icon picker
Social Interaction & Research Communication-Doctoral Consortium (SIRC-DC)

COMP597 Fall 2023: Applications of Machine Learning in Real-World Systems

Course Overview

sheet-of-paper
This is an advanced undergraduate level / graduate-level course for students who are interested in learning how to apply machine learning algorithms to solve real-world problems. We will start with a quick review of machine learning basics and then focus on a few selected interesting (subjective) topics including communication networks, web search and recommendation, LLMs, generative models, smart grid, and medical applications. We will also discuss some high-impact industry machine learning products and the research problems behind their successes. The class consists of instructor lectures, student-led presentations, class discussions, and class projects.

Prerequisites

Math courses: Calculus (Math 141), Linear Algebra (Math 223), Matrix Numerical Analysis (Math 327), Probability Theory (Math 323 or ECSE 205 or ECSE 305)
Computer Systems Courses: Foundations of Programming (COMP 202 or similar), Operating Systems (COMP 310), Algorithms and Data Structures (COMP 251 or similar)
Machine Learning courses: Applied Machine Learning (COMP551, or COMP-652/ ECSE-608).
megaphone
Please Note: Instructor approval is needed to register this course. We will check whether the prerequisites are met. These prerequisites are strict. These prerequisites are important for you to be successful in this fast-paced class. Please register for later offerings if you do not meet these prerequisites currently.
light
For approval, please email the instructor with the EXACT title “COMP597: Registration Approval Request”. In the email body, please list the prerequisite courses you took, and the course grades you got, with each line for one course. Please mark missing prerequisite course(s) in bold and red color. Please also attach (1) your transcript(s) (university and above) and (2) a CV with your detailed project(s) and research or industry/internship experiences. Please include your McGill ID# in the email and your CV. Thanks.

General Information

info
👨🏼‍🏫 Instructor: Prof. Steve Liu
Email: solve the reCAPTCHA on my webpage (Recommended means for communication. Do NOT use the phone for contact.)
Office: Room 326, McConnell Engineering Building
Office Hours: TBD
Location: Zoom or Office

ask-question
💁🏼 Teaching Assistant: TBD
Email: TBD

Course Quota: 25
Course materials:
Project submission page:
GitLab or GitHub. Link: TBD
Please note: Emails should be sent from your official McGill email address in order to get the response. Emails not from your official McGill email address will NOT be properly filtered hence will not be responded. Emails should be started with the title “COMPXXX: ***”. Replace XXX with the correct course number. For every email communication, please make sure to use “COMPXXX:” as a single word (with no spaces) as the start of the title and replace *** with your topic/questions, and replace XXX with the correct course number.
Please note: Due to a LARGE number of emails (including spams, unfortunately) I receive every day, emails not started with this title may be categorized as spams by the spam filter and will be missed. We will NOT use WebCT / MyCourses email. Thank you for your understanding.
high-priority
Academic Integrity: “McGill University values academic integrity. Therefore, all students must understand the meaning and consequences of cheating, plagiarism, and other academic offences under the Code of Student Conduct and Disciplinary Procedures (see for more information).”

Course Syllabus

Textbooks

Due to the nature of this course, many topics are not available in any textbook. Hence there is no required textbook. Instead, we will use many publications, technical notes or materials available from the Internet.

Evaluation

Scores
Objective
Credit
1
Class participation/presentations (class topic presentation, and project progress checkpoint presentations/demo(s) )
35%
2
Class presentation topic summary/survey paper
30%
3
Project and final report
35%
4
Total
100%
There are no rows in this table
megaphone
Please note: In the event of extraordinary circumstances beyond the University’s control, the evaluation scheme in a Course is subject to change, provided that there be timely communications to the students regarding the change.

Final project evaluation

Two intermediate (milestone) presentations are needed for your final project. These presentations / demos are expected to receive proper feedbacks on your project. Also, these milestone presentations / demos could help you pace the project for timely completion. Every final project must have a final report (and other associated materials, such as software programs) submitted for final grading.

Late project policy

There will be a strict deadline for the final project (the week before the final exams – subject to change). Please pay close attention to the announcements during the course. It is your responsibility to make sure that the final project report (and its associated materials, if any) is properly submitted via Git.

Click here to see .



Want to print your doc?
This is not the way.
Try clicking the ⋯ next to your doc name or using a keyboard shortcut (
CtrlP
) instead.