General Information

--------------------------

Schedule:

8/27 (Tu) Class begins on 8/28

8/29 (Th)

introduction, linear regression, gradient descent

Week 1

9/3 (Tu)

linear regression in closed form, probabilistic interpretation

9/5 (Th)

logistic regression, softmax regression, perceptron

Week 2

9/10 (Tu)

Newton's method, least mean squares with the kernel trick

9/12 (Th)

SVM, primal and dual optimization

Week 3

9/17 (Tu)

xxx

9/19 (Th)

kernel method, SVM

Week 4

9/24 (Tu)

Kernel, regularization, SMO (sequential minimal optimization), coordinate ascent

9/26 (Th)

Generative learning algorithm, multivariate Gaussian, GDA, naive Bayes

Week 5

10/1 (Tu)

Example (naive Bayes, multivariate Gaussian), k-means clustering

10/3 (Th)

Gaussian mixture, EM

Week 6

10/8 (Tu)

general EM - convergence proof intuition

10/10 (Th)

midterm

Week 7

10/12-15 Fall Break

10/17 (Th)

More EM

Week 8

10/22 (Tu)

Principal Components Analysis, eigenface

10/24 (Th)

Independent Components Analysis

Week 9

10/29 (Tu)

bias/variance tradeoff, decision tree, entropy, random forest

10/31 (Th)

AdaBoost

Week 10

11/5 (Tu)

11/7 (Th)

Week 11

11/12 (Tu)

deep learning -- forward propagation

11/14 (Th)

deep learning -- back propagation

Week 12

11/19 (Tu)

deep learning dl1.pdf

11/21 (Th)

deep learning dl2.pdf

Week 13

11/26 (Tu)

deep learning dl3.pdf

11/28 (Th)

No class: 11/27-12/1 Thanksgiving Break

Week 14

12/3 (Tu)

adversarial example, generative adversarial networks

12/5 (Th)

Week 15

12/6 class ends

Exam:

11:00TR — 12/10 Tue. 2:00PM-5:00PM