CSC 580: Principles of Machine Learning - Fall 2020

This is a graduate level machine learning course.

Here is the syallabus updated on Sep 9, 2020. Further adjustments will be available in D2L.

The required textbook is Hal Daumé’s Course in Machine Learning, fully and freely available online.

Here are some excellent notes for probability review and linear algebra review. You should have no difficulty in Python programming (matlab/julia allowed). You may also find The matrix cookbook, The Probability and Statistics Cookbook useful, and Calculus cheatsheet.

For updated schedule, please see D2L

#	Topics	Readings	Homework
1: 08/24	intro / math review / decision tree	Ch 1	HW0
2: 08/26	.
3: 08/31	limits of learning / instance-based learning	Ch 2,3
4: 09/02	.		HW1
: 09/07	(no class)
5: 09/09	perceptron	Ch 4
6: 09/14	.
7: 09/16	practical issues: cross validation, evaluation, feature selection	Ch 5
8: 09/21	.		HW2
9: 09/23	bias-variance decomposition	Ch 5
10: 09/28	reduction	Ch 6
11: 10/05	.
12: 10/07	.
13: 10/12	linear models	Ch 7
14: 10/14	.		HW3
15: 10/19	kernel methods	Ch 11
16: 10/21	.		project proposal due
17: 10/26	naive Bayes, graphical models	Ch 9
18: 10/28	.
19: 10/30	.		HW4
20: 11/02	bias and fairness	Ch 8
21: 11/04	neural networks	Ch 10
22: 11/09	.
: 11/11	(no class)
23: 11/16	ensemble	Ch 13
24: 11/18	efficient learning, sgd	Ch 14	HW5
25: 11/23	unsupervised learning	Ch 15
26: 11/25	.
27: 11/30	reinforcement learning	Ch 16
28: 12/02	learning theory	Ch 12
29: 12/07	(reserved for catch up)
30: 12/09	(reserved for catch up)
: 12/14	final exam
: 12/17	final project due