A self-paced companion to Stanford's CME 295. Nine lectures take you from word vectors and attention all the way to reasoning agents — with the original videos, distilled notes, and the math that makes it click.
CME 295 traces the evolution of NLP, the core components of the Transformer, and how they scale into the large language models behind today's AI — blending theory with practical engineering. This hub reorganizes the public material into a clean, self-paced path.
Hover or tap any word to see how strongly it attends to every other word — the single operation at the heart of every Transformer.
Each lecture pairs the original Stanford recording with distilled notes, key formulas and takeaways. Click any card to dive in.
The original course is taught by the Amidi brothers, well known for the CS 229 cheatsheets that have helped millions of learners.
Fridays 3:30–5:20pm · Thornton 110 · Autumn 2025. This is an independent study hub, not affiliated with or endorsed by Stanford.
Pair this hub with the official material from the course authors.
Start with Lecture 1 and build your way up to reasoning agents. Your progress is saved automatically in your browser.
Enter the learning hub