Homework 1 deadline has been extended to Friday January 29, 11:55pm.
Doina's regular office hours will be cancelled on Thursday January 28. She will instead be available in the afternoon 3:30-4:00pm.
Assignment 1 is now available, due January 28. TA information has been updated below.
Lecture 1 slides have been revised to reflect that we only discussed part of the previous deck in class. Lecture 2 slides have been posted.
Class has been moved to ENGMD 280 (McDonald Engineering Building), starting on January 14, 2016, due to lack of space in the previous room
The first class takes place Tuesday, January 12, 2016
General InformationWhere: MacDonald Engineering, room 280
When: Tuesday and Thursday, 10:05-11:25am.
What: The goal of this class is to provide an overview of the state-of-art algorithms used in machine learning. The field of machine learning is concerned with the question of how to construct computer programs that improve automatically with experience. In recent years, many successful applications of machine learning have been developed, ranging from data-mining programs that learn to detect fraudulent credit card transactions, to autonomous vehicles that learn to drive on public highways, and computer vision programs that can recognize thousands of different object types. At the same time, there have been important advances in the theory and algorithms that form the foundation of this field. During this course, we will study both the theoretical properties of machine learning algorithms and their practical applications.
School of Computer Science
Office: McConnell Engineering building, room 111N (left from elevators)
Office Hours: Tuesday and Thursday, 11:30-12:00. Meetings at other times by appointment only
Phone: (514) 398-6443
Ryan Lowe (firstname.lastname@example.org): Office hours Wednesdays 10:30-11:30, McConnell Engineering room 112
Boyu Wang (email@example.com): Office hours Thursdyas 2:00-3:00pm, McConnell Engineering room 108.
ReferencesThere is no required textbook. However, there are several good machine learning textbooks describing parts of the material that we will cover. The schedule will include recommended reading, either from these books, or from research papers, as appropriate.
- Christopher M. Bishop, "Pattern Recognition and Machine Learning", Springer, 2006.
- Richard S. Sutton and Andrew G. Barto, "Reinforcement learning: An introduction", MIT Press, 1998.
- Richard O. Duda, Peter E. Hart & David G. Stork, "Pattern Classification. Second Edition", Wiley & Sons, 2001.
- Trevor Hastie, Robert Tibshirani and Jerome Friedman, "The Elements of Statistical Learning", Springer, 2009.
- David J.C. MacKay, "Information Theory, Inference and Learning Algorithms", Cambridge University Press, 2003.
- Kevin P. Murphy, "Machine Leanring: a Probabilistic Perspective", MIT Press, 2012.
- Csaba Szepesvari, "Algorithms for Reinforcement Learning", Morgan and Claypool, 2010.
MyCourses will be used only for bulletin board, discussion groups and assignment submission and grading.