// the take
A set of PDF cheatsheets covering the syllabus of Stanford's CS229 machine learning course — supervised learning, unsupervised learning, deep learning, and general tips/tricks, plus math refreshers on probability and linear algebra. Good for someone who took an ML course once and needs a fast reference for formulas and definitions, not for someone learning the material from scratch.
The content is dense and well organized by topic instead of being one giant dump — you can grab just the deep learning sheet without wading through everything else. The 'super cheatsheet' that merges all of them into one document is a nice touch for exam-style review. Translated into a dozen languages by community contributors, which is unusual reach for a personal project. The math refreshers (algebra/calculus, probability/stats) are a genuinely useful inclusion most ML cheatsheet repos skip.
It's PDFs, not text or markdown — you can't grep it, diff it, or easily pull a formula into your own notes without retyping it. No code, no worked examples, no exercises, so it's only useful if you already understand the concepts and need a memory jog, not for learning them. Last updated in 2020, so there's nothing on transformers, LLMs, or anything past classic supervised/unsupervised ML — it's frozen at a 2017-era course syllabus. No sources or derivations for the formulas, so if something looks off you have no way to check it against the original math.
We read the README, the directory tree and a key source file in September 2026. Nobody pays to be listed. How we judge →