🌐 AI-ML Learning Resources

A curated library of the best free resources on the internet for learning AI / ML / DL — not a link dump. For each topic, a short shortlist of the best courses, videos, papers, articles, and books, chosen for authority and clarity (top institutions, researchers, and the people who explained it best), and free / open wherever possible.

The curation bar

• Authoritative — Stanford/MIT/DeepMind/Anthropic, seminal-paper authors, 3Blue1Brown, Karpathy, Olah, StatQuest… the best explainer, not the top SEO result.
• Free / open preferred (audit links, free books, open courses).
• ~2 per type — a couple of courses, videos, papers, articles, books. Curated, not exhaustive.
• Every entry says who made it and why it's the best.

Structure (one pattern, everywhere)

Each topic is a folder with a single README.md carrying YAML frontmatter (id, topic, level, prereqs) + curated sections (Courses / Videos / Papers / Articles / Books) + platform cross-links. This consistent, parseable format lets the library double as a dataset for the interview-prep project.

🗺️ Topics

Foundations

#	Topic	Level
00	Getting Started	beginner
01	Math & Programming Foundations — incl. full math curriculum	beginner
02	Data Handling & Feature Engineering	beginner

Core Machine Learning

#	Topic	Level
03	Supervised Learning	intermediate
04	Unsupervised Learning	intermediate
05	Deep Learning	intermediate

Domains & Modalities

#	Topic	Level
06	Natural Language Processing	intermediate
07	Computer Vision	intermediate
08	Reinforcement Learning	advanced

Generative AI & LLMs

#	Topic	Level
09	Large Language Models	advanced
10	Generative AI	advanced
11	RAG & LLM Applications	advanced
12	Agentic AI & Tool Use	advanced

Engineering & Production

#	Topic	Level
13	Tools & Frameworks	beginner
14	MLOps & Deployment	advanced

Advanced & Frontier

#	Topic	Level
15	Advanced Research Math	advanced
16	Neuroscience & Brain-Inspired AI	advanced
17	Frontier & Staying Current	advanced

Specializations (deep-dive curricula)

• Computer Vision math · Neuroscience & Brain-Inspired AI · Advanced Research Math — full what/why/resources curricula
• LLM Systems Engineering curriculum — 14-chapter inference-stack syllabus

🔗 Sibling projects

• AI-ML-intuition — deep concept pages (the why)
• AI-ML-problemsets — problems, labs & build projects (the practice)
• PyTorch-fundamental-notes — PyTorch mechanics