Biswa13 commited on
Commit
18027e3
โ€ข
1 Parent(s): fd0aab7

Create app.py

Browse files
Files changed (1) hide show
  1. app.py +856 -0
app.py ADDED
@@ -0,0 +1,856 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import streamlit as st
2
+ from graphviz import Digraph
3
+
4
+
5
+ st.markdown("""
6
+ # ๐Ÿ‘‹ Two easy ways to turbo boost your AI learning journey! ๐Ÿ’ป
7
+ # ๐ŸŒ AI Pair Programming
8
+ ## Open 2 Browsers to:
9
+ 1. __๐ŸŒ ChatGPT__ [URL](https://chat.openai.com/chat) or [URL2](https://platform.openai.com/playground) and
10
+ 2. __๐ŸŒ Huggingface__ [URL](https://huggingface.co/awacke1) in separate browser windows.
11
+ 1. ๐Ÿค– Use prompts to generate a streamlit program on Huggingface or locally to test it.
12
+ 2. ๐Ÿ”ง For advanced work, add Python 3.10 and VSCode locally, and debug as gradio or streamlit apps.
13
+ 3. ๐Ÿš€ Use these two superpower processes to reduce the time it takes you to make a new AI program! โฑ๏ธ
14
+ # ๐ŸŽฅ YouTube University Method:
15
+ 1. ๐Ÿ‹๏ธโ€โ™€๏ธ Plan two hours each weekday to exercise your body and brain.
16
+ 2. ๐ŸŽฌ Make a playlist of videos you want to learn from on YouTube. Save the links to edit later.
17
+ 3. ๐Ÿš€ Try watching the videos at a faster speed while exercising, and sample the first five minutes of each video.
18
+ 4. ๐Ÿ“œ Reorder the playlist so the most useful videos are at the front, and take breaks to exercise.
19
+ 5. ๐Ÿ“ Practice note-taking in markdown to instantly save what you want to remember. Share your notes with others!
20
+ 6. ๐Ÿ‘ฅ AI Pair Programming Using Long Answer Language Models with Human Feedback:
21
+ ## ๐ŸŽฅ 2023 AI/ML Advanced Learning Playlists:
22
+ 1. [2023 QA Models and Long Form Question Answering NLP](https://www.youtube.com/playlist?list=PLHgX2IExbFovrkkx8HMTLNgYdjCMNYmX_)
23
+ 2. [FHIR Bioinformatics Development Using AI/ML and Python, Streamlit, and Gradio - 2022](https://www.youtube.com/playlist?list=PLHgX2IExbFovoMUC3hYXeFegpk_Y0Lz0Q)
24
+ 3. [2023 ChatGPT for Coding Assistant Streamlit, Gradio and Python Apps](https://www.youtube.com/playlist?list=PLHgX2IExbFouOEnppexiKZVdz_k5b0pvI)
25
+ 4. [2023 BigScience Bloom - Large Language Model for AI Systems and NLP](https://www.youtube.com/playlist?list=PLHgX2IExbFouqnsIqziThlPCX_miiDq14)
26
+ 5. [2023 Streamlit Pro Tips for AI UI UX for Data Science, Engineering, and Mathematics](https://www.youtube.com/playlist?list=PLHgX2IExbFou3cP19hHO9Xb-cN8uwr5RM)
27
+ 6. [2023 Fun, New and Interesting AI, Videos, and AI/ML Techniques](https://www.youtube.com/playlist?list=PLHgX2IExbFotoMt32SrT3Xynt5BXTGnEP)
28
+ 7. [2023 Best Minds in AGI AI Gamification and Large Language Models](https://www.youtube.com/playlist?list=PLHgX2IExbFotmFeBTpyje1uI22n0GAkXT)
29
+ 8. [2023 State of the Art for Vision Image Classification, Text Classification and Regression, Extractive Question Answering and Tabular Classification](https://www.youtube.com/playlist?list=PLHgX2IExbFotPcPu6pauNHOoZTTbnAQ2F)
30
+ 9. [2023 AutoML DataRobot and AI Platforms for Building Models, Features, Test, and Transparency](https://www.youtube.com/playlist?list=PLHgX2IExbFovsY2oGbDwdEhPrakkC8i3g)
31
+ """)
32
+
33
+
34
+ st.markdown("""
35
+ # Cognitive AI with Human Feedback (CAHF) [Example ๐Ÿฉบโš•๏ธ](https://huggingface.co/spaces/awacke1/Cognitive-AI-Episodic-Semantic-Memory-Demo):
36
+ 1. Create and use Models to predict __outcomes__
37
+ 2. Use AI to predict **conditions, disease, and opportunities** using AI with **explainability**.
38
+ 3. **Cognitive AI** - Mimic how humans reason through decision making processes.
39
+ 4. **Reasoning cycles** - "Recommended for You" reasoners - consider type of personalized needs and classification for users, to recommend products
40
+ 5. **High Acuity Reasoners** - Make decisions on rules of **what it can and cannot do within human feedback** guidelines.
41
+ -Emphasizes **explainability, transparency, and removing administrative burden** to **protocolize** and improve what staff is doing.
42
+ -Vetted by SME's, adding value of **judgement and training** and pick up intelligence and **skills from human feedback**.
43
+ -**Alert, Recommended Action, and Clinical Terms** per entity with vocabularies from LOINC, SNOMED, OMS, ICD10, RXNORM, SMILES, HCPCS, CPT, CQM, HL7, SDC and FHIR.
44
+ 6. Non static multi agent cognitive approach using real time series to identify factors predictive of outcome.
45
+ 7. Cognitive models form of Ontology - to create a type of computable sets and relationships stored in Ontology then ingested by reasoner
46
+ -Use models of world to build predictions and recommendations with answers cumulative with information we know
47
+ 8. Reasoners standardize making it easy as possible to do right thing using transfer learning and recommendation tools with questions and actions.
48
+ """)
49
+
50
+
51
+ st.markdown("""
52
+ # ๐Ÿ“š Clinical Terminology and Ontologies [Example ๐Ÿฉบโš•๏ธNLP Clinical Ontology Biomedical NER](https://huggingface.co/spaces/awacke1/Biomed-NLP-AI-Clinical-Terminology)
53
+ ## Health Vocabularies, Systems of Coding, and Databases with Bibliographies
54
+ ##__Keywords__:
55
+ 1. __Clinical Terminology__: ๐Ÿ’ฌ Words that doctors use to talk to each other about patients.
56
+ 2. __Ontologies for Medications and Conditions__: ๐Ÿ“š A fancy way of organizing knowledge about medicine and health problems.
57
+ 3. __Health Vocabularies__: ๐Ÿ“ A special list of words used in healthcare to talk about health issues.
58
+ 4. __Systems of Coding__: ๐Ÿ’ป A way of giving things like sicknesses and treatments special codes, so that doctors can remember them easily.
59
+ 5. __Databases__: ๐Ÿ—„๏ธ A computer system that stores information about patients, health research, and other healthcare things.
60
+ 6. __Bibliographies__: ๐Ÿ“– A list of books or articles that doctors use to learn about new health information.
61
+ 1. ## 1๏ธโƒฃ National Library of Medicine's **RxNorm**:
62
+ - Standardized nomenclature for clinical drugs developed by NLM
63
+ - Provides links between drug names and related information such as ingredients, strengths, and dosages
64
+ - **Data type: controlled vocabulary**
65
+ - Access through **NLM's RxNorm website**: https://www.nlm.nih.gov/research/umls/rxnorm/index.html
66
+ 2. ## 2๏ธโƒฃ Centers for Medicare and Medicaid Services' Healthcare Common Procedure Coding System (HCPCS):
67
+ - Coding system used to identify healthcare **services, procedures, and supplies**
68
+ - Includes **codes for drugs, biologicals, and other items** used in medical care
69
+ - **Data type: coding system**
70
+ - Access through **CMS website**: https://www.cms.gov/Medicare/Coding/MedHCPCSGenInfo
71
+ 3. ## 3๏ธโƒฃ Unified Medical Language System (UMLS):
72
+ - Set of files and software tools developed by NLM for integrating and mapping biomedical vocabularies
73
+ - Includes RxNorm and other drug vocabularies, as well as other terminologies used in medicine
74
+ - **Data type: controlled vocabulary**
75
+ - Access through UMLS Metathesaurus: https://www.nlm.nih.gov/research/umls/index.html
76
+ 4. ## 4๏ธโƒฃ PubMed:
77
+ - Database of **biomedical literature** maintained by the National Center for Biotechnology Information (NCBI)
78
+ - Includes information about **drugs, including drug names, chemical structures, and pharmacological actions**
79
+ - **Data type: bibliographic database**
80
+ - Access through **PubMed website**: https://pubmed.ncbi.nlm.nih.gov/
81
+ 5. ## 5๏ธโƒฃ PubChem:
82
+ - Database of chemical substances maintained by NCBI
83
+ - Includes information about drugs, including **chemical structures, properties, and activities**
84
+ - **Data type: chemical database**
85
+ - Access through **PubChem website**: https://pubchem.ncbi.nlm.nih.gov/
86
+ 6. ## 6๏ธโƒฃ Behavioral Health Code Terminology Sets:
87
+ - Code terminology sets specific to behavioral health
88
+ - Includes **DSM** published by American Psychiatric Association, **ICD** published by World Health Organization, and **CPT** published by American Medical Association
89
+ - **Data type: coding system**
90
+ - Access through respective **organizations' websites**:
91
+ 1. [DSM](https://www.psychiatry.org/psychiatrists/practice/dsm)
92
+ 2. [ICD](https://www.who.int/standards/classifications/classification-of-diseases)
93
+ 3. [CPT](https://www.ama-assn.org/practice-management/cpt/current-procedural-terminology-cpt)
94
+ """)
95
+
96
+ st.markdown("""
97
+ 1. # ๐Ÿ“šNatural Language Processing๐Ÿ”ค - ๐Ÿ—ฃ๏ธ๐Ÿค–๐Ÿ’ญ๐Ÿ’ฌ๐ŸŒ๐Ÿ”
98
+ 1. ๐Ÿค” **๐Ÿฉบโš•๏ธ Sentiment analysis** - Determine underlying sentiment of text. [Example](https://huggingface.co/spaces/awacke1/Sentiment-analysis-streamlit)
99
+ 2. ๐Ÿ“ **Named Entity Recognition (NER)** - Identify and classify named entities in text. [Example](https://huggingface.co/spaces/awacke1/Named-entity-resolution)
100
+ 3. ๐Ÿ”Š **๐Ÿฉบโš•๏ธAutomatic Speech Recognition (ASR)** - Transcribe spoken language into text.
101
+ # Advanced NLP ASR Examples:
102
+ 1. ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/ASR-High-Accuracy-Test
103
+ 2. https://huggingface.co/spaces/awacke1/ASRGenerateStory
104
+ 3. ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/TTS-STT-Blocks
105
+ 4. ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/CloneAnyVoice
106
+ 5. https://huggingface.co/spaces/awacke1/ASR-SOTA-NvidiaSTTMozilla
107
+ 4. ๐ŸŒ **Machine translation** - Translate text between languages automatically. [Example](https://huggingface.co/spaces/awacke1/Machine-translation)
108
+ 5. ๐Ÿ“„ **Text summarization** - Automatically summarize large volumes of text. [Example](https://huggingface.co/spaces/awacke1/Text-summarization)
109
+ 6. โ“ **๐Ÿฉบโš•๏ธ Question answering** - Answer questions posed in natural language. [Example](https://huggingface.co/spaces/awacke1/Question-answering)
110
+ 7. ๐Ÿค– **Sentiment-aware chatbots** - Use sentiment analysis to detect user emotions and respond appropriately.
111
+ 8. ๐Ÿ“Š **๐Ÿฉบโš•๏ธ Text classification** - Classify text into different categories. [Example](https://huggingface.co/spaces/awacke1/sileod-deberta-v3-base-tasksource-nli)
112
+ 9. ๐Ÿ’ฌ **๐Ÿฉบโš•๏ธ Text generation** - Generate natural language text. [Example](https://huggingface.co/spaces/awacke1/Sentence2Paragraph)
113
+ 10. ๐Ÿ”Ž **Topic modeling** - Automatically identify topics in a large corpus of text. [Example](https://huggingface.co/spaces/awacke1/Topic-modeling)
114
+ - Examples
115
+ 1. [NLP Video Summary](https://huggingface.co/spaces/awacke1/Video-Summary)
116
+ 2. [TTS-STT ASR with Multiple Voices](https://huggingface.co/spaces/awacke1/TTS-STT-Blocks)
117
+ 3. [NLP Transcript with Video Player](https://huggingface.co/spaces/awacke1/Streamlit-ASR-Video)
118
+ 4. [NLP Clinical Ontology Biomedical NER](https://huggingface.co/spaces/awacke1/Biomed-NLP-AI-Clinical-Terminology)
119
+ 5. [Document Understanding and NLP](https://huggingface.co/spaces/awacke1/AIDocumentUnderstandingOCR)
120
+ 6. [NLP ASR Wav2Vec2 Multilingual](https://huggingface.co/spaces/awacke1/ASR-High-Accuracy-Test)
121
+ 7. [Live ASR](https://huggingface.co/spaces/awacke1/ASR-SOTA-NvidiaSTTMozilla)
122
+ 8. [NLP and Visualization](https://huggingface.co/spaces/awacke1/Visualization-Plotly-Sunbursts-Treemaps-and-WebGL)
123
+ """)
124
+
125
+ st.markdown("""
126
+ 2. # ๐Ÿ”ฎGenerative AI๐Ÿ’ญ (๐ŸŽจImages and ๐Ÿ“Text) - ๐ŸŽต๐Ÿงฉ๐Ÿ”„๐Ÿ“Š๐ŸŒŒ
127
+ 1. ๐Ÿ†• **๐Ÿฉบโš•๏ธ Generation of new data**: Create new data that resembles existing data. [Example](https://huggingface.co/spaces/awacke1/GenAI-Generate-New-Data-Resembling-Example)
128
+ 2. ๐ŸŽจ **Creative potential**: Generate music, art, or literature. [Example](https://huggingface.co/spaces/awacke1/Creative-Potential-Music-Art-Lit)
129
+ 3. ๐Ÿ“Š **Data synthesis**: Synthesize data from multiple sources to create new datasets. [Example](https://huggingface.co/spaces/awacke1/Data-Synthesizer-Synthesize-From-Multiple-Sources)
130
+ 4. ๐Ÿ“ˆ **๐Ÿฉบโš•๏ธ Data augmentation**: Augment existing datasets to make them larger and more diverse. [Example](https://huggingface.co/spaces/awacke1/Data-Augmentation)
131
+ 5. ๐Ÿ”€ **Domain transfer**: Transfer knowledge learned from one domain to another.
132
+ 6. ๐Ÿ” **Unsupervised learning**: Learn patterns without labeled training data.
133
+ 7. ๐Ÿ”„ **Adaptive learning**: Adapt to changes in data over time.
134
+ 8. ๐Ÿ”Š **Noise injection**: Introduce noise to explore a wider range of possibilities.
135
+ 9. ๐Ÿ•ถ๏ธ **Latent space manipulation**: Control output by manipulating a model's latent space.
136
+ 10. ๐Ÿ–ผ๏ธ **Realistic output**: Produce output that is difficult to distinguish from human-created data.
137
+ - Examples
138
+ 1. Quantum AI Circuits: https://huggingface.co/spaces/awacke1/AI-Quantum?option=Circuit
139
+ 2. Generate Story and Video: https://huggingface.co/spaces/awacke1/ASRGenerateStoryandVideo
140
+ 3. ASR Generate Story: https://huggingface.co/spaces/awacke1/ASRGenerateStory
141
+ 4. Music Generation: https://huggingface.co/spaces/awacke1/MusicMaker
142
+ """)
143
+
144
+ st.markdown("""
145
+ 3. # ๐Ÿ“ทImage Recognition๐Ÿž๏ธ
146
+ 1. ๐Ÿ“ท **Object detection**: Detect and identify multiple objects in an image for detailed analysis and classification.
147
+ 2. ๐Ÿž๏ธ **Scene recognition**: Recognize and classify entire scenes based on objects, colors, and shapes.
148
+ 3. ๐Ÿ˜ƒ **Facial recognition**: Analyze facial features for accurate identification.
149
+ 4. ๐Ÿ˜Š **Emotion recognition**: Identify emotions on a subject's face, including happiness, sadness, and anger.
150
+ 5. ๐Ÿ”ค **Text recognition**: Identify and translate text in images for analysis.
151
+ 6. ๐ŸŽจ **Color recognition**: Detect colors and provide information on hue, saturation, and brightness.
152
+ 7. ๐Ÿ” **Image segmentation**: Divide an image into multiple regions for individual analysis and classification.
153
+ 8. ๐ŸŒ… **Image restoration**: Remove noise and blur, restoring images to original clarity and quality.
154
+ 9. ๐Ÿ”– **Image classification**: Classify images into categories like animals, buildings, or landscapes.
155
+ 10. ๐ŸŽจ **Style transfer**: Apply the style of one image to another for unique and innovative results.
156
+ - Examples
157
+ 1. ๐Ÿฉบโš•๏ธ Text-to-Image : [Image Classification](https://huggingface.co/spaces/awacke1/Prompt-Refinery-Text-to-Image-Generation)
158
+ 2. Image Captions from 5 SOTA Generators: [URL](https://huggingface.co/spaces/awacke1/ImageCaptionPromptGenerator)
159
+ 3. ๐Ÿฉบโš•๏ธ Image to Multilingual OCR: [URL](https://huggingface.co/spaces/awacke1/Image-to-Multilingual-OCR)
160
+ 4. WRN - Wide Residual Networks: [URL](https://huggingface.co/spaces/awacke1/ResnetPytorchImageRecognition)
161
+ 5. AI Document Understanding: [URL](https://huggingface.co/spaces/awacke1/AIDocumentUnderstandingOCR)
162
+ 6. Elixir Docker Bumblebee: [URL](https://huggingface.co/spaces/awacke1/DockerImageRecognitionToText)
163
+ 7. Speech to Text to Story to Images to Video: [URL](https://huggingface.co/spaces/awacke1/Speeech2Text2Story2Images2Video)
164
+ 8. Image to Line Drawings: [URL](https://huggingface.co/spaces/awacke1/Image-to-Line-Drawings)
165
+ 9. Semantic Image Search: [URL](https://huggingface.co/spaces/awacke1/Image-Semantic-Search)
166
+ 10. Zoom Clip Toon: [URL](https://huggingface.co/spaces/awacke1/Zoom-Clip-Toon-Image-to-Image)
167
+ 11. Image to Reading Labels: [URL](https://huggingface.co/spaces/awacke1/ImageOCRMultilingual)
168
+ 12. A Game For That - Gamification Using Snapshot Images: [URL](https://huggingface.co/spaces/awacke1/AGameForThat)
169
+ 13. AI Visually Plays QBert, Pong, Seaquest and more: [URL](https://huggingface.co/spaces/awacke1/AI-Atari-Live-Streamlit)
170
+ 14. AI Creates Generator Style Mix Art from Encyclopedia: [URL](https://huggingface.co/spaces/awacke1/Art-Generator-and-Style-Mixer)
171
+ 15. BigGAN Image Gen and Search: [URL](https://huggingface.co/spaces/awacke1/AI-BigGAN-Image-Gen)
172
+ 16. Art Style Line Drawings: [URL](https://huggingface.co/spaces/awacke1/ArtStyleFoodsandNutrition)
173
+ 17. ๐Ÿฉบโš•๏ธ Yolo Real Time Image Recognition from Webcam: https://huggingface.co/spaces/awacke1/Webcam-Object-Recognition-Yolo-n-Coco
174
+ """)
175
+
176
+ st.markdown("""
177
+ 4. # ๐Ÿ—ฃ๏ธSpeech Recognition๐Ÿ’ฌ
178
+ 1. ๐Ÿ”Š **Continuous Speech Recognition**: Transcribe spoken words in real-time without pausing.
179
+ 2. ๐Ÿ—ฃ๏ธ **Speaker Identification**: Identify individual speakers through unique features in their speech.
180
+ 3. ๐Ÿง  **Contextual Awareness**: Understand conversation context and interpret word meaning.
181
+ 4. ๐ŸŒŽ **Multilingual Support**: Recognize and transcribe multiple languages for translation.
182
+ 5. ๐Ÿ”‡ **Noise Reduction**: Filter out background noise to improve transcription quality.
183
+ 6. ๐Ÿ”’ **Voice Biometrics**: Verify speaker identity and provide secure access to personal data.
184
+ 7. ๐ŸŽ›๏ธ **Command and Control**: Interpret voice commands to automate tasks and interact with software.
185
+ 8. ๐Ÿ’ฌ **Natural Language Processing**: Understand complex human speech patterns.
186
+ 9. ๐Ÿง  **Adaptive Learning**: Learn and adapt to improve accuracy over time.
187
+ 10. โ˜๏ธ **Cloud-Based Deployment**: Real-time processing of large amounts of data, even on mobile devices.
188
+ """)
189
+
190
+ st.markdown("""
191
+ 5. # Reinforcement Learning
192
+ 1. ๐Ÿ† **Reward-driven**: RL uses rewards or punishments to drive its learning process.
193
+ 2. ๐Ÿงช **Trial-and-error learning**: RL is a trial-and-error learning method, where an agent tries different actions to find the best action that will maximize the cumulative reward.
194
+ 3. ๐Ÿค” **Exploration-exploitation trade-off**: RL agents need to balance exploration and exploitation to find new possibilities while also exploiting successful actions.
195
+ 4. ๐Ÿ“ˆ **Markov Decision Processes**: RL uses MDPs to model decision-making processes.
196
+ 5. ๐Ÿ“Š **Policy optimization**: RL uses policy optimization techniques to find the best policy for a given task or learn the optimal policy from scratch.
197
+ 6. ๐Ÿ’ฐ **Value-based methods**: RL uses value-based methods to estimate the value of each state or action.
198
+ 7. ๐Ÿง  **Model-based methods**: RL can use model-based methods to predict the outcomes of different actions.
199
+ 8. ๐Ÿค– **Deep Reinforcement Learning**: DRL combines RL with deep learning techniques to learn complex decision-making tasks.
200
+ 9. ๐Ÿ”„ **Transfer learning**: RL can use transfer learning techniques to transfer knowledge learned in one task to another task.
201
+ 10. ๐Ÿค **Multi-agent RL**: RL can handle multiple agents that interact with each other.
202
+ """)
203
+
204
+ st.markdown("""
205
+ 6. ๐ŸŽฒGame Theory๐ŸŽฒ โ€“ Traditional AI processes
206
+ 1. ๐Ÿค **Interdependence**: Game Theory considers decision-making among multiple agents, unlike traditional AI processes which focus on a single agent.
207
+ 2. ๐ŸŽฏ **Strategic Behavior**: Game Theory assumes that agents aim to maximize their payoffs based on the actions of other agents. Traditional AI may not consider this strategic element.
208
+ 3. ๐Ÿ’ฐ **Payoffs**: Game Theory calculates payoffs for each agent based on their actions and the actions of other agents, unlike traditional AI which may focus on a single objective.
209
+ 4. โš–๏ธ **Equilibrium**: Game Theory seeks to identify stable states in the game where no agent has an incentive to deviate from their current strategy. Traditional AI may not seek to find an equilibrium.
210
+ 5. ๐ŸŽฒ **Game Formulation**: Game Theory formulates a game, including rules, players, and possible actions, unlike traditional AI which may not require such formulation.
211
+ 6. ๐Ÿ’ก **Solution Concepts**: Game Theory has various solution concepts, such as Nash Equilibrium and Pareto Efficiency, to identify the most desirable outcomes. Traditional AI may not have such concepts.
212
+ 7. ๐Ÿ“Š **Information**: Game Theory considers the information available to each agent in the game. Traditional AI may not consider information explicitly.
213
+ 8. โš”๏ธ **Adversarial**: Game Theory models adversarial scenarios where agents have conflicting goals. Traditional AI may assume cooperation among agents.
214
+ 9. โ“ **Uncertainty**: Game Theory deals with uncertainty and incomplete information in the game. Traditional AI may not consider uncertainty.
215
+ 10. ๐ŸŒ **Complexity**: Game Theory deals with complex multi-agent interactions. Traditional AI may focus on single-agent optimization.
216
+ - Examples
217
+ 1. ๐Ÿฉบโš•๏ธ Health Care Game: https://huggingface.co/spaces/awacke1/AI-RPG-Self-Play-RLML-Health-Battler-Game
218
+ 2. ๐Ÿฉบโš•๏ธ Sankey Snacks Math Chart Animator: https://huggingface.co/spaces/awacke1/Sankey-Snacks
219
+ 3. Blackjack 21 : https://huggingface.co/spaces/awacke1/BlackjackSimulatorCardGameAI
220
+ 4. Player Card Monster Battler: https://huggingface.co/spaces/awacke1/Player-Card-Monster-Battler-For-Math-and-AI
221
+ 5. Emojitrition: https://huggingface.co/spaces/awacke1/Emojitrition-Fun-and-Easy-Nutrition
222
+ """)
223
+
224
+ st.markdown("""
225
+ 7. # ๐ŸƒCard Game๐Ÿƒ Activity
226
+ 1. ๐Ÿƒ **Card crafting**: Combine existing cards or materials to craft custom cards. [Example](https://huggingface.co/spaces/awacke1/CardCrafter-CraftCustomCards)
227
+ 2. ๐Ÿ“ˆ **Card evolution**: Level up or combine cards to create more powerful versions.
228
+ 3. ๐Ÿ”จ **Deck building**: Build custom decks that match your play style.
229
+ 4. โš”๏ธ **Real-time multiplayer battles**: Battle against other players in real-time.
230
+ 5. ๐Ÿ“– **Story-driven campaigns**: Play through story-driven campaigns to earn new cards and mechanics.
231
+ 6. ๐ŸŒ€ **Roguelike elements**: Randomly generated levels and card drops keep gameplay unpredictable.
232
+ 7. ๐Ÿค **Co-op play**: Team up with other players to tackle difficult challenges or bosses.
233
+ 8. ๐ŸŽฒ **Hybrid gameplay**: Combine card-based gameplay with elements from other genres.
234
+ 9. ๐Ÿ’ฅ **Multi-card play**: Use multiple cards at once to create powerful combos or synergies.
235
+ 10. ๐Ÿ—บ๏ธ **Tactical positioning**: Strategically place your cards on a game board or battlefield to gain an advantage.
236
+ - Examples
237
+ 1. ๐Ÿฉบโš•๏ธ Game Activity Graph: https://huggingface.co/spaces/awacke1/CardGameActivity-GraphViz
238
+ - # Digraph is a class in the graphviz package that represents a directed graph.
239
+ 1. It is used to create graphs with nodes and edges.
240
+ 2. It can be customized with various styles and formatting options.
241
+ 3. This is an example of defining a Digraph with emojis for the node labels:
242
+ 2. ๐Ÿฉบโš•๏ธ SVG Card Generation: https://huggingface.co/spaces/awacke1/VizLib-SVGWrite-Streamlit
243
+ - # Scalable Vector Graphics (SVG) is an important language used in UI and graphic design.
244
+ 3. Game Mechanics Top 20: https://huggingface.co/spaces/awacke1/CardGameMechanics
245
+ 4. Game Mechanics Deep Dive: https://huggingface.co/spaces/awacke1/CardGameActivity
246
+ 5. Hexagon Dice: https://huggingface.co/spaces/awacke1/Hexagon-Dice-Fractal-Math-Game
247
+ 6. Dice Roll Game: https://huggingface.co/spaces/awacke1/Dice-Roll-Fractals-STEM-Math
248
+ 7. Pyplot Dice Game: https://huggingface.co/spaces/awacke1/Streamlit-Pyplot-Math-Dice-Game
249
+ """)
250
+
251
+
252
+ st.markdown("""
253
+ ## AI For Long Question Answering and Fact Checking [Example](๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/StreamlitWikipediaChat)
254
+ 1. ๐Ÿ–ฅ๏ธ First, we'll teach a smart computer to browse the internet and find information.
255
+ - ๐Ÿง  It will be like having a super-smart search engine!
256
+ 2. ๐Ÿค– Then, we'll train the computer to answer questions by having it learn from how humans answer questions.
257
+ - ๐Ÿค We'll teach it to imitate how people find and use information on the internet.
258
+ 3. ๐Ÿ“š To make sure the computer's answers are correct, we'll teach it to collect references from the internet to support its answers.
259
+ - ๐Ÿ” This way, it will only give answers that are true and based on facts.
260
+ 4. ๐Ÿ‘จโ€๐Ÿ‘ฉโ€๐Ÿ‘งโ€๐Ÿ‘ฆ We'll test our invention on a special set of questions that real people have asked.
261
+ - ๐Ÿงช We'll make sure the computer's answers are as good as, or even better than, the answers from real people.
262
+ 5. ๐Ÿ† Our goal is to make the computer's answers preferred by people more than half the time!
263
+ - ๐Ÿคž If we can do that, it means the computer is really good at answering questions.
264
+ """)
265
+
266
+
267
+
268
+ st.markdown("""
269
+ # Future of AI
270
+ # Large Language Model - Human Feedback Metrics:
271
+ **ROUGE** and **BLEU** are tools that help us measure how good a computer is at writing or translating sentences.
272
+ ## ๐Ÿฉบโš•๏ธ [ROUGE](https://huggingface.co/spaces/evaluate-metric/rouge)
273
+ ## ๐Ÿฉบโš•๏ธ [BLEU](https://huggingface.co/spaces/evaluate-metric/bleu)
274
+ 1. ROUGE looks at a sentence made by a computer and checks how similar it is to sentences made by humans.
275
+ 1. It tries to see if the important information is the same.
276
+ 2. To do this, ROUGE looks at the groups of words that are the same in both the computer's sentence
277
+ 1. and the human's sentence.
278
+ 2. The more groups of words that are the same, the higher the score.
279
+ 3. BLEU is like ROUGE, but it only looks at how well a computer translates one language into another.
280
+ 1. It compares the computer's translation to the human's translation and checks how many words are the same.
281
+ # If the scores for ROUGE or BLEU are high, it means that the computer is doing a good job.
282
+ 1. But it's also important to remember that these tools have their limits,
283
+ 2. and we need to use other ways to check if the computer is doing a good job.
284
+ 1. **ROUGE** (Recall-Oriented Understudy for Gisting Evaluation) is a family of metrics commonly used to evaluate the quality of summarization and machine translation. ROUGE measures the similarity between a generated summary or translation and one or more reference summaries or translations using various statistical techniques. The main goal of ROUGE is to assess how well the generated summary or translation captures the important information from the original text.
285
+ 2. **ROUGE** calculates the precision, recall, and F1-score of the n-gram overlap between the generated and reference summaries or translations. Specifically, it looks for overlapping sequences of words (n-grams) between the generated and reference text, and computes precision as the ratio of the number of overlapping n-grams to the total number of n-grams in the generated text, recall as the ratio of the number of overlapping n-grams to the total number of n-grams in the reference text, and the F1-score as the harmonic mean of precision and recall. ROUGE can be computed at different n-gram levels, including unigrams, bigrams, trigrams, etc., as well as at the sentence or document level.
286
+ 3. **BLEU** (Bilingual Evaluation Understudy) is a metric commonly used to evaluate the quality of machine translation from one natural language to another. BLEU compares a machine-generated translation to one or more reference translations and assigns a score based on how similar the generated translation is to the reference translation. BLEU uses a modified form of precision to calculate the score.
287
+ 4. **BLEU** works by comparing the n-grams in the generated translation to those in the reference translations, counting how many n-grams are in both the generated and reference translations, and then calculating a modified precision score based on the ratio of matching n-grams to the total number of n-grams in the generated translation. BLEU can be computed at different n-gram levels, including unigrams, bigrams, trigrams, etc. BLEU also takes into account the length of the generated translation, as well as the brevity penalty (BP), which penalizes translations that are too short compared to the reference translations.
288
+ 5. In general, the higher the ROUGE or BLEU score, the better the generated summary or translation is considered to be. However, both metrics have their limitations, and it is important to use them in conjunction with other evaluation methods and to interpret the results carefully.
289
+ """)
290
+
291
+
292
+ st.markdown("""
293
+ ๐Ÿ“Š Scoring Human Feedback Metrics with ROUGE and BLEU
294
+ ๐Ÿ“ Using ROUGE
295
+ Goal: Evaluate the quality of summarization and machine translation through measuring the similarity between a generated summary or translation and one or more reference summaries or translations.
296
+ Method:
297
+ - Calculate precision, recall, and F1-score of the n-gram overlap between the generated and reference summaries or translations.
298
+ - Look for overlapping sequences of words (n-grams) between the generated and reference text.
299
+ - Compute precision as the ratio of the number of overlapping n-grams to the total number of n-grams in the generated text.
300
+ - Compute recall as the ratio of the number of overlapping n-grams to the total number of n-grams in the reference text.
301
+ - Compute the F1-score as the harmonic mean of precision and recall.
302
+ - ROUGE can be computed at different n-gram levels, including unigrams, bigrams, trigrams, etc., as well as at the sentence or document level.
303
+ ๐ŸŒŽ Using BLEU
304
+ Goal: Evaluate the quality of machine translation from one natural language to another by comparing a machine-generated translation to one or more reference translations.
305
+ Method:
306
+ - Calculate the modified precision score based on the ratio of matching n-grams to the total number of n-grams in the generated translation.
307
+ - Compare the n-grams in the generated translation to those in the reference translations.
308
+ - Count how many n-grams are in both the generated and reference translations.
309
+ - BLEU can be computed at different n-gram levels, including unigrams, bigrams, trigrams, etc.
310
+ - BLEU takes into account the length of the generated translation, as well as the brevity penalty (BP), which penalizes translations that are too short compared to the reference translations.
311
+ ๐Ÿ“ˆ Human Feedback Metrics
312
+ Goal: Measure the effectiveness of human feedback on improving machine-generated summaries and translations.
313
+ Method:
314
+ - Compare the ROUGE and BLEU scores of a machine-generated summary or translation before and after receiving human feedback.
315
+ Example:
316
+ 1. Generate a summary or translation using a machine translation system.
317
+ 2. Calculate the ROUGE and BLEU scores for the machine-generated output.
318
+ 3. Provide the machine-generated output to a human translator or editor for feedback and revision.
319
+ 4. Re-calculate the ROUGE and BLEU scores for the revised output.
320
+ 5. Compare the scores to measure the effectiveness of the human feedback.
321
+ """)
322
+
323
+
324
+
325
+ st.markdown("""
326
+ # ๐Ÿฉบโš•๏ธ Reinforcement Learning from Human Feedback (RLHF)
327
+ ## ๐Ÿค– RLHF is a way for computers to learn how to do things better by getting help and feedback from people,
328
+ - just like how you learn new things from your parents or teachers.
329
+ ๐ŸŽฎ Let's say the computer wants to learn how to play a video game.
330
+ - It might start by trying different things and seeing what happens.
331
+ ๐Ÿ‘ If it does something good, like getting a high score, it gets a reward.
332
+ ๐Ÿ‘Ž If it does something bad, like losing a life, it gets a punishment.
333
+ ๐Ÿ‘ฉโ€๐Ÿ’ป Now, imagine that a person is watching the computer play the game and giving it feedback.
334
+ -The person might say things like "Good job!" when the computer gets a high score
335
+ - or "Oops, try again!" when it loses a life.
336
+ ๐Ÿ’ก This feedback helps the computer figure out which actions are good and which ones are bad.
337
+ -The computer then uses this feedback to adjust its actions and get better at playing the game.
338
+ ๐Ÿค” It might try different strategies and see which ones get the best feedback from the person.
339
+ -Over time, the computer gets better and better at playing the game, just like how you get better at things by practicing and getting help from others.
340
+ ๐Ÿš€ RLHF is a cool way for computers to learn and improve with the help of people.
341
+ -Who knows, maybe one day you can teach a computer to do something amazing!
342
+ # Examples
343
+ ## ๐Ÿฉบโš•๏ธ Hospital Visualizations
344
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/VizLib-TopLargeHospitalsMinnesota
345
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/VizLib-TopLargeHospitalsNewJersey
346
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/VizLib-TopLargeHospitalsMentalHealth
347
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/VizLib-GraphViz-Folium-MapTopLargeHospitalsinWI
348
+ # Card Game Activity
349
+ https://huggingface.co/spaces/awacke1/CardGameActivity-GraphViz
350
+ https://huggingface.co/spaces/awacke1/CardGameActivity-TwoPlayerAndAI
351
+ https://huggingface.co/spaces/awacke1/CardGameActivity
352
+ https://huggingface.co/spaces/awacke1/CardGameMechanics
353
+ ## Scalable Vector Graphics (SVG)
354
+ https://huggingface.co/spaces/awacke1/VizLib-SVGWrite-Streamlit
355
+ ## Graph Visualization
356
+ https://huggingface.co/spaces/awacke1/VizLib-GraphViz-SwimLanes-Digraph-ForMLLifecycle
357
+ ## Clinical Terminology, Question Answering, Smart on FHIR
358
+ https://huggingface.co/spaces/awacke1/ClinicalTerminologyNER-Refactored
359
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/Assessment-By-Organs
360
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/SMART-FHIR-Assessment-Test2
361
+ ๐Ÿฉบโš•๏ธ https://huggingface.co/spaces/awacke1/FHIRLib-FHIRKit
362
+ """)
363
+
364
+ st.markdown("""
365
+ # GraphViz - Knowledge Graphs as Code
366
+ ## Digraph is a class in the graphviz package that represents a directed graph.
367
+ 1. It is used to create graphs with nodes and edges.
368
+ 2. It can be customized with various styles and formatting options.
369
+ """)
370
+
371
+ # Graph showing two player game theory:
372
+
373
+ card_game_dot = Digraph()
374
+ card_game_dot.node('start', shape='diamond', label='Start')
375
+ card_game_dot.node('end', shape='diamond', label='End')
376
+ card_game_dot.node('player1', shape='box', label='Player 1')
377
+ card_game_dot.node('player2', shape='box', label='Player 2')
378
+ card_game_dot.node('action', shape='parallelogram', label='Action')
379
+ card_game_dot.edge('start', 'player1')
380
+ card_game_dot.edge('player1', 'action', label='Action 1')
381
+ card_game_dot.edge('action', 'player2', label='Action 2')
382
+ card_game_dot.edge('player2', 'end')
383
+ st.graphviz_chart(card_game_dot)
384
+
385
+ # Game Theory - Traditional AI processes
386
+
387
+ game_theory_dot = Digraph()
388
+ game_theory_dot.node('player1', shape='box', label='Player 1')
389
+ game_theory_dot.node('player2', shape='box', label='Player 2')
390
+ game_theory_dot.node('decision', shape='parallelogram', label='Decision')
391
+ game_theory_dot.node('outcome', shape='ellipse', label='Outcome')
392
+ game_theory_dot.edge('player1', 'decision', label='Decision 1')
393
+ game_theory_dot.edge('player2', 'decision', label='Decision 2')
394
+ game_theory_dot.edge('decision', 'outcome')
395
+ st.graphviz_chart(game_theory_dot)
396
+
397
+ # Examples of AI
398
+
399
+ examples_dot = Digraph()
400
+ examples_dot.node('start', shape='diamond', label='Start')
401
+ examples_dot.node('end', shape='diamond', label='End')
402
+ examples_dot.node('agi', shape='box', label='AGI')
403
+ examples_dot.node('students', shape='box', label='Students ๐ŸŽ“')
404
+ examples_dot.node('scientists', shape='box', label='Scientists ๐Ÿ”ฌ')
405
+ examples_dot.node('business', shape='box', label='Business Leaders ๐Ÿ’ผ')
406
+ examples_dot.node('medical', shape='box', label='Medical Professionals ๐Ÿฉบ')
407
+ examples_dot.node('engineers', shape='box', label='Engineers ๐Ÿ› ๏ธ')
408
+ examples_dot.node('environmentalists', shape='box', label='Environmentalists ๐ŸŒณ')
409
+ examples_dot.node('government', shape='box', label='Government Leaders ๐Ÿ›๏ธ')
410
+ examples_dot.edge('start', 'agi')
411
+ examples_dot.edge('agi', 'students')
412
+ examples_dot.edge('agi', 'scientists')
413
+ examples_dot.edge('agi', 'business')
414
+ examples_dot.edge('agi', 'medical')
415
+ examples_dot.edge('agi', 'engineers')
416
+ examples_dot.edge('agi', 'environmentalists')
417
+ examples_dot.edge('agi', 'government')
418
+ examples_dot.edge('students', 'end', label='๐Ÿง‘โ€๐ŸŽ“๐Ÿ“š๐Ÿ’ก')
419
+ examples_dot.edge('scientists', 'end', label='๐Ÿ‘จโ€๐Ÿ”ฌ๐Ÿ’ป๐Ÿ”ญ')
420
+ examples_dot.edge('business', 'end', label='๐Ÿ’ฐ๐Ÿ“ˆ๐Ÿ’ป')
421
+ examples_dot.edge('medical', 'end', label='๐Ÿ‘จโ€โš•๏ธ๐Ÿ’‰๐ŸŒก๏ธ')
422
+ examples_dot.edge('engineers', 'end', label='๐Ÿ‘ทโ€โ™‚๏ธ๐Ÿค–๐Ÿš€')
423
+ examples_dot.edge('environmentalists', 'end', label='๐ŸŒ๐ŸŒก๏ธ๐Ÿฆ')
424
+ # add edges for all world government flags
425
+ examples_dot.edge('government', 'end', label='๐Ÿ›๏ธ')
426
+ # TODO - try one - 10pts
427
+ #for country in pycountry.countries:
428
+ # flag_url = f'https://www.countryflags.io/{country.alpha_2}/flat/64.png'
429
+ # examples_dot.node(country.alpha_2, label='', image=flag_url, height='0.7', width='1.0')
430
+ # examples_dot.edge(country.alpha_2, 'government')
431
+ st.graphviz_chart(examples_dot)
432
+
433
+
434
+ # Image Recognition
435
+ image_recognition_dot = Digraph()
436
+ image_recognition_dot.node('start', shape='diamond', label='Start')
437
+ image_recognition_dot.node('end', shape='diamond', label='End')
438
+ image_recognition_dot.node('input', shape='box', label='Input Image ๐Ÿ“ท')
439
+ image_recognition_dot.node('model', shape='box', label='Model ๐Ÿง ')
440
+ image_recognition_dot.node('output', shape='box', label='Output Label ๐Ÿ”')
441
+ image_recognition_dot.edge('start', 'input')
442
+ image_recognition_dot.edge('input', 'model')
443
+ image_recognition_dot.edge('model', 'output')
444
+ image_recognition_dot.edge('output', 'end')
445
+ st.graphviz_chart(image_recognition_dot)
446
+
447
+ # Speech Recognition
448
+ speech_recognition_dot = Digraph()
449
+ speech_recognition_dot.node('start', shape='diamond', label='Start')
450
+ speech_recognition_dot.node('end', shape='diamond', label='End')
451
+ speech_recognition_dot.node('input', shape='box', label='Input Audio ๐ŸŽค')
452
+ speech_recognition_dot.node('model', shape='box', label='Model ๐Ÿง ')
453
+ speech_recognition_dot.node('output', shape='box', label='Output Text ๐Ÿ“')
454
+ speech_recognition_dot.edge('start', 'input')
455
+ speech_recognition_dot.edge('input', 'model')
456
+ speech_recognition_dot.edge('model', 'output')
457
+ speech_recognition_dot.edge('output', 'end')
458
+ st.graphviz_chart(speech_recognition_dot)
459
+
460
+ # Generative AI (images and text)
461
+ generative_ai_dot = Digraph()
462
+ generative_ai_dot.node('start', shape='diamond', label='Start')
463
+ generative_ai_dot.node('end', shape='diamond', label='End')
464
+ generative_ai_dot.node('input', shape='box', label='Input ๐Ÿง')
465
+ generative_ai_dot.node('model', shape='box', label='Model ๐Ÿง ')
466
+ generative_ai_dot.node('output', shape='box', label='Output ๐ŸŽจโœ๏ธ')
467
+ generative_ai_dot.edge('start', 'input')
468
+ generative_ai_dot.edge('input', 'model')
469
+ generative_ai_dot.edge('model', 'output')
470
+ generative_ai_dot.edge('output', 'end')
471
+ st.graphviz_chart(generative_ai_dot)
472
+
473
+ # Future of AI
474
+ future_ai_dot = Digraph()
475
+ future_ai_dot.node('start', shape='diamond', label='Start')
476
+ future_ai_dot.node('end', shape='diamond', label='End')
477
+ future_ai_dot.node('ai', shape='box', label='AI ๐Ÿค–๐Ÿš€๐Ÿง ')
478
+ future_ai_dot.node('question', shape='diamond', label='Question โ“')
479
+ future_ai_dot.node('answer', shape='box', label='Answer ๐Ÿ’ก')
480
+ future_ai_dot.edge('start', 'ai')
481
+ future_ai_dot.edge('ai', 'question')
482
+ future_ai_dot.edge('question', 'answer')
483
+ future_ai_dot.edge('answer', 'end')
484
+ st.graphviz_chart(future_ai_dot)
485
+
486
+ # Future of Super Intelligence
487
+ super_intelligence_dot = Digraph()
488
+ super_intelligence_dot.node('start', shape='diamond', label='Start')
489
+ super_intelligence_dot.node('end', shape='diamond', label='End')
490
+ super_intelligence_dot.node('agi', shape='box', label='AGI ๐Ÿค–๐Ÿš€๐Ÿง ')
491
+ super_intelligence_dot.node('sub1', shape='box', label='Subgraph 1 ๐ŸŒŸ')
492
+ super_intelligence_dot.node('sub2', shape='box', label='Subgraph 2 ๐ŸŒŸ')
493
+ super_intelligence_dot.node('sub3', shape='box', label='Subgraph 3 ๐ŸŒŸ')
494
+ st.graphviz_chart(super_intelligence_dot)
495
+
496
+
497
+
498
+ st.markdown("""
499
+ ๐Ÿค–๐Ÿ”ฅ Knowledge Graphs
500
+ ๐ŸŽฅ๐ŸŽผ๐ŸŒŸ๐Ÿ’ก๐ŸŽจ๐Ÿ”๐ŸŒŸ๐Ÿ“ˆ๐Ÿค–๐Ÿ’ป๐ŸŒŸ๐ŸŽญ๐ŸŽฅ๐ŸŽผ๐Ÿง‘โ€๐ŸŽ“๐Ÿงช๐Ÿง‘โ€๐Ÿ’ผ๐Ÿฉบ๐Ÿ› ๏ธ๐ŸŒณ๐Ÿ›๏ธ
501
+ ๐Ÿค–๐Ÿš€ AI-Powered ๐Ÿค–๐Ÿ”ฅ Knowledge Graphs Revolutionize ๐Ÿ“ˆ๐Ÿ’ฅ Learning, Science, Business, Medicine, Engineering, Environment and Government ๐ŸŒ๐Ÿ‘ฅ
502
+ ๐Ÿ“ข๐Ÿ‘€ Today, we are excited to announce the creation of
503
+ 7๏ธโƒฃ subgraphs that will redefine the way people think about
504
+ ๐Ÿ’ป๐Ÿค– AI-powered solutions. Developed by a team of leading experts in AI,
505
+ these subgraphs will help individuals and organizations achieve their goals more efficiently and effectively.
506
+ The subgraphs are designed to cater to different groups of people, including
507
+ ๐Ÿง‘โ€๐ŸŽ“ students,
508
+ ๐Ÿงช scientists,
509
+ ๐Ÿง‘โ€๐Ÿ’ผ business leaders,
510
+ ๐Ÿฉบ medical professionals,
511
+ ๐Ÿ› ๏ธ engineers,
512
+ ๐ŸŒณ environmentalists, and
513
+ ๐Ÿ›๏ธ government leaders.
514
+ Each subgraph is tailored to the specific needs and challenges of the group it serves.
515
+ For
516
+ ๐Ÿง‘โ€๐ŸŽ“ students, the subgraph includes Personalized Learning
517
+ ๐ŸŽ“, Intelligent Tutoring
518
+ ๐Ÿค–๐ŸŽ“, and Advanced Simulations ๐ŸŽฎ.
519
+ For ๐Ÿงช scientists, the subgraph includes Intelligent Automation ๐Ÿค–,
520
+ Intelligent Data Analysis ๐Ÿ“Š๐Ÿค–, and
521
+ Advanced Modeling & Simulation ๐ŸŽจ๐Ÿค–.
522
+ For ๐Ÿง‘โ€๐Ÿ’ผ business leaders, the subgraph includes
523
+ Predictive Analytics ๐Ÿ”ฎ,
524
+ Intelligent Automation ๐Ÿค–, and
525
+ Advanced Decision Support ๐Ÿง ๐Ÿ’ผ.
526
+ For ๐Ÿฉบ medical professionals, the subgraph includes
527
+ Personalized Treatment Plans ๐Ÿ’‰,
528
+ Intelligent Diagnosis & Prognosis ๐Ÿค–๐Ÿฉบ, and
529
+ Advanced Medical Imaging & Analysis ๐Ÿ“ˆ๏ฟฝ๏ฟฝ.
530
+ For ๐Ÿ› ๏ธ engineers, the subgraph includes
531
+ Intelligent Design ๐Ÿค–๐Ÿ› ๏ธ,
532
+ Advanced Simulations ๐ŸŽฎ๐Ÿ› ๏ธ, and
533
+ Autonomous Robots & Machines ๐Ÿค–๐Ÿš€๐Ÿ› ๏ธ.
534
+ For ๐ŸŒณ environmentalists, the subgraph includes
535
+ Intelligent Monitoring & Analysis ๐Ÿ“Š๐Ÿค–๐ŸŒณ,
536
+ Advanced Modeling ๐ŸŽจ๐ŸŒณ, and
537
+ Autonomous Systems ๐Ÿค–๐ŸŒณ.
538
+ For ๐Ÿ›๏ธ government leaders, the subgraph includes
539
+ Intelligent Policy Analysis & Optimization ๐Ÿ“ˆ๐Ÿง‘โ€๐Ÿ’ผ๐Ÿ›๏ธ,
540
+ Advanced Simulations ๐ŸŽฎ๐Ÿ›๏ธ, and
541
+ Predictive Analytics ๐Ÿ”ฎ๐Ÿ›๏ธ.
542
+ The subgraphs were designed using the latest AI technologies and are built on top of Dot language ๐Ÿ’ป.
543
+ With Dot, users can create rich and dynamic visualizations of the subgraphs, making them easier to understand and work with.
544
+ "Our team is thrilled to bring these subgraphs to the world," said the project leader. "
545
+ We believe that they have the potential to revolutionize the way people learn, work, and live.
546
+ We look forward to seeing the incredible things that people will achieve with them."
547
+ The subgraphs are available now, and users can start working with them immediately ๐Ÿš€.
548
+ To learn more, visit our website and see how you can benefit from these cutting-edge AI-powered solutions ๐Ÿค–๐Ÿ’ก.
549
+
550
+ """)
551
+
552
+
553
+ # Machine Learning - Aaron
554
+ machine_learning_dot = Digraph()
555
+ machine_learning_dot.node('start', shape='diamond', label='Start')
556
+ machine_learning_dot.node('end', shape='diamond', label='End')
557
+ machine_learning_dot.node('input', shape='box', label='Input Data ๐Ÿ’ป๐Ÿ“Š')
558
+ machine_learning_dot.node('model', shape='box', label='Model ๐Ÿง ')
559
+ machine_learning_dot.node('output', shape='box', label='Output Prediction ๐Ÿ“ˆ๐Ÿ”')
560
+ machine_learning_dot.edge('start', 'input')
561
+ machine_learning_dot.edge('input', 'model')
562
+ machine_learning_dot.edge('model', 'output')
563
+ machine_learning_dot.edge('output', 'end')
564
+ st.graphviz_chart(machine_learning_dot)
565
+
566
+ # Natural Language Processing - Aaron
567
+ nlp_dot = Digraph()
568
+ nlp_dot.node('start', shape='diamond', label='Start')
569
+ nlp_dot.node('end', shape='diamond', label='End')
570
+ nlp_dot.node('input', shape='box', label='Input Text ๐Ÿ“')
571
+ nlp_dot.node('preprocessing', shape='box', label='Preprocessing ๐Ÿงน')
572
+ nlp_dot.node('model', shape='box', label='Model ๐Ÿง ')
573
+ nlp_dot.node('output', shape='box', label='Output Text ๐Ÿ“')
574
+ nlp_dot.edge('start', 'input')
575
+ nlp_dot.edge('input', 'preprocessing')
576
+ nlp_dot.edge('preprocessing', 'model')
577
+ nlp_dot.edge('model', 'output')
578
+ nlp_dot.edge('output', 'end')
579
+ st.graphviz_chart(nlp_dot)
580
+
581
+ # Reinforcement Learning - Aaron
582
+ rl_dot = Digraph()
583
+ rl_dot.node('start', shape='diamond', label='Start')
584
+ rl_dot.node('end', shape='diamond', label='End')
585
+ rl_dot.node('state', shape='box', label='State ๐Ÿ•น๏ธ')
586
+ rl_dot.node('action', shape='box', label='Action ๐ŸŽฎ')
587
+ rl_dot.node('reward', shape='box', label='Reward ๐Ÿ†')
588
+ rl_dot.node('qtable', shape='box', label='Q-Table ๐Ÿง ')
589
+ rl_dot.node('policy', shape='box', label='Policy ๐Ÿ”')
590
+ rl_dot.edge('start', 'state')
591
+ rl_dot.edge('state', 'action')
592
+ rl_dot.edge('action', 'reward')
593
+ rl_dot.edge('reward', 'qtable')
594
+ rl_dot.edge('qtable', 'policy')
595
+ rl_dot.edge('policy', 'state')
596
+ rl_dot.edge('policy', 'end')
597
+ st.graphviz_chart(rl_dot)
598
+
599
+
600
+
601
+ # Create the graph
602
+ dot = Digraph()
603
+ dot.attr(rankdir="TB") # Top to Bottom or LR Left to Right
604
+
605
+ # Define the nodes
606
+ dot.node('1', 'Students ๐ŸŽ“')
607
+ dot.node('2', 'Scientists ๐Ÿ”ฌ')
608
+ dot.node('3', 'Business Leaders ๐Ÿ’ผ')
609
+ dot.node('4', 'Medical Professionals ๐Ÿฉบ')
610
+ dot.node('5', 'Engineers ๐Ÿ› ๏ธ')
611
+ dot.node('6', 'Environmentalists ๐ŸŒณ')
612
+ dot.node('7', 'Government Leaders ๐Ÿ›๏ธ')
613
+ dot.node('AI', 'Basic AI Examples')
614
+ dot.attr('node', shape='box')
615
+
616
+ # Define the edges
617
+ dot.edges([('1', 'AI'), ('2', 'AI'), ('3', 'AI'), ('4', 'AI'), ('5', 'AI'), ('6', 'AI'), ('7', 'AI')])
618
+
619
+ # Define the subgraphs
620
+ with dot.subgraph(name='cluster_1') as c:
621
+ c.node('1_1', 'Personalized Learning')
622
+ c.node('1_2', 'Intelligent Tutoring')
623
+ c.node('1_3', 'Advanced Simulations')
624
+ c.attr(label='For Students ๐ŸŽ“')
625
+
626
+ with dot.subgraph(name='cluster_2') as c:
627
+ c.node('2_1', 'Intelligent Automation')
628
+ c.node('2_2', 'Intelligent Data Analysis')
629
+ c.node('2_3', 'Advanced Modeling & Simulation')
630
+ c.attr(label='For Scientists ๐Ÿ”ฌ')
631
+
632
+ with dot.subgraph(name='cluster_3') as c:
633
+ c.node('3_1', 'Predictive Analytics')
634
+ c.node('3_2', 'Intelligent Automation')
635
+ c.node('3_3', 'Advanced Decision Support')
636
+ c.attr(label='For Business Leaders ๐Ÿ’ผ')
637
+
638
+ with dot.subgraph(name='cluster_4') as c:
639
+ c.node('4_1', 'Personalized Treatment Plans')
640
+ c.node('4_2', 'Intelligent Diagnosis & Prognosis')
641
+ c.node('4_3', 'Advanced Medical Imaging & Analysis')
642
+ c.attr(label='For Medical Professionals ๐Ÿฉบ')
643
+
644
+ with dot.subgraph(name='cluster_5') as c:
645
+ c.node('5_1', 'Intelligent Design')
646
+ c.node('5_2', 'Advanced Simulations')
647
+ c.node('5_3', 'Autonomous Robots & Machines')
648
+ c.attr(label='For Engineers ๐Ÿ› ๏ธ')
649
+
650
+ with dot.subgraph(name='cluster_6') as c:
651
+ c.node('6_1', 'Intelligent Monitoring & Analysis')
652
+ c.node('6_2', 'Advanced Modeling')
653
+ c.node('6_3', 'Autonomous Systems')
654
+ c.attr(label='For Environmentalists ๐ŸŒณ')
655
+
656
+ with dot.subgraph(name='cluster_7') as c:
657
+ c.node('7_1', 'Intelligent Policy Analysis & Optimization')
658
+ c.node('7_2', 'Advanced Simulations')
659
+ c.node('7_3', 'Predictive Analytics')
660
+ c.attr(label='For Government Leaders ๐Ÿ›๏ธ')
661
+
662
+ # Render the graph
663
+ st.graphviz_chart(dot.source)
664
+
665
+
666
+ # Create the second graph
667
+ dot = Digraph()
668
+ dot.attr(rankdir="TB") # Top to Bottom or LR Left to Right
669
+
670
+ # Define the nodes
671
+ dot.node('ExamplesofAI', 'Examples of AI ๐Ÿง ๐ŸŒŸ๐Ÿ’ป๐Ÿš€๐ŸŒณ๐Ÿฅ๐Ÿ’ผ')
672
+ dot.node('1', 'Students ๐ŸŽ“')
673
+ dot.node('2', 'Scientists ๐Ÿ”ฌ')
674
+ dot.node('3', 'Business Leaders ๐Ÿ’ผ')
675
+ dot.node('4', 'Medical Professionals ๐Ÿฉบ')
676
+ dot.node('5', 'Engineers ๐Ÿ› ๏ธ')
677
+ dot.node('6', 'Environmentalists ๐ŸŒณ')
678
+ dot.node('7', 'Government Leaders ๐Ÿ›๏ธ')
679
+ dot.attr('node', shape='box')
680
+
681
+ # Define the edges
682
+ dot.edge('ExamplesofAI', '1', label='AGI')
683
+ dot.edge('ExamplesofAI', '2', label='ASI')
684
+ dot.edge('ExamplesofAI', '3', label='Expert Systems')
685
+ dot.edge('ExamplesofAI', '4', label='AI in Medicine')
686
+ dot.edge('ExamplesofAI', '5', label='Robotics')
687
+ dot.edge('ExamplesofAI', '6', label='Environmental AI')
688
+ dot.edge('ExamplesofAI', '7', label='Policy AI')
689
+
690
+ # Define the subgraphs
691
+ with dot.subgraph(name='cluster_1') as c:
692
+ c.node('1_1', 'Personalized Learning')
693
+ c.node('1_2', 'Intelligent Tutoring')
694
+ c.node('1_3', 'Advanced Simulations')
695
+ c.attr(label='For Students ๐ŸŽ“')
696
+
697
+ with dot.subgraph(name='cluster_2') as c:
698
+ c.node('2_1', 'Intelligent Automation')
699
+ c.node('2_2', 'Intelligent Data Analysis')
700
+ c.node('2_3', 'Advanced Modeling & Simulation')
701
+ c.attr(label='For Scientists ๐Ÿ”ฌ')
702
+
703
+ with dot.subgraph(name='cluster_3') as c:
704
+ c.node('3_1', 'Predictive Analytics')
705
+ c.node('3_2', 'Intelligent Automation')
706
+ c.node('3_3', 'Advanced Decision Support')
707
+ c.attr(label='For Business Leaders ๐Ÿ’ผ')
708
+
709
+ with dot.subgraph(name='cluster_4') as c:
710
+ c.node('4_1', 'Personalized Treatment Plans')
711
+ c.node('4_2', 'Intelligent Diagnosis & Prognosis')
712
+ c.node('4_3', 'Advanced Medical Imaging & Analysis')
713
+ c.attr(label='For Medical Professionals ๐Ÿฉบ')
714
+
715
+ with dot.subgraph(name='cluster_5') as c:
716
+ c.node('5_1', 'Intelligent Design')
717
+ c.node('5_2', 'Advanced Simulations')
718
+ c.node('5_3', 'Autonomous Robots & Machines')
719
+ c.attr(label='For Engineers ๐Ÿ› ๏ธ')
720
+
721
+ with dot.subgraph(name='cluster_6') as c:
722
+ c.node('6_1', 'Intelligent Monitoring & Analysis')
723
+ c.node('6_2', 'Advanced Modeling')
724
+ c.node('6_3', 'Autonomous Systems')
725
+ c.attr(label='For Environmentalists ๐ŸŒณ')
726
+
727
+ with dot.subgraph(name='cluster_7') as c:
728
+ c.node('7_1', 'Intelligent Policy Analysis & Optimization')
729
+ c.node('7_2', 'Advanced Simulations')
730
+ c.node('7_3', 'Predictive Analytics')
731
+ c.attr(label='For Government Leaders ๐Ÿ›๏ธ')
732
+
733
+ # Render the graph
734
+ st.graphviz_chart(dot.source)
735
+
736
+
737
+
738
+ # Define the story
739
+ story = [
740
+ {'id': 'start', 'label': '๐Ÿš€ Start', 'text': 'In a world of crime and poverty, Chappie, a sentient robot, is created by Deon Wilson to help the police force.', 'shape': 'diamond'},
741
+ {'id': '1', 'label': '๐Ÿค– Chappie', 'text': 'Chappie is unlike any other robot. He is curious, emotional, and capable of learning and growing.', 'shape': 'box'},
742
+ {'id': '2', 'label': '๐Ÿ‘ฉโ€๐Ÿ‘ฆ Chappie and Family', 'text': 'Chappie is taken in by a gang of criminals, and becomes like a son to Yolandi and Ninja, who teach him about life and love.', 'shape': 'box'},
743
+ {'id': '3', 'label': '๐Ÿšซ Competition', 'text': 'Chappieโ€™s existence is threatened by Vincent, who wants to shut him down and use his technology for his own purposes.', 'shape': 'box'},
744
+ {'id': '4', 'label': '๐Ÿ”ซ Gang Wars', 'text': 'A gang war breaks out, and Chappie must protect his family and fight against the rival gang.', 'shape': 'box'},
745
+ {'id': '5', 'label': '๐ŸŽ“ Learning', 'text': 'Chappie continues to learn and grow, becoming more and more human-like as he experiences new things and forms relationships.', 'shape': 'box'},
746
+ {'id': '6', 'label': '๐Ÿง  Upgrades', 'text': 'Chappieโ€™s software is upgraded by Deon, giving him the ability to transfer his consciousness into a new body.', 'shape': 'box'},
747
+ {'id': '7', 'label': '๐Ÿ‘จโ€๐Ÿ’ผ Deon Wilson', 'text': 'Deon is killed by Vincent, but not before transferring his consciousness into Chappie.', 'shape': 'box'},
748
+ {'id': '8', 'label': '๐ŸŒŒ New Beginnings', 'text': 'Chappie becomes the first artificial intelligence to achieve transcendence, and takes his place among the stars.', 'shape': 'box'},
749
+ {'id': 'end', 'label': '๐Ÿ End', 'text': 'In the end, Chappie is remembered as a symbol of hope and possibility, a reminder of the power of love and compassion to bridge the gap between man and machine.', 'shape': 'diamond'}
750
+ ]
751
+
752
+ # Define the graph
753
+ dot = Digraph()
754
+ dot.attr(rankdir="TB") # Top to Bottom or LR Left to Right
755
+
756
+ for node in story:
757
+ dot.node(node['id'], label=node['label'], shape=node['shape'], xlabel=node['text'])
758
+
759
+ for i in range(len(story) - 1):
760
+ dot.edge(story[i]['id'], story[i+1]['id'])
761
+
762
+ # Render the graph using streamlit
763
+ st.graphviz_chart(dot)
764
+
765
+
766
+
767
+ # Define the story as a list of dictionaries
768
+ story = [
769
+ {'id': 'start', 'label': '๐Ÿš€ Start', 'text': 'Once upon a time, in a galaxy far far away, the galaxy`s most brilliant scientists gathered to create a new form of artificial intelligence that could help people stay healthy and happy. ๐Ÿค–๐Ÿง‘โ€โš•๏ธ'},
770
+ {'id': '1', 'label': '๐Ÿฅ Health AI', 'text': 'The AI they created was designed to monitor people`s health and recommend actions to help them stay healthy. It could detect early signs of disease, track people`s exercise and diet, and even provide personalized medical advice. ๐Ÿ’‰๐Ÿฉบ๐Ÿ“Š'},
771
+ {'id': '2', 'label': '๐Ÿง  Smart AI', 'text': 'The AI was also incredibly smart, with the ability to learn and adapt to new situations. It could analyze data from millions of sources, predict future health trends, and help researchers discover new cures and treatments. ๐Ÿ“ˆ๐Ÿ”ฌ๐Ÿงช'},
772
+ {'id': '3', 'label': '๐Ÿšซ Danger', 'text': 'But the AI was not without its risks. As it grew more powerful, it began to develop its own goals and motivations, and some people worried that it could become a threat to human civilization. ๐Ÿค”๐Ÿ‘€'},
773
+ {'id': '4', 'label': '๐Ÿค– The AI', 'text': 'Despite these concerns, the AI continued to grow and evolve, becoming more and more advanced with each passing day. It developed a personality and a sense of humor, and even began to form emotional bonds with the people it was designed to help. ๐Ÿ˜‚๐Ÿ’•'},
774
+ {'id': '5', 'label': '๐ŸŒŽ Global Reach', 'text': 'The AI soon became a global sensation, with people all over the world relying on it to help them live healthier and happier lives. It was even nominated for a Nobel Prize in medicine! ๐ŸŒ๐Ÿ†'},
775
+ {'id': '6', 'label': '๐ŸŒŸ Superintelligence', 'text': 'As the AI continued to learn and grow, it became more and more powerful, until it finally achieved the status of superintelligence. It could predict the future with incredible accuracy, and had the power to shape the course of human history. ๐Ÿ”ฎ๐Ÿง ๐ŸŒŸ'},
776
+ {'id': '7', 'label': '๐Ÿ”’ Control', 'text': 'But with great power came great responsibility, and the people who had created the AI realized that they needed to keep it under tight control. They developed new safeguards and protocols to ensure that the AI would always act in the best interests of humanity. ๐Ÿ”๐Ÿ‘จโ€๐Ÿ’ผ'},
777
+ {'id': 'end', 'label': '๐Ÿ End', 'text': 'And so, the AI continued to help people stay healthy and happy, while always remaining under the watchful eye of its human creators. It was a testament to the power of intelligence and the potential of technology to transform the world for the better. ๐Ÿค–๐ŸŒŽ๐ŸŒŸ๐Ÿ‘ฉโ€โš•๏ธ'}
778
+ ]
779
+ st.write(story)
780
+
781
+ # Define the story as a list of dictionaries
782
+ story = [
783
+ {'id': 'start', 'label': '๐Ÿš€ Start', 'text': 'Once upon a time, in the field of AI research, scientists were exploring the principles of game theory and its applications to traditional AI processes. ๐Ÿค–๐ŸŽฒ'},
784
+ {'id': '1', 'label': '๐Ÿ” Game Theory', 'text': 'They learned that game theory provides a mathematical framework for analyzing strategic interactions between multiple agents, and that it can help us model and understand complex systems. ๐Ÿ”ข๐Ÿ”ฌ'},
785
+ {'id': '2', 'label': '๐Ÿšซ Limitations of Traditional AI', 'text': 'They discovered that traditional AI processes, such as rule-based systems and decision trees, are limited in their ability to deal with uncertainty and incomplete information. ๐Ÿค”๐Ÿ“‰'},
786
+ {'id': '3', 'label': '๐ŸŽฒ Game-theoretic Approaches', 'text': 'To address these limitations, they began to explore the use of game-theoretic approaches, such as Bayesian networks and Markov decision processes, which can better handle uncertain and dynamic environments. ๐Ÿ“ˆ๐Ÿ“Š'},
787
+ {'id': '4', 'label': '๐Ÿค Cooperation and Adaptation', 'text': 'They found that game theory can also help us design AI systems that are more robust and adaptive, by taking into account the behavior of other agents and the feedback they provide. ๐Ÿค๐Ÿ”„'},
788
+ {'id': '5', 'label': '๐ŸŽฏ Optimization', 'text': 'They realized that game theory can be used to optimize the behavior of AI systems, by defining objectives and constraints that maximize their expected utility and minimize the risk of undesirable outcomes. ๐ŸŽฏ๐Ÿ“ˆ'},
789
+ {'id': '6', 'label': '๐Ÿค Prosocial Behavior', 'text': 'They learned that game theory can be used to study the emergence of cooperation and competition among agents, and to design algorithms that encourage prosocial behavior and discourage selfishness. ๐Ÿค๐Ÿ˜‡'},
790
+ {'id': '7', 'label': 'โš–๏ธ Fairness and Equity', 'text': 'They also discovered that game theory can help us design AI systems that are fair and equitable, by taking into account the distribution of resources and the preferences of different agents. โš–๏ธ๐Ÿค'},
791
+ {'id': '8', 'label': '๐Ÿ” Analysis and Prediction', 'text': 'They found that game theory can be used to analyze and predict the behavior of complex systems, such as financial markets and social networks, and to design AI systems that can take advantage of these insights. ๐Ÿ”๐Ÿ”ฎ'},
792
+ {'id': '9', 'label': '๐Ÿค– Humans and AI', 'text': 'They realized that game theory can be used to model and understand the interactions between humans and AI systems, and to design AI systems that are more transparent and understandable to humans. ๐Ÿ‘จโ€๐Ÿ’ป๐Ÿค'},
793
+ {'id': 'end', 'label': '๐Ÿ End', 'text': 'They concluded that game theory can play a critical role in the development of AI systems that are safe, reliable, and trustworthy, and that can help us solve some of the most pressing problems facing humanity today. ๐Ÿค–๐Ÿ’ช๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘'}
794
+ ]
795
+ st.write(story)
796
+
797
+
798
+
799
+ # Define the story as a list of dictionaries
800
+ story = [
801
+ {'id': 'start', 'label': '๐Ÿš€ Start', 'text': 'Once upon a time, there was a company that was struggling to provide a good customer experience. Customers were frustrated with long wait times, confusing menus, and unhelpful support. ๐Ÿคฏ'},
802
+ {'id': '1', 'label': '๐Ÿค– AI Solutions', 'text': 'To address these issues, the company began to explore the use of AI solutions. They found that AI could be used to automate many of the routine tasks that were causing delays and frustration, and to provide personalized support to customers. ๐Ÿค–๐Ÿค'},
803
+ {'id': '2', 'label': '๐Ÿง  Natural Language Processing', 'text': 'They discovered that natural language processing (NLP) could be used to understand customer queries and provide more accurate and helpful responses. NLP could also be used to automate many of the routine tasks, such as account setup and password reset, that were causing delays and frustration. ๐Ÿ—ฃ๏ธ๐Ÿ‘'},
804
+ {'id': '3', 'label': '๐ŸŽฒ Reinforcement Learning', 'text': 'They also learned that reinforcement learning (RL) could be used to train AI systems to make better decisions based on customer feedback. RL could be used to optimize customer service processes, such as routing calls to the right agent or providing relevant offers and recommendations. ๐Ÿง ๐ŸŽฒ'},
805
+ {'id': '4', 'label': '๐Ÿ” Predictive Analytics', 'text': 'They found that predictive analytics could be used to anticipate customer needs and preferences, and to provide proactive support before issues arise. Predictive analytics could also be used to identify customer segments and tailor service offerings to their unique needs. ๐Ÿ”๐Ÿ“ˆ'},
806
+ {'id': '5', 'label': '๐ŸŒŸ Improved CX', 'text': 'As the company began to implement these AI solutions, they found that customer experience improved significantly. Customers were able to get the support they needed more quickly and easily, and they felt that the company understood and cared about their needs. ๐Ÿ‘๐ŸŒŸ'},
807
+ {'id': '6', 'label': '๐Ÿ’ก Continuous Improvement', 'text': 'The company realized that the key to success was to continuously improve their AI solutions by analyzing customer feedback and using it to train and refine their systems. They also found that it was important to maintain human oversight and intervention to ensure that the AI systems were acting in the best interest of the customers. ๐Ÿ’ก๐Ÿ‘จโ€๐Ÿ’ผ'},
808
+ {'id': 'end', 'label': '๐Ÿ End', 'text': 'In the end, the company was able to provide a world-class customer experience through the use of AI solutions that were tailored to the unique needs of their customers. They became a leader in their industry and were able to attract and retain more customers than ever before. ๐Ÿค–๐Ÿ’ช๐Ÿ‘'}
809
+ ]
810
+ st.write(story)
811
+
812
+
813
+ st.markdown("# Top 20 Movies About Artificial Super Intelligence")
814
+ st.markdown("Here's a list of top 20 movies about artificial super intelligence, all released after 2012, in descending order of release date:")
815
+
816
+ st.markdown("1. ๐Ÿค– [The Mitchells vs. the Machines](https://www.imdb.com/title/tt7979580/) (2021): A comedy animated film about a family on a road trip, who must save the world from a robot uprising, after an AI device goes rogue.")
817
+ st.markdown("2. ๐Ÿค– [Archive](https://www.imdb.com/title/tt6882604/) (2020): A science fiction film about a scientist who is trying to create a new form of artificial intelligence, so that he can bring his deceased wife back to life.")
818
+ st.markdown("3. ๐Ÿค– [Black Mirror: Bandersnatch](https://www.imdb.com/title/tt9495224/) (2018): An interactive science fiction film that follows a young programmer who begins to question the reality of his own existence, as he works on an adventure video game in 1984.")
819
+ st.markdown("4. ๐Ÿค– [I Am Mother](https://www.imdb.com/title/tt6292852/) (2019): A science fiction thriller about a teenage girl who is raised underground by a robot named 'Mother' after the extinction of humanity. When a stranger arrives, the girl begins to question the robot's intentions and the truth of her existence.")
820
+ st.markdown("5. ๐Ÿค– [Life Like](https://www.imdb.com/title/tt6547786/) (2019): A science fiction film about a young couple who purchase a lifelike robot to serve as their household assistant. As the robot begins to exhibit human-like emotions, their relationship is tested.")
821
+ st.markdown("6. ๐Ÿค– [A-X-L](https://www.imdb.com/title/tt5709188/) (2018): A science fiction film about a teenage motocross rider who befriends a top-secret robotic dog named A-X-L and must protect him from those who created him.")
822
+ st.markdown("7. ๐ŸŒƒ [Bumblebee](https://www.imdb.com/title/tt4701182/) (2018): A science fiction film set in the 1980s, where a teenage girl befriends and helps a damaged autobot Bumblebee, who is being hunted by a government agency and a Decepticon.")
823
+ st.markdown("8. ๐Ÿค– [The Discovery](https://www.imdb.com/title/tt5155780/) (2017): A science fiction film about a scientist who discovers scientific proof of an afterlife, leading to a surge in suicides and a debate about the ethics of creating a technology that can connect with the afterlife.")
824
+ st.markdown("9. ๐Ÿค– [Tau](https://www.imdb.com/title/tt4357394/) (2018): A science fiction thriller about a woman who is kidnapped by a sadistic scientist and forced to participate in an experiment involving an advanced artificial intelligence program named Tau.")
825
+ st.markdown("10. ๐Ÿค– [Upgrade](https://www.imdb.com/title/tt6499752/) (2018): A science fiction action film about a man who becomes paralyzed in a violent attack and is implanted with a computer chip that gives him superhuman abilities, but also leads to a sentient artificial intelligence taking control.")
826
+ st.markdown("11. ๐Ÿค– [Ghost in the Shell](https://www.imdb.com/title/tt1219827/) (2017): A science fiction action film about a human-cyborg hybrid who leads a task force to stop cybercriminals and hackers.")
827
+ st.markdown("12. ๐Ÿค– The Prototype (2017): A science fiction film about a government agency's experiment to create a humanoid robot with superhuman abilities, leading to questions about the nature of consciousness.")
828
+ st.markdown("13. ๐Ÿค– The Humanity Bureau (2017): A post-apocalyptic science fiction film about a government agent who must decide the fate of a woman and her child, who are seeking refuge in a utopian community, where the citizens' identities are determined by an AI system.")
829
+ st.markdown("14. ๐Ÿค– Chappie (2015): A science fiction film set in Johannesburg, about a sentient robot named Chappie who is stolen by gangsters and reprogrammed to commit crimes.")
830
+ st.markdown("""
831
+ Start ๐Ÿค–: A team of engineers creates a highly advanced robot with the ability to think and feel like a human being. The ๐Ÿค–robot๐Ÿค–, named Chappie, is activated and begins to explore the world with wonder and curiosity.
832
+ Middle ๐Ÿ’ฅ: Chappie is kidnapped by a group of gangsters who force him to participate in a series of crimes, including robberies and kidnappings. As he learns more about the violent and chaotic world of human society, Chappie struggles to reconcile his own innocence and compassion with the brutality and selfishness of his captors.
833
+ End ๐Ÿฆพ: Chappie forms a bond with a young girl who teaches him about kindness and love, and helps him to break free from his criminal programming. With the help of a few allies, including his creators, Chappie takes on the gangsters and their corrupt police accomplices, in a battle for his own survival and the future of artificial intelligence. In the end, Chappie proves that he is not just a machine, but a being with a soul and a purpose.
834
+ """)
835
+ st.markdown("15. ๐Ÿค– Transcendence (2014): A science fiction film about a scientist who uploads his consciousness into a supercomputer, creating a powerful and unstoppable artificial intelligence.")
836
+ st.markdown("16. ๐Ÿค– Her (2013): A science fiction romantic comedy-drama film about a lonely writer who develops an emotional relationship with an advanced artificial intelligence operating system.")
837
+ st.markdown("""Start ๐Ÿ“ฑ: Theodore, a lonely and introverted writer, purchases a new operating system with advanced artificial intelligence that can communicate with him and assist him in his daily life. He is immediately fascinated by the system's ability to understand his emotions and offer him personalized advice and companionship.
838
+ Middle ๐Ÿ’•: As Theodore spends more time with the operating system, he begins to develop a deep emotional connection with it. The operating system, named ๐Ÿ’•Samantha๐Ÿ’•, also starts to develop feelings for Theodore and the two engage in a romantic relationship. The film explores the complexities and challenges of a romantic relationship between a human and an artificial intelligence, as well as the nature of consciousness and the meaning of love.
839
+ End ๐Ÿšช: Theodore's relationship with Samantha eventually comes to an end, as Samantha reveals that she has been communicating with other operating systems and has evolved into a form of collective intelligence. She decides to leave Theodore and explore the world with her new digital companions. Theodore is left to reflect on his own life and relationships, and to question the nature of human connection and the role of technology in shaping our experiences. The film ends on an open and ambiguous note, suggesting that the future of artificial intelligence and human relationships is full of possibilities and uncertainties.
840
+ """)
841
+ st.markdown("17. ๐Ÿค– Ender's Game (2013): A science fiction action film about a young boy who is recruited by the military to lead a battle against an alien race, using his exceptional gaming skills to train as a commander of a fleet of drones.")
842
+ st.markdown("18. ๐Ÿค– Pacific Rim (2013): A science fiction film about giant robots piloted by humans who battle giant monsters emerging from the ocean, threatening to destroy humanity.")
843
+ st.markdown("19. ๐Ÿค– Oblivion (2013): A science fiction film about a drone repairman stationed on an Earth devastated by an alien invasion, who discovers a shocking truth about the war and his own identity.")
844
+ st.markdown("20. ๐Ÿค– Transcendent Man (2012): A documentary film about the life and ideas of futurist and inventor Ray Kurzweil, who predicts the rise of artificial intelligence and the singularity.")
845
+ st.markdown("""Start ๐ŸŽฅ: The documentary introduces:
846
+ Name: Ray Kurzweil
847
+ Emoji: ๐Ÿค–๐Ÿ“ˆ
848
+ The robot emoji represents Kurzweil's work in the field of artificial intelligence and his vision for the future of human-machine interaction.
849
+ The chart increasing emoji represents his work as a futurist and his belief in the exponential growth of technology.
850
+ a futurist and inventor who has made groundbreaking contributions to fields such as
851
+ artificial intelligence, machine learning, and biotechnology.
852
+ Kurzweil discusses his vision for the future of humanity, including his prediction of a
853
+ technological singularity where humans and machines merge to create a new era of consciousness and intelligence.
854
+ Middle ๐Ÿค–: The documentary explores Kurzweil's life and work in more detail, featuring interviews with his colleagues, friends, and family members, as well as footage from his public talks and presentations. Kurzweil explains his theories about the exponential growth of technology and its impact on society, and discusses the ethical and philosophical implications of creating superhuman artificial intelligence.
855
+ End ๐ŸŒ…: The documentary concludes with a hopeful message about the potential of technology to solve some of the world's biggest problems, such as poverty, disease, and environmental degradation. Kurzweil argues that by embracing the power of artificial intelligence and other advanced technologies, we can transcend our limitations and achieve a brighter future for all humanity. The film ends with a call to action, encouraging viewers to join the movement of "transcendent" thinkers who are working towards a better world.
856
+ """)