Machine Learning
31 Aug 2021
Machine learning is a deep and broad enough field that it could be its own college major. If I was designing a machine learning major, here are the core classes I would include. (This can also serve as a personal study guide.)
For some topics, I’ve linked to a set of class notes or textbook that I’ve used and enjoyed. I favor class notes wherever possible.
Let me know if I’m missing something! (or if you just love any of these topics!)
Core
Foundations
Reinforcement Learning 1
Theory
Systems
Applications
Background
Programming
- Python (with numpy)
Mathematics
Probability & Statistics
Multivariable Calculus
Enrichment
Mathematics
Optimization
Information Theory
Biology
Neuroscience
Cognitive Psychology 6
Electrical Engineering
- Signal Processing
Footnotes
Class notes I haven’t used, but that I’d recommend:
1: Check out Stanford’s CS 234 video lectures or David Silver (Deep Mind)’s course.
2: Check out Stanford’s STATS 214 class page for references to some good SLT resources. Percy Liang’s notes, in particular, look good.
3: Check out Stefano Ermon’s (rather concise) notes.
4: Check out Stanford’s CS 131 syllabus and lecture notes.
5: Check out Stanford’s CS 224N syllabus and video lectures.
6: I can’t miss an opportunity to shill Steven Pinker. Check out his PSY 101 videos.
Read More
- 2022 Job Search (21 Jun 2022)
- 2021 Books (01 Jan 2022)
- Regret Minimization (08 Sep 2021)
- Required Reading (16 Jul 2021)
- Revolutions (14 Oct 2017)
- On Computer Science (15 Sep 2017)
- Samvit's Guide to the World Wide Web (28 Aug 2017)
- How to Pick Your Next Gig: Evaluating Startups - Part II (14 Aug 2017)
- How to Pick Your Next Gig: Evaluating Startups - Part I (14 Aug 2017)
- A Brief Primer: Stochastic Gradient Descent (20 Jul 2017)
- Why Parallelism? An Example from Deep Reinforcement Learning (06 Jul 2017)