A list of resources explaining core machine learning concepts.
- Transformers
- Transformer Explainer. Cho et. al.
- Formal Algorithms for Transformers. Phuong & Hutter, Jul 2022.
- The Illustrated Transformer. Jay Alammar, Jun 2018.
- Attention is all you need. Łukasz Kaiser, Oct 2017.
- The Transformer Family Version 2.0. Lilian Weng, Jan 2023.
- LLM Visualization. Brendan Bycroft, Jan 2024.
- Graph Neural Networks: Theoretical Foundations of Graph Neural Networks. Petar Veličković, Feb 2021.
- Gaussian Processes: A Visual Exploration of Gaussian Processes. Görtler, Kehlbeck & Deussen, Apr 2019.
- Momentum: Why Momentum Really Works. Gabriel Goh, Apr 2017.
- LSTMs: Understanding LSTM Networks. Chris Olah, Aug 2015.
- Numerical Sampling: Sampling: Two Basic Algorithms. Gregory Gundersen,Sep 2019.
- Graph Neural Networks: Theoretical Foundations of Graph Neural Networks. Petar Veličković, Feb 2021.
- Game Theory: The Evolution of Trust, Jul 2017
- Diffusion
- Diffusion is spectral autoregression. Sander Dieleman, Sep 2024.
- A Mathematical Framework for Transformer Circuits, Anthropic.
- In context learning and Induction Heads, Anthropic.
- Bayesian Deep Learning: NeurIPS '17 keynote. Yee Whye Teh, Dec 2017.
- A Mechanistic Interpretability Analysis of Grokking. Nanda & Lieberum, Aug 2022.
- https://sebastianraschka.com/blog/2023/llm-reading-list.html
- Recent Advances in Foundation Models
- Geodesics, Data Manifolds, and Metric Tensors ... oh my!