Difference between revisions of "Machine Learning"

From David Vernon's Wiki
Jump to: navigation, search
(Foundation Models: Large Language Models & Multimodal Models)
Line 51: Line 51:
  
 
== Foundation Models: Large Language Models & Multimodal Models ==
 
== Foundation Models: Large Language Models & Multimodal Models ==
(Also see [[#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[#Limitations_of_AI|Limitations of AI]])
+
(Also see [[Robotics#Vision-Language-Action_Models|Vision-Language-Action Models]] and [[Artificial_Intelligence#Limitations_of_AI|Limitations of AI]])
  
[[https://eng.bigai.ai/ Beijing Institute for General Artificial Intelligence (BIGAI)] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" '''but not based on foundation models'''; <BR>
+
[[https://eng.bigai.ai/ Beijing Institute for General Artificial Intelligence (BIGAI)]] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" '''but not based on foundation models'''; <BR>
 
see also this insightful [https://www.theguardian.com/news/ng-interactive/2025/sep/16/song-chun-zhu-why-one-of-the-worlds-most-brilliant-ai-scientists-left-the-us-for-china article] about Song-Chun Zhu, the director of BIGAI, and his vision of the future of AI <BR>
 
see also this insightful [https://www.theguardian.com/news/ng-interactive/2025/sep/16/song-chun-zhu-why-one-of-the-worlds-most-brilliant-ai-scientists-left-the-us-for-china article] about Song-Chun Zhu, the director of BIGAI, and his vision of the future of AI <BR>
 
[https://arxiv.org/abs/2507.02092 Energy-Based Transformers are Scalable Learners and Thinkers] arXiv:2507.02092 <BR>
 
[https://arxiv.org/abs/2507.02092 Energy-Based Transformers are Scalable Learners and Thinkers] arXiv:2507.02092 <BR>

Revision as of 11:44, 20 August 2026

(Also see Artificial Intelligence and Robotics)

Bayesian Approaches

A Gentle Introduction to Bayesian Belief Networks

Books and Resources

Data Science and Machine Learning; free book to download
Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Hugging Face "The platform where the machine learning community collaborates on models, datasets, and applications"
Model-based Machine Learning, co-authored by Chris Bishop, and the related Infer.NET framework running Bayesian inference in graphical models
Model-based Machine Learning Companion Paper, C. M. Bishop, Phil. Trans. R. Soc. A 2013 371: 20120222; see Section 4. for an overview of probabilistic graphical models.
Deep Learning for Computer Vision with Python; great book and software, including a fully-configured virtual machine.

Comparisons

Classifier Comparison with instructive visualization
Computer Scientist Explains Machine Learning in 5 Levels of Difficulty
Neural Network Zoo from Fjodor van Veen, The Asimov Institute
Neural Network Zoo Prequel: Cells and Layers with more detail on how each cell type works

Datasets

Hugging Face "The platform where the machine learning community collaborates on models, datasets, and applications"
Kaggle Facial Expression Recognition dataset FER13

Deep Learning

Deep Learning overview
Neural Networks and Deep Learning
On the Origin of Deep Learning Haohan Wang and Bhiksha Raj
The original paper on the CNN by Yann LeCun, Leon Bottio, Yoshua Bengio, and Patrick Haffner

Environments

Colab from Google
Hugging Face "The platform where the machine learning community collaborates on models, datasets, and applications"
Using Keras and TensorFlow for Anomaly Detection (including the use of LSTM)

Ethical Issues

Deep fakes: one element of the dark side of AI and ML
The rise of the deepfake and the threat to democracy
The Tank Story

Gaussian Processes

Gaussian processes - Visual exploration of Gaussian processes
Gaussian processes - Interactive Gaussian process visualization
Gaussian processes - Gaussian Processes for Machine Learning (Rasmussen and Williams, 2006)
Gaussian processes - The Kernel Cookbook: Advice on Covariance functions
Gaussian processes - An intuitive guide to Gaussian processes
Gaussian processes - An Intuitive Tutorial to Gaussian Processes Regression (Wang, 2022)
Gaussian processes - Introduction to Gaussian Processes Video Lecture (Nando de Freitas, 2013)

Generative Adversarial Networks

GAN Series; comprehensive overview of Generative Adversarial Networks

Foundation Models: Large Language Models & Multimodal Models

(Also see Vision-Language-Action Models and Limitations of AI)

[Beijing Institute for General Artificial Intelligence (BIGAI)] "Pursuing a Unified Theory of Artificial Intelligence to Create General Intelligent Agents for Lifting Humanity" but not based on foundation models;
see also this insightful article about Song-Chun Zhu, the director of BIGAI, and his vision of the future of AI
Energy-Based Transformers are Scalable Learners and Thinkers arXiv:2507.02092
A robot wrote this entire article. Are you scared yet, human? GPT-3
How Trustworthy Are Large Language Models Like GPT? Stanford University Human-Centered Artificial Intelligence
Music publishers sue Amazon-backed AI company over song lyrics
Sarah Silverman sues OpenAI and Meta claiming AI training infringed copyright
TechScape: why you shouldn’t worry about sentient AI … yet
Meta steps up AI battle with OpenAI and Google with release of Llama 3
DALL·E 3 Generative AI image creation from OpenAI
Large Language Models explained briefly by Grant Sanderson, 3Blue1Brown
Stable Diffusion Generative AI image creation from Stability AI
Midjourney Generative AI image creation from from Midjourney Inc.
GPT-4 and ChatGPT from OpenAI
Llama 3 from Meta
Gemini (formerly known as BARD) from Google
LaMDA and the Sentient AI Trap
Collaborative AI Arena Benchmarking collaborative capabilities of AI in the wild
TrueReason AI Tutor Demo
Three Things to Know About Prompting LLMs
AI Prompt Engineering is Dead Long live AI prompt engineering (IEEE Spectrum)
What is In-context Learning, and how does it work: The Beginner’s Guide
What Is Retrieval-Augmented Generation, aka RAG? a blog by Nvidia; here is how Chat LangChain from LangChain explains it using Claude 3.5 Haiku, GPT4.1 Mini and Gemini 2.0 Flash
Methods for adapting large language models from Meta
Molmo Multimodal Open Language Model built by Ai2
On the Opportunities and Risks of Foundation Models arXiv article
New.jpg What is a Mamba model?

Physics Informed Machine Learning

High Level Overview of AI and ML in Science and Engineering

Recurrent Neural Networks

Illustrated guide to LSTMs and GRUs: a step by step explanation
Introducing Deep Learning and Long Short-Term Memory Networks
The original paper on the LSTM by Sepp Hochreiter and Jurgen Schmidhuber
The Unreasonable Effectiveness of Recurrent Neural Networks a blog by Andrej Karpathy
Andrej Karpathy's Blog
Understanding LSTMs

Reinforcement Learning

A (Long) Peek into Reinforcement Learning
Learning to Optimize with Reinforcement Learning and learning to learn
Learning to Optimize

Robot Learning

Robot Learning a talk by Jan Peters
Human-Interactive Robot Learning a course developed in Micro Project TMP-038 as part of the HumanE-AI-Net Network of Excellence (click the Home text at the top-right of the page to access the slides)

Self-Supervised Learning

Self-supervised Learning Andrew Zisserman
Yann LeCun Cake Analogy 2.0; the slides from his ISCC talk are here and the video of the talk is here

Transformers

Energy Transformer NeurIPS 2023 (note: Energy Transformers are not the same as Energy-Based Transformers)
Energy-Based Transformers are Scalable Learners and Thinkers arXiv:2507.02092 (Note: Energy-Based Transformers are not the same as Energy Transformers)
Multimodal Perception and Interaction with Transformers HumanE-AI-Net Micro Project
Multimodal Perception and Interaction with Transformers Tutorial Presented at ACAI 2021
Multimodal Perception and Interaction with Transformers Research Tools
Multimodal Perception with Transformers Research Challenges and Data Sets
The Illustrated Transformer by Jay Alammar