Description: In this course, we will cover theories and algorithms that capture (or approximate) some of the core elements of computational intelligence. Assignments provide practical experience, in both theory and programming, of the core topics.

Prerequisites: Although we will cover all relevant background material, it is still expected that you have a basic understanding of algorithms design and probability theory. In particular, you should have taken;

• one of CSC263, CSC265, CSC263, CSCC63, ECE345, ECE358, MIE335

• one of STA237, STA247, STA255, STA257, STA237, STAB57, STAB52, STA286, CHE223, CME263, ECE302, ECE286, MIE231, MIE236, MSE238

• working knowledge of Python

If you do not have the appropriate prerequisites, you will need to obtain a prerequisite waiver from the CS undergraduate office (cs .undergrad@utoronto .ca). You do not need to email the teaching team. Even if your request is accepted, it is your responsibility to understand the prerequisite material.

Instructor:

Chandra Gummaluru

MASc Computer Engineering - Systems Control

[email protected]

Teaching Assistants: Parsa Mirdehghan, Evi Micha, Zhewei Sun, Hongkai Chen

Textbook (Optional): This course has no required textbook. However, if you wish to have a reference, we recommend Artifcial Intelligence: A Modern Approach (3rd edition) by Stuart Russel and Peter Norvig.

Lectures: The lectures take place weekly on Mondays1 from 18:00 - 21:00 in-person in BA1180. Note that although the Arts and Sciences calendar lists Mondays 20:00 - 21:00 for tutorials, we will use it as a lecture hour in the same room. Lectures are not recorded.

Office Hours: Weekly on Tuesdays from 19:00 - 20:002 online via Zoom (the link will be made avail- able on the course page). Office hours are not recorded.

Software and Tools: We will use multiple tools for the delivery and collection of material in this course:

• Quercus: The syllabus, lecture slides, information about individual evaluations, and practice prob- lems can all be found here.

• Piazza: A discussion form where you can ask questions about anything in the course (including personal concerns). We aim to respond to all inquiries within 24 hours.

• Markus: All programming assignments and problem sets should be submitted here. You will find your marks and can submit remark requests for all evaluations here as well.

• Zoom: We will use this to hold office hours and help sessions. You will need to use your University of Toronto account.

Links to all of the above will be posted on the course page.

Grading Scheme: This course consists of 3 programming assignments (24%), a mid-term exam (18%), two problem sets (10%) a final exam (36%), and a course presentation (12%). The tentative grade distri- bution is shown in the table below:

• All release dates and due dates are tentative.

• The deadlines for the programming assignments / problem sets are at 15:00 EST on their re- spective due dates.

• The mid-term test will be scheduled between Jun 22 - Jun 29.

• The final exam will be scheduled between Aug 17 - Aug 30.

• You must obtain a grade of at least 40% on the final exam to pass the course.

• You may discuss the programming assignments and problem sets with each other but must submit your own individual work.

• The course project must be done in groups of three students unless this is not possible.

• You will be provided with practice problems for each module. These will not be graded.

Late Policies: You will be given two weeks to complete each programming assignment, and one week to complete each problem set. Late submissions will not be accepted unless you use grace days.

• You will be given 5 grace days at the beginning of the term.

• If you use n grace days on an evaluation, you may submit the evaluation up to 24n hours beyond the due date without penalty. For example, if the deadline is Jun 13 at 15:00 EST, and you use 2 grace days, your new deadline is Jun 15 at 15:00 EST.