Teaching
Current and recent courses taught by Martha White.
CMPUT 467/504 · Machine Learning II
Another miracle has come to pass, and we will now have a Machine Learning II course! This follows CMPUT 267, now called Machine Learning I. This course is meant to provide more depth than 466, and relies on having knowledge from Machine Learning I.
This course replaces CMPUT 367, but much of the content is similar. As with all courses, the content has evolved, both to simply be better with more iteration and to update as the world changes.
For TMI, CMPUT 367 was moved to CMPUT 467 because (a) it was confusing everyone that CMPUT 367 was seemingly more advanced than CMPUT 466 but at the 300-level and (b) we realized that offering ML III (Advanced ML) could and should be done only at the graduate level with the option for undergrads to request enrollment after completing ML II. We all appreciate you being patient as we figured out how to modify and improve our AI and ML offerings.
See the website for the syllabus and a tentative schedule.
CMPUT 267 · Basics of Machine Learning
This course is equivalent to CMPUT 296, now with a non-topics number as it will be taught every year. It will become a standard pre-req for later machine learning courses, including Intermediate Machine Learning and for CMPUT 365 Reinforcement Learning. I will teach CMPUT 267 both in the Fall semester, and then again in the Winter semester.
CMPUT 367 · Intermediate Machine Learning
A miracle has come to pass, and we will now have an Intermediate Machine Learning course! This follows CMPUT 267 (previously called CMPUT 296). This will be the first offering of this course, and it is being created from scratch. It should be fun (and challenging) for everyone involved.
This course will have a similar structure to CMPUT 267. It will cover more advanced topics in machine learning, relying on the foundations given by CMPUT 267. See the website for the syllabus and a tentative schedule.
CMPUT 267 · Basics of Machine Learning
This course is equivalent to CMPUT 296, now with a non-topics number as it will be taught every year. It will become a standard pre-req for later machine learning courses, including Intermediate Machine Learning and for CMPUT 365 Reinforcement Learning. I will teach CMPUT 267 both in the Fall semester, and then again in the Winter semester.
CMPUT 267 · Basics of Machine Learning
This course is equivalent to CMPUT 296, now with a non-topics number as it will be taught every year. It will become a standard pre-req for later machine learning courses, including Intermediate Machine Learning and for CMPUT 365 Reinforcement Learning. I will teach CMPUT 267 both in the Fall semester, and then again in the Winter semester.
CMPUT 367 · Intermediate Machine Learning
A miracle has come to pass, and we will now have an Intermediate Machine Learning course! This follows CMPUT 267 (previously called CMPUT 296). This will be the first offering of this course, and it is being created from scratch. It should be fun (and challenging) for everyone involved.
This course will have a similar structure to CMPUT 267. It will cover more advanced topics in machine learning, relying on the foundations given by CMPUT 267. See the website for the syllabus and a tentative schedule.
CMPUT 296 · Basics of Machine Learning
This is a new course, starting with the Basics of Machine Learning. We will actually cover a lot of the same core concepts as the more advanced machine learning course, 466, though with simpler modeling approaches. The goal is to provide the mathematical foundations to continue onto more advanced ML courses. An Intermediate ML course should be taught in Fall 2021, and will continue to be taught in following years. 296 will become the base course for several following ML courses, and is a better choice than 466 if you plan to take ML in more depth.
CMPUT 397 · Reinforcement Learning
All materials on the github pages.
CMPUT 655 · Reinforcement Learning I
This course will introduce RL, at a graduate level. This course is useful to take the graduate course, RL 2, taught by Rich Sutton. We will cover the RL Mooc designed for undergrads, but we will do so more quickly, will cover more advanced topics in class and will have a big focus on a research project.
CMPUT 296 · Basics of Machine Learning
Materials still hosted on [Website].
NeurIPS Tutorial on Policy Optimization in Reinforcement Learning
We did a NeurIPS Tutorial on Policy Optimization in Reinforcement Learning. It has some fun notebooks and lectures from myself, Sham Kakade and Nicolas Le Roux.
CMPUT 397 · Reinforcement Learning
This course was previously taught as CMPUT 366, and was introduced as an explicit course on Reinforcement Learning. Materials still hosted on github pages.
CMPUT 466/566 · Machine Learning
CMPUT 659 · Fundamentals of Stochastic Approximation Theory
CMPUT 466/566 · Machine Learning
CMPUT 659 · Optimization Principles for Reinforcement Learning
Students at the University of Alberta can access scribed notes from this course with a description of the course.