These notes are a dedicated collection of condensed educational materials relating to machine learning (ML). I hope that eventually they will contain a comprehensive, rigorous overview of practical and theoretical concerns for machine learning, ultra-compacted (but with links everywhere for deep-diving!). The goal here isn't to fully recount all the notes, just to give a brief overview and index of existing work useful for a high-level view of a topic.
- Probability theory (formal preferred; elementary required)
- Linear algebra
- Theoretical Statistics (just check Sinho Chewi's Statistics 210A and 210B notes).
- Statistical learning theory
- Common models (and their considerations) for ERM-based supervised learning
- Bayesian-motivated unsupervised learning
- Deep Learning
- Optimization concerns
- RKHS and kernel methods overview
This repository contains copied copyrighted material with attribution (under fair use).