AI · Archive¶
About
Earlier resource collection, kept for reference rather than as a study list. Systematic content lives in the topic pages.
PART A: BASICS
This part serves as the foundation.
GET STARTED
HANDS-ON
HUGGING FACE 🏆PART B: ADVANCED TOPICS
This part is the advanced content.
ADVANCED TOPICS
Geometry, Representations & Generative Modeling
| Topic | First understand | Guided experiment |
|---|---|---|
| Overview and path | Representations, architectures and generation | One MIT course for diffusion and flow matching |
| Manifolds and latent spaces | Low-dimensional structure and geometry | G1 Swiss roll reduction |
| Diffusion models | Noise, denoising, scores and sampling | G2 2D denoising/generation |
| Flow matching | Probability paths, vector fields and ODEs | G3 transport and trajectories |
Read concepts first, then choose experiments. Start geometry with diagrams/CPU; use the same MIT 6.S184 notes, videos and labs for diffusion and flow matching. Topic pages connect to foundation models and embodied intelligence.
REINFORCEMENT LEARNING
-
李宏毅-Reinforcement Learning🎯🏆
Notes: In Chinese
Easy for beginners to understand.
-
Easy RL🎯✅🏆
Notes: In Chinese This project should be taken as the notes of 李宏毅-Reinforcement Learning.
-
Deep Reinforcement Learning: Fundamentals, Research, and Applications🎯🏆
-
UCL Course on RL🎯🏆
-
CS285: Deep Reinforcement Learning
-
Reinforcement Learning: An Introduction
-
Reinforcement Learning
**