| Week (Subject to change) |
Topics |
Homework |
Reading |
Special Events and Due Dates |
Slides & Lecture Notes |
| 1 (8/26+28+30) |
Introduction, class logistics, Review: linear algebra |
|
DL Ch. 1 & Ch. 2 |
|
Slides (1), (2) |
2 (9/4+6) |
Stochastic processes & probability, distributions, information theory |
|
DL Ch. 3, TEoSL Ch. 1
| HW #0 due 9/20 |
Slides (1), (2), (3) |
3 (9/9+11+13) |
Optimization, foundational principles of ML |
|
DL Ch. 4 & Ch. 5 |
|
Slides (1), (2), (3), (4) |
4 (9/16+18+20) |
Learning theory |
|
DL Ch. 5 |
|
Slides (1), (2), (3), (4) |
5 (9/23+25+27) |
Supervised learning: Linear regression, polynomial regression |
|
TEoSL Ch. 2.3, 3.1 |
HW #1 due X/XX |
Slides (1), (2), (3) |
6 (9/30, 10/2+4) |
Logistic regression (LR) and classification |
|
TEoSL Ch. 4.4 |
|
Slides (1), (2), (3) |
7 (10/9+11+13) |
Discriminative modeling with linear classifiers |
|
|
|
Slides (1), (2) |
8 (10/16+18+20) |
Unsupervised learning: dimensionality reduction PCA (Guest lec) |
|
|
|
Slides (1), (2) |
9 (10/23+25+27) |
Probabilistic graphical models (PGMs): naïve Bayes (NB) |
|
NB vs. LR (Ng & Jordan '01) |
|
Slides (1) |
12 (10/30, 11/1+3) |
Generative models/PGMs: Mixtures of Gaussians, clustering |
|
| |
Slides (1), (2), (3) |
11 (11/6+8+10) |
Clustering, decision trees, ensembling |
|
Random Forests (Breiman '01) |
|
Slides (1), (2), (3) |
13 (11/13+15+17) |
Artificial neural networks (ANNs), reverse-mode differentiation |
|
DL Ch. 6 |
|
(1), (2) |
12 (11/20) |
ANNs: tricks of the trade, variational generative modeling |
|
|
|
Slides (1) |
14 (11/27+29, 12/1) |
VAEs, violating i.i.d.: time-series |
|
DL Ch. 10 |
|
Slides (1), (2), (3) |
15 (12/4+6+8) |
ANNs: recurrence, uncertainty modeling (Guest lec) |
|
|
Final Exam/Project |
Slides (1), (2), (3) |
16 (12/13, 10:45am-1:15pm) |
Final Project Presentations |
|
|
| Slides due 12/13, 11:59pm |
| (Papers due 12/14, 8am) |
|
|
