CSE 4404A / 5327A (Fall 2012) INTRODUCTION TO MACHINE LEARNING AND PATTERN RECOGNITION

Location & Time: Chemistry Building 122  MW 17:30-19:00

Purpose:        
Machine learning is the study of algorithms that learn how to perform a task from prior experience. Machine learning algorithms find widespread application in diverse problem areas, including machine perception, natural language processing, search engines, medical diagnosis, bioinformatics, brain-machine interfaces, financial analysis, gaming and robot navigation.  This course will thus provide students with marketable skills and also with a foundation for further, more in-depth study of machine learning topics.

This course introduces the student to machine learning concepts and techniques applied to pattern recognition problems in a diversity of application areas.  The course takes a probabilistic perspective, but also incorporates a number of non-probabilistic techniques. 

Instructor Information:

James H. Elder

0003G Computer Science and Engineering Building
tel: (416) 736-2100  ext. 66475  fax: (416) 736-5857
email: jelder@yorku.ca   website: www.yorku.ca/jelder

Office Hour:  Friday 12:00-13:00

Complete Syllabus & Schedule

Moodle:

I will post lectures on this website, but will use Moodle to post supplementary readings. We will also use Moodle for discussion - I encourage you to make full use of this facility, but please remember that the two graded assignments must be done individually - do not post solutions or partial solutions.

Lectures:

  1. Introduction
  2. Bayesian Decision Theory
  3. Multivariate Normal Distribution
  4. Linear Regression
  5. Linear Classifiers
  6. Mixture Models and EM
  7. Dimensionality Reduction
  8. Kernel Methods
  9. Boosting
  10. Multi-layer Perceptrons

I reserve the right to make changes to the lectures up to the time of the class. Small changes may also be made after class, e.g., to correct errors. I will indicate in each set of slides the date they were last modified: please verify that you have the most recent versions

Assignments:

Please note that datasets for assignments will be posted on the moodle site for the course.