ECE 503

Optimization for Machine Learning

Units: 1.5

Formerly: ELEC 503

The steepest-descent, Newton, conjugate, and quasi-Newton algorithms for unconstrained optimization. Inexact line-search techniques. Application of optimization methods to classification, logistic regression, and support vector machines for signal processing and machine intelligence involving audio, image, video and other types of data. Introduction to constrained optimization. Students are required to complete a project.

Note:

  • Credit will be granted for only one of ECE 503, ECE 403, ELEC 403, ELEC 503.

Graduate course in the Electrical and Computer Engineering program offered by the Faculty of Graduate Studies.

Schedules:
Summer 2018 Fall 2018 Spring 2019

Summer timetable available: February 15. Fall and Spring timetables available: May 15.

Before these dates the class schedule will show "No classes were found that meet your search criteria". If this message is shown after these dates, the course is not scheduled for the selected term.