A degree's worth of ML lectures, minus the tuition

What it does

This is a classic “awesome list” that catalogs freely available machine learning and AI courses taught by top-tier universities and research labs like Stanford, Berkeley, DeepMind, and MIT. Each entry links to full video lecture playlists plus course websites, notes, and assignments. The list splits cleanly into introductory material—expect linear algebra and calculus prerequisites—and advanced topics like meta-learning, unsupervised deep learning, and the geometry of neural nets.

The interesting bit

The curation is the product. The README acts like a syllabus compiler for a self-directed graduate degree, and the descriptions distinguish between Andrew Ng’s mathematical CS229 and Columbia’s code-heavy applied alternative—evidence that the curation goes beyond copy-pasting YouTube titles.

Key highlights

• Organized into introductory and advanced tracks, with prerequisites noted upfront.
• Covers the modern ML stack: CNNs, transformers, GNNs, reinforcement learning, NLP, and probabilistic graphical models.
• Includes niche topics like photogrammetry, mobile robotics, and data-centric AI alongside core deep learning canon.
• Every entry links to video playlists plus original course websites with lecture notes and assignments.
• Draws heavily from Stanford, Berkeley, DeepMind/UCL, and MIT.

Caveats

• Strictly a curated link directory: no code, no search, no progress tracking—just a well-organized README.
• Several spelling inconsistencies (“Carneggie Mellon,” “Institure for Advanced Study,” “Reinforcment”) suggest light-touch maintenance.

Verdict

Worth keeping handy if you’re self-studying AI from first principles. Skip it if you already have a graduate degree in the field or just want runnable code.