CMPUT 466/551 - Machine Learning

Winter 2004
Department of Computing Science
University of Alberta


Instructor: Dale Schuurmans, Ath409, x2-4806, dale@cs.ualberta.ca


Course outline

Lecture 1 Introduction Tues Jan 6
Part 1 Learning to predict
Lecture 2 Linear prediction Thur Jan 8 P0 out
Lecture 3 Generalized linear prediction Tues Jan 13 A1 out
Lecture 4 Neural networks Thur Jan 15
Lecture 5 Regularization Tues Jan 20
Lecture 6 Learning theory: bias-variance Thur Jan 22
Lecture 7 Automated complexity control Tues Jan 27 A1 due
Part 2 Learning to classify
Lecture 8 Linear classification, Support Vector Machines Thur Jan 29 A2 out
Lecture 9 Duality Tues Feb 3
Lecture 10 Kernel methods Thur Feb 5
Lecture 11 Discrete classification, Computational complexity Tues Feb 10 P0 due
Lecture 12 Decision trees, Noise Thur Feb 12 A2 due, A3 out
Reading Week
Lecture 13 Learning theory: Uniform convergence Tues Feb 24
Lecture 14 Vapnik-Chervonenkis dimension Thur Feb 26
Part 3 Probability models
Lecture 15 Probability models Tues Mar 2
Lecture 16 Bayesian networks Thur Mar 4 A3 due
Lecture 17 Maximum likelihood estimation Tues Mar 9 A4 out
Lecture 18 Expectation-maximization algorithm Thur Mar 11
Lecture 19 Bayesian learning Tues Mar 16
Lecture 20 Bayesian learning (cont.) Thur Mar 18
Part 4 Ensemble learning methods
Lecture 21 Ensemble learning methods Tues Mar 23 A4 due
Lecture 22 Boosting Thur Mar 25
Part 5 Other learning problems
Lecture 23 Unsupervised learning Tues Mar 30
Lecture 24 Manifold learning Thur Apr 1
Lecture 25 Reinforcement learning Tues Apr 6 Project due