COMP-551: Topics in Computer Science: Applied Machine Learning

Schedule for Fall 2017

Lec.
Date
Topic
Lecture Material and Readings
Projects
1
Sep. 6

Introduction to machine learning.

Mandatory reading: This paper.
Suggested readings:
Bishop, Ch.1-2. Hastie et al., Ch.1. Shalev-Schwartz et al., Ch.2.
Slides
2
Sep. 11

Linear regression.

Suggested readings:
Bishop, Ch.3. Hastie et al., Ch.2 (Sec.2.1-2.4, 2.9).
Shalev-Schwartz et al., Ch.9
Slides
3
Sep. 13

Linear regression.

Suggested readings:
Ch.3 (Sec.3.1-3.4, 3.9) of Hastie et al.
Ch.3 of Bishop (Sec.3.1-3.2).
Ch.5 and 11 of Shalev-Schwartz
Slides
Project 1 instructions and sample file available
Tutorial 1 (in class)
4
Sep. 18

Linear classification.

Suggested readings:
Ch.4 of Hastie et al.
Ch.4 of Bishop (Sec.4.1-4.3).
Sec.9.3 of Shalev-Schwartz
Slides
5
Sep. 20

Linear classification.

Suggested readings:
Sec. 6.6.3 of Hastie et al.
Ch.4 of Bishop (Sec.4.1-4.3).
Sec.24.1-24.3 Shalev-Schwartz
Slides
6
Sep. 25

Performance analysis and error estimation.

Suggested readings:
Ch.7 of Hastie et al.
Wagstaff (2012) paper
7
Sep. 27

Decision trees

Suggested readings:
Sec.14.4 of Bishop.
Sec.9.2 of Hastie et al.
Project 1 due.
8
Oct. 2

Instance-based learning

Suggested readings:
Sec.2.5 of Bishop.
Sec.13.3 of Hastie et al.
Ch.19 of Shalev-Schwartz
Project 2 available
Tutorial 2: Thursday Sept.28, TR3120, 4-5pm.
9
Oct. 4

Feature construction and selection
Oct. 9

Thanksgiving (no class)
10
Oct. 11

Ensemble methods

Suggested readings:
Sec.8.7, Ch.10 of Hastie et al.
Ch.14 of Bishop Ch.10 of Shalev-Schwartz
11
Oct. 16

Support vector machines

Suggested readings:
Ch.7 of Bishop.
Ch.12 (Sec.12.1-12.4) of Hastie et al.
Ch.15 of Shalev-Schwartz
For more on convex optimization: see book by S. Boyd and L. Vandenberghe
12
Oct. 18

Support vector machines (cont'd)

Suggested readings:
See lecture 9.
13
Oct. 23

Unsupervised learning
Project 2 due.
14
Oct. 25

Neural networks

Suggested readings
Ch.11 of Hastie et al.
Ch.5 of Bishop
Ch.14 of Shalev-Schwartz
Project 3 available.
Tutorial 3
15
Oct. 30

Neural networks (cont'd)
16
Nov. 1

Deep learning
17
Nov. 6

Deep learning (cont'd)
18
Nov. 8

Semi-supervised learning / Generative Models
19
Nov. 13

Bayesian Inference
Project 3 due.
20
Nov. 15

Gaussian Processes
Project 4 available.
21
Nov. 20

Bayesian Optimization
Tutorial 4
22
Nov. 22

Midterm (confirmed, 6-8pm, in Leacock 132).
23
Nov. 27

Parallelization for large-scale ML
24
Nov. 29

Missing data
25
Dec. 4

Final project discussion session with TAs (optional)
26
Dec. 6

Final project presentation session
Project 4 report due.