Lecture
|
Date
|
Topic
|
Readings
(textbooks)
|
1
|
Jan 4
|
Introduction to Machine
Learning (Lecture slides)
|
|
2
|
Jan 9
|
K-nearest neighbours (Lecture slides) |
[RN] Sec. 18.8.1, [HTF] Sec.
2.3.2, [D] Chapt. 3, [B] Sec. 2.5.2, [M] Sec. 1.4.2 |
3
|
Jan 11
|
Linear regression (Lecture slides) (Notation
reference sheet)
|
[RN] Sec. 18.6.1, [HTF] Sec.
2.3.1, [D] Sec. 7.6, [B] Sec. 3.1, [M] Sec. 1.4.5
|
4
|
Jan 16
|
Statistical learning (Lecture slides)
|
[RN] Sec. 20.1, 20.2, [M]
Sec. 2.2, 3.2 |
5
|
Jan 18
|
Linear regression by maximum
likelihood, maximum a posteriori, Bayesian learning (Lecture slides)
|
[B] Sec. 3.1-3.3, [M] Chap. 7
|
|
Jan 20
|
Assignment 1 due (11:59 pm) |
|
6
|
Jan 23 |
Mixture of Gaussians (Lecture slides)
|
[B] Sec. 4.2, [M] Sec. 4.2 |
7
|
Jan 25
|
Logistic regression,
generalized linear models (Lecture slides (revised
Jan 30)) |
[RN] Sec. 18.6.4, [B] Sec.
4.3, [M] Chap. 8, [HTF] Sec. 4.4 |
8
|
Jan 30
|
Perceptrons, single layer
neural networks (Lecture
slides (Slide 19 revised Feb 20)
|
[D] Chapt. 4, [HTF] Chapt.
11, [B] Sec. 4.1.7, 5.1, [M] Sec. 8.5.4, [RN] Sec. 18.7 |
9
|
Feb 1
|
Multi-layer neural networks,
backpropagation (Lecture
slides)
|
[D] Chapt. 10, [HTF] Chapt.
11, [B] Sec. 5.2, 5.3, [M] Sec. 16.5, [RN] Sec. 18.7 |
|
Feb 3
|
Assignment 2 due (11:59 pm) |
|
10
|
Feb 6
|
Kernel methods (Lecture slides)
|
[D] Chapt. 11, [B] Sec. 6.1,
6.2 [M] Sec. 14.1, 14.2 [H] Chap. 9 [HTF] Chap. 6 |
11
|
Feb 8
|
Gaussian Processes (Lecture slides)
|
[B] Sec. 6.4 [M] Chap. 15
[HTF] Sec. 8.3 |
12
|
Feb 13
|
Support vector machines (Lecture slides)
|
[B] Sec. 7.1 [D] Sec.
11.5-11.6 [HTF] Chap. 12 [M] Sec. 14.5 [RN] Sec. 18.9 [MRT]
Chap. 4 |
13
|
Feb 15
|
Midterm (in class)
- HH1102: Students with last name
starting with A-L
- PAS2083: Students with last name starting with M-Z
|
|
|
Feb 20
|
Family day (no class)
|
|
|
Feb 22
|
Reading break (no class)
|
|
14
|
Feb 27
|
Support vector machines
continued (Lecture
slides)
|
|
|
Feb 27
|
Project proposal due (11:59 pm)
|
[B] Sec. 7.1 [D] Sec. 6.7 [HTF] Chap. 12 [M]
Sec. 14.5 [RN] Sec. 18.9 [MRT] Chap. 4 |
15
|
Mar 1
|
Hidden Markov models (Lecture slides (Slide 16
revised April 10) (HMM
example (revised March 17))
|
[RN] Sec. 15.3 [B] Sec.
13.1-13.2 [M] Sec. 17.3-17.5 |
|
Mar 3
|
Assignment 3 due (11:59 pm) |
|
16
|
Mar 6
|
Deep neural networks (Lecture slides)
|
[GBC] Chap. 6, 7, 8 |
17
|
Mar 8
|
Convolutional neural networks
(Lecture slides
(Slide 6 revised March 15))
|
[GBC] Chap. 9 |
18
|
Mar 13
|
Recurrent and recursive
neural networks (Lecture
slides)
|
[GBC] Chap. 10 |
19
|
Mar 15
|
Autoencoders (Lecture slides)
|
[GBC] Chap. 14 |
|
Mar 17
|
Assignment 4 due (11:59 pm) |
|
20
|
Mar 20
|
Generative networks
(variational autoencoders and generative adversarial
networks) (Lecture
slides) |
[GBC] Chap. 20 |
21
|
Mar 22
|
Ensemble learning: bagging
and boosting (Lecture
slides)
|
[RN] Sec 18.10, [M] Sec.
16.2.5, [B] Chap. 14, [HTF] Chap. 15-16, [D] Chap. 11 |
22
|
Mar 27
|
Bagging, decision forests and
distributed computing (Lecture
slides)
|
[RN] Sec 18.10, [M] Sec.
16.2.5, [B] Chap. 14, [HTF] Chap. 15-16, [D] Chap. 11 |
23
|
Mar 29
|
Stream learning and course
wrap up (Lecture slides)
|
[M] Sec. 8.5 |
|
Mar 31
|
Assignment 5 due (11:59 pm) |
|
24
|
Apr 3
|
Question answer session
|
|
|
Apr 14
|
Project report due (11:59 pm)
|
|