Awesome Free University AI/ML Course Notes

Key Takeaways#

• Awesome Free University AI/ML Course Notes is a curated index of official, written machine-learning course notes.
• The list intentionally excludes slide decks, video-only classes, paywalled material, and unofficial mirrors.
• Current entries include notes from MIT, Harvard, Princeton, Stanford, UC Berkeley, Caltech, Cornell, Oxford, LMU Munich, KAIST, and USP.
• The repository is best used as a starting point for self-study when you want textbook-style prose from university courses.

What this resource is#

Awesome Free University AI/ML Course Notes is a focused GitHub resource for learners who want written AI and machine-learning course notes from universities. The repository is curated by Marcos Cruz and is positioned as a companion to Awesome Free AI Books. Its narrower goal is useful: find instructor-published course notes that are free, permanent, official, and detailed enough to work as a textbook substitute.

That strict scope makes the list more reliable than broad “AI course” link dumps. The README explains that an entry must be written prose notes, not just slides or recorded lectures. It must come from the professor, course, or department. It must be available without a login, institutional email address, or paywall. The list is short because many strong universities do not publish qualifying material, but that is the point: quality and traceability matter more than a huge catalog.

What is included#

The repository currently points to machine-learning notes from institutions such as MIT, Harvard, Princeton, Stanford, UC Berkeley, Caltech, Cornell, Oxford, LMU Munich, KAIST, and USP. The table format includes the university, course, instructor when available, and the official notes link. Examples include MIT 6.390 Introduction to Machine Learning, Harvard CS181, Princeton COS 324, Stanford CS229, UC Berkeley CS189/289A, Caltech CS156, and Cornell CS4780.

For a builder or student, this is useful because the notes are closer to durable references than social posts or short tutorials. You can use them to review fundamentals, compare how different schools explain the same topic, or build a self-study path before jumping into papers and implementation work.

How to use it#

Start by choosing one course whose level matches your background. If you are new to the topic, pick an introductory machine-learning course and read the notes in order instead of hopping across every link. Keep a notebook of definitions, assumptions, loss functions, and algorithms. Then implement small examples from scratch or connect each concept to a framework you already use.

More experienced builders can use the list differently. Compare multiple courses on the same topic when a concept does not click. For example, read one school’s explanation of linear models, another school’s treatment of kernel methods, and a third school’s approach to probabilistic modeling. The different notation and examples often make the idea easier to retain.

Contribution standard#

The contribution rules are also part of the value. New links should point to primary sources, one entry should be added per pull request, and the material must remain written, official, free, and permanent. The README also documents universities that were checked but did not have a qualifying entry. That transparency helps contributors avoid adding weaker links just to make the repository look larger.

Best fit#

Use this resource if you want university-quality AI and ML study material without relying on paid textbooks or video-heavy courses. It is especially useful for students, self-taught engineers, ML practitioners refreshing fundamentals, and founders who want to understand model concepts deeply enough to make better technical decisions. It is not a course platform, does not host the notes itself, and does not promise full coverage of every AI subfield. It is a clean index of high-signal written material.