The centralized knowledge base for the Coordinated Systems Lab (CSL). This repository serves as the definitive jumping-off point for current and incoming lab members working across Machine Learning, Deep Learning, and Reinforcement Learning.
| What This IS | What This IS NOT |
|---|---|
| A curated launchpad: Papers, foundational textbooks, specific blogs, and YouTube playlists. | A data dump: A place to dump every paper you skimmed this week or links to generic "Intro to Python" courses. |
| Lab-vetted: Resources that align directly with CSL's research directions and core mathematical foundations. | A code repository: Active research code, datasets, or scratchpad scripts belong in project-specific repos. |
| An onboarding tool: A structured guide to help new members get up to speed with the lab's technical baseline. | A comprehensive encyclopedia: An exhaustive list of everything ever written about AI/ML. |
/foundations— Linear algebra, optimization, and probability resources essential for CSL./ML_Resources— Core ML paradigms, classical algorithms, and statistical learning theory, architectures, optimization techniques, frameworks./RL_Resources— MDPs, value-based/policy-gradient methods, and multi-agent RL.
We keep this repo high-signal. Before adding a link or paper:
- Is it foundational or state-of-the-art? Avoid redundant tutorials.
- Is it categorized correctly? Place it in the appropriate folder with a one-sentence summary of why it is valuable.
- Open a PR: Ensure your markdown formatting is clean before submitting.