👋 Hi there! Please go to Canvas for our official fall23 course website.
This here is a draft site currently under construction 🚧. (Bug reports very welcome though; thanks!)
Calendar
Rough semester calendar draft; dates/events are subject to change/update.
Module 1 - Intro and Review
- Sep/7
- Lecture 1 Intro
- Sep/7
-
- Homework 0 HW0 out
- Homework 0
- Sep/8
- Recitation 1 Background review
Module 2 - The Basics
- Sep/12
-
- Lecture 2 Supervised Learning, ERM
- Slides
[SSS] Chapter 1, 2, 3,
- Sep/14
-
- Lecture 3 Optimization, regularization
- Slides
[SSS] Chapter 12.1.1, 13.1, 13.2
- Sep/15
- Recitation 2
- Sep/19
-
- Lecture 4 Linear vs. nonlinear models, bias variance
- [B] Chapter 3, [SSS] Chapter 5, [HTF] Chapter 3
- Sep/21
-
- Lecture 5 Intro to PAC Learning
- [SSS] Chapter 1, 2, 3,
- Sep/22
- Holiday student holiday; no recitation
- Sep/26
-
- Lecture 6 On-line learning, regret
- [SSS] Chapter 21
- Sep/28
-
- Lecture 7 Decision problems, bandits
- [SB] Chapter 1, 2
- Sep/29
- Recitation 3
- Oct/03
- Oct/05
-
- Lecture 9 Robustness, stability, adversarial predictions
- [KM] tutorial
- Oct/06
- Recitation 4
- Add Date
- Oct/09
- Holiday indigenous peoples’ day holiday
- Oct/10
- Holiday student holiday; no lecture
- Oct/12
-
- Lecture 10 Uncertainty, conformal prediction
- [AB] tutorial
- Oct/13
- Recitation 5
- Oct/17
- Oct/19
- Exam 1 Walker
- Oct/20
- Recitation 6
Module 3 - Deep Dive
- Oct/24
- Oct/26
- Oct/27
- Recitation
- Oct/31
-
- Lecture 14 Deep generative models, VAEs
- [KW]
- Nov/02
- Nov/03
- Recitation
- Nov/07
- Nov/09
- Nov/10
- Holiday veterans day holiday; no recitation
- Nov/14
- Nov/16
- Nov/17
- Recitation
- Nov/21
- Lecture Few-shot learning, in-context learning
- Nov/22
- Drop Date
- Nov/23
- Holiday thanksgiving holiday; no lecture
- Nov/24
- Holiday thanksgiving holiday; no recitation
- Nov/28
- Lecture Self-supervised learning, masking, contrastive
- Nov/30
- Lecture Foundation models
- Dec/01
- Recitation
- Dec/05
- Lecture State-of-the-art LLMs
- Dec/07
- Exam 2 Walker
- Dec/08
- Recitation Project help
- Dec/12
-
- Lecture Some Recent trends/ applications
- Slides
Recommended Reading
All freely accessible (an MIT IP may be required):
- [B] Pattern Recognition and Machine Learning, Bishop; Springer, 2006.
- [HTF] The Elements of Statistical Learning, Hastie, Tibshirani, and Friedman; Springer, 2009.
- [SB]/[SSS] Understanding Machine Learning: From Theory to Algorithms, Shalev-Shwartz and Ben-David; Cambridge University Press, 2014.
- [SB] Reinforcement Learning: An Introduction, Sutton and Barton; The MIT Press, 2018.
- [JWHT] An Introduction to Statistical Learning, James, Witten, Hastie, and Tibshirani; Springer, 2013.