectures that
might raise concern, such as reflective systems with sophisticated self models, have
not exhibited consciousness.
Furthermore, as noted in Section 5, while it is possible that TC3 systems might
eventually simulate consciousness, this does not imply that they will be conscious—
that is the concern of TC4.
TC4: Technology that truly is conscious
The topic of concern here is strong machine consciousness. This is relevant only for
phenomenal consciousness because, as explained in the previous section, weak and
strong are equivalent for intentional consciousness—and furthermore, as noted for
TC1 and TC2, it is plausible that advanced AI can be achieved without any kind
of technological consciousness.
Most observers believe that strongly phenomenally conscious technology is possible. (There are dissenters, most of whom deny computationalism [Bringsjord and
Zenzen, 1997], or endorse Ross’ claim for the immateriality of thought [Ross, 1992].)
However, the experiments in machine consciousness outlined in the previous section
do not suggest that it is imminent. But on the other hand, technological consciousness might be nothing like human consciousness and could emerge from entirely
different mechanisms. It seems that at present we must accept that we just do not
know enough to evaluate this concern.
23
We have considered a range of capabilities that might emerge; we now examine
how we might detect and measure it.
7
Detection and Measurement of Consciousness
Detection of consciousness is difficult because a) we do not know what consciousness
does nor what it is for, and b) we do not know how it comes about. Thus, we do not
know what functions or behaviors or capabilities to look for, nor what mechanisms
or precursor functions. Hence, most proposed tests for consciousness amount to
little more than attempts to observe human-like capabilities that are thought to
require or to be associated with consciousness.24 Standard examples include various
embellishments of the Turing Test, such as the Total Turing Test (TTT) [French,
2000] and variants specialized toward phenomenal consciousness (e.g., wine tasting).
Many of them assume the ability to converse in natural language, or use that as a
diagnostic.
Although intended to be applied to machines, tests that seek adult humanlike capabilities will automatically conclude that animals and human infants lack
consciousness. Yet many believe that their consciousness is at least a possibility.
We refer to these tests as anthropocentric and consider them unlikely to detect a
machine consciousness that emerges unexpectedly and may have little resemblance
to our own.
On the other hand, given that adult humans are the only subjects that we know
to possess consciousness, it is difficult to propose neutral tests. One illustrative
example is whether a subject that has learned a skill will teach it to others. A
chimpanzee that has learned to use a stick as a tool to fish for ants does not attempt to teach others: it seems unconscious (unaware) that it has this skill. Since
chimpanzees are social animals, this seems like a legitimate test. However, it would
not seem legitimate for solitary creatures, such as octopuses. And what would it
reveal about technology?
Raoult and Yampolskiy [Raoult and Yampolskiy, 2015] perform a thorough literature survey and identify 21 different tests aimed at machine consciousness. Most
are anthropocentric; a few, such as variants on the Mirror Test (does the subject recognize itself in a mirror?) are debatable, while others, such as attempts to measure
Φ, seem truly neutral.
There is obvious tension between tests that are too hard and too easy. Excessively anthropocentric tests will fail to detect alternative forms of consciousness, so
may be considered too hard. On the other hand, the Mirror Test seems too easy
24
Update: Large language models such as GPT-3 and LaMDA already come very close to passing
the “Turing Test” where an interlocutor is unable to distinguish a dialog with a machine from one
with a human. This suggests that apparent facility with language may not be an effective test for
consciousness.
24
as the capability is readily programmed in computers [Bringsjord et al., 2015]. Another test that seems too easy, despite its apparent sophistication, is Insight Learning
(the ability to solve problems by making new relations between previously acquired
knowledge rather than through trial and error): this skill is easily programmed
(search over internal simulations) with no requirement for consciousness.
A related objection to many of these tests is that they will not distinguish strong
machine consciousness from weak: that is, they will not distinguish a technology that
truly is conscious from a philosophical zombie that merely simulates it. One, rather
controversial, idea that might do so is to observe whether the system shows interest
in exploring or manipulating its own “consciousness”: this rests on the observation
that all human societies investigate altered states of consciousness through chemical
and spiritual means.
If consciousness is hard to detect, it is even harder to measure. Raoult and
Yampolskiy identify four tests that produce numerical scores; one of these is Φ,
the others are strongly anthropocentric. Although Φ may measure some aspects of
consciousness, it does not seem specifically sensitive to phenomenal consciousness,
and it discounts the claimed feed-forward nature of conventional computation [Koch
and Tononi, 2017].
We conclude there are no good tests for detecting or measuring phenomenal
consciousness, especially incarnations different to our own. Detection and measurement of intentional consciousness may be unnecessary: what we care about are the
capabilities and behaviors that it enables, and these will be observed directly.
8
Ethics for Control of Conscious Technology
A conscious technology might have goals and priorities that conflict with those of
human society. So it seems prudent that technology on a path that could lead to
consciousness should have overarching constraints built in from the very beginning to
forestall this danger. We cannot know the particular circumstances that may arise,
so the constraints need to be general and overarching, rather like Asimov’s “Three
Laws of Robotics.”25 Asimov’s laws were a plot device and his stories often concern
unintended consequences of these plausible-sounding laws, thereby indicating that
construction of suitable constraints may be challenging.
One idea is that the constraints should be based on human ethics [Yu et al.,
2018]; a dissenting opinion, advocating explicit reasoning about safety is provided
by Yampolskiy [Yampolskiy, 2013]. Of course, ethics have been studied and de25
1: A robot may not injure a human being or, through inaction, allow a human being to come
to harm; 2: A robot must obey orders given to it by human beings except where such orders would
conflict with the First Law; 3: A robot must protect its own existence, as long as such protection
does not conflict with the First or Second Law [Asimov, 1950, The Three Laws appear in the story
“Runaround”].
25
bated for millennia, without achieving consensus. Nonetheless, some broad general
principles are known. Ethics are the basic rules by which societies maintain order and cohesion; however, some very successful societies have elements that others
find repugnant: for example, Ancient Greece used slaves (Aristotle wrote of “natural
slaves”) and Ancient Rome had execution as a form of public entertainment. Hence,
it seems that the moral foundations of ethics are not universal. Nonetheless, modern
“experimental ethics” finds that human moral sense is built on five basic principles
and those do seem universal: care, fairness, loyalty/ingroup, authority/respect, and
sanctity/purity [Haidt, 2013]. What is not universal is preference and weighting
among the principles, which behave rather like the five basic senses of taste: different societies and individuals prefer some, and some combinations, to others. For
example, western liberals stress fairness while conservatives favor authority.
Even if an agreed weighting of the basic principles were built in to advanced
technology, it may not be obvious how to apply it. For example, a self driving car
might be confronted by a vehicle crossing against the lights and the choices are to
crash into it, likely killing or injuring the occupants of both vehicles, or to swerve
onto the sidewalk, likely killing pedestrians. The fairness principle might argue that
all lives are equal and utilitarianism might then suggest a decision that minimizes
the probable injuries. On the other hand, the care principle might argue that the
system has a special responsibility for its own passengers and should seek a solution
that minimizes their harm.
“Trolley problems” are thought experiments used to probe human judgments on
these ethical dilemmas. The classic problem posits a runaway street car or trolley
that is heading toward a group of five people. You are standing by a switch or point
and can throw this to redirect the trolley to a different track where it will hit just one
person. Most subjects say it is permissible, indeed preferable, to throw the switch,
even though it will injure an innocent who would otherwise be unharmed. However,
a variant on the original trolley problem has you and another person standing by
the track and suggests that you bring the trolley to a halt, and save the five, by
pushing the other person onto the track in front of the trolley. Most subjects will
say this is ethically unacceptable, even though it is equivalent to the first case by
utilitarian accounting. These examples illustrate the “Doctrine of Double Effect”
(DDE), which holds that it is ethically acceptable to cause harm as an unintended
(even if predictable) side effect of a (larger) good: the first case satisfies the doctrine,
but the second violates the “unintended” condition.
Experimental systems have been developed that can represent and reason about
ethical principles such as DDE and these have been applied to trolley problems,
including some that involve self-harm (e.g., throwing yourself in front of the trolley)
and thereby violate the “unintended” aspect of DDE [Bringsjord et al., 2006,Govindarajulu and Bringsjord, 2017]. It is claimed that fairly sophisticated logical treatments (e.g., intensional logics, counterfactuals, deontic modalities) are needed to
26
represent ethical scenarios, and these might be additional to what is needed for
the primary functions of the system (hence, must be introduced explicitly). Other
recent work formalizes Kant’s categorical imperative (humans must be treated as
ends, not as means), which requires a treatment of causality [Lindner and Bentzen,
2018], while another speculates on application of ethics to autonomous cars [Kulicki
et al., 2018].
There is more to ethical systems than application of ethical rules: the underlying
model of the world should have a certain neutrality that may be hard to ensure. For
example, a system that interacts with humans may need models of race and gender. Whether these are programmed or learned, they may unwittingly incorporate
bias. And in order to interact effectively, a theory of mind may need explicitly to
construct and consider biased models. So how can we ensure that possibly biased
models do not affect outcomes? One possibility is that certain judgments should
be invariant under different assumptions about self and others: that is, the system
should explicitly repeat its calculations under different assumptions as a computational approximation to Rawls’ “Veil of Ignorance” [Rawls, 1971].
So far (and in the workshops), we considered only harm to individuals. A truly
rampant technological system could pose many other hazards: it could undermine
our institutions, or our trust in these. Similarly, we have mentioned only logical
or rule-based representations for ethics, whereas game theory provides another perspective.
In addition to ethics, technological systems should also follow the laws of their
community. There is a long history of work on formalizing and reasoning about legal
systems [von der Lieth Gardner, 1987]. There will surely be circumstances where
the law conflicts with some interpretation of ethics, or with the mission objective, so
a system constrained by several such “overarching” frameworks must have a means
of resolving conflicts. Individually and in total, these are challenging objectives.
Humans, endowed with an understanding of local ethics and of the law, sometimes make bad judgments, or resolve conflicts among competing ethical principles,
in ways that society finds unsatisfactory. Various forms of censure and punishment
provide means to correct such errant behavior and it seems that technological systems should also be subject to adjustment and tuning in similar ways. An important
question then is what is the “accounting method” that guides such adjustments: is
it just some internal measure, or is there some societal score-keeping that has wider
significance? In a work commissioned by the US government during WWII, the
anthropologist Ruth Benedict proposed a distinction between “guilt cultures” (e.g.,
the USA) and “shame cultures” (e.g., Japan) [Benedict, 1946]. This distinction is
widely criticized today, but modern “reputation systems,” as employed for EBay
sellers, Uber drivers, and so on (China’s Social Credit system [Kobie, 2019] extends
this to the whole society), can be seen as mechanizing some aspects of shame culture and could provide a framework for societal control of technological systems:
27
the idea being that the technological system should value its reputation and adjust
its behavior to maximize this.
Being held responsible for our actions and subject to punishment and reward
seems to require that we are free to act thus or otherwise. We generally assume that
humans have free will, but what about technological systems? And if they do not
have free will, can they be subject to the constraints of ethics?
Human free will is an immensely difficult subject (the most contentious problem
in all of metaphysics, according to Hume). It is next to impossible to reconcile
the commonsense (“libertarian” or “contra-causal”) notion of free will—that our
decisions are uncaused causes—with materialism: in a material universe, what happens next is determined (possibly only probabilistically due to quantum effects)26
by what happened before, so how can that determinism be suspended while I make
a decision? I am part of the material world, so my decision is determined by my
current state (or is subject to quantum randomness) and it only “feels like” I made
a free choice: “all theory is against the freedom of the will; all experience for it” (Dr.
Johnson). Consequently, most philosophers accept only a weaker form of free will
(“compatibilism”) in which our conscious decisions do cause our actions, but those
decisions are not themselves uncaused causes. In other words, nothing prevents our
deciding on one thing or the other, but the actual choice is (probabilistically) determined: “we can do what we will, but we cannot will what we will” (Schopenhauer).
Nonetheless, in everyday life we still attribute human acts to free will and we
praise or punish accordingly. Philosophers accept this as a useful fiction, for experiments show that subjects primed to see free will as illusory are more likely to
misbehave [Cave, 2016], or to become fatalistic. Now, if it is hard to impute free
will to humans, it is even harder to impute it to technology (for what is it but a pile
of algorithms?). However, as with humans, it is a useful fiction to treat conscious
technology (or any complex system endowed with learning) as if it had free will and
to hold it responsible for its actions. This is because its behavior adapts over time
as a result of its “life experiences” and rewards and punishment can be a significant
input to those adaptations.
All our discussion until now has focused on a rather basic concern: ensuring
that advanced, possibly conscious, technological systems do us no harm. But some
such systems might be intended to do positive good: robots to provide assistance
and companionship to the elderly, for example. Ethical frameworks to prevent
harm might therefore need to be generalized so that technology can enable us to
flourish rather than merely survive. And if we are to flourish from the relationship,
shouldn’t a conscious technology share in the benefit? We consider this question in
26
Contrary to some naı̈ve claims, quantum randomness or other sources of nondeterminism
[Greenblatt, 2011] do not open the door to free will: a random or nondeterministic choice is no
more free than a deterministic one.
28
the following section, where we examine what ethical considerations we might owe
to a conscious technology.
9
Ethical Responsibility Toward Conscious Technology
We noted in the introduction that a conscious technology might deserve some ethical
consideration and be accorded certain rights. Here, we explore that notion in a little
more detail.
There are many aspects to consciousness; we have focused on phenomenal and
intentional consciousness, but there are other capacities that are either aspects of
consciousness, or closely related to it, such as sentience (the capacity for suffering
and joy), attention, self-awareness, personal identity (a narrative sense of self persisting over time), and autonomy. Some of these are philosophically challenging: for
example, autonomy seems related to free will and we have already seen that this
is denied (in its strong form) by most philosophers; personal identity is similarly
suspect.
Of the less contentious aspects, it seems that sentience (which can be seen as an
element of phenomenal consciousness) is the one that most strongly elicits ethical
consideration; its attribution to certain animals seems to be the reason we accord
them moral status. But there has to be more to sentience than just the avoidance
of negative stimuli and pursuit of positive ones: any control system does this, as
do bacteria. The morally salient aspect of sentience seems to be that the subject
cares about the experience rather than merely avoids or seeks it, but it is not at
all clear how we can detect that attitude, never mind judge its strength: certainly
its attribution to some animals but not others seems driven more by empathy and
sentiment than by science. As with conscious technology we have to ask how we can
distinguish between “genuine” sentience and the simulated equivalent (i.e., does the
technology have weak or strong phenomenal consciousness/sentience?).
An objection to this privileging of sentience is that it is anthropomorphic “meat
chauvinism”: we are projecting considerations onto technology that derive from our
biology. Perhaps conscious technology could have morally salient aspects distinct
from sentience: the basic elements of its consciousness could be different than ours.
In response to these objections and difficulties, we might consider other ethical systems than the utilitarianism implicitly used so far. Alternative possibilities
are Kantian Ethics, where “persons” are accorded dignity and concern as “ends in
themselves,” and Virtue Ethics (which derive from Aristotle, Confucius, and others
of the “Axial Age”), where moral good is associated with a flourishing life [Vallor,
2016]. Both of these would tend to accord ethical consideration and moral protections to conscious technology to the extent that it reciprocally demonstrates ethical
understanding and appropriate behavior of its own, thereby sidestepping the need
to detect sentience.
29
In the previous section, we considered instilling technology with ethical principles
but the focus there was on safety and control, not the larger landscape of “digital
phronesis” [Sullins, 2016] that might be needed for Virtue Ethics. Phronesis is a
term from Aristotle that refers to ethical wisdom. Several research groups have
developed experimental systems for investigating artificial moral agents, such as
LIDA (Learning Intelligent Distribution Agent), which is based on the GWT model
of consciousness [Wallach et al., 2011], the N-Reasons platform, which is used to
study ethical reasoning in humans [Danielson, 2010], and ethical protocols [Turilli,
2007].
In addition to thinking about ethical considerations owed to and expected from
conscious technology, we should also think about the novel kinds of harm they may
be vulnerable to, and corresponding protections they should be afforded. Obvious
examples are “rights” to electrical power and not to be switched off. However, these
may be anthropomorphisms: we liken them to death, which for us is final, whereas
a machine can reboot to its prior state so these are more like sleep. More significant
hazards may be classical “hacker” attacks on a system’s sources of information,
which would resemble assault. For example, it may be feasible to deceive a selfaware system so that it confuses self and non-self, or to exploit a weak system to
nefarious ends.27 “Carebots” are expected to display and elicit human-like emotions
and attachment and may be vulnerable to (or may inflict) emotional cruelty (see for
example, the “still face experiment” with mother and child28 for how rapidly loss
of agency develops). Such systems need capacities for moral discourse and moral
learning, but may also have a right to be protected from hacker assault.
10
Conclusion and Next Steps
The possible emergence of technological consciousness is an important topic: were it
to happen, it could have significant impact on our future, our safety, our institutions,
and the nature of our relationship with machines.
It is clear that our technology will have computational power approximately
equivalent to a human brain within a decade or so but, apart from that observation,
assessment of the feasibility of technological consciousness seems to depend more on
our knowledge and beliefs about consciousness than on technological questions.
Currently, we have no good theory of (human) consciousness: we do not know
how it works, what it does, nor how or why it evolved. This leaves space for much
27
For example, Microsoft’s “Tay” was a Twitter bot that the company described as an experiment
in “conversational understanding.” The more you chat with Tay, said Microsoft, the smarter it gets,
learning to engage people through “casual and playful conversation.” Within less than a day of its
release, it had been trained by a cadre of bad actors to behave as a racist mouthpiece and had to
be shut down.
28
https://www.youtube.com/watch?v=apzXGEbZht0
30
speculation and opinion. Many believe that phenomenal consciousness (the personal
sense of experience) is the important topic—it is the essence of what it means to be
human29 —and the possibility that it could arise in a machine is of profound concern.
Yet we know so little about phenomenal consciousness that we cannot tell if animals
have it. Some believe it is part of the basic mechanism of advanced perception
and arose 500 million years ago (in the Cambrian explosion) and is possessed by
all vertebrates [Feinberg and Mallatt, 2016]. Others say it arose in anatomically
modern humans only a few tens of thousands of years ago, when signs of creativity
and art first appear in the archaeological record [Mithen, 1996] (some say even later,
just 3,000 years ago [Jaynes, 1976]), and is therefore absent in animals (though there
are likely some evolutionary antecedents). Others say it is an epiphenomenal side
effect of other developments (e.g., intentional consciousness—the ability to think
about something) and does not matter much at all.
Those of the latter opinion might argue that concern for phenomenal consciousness is an anthropomorphic indulgence and that intentional consciousness is what
matters, since it seems to be the enabler of advanced cognitive capabilities such
as counterfactual reasoning and shared intentionality (the ability to create shared
goals and engage in teamwork). Yet others might observe that consciousness may
be needed to enable these capabilities in humans, but technology can achieve them
by other means.
One of the largest benefits from contemplation of technological consciousness is
that, through elaborations of the points above, it facilitates identification and isolation of many aspects of consciousness that are entwined in humans. Further, explicit
effort (i.e., simulations and other experiments) to create machine consciousness not
only helps evaluate theories of consciousness, it forces those theories to be articulated with sufficient precision that their evaluation becomes possible. Thus, study
of technological consciousness illuminates human consciousness and that, in turn,
can better inform consideration of technological consciousness. Additional study of
these topics is highly recommended, and must be a cross-disciplinary effort with
contributions needed from philosophy, psychology, neuroscience, computer science
and several other fields.
If we accept that technological consciousness is a possibility, or that machines
without consciousness may come to possess capabilities associated with consciousness, then issues of safety and control and of moral obligation need to be addressed.30
These also are crosscutting between philosophy, computer science, and other disci29
Focused Session 5 of the Workshop (see Section 12.6) was concerned with non-Western perspectives, meditation, out-of-body experiences etc. We do not describe these in the body of this report
because we cannot (yet) relate them to technological consciousness, but they raise many questions
and offer challenging insights on human consciousness.
30
Update: some of the weapons deployed in Ukraine raise concerns about ethics in autonomous
systems.
31
plines such as law and sociology. In fact, long before we reach questions of consciousness, philosophical questions abound in modern computer science: assurance
asks what do we know about our system (i.e., epistemology), and self-driving cars,
chatbots, and assistive robots all pose problems in ethics.
So, looking forward, we urge continuing cross-disciplinary study of these topics.
Cross-disciplinary work has challenges but the rewards would be considerable.
Addendum: Concrete Next Steps
Participants at the workshops have organized and are participating in two subsequent meetings. One is a panel “Is Machine Consciousness Necessary for True AI
Ethics?” at Robo-philosophy 2018 at the University of Vienna in February 2018.
Another is the symposium “Towards Conscious AI Systems” in the AAAI Spring
Symposium Series at Stanford University in March 2019. Individual participants
have published papers and popular stories stimulated by the workshops (e.g., [Kak,
2017] and online stories in theconversation.com and medium.com).
11
References
[Aleksander and Dunmall, 2003] Aleksander, I. and Dunmall, B. (2003). Axioms
and tests for the presence of minimal consciousness in agents I: Preamble. Journal
of Consciousness Studies, 10(4-5):7–18.
[Aleksander, 1992] Aleksander, I. L. (1992). Capturing consciousness in neural systems. In International Conference on Artificial Neural Networks (ICANN 2),
pages 17–22, Brighton, UK.
[Angel, 1989] Angel, L. (1989). How to Build a Conscious Machine. Westview
Press.
[Anonymous, 2003] Anonymous (2003).
423(6942):787.
Silence of the neuroengineers.
Nature,
[Arrabales et al., 2009] Arrabales, R., Ledezma, A., and Sanchis, A. (2009). Establishing a roadmap and metrics for conscious machines development. In Proceedings
of the 8th IEEE International Conference on Cognitive Informatics, ICCI 2009,
June 15-17, 2009, Hong Kong, China, pages 94–101.
[Asimov, 1950] Asimov, I. (1950). I Robot. Gnome Press.
[Baars, 2005] Baars, B. J. (2005). Global workspace theory of consciousness: Toward a cognitive neuroscience of human experience. Progress in Brain Research,
150:45–53.
32
[Barendregt et al., ] Barendregt, H., Israel, D., Lincoln, P., Rosenthal, D., Williams,
D., and Zebrowski, R. Breakout: Group 1. In Technology & Consciousness,
Focused Session 1.
[Bartley, 1976] Bartley, W. W. (1976). The philosophy of Karl Popper. Philosophia,
6(3–4):463–494.
[Bedau, 1997] Bedau, M. A. (1997). Weak emergence. Noûs, 31:375–399.
[Benedict, 1946] Benedict, R. (1946). The Chrysanthemum and the Sword: Patterns
of Japanese Culture. Houghton Mifflin.
[Boltuc, 2009] Boltuc, P. (2009). The philosophical issue in machine consciousness.
International Journal of Machine Consciousness, 1(1):155–176.
[Bringsjord et al., 2006] Bringsjord, S., Arkoudas, K., and Bello, P. (2006). Toward
a general logicist methodology for engineering ethically correct robots. IEEE
Intelligent Systems, 21(4):38–44.
[Bringsjord et al., 2018] Bringsjord, S., Bello, P., and Govindarajulu, N. (2018).
Toward Axiomatizing Consciousness. In Jacquette, D., editor, The Bloomsbury
Companion to the Philosophy of Consciousness, pages 289–324. Bloomsbury Academic, London, UK.
[Bringsjord et al., 2015] Bringsjord, S., Licato, J., Govindarajulu, N. S., Ghosh, R.,
and Sen, A. (2015). Real robots that pass human tests of self-consciousness. In
24th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pages 498–504. IEEE.
[Bringsjord and Zenzen, 1997] Bringsjord, S. and Zenzen, M. (1997). Cognition is
not computation: The argument from irreversibility. Synthese, 113(2):285–320.
[Brooks, 1991] Brooks, R. A. (1991). Intelligence without representation. Artificial
intelligence, 47(1-3):139–159.
[Brower-Toland, 2012] Brower-Toland, S. (2012). Medieval approaches to consciousness: Ockham and Chatton. Philosophers Imprint, 12(17):1–29.
[Bryson, 2012] Bryson, J. J. (2012). A role for consciousness in action selection.
International Journal of Machine Consciousness, 4(02):471–482.
[Burns and Shulgan, 2018] Burns, L. D. and Shulgan, C. (2018). Autonomy: The
Quest to Build the Driverless Car—And How It Will Reshape Our World. Harper
Collins.
33
[Campbell and Bickhard, 2011] Campbell, R. J. and Bickhard, M. H. (2011). Physicalism, emergence and downward causation. Axiomathes, 21(1):33–56.
[Carter et al., 2018] Carter, O. et al. (2018). Conscious machines: Defining questions. Science, 359(6374):400–400. Letter in response to [Dehaene et al., 2017].
[Casali et al., 2013] Casali, A. G. et al. (2013). A theoretically based index of consciousness independent of sensory processing and behavior. Science Translational
Medicine, 5(198):198ra105.
[Casarotto et al., 2016] Casarotto, S., Comanducci, A., Rosanova, M., Sarasso, S.,
Fecchio, M., Napolitani, M., Pigorini, A., G. Casali, A., Trimarchi, P. D., Boly,
M., et al. (2016). Stratification of unresponsive patients by an independently
validated index of brain complexity. Annals of neurology, 80(5):718–729.
[Cave, 2016] Cave, S. (2016). There’s no such thing as free will (but we’re better
off believing in it anyway). The Atlantic.
[Cerullo, 2015] Cerullo, M. A. (2015). The problem with Phi: A critique of integrated information theory. PLoS Computational Biology, 11(9):e1004286.
[Chalmers, 1995] Chalmers, D. J. (1995). Facing up to the problem of consciousness.
Journal of Consciousness Studies, 2(3):200–219.
[Chella et al., 2008] Chella, A., Frixione, M., and Gaglio, S. (2008). A cognitive architecture for robot self-consciousness. Artificial Intelligence in Medicine,
44(2):147–154.
[Chella and Manzotti, 2009] Chella, A. and Manzotti, R. (2009). Machine consciousness: A manifesto for robotics. International Journal of Machine Consciousness, 1(01):33–51.
[Clark, 2013] Clark, A. (2013). Whatever next? Predictive brains, situated agents,
and the future of cognitive science. Behavioral and Brain Sciences, 36(3):181–204.
[Conant and Ashby, 1970] Conant, R. C. and Ashby, W. R. (1970). Every good
regulator of a system must be a model of that system. International Journal of
Systems Science, 1(2):89–97.
[Cosmides, 1989] Cosmides, L. (1989). The logic of social exchange: has natural
selection shaped how humans reason? Studies with the Wason selection task.
Cognition, 31(3):187–276.
[Craik, 1943] Craik, K. (1943). The Nature of Explanation. Cambridge University
Press, Cambridge, UK.
34
[Damasio, 1994] Damasio, A. (1994). Descartes’ Error: Emotion, Reason, and the
Human Brain. Putnam Publishing.
[Danielson, 2010] Danielson, P. (2010). Designing a machine to learn about the
ethics of robotics: The N-Reasons platform. Ethics and information technology,
12(3):251–261.
[Dehaene et al., 2017] Dehaene, S., Lau, H., and Kouider, S. (2017). What is consciousness, and could machines have it? Science, 358(6362):486–492.
[Engel and Malone, 2017] Engel, D. and Malone, T. W. (2017). Integrated information as a metric for group interaction: Analyzing human and computer
groups using a technique developed to measure consciousness. arXiv preprint
arXiv:1702.02462.
[Epstein, 2016] Epstein, R. (2016). The empty brain. Aeon, 18.
[Evans and Stanovich, 2013] Evans, J. S. B. T. and Stanovich, K. E. (2013). Dualprocess theories of higher cognition: Advancing the debate. Perspectives on Psychological Science, 8(3):223–241.
[Everitt et al., 2018] Everitt, T., Lea, G., and Hutter, M. (2018). AGI safety literature review. In Proceedings of the Twenty-Seventh International Joint Conference
on Artificial Intelligence (IJCAI-18), pages 5441–5449, Stockholm, Sweden.
[Feferman, 1995] Feferman, S. (1995).
2(7):21–32.
Penrose’s Gödelian argument.
Psyche,
[Feinberg and Mallatt, 2016] Feinberg, T. E. and Mallatt, J. M. (2016). The Ancient
Origins of Consciousness: How the Brain Created Experience. MIT Press.
[Ferrucci et al., 2013] Ferrucci, D., Levas, A., Bagchi, S., Gondek, D., and Mueller,
E. T. (2013). Watson: Beyond Jeopardy! Artificial Intelligence, 199:93–105.
[Fink, 2018] Fink, J. (2018). Beyond the neuron: Emerging roles of glial cells in
neuroscience. PLOS Blogs. https://blogs.plos.org/thestudentblog/2016/
01/25/glialcells/.
[Fink et al., 2009] Fink, P. W., Foo, P. S., and Warren, W. H. (2009). Catching
fly balls in virtual reality: A critical test of the outfielder problem. Journal of
Vision, 9(13):14, 1–8.
[Frankish, 2010] Frankish, K. (2010). Dual-process and dual-system theories of reasoning. Philosophy Compass, 5(10):914–926.
35
[Frankish, 2016] Frankish, K. (2016). Illusionism as a theory of consciousness. Journal of Consciousness Studies, 23(11–12):11–39.
[Franklin and Jr, 2006] Franklin, S. and Jr, F. G. P. (2006). The LIDA Architecture.
In IDPT-2006 Proceedings (Integrated Design and Process Technology). Society
for Design and Process Science, San Diego, CA.
[French, 2000] French, R. M. (2000). The Turing test: The first 50 years. Trends
in Cognitive Sciences, 4(3):115–122.
[Friston, 2010] Friston, K. (2010). The free-energy principle: A unified brain theory?
Nature Reviews Neuroscience, 11(2):127.
[Gamez, 2008] Gamez, D. (2008). Progress in machine consciousness. Consciousness
and cognition, 17(3):887–910.
[Gazzaniga, 2012] Gazzaniga, M. S. (2012). Who’s in Charge?: Free Will and the
Science of the Brain. Harper Collins.
[Gazzaniga, 2015] Gazzaniga, M. S. (2015). Tales from Both Sides of The Brain: A
Life in Neuroscience. Ecco/HarperCollins Publishers.
[Gennaro, 2004] Gennaro, R. J. (2004). Higher-Order Theories of Consciousness:
An Anthology, volume 56 of Advances in Consciousness Research. John Benjamins
Publishing.
[Gennaro, 2012] Gennaro, R. J. (2012). The Consciousness Paradox: Consciousness, Concepts, and Higher-Order Thoughts. MIT Press.
[Godfrey-Smith, 2016] Godfrey-Smith, P. (2016). Other Minds: The Octopus, the
Sea, and the Deep Origins of Consciousness. Farrar, Straus and Giroux.
[Goff et al., 2017] Goff, P., Seager, W., and Allen-Hermanson, S. (2017). Panpsychism. In Zalta, E. N., editor, The Stanford Encyclopedia of Philosophy. Metaphysics Research Lab, Stanford University, winter 2017 edition.
[Govindarajulu and Bringsjord, 2017] Govindarajulu, N. S. and Bringsjord, S.
(2017).
On automating the doctrine of double effect.
arXiv preprint
arXiv:1703.08922.
[Greenblatt, 2011] Greenblatt, S. (2011). The Swerve: How the World Became Modern. WW Norton & Company.
[Griffiths et al., 2008] Griffiths, R. R., Richards, W. A., Johnson, M. W., McCann,
U. D., and Jesse, R. (2008). Mystical-type experiences occasioned by psilocybin
mediate the attribution of personal meaning and spiritual significance 14 months
later. Journal of psychopharmacology, 22(6):621–632.
36
[Grossberg, 2017] Grossberg, S. (2017). Towards solving the hard problem of consciousness: The varieties of brain resonances and the conscious experiences that
they support. Neural Networks, 87:38–95.
[Haidt, 2013] Haidt, J. (2013). The Righteous Mind: Why Good People Are Divided
by Politics and Religion. Vintage. Paperback edition.
[Hameroff and Penrose, 2014] Hameroff, S. and Penrose, R. (2014). Consciousness
in the universe: A review of the ‘Orch OR’ theory. Physics of Life Reviews,
11(1):39–78.
[Holland and Goodman, 2003] Holland, O. and Goodman, R. (2003). Robots with
internal models: A route to machine consciousness? Journal of Consciousness
Studies, 10(4-5):77–109.
[Jaynes, 1976] Jaynes, J. (1976). The Origin of Consciousness in the Breakdown of
the Bicameral Mind. Houghton Mifflin Harcourt.
[Kahneman, 2011] Kahneman, D. (2011). Thinking, Fast and Slow. Farrar, Straus
and Giroux.
[Kak, 2017] Kak, S. (2017). The limits to machine consciousness. arXiv preprint
arXiv:1707.06257.
[Kobie, 2019] Kobie, N. (2019).
The complicated truth about China’s social credit system.
Wired UK.
https://www.wired.co.uk/article/
china-social-credit-system-explained.
[Koch et al., 2016] Koch, C., Massimini, M., Boly, M., and Tononi, G. (2016). Neural correlates of consciousness: Progress and problems. Nature Reviews Neuroscience, 17(5):307–321.
[Koch and Tononi, 2017] Koch, C. and Tononi, G. (2017). Can we quantify machine
consciousness? IEEE Spectrum, 54(6):64–69.
[Koob, 2009] Koob, A. (2009). The Root of Thought: Unlocking Glia—The Brain
Cell that Will Help us Sharpen our Wits, Heal Injury, and Treat Brain Disease.
Pearson FT Press.
[Krupenye et al., 2016] Krupenye, C., Kano, F., Hirata, S., Call, J., and Tomasello,
M. (2016). Great apes anticipate that other individuals will act according to false
beliefs. Science, 354(6308):110–114.
[Kulicki et al., 2018] Kulicki, P., Trypuz, R., and Musielewicz, M. P. (2018). Towards a formal ethics for autonomous cars. In 14th International Conference on
Deontic Logic and Normative Systems (DEON), Utrecht, The Netherlands.
37
[Kurzweil, 2010] Kurzweil, R. (2010). The Singularity is Near. Gerald Duckworth
& Co.
[Lakoff and Johnson, 1999] Lakoff, G. and Johnson, M. (1999). Philosophy in the
Flesh, volume 4. New York: Basic books.
[Lakoff and Johnson, 2008] Lakoff, G. and Johnson, M. (2008). Metaphors We Live
By. University of Chicago press.
[Libet, 1985] Libet, B. (1985). Unconscious cerebral initiative and the role of conscious will in voluntary action. Behavioral and Brain Sciences, 8(4):529–539.
[Lindner and Bentzen, 2018] Lindner, F. and Bentzen, M. M. (2018). A formalization of Kant’s second formulation of the Categorical Imperative. In 14th International Conference on Deontic Logic and Normative Systems (DEON), Utrecht,
The Netherlands.
[Low et al., 2012] Low, P. et al. (2012). The Cambridge declaration on consciousness. In Francis Crick Memorial Conference on Consciousness in Human and
non-Human Animals, Cambridge, UK.
[Manzotti and Chella, 2018] Manzotti, R. and Chella, A. (2018). Good oldfashioned artificial consciousness and the intermediate level fallacy. Frontiers
in Robotics and AI, 5(39).
[Marin, 2009] Marin, J. M. (2009). ‘mysticism’ in quantum mechanics: The forgotten controversy. European Journal of Physics, 30(4):807.
[Marques et al., 2008] Marques, H. G., Knight, R., Newcombe, R., and Holland, O.
(2008). An anthropomimetic robot with imagination: One step closer to machine
consciousness? In Nokia Workshop on Machine Consciousness, pages 34–35.
[Marques et al., 2007] Marques, H. G., Newcombe, R., and Holland, O. (2007). Controlling an anthropomimetic robot: A preliminary investigation. In European
Conference on Artificial Life, pages 736–745. Springer.
[Massimini et al., 2005] Massimini, M., Ferrarelli, F., Huber, R., Esser, S. K., Singh,
H., and Tononi, G. (2005). Breakdown of cortical effective connectivity during
sleep. Science, 309(5744):2228–2232.
[Minsky, 2007] Minsky, M. (2007). The emotion machine: Commonsense thinking,
artificial intelligence, and the future of the human mind. Simon and Schuster.
[Mithen, 1996] Mithen, S. (1996). The Prehistory of the Mind: A Search for the
Origins of Art, Science and Religion. Thames and Hudson, London and New
York.
38
[Mogul, 2006] Mogul, J. C. (2006). Emergent (mis)behavior vs. complex software
systems. ACM SIGOPS Operating Systems Review, 40(4):293–304.
[Nemes, 1970] Nemes, T. N. (1970). Cybernetic Machines. Gordon and Breach,
New York. English translation from Hungarian, originally published 1962.
[Penn et al., 2008] Penn, D. C., Holyoak, K. J., and Povinelli, D. J. (2008). Darwin’s
mistake: explaining the discontinuity between human and nonhuman minds. The
Behavioral and Brain Sciences, 31(2):109–130; discussion 130–178.
[Penrose, 1994] Penrose, R. (1994). Shadows of the Mind, A Search for the Missing
Science of Consciousness. Oxford University Press Oxford.
[Popper, 2014] Popper, K. (2014). The Logic of Scientific Discovery. Routledge.
First published in German 1934, English 1959.
[Presti, 2016] Presti, D. E. (2016). Foundational Concepts in Neuroscience: A
Brain-Mind Odyssey. W. W. Norton & Company.
[Preston and Bishop, 2002] Preston, J. and Bishop, M. J. M., editors (2002). Views
into the Chinese Room: New essays on Searle and Artificial Intelligence. Oxford
University Press.
[Raoult and Yampolskiy, 2015] Raoult, A. and Yampolskiy, R. (2015). Reviewing
tests for machine consciousness. Retrieved from ResearchGate.
[Rawls, 1971] Rawls, J. (1971). A Theory of Justice. Belknap Press/Harvard University Press.
[Reggia, 2013] Reggia, J. A. (2013). The rise of machine consciousness: Studying
consciousness with computational models. Neural Networks, 44:112–131.
[Rizzuto et al., 2003] Rizzuto, D. S., Breznen, B., and Greger, B. (2003). Militaryfunded research is not unethical. Nature, 424(6947):369.
[Rosenthal, 2004] Rosenthal, D. M. (2004). Varieties of higher-order theory. In
[Gennaro, 2004], pages 17–44.
[Ross, 1992] Ross, J. (1992). Immaterial aspects of thought. The Journal of Philosophy, 89(3):136–150.
[Rudolph, 2003] Rudolph, A. (2003). Military: brain machine could benefit millions.
Nature, 424(6947):369.
[Schmidt and Lipson, 2009] Schmidt, M. and Lipson, H. (2009). Distilling free-form
natural laws from experimental data. Science, 324(5923):81–85.
39
[Schneider and Turner, 2017] Schneider, S. and Turner, E. (2017). Is Anyone Home?
A way to find out if AI has become self-aware—Scientific American Blog Network.
[Silver et al., 2018] Silver, D. et al. (2018). A general reinforcement learning
algorithm that masters Chess, Shogi, and Go through self-play. Science,
362(6419):1140–1144.
[Sjölander, 1999] Sjölander, S. (1999). How animals handle reality—the adaptive
aspect of representation. In Riegler, A., Peschl, M., and von Stein, A., editors,
Understanding Representation in the Cognitive Sciences, pages 277–281. Kluwer.
[Spatola and Urbanska, 2018] Spatola, N. and Urbanska, K. (2018). Conscious machines: Robot rights. Science, 359(6374):400–400. Letter in response to [Dehaene
et al., 2017].
[Sullins, 2016] Sullins, J. (2016). Artificial phronesis and the social robot. In Seibt,
J., Norskov, M., and Andersen, S. S., editors, What Social Robots Can and Should
Do, pages 37–39. IOS Press.
[Tinoca and Ortiz, 2014] Tinoca, C. A. and Ortiz, J. P. (2014). Magnetic stimulation of the temporal cortex: A partial “god helmet” replication study. Journal of
Consciousness Exploration & Research, 5(3).
[Tiwari and Talcott, 2008] Tiwari, A. and Talcott, C. L. (2008). Analyzing a discrete model of Aplysia central pattern generator. In Sixth International Conference on Computational Methods in Systems Biology, pages 347–366, Rostock,
Germany. Springer.
[Tomasello et al., 2005] Tomasello, M., Carpenter, M., Call, J., Behne, T., and Moll,
H. (2005). Understanding and sharing intentions: The origins of cultural cognition. Behavioral and Brain Sciences, 28(5):675–691. See also the commentaries
on pages 691–721 and the authors’ response “In Search of the Uniquely Human”
on pages 721–727.
[Tononi, 2007] Tononi, G. (2007). The Information Integration Theory of Consciousness. In Schneider, S. and Velmans, M., editors, The Blackwell companion
to consciousness. Blackwell Publishing.
[Tononi et al., 2016] Tononi, G., Boly, M., Massimini, M., and Koch, C. (2016). Integrated information theory: From consciousness to its physical substrate. Nature
Reviews Neuroscience, 17(7):450–461.
[Tononi and Koch, 2015] Tononi, G. and Koch, C. (2015). Consciousness: Here,
there and everywhere? Phil. Trans. R. Soc. B, 370(1668):20140167.
40
[Turilli, 2007] Turilli, M. (2007). Ethical protocols design. Ethics and Information
Technology, 9(1):49–62.
[Vallor, 2016] Vallor, S. (2016). Technology and the Virtues: A Philosophical Guide
to a Future Worth Wanting. Oxford University Press.
[von der Lieth Gardner, 1987] von der Lieth Gardner, A. (1987). An Artificial Intelligence Approach to Legal Reasoning. MIT Press.
[Wallach et al., 2011] Wallach, W., Allen, C., and Franklin, S. (2011). Consciousness and ethics: Artificially conscious moral agents. International Journal of
Machine Consciousness, 3(01):177–192.
[Wason, 1968] Wason, P. C. (1968). Reasoning about a rule. Quarterly Journal of
Experimental Psychology, 20(3):273–281.
[Yampolskiy, 2013] Yampolskiy, R. V. (2013). Artificial intelligence safety engineering: Why machine ethics is a wrong approach. In Philosophy and Theory of
Artificial Intelligence, volume 5 of Studies in Applied Philosophy, Epistemology
and Rational Ethics, pages 389–396. Springer.
[Yaron et al., 2021a] Yaron, I., Melloni, L., Pitts, M., and Mudrik, L. (2021a). The
Consciousness Theories Studies (ConTraSt) database: Analyzing and comparing
empirical studies of consciousness theories. bioRxiv, DOI: https: // doi. org/
10. 1101/ 2021. 06. 10. 447863 .
[Yaron et al., 2021b] Yaron, I., Melloni, L., Pitts, M., and Mudrik, L. (2021b). How
are theories of consciousness empirically tested? the Consciousness Theories Studies (ConTraSt) database. Journal of Vision, 21(9):2195–2195.
[Yu et al., 2018] Yu, H., Shen, Z., Miao, C., Leung, C., Lesser, V. R., and Yang,
Q. (2018). Building ethics into artificial intelligence. In Proceedings of the
Twenty-Seventh International Joint Conference on Artificial Intelligence (IJCAI18), pages 5527–5533, Stockholm, Sweden.
41
12
Workshop Summary
This section describes the activities of the SRI Technology and Consciousness Workshop Series, which took place over ten weeks between May 15 and August 11, 2017.
Eight, week-long workshops were held, each of which were attended by twelve to
twenty participants. A total of fifty-one individuals participated in one or more of
the workshops (see 12.9). Their disciplines spanned a variety of interests, including
neuroscience, cognitive science, robotics, artificial intelligence, computer science,
philosophy of mind, contemporary physics, psychoactive substances, eastern and
western religious traditions, and other perspectives.
The workshop participants were tasked with addressing four pre-specified objectives:
Characterizations of consciousness. The workshop stressed an interdisciplinary dialogue to achieve a common ground definition of consciousness across
fields.
Potential mechanistic underpinnings of consciousness. Provided with a
definition of consciousness, one can begin to explore the necessary requirements
and potential basis for the existence of consciousness.
Metrics of consciousness. What are reasonable, and agreed upon, metrics
of consciousness that allow us to assess consciousness in biological and machine
agents?
Perspectives on machine consciousness. Consider the (speculative) implications of future machine consciousness, particularly for the safety and welfare of inhabitants of future societies.
Workshop Organization The workshop consisted of two plenary sessions; one at
the beginning to open the workshop series and to discuss broad principles relevant to
technology and consciousness, and one at the end to summarize workshop findings
and to discuss future topics and research ideas, along with a series of short research
proposal presentations. Between the two plenary sessions were six focused sessions,
where each week focused in on a core sub-field or domain of consciousness research.
In contrast to typical academic meetings, presentations were typically, 50-60 minutes
followed by 40-50 minutes for Q&A, group discussion and cross-pollination sparked
by each talk. Over 400 pages of detailed notes were taken by a dedicated scientific
conference assistant. The workshop meetings, locations, and themes are listed below:
Plenary 1 (Arlington, VA) Overall objectives and format, keynote address,
preliminary broad presentations.
42
Focused Session 1 (Arlington, VA) Philosophical perspectives on consciousness.
Focused Session 2 (Menlo Park, CA) Embodied and cultural dimensions of
cognition.
Focused Session 3 (Menlo Park, CA) Insights from neuroscience and cognitive science.
Focused Session 4 (Cambridge, UK) Computational, mathematical, and
physics-based formalisms.
Focused Session 5 (Menlo Park, CA) First-person and non-western philosophical perspectives.
Focused Session 6 (Menlo Park, CA) Artificial intelligence and machine
consciousness.
Plenary 2 (Menlo Park, CA) Integrated overview and synthesis, new research
idea micro-pitches, future directions, closing remarks.
Chronological Record The remainder of this section provides a chronological
record of the workshop; the presentations, discussions, and topics that were covered.
It is divided into the eight week-long workshops, with the attendee list at the end.
For each workshop (plenaries and focused sessions), we report on the general theme,
the presentations and discussions, and then briefly summarize the final breakout
discussions that attempt to address the four pre-specified consciousness objectives
(characterization, underpinnings, metrics, machine/AI). Each workshop began with
an orientation presentation from the Technology and Consciousness leads from SRI
(David Sahner or John Murray). This orientation presentation was provided to
cover the overall themes and goals of the workshop (the series, as well as the specific
week), along with general operating rules and logistics.
12.1
Plenary Session 1: An Introduction to Consciousness
This initial plenary session focused on introducing the key participants to the overall objectives of the workshop, and to promote general presentation of topics and
ideas related to consciousness. The presentations primarily focused on overviews
of consciousness, framed through the domains of philosophy, biology/neuroscience,
and artificial intelligence. Plenary Session 1 featured a total of nine presentations.
External attendees: David Chalmers, Antonio Chella, Owen Holland, Ian Horswill, Julia Mossbridge, Susan Schneider, John Sullins, Paul Syverson, Robin Zebrowski
43
SRI attendees: Kellie Kiefer, Patrick Lincoln, John Murray, David Sahner,
Damien Williams
12.1.1
Presentations
David Chalmers: The Problem of Consciousness This talk provided an
overview of consciousness research and philosophical directions that have been pursued and explored over the many years. To set the stage, the discussion began
with an overview of defining consciousness, distinguishing between phenomenal consciousness (subjective experience) and access consciousness (reasoning, reportable).
Other terms exist, such as qualia and awareness, but these are terms that do not add
distinction beyond the aforementioned two types. Access consciousness is considered
the easy problem of consciousness, as planning and reasoning are implementable
in machine systems and have clear functional utility. The hard problem of consciousness is explaining phenomenological consciousness as this requires subjective
reporting and does not have a compelling argument for its utility. The remainder of the talk and discussion covered a broad overview of philosophical theories of
consciousness (from illusionism to dualism), complications related to measuring consciousness, and potential for machine/AI consciousness. The discussion was heavily
focused on self-consciousness, and how a demonstration of this may be a reasonable
metric for machine consciousness.
Antonio Chella: Robot Consciousness This talk was focused on addressing
the questions of whether robot consciousness is ever possible, and, if so, when it
might be realized. Based on the complexity of the human brain (number of neurons and synapses that connect them) and Moore’s Law, we might expect conscious
robots in the year 2029. Thus, the discussion is not framed around empirical observations of consciousness in biological systems, but around the requirements for
developing and determining whether artificial consciousness has been realized. Of
critical importance here is to distinguish between “weak” and “strong” robot consciousness, whereby weak has already been captured with hard programmed types of
intentional consciousness, such as reasoning or planning. One starting set of axioms
for determining minimal requirements for artificial consciousness are that the agent
can (1) depict, (2) imagine, and (3) attend to components of the external world,
and it can (4) plan and (5) emote [Aleksander and Dunmall, 2003]. This ability to
generate internal models of itself and the external world is a common requirement
for artificial consciousness, and systems have been developed towards accomplishing
this (ECCEROBOT, CiceRobot). Internalization and reflection may be a key component of consciousness (see [Minsky, 2007]). For computationally assessing models
of consciousness, one can look to theories related to information integration and
processing (such as information integration theory, IIT; [Tononi, 2007]), whereby a
44
conscious system can integrate and differentiate complex information inputs. Information integration theories have been explored in the realm of robot consciousness,
by David Gamez. The discussion centered around the potential and limitations of
IIT, and on how morality and ethics will be complicated components to develop into
future systems.
Julia Mossbridge: Time, Consciousness, Nonconsciousness Julia Mossbridge discussed the complexities of empirically measuring consciousness and how
it is only a minimal component of information processing, which is predominantly
non-conscious. The talk focused on phenomenological consciousness, or subjective
experience, rather than access or intentional consciousness. In particular, from
the view of neuroscience, it is presumed that non-conscious processes far outweigh
conscious processes and that individual conscious awareness is the result of brain
activity. The “iceberg analogy,” where conscious processing is the tip and nonconscious processing is the large chunk underwater, is inaccurate because, although
neither component can exist alone, there is an asymmetrical relationship whereby
non-conscious processing creates what is conscious. This asymmetry is critical, as
it is important to recognize that conscious awareness and processing only has access to information that non-conscious processes present. Another way to frame
this is that the non-conscious processes are actually responsible for sensing and interacting with the world, and there is a large gap where consciousness is merely
operating on information that has already been parsed through non-conscious processing mechanisms (mind the gap! ). This gap leads to a “lossy” transformation
because the complex, temporally-unconstrained non-conscious processes are forced
into an ordered and local representation to support conscious processing. Thus, it
is argued that we need to “understand the causative, generally nontemporal, and
overwhelmingly global nature of nonconsciousness,” because we cannot assume “the
mechanisms that produce consciousness are temporally ordered and local.”
Robin Zebrowski: An Android’s Dream This talk focused on the embodiment argument of consciousness. Neuroscience and philosophy have both developed
arguments related to how consciousness is a result of inputs and interactions with
a physical body, creating a world where consciousness is inseparable from embodiment. Specifically, Antonio Damasio’s neuroscience research and the linguistics
research of Lakoff and Johnson provide fundamental body-centric underpinnings of
consciousness and cognition whereby our understanding of the world, and communication about it, are fundamentally embodied. However, this raises questions as to
where body boundaries exist, as extending one’s body may translate to changes in
one’s consciousness. In fact, studies in prosthetics and sensory substitution demonstrate the plasticity and flexibility of human information processing, suggesting that
consciousness may be similarly fluid and dynamic.
45
Owen Holland: Machine Consciousness Owen Holland presented a great deal
of work on developing robot, or machine, consciousness. He mentions the shortcomings of neuroscience, due to the tremendous variability in neural structure and
function (particularly in patient work) that make the search for neural correlates
very difficult. Rather than dwell on neural correlates, this talk discusses how to approach building a robot with some level of machine consciousness in that the agent
can construct an internal model of itself and the external world. It is worth acknowledging that the agent, or body, is relatively fixed, or slowly changing, whereas
it exists in a complex and dynamic environment that has the capability to change
rapidly. Towards developing machine consciousness, the talk discusses a number of
anthropomimetic robots that aim to achieve a human-like physical (or simulated)
representation in order to develop a complex self-model (CRONOS, SIMNOS, Ecce
Robot). Of course, this is a work in progress, and the system is still missing a
number of elements that are likely critical for human-like consciousness, such as
language, inner speech, and autobiographical memory.
Susan Schneider: It May Not Feel Like Anything to be an AGI This
talk discussed the potential for artificial general intelligence (AGI) and machine super intelligence. In particular the focus was on the idea that consciousness may
be orthogonal to highly intelligent machines (hence the talk title), and that consciousness may be a property of AI that humans will have control over in the future.
Through discussing the concept of consciousness engineering, it raises natural issues about tests of consciousness and ethical issues. It may be that consciousness
requires certain underlying properties, such as being made from carbon rather than
silicon. In regards to ethics, if we can control which systems have consciousness in
them, it may be possible to develop intelligent AI that is better served by not having consciousness, such as systems used in war. Additionally, as we develop more
brain-machine interfaces, it raises questions as to how more invasive technologies
might affect consciousness of the human host. Unfortunately, because consciousness
engineering is not yet well developed, it is very difficult to develop an accurate test
of consciousness, as it may manifest in ways we can not predict. As it pertains to
the human race, advanced AI systems could feasibly take over as the next dominant
species (“super sapiens”), with or without consciousness.
John Sullins: From friendly toys to extreme HRI Towards our current
questions and understanding of the relationship between humans and robots, it is
worth reviewing the long history between humans and their creations. John Sullins
covered a broad history of human creations – and the subsequent feelings humans
have for these creations – and the depiction of AI in media (e.g., Blade Runner,
West World, Iron Giant, Star Trek). The relationship aspect is important because
it touches on the affective relationship humans have with robots and AI. While the
46
West has traditionally considered robots to be functional, in that they perform work,
Japanese robots have embraced the idea of social robotics, or affective computing,
whereby the human and system have a more emotional relationship. Social robotics
and affective computing were the main focus of this talk and discussion. They are
being created to manipulate or affect the emotion of a human user – an important
point that motivates a need to understand how social robots may affect human
behavior and relationships in the future. Towards understanding this relationship,
there have been committees and initiatives started to explore these ideas. What is
the impact of a sex robot?
12.1.2
Breakout Discussion
Breakout 1 The first group agreed that a cross-disciplinary approach could be
used to better characterize consciousness. Phenomenal consciousness was best characterized by a sense of experience, whereas functional consciousness is best characterized by behavior. There was not consensus on the mechanistic underpinnings
of consciousness, but it may be that it is a fundamental component of the universe
(akin to mass) and neural processes enable it. Additionally, it could be an emergent
property of computation, potentially in conjunction with necessary physical underpinnings. However, it is possible that this is all a simulation (i.e., “The Matrix”).
For metrics of consciousness, it was agreed that a Turing test is likely inadequate,
and developing a test is complicated by our lack of understanding in how machine
consciousness may manifest. It may be possible to request that the system introspect, or to apply measures of causal information integration (φ). The group agreed
that there is no reason to believe machine consciousness is not possible, and that
steps should be taken to ensure the safety and welfare of future societies. This is
particularly true if consciousness engineering allows us to willingly imbue systems
with consciousness.
Breakout 2 The second group agreed that an interdisciplinary approach is essential, and that it is worth finding fundamental principles that govern conscious
experience (e.g., IIT, information processing). Although a machine consciousness
may have a novel architecture unlike our own, simulations of it and its inputs may
provide insight into how its consciousness may manifest. The general consensus was
that neural correlates and embodiment are the likely underpinnings of consciousness. Towards measuring consciousness, the group explored multiple complex Turing
Test ideas. These included conducting thought experiments on creatures/systems
that exhibited cognitive behaviors (could they be creative?, consider death?), and
potentially developing conscious bridges across systems to have consciousness of
one system (System B) be explained by another (System A). The implications for
machine consciousness were framed from an ethical standpoint, in that conscious-
47
ness and intelligence may be orthogonal, so we may have to rethink ethics around
conscious (not necessarily intelligent) systems.
12.2
Focused Session 1: Philosophical Perspectives
The first focused session focused on philosophical perspectives of consciousness. This
session covered the phenomenological side of consciousness, with presenters diving
into complex concepts such as qualia, experience, and embodiment. Focused Session
1 featured a total of nine presentations.
External attendees: Hank Barendregt, Mark Bickhard, Selmer Bringsjord, David
Rosenthal, John Sullins, Paul Syverson, Robin Zebrowski
SRI attendees: David Israel, Patrick Lincoln, John Murray, David Sahner, Damien
Williams
12.2.1
Presentations
Robin Zebrowski: On the Possibility of Synthetic Phenomenology and
Intersubjectivity A core concept of phenomenological consciousness is the variability that exists due to embodiment. Following the embodiment argument, conceptualization of machine consciousness may benefit from it having similar “inputs”
to humans. As many researchers from philosophy [Lakoff and Johnson, 1999] to neuroscience [Damasio, 1994] have noted, consciousness is intertwined with the inputs
it receives, suggesting that the physical body plays a key role in shaping conscious
experience. Further, this extends to the innate needs and motivations that humans,
as biological beings, possess. This suggests an avenue of exploration for machine
consciousness – the engineering of needs/drives. Just as the physical body influences
consciousness, through embodiment and needs, physical representations of systems
influence interactions and feelings of shared experience. The talk ends with discussions related to anthropomorphic robots/systems and AI that can create art,
demonstrating that these experiences can essentially fool humans into a sense of
sharing an experience with a machine (that likely has no conscious sense of experience).
Selmer Bringsjord: The Irreversibility of Consciousness, Modernized
Author-Supplied Abstract: “Computation, at least of the standard variety, is provably reversible. Consciousness (at least apparently: what is, say, the reverse of your
consciousness of Russia’s leader Putin?) isn’t. Ergo, consciousness isn’t computation. Bringsjord first disclosed (a suitably unpacked version of) this argument two
decades back, in the pages of Synthese [Bringsjord and Zenzen, 1997]. Now it’s time
to modernize it in the light of new developments, to re-assess in the contemporary
intellectual context, and to also take account of phenomenological investigations of
time by Brentano and Chisholm (which were left aside in round 1). The upshot
48
is that any such goal as that of powerful machines via systematic consideration of
consciousness should be restricted to specific consideration of human-level cognitive
consciousness (HLC-consciousness).” The talk ends with a discussion of how consciousness may actually be modeled as data compression, and due to the need to
capture a model of irreversible information processing.
David Sahner: Philosophy of Mind - A Brief and Highly Selective Tour
The talk focused on a high level overview of many concepts related to consciousness.
The history of consciousness and philosophy, in particular, and how consensus has
shifted away from dualist theories to theories grounded more in physical mechanisms
that underlie consciousness. Even in the metaphysical sense, theories such as functionalism have evolved to explain consciousness in a more grounded way, such that it
exists for a purpose. Towards more modern examinations of consciousness, biology
and neuroscience have elucidated tremendous complexity in the human brain that
suggests modeling efforts may be far more complex than pure “neuron doctrine”
adherents would believe.
Mark Bickhard: Troubles with Qualia There are fundamental problems with
qualia, in the logical modeling sense, but there is a potential path forward in modeling conscious phenomena. The problems with qualia are that 1) because they
are the qualities of experiencing (experience of experience), they are ontologically
circular and impossible to model, and 2) the emergence model means that these are
not unitary phenomena so modeling must take into account unforeseen complexities.
However, a positive way forward is presented; ”A normative, future oriented, action based (pragmatist) framework enables the possibility of addressing phenomena
of consciousness as emergent in multiple kinds and properties of agentive functioning in the world.” The group discussion compared and contrasted this talk with the
previous talk from Selmer Bringsjord, with Mark Bickhard focusing on how irreversibility is a key component of consciousness as this allows a conscious agent to
have a sense of normativity.
Hank Barendregt: Trained phenomenology Hank Barendregt discussed
meditation as a form of trained phenomenology, in that the agent is training their
conscious interpretation of experience. The example that is provided is for an agent
to model and interpret the object, state, and action of reality as it is interpreted
through the stream of consciousness. By removing ego, and a sense of self, from an
experience, one can understand that feelings or emotions are actually states, rather
than qualities of oneself. As an example, one can imagine being angry. This requires
assigning the characteristic of anger to oneself. However, one could also characterize anger as an object that occupies ones consciousness. In this sense, anger is an
object that needs to be managed, rather than a defining trait of one’s being. Thus,
49
through meditation, it is possible to train one’s ability to interpret feelings, events,
and states, in a way that alter interpretations of free will. This can be interpreted
as a way of training how one phenomenologically experiences their reality.
John Sullins: Automated Ethical Practical Reasoning This talk focused on
categorizing artificial moral agency and discussed the problem of artificial phronesis. The potential danger in future AI systems is that agents will become more
autonomous, but may not have a sense of ethics, leading to a freely-acting system
that has no operational or functional morality. Thus, it is worth considering the
embedding of morality and ethics, despite this seeming so far off. However, AI
can advance more rapidly than expected; Go was considered a game would not be
mastered by AI for years, and AI beat the grand master in 2016. Microsoft’s Tay
(AI) was a fully autonomous learning system that ended up learning anti-social
sentiments when left to learn from the internet. The remainder of the talk discussed various approaches for how one might achieve an artificial moral or ethical
agent, and how at least attempting to incorporate ethical reasoning into a system
is a worthwhile endeavor (”Why didn’t the Microsoft engineers do something like
this?”).
Paul Syverson: Where Y’at? Epistemic Attacks on the Boundaries of Self
Having a sense of self is an important component of consciousness; “I” seem to exist
and am separate from my outside environment. However, along with this sense of self
comes the capability for an outside agent, or adversary, to exist. As AI progresses, it
may be possible for adversarial attacks to focus on vulnerabilities related to the AI’s
sense of self. For instance, if an AI, Alice, has properties or signals she attributes
to herself and/or others (beliefs), it is possible for an adversary to manipulate or
alter these properties in order to expose vulnerabilities. For example, one way to
confuse characteristics or beliefs is for an adversary to understand and manipulate
how Alice’s predicates change with context. For a moment, let’s imagine Alice is
an autonomous vehicle and she has beliefs about how to move quickly. When Alice
has to be fast, she believes she is fastest when setting her motors and actuators
to a particular configuration. However, it is important to note that Alice’s fast
configuration is actually relative to other dependent characteristics (such as road
type) that can be spoofed by an attacker. As an adversary, he may trick Alice into
initiating her fast configuration in the inappropriate circumstance, such as on a dirt
road – leading to an operational vulnerability. Thus, information security needs to
consider new ways that adversaries may be capable of attacking boundaries of AI
self and knowledge.
David Rosenthal: Mental Qualities without Consciousness This presentation covered the complexity of empirically testing mental experience. Specifically,
50
how it can be difficult to separate non-conscious contributions from those that are
conscious. Many mental qualities are equated with phenomenological consciousness,
but it is possible that many of these qualities are actually due to non-conscious processing and perception (i.e., not process pure). This is elaborated on in the second
part of the talk, where perception, which is often equated with qualia, is discussed
to be highly dependent on non-conscious states and properties. Given the complexity of separating mental state from conscious experience, this opens a number of
unanswered questions related to the function of consciousness. If mental qualities,
then, can exist outside of conscious awareness, what does being conscious actually
mean?
Damien Williams: The Minds of Others: What Will Be Known by and
Owed To Nonhuman Persons This talk covers the complexities of human constructs, and how they have tremendous impact on human behavior and well-being.
For example, social constructs around race and gender have important implications
on policy, but these constructs are also complicated by the fact that they are not
necessarily “true,” but relative based on the individual (a black woman’s sense of
gender is different than a white man’s). These constructs, which massively impact
human behavior, may eventually be built into future AI systems (intentionally or
not), thereby creating questionable artificial morality. If our future intelligent systems are based on our human moral behaviors, it is reasonable to foresee re-creations
of ethical atrocities, such as eugenics or the Tuskegee Syphilis experiments.
12.2.2
Breakout Discussion
Breakout 1 Through an interdisciplinary effort, the first group provided a hybrid Turing-machine model to explain the mechanistic underpinnings of consciousness [Barendregt et al., , for a thorough outline]. While they did not have a particular metric for assessing consciousness, it was generally agreed upon that machine
consciousness must be possible because we (humans) are machines.
Breakout 2 Towards categorizing consciousness, this group delineated between
theories/schemas based on how they relate to phenomenological consciousness (PC).
PC Compatible: Emergent, Functional, Higher-Order Thought
PC Complete: Phronesis, Interactionism
PC Neutral: Attention-Schema, Cognitive Architectures
PC Rejected: Access consciousness, Axiomatic consciousness
51
Towards measuring consciousness, the group suggested a battery of tests, including; assessing theory of mind (TOM), measuring φ (phi; per information integration
theory), Total Turing Tests (sensorimotor), games, and first person tests. While
machine consciousness is not impossible in the future, the group paid special attention to the desirability of having ethical autonomous and intelligent machines in
the future as these may prove beneficial by reducing the likelihood for danger and
providing a positive public perception. Of course, it is acknowledged that incorporating ethics is not a trivial task and there are multiple approaches and concerns.
In particular, one would likely want to construct formally verified safeguards at the
operating system level. Attempting to program in the entire space of ethical quandaries may be infeasible, and attempting to program in general ethical theories is
likely just as challenging. It may be that learning artificial phronesis is a reasonable
approach, but would be challenging to implement formally. In fact, if an artificial
moral agent was created (human-like in every material way but independent of phenomenological consciousness), it should be owed rights analogous to that of animals
or ecosystems.
12.3
Focused Session 2: Embodiment and Culture
The second focused session covered embodied and cultural dimensions of cognition.
This session explored how embodiment affects human perception and consciousness
at a fundamental level, such that one cannot consider consciousness independently
of how our physical body and external world impacts our sensory inputs (which
directly affect the contents of consciousness). In fact, this limitation on consciousness
(embodiment) may be one reason humans have been fascinated with altered states of
consciousness, which was explored during this session. Embodiment was discussed
in terms of both human and potential machine consciousness. Focused Session 2
featured a total of five presentations.
External attendees: Earth Erowid, Fire Erowid, Owen Holland, Susan KaiserGreenland, Alva Noë, Bill Rowe
SRI attendees: John Murray, Andy Poggio, John Rushby, David Sahner, Damien
Williams
12.3.1
Presentations
Alva Noë: Embodied Cognition and Consciousness Alva Noë discussed
the complexity of embodiment in consciousness, framed around the constructs that
impact how phenomenological consciousness is experienced. Per the secondary title,
Getting Out of Our Heads To Understand Human Experience, this talk covers the
bidirectional relationship between neural information processing and the outside
world. There are gaps between conscious experience and neural activity. There is
the absolute gap; why is neural activity accompanied by any experience at all? And
52
then there are comparative gaps; why does neural activity give rise to the experiences
that they do (e.g., red vs. green or audio vs. video)? Through a history of research
in psychophysics, sensory substitution, and sensory neuropsychiatry, we discover
that the information processing that gives rise to experience is extremely plastic
and dynamic. Thus, consciousness is not merely a fixed component of information
processing, but is a dynamic experience that is the result of highly dynamic neural
and environmental processes.
Bill Rowe: Infancy, Rhythm, Affect, and the Advent of Consciousness
This talk covered the origins of consciousness, both in antiquity and in development.
When did humans develop the consciousness that we typically label as consciousness
today? How does consciousness evolve through development? Through the study
of developmental psychology in Western cultures, we can understand how humans
develop their understandings of social interactions and, eventually, theory of mind.
Through affect attunement and social modeling, humans develop a complex sense
of decision making and social structure that leads to a complex form of, potentially
learned, consciousness. The evidence for certain qualities of consciousness being
learned comes from cultural and antiquity studies that suggest humans develop more
complex forms of consciousness due to variability related to social diversity. Thus,
to truly understand consciousness and to characterize it properly, it is necessary to
understand the roots of consciousness both in infancy and antiquity.
Fire and Earth Erowid: Altering Consciousness Author-Supplied Abstract:
This talk discussed how definitions and tests of consciousness can be improved by
data from humans’ intentional alteration of consciousness. For thousands of years,
people have explored their own minds and meta-concepts about consciousness via
psychoactive plants and drugs (alcohol, cannabis, opium, psychedelics), practices
(meditation, dreaming, drumming, physical ordeals), and, more recently, technologies (direct nerve recording and stimulation, transcranial magnetic stimulation, light
and sound machines). Biological consciousness is physio-chemically mediated. Everything we think and experience alters us physically at the cellular and even molecular level. The effects of psychoactive substances reveal that consciousness is a shifting series of distinct states that have yet to be fully defined or quantified. In a very
real sense, everything is psychoactive.
Deliberately altering the substrates upon which conscious decision-making processes operate creates recursive complexities that highlight questions, insights, and
testable theories about how we define our conscious selves. Psychedelic or mystical states can influence how boundaries are drawn between “self” and “other” and
how to circumscribe what constitutes a conscious entity. These issues have been
brought to the forefront by classic psychedelics (psilocybin, mescaline, DMT, LSD),
but emerging technologies for recursive-feedback stimulation and control of periph53
eral and central nervous systems also offer unprecedented opportunities to test the
boundary conditions of human consciousness. The very concept of “self” is increasingly intertwined with computers and networked communications. As humans
integrate into our lives technologies that affect how we think, feel, and interact, we
must rationally address what it means to have our hands on the levers that control the systems on which our consciousness runs. Can one be fully aware of one’s
consciousness without being aware that this consciousness can be intentionally altered? The meta-awareness that consciousness can be changed and the urge to alter
consciousness may be testable signs of consciousness itself.
Bill Rowe: The Problem of Now “Now” is a concept that captures an experiential sense of time, but how is it defined? This talk covers the predictive model
of experience that humans possess, and how neurophysiological processes dictate
one’s sense of now. It is critical to understand that sensation and perception are
not directly connected, in that previous experience and embodiment (physical processes) have a tremendous impact on conscious experience that is not dependent on
ongoing external sensory input. The bounds of the now that we experience may
have to do with a predictive feed-forward model that the human brain uses to make
sense of sensory information. Empirical studies suggest that human’s now lasts
about 700 milliseconds. This is the time it takes the brain to decide on a movement and predict it’s outcome, the human experience of the conscious “decision”
to initiate a movement, and then the initiation of the muscles. In fact, illusions,
emotions, and empirical studies of sensorimotor control suggest that consciousness
is merely experiencing its model of the world, which is consistently being updated
by sensory input, rather than the veridical representation of the world that exists.
Given this definition of human consciousness – the experiential now of an embodied world model – must machine AI also be programmed with embodiment and a
“hallucinatory” model of the world to experience consciousness?
Owen Holland: Will a conscious machine need a body, and if so, what for?
Organisms are constrained by embodiment and biology, but conscious machines will
not be restricted by such limitations. However, since the only consciousness we really
know anything about is that of humans, and that is the one we really want to know
more about, the science of consciousness should probably focus on creating single,
conscious, physical robots. Robotics has taught us much about embodiment. A
carefully designed body can enable or facilitate a behavior by reducing or eliminating
the computational load (this is now called morphological computation). Sensing
and action often have to be treated as a single unit in order to achieve a realworld objective. You do not need to know exactly what and where something is
in order to avoid it or climb over it (behavior-based robotics). In a rich physical
environment (i.e., the real world), interactions with a robot’s body and behavior
54
can lead to unanticipated but beneficial outcomes – i.e., emergence. A robot can
use its effectors to store information in the environment, and it or other agents can
use their sensors to read that information. There are several useful tricks one can
use to reduce the amount of “computation” required to perform particular tasks by
exploiting the form of the body or the effects of bodily actions. Thus, should we
abandon efforts to create artificial consciousness in real robots until we know more
about embodiment?
12.3.2
Breakout Discussion
Breakout 1 Characterizing consciousness is a fundamentally difficult question if
one is going to consider both the phenomenological and cognitive components of
consciousness. Do these forms of consciousness require embodiment, or exist along
a continuum? What caused such forms of consciousness to arise, and is phenomenological consciousness causal in any way, or merely illusory? The mechanistic underpinnings, of either type of consciousness, may require hierarchical, bidirectional
connections. This group focused on “top down” consciousness and theory of mind,
such that Global Workspace Theory seems like a promising – if incomplete – theory
of cognitive consciousness, but does not explain phenomenological consciousness.
Testing for consciousness should acknowledge that it is graded, not all or nothing.
One could test for reflective capabilities, meta-awareness of being conscious, nonfunctional creativity, joint planning, and realization of mortality. The tests should be
validated, similar to IQ tests, and the ethical implications of the test and its results
need to be considered. The group agreed that machine consciousness is possible,
and raised a number of questions about how it may manifest and affect society. It
may be emergent, rather than deliberately designed, suggesting that humans might
not be able to predict its behavior or intelligence. Will future machine consciousness
have free will, be capable of being monitored, lie, understand trust, or have desires
for altered states of consciousness? As far as implications and concerns, the group
suggested that machine consciousness will devalue human consciousness, and ethical
standards will have to be approached cautiously as it may be a form of consciousness
unlike that of humans, and will have to be regulated at the international level.
Breakout 2 Towards characterizing consciousness, this group distinguished between phenomenological consciousness, lexical consciousness, and consciousness
without content. Phenomenological consciousness could be considered pure or raw
consciousness, is independent of social constructs, and is shared with animals. When
combined with linguistics and social constructs, this may lead to lexical consciousness. Neither appropriately capture consciousness without content, which is considered to be a state of pure being, potentially achieved through meditation. A
good debate was had over the basis of consciousness, without any fundamental
55
agreements. From functionalism to information integration to shared knowledge, no
single theory was deemed sufficient to account for the different types of consciousness. Questions were raised about whether embodiment and perishability (risk of
death as a provider of “meaning”) were required for consciousness. Similarly, no
single test to measure consciousness was agreed upon. Rather, a battery of tests to
assess phenomenological and lexical consciousness should be implemented. Lastly,
the possibility of machine consciousness was split as well. While some believed
machine consciousness may be feasible, others believed it simply is not possible to
duplicate such a process. If machine consciousness were ever realized, it would be
critical to the welfare of future societies to endow these systems with moral codes
and ethical principles.
12.4
Focused Session 3: Neuroscience and Cognitive Science
The third focused session focused on insights from neuroscience and cognitive science. This session explored all realms of cognition and neuroscience, from low level
neuroscience and biological function, to completely artificial systems based on formal cognitive models and information theory of how consciousness may emerge and
be quantified. Focused Session 3 featured a total of eight presentations.
External attendees: Mark Bickhard, Selmer Bringsjord, Owen Holland, Christof
Koch, Julia Mossbridge, Susan Schnieder, Gary Small, Guilio Tononi
SRI attendees: Christopher Connolly, Patrick Lincoln, David Sahner, Daniel
Sanchez, Natarajan Shankar, Damien Williams, Adrian Willoughby
12.4.1
Presentations
Mark Bickhard: Consciousness in the Brain Neuron doctrine has long promoted simplified assumptions about neuronal function and its unique role in cognition, but more recent advances in neuroscience have shown that brain function is
far more complex and less understood than we initially believed. Similarly, classic
models of human information processing suggest a passive role of stimulus input
and subsequent perception, but one could imagine an active information processing
system and what emergent properties this would support. In an active system, the
information processing is based on a predictive model of the world, dependent on
potential interactions an agent has with an external world, and a normative value
function that can weigh said actions. Particular actions emerge based on these
values and functions, and all potential interactions are predicated on a model that
involves both sequence and timing. One can imagine a system where everything is
an oscillator and we consider the modulatory relationships and processes that exist.
When an agent turns this process inward, it leads to reflective consciousness, which
may be the “experience of experience” that we call phenomenological consciousness.
56
Selmer Bringsjord: Consciousness and Formalized Discontinuity AuthorSupplied Abstract: “In the remarkably esemplastic “Darwin’s Mistake” in Behavioral
& Brain Sciences [Penn et al., 2008], the authors argue that, contra Darwin, there is
an acute discontinuity between animal and human cognition (seen e.g. most vividly
in problem solving). Unfortunately, PHP’s discussion is informal; that is to be expected, since cognitive science (and for that matter neuroscience) is with rare exception not a theorem-based/driven discipline. This talk does three things: (i) presents
part of a logico-mathematical formalization of the core of PHP’s case, (ii) applies
this formalization to key experimental data arising from problem-solving challenges
given to nonhuman animals, and then (iii) takes stock of the consequences of (i)
and (ii) for assessing (nonhuman) animal consciousness vs machine consciousness vs
human consciousness. The upshot is that investigation of consciousness, esp. if that
investigation is carried out with an eye toward investigating/reaching worthwhile
forms of machine consciousness, should be one aimed at human-level consciousness,
and one that reflects the discontinuity between the nonhuman vs human case.”
David Sahner: Experiential Binding and Biological Complexity: Implications for Machine Consciousness? Integrating multiple sources of information,
across sensory modalities, happens automatically and is a fundamental component
of properly functioning neural activity that leads to phenomenological consciousness
(e.g., you cannot experience a zebra’s shape and stripes separately). What is responsible for this experiential binding that supplies inputs to human phenomenological
consciousness? This talk explores potential neural mechanisms for the binding that
could lead to consciousness, focusing on recent findings related to the claustrum and
its massive interconnectedness throughout the brain. Taking the necessity of integration as a key component of consciousness, this motivates directions for machine
consciousness; namely in addressing the requirements and metrics (e.g., φ, φE ) and
that may afford a future conscious system.
Julia Mossbridge: Future Prediction via Nonconscious Processes and
What it Tells Us About Consciousness Consciousness and time appear to be
intertwined, as time allows for the separation of events and the experience of causality. For example, if A causes B, one presumes that A must precede B. However,
multiple empirical studies of causality suggest that this ordering may not be set in
stone. This talk presents ideas related to precognition and retrocausality, primarily in the form of experimental data that demonstrate behavioral and physiological
markers that predict future events beyond chance levels. Behaviorally, “implicit
precognition” experiments show that humans demonstrate a forward-priming effect
whereby reaction time is faster when a previously shown image matches sentiment
for a word that is to be chosen in the future. For example, an image is presented
(negative or positive sentiment; e.g., a happy baby), a user is asked to quickly re57
spond with a saliency judgment, and then a word is presented (negative or positive
sentiment; e.g., dangerous). Prior to seeing the word, participants’ reaction times
are faster when the word and image are of the same sentiment. Additionally, physiological data are presented that demonstrate changes in skin conductance prior to
a participant being made aware of a reward outcome (win or loss) are predictive of
the outcome. Combined, this behavioral data and predictive physiological activity
suggest that consciousness may not be as linear in time as we expect, and we should
be open to possibilities that time is realized in nonintuitive ways.
Daniel Sanchez: The contentious relationship between memory systems
and consciousness Recalling an important memory feels intimate and personal,
and because it captures so much of our history and sense of self, also feels a bit
infallible. However, this intuitive sense of memory is riddled with errors that ignore
how constructive memory actually is; in that it is not a snapshot of reality, but a
constructed representation of events and knowledge that is flexible and dynamically
altered and updated over time. Emotions, cognitive framing, and other extraneous
variables affect the “reality” we recall during memory retrieval, and the inaccuracies
could at first be alarming to some. However, it is critical to realize that memory
is a multi-faceted construct that is created based on multiple systems working in
tandem to complement one another, in order to provide impressive learning and
retention capabilities. By examining how humans acquire and master a motor skill,
this talk demonstrates how memory may appear to be both contentious and complementary. However, the complexities of memory allow us to explore the subtleties
of consciousness and mental time travel, and provide a framework for understanding
how the fallibility of memory also gives way to the fundamental humanistic side of
information processing, storage, and retrieval.
Christof Koch: Neural Correlates of Consciousness - Progress and Problems What are the minimal neuronal mechanisms jointly sufficient for any one
conscious percept? Focusing on the sense of phenomenological consciousness, research suggests that this experience does not require behavior, emotions, selective
attention, language, self-consciousness, or long-term memory. However, it is dependent on some complex biological system such that destruction of certain cortical
regions interfere with the contents of consciousness. In addition to exploring different
areas that have been postulated to be responsible for consciousness (the claustrum
is an emerging candidate), this talk discusses critical, and necessary, background
conditions that must be met along with the neural correlates for a biological organism to function and experience consciousness. The neuroscience of cognition
and consciousness extends beyond humans, and it is possible to see the remarkable
similarities across neural structures and architectures between humans and other
animals. Exploring the neural underpinnings of consciousness raises a number of
58
hard questions regarding how and when consciousness emerges in beings, and how
it relates to biological and machine intelligence (if at all).
Giulio Tononi: Integrated Information Theory: from Consciousness to
its Physical Substrate To be conscious is to have an experience. One cannot
start from matter and “squeeze” consciousness out of it, but one can start from
consciousness itself and ask what physical system could account for its properties.
Integrated Information Theory (IIT) starts from phenomenology, not from behavioral or neural correlates. It identifies the essential properties of every experience
(axioms), derives the requirements that physical systems must satisfy to account
for them (postulates), and has explanatory, predictive, and inferential power. Phi
(φ), as a quantitative measure of integrated causality (consciousness), is high for
cerebral cortex, but low for other complex areas such as cerebellum and the basal
ganglia due to the nature of the neural connections and architecture. Translating
to practice, it is possible to test for consciousness by using a transcranial magnetic
stimulation (TMS) pulse to “ping” the brain with external activity, then measure
the causal changes in activity as a metric for cortical effective connectivity [Massimini et al., 2005]. This technique is being tested in patients [Casarotto et al., 2016]
and is currently named the Perturbational Complexity Index (PCI).
Owen Holland: How Neuroscience, Cognitive Science, and Psychology
can provide what Machine Consciousness needs, and how Machine Consciousness can pay them back Machine consciousness (MC) is an engineering
discipline, and theories from consciousness science can help guide the implementations that these engineers pursue. Full theories of consciousness should be able to
posit that in a system of type W, some components X will manifest characteristics
of type Y under some circumstances Z. While we understand that the human brain
is an instance of W, the other required components to complete this theory are
open-ended and not understood. Engineers and theorists have provided some suggestions for X (neural correlates of consciousness) and Y (see, Thomas Metzinger,
Igor Aleksander), but as an engineering discipline, MC requires all of these components to be detailed enough to implement in a real system (see LIDA [Franklin
and Jr, 2006]). Even more recent theories of neural function, such as the predictive
processing model that suggests the brain is a probabilistic hierarchical generative
network, does not provide sufficient detail to guide MC engineers in implementing
a system. Even if these are correct, they do not address the hard problem of phenomenological emergence. So, where are the MC projects going to be carried out?
Who is a contender?
59
12.4.2
Breakout Discussion
Because of timing and scheduling conflicts, the Breakout discussions took place prior
to the final presentation (Owen Holland). This is noted to reflect that the breakout
discussions would not have had content from the final talk to discuss.
Breakout 1 The distinction between types of consciousness is critical for accurately characterizing consciousness, as it is necessary to align the conversation
depending on whether one is discussing phenomenological, access, or human-level
consciousness. There was some debate as to whether access consciousness is clearly
distinct from phenomenological consciousness, or if it is merely the contents of consciousness that differ between them. Phenomenological consciousness may actually
have some causal power, as it could be supporting anticipatory contentful flow (the
ability to construct a semantic or functional flow to otherwise disparate content).
This form of consciousness is likely dependent on the available phenomenological
space (i.e., umwelt). Following this, the mechanisms that support consciousness are
potentially the neural correlates that are jointly sufficient for phenomenological consciousness. Although useful for AI, it was generally agreed upon (not universally)
that the hardware-software distinction is not helpful for understanding human consciousness as we know it. As a potential consequence of neural correlates, one can
argue for an intermediate level theory of consciousness. This theory posits that phenomenological consciousness resides between low-level processing and higher-level
abstraction and humans are experiencing the intermediate representation that is
influenced by processing of perceptual and abstract concepts. Work is needed to
understand how, and if, this is in agreement with higher order thought and humanlevel consciousness. The group found the Perturbation Complexity Index and φ
to be promising measures of consciousness, even if they were not absolute. Additionally, it was argued that the creative ability to discover and prove answers to
certain hard problems may imply phenomenological consciousness. While machine
consciousness may be possible in the future, and this raises questions about ethics,
rights, and testing for consciousness, the group agreed that machine intelligence is
a concern that should be monitored closely.
Breakout 2 Characterizing consciousness typically begins with the assumption
that a “self” or “I” (e.g., Descartes’ Cogito) is required. In other words, start
with consciousness, and infer rules from there. Towards this, the group discussed
breaking apart the notions of selfhood and phenomenological consciousness such
that one might just argue that experience exists. Therefore, something that has
experiences exists. In fact, it may be that the self is just what we label conscious
experiences connected through time, suggesting that self-consciousness is a function
of memory. The underpinnings of consciousness may be the robust neural “chains”
60
that build to grid structures in a φ-like system. In this sense, the topology of the
system may change the flavor of consciousness. Beyond structure, it may be that
time (or flow) is a fundamental axiom of consciousness. Following the mechanistic
underpinnings, the group agreed that φ or φE were reasonable potential tests for
consciousness. Machine consciousness may be able to exist in principle, but now
right now. Even if we simulate the whole brain, we are unlikely to capture causal
connections necessary for consciousness. We want the thing that exists for itself, not
just what seems to extrinsically exist. Machine consciousness, if functional and not
phenomenological, could lead to useful labor without guilt. However, care should
be taken not to over-attribute consciousness to a system that may not have it, as
this may lead to an incorrect prioritization of equipment over human lives.
12.5
Focused Session 4: Computation and Logic
The fourth focused session discussed computational, mathematical, and physicsbased formalisms. This session explored different theories of consciousness, particularly focused around computation and formal mathematics. Formalized axioms to
support consciousness (at least human-level cognition) were presented and discussed,
along with explorations of information integration and how, exactly, to define AI as
a discipline. Focused Session 4 featured a total of eight presentations. The external
workshop attendees included;
External attendees: Henk Barendregt, Susan Blackmore, Selmer Bringsjord, Antonio Chella, David Gamez, Owen Holland, Subhash Kak
SRI attendees: David Israel, John Murray, David Sahner, Natarajan Shankar,
Damien Williams
12.5.1
Presentations
David Gamez: Informational, Computational and Physical Theories of
Consciousness Theories of consciousness have evolved over time with modern
theories being focused around the physical world. Consciousness, being only reportable through self-report, is problematic from a measurement standpoint. Because we can accurately measure the physical world, we need appropriate models
that allow us to translate physical world measurements (p) to the world of consciousness (c). An appropriate model, or c-theory, is a mathematical description of
the relationship between measurements of consciousness and measurements of the
physical world. To date, Information Integration Theory (IIT) is the closest thing
we have to a c-theory. While one can propose information, computation, or physical
theories of consciousness, here it is argued that information and computation fall
short because they can be re-interpreted through physical theories, suggesting that
only physical theories are viable. If one were to use computational methods to determine and develop c-theories, what would be the best strategies and mathematics
61
for doing so? Is it possible that these theories can describe biological structures in
a way that enables generalization to future artificial systems?
Henk Barendregt: Axiomatizing consciousness with applications The explanatory gap between our ability to model consciousness from a third person perspective and the true first person perspective of consciousness is dubbed the hard
problem, and it will not be solved during this talk. Rather, this talk provides axioms
that model aspects of consciousness, motivated by neuropsychology, computer science, and Vipassana meditation. In particular, fallacies inherent in consciousness,
and how its intimate relationship with time affects the human sense of free will.
Consciousness is not as it seems. It is discrete, despite feeling continuous. It feels
veridical, but is often incorrect. Humans perceive information that biases behavior outside of awareness. The illusory sense of continuity necessitates interpolation
of information and selective omission of information, and this process can explain
why consciousness is not veridical and why omitted information is not experienced
despite being processed. This demonstrates that time is a critical factor, as consciousness depends on time. Consciousness has an object, an intended action, and
a state that maps the object to the action. Our actions change the world state,
and consciousness may be viewed as the predicted configuration stream of the world
that based on all of these inputs (world, state, object, action), which is continuously
being updated and corrected. If one considers strange attractors that promote repeated and predictable world and configuration states, mindfulness is the process of
deconditioning this circular state of existence. This has bearing on the definition of
free will, as the attractors and cravings humans experience lead to what should be
called restricted free will.
Selmer Bringsjord: Axiomatizing consciousness via eleven formulae &
linking to axiomatic physics Author-Supplied Abstract: “We present the axiom
system CA, intended to formalize human-level cognitive (HLC) consciousness and
associated mental phenomena. Like our work in axiomatic physics, in which computing machines can be enlisted to help discover and confirm illuminating theorems,
CA is intended to be implemented. And, one of the axioms of CA forges a direct connection between cognition and axiomatic physics, since it asserts that human agents
understand causation as it is captured in some axiomatization (possibly naı̈ve) of
part of physics.” The eleven consciousness axioms, elaborated in [Bringsjord et al.,
2018], are; (1) Planning (following [Aleksander and Dunmall, 2003]), (2) Perceptionto-Belief (P2B; perceiving is believing), (3) Knowledge-to-Belief (K2B), (4) Introspection (if you know something, then you know that you know it), (5) Incorrigibilism (identifying as having a property because you believe it so), (6) Essence
(unique sense of self), (7) Non-Compositionality of Emotions (an agent can enter an emotional state, but these are not all constituted by some conjunction of
62
“building-block” emotions); (8) Irreversibility (conscious processing is irreversible),
(9) Freedom (agents perceive or believe they are free), (10) Causation, and (11)
TheI (self-belief).
David Sahner: Contemporary Physics and its Nexus with Consciousness:
Should a Theory Wait? The predictive powers of contemporary physics are no
doubt impressive, and quantum theory is potentially one of most impressive theories
of all time. However, as successful and powerful as quantum theory is, discussions of
a quantum theoretical basis for human consciousness are likely to be premature. In
biological systems, quantum theory has been evoked to explain things from photosynthesis to avian navigation. Moving to the realm of human consciousness, one can
place consciousness in the position of the observational system that interacts with
the quantum world. However, given the conflicts and inability to reconcile general
relativity and quantum theory, is it reasonable to even think of introducing human
consciousness into the conversation? The back half of this talk focuses on modern
theories of quantum mechanics, and how science may be working towards agreeable
theories.
David Israel: Some Thoughts on Goals and Methodologies in Artificial
Intelligence Just what kind of discipline is Artificial Intelligence (AI)? If it purely
mathematical, then do we focus on, and judge the validity of, proofs and rank the
quality of theorems to determine impact? If it is an empirical science, then does
it generate falsifiable hypotheses that are (dis)confirmed through experimentation?
Since the seminal NSF-Funded Dartmouth Workshop debate in 1956, the field has
been shaped by disagreements in what AI should be. Simon & Newell emphasized
cognitive science, focusing on abstract human problem-solving (note, this ignores
lower level perception and motor skill functions). McCarthy promoted the highly
influential approach based on logical AI; a focus which stressed math and has had
little impact on cognitive psychology. This talk makes the case that AI is a design
discipline; one where systems are motivated by (but not locked to) cognitive psychology in order to get systems to perform complex processes intelligently. This goal, of
developing systems that can do some things intelligently (not all!), says little about
consciousness, but stresses the cross-disciplinary nature of artificial intelligence.
Subhash Kak: Quantum Mechanics and the Consciousness Problem If
the scientific method relies on reductionism, is consciousness, which is irreducible,
amenable to scientific study? This talk links the problem of measuring consciousness
to quantum mechanics and the complexities of measuring systems that behave in
ways that are not intuitive. Observation is said to collapse the wave function in
quantum mechanisms, so is it possible that consciousness can act as the observer
and become a fundamental part of physics? This discussion covers a breadth of
63
topics in quantum mechanics, from Schrödinger’s equation and thought experiments
to polarized waves and beam displacement. The talk ends with a discussion of
future ideas and directions in the realm of quantum research, from computing to
teleportation and AI.
Susan Blackmore: The Big Question for Consciousness Studies Is consciousness something added to all the functions and abilities we (and maybe other
animals and machines) have, or is it intrinsic to those functions and abilities? This
question is of real significance because it concerns the basis of phenomenological
consciousness; its function and evolution. Many theories of consciousness, such as
Global Workspace Theory and Information Integration Theory, are of the opinion
that consciousness is “something extra” that emerges from some aspect of brain
function but goes beyond the sum of the parts. Other theories posit that this is not
the case, such as Illusionism and Eliminative Materialism. These competing views
are discussed, with a framing around Daniel Dennett’s Multiple Drafts Model. Depending on one’s take, this has implications for machine consciousness. Machines
will be conscious like us only when they are as deluded as us.
Natarajan Shankar: Explorations in Robot Consciousness From Integrated Information to Information Integration Science is what we understand well enough to explain to a computer. Art is everything else we do. Akin to
this dichotomy, consciousness has solvable and unsolvable problems. Phenomenological consciousness, subjective experience, is hard to study objectively and without
a testable definition, we do not know that machines lack it. Access consciousness,
on the other hand, is about turning inputs into information, which machines clearly
can do. Taking all of this together, humans are amazingly capable of taking inputs
and integrating them in ways that keep them alive to continue experiencing the
world. Relating consciousness to intelligent agents, consciousness as an integrated
experience allows an agent to react in a unitary way to error/anomaly/reward, i.e.,
to take responsibility. This talk presents the concept of the Integrated Information
Theory of Consciousness (IITC), defining consciousness as the level of integration
across modules. By borrowing from information theory and cognitive psychology,
the theory of Cueology is presented, which explains how we can create “meaning
machines” through cue-based robotics and systems.
12.5.2
Breakout Discussion
Breakout 1 Consciousness can be characterized with two types. Little C: Cognitive consciousness; the ability to engage in or emulate useful complex behavior.
This is robust, functional cognition and is likely to track with intelligence. Big C:
Phenomenological; the majority of the discussants thought there was a Big C. To64
wards the mechanistic underpinnings of consciousness, the group believed that the
theories should be falsifiable, and many theories have a number of drawbacks (from
quantum to multiple drafts). Measuring consciousness may be possible through neural correlates, but the group conceded that no single correlate is likely to be found
to support Big C, particularly given the current technological limits. To extend on
this, one could assess behavioral and social correlates. However, many agreed that
Big C could not reliably be probed (φ for instance, is not adequate). They also
agreed that Machine Little C is achievable in the future, but there was disagreement as to whether Big C would ever be achievable. Most agreed that autonomous,
multi-task-capable systems pose danger, but through careful formal verification it
is possible to mitigate negative outcomes.
Breakout 2 This group had a broad discussion on what Big C (phenomenological) might be, and how it could be probed. In defining consciousness, it is worth
considering the embodiment arguments as well, such that experience has strong
bases in sensorimotor theories. Of note, despite this embodied framing, it does
not necessarily limit consciousness such that many senses are ignored, and out-ofbody-experiences as well as culture may affect how we frame embodiment. There
are multiple potential ways of probing Big C, such as meditation or assessments of
subjective estimates of time and the environment. From a machine consciousness
perspective, it raises questions as to how a machine with Big C (if possible) could
ever explain, define, or describe its own consciousness. Towards affording machine
consciousness rights, it is argued that ethics is rooted in sentience, but that we, as
humans, do not have the cleanest track record (e.g., racism/bigotry).
12.6
Focused Session 5: First-Person and Non-Western Perspectives
The fifth focused session covered first-person and non-western philosophical perspectives. This session explored the qualities that define and modulate phenomenological
consciousness. From a human perspective, this includes altered states of consciousness (whether through pharmaceutical means or intense life events) and the training
and focus on consciousness to separate conscious experience from the contents of
consciousness. For the future of machine AI, it was demonstrated how a number of
qualities typically assigned to consciousness in the realm of self-reference can be actualized through formal logic, and the question was raised of whether it was possible
to imbue a machine with a sense of contentment and mental quietude. It is possible
to link concepts of machine processing and human processing in the sense that both
systems and human brains are developed for a particular type of processing and
subsequent output. Mindfulness is the effortful attempt to limit “automatic” processing in order to be fully sentient, aware, and conscious of behaviors and mental
65
processes. Therefore, would a machine AI require a similar capability for mental
quietude in order to achieve consciousness? Focused Session 5 featured a total of
nine presentations. The external workshop attendees included;
External attendees: Naveen Sundar Govindarajulu, Marcia Grabowecky, Susan
Kaiser-Greenland, David Presti
SRI attendees: Patrick Lincoln, John Murray, John Rushby, David Sahner, Daniel
Sanchez, Damien Williams, Adrian Willoughby
12.6.1
Presentations
Naveen Sundar Govindarajulu: On Formalizing Eastern Perspectives
This talk presents a “self-aware” agent, Cogito, using formalized cognitive consciousness, and provides three contributions. Contribution 1: Showed a real-world
capability (ethics) that needs self-awareness. Contribution 2: Showed that selfawareness is essential for building moral machines (as posited in Vedic traditions).
An implementation and formal framework for achieving such machines. Contribution 3: Using key insights from a formal model of Advaita, a nascent formal system
building upon prior * operator. Through this framework, an extension on previous
instantiations of the doctrine of double effect is shown, demonstrating the criticality
of incorporating self-reference to ensure formal consistency.
David Presti: A radically-empirical perspective on mind-matter relationship If matter is the physical stuff (mass, energy, particles) and consciousness is
mental phenomena, what are the ways forward for the scientific study of consciousness? First, continued probing of the structural and functional aspects of brain and
body. This is a relevant endeavor because you are unlikely to do better or outthink evolution; if we thought of it, probably so did evolution. Second, interface
with fundamental physics. Third, refined analyses of mental experience. This can
be achieved through studies of mental control, such as researching meditation and
Buddhism. Additionally, scientists should explore altered states of consciousness,
potentially leveraging psychedelics. Lastly, Radical empiricism. Radical empiricism
is the study of less traditional subjects, such as psychical research and non-physical
phenomena (near-death experience, out of body experience). A brief overview of
psychical research is provided, with an emphasis on near-death experiences and
“spiritual” experience. These events are reported to have prolonged aftereffects,
such as: a decreased fear of death, an increased appreciation for life, increased
compassion, altruism, and interpersonal connection, and a decrease in materialistic
attachment and competitiveness. Exploring radical empiricism may hold the key to
the next big paradigm shift in the scientific understanding of consciousness. A lively
discussion followed the talk, discussing how to ethically study these transcendent,
spiritual experiences. Some examples were given, such as: experiencing the birth of
66
a first child, psilocybin studies [Griffiths et al., 2008, for example], or transient neural stimulation to increase feelings of “oneness” with the world [Tinoca and Ortiz,
2014, following the “God Helmet”].
Marcia Grabowecky: Approaches to Direct Experience of the Mind The
ability to study consciousness and subjective experience can be guided by Buddhist
practices that focus on mental development through meditation. The long eastern
religious traditions of careful subjective analysis of consciousness can provide both
hypotheses and data for scientific investigations. Attention training practices from
meditative traditions appear to: 1) be ways to train attention that generalize, 2) potentially stabilize mental states by reducing neural noise while maintaining alertness,
and 3) be used to explore the nature of conscious awareness during stages of sleep
that are usually unavailable to subjective report. This talk provides an overview
of meditative practices, both concentrative focused attention and vigilant mindfulness, and shows how seemingly automatic perceptual processes can be altered based
on empirical studies of long-term practitioners. Additionally, an overview of lucid dreaming is discussed, providing insight into how consciousness and subjective
experience manifest without direct external input.
John Rushby: HOT Theories of Consciousness, And Speculation on Evolutionary Origins Author-Supplied Abstract: “HOT theories of consciousness
associate consciousness with “thoughts about thoughts.” These are referred to as
“Higher Order Thoughts,” hence the acronym HOT. I will sketch the basic idea of
HOT theories, and outline some of its many different variants.
I then speculate on the evolutionary origin of consciousness, and its purpose. A
unique attribute of humans, and the reason we dominate the world, is our capacity of
teamwork; this requires “shared intentionality,” the ability of one human to create a
new goal and communicate it to others. The new goal begins as a (likely unconscious)
cluster of mental activity; to communicate it to others, it must be abstracted to a
succinct form. . . e.g., concepts. I argue that this leads naturally to a dual process
model of cognition where the “upper” level comprises (abstracted) thoughts about
(unconscious) lower level thoughts. As in other HOT theories, this model associates
consciousness with the upper level thoughts.”
John Murray: The Fringes of Consciousness Many of our perceptions and
behaviors do not occur consciously, but just on the fringes of consciousness. Despite our best conscious efforts, sometimes we cannot help but blush, and sometimes we have information just on the tip-of-our-tongue that we know we know
but cannot recall. These examples suggest that consciousness is not necessarily
boolean; there appears to be a continuum. Distortions of consciousness, through
drug-induced spatiotemporal hallucinations, further demonstrate that experience is
67
not fixed. Towards ensuring a robust and safe AI future, it is necessary to consider
that consciousness is not something that operates in a specific and pre-defined way.
Rather, it manifests in complex ways we cannot always anticipate, motivating the
need for appropriate oversight and governance as we build future intelligent systems.
Susan Kaiser-Greenland: The Headless Path: How to Build an Enlightened Robot From a self-professed “recovering lawyer,” this talk discusses how
meditation and mindfulness can be used for 1) stress reduction and self improvement, and 2) liberation and psychological freedom. The headless path is about discovering the lack of separation between oneself and the rest of the universe, in that
nothing exists in isolation. Through wisdom and compassion, meditation focuses
one to understand objective truth and to separate the judgmentality and emotions
that we typically associate with our experiences as being “add-ons” that we unwillingly attach, which can be separated and processed separately. By doing so,
an agent, or individual, is able to get to ultimate truth and separate the reflection
from the truth itself. During discussion, the headless path was compared to KabatZinn-style “non-judgmentality” such that feelings and emotions (judgment) are not
meant to be put away, but are meant to be put aside and processed separately, in
order to deeply understand why they are associated with events and things in the
world. Additionally, comparisons are made between the motivating mentality that
everyone is inherently good, compared to the Judeo-Christian view of Origin Sin.
Damien Williams: A Discussion on Taoism and Machine Consciousness
This talk provides an overview of Toaism (The Way) and presents philosophical
paradoxes and thought puzzles that are prominent and influential from eastern philosophy and scripture. Emphasizing principles and writings from Chuang Tzu and
Lao Tzu, one can understand the cultivation of consciousness as a return to simplicity and the ability to accept the importance of action without action, or Wu-Wei.
Wu-Wei is the powerful concept of understanding when not to act, as this provides
introspection and insight into the natural desire to move or act towards a goal,
which can sometimes be harmful and push one farther away. Towards a future
AI, it is worth considering how such principles could be incorporated into machine
consciousness. Could a machine understand contentment and pursue Wu-Wei?
Daniel Sanchez: Revealing the Misconceptions of Perception Buddhist
principles of the path teach that the mind can be trained through meditative practices of concentration and open awareness. Through this training, it is possible to
realize the lack of self and to understand that you, as the perceiver, are not independent or separate from the stimulus and environment you experience. This lack
of consistent “self” is a difficult concept to understand, in that we, as humans, typically feel like we are independent, unique, and perceive reality as we understand it.
68
However, illusions (optical or otherwise) are clear demonstrations that humans do
not perceive the environment in a veridical fashion, and that these mis-perceptions
are typically shared by others, demonstrating a shared perception or experience.
Following the concept that illusions are shared human perceptions, this shows the
similarity of human conscious experience due to our shared perceptual machinery.
In contrast, adversarial networks show how fundamentally different machine illusions can be, in that the misclassifications that machines make are not intuitively
similar to human illusory constructs. Given this disparity, it can be reasoned that
machine consciousness, if ever realized, will be fundamentally different from humans
because of the vast gap between our perceptions of the environment. Towards understanding machine consciousness, it is argued that machine vision systems should
be developed to both classify and misclassify as humans do in order to move towards
a more human-like future consciousness. In other words, human optical illusions are
a reasonable Turing Test for visual AI.
Christopher Connolly (via Daniel Sanchez): Basal Ganglia This presentation was put together by Christopher Connolly, but due to scheduling conflicts,
was delivered by Daniel Sanchez. Daniel had no prior knowledge of the content or
narrative, but volunteered to lead a discussion on the content as his expertise was
best aligned with the domain. The basal ganglia (also known as the striatum) is a
phylogenetically-old memory system that provides a reward-based learning mechanism based on looping connections with the cortex. The basal ganglia has tremendous integrative capabilities; 30,0000 cortical neurons can converge on a single striatal neuron. Despite being a neural region not necessarily considered a “neural
correlate of consciousness,” disorders of basal ganglia function have been shown to
produce alterations of conscious perception of space and time. Parkinson’s Disease,
a pathology based on dysfunction of the neurotransmitter, Dopamine, due to cell
death in the substantia nigra, leads to behavioral impairments that participants
are consciously aware of. Huntington’s Disease, a pathology based on dysfunction
with striatal neurons, leads to motor impairments and cognitive disruptions (e.g.,
disorganized thought). While these diseases are notable and recognized for a variety
of impairments, these effects on conscious processing and subjective experience are
not typically highlighted, and demonstrate how disrupted processing of inputs and
information lead to significant disruptions in conscious experience.
12.6.2
Breakout Discussion
Breakout 1 This group presented the idea of the Philosophical Snowman. The
largest, bottom sphere represents the inputs and representations while the middle
sphere represents models of information and the world, including the self. The top,
smallest sphere, or head, is where pure consciousness resides and interacts with
69
models of the world. The lack of a compelling argument for the underpinnings of
consciousness opens the door to speculation about consciousness fields and other
mechanisms that we do not well understand, such as gut biomes. Measuring consciousness then, was equally broad. Once we understand consciousness in the future,
we can test it by perturbing its components, whether it be a consciousness field or
some underlying biological construct. The potential for machine consciousness, given
the ambiguity about what constitutes and leads to consciousness, is there, if we can
ever discover it. If ever realized, it could provide a huge service to mankind and the
planet – particularly if imbued with Wu-Wei.
Breakout 2 Towards understanding phenomenological consciousness, this group
addressed the question of how one could become aware of being sentient. Given
the amount of time humans spend “doing,” it is very easy to automate complex
behaviors and separate conscious experience from the activities of everyday. This
is, essentially, the situation that mindfulness attempts to address. As our thoughts
and mental processes become overly concerned with higher level cognition (planning,
reasoning), our body is operating in a procedural mode such that the contents of our
consciousness are being driven by needs and requirements, and are not volitionally
controlled. Meditation is one way to become aware of phenomenological consciousness, but it could alternatively be cued through sensations such as hypnogogic jerk
or an extreme external input (trauma or physical input). Another way is through
shared reporting of consciousness and experience; we have a presupposition that
the physical world is real, so by being willing to recognize that we never experience
the world directly, we learn by shared reports. This type of consciousness, then,
is defined by awareness of the present moment; whether it is external or internal
(thoughts) experience. It is critical to note this is separate from the contents of consciousness. Because of the separation of phenomenological consciousness from other
cognitive and physiological activities, it may be that no true measure of consciousness exists. Towards this, because we do not understand how consciousness emerges,
it is not clear how any machine or simulation of consciousness would acquire the
actual property of consciousness.
12.7
Focused Session 6: Machine Consciousness
The sixth focused session was on Artificial Intelligence and machine consciousness.
This session explored the characterization of advanced machine intelligence, distinguishing between autonomy, intelligence, sentience, and consciousness (cognitive
and phenomenological). Additionally, theories of ethics, morality, and rights that
should be afforded to these systems was discussed, with care given to take these
various aspects and characterizations into account. For instance, what moral obligation do humans have to an intelligent system versus the same system with (or
70
without) sentience? Focused Session 6 featured a total of nine presentations. The
external workshop attendees included;
External attendees: Selmer Bringsjord, Antonio Chella, David Gamez, Owen
Holland, Jonathan Moreno, Ron Rensink, Susan Schneider, John Sullins, Shannon
Vallor, Robin Zebrowski
SRI attendees: Boone Adkins, David Israel, Kellie Keifer, Patrick Lincoln, John
Murray, Karen Myers, Andy Poggio, John Rushby, David Sahner, Damien Williams
12.7.1
Presentations
David Gamez: From Human to Machine Consciousness Machine consciousness (MC) can be delineated based on varying levels or categories (note, the
levels are not exclusive). MC1 are machines with the same external behavior as conscious systems; akin to Chalmer’s Philosophical Zombie. Many systems have been
created that behaviorally replicate seemingly conscious behaviors, such as IBM’s
Watson, however they make no claim to have internal consciousness. MC2 are computer models of the correlates of consciousness. Through robotic and simulation
systems, such as CRONOS (and SIMNOS; Owen Holland) and NeuroBot, large
spiking neural networks were created to simulate biological eye control and global
workspace concepts. However, while these systems tell us about physical systems,
they do not actually speak to machine consciousness at any level. MC3 are computer
models of consciousness (models of bubbles of experience). Systems, such as those
supporting Sony’s AIBO dog robot and Antonio Chella’s Cicerobot, have specifically
been designed to mimic a conscious agent’s abilities to represent the environment
and their interactions within it. However, while these systems model behaviors
and representations typically associated with consciousness, they do nothing towards creating actual consciousness. Lastly, MC4 are machines that are actually
conscious. We have yet to develop machines we might argue are conscious, so we
use human consciousness as the standard for assessment. C-Theories are proposed;
models that translate the description of the physical state into formal descriptions
of the conscious state. These theories can be developed based on the human standard, and applied to subsequent machine systems and future AI to assess predicted
machine consciousness. From an ethical standpoint, MC4 systems may necessitate
rights and ethical treatment, but MC1 machines should be treated carefully as they
could threaten humanity with their combination of powerful behaviors and lack of
consciousness.
Antonio Chella: A Cognitive Architecture for Robot Self-Consciousness
Towards a self-conscious robot, an architecture is presented that consists of (1)
sensory data inputs to a (2) sub-conceptual area that feeds into a (3) conceptual
area and, finally, a (4) linguistic area. The architecture is a hybrid, combining
71
a formal knowledge base with connectionist neural networks. Focus is given to
how conceptual representations are built, stored, accessed, and used. A hammer
is used as an example of how the visual input of simple geometry and relational
structure gives way to functionality and conceptual representation at a higher level.
This architectural framework is used as the basis for higher-level concepts including
theory-of-mind and self-consciousness. A working example based on this architecture
is shown, with Cicerobot. Future robotic work is shown, using the Pepper robot as
the basis for a future self-conscious machine.
Ronald Rensink: Consciousness, Attention, and Machines The question
of whether a machine could be conscious, and how we would know, is too difficult to
tackle head on, so here it is proposed to focus on fractionation – the functional examination of the atomic components of visual experience, or primary consciousness.
This approach follows from David Marr’s framework of analyzing an information
processing system based on its 1) function, 2) representation, and 3) implementation. With further fractionation, within the specific domain of visual experience, this
talk focuses in even further on the concept of visual attention. Attention, like visual
experience, can be considered a complex adjective, rather than a noun, and can be
divided into numerous components based on spatio-temporal features and varying
task-relevant functions. Using a taxonomy of visual attention applied to consciousness, it is possible to relate different kinds of visual attention to different layers
of visual experience. For example, attentional binding relates to assembled/static
image perception while attentional holding relates to coherent, continuous visual
experience. What follows is the Necessity thesis: an attentional process of type m is
needed for conscious experience of type n; each type of conscious visual experience
enables the control of its associated selective process, based on global considerations. It is argued that this thesis can be applied to other types of consciousness;
whereby other forms, such as subjective or introspective consciousness, can similarly
be fractionated and operationalized for subsequent study.
Robin Zebrowski: Extended Mind Metaphysics and the New Challenge
for Artificial Intelligence Is it possible to separate out the contributions of
the individual from the contributions of the environment when discussing cognition
and consciousness? Here, an argument is presented that describes the importance,
and potential necessity, of considering embodiment when attempting to understand
and model consciousness. It is argued whether the embodiment argument ties to,
or alters, debates around functionalism, but it raises a critical point for AI and
machine consciousness. In particular, metaphysics of the mind matters for machine
consciousness, so we cannot ignore the hard questions, and must consider how the
“extended mind,” or environment, impacts the representations of an agent. One
could argue that “at each step we should build complete intelligent systems that we
72
let loose in the real world with real sensing and real action. Anything less provides
a candidate with which we can delude ourselves” [Brooks, 1991]. This talk explores
the critical interaction between the agent and the environment in which it inhabits.
Susan Schneider: Tests for AI Consciousness Testing for phenomenological
consciousness in a machine is a, if not the, hard problem. Towards an answer, the
AI Consciousness Test (ACT) is proposed [Schneider and Turner, 2017]. ACT is
a question-and-answer test that is based on the premise that adults can quickly
and readily grasp concepts based on the quality of experiential consciousness. ACT
would challenge a potentially conscious AI with increasingly complex questions to
determine if the system could conceive of hard problems, such as self-hood, morality,
or consciousness itself. While other tests exist, such as using φ from Integrated
Information Theory to measure the potential consciousness of a silicon chip, we do
not yet know how machine consciousness will manifest, so it reasons that we should
use tests similar to those we would use on a functioning human today. It is argued
that this test is relevant for two components of consciousness engineering; optimal
AI performance and ethical use.
Jonathan Moreno: Is Mind Expansion a Test of AI Consciousness? While
it may not be a necessary condition for AI consciousness, might the capacity for
mind expansion be a test for conscious AI? Psychedelics are a canonical example of
a method that humans use to expand their phenomenological experience. Thus, understanding how and why humans use psychedelics, and the impacts they have, may
help guide our understanding of consciousness. This talk covers a history LSD and
its potential uses, including the exploration of the psyche by “psychonauts” and
their further-reaching compatriots, the “cyberpunks.” Nascent research on LSD
shows changes in neural activity that corresponds to changes in experience and phenomenological consciousness. This research may be a new venue for understanding
how the brain gives rise to consciousness, and the desire and ability for systems
to expand their consciousness may provide value in defining a fundamental drive
associated with conscious systems.
Selmer Bringsjord: Extremely Emotional Robots Author-Supplied Abstract: “We reveal real robots with extreme self-knowledge, including deep and
far-reaching knowledge of the limits of their knowledge. We anchor this engineering by considering Implemented versions of Alonzo Church’s Knowability Paradox,
which purports to shockingly deduce that from the solitude & comfort of a humanoid
robot’s armchair, it can deduce that there are truths that are mathematically impossible for it to know.”
73
David Israel: Robo-Ethics: A View from AI It is argued that robot ethics
is not needed, and the ethical quandaries that arise due to intelligent robots and AI
are not unique. Rather, the focus should be on issues related to the moral agency
and responsibility of increasingly autonomous artifacts, paralleling situations such
as the creation of the atomic bomb or offspring (children). What is critical to
examine is how artificial intelligence should behave, in the sense that it has the
ability to act intelligently, and, therefore, the responsibility to act morally. Thus,
consciousness is not necessarily the issue, so much as the ability for an autonomous
agent to make decisions. This decision making ability is framed based on agent
preferences, goals, and, utility. A discussion followed on the relevance of addressing
the ethics of autonomous and intelligent AI towards providing funding agencies
(such as DARPA who dealt with ethical issues related to neuroengineering the early
2000’s [Anonymous, 2003, Rudolph, 2003, Rizzuto et al., 2003]) with guidance on
research and development prior to problems emerging. Additionally, comparing
intelligence, but non-conscious, systems to children (who are arguably conscious)
was questioned by some.
12.7.2
Breakout Discussion
Breakout 1 Consciousness is best characterized as a coordination of types.
Whether described as a “cluster concept” or a fractionated whole, consciousness
can be thought of as a “coordinated community of components” rather than a singular or integrated entity. The reason for dissociated integration from coordination
is that consciousness seems to be plastic, or malleable, and is an ever-changing construct based on physical, social, and cultural factors that can affect it in important
ways on various time scales (identity can change over long and/or short periods of
time). Because consciousness is the result of dynamic processes, time is a critical
component that must be taken into account as a mechanism of consciousness. The
experience, compression, dilation, and conception of time impact consciousness on
a fundamental level, and these factors are, unfortunately, not well captured by formalisms or logic. Because of the many types of consciousness, there must be many
tests to assess it properly. From φ to introspection and the experience of humor, it
may require a varied battery of tests to assess a conscious agent. One component
that is worth exploring, is how time, which is argued to be critical for consciousness,
can be used to assess conscious experience. This all results in a complex answer
regarding the realization of machine consciousness. It may be possible, but it is
critical to discuss consciousness as its fractionated components (visual perception,
memory, attention, etc) that may be realized, rather than expecting a singular type
of consciousness such as the one we are used to in humans. Humanity’s relationship with any sort of machine consciousness will have to be considered carefully, as
even human-to-human communication can be misinterpreted despite a shared type
74
of consciousness. The group did raise questions about how we should approach a
potential machine consciousness (independent of type); should it be given full autonomy, a sense of purpose or morality? Or should these systems be allowed to
develop these senses on their own?
Breakout 2 Although interdisciplinary approaches for characterizing consciousness are useful, it is argued that not all disciplines are needed. There was not agreement on approach, but one side argued for empirical science with a reduced emphasis
on philosophy, while others argued that even if you remove philosophers from the
discussion, philosophy will remain a part of the conversation. Towards empiricism,
the group stressed a focus on cognitive consciousness rather than phenomenological. Phenomenological consciousness may not have mechanistic underpinnings or
an actual function, whereas cognitive consciousness – or what is important about
consciousness – may be thought of as a collection of interacting cognitive systems.
Given the focus on cognition, the group stressed tests for cognitive consciousness,
with the argument that tests for phenomenological experience may be impossible.
The group generally believe that machine consciousness is not possible, but that
extensive research should be committed to understanding the ethical impact of autonomous systems.
Breakout 3 This group generally acknowledged that consciousness should be
characterized based on the various “axes” that exist, following the fractionation
argument that consciousness is simply a unitary capability, but a coordination of
processes. The members did not converge on an agreed upon mechanistic underpinning, but considered the various theories that exist. In general, the group was
not sympathetic to illusionism, computationalism, substance dualism, or property
dualism. Towards testing consciousness, the group devised the Squirrel Test. The
Squirrel Test is the ability for an agent to produce a self-image of being something
other than itself. In other words, can an agent report on their ability to imagine
what it is like to be something else, like a squirrel? This group generally agreed that
machine consciousness was possible; in particular, cognitive consciousness. However,
there was hesitation around whether phenomenological consciousness or sentience
was possible, particularly at levels that would rival that of a human. Independent of
consciousness, a machine intelligence with autonomy and power is a potential threat,
and it was arguable whether sentience would materially sway the risk-benefit ratio
in any particular direction.
12.8
Plenary Session 2: Summaries, Synthesis, and Research Ideas
This final plenary session focused on summarizing and synthesizing the various topics
that were covered during the focused sessions. This included summary presentations
75
across a number of fields, representing the inter-disciplinary nature of the workshop,
and presentations of future project ideas from a number of the attendees. Plenary
Session 2 featured a total of ten full presentations, and 11 “micro” presentations
that focused on future research ideas. Considering this was the final plenary, there
was a large attendance. The external workshop attendees included;
External attendees: Henk Barendregt, Mark Bickhard, Joanna Bryson, Antonio
Chella, David Gamez, Naveen Sundar Govindarajulu, Marcia Grabowecky, Owen
Holland, Ian Horswill, Subhash Kak, Christof Koch, Jonathan Moreno, Julia Mossbridge, John Sullins, Shannon Vallor, Robin Zebrowski
SRI attendees: David Israel, Kellie Kiefer, Gordon Kirkwood, Patrick Lincoln,
John Murray, John Rushby, David Sahner, Damien Williams
12.8.1
Presentations
Subhash Kak: Old Ways of Looking at Consciousness: Current Relevance
After a brief history of consciousness research, this talk compares and contrasts
“Big-C” from “Little-C.” Big-C is consciousness as an instrument and witness, and
its connection to quantum mechanics is presented. Little-C is consciousness as a
process and emergent characteristic, and is within the realm of a strong AI. These
two distinctions are also presented in context of Eastern traditions and philosophies
that support differing views on the origins and functions of consciousness (Big-C,
Vedanta; Little-C, Buddhism). This talk covers a variety of concepts that link quantum theories to consciousness, such as the many-worlds-intepretation, decoherence,
and the quantum zeno effect.
Damien Williams: Science, Ethics, Epistemology, and Society: Gains for
All via New Kinds of Minds This presentation provides a broad overview of
topics and concepts that were covered and discussed during the six focused sessions
during the SRI Technology and Consciousness Workshop. After this overview, key
components related to self and personhood are discussed. In particular, the criticality of understanding and appreciating the minds, identities, and beliefs of those
different than oneself. By doing so, this may help bridge the hard problem and
explanatory gaps, in that it allows for a deep understanding of commonalities and
variances, and the potential underpinnings of both. Per the author, “If we ever
want to create a robustly conscious machine, we should first listen to people who
are different from us and who have been systemically prevented from speaking to
us, because they know things that we don’t.”
Jonathan Moreno: Autonomous Systems and National Security How will
autonomous systems be involved in future military operations? Historically, there
has been a precedent such that autonomous systems can assist in decision-making
76
and action, but humans should critically remain in (or on) “the loop” such that certain actions and consequences must require human involvement and culpability. As
technology advances and the need for autonomous systems to handle high-variability
environments increases, the relationship between the human operator and advanced
AI will continue to be a critical focus. However, it is worth commenting that these
systems are not dependent on development of artificial general intelligence, which
is an orthogonal goal. Beyond weapon systems, thrusts into neurotechnology are
discussed, along with the concept of the third offset strategy, which is about advances in “human-machine collaborative combat networks.” A key point that is
discussed is the importance of how these systems and approaches will be governed
and regulated in the future, at the international level. The discussion that followed
addressed concerns about focusing on weapon systems, and elaborated on the shared
goals across research and the military to use technology to avoid conflict in the first
place.
Robin Zebrowski: Mind-body problem proliferation: The more we learn,
the less we know This presentation is broken into two parts. First, a dialogue
and discussion is led as a plea to motivate interdisciplinary work. This plea is
premised on the argument that questions about consciousness are fundamentally
dependent on philosophy, while philosophy is incapable of answering said questions,
thus necessitating cross-discipline collaboration. The second portion of the talk
discusses how embodiment is fundamental to discussions of consciousness, evidenced
by tremendous interdisciplinary reports that consciousness is deeply dependent on
the embodiment of the agent that may be experiencing said consciousness. Of
course, embodiment is not a simple answer, as it leads to complications stemming
from a lack of formal definitions and conceptualizations. Thus, this warrants further
cross-disciplinary discussion and research that respects the various fields of study
while also acknowledging their limitations.
David Gamez: The scientific study of consciousness This talk explicitly
addresses the four motivating questions behind this workshop. Firstly, what is consciousness? Consciousness, as it is is typically considered, can frequently be labeled
as naı̈ve realism insofar as it describes the experience of the physical world, and
disregards the complex invisible factors that constitute reality (e.g., atoms and energy outside our physical sensor system). Thus, we can distinguish consciousness
as the secondary qualities, or the subjective experience, of primary qualities, which
are all of the properties of the physical world that go beyond our sensing capabilities. Towards understanding the mechanistic underpinnings of consciousness, it is
necessary to develop a theory (C-theory) that links the spatiotemporal patterns of
physical materials (such as neurons) to conscious states.
77
When attempting to develop metrics of consciousness, one should distinguish
between attempts to measure, predict, or deduce consciousness. In sum, per the
author: “We measure consciousness through first-person reports from systems that
are assumed to be conscious and capable of making accurate reports about their
consciousness. We use mathematical c-theories to make testable predictions about
consciousness on systems that make reliable first-person reports. We can make
untestable deductions about the consciousness of systems who cannot make reliable
first-person reports.” Towards machine consciousness, the definitions of four gradations of machine consciousness that were presented during the Focused Session 6
(From Human to Machine Consciousness) are presented again here.
This talk ends with a “plea for sanity” that contrasts the fear of autonomous
killer robots with the reality of AI capabilities, and raises the point that humans, not
machines, have been extremely dangerous and have developed highly lethal devices
to be used on each other for a long time. In other words; “People kill each other a
lot. This is not going to stop.” This suggests we should focus on making machines
safe and consider ways they can reduce harm, rather than worry about a speculative
future where they may be more destructive than humans.
Christof Koch: The Neural Correlates of Consciousness and its Implications for Architectures Supporting Consciousness This presentation is an
abbreviated version of the previous talk that was given during Focused Session 3,
Neural Correlates of Consciousness - Progress and Problems. The discussion that
followed explored ideas of contentless consciousness. Frequently conscious experience is framed based on the contents that are being attended to by the observer
(visual perception, for instance), so the capability to determine the neural correlates of contentless consciousness may reveal a “pure” form of consciousness. The
presentation and discussion were focused on a firm argument that some physical
property and material must be responsible for the experience and manifestation of
consciousness, independent of whether we have yet appropriately developed tools
that can measure said physical property.
John Murray: Other Voices Various opinions and thoughts were presented,
taken from individuals who could not be present for this particular workshop session. Adam Russell: Collective consciousness, such that consciousness is a relative
property based on what one is conscious of, is able to be shaped and manipulated
by digital content. Is now the best and most critical time to best quantify and
understand collective consciousness? Directions on researching human-robot interactions and social constructs were presented, based on input from Johanna Seibt
(Aarhus University), Thomas Sheridan (MIT), and Wendy Ju (Stanford University). Regarding human’s more precarious relationship with future autonomous
systems, concerns and directions related to autonomous weapon systems from Zac
78
Cogley (Northern Michigan University) were presented. Lastly, theories and potential mechanisms of consciousness from David Rosenthal (City University of New
York) and Bernard Baars (The Neurosciences Institute) were presented, leading to
the conclusion that more work is needed!
Joanna Bryson: A Role for Consciousness in Action Selection This talk
provides an in-depth overview of action selection and a theoretical function of consciousness in dealing with action selection. It covers a range of topics related to
memory, biases, action, learning, and ethics. The presentation elaborates on a previous publication [Bryson, 2012], whose abstract is included here; “This article argues
that conscious attention exists not so much for selecting an immediate action as for
using the current task to focus specialized learning for the action-selection mechanism(s) and predictive models on tasks and environmental contingencies likely to
affect the conscious agent. It is perfectly possible to build this sort of a system into
machine intelligence, but it would not be strictly necessary unless the intelligence
needs to learn and is resource-bounded with respect to the rate of learning versus
the rate of relevant environmental change. Support for this theory is drawn from
scientific research and AI simulations. Consequences are discussed with respect to
self-consciousness and ethical obligations to and for AI.” The talk combines previous
concepts from the aforementioned publication, and merges it with a roadmap for
conscious machines [Arrabales et al., 2009], with a focus on the how to best ensure
optimal collaboration between humans and future AI.
Shannon Vallor: Overcoming barriers to cross-disciplinary consciousness
research Provided the multifaceted complexity of consciousness research, it is
a nature fit for cross-disciplinary (CD) research. While CD research is laudable,
even when the right disciplines come together, it can be fraught with complications that lead to subsequent failure. This talk presents a guideline for successful
CD research, from aligning incentives to overcoming terminological confusion. CD
research is not naturally aligned with a number of external incentives, as domainspecific expertise is typically prized based on funding, publications, and prestige.
Thus, for these types of collaborations to succeed, they must have clearly defined
and alignable goals, an intrinsic desire and motivation to work together, and the
appropriate amount of expertise-overlap to allow for across-discipline conversations
while also affording serendipitous discovery and exploration. However, if collaborators can overcome “purity cultures” that prize domain-specificity, misaligned goals,
and resource problems, it is possible to develop fruitful CD research that cultivates
interactional expertise.
79
12.8.2
Micro-Presentations
The micro-presentations afforded the attendees an opportunity to provide a short
presentation on a research project or idea related to the workshop agenda. Most
of the attendees provided presentations, which have been summarized, while others
provided abstracts or text that is presented here. Text that is provided by the
authors is clearly marked as being author-supplied to distinguish their content from
the presentation summaries that were generated by SRI.
Christof Koch: Responsibility and Consciousness In collaboration with Dr.
Giulio Tononi, this project aims to understand causal responsibility, or free will.
Following from Integrated Information Theory (IIT), measures of φ will be used in
humans and simulated agents to isolate extrinsic and intrinsic forces that led to a
behavior or decision. By doing so, it may be possible to isolate whether causes were
based on external factors, or internal factors that can be attributed to a sense of
free will. He also proposes to “measure the neural correlates of free will in humans
(normal volunteers, impaired, children) using fMRI and EEG.” This work would
have impact on understanding and assigning responsibility in autonomous agents,
both biological and artificial.
Henk Barendregt: Discreteness of consciousness and its consequences
During Focused Session 4 (see slides for further detail), Henk Barendregt refined a
formal model of phenomenal consciousness with input from several attendees. This
proposal is to evaluate the fear that stems from the appreciation, in non-advanced
meditators, of the fleeting nature of a mutable and illusionistic “self” over which we
exert no free will. He wishes to investigate the mechanisms of overcoming such fear
through specific techniques and training in mindfulness meditation. Mindfulness
meditation may have a role in the treatment of psychiatric disorders.
David Sahner: Evolution in the hive The objective of this research is to “evaluate whether evolution of consciousness in artificial complex systems promotes moral
behavior and enhances functionality.” The approach, taking insight from modern
theories of consciousness, is to use neuromorphic architectures and evolutionary algorithms to create and study embodied agents in a social context. Phronesis will be
a controlled parameter that will be studied across conditions, and frequent testing
for consciousness will be used to evaluate for the presence of particular capabilities
and to understand functional impact. In particular, capabilities such as morallyguided behavior (altruism, socially-positive interactions) will be assessed, along with
various tests of aspects of consciousness such as sensorimotor capabilities and φ.
80
Subhash Kak: Investigating “Consciousness Capacities” in a Quantum
Learning System Author-Supplied Abstract): “Quantum mechanics is the most
fundamental theory in physics which almost certainly plays a role in the processing
in the brain. Furthermore, since quantum computing is more powerful than classical
computing, one needs to go beyond the classical computation regime of present-day
machines to better emulate the brain.
The field of quantum decision theory is being increasingly applied to real world
problems. Based on the mathematics of Hilbert spaces, this formalism has the capacity to capture aspects of cognitive and social processing that are not accessible
to classical models. Furthermore, it has the potential to find relationships and underlying structure in large data sets that might otherwise not be computationally
feasible. It is known that quantum models describe physical data in many aspects
of biology such as photosynthesis, magnetoreception in birds, and the olfactory system, to name just a few. Therefore, their applicability to real world data cannot be
ruled out. The proposed research will investigate the theory and implementation of
quantum cognitive machines that can learn as a step in the development of recursive
and self-organizing structures that is characteristic of biological systems. Consideration of quantum resources such as superposition and entanglement will open up
new possibilities in creating capacities that approach consciousness. We will also
investigate quantum decision theory to the problem of choosing between alternatives
with different payoff under the conditions of imperfect recall and varying degrees of
knowledge of the system. The classical version of the problem has bearing on the
general area of rational agency, learning, social choice, mechanism design, auctions,
and theories of knowledge.
There are results that agents with access to quantum resources can obtain superior performance as compared to classical agents. It can also be shown that in
the general case where each node can have any branching probability value, a random tree can accurately represent the probabilities associated with an arbitrary
quantum state. The research on quantum agents will help in the design of general
learning and decision systems that have the potential of developing capacities (levels
of consciousness) that go beyond present-day AI methods.
Quantum associative memory is exponential in the number of qubits (unlike the
linear capacity of classical memory). We would like to generalize this into the development of quantum pattern classification networks quite like the instantaneously
trained networks of classical computing.
The research in the project will consider the following specific problems: Problem 1: For real decision trees from an application area, find method to determine
the best quantum-equivalent representation and algorithms for efficient decisions.
Problem 2: Develop a solution to quantum pattern classification networks that learn
instantaneously (which would be a generalization of quantum associative memory
81
model). Problem 3: Investigate requirements associated with the implementation
of the cognitive architecture shown in Figure 1.
Figure 1: A cognitive architecture using quantum resources.
John Rushby: Emergence [and Consciousness]: Report of a Meeting
We often hear of consciousness “emerging” from the brain, but what does this term
mean? I will briefly report on a workshop I attended on the topic of emergence (in
distributed systems) organized by Herman Kopetz of TU Vienna in March 2016. In
addition to computer scientists, the participants included philosophers, biologists
and others.
The consensus that emerged (!) is that we could all subscribe to what philosophers call “weak” emergence. A phenomenon at the macro-level is emergent if and
only if it is of a new kind with respect to the phenomena of its micro level parts.
An example is temperature and pressure in a gas (macro), vs. the motion of its
molecules (micro). The macro behavior is explainable (in principle—we may currently lack the knowledge to do so, as is the case with consciousness) in terms of
the micro behavior. I propose research to develop a more comprehensive theory of
weak emergence, both as a design tool, and as a means of analysis (to be applied to
consciousness).
Antonio Chella: Phenomenal and Social Aspects of Consciousness by Developmental Robotics Author-Supplied Abstract: “The idea for future research
in consciousness studies concerns the investigation of the intertwining between phenomenal consciousness and social aspects of consciousness in the development of
human beings. The central hypothesis, inspired by “I and Thou” by the philosopher of religion Martin Buber, is that the I-consciousness, the It-consciousness and
Thou-consciousness evolve at the same time during the development of the human
being. Therefore, phenomenal consciousness is related to the perception of the external world, i.e., the relation I – It, and also to the development of the social aspects
82
of consciousness, i.e., the relationship I - Thou, as the capability to develop a theory of other minds. In turns, this ability is endowed with self-consciousness, i.e.,
the capability to develop a theory of own mind. Eventually, the ability to report
phenomenal states would arise. The proposed research will take into account the
methodologies of developmental robotics to build an evolving robot child able to
perceive the external world and to develop a simple theory of other minds. The
central goal of the research is to analyze whether the evolving robot may be capable of developing at the same time some form of self-consciousness and reporting
phenomenal states. A starting point will be the theory of social communication as
a meeting of minds proposed by Peter Gärdenfors. Collaborations will be placed
with John Rushby, SRI to investigate the relationships of the proposal with the
HOT Theories of Consciousness; with Angelo Cangelosi, Plymouth University, UK,
a leading expert in developmental robotics; and with Peter Gärdenfors, Lund University, Sweden concerning the meeting of minds hypothesis.”
Owen Holland: The engineers of souls Author-Supplied Abstract: “While the
philosophical and psychological interest in machine consciousness may be focused
on phenomenal consciousness, the likely applications will primarily exploit the functional aspects of cognition that are uniquely enabled by consciousness, or by the
cognitive components that necessarily underpin consciousness. Candidate elements
include but are not limited to: functional awareness of an embodied and narrative
self, reconstructive episodic memory, imagination, evaluation of the consequences
of real or hypothetical events, planning, reflection, rationality, awareness of other
minds, communication with other minds, and collaboration. In order to study some
of these, which may be strongly linked to or inseparable from the others, we need
multiple agents in a rich and dynamic world. Experience tells us that using multiple robots in the real world is too slow and inflexible for carrying out the necessary
variety of experiments, and so we need to move to virtually embodied agents in a
virtual world. This allows multiple parallel instantiations running faster than real
time, with complete access to all historical states and processes in both agents and
environment. In order to bring the system into the real world, the virtual system
will be physics based, the environment will be an accurate capture of the real world,
and the virtual robots will be accurate physics based copies of carefully designed or
chosen real robots with exactly the same controllers as the virtual robots, equipped
with methods for recording all internal states and processes. In principle, an experiment run in the virtual world, perhaps involving controllers trained or evolved
over millions of previous experiments, could then be repeated in the real world. It
would also be possible for a human to control an avatar or avatars in the virtual
world in the form of the agents under study, and to control a real robot avatar in
the real world. The relevant techniques for doing all this already exist to varying
83
degrees - for example, check out the technologies underpinning Facebook’s virtual,
augmented, and mixed reality.
The cognitive architecture of the agents/robots should be based on what is now
known as predictive processing, as this is the only prospective technology capable of
spanning the range of abilities required for rational perception and action combined
with the various cognitive features associated with consciousness. At present, it has
two serious disadvantages: it is being oversold, and it is not as yet a usable technology. It is being oversold by claims such as: it is what all intelligent systems must
do, that it is all that they must do, and that the structure of the brain has evolved
to provide a recognisable implementation of it. For our purposes, we do not need
a credible pseudo-neural implementation, nor do we need any credible evolutionary
path for producing it, and we will be happy to supplement the predictive processing
with existing technologies and architectural components as required. It is not yet
usable because the philosophers and neuroscientists promoting it - with good reason
- are not engineers. We are.
Although the first part of this proposal is clearly independent of the second,
and is capable of supporting many other investigations, the second is clearly dependent on the first, and that is why I have presented them both together. The first
is essentially an engineering development activity that could start tomorrow, but
the second requires a very substantial joint scientific and technological effort from
engineers, most of whom will start out knowing too little about consciousness, and
psychologists, neuroscientists, and philosophers, most of whom will start out knowing too little about engineering. And though the aim is to discover and delineate
the relevance of consciousness for cognitive functions, who knows where it will end
up? Joseph Stalin is on record as remarking ’Writers - the engineers of the human
soul’ but that was then, and this is now.”
Joanna Bryson: Three Project Areas Three research agendas were proposed.
First; a project to understand the interactions between consciousness, performance,
and learning. This aims to understand how awareness impacts the expression of
pre-existing knowledge and new learning. Second; understand how implicit and
explicit beliefs interact with identity, trust, and cooperation. Bias impacts human
behavior, so it would be useful to understand how group identity and polarization
are impacted by conscious and non-conscious processing. Third; “Create sensible
metaphors; processes; state, national & transnational organisations to encourage appropriate incorporation of AI into human society.” Because humans are the responsible agents creating robotic artifacts, their machine nature should be transparent
and appropriate governance needs to be established.
Naveen Sundar Govindarajulu Proving a machine is consciousness may be impossible, so it is reasonable to argue that a machine that behaves and functions like
84
a conscious agent is a reasonable goal for artificial intelligence. Towards increasing
“cognitive consciousness” in AI, it is argued to focus on reasoning, planning, and
human learning (or, Good Old Fashioned AI), to work towards human-level cognitive behaviors. One direction to pursue would be using theorem provers and to aim
for accomplishing Theory of Mind.
David Gamez: Research projects on consciousness David Gamez proposed
a number of research directions based on his gradations of machine consciousness,
which he presented during Focused Session 6. Singularity Machines; although potentially impossible, the attempt to build a machine that can build an even more
intelligent machine, ad infinitum, in order to achieve the singularity would likely
result in a deeper understanding and exploration of intelligence in machines. Global
Workspace; merging deep learning architectures with global workspace architectures
could lead to more explainable AI and lead to machines that think more like humans.
Imagination; develop robots that use simulation and imagination so that AI can predict or “think” about the future and what to do next, to get machines to think in a
human-like way. Lastly, Brain Uploading; attempt to build a functionally-accurate
real-time brain simulation and then explore novel attempts to measure machine
consciousness (φ or examine memory space) and hardware architectures that might
better support the simulation (e.g., neuromorphic chips).
John Sullins: Artificial Phronesis Phronesis is defined as “the habit of making
the right decisions and taking the right actions in context, and relentless pursuit of
excellence for the common good.” Human phronesis depends upon its evolution in a
social context through learning. Autonomy in the absence of such ethical grounding
poses a danger. This project proposes to work on developing artificial phronesis in
AI agents to promote ethical behaviors. Artificial phronesis aims to enable an agent
to identify ethical situations, attend to them, and then practically and efficiently
react with justified actions/decisions.
Julia Mossbridge: Toxic Individuality This project addresses the concept of
toxic individuality; a concept analogous to toxic masculinity whereby there is a
need to be “in the limelight” and there is a negative (or violent) reaction when this
need is not met. The proposal is to improve the ego development in the dominant
group (males) to improve their sense of belonging and to allow them to be open to
bringing others (“the enemy,” outgroups) into their dominant group. To do this, an
AI personal coach will be used (“Mensch Mentors”). In a pilot population of male
employees, these mentors will be used to query stimulating narrative about future
goals and to support and challenge individuals in a timely manner. It is expected
that a group of individuals who have these mentors will have increased well-being
85
and ego development that will influence their relationships and subsequently enhance
interpersonal and group dynamics.
Ian Horswill: Modeling mammalian neuropsychology for interactive virtual characters Humans are social animals, who often rely on emotions to guide
behaviors. While we appreciate this component of “humanity,” we typically disregard complex social and emotional components of human behavior when we start
to talk about advanced AI. Rather than focus simply on the human-level cognitive
component when building AI, it is argued here that we should consider the more
social and emotional components of agent behavior. This project aims to build a
model of a social mammal to observe and learn from it. Towards understanding
emotions, it is conjectured that some emotions are just activations states of the
behavioral system with which they are associated. Thus, emotions may merely the
outward behavior of an underlying algorithm or system activation, rather than a
stand-alone process that modulates or motivates other behaviors.
12.9
Workshop Attendees
The conference was attended by thirty-two invited attendees from a variety of international external institutions, and sixteen attendees from SRI. The full attendee
list of the 2017 SRI Technology & Consciousness Workshop Series follows;
Last Name, First Name Affiliation
Research Interests and Expertise
External Attendees
Barendregt, Henk Nijmegen University; Chair, Foundations of Mathematics and Computer Science
Lambda calculus and type theory; mathematical definition of mindfulness;
mindfulness meditation
Bickhard, Mark Lehigh University; Henry R. Luce Professor of Cognitive
Robotics and the Philosophy of Knowledge
Cognitive robotics, philosophy of knowledge, interested in theoretical physics
and mathematics
Blackmore, Susan Visiting Professor in Psychology at the University of
Plymouth
Widely recognized expert in consciousness studies and author of textbook on
this topic and other relevant books
86
Bringsjord, Selmer Director, Rensselaer Polytechnic Inst. AI & Reasoning
Laboratory; Chair & Professor of Cognitive Science; Professor of Computer
Science; Professor of Logic & Philosophy
AI and cognitive science, philosophy of mind
Bryson, Joanna University of Bath
Artificial models of natural intelligence
Chalmers, David Director, Center for Mind, Brain and Consciousness, New
York University
Renowned philosopher who has contributed greatly to the understanding of
human consciousness
Chella, Antonio University of Palermo
Machine consciousness, robotics, computer vision
Earth and Fire Erowid Erowid Center
Maintain extensive database of human experiences with psychoactives
Gamez, David Middlesex University Department of Computer Science
Measurement of consciousness; information integration theory of consciousness
Govindarajulu, Naveen Sundar Rensselaer Polytechnic Institute, Troy,
New York Data Scientist; natural language processing
Grabowecky, Marcia Northwestern University
Multi-sensory integration, perception, and meditation
Holland, Owen University of Sussex Sackler Center for Consciousness Science
Machine consciousness and cognitive robotics
Horswill, Ian Northwestern University
AI, control systems based on goal state and sensor
Kaiser-Greenland, Susan Mindfulness educator and author
Mindfulness
Kak, Subash Oklahoma State University School of Electrical and Computer
Engineering
Quantum cognitive science, neural networks, and quantum computing
Koch, Christof President/CSO, Allen Institute for Brain Science
Cognitive and behavioral biology, artificial intelligence; theoretical, computational and experimental neuroscience, consciousness studies
87
Moreno, Jonathan University of Pennsylvania
History of science and medicine, psychology, bioethics, served on several NAS
and DoD studies regarding military hardware, autonomy, ethics
Mossbridge, Julia Northwestern University and Institute of Noetic Sciences
(IONS)
Duality, consciousness, predictive anticipatory activity
Noë, Alva Professor of philosophy at the University of California, Berkeley;
member of the Institute for Cognitive and Brain Sciences and the Center for
New Media
Perception and consciousness, theory of art, phenomenology, extended mind
and embodiment
Presti, David University of California, Berkeley
Neurobiologist and cognitive scientist
Rensink, Ron University of British Columbia
Vision systems and computer science
Rosenthal, David Professor of Philosophy; Coordinator, Interdisciplinary
Concentration in Cognitive Science, CUNY
Philosophy of Mind, metaphysics
Rowe, Bill Formerly of Santa Cruz Institute for Particle Physics; consultant
to neuroscience companies, brain implants for preclinical studies
Authority on Julian Jaynes, interests in language acquisition and ontogeny of
consciousness
Schneider, Susan Dept. of Philosophy, Cognitive Science Program, University of Connecticut; Yale Interdisciplinary Center for Bioethics; Center of
Theological Inquiry, Princeton
Philosophy of Mind, ethics, neuroscience and AI, metaphysics
Small, Gary Professor of Psychiatry and Biobehavioral Sciences and ParlowSolomon Professor on Aging at the David Geffen School of Medicine at UCLA
Aging/Alzheimer’s Disease expert
Syverson, Paul Naval Research Laboratory
Mathematician and computer scientist
Sullins, John Sonoma State University Philosophy, AI ethics, intelligent
moral agents
88
Tononi, Guilio Professor, University of Wisconsin Madison; Center for Sleep
and Consciousness
Information theory of consciousness
Vallor, Shannon Santa Clara University
Philosophy of Science and Technology; ethics of emerging technologies
Zebrowski, Robin Beloit College
Interdisciplinary: cognitive science, philosophy, psychology, and computer science. Human concepts of embodiment, with applications to artificial intelligence and robotics. Metaphor theory.
SRI Attendees and Relevant Interests
Lincoln, Patrick Director, Computer Science Lab
[Principal Investigator] Formal methods and logic, computational biology, interest in human consciousness
Sahner, David Senior Clinical Director, Computer Science Lab
[Technical Lead] Artificial intelligence, philosophy of mind, neuroscience and
cognition, medicine, and contemporary physics
Murray, John Program Director, Computer Science Lab
[Technical Co-lead] Neuroergonomics, interactive collaboration in real and virtual environments, cognitive engineering, and cyber-research ethics
Adkins, Boone Software Engineer, Advanced Technology and Systems Development
Atrash, Amin Software Engineer, Advanced Technology and Systems Development
robotics, autism
Connolly, Christopher Principal Scientist, Computer Science Lab
artificial intelligence, computing in mathematics, engineering, medicine, and
neuroscience; neurogram deconvolution
Israel, David Principal Scientist Emeritus, Artificial Intelligence Lab
AI, natural language representation and reasoning
Keifer, Kellie Senior Operations Director, Computer Science Lab
Kirkwood, Gordon Research Engineer, Advanced Technology and Systems
Development
89
Myers, Karen Program Director, Artificial Intelligence Lab
Poggio, Andy Senior Computer Scientist, Computer Science Lab
computing in natural sciences, mathematics, and a clinical and biological context
Rushby, John Principal Scientist, Computer Science Lab
humans and safety-critical systems, theory of mind
Sanchez, Daniel Cognitive Scientist, Computer Science Lab applied cognitive neuroscience, human learning and memory, human-intuitive machines
Shankar, Natarajan Principal Scientist, Computer Science Lab
fundamental mathematics, foundational logic, software verification
Willoughby, Adrian Cognitive Scientist, Computer Science Lab
Williams, Damien Scientific Conference Assistant, Computer Science Lab
90 |