F.A.Q.

Should I take this course or Comp 451? what is the difference?

COMP 451 is a 3 credit course, so it will have a slightly smaller workload but it covers mostly the same material as COMP 551.

Class/waitlist is full, can I still register?

If you are on the waiting list, you will probably be ok. Usually ~160 students drop out of the class before the add/drop deadline when they realize how hard this class will be. If you are not on the waiting list, are a graduate student and really need class for your research, you may contact me at isabeau.premont-schwarz@mcgill.ca with a clear subject title and I will see what I can do. Otherwise you will need to wait for another semester. COMP 551 fills up really quickly, so make sure to register for it when registration opens. You should also consider alternative courses which are very similar like COMP 451 and ECSE 551.

Who to contact for department approval required for taking the course?

Please contact teresa.pian@mcgill.ca.

Do I have the prerequisites to take the course?

This course requires strong Python programming skills and knowledge of probabilities, multivariate calculus and linear algebra (in particular you should be very comfortable with index notation in linear algebra). Please check this quiz.this quiz to test if your background is strong enough for taking the course. It can also be used to diagnose where your background might be lacking and be used to self-study before taking the course. Most concepts covered in these questions will be used throughout the course in the slides.

How similar is it to the last years?

Very similar, please check last year's websites to get a glimpse of the slides, expectations, etc. We will have an updated version and not exactly the same materials but very similar overall.

Will there be lecture recordings?

We will attempt to provide lecture recordings, but there is no guarantee. If there are technical problems, it might be that a lecture ends up missing. Also the sound quality might not be the best. The recordings will be provided on a best attempt basis only.

What do I learn in this course?

You will learn how the most common machine learning algorithms are designed, how they are implemented, and how to apply them in practice. This course has a heavy theory component, since it is important to understand the inner-workings of the algorithms in order to effectively utilize them in practice. Please check the Lectures section for more information but note that everything is tentative.