| Week (Subject to change) |
Topics |
Homework |
Reading |
Special Events and Due Dates |
Slides & Lecture Notes |
| 1 (8/24+26) |
Introduction, class logistics, Review: linear algebra |
|
DL Ch. 1 & Ch. 2 |
|
Slides (1), (2) |
2 (8/31+9/2) |
Linear algebra; basics of optimization (hill-climbing) |
|
DL Ch. 3, TEoSL Ch. 1
| HW #0 due 8/XX |
Slides (1), (2) |
3 (9/7+9) |
Optimization; differential calculus |
|
DL Ch. 4 & Ch. 5 |
|
Slides (1),
(2)
|
| 4 (9/14+16) |
Probability theory, statistics |
|
DL Ch. 5 |
|
Slides (1),
(2),
(3)
|
5 (9/21+23) |
Distributions, learning theory, non-parametrics/parametrics, K-NN |
|
TEoSL Ch. 2.3, 3.1 |
|
Slides (1),
(2),
(3)
|
6 (9/28+30) |
Learning theory, supervised learning: linear regression |
|
TEoSL Ch. 4.4 |
|
Slides (1),
(2),
(3)
|
7 (10/5+7) |
Linear regression |
|
|
|
Slides (1),
(2),
(3)
|
8 (10/12+14) |
Dimensionality reduction: PCA (Guest lec; Will Gebhardt) |
|
|
HW #1 due X/XX |
Slides (1),
(2),
(3)
|
| 9 (10/19+21) |
YYYY (X/X through X/X) |
|
|
|
|
10 (10/26+28) |
Polynomial & logistic regression |
|
| HW #2 due X/X |
Slides (1),
(2),
(3) |
11 (11/2+4) |
Multinoulli regression, generative & discriminative modeling |
|
|
|
Slides (1),
(2),
(3)
|
12 (11/9+11) |
Naïve Bayes, mixture models & expectation-maximization |
|
|
|
Slides (1),
(2),
(3)
|
13 (11/16+18) |
Decision trees, ensembles (bagging, forests, & AdaBoost) |
|
Random Forests (Breiman '01) |
HW #3 due X/X |
Slides (1),
(2),
(3)
|
14 (11/23+25) |
Artificial neural networks (ANNs), reverse-mode differentiation |
|
DL Ch. 6 |
|
Slides (1),
(2),
(3)
|
15 (11/30, 12/1) |
ANNs: Back-propagation, tricks of the trade |
|
DL Ch. 10 |
Final Exam - Project |
Slides (1),
(2),
(3) |
16 (12/X, Final: 12/X, X:XX-X:XXpm) |
ANN generative models, breaking i.i.d., final exam |
|
|
| Slides due 12/X, 4:10pm |
| (Papers due 12/X, 8am) |
|
Slides (1) (Last lecture)
|
