AI by Hand: Demystifying Deep Learning with Interactive Workbooks
Prof. Tom Yeh's Substack, AI by Hand, teaches the math, algorithms, and architectures of AI through hands-on, interactive lessons. With over 73,000 subscribers, it offers a library of workbooks and seminars covering topics from attention mechanisms and activation functions to fine-tuning and frontier models like Qwen and Gemma. The approach emphasizes understanding by doing, with visual tools like Matmul Flow and Self-Attention Flow.
Fine-tuning is how you turn a general-purpose pretrained model into something that actually does your task, and getting it right means knowing which…
- iamnotarobotman
This is also recommended reading if you want to learn more about building LLMs from scratch: See:
Train your own LLM - https://github.com/angelos-p/llm-from-scratch
HN Discussion - https://news.ycombinator.com/item?id=48017948
- rustyminnow
https://www.byhand.ai/p/library
> AI by Hand is the research publication of By Hand Research, founded by Prof. Tom Yeh. By Hand Research studies model interpretability and explainability at the math and algorithm level. Subscribers receive free new articles and join live seminars. Members get access to our full research library.
- slowin
I found Deep Learning by No Starch Press to be an excellent primer the foundation of AI: