COMP-598: Topics in Computer Science: Applied Machine Learning (Fall 2014)

INSTRUCTOR: Joelle Pineau
TA: T.b.d.

Term: Fall 2014.
When: Tuesday / Thursday, 11:30am-1:00pm
Where: ENGTR 2120

The course is currently full. Enrollment is closed because the room is already beyond capacity. Numerous students have contacted me, asking whether they can be enrolled, or whether they can audit. My standard reply is that if you are interested, you should come to the first class, and we will see what is feasible. I am delighted to let everyone in, but there is a point at which the quality of the course may suffer, and authorities will be concerned that overcrowding is a potential fire hazard. I will try to provide an update during the first class.

Course syllabus

Course schedule (including lecture slides, homeworks, solutions.)

Description

The course will cover selected topics and new developments in data mining and applied machine learning, with a particular emphasis on good methods and practices for effective deployment of real systems. We will study commonly used algorithms and techniques, including linear and logistic regression, clustering, neural networks, support vector machines, decision trees and more. We will also discuss methods to address practical issues such as feature selection and dimensionality reduction, error estimation and empirical validation, algorithm design and parallelization, and handling of large datasets. Important note:Students who took COMP-652 in 2013 or before CANNOT take COMP-598. Students who took COMP-652 in Winter 2014 (or intend to take it later) can take COMP-598. Contents of both courses have been designed to avoid too much overlap. COMP-598 focuses on the practical application of machine learning, whereas COMP-652 (starting in Winter 2014) focuses on theoretical analysis of machine learning, reinforcement learning, bandits and analysis of time series.

List of topics (subject to minor changes):

IMPORTANT: The schedule is subject to change. Up-to-date information about the schedule and assigned readings will be posted on the class web page.