Lectures: Monday, Wednesday 3-4
Lecture Room: Bahen 1220
Instructor: Richard Zemel csc411prof at cs.toronto.edu
Office hours: Thursday 4-5 Pratt 290D, and by appointment

Tutorials: Friday 3-4
Tutorial Room: Bahen 1220
TAs: Hannes Bretschneider, Kevin Swersky, and Charlie Tang
TA email: csc411ta at cs.toronto.edu

Pre-requisites: You should understand basic probability and statistics, and college-level algebra and calculus. Knowledge of linear algebra will be a big help. For the programming assignments, you should have some background in programming,and it would be helpful if you know Matlab. Some introductory material for Matlab will be available on the course website as well as in the first tutorial.

Readings: The textbook for this year is a new book by Kevin Murphy. The book has not been published yet, but Kevin has let me print advanced copies of the book. You can purchase the book in the AI Office: Pratt 283, from Kelly Barnes. She will be there 9-5, except for lunch from 1-2. The cost is $14.52, and you can pay by check or cash.

Course schedule: The schedule of lectures, readings, and assignments can be found [here], but is subject to change.

Course requirements and grading: The format of the class will be lecture, with some discussion. I strongly encourage interaction and questions. There are assigned readings for each lecture that are intended to prepare you to participate in the class discussion for that day.

The grading in the class will be divided up as follows:

Assignments 50%
Mid-Term Exam 20%
Final Exam 30%

There will be an initial small assignment worth 5% of your grade, and then three more assignments, each of which will be worth 15% of your grade.

Homework assignments: The best way to learn about a machine learning method is to program it yourself and experiment with it. So the assignments will generally involve implementing machine learning algorithms, and experimentation to test your algorithms on some data. You will be asked to summarize your work in brief (3-4 page) write ups. The implementations must be done in Matlab, but prior knowledge of Matlab is not required. A brief tutorial on Matlab is included here. You may also use Octave.

Collaboration on the assignments is not allowed. Each student is responsible for his or her own work. Discussion of assignments and programs should be limited to clarification of the handout itself, and should not involve any sharing of pseudocode or code or simulation results. Violation of this policy is grounds for a semester grade of F, in accordance with university regulations.

The schedule of assignments is included in the syllabus. Assignments are due at the beginning of class/tutorial on the due date. Because they may be discussed in class that day, it is important that you have completed them by that day. Assignments handed in late but before 5 pm of that day will be penalized by 5% (i.e., total points multiplied by 0.95); a late penalty of 10% per day will be assessed thereafter. Extensions will be granted only in special situations, and you will need a Student Medical Certificate or a written request approved by the instructor at least one week before the due date.

For one of the assignments, we will have a bake-off: a competition between machine learning algorithms. I will give everyone some data for training a machine learning system, and you will try to develop the best method. We will then determine which system performs best on some unseen test data.

Computing: [Computing Information] [Matlab Information]

Exams: There will be a mid-term in class on October 24th, which will be a closed book exam on all material covered up to that point in the lectures, tutorials, required readings, and assignments.

The final will not be cumulative, except insofar as concepts from the first half of the semester are essential for understanding the later material.

Attendance: I expect students to attend all classes, and all tutorials. This is especially important because I will cover material in class that is not included in the textbook. Also, the tutorials will not only be for review and answering questions, but new material will also be covered.

Electronic Communication: Feel free to email me with questions or comments about the course. I will try to respond promptly. You should include your full name in the email, and it may also be useful to include your CDF account name and/or student number.

There is a bulletin board set up for this course. This is a good place for discussion of class topics and assignments. For questions about marks on the assignments, please first contact the TA. Questions about the exams should be addressed to me.