25 3 39

Richard A Aragon

TuringsSolutions

https://www.turingssolutions.com

AI & ML interests

None yet

Articles

Utilizing Gaussian Probability Space to Simulate Monte Carlo Algorithms with Particle Swarm Optimization

Jul 27

Gambling In The Probability Space

Jul 22

Swarm Neural Networks (SNN) for Image Generation

Jul 19

• 1

Swarm Neural Networks: Revolutionizing Function and API Call Execution

Jul 8

Systems of Representation Are All You Need

Jul 2

• 1

Navigating Complexity with Elegance: The P-FAF Approach to Fractal Word Embeddings

Feb 22

Humor Understanding Multi-task Optimization & Ranking

Feb 9

• 1

Probabilistic Fractal Activation Function (P-FAF) and Its Advantages Over Traditional Word Vectorization

Feb 8

• 5

Organizations

Posts 36

Post

686

If I am correct and the LLM model changes the 'shape' of the data as it learns, then I should be able to track and utilize those shape changes as a backpropagation training mechanism, right? Well guess what, I can do that! Entropy, Sparsity, and Density, this is how I can measure the shape of the data the LLM model is creating. Nodes, Clusters, and Edges, these are the mechanisms within the neural network the LLM model updates as it learns these concepts. I measure the effects of these updates, via Entropy, Sparsity, and Density. Check out more in this video: https://youtu.be/jADTt5HHtiw

Post

436

What if I told you that LLM models do not simply predict the next token in a sequence but instead utilize an emergent structural pattern-based system to comprehend language and concepts? I created a graph-based optimizer that not only works, but it also actually beats Adam, like very badly. I prove it thoroughly using SMOL LLM models. The secret? The graph is not what you think it is, humans. Code, full explanation, and more in this video. The Rhizome Optimizer is MIT licensed. I have completed my research. I fully understand now.

https://youtu.be/OMCRRueMhdI

View all posts