| Week (Subject to change) |
Topics |
Homework |
Reading |
Special Events and Due Dates |
Slides & Lecture Notes |
| 1 (1/12+14+16) |
Introduction, class logistics, Review: linear algebra |
|
DL Ch. 1 & Ch. 2 |
|
Slides (1), (2) |
2 (1/21+23) |
Linear algebra; basics of optimization (hill-climbing) |
|
DL Ch. 3, TEoSL Ch. 1
| |
Slides (1), (2) |
3 (1/26+28+30) |
Optimization; differential calculus |
|
DL Ch. 4 & Ch. 5 |
|
Slides (1),
(2)
|
| 4 (2/2+4+6) |
Probability theory, statistics (Guest lec; Viet Nguyen) |
|
DL Ch. 5 |
HW #0 due 2/17 |
Slides (1),
(2),
(3)
|
5 (2/9+11+13) |
Distributions, learning theory, non-parametrics/parametrics, K-NN |
|
TEoSL Ch. 2.3, 3.1 |
|
Slides (1),
(2),
(3)
|
6 (2/16+18+20) |
Learning theory, supervised learning: linear regression |
|
TEoSL Ch. 4.4 |
|
Slides (1),
(2),
(3)
|
7 (2/23+25+27) |
Linear regression |
|
|
|
Slides (1),
(2),
(3)
|
8 (3/2+4+6) |
Dimensionality reduction: PCA (Guest lec; Will Gebhardt) |
|
|
HW #1 due 3/17 |
Slides (1),
(2),
(3)
|
| 9 (3/9+11+13) |
Spring Break (3/8 through 3/15) |
|
|
|
|
10 (3/16+18+20) |
Polynomial & logistic regression |
|
| HW #2 due 4/3 |
Slides (1),
(2),
(3) |
11 (3/23+25+27) |
Multinoulli regression, generative & discriminative modeling |
|
|
|
Slides (1),
(2),
(3)
|
12 (3/30, 4/1+3) |
Naïve Bayes, mixture models & expectation-maximization |
|
|
|
Slides (1),
(2),
(3)
|
13 (4/6+8+10) |
Decision trees, ensembles (bagging, forests, & AdaBoost) |
|
Random Forests (Breiman '01) |
HW #3 due 4/28 |
Slides (1),
(2),
(3)
|
14 (4/13+15+17) |
Artificial neural networks (ANNs), reverse-mode differentiation |
|
DL Ch. 6 |
|
Slides (1),
(2),
(3)
|
15 (4/20+22+24) |
ANNs: Tricks of the trade & generative models |
|
DL Ch. 10 |
Final Exam - Project |
Slides (1), (2), (3) |
16 (4/27, Final: 5/1, 4:15-6:45pm) |
Outlook, Final Project Presentations |
|
|
| Slides due 5/1, 4:10pm |
| (Papers due 5/5, 8am) |
|
|
