Curated notes, articles, and experiments on topics that interest me in machine learning.
Clean, practical, and citation-friendly.
This is a personal knowledge base for machine learning. I collect what I’m learning, distill it into concise guides, and keep references handy. Expect:
- 🧭 Clear, purpose-driven writeups
- 🧠 Practical patterns and diagrams-as-code
- 🔗 Citations and further reading
- 📚 Graph Theory & Machine Learning: docs/graph-theory-llms-agents.md
- Graphs as a native abstraction, knowledge representation, MCP, multi-agent systems, and inference-time compute.
- Articles in
docs/ - Links to talks, posts, and libraries I find useful
- Small experiments and patterns I want to reuse
It’s primarily for my own learning, but suggestions are welcome—open an issue or PR.