Description
This is a graduate-level introduction to the theory and practice of applying machine learning and signal processing techniques to real-world signals, especially 1-D signals (e.g. acoustic, electromagnetic) and 2-D signals (e.g. images).
Prior familiarity with machine learning techniques is required (e.g. an undergrad course in machine learning such as CPSC 340 Machine Learning and Data Mining). Familiarity with the Python programming language is recommended.
Prior familiarity with machine learning techniques is required (e.g. an undergrad course in machine learning such as CPSC 340 Machine Learning and Data Mining). Familiarity with the Python programming language is recommended.
General Information
Join the Class
If you are not yet signed up for this course on Piazza, click here to register: https://piazza.com/ubc.ca/winterterm12021/cpsc554x
You will also need access to the course in Canvas (https://canvas.ubc.ca/courses/78072) in order to submit assignments and view the video lectures.
You will also need access to the course in Canvas (https://canvas.ubc.ca/courses/78072) in order to submit assignments and view the video lectures.
Schedule
See the Syllabus posted under Resources for the course schedule.
Grading
5% Participation
25% Homework
70% Group Project, broken down as:
- 10% Proposal
- 25% Milestones
- 15% Final Demo
- 20% Final Report
25% Homework
70% Group Project, broken down as:
- 10% Proposal
- 25% Milestones
- 15% Final Demo
- 20% Final Report
Lectures
Monday/Wednesday 10:30am-12:00pm Pacific Time. Lectures for the first few weeks will be held online through Zoom (links on Canvas), and will thereafter be held in Hugh Dempster 101. Lecture recordings for online lectures will be available on Canvas.
Course Staff
Instructor: Robert Xiao <brx@cs.ubc.ca>
TA: Abi Kuganesan <akuganes@cs.ubc.ca>
TA: Abi Kuganesan <akuganes@cs.ubc.ca>
Office Hours
Make an appointment with the instructor by email
TA office hours: Fridays 11-12pm PT by Zoom: https://ubc.zoom.us/j/68028119764?pwd=R3V4WUQyKzVIMDEyLzQwRWJwWkM1UT09
TA office hours: Fridays 11-12pm PT by Zoom: https://ubc.zoom.us/j/68028119764?pwd=R3V4WUQyKzVIMDEyLzQwRWJwWkM1UT09
Academic Policy
The academic enterprise is founded on honesty, civility, and integrity. As members of this enterprise, all students are expected to know, understand, and follow the codes of conduct regarding academic integrity. At the most basic level, this means submitting only original work done by you and acknowledging all sources of information or ideas and attributing them to others as required. This also means you should not cheat, copy, or mislead others about what is your work. Violations of academic integrity (i.e., misconduct) lead to the breakdown of the academic enterprise, and therefore serious consequences arise and harsh sanctions are imposed. For example, incidences of plagiarism or cheating may result in a mark of zero on the assignment or exam and more serious consequences may apply if the matter is referred to the President’s Advisory Committee on Student Discipline. Careful records are kept in order to monitor and prevent recurrences.
Assignments are to be completed individually without assistance from other students, unless otherwise noted. You must acknowledge any sources you use (e.g. Internet resources) in your solution. The course project can be completed as a team of up to three students.
Assignments are to be completed individually without assistance from other students, unless otherwise noted. You must acknowledge any sources you use (e.g. Internet resources) in your solution. The course project can be completed as a team of up to three students.
| Name | Office Hours | |
|---|---|---|
Robert Xiao | When? Where? | |
Abiramy Kuganesan | When? Where? |