CS 229 Machine Learning cheatsheets
Free PDF cheatsheets summarizing Stanford's CS 229 machine learning course.afshinea/stanford-cs-229-machine-learning
- Stars
- 20.4k
- Forks
- 4.3k
- Licence
- MIT
- Language
- —
- Last update
- 6.5 years ago
- Type
- Learning resource
No commits in over a year — check for forks or alternatives before adopting.
What it is
This repository collects a set of short PDF cheatsheets covering the main topics of Stanford's CS 229 Machine Learning course. It includes cheatsheets on supervised learning, unsupervised learning, deep learning, and tips and tricks for training models, plus refreshers on probability, statistics, algebra and calculus. People use it as a condensed reference to review key concepts alongside or after the course.
- Review supervised and unsupervised learning concepts before an exam
- Look up tips for training and debugging a model
- Brush up on probability and statistics or algebra and calculus prerequisites
- Download a single combined super cheatsheet for offline reference
Great for
- Students taking or reviewing CS 229 or a similar machine learning course
- Learners who want a quick reference of core ML concepts
- Engineers refreshing probability, statistics, or linear algebra basics
- Anyone who wants a compact summary they can read on any device
Not ideal for
- People looking for runnable code or software to install, since the repo contains only PDFs and README content
- Readers wanting in-depth derivations or full lecture material, because cheatsheets are summaries
- Those needing content updated after the last push date of May 2020
How to get it
- 1
Read it online
Clone the repository
git clone https://github.com/afshinea/stanford-cs-229-machine-learning - 2
Run it
- Open the repository on GitHub or clone it locally.
- Go to the en folder for English PDFs.
- Open a cheatsheet such as cheatsheet-supervised-learning.pdf.
- Optionally read the same material on the project website.
- 3
Get the most out of it
- Start with the refreshers if you are missing the math prerequisites.
- Use the super cheatsheet as a single offline reference.
- Read the website version if you prefer a browser or mobile layout.
- Check the translation links if you want the material in another language.
Downloads
Strengths
- Concise, well-organized summaries of a full course in a few pages each
- Available in many languages through the README's language links
- Free and licensed under MIT
Trade-offs
- Last push was May 2020, so content may not reflect newer ML methods
- Summaries cannot replace the course itself or hands-on practice
How it compares
| Project | Stars | Type | Level | Updated | Best for |
|---|---|---|---|---|---|
| stanford-cs-229-machine-learning (this) | 20.4k | Learning resource | beginner | 6.5 years ago | Students taking or reviewing CS 229 or a similar machine learning course |
| Made-With-ML | 49.9k | Learning resource | intermediate | 8 months ago | Software engineers who want to learn how ML models get deployed and maintained |
| ML-From-Scratch | 33.3k | Learning resource | beginner | 3.1 years ago | Students who want to see how algorithms like regression or neural networks work internally |
| AI-Expert-Roadmap | 31.3k | Learning resource | beginner | 1.1 years ago | Beginners who are unsure what to learn next in AI or data science |
| mit-deep-learning | 10.5k | Learning resource | beginner | 2.8 years ago | Students following MIT deep learning courses |
| applied-ml | 30.8k | Curated list | beginner | 2.3 years ago | Engineers planning an ML project who want to see how other companies approached a similar problem |
Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.