## Computer Science Department

University of Western Ontario

# CS 434s/541a Pattern Recognition

## Fall 2004

Schedule
 Date September 13 September 15 Lecture Notes Suggested Reading HW and Solutions Lecture 1: Introduction and Review of Probability and Statistics DHS Chapter 1 Lecture 2: Review of Linear Algebra and Introduction to Matlab Any matlab tutorial, for example this tutorial, or matlab primer Lecture 3: Bayesian Decision Theory DHS Sections 2.1, 2.2, 2.3 (but not sections with stars), 2.4 Assignment 1 Due Oct.4 Lecture 3: Bayesian Decision Theory continued Note Assignment 1 has been corrected. Lecture 4: Discriminant Functions for Gaussian Random Variable Ch 2.5 and 2.6 Lecture 5: Maximum Likelihood and Baysian Parameter Estimation Ch 3.1, 3.2, 3.3, 3.5 Note Assignment 1, Problem 1 has been corrected Lecture 6: Nonparametric Density Estimation Ch 4.1, 4.2, 4.3 (except 4.3.1 and 4.3.2, 4.3.5), 4.4, 4.5 (except 4.5.1, 4.5.2), 4.6 (except 4.6.2) Assignment 2 , due Oct. 18. Data for this assignment Lecture 6 continued Solutions to Assignment1 Matlab Code Problem 1 Problem 2 Problem 4 Thanskgiving Lecture 6 continued Hints for Assignment 1, problem 1. Lecture 7: The Curse of Dimensionality and PCA Ch. 3.7 and 3.8.1 Lecture 8: Fisher Linear Discriminant 3.8.2 Assignment 3 , due Nov. 10 Data and functions for this assignment Lecture 9: Linear Discriminant Functions 5.1, 5.2, 5.4, 5.5, 5.7 Continue Lecture 9 Solution to Assignement2 and Matlab Code Lecture 10: Continuie Liner Discriminant Functions 5.8 Assignment 3 problem 2 has been modified. Review before the midterm Assignment 3 problem 1(e) and (f) has been clarified Midterm Lecture 11: Support Vector Machines 5.11 Midterm solutions Lecture 11: Continue Support Vector Machines Lecture 12: MultiLayer Neural Networks 6.1, 6.2 Assignment 4 Due Dec. 1 Lecture 13: Continue MultiLayer Neural Networks 6.3 Assignment 4 problem weights adjusted Lecture 14: Continue MultiLayer Neural Networks 6.3.3, 6.5, 6.8 Lecture 15: Unsupervised Learning: Clustering 10.1, 10.6, 10.7, 10.8, 10.9 Lecture 16: Finish Clustering example in slide 27 corrected, example in slide 19 actually works Lecture 17: EM algorithm and Parametric Unsupervised Clustering Lecture 18: Low dimensional Representation of High dimensional Data Assignment 4 solutions (short)