W24 Topics Course Descriptions Released!

The winter semester is nearly upon us, and with course registration in full swing, the topics that will be covered in STAT*4050, STAT*6920, MATH*4060, and MATH*6181 are now available! 

STAT*4050 & STAT*6920 (Bayesian Data Analysis)

This course will be led by Dr. Justin Slater, and will be an applied statistics course from the perspective of the Bayesian. We will introduce the Bayesian framework as an intuitive framework for statistical analysis, with an emphasis on modern applied techniques from a conceptual perspective. Topics in this course include:

• The practical differences between Bayesian and frequentists statistics
• Prior beliefs, updating, and statistical evidence
• Bayesian hierarchical models
• Bayesian computation
• The Bayesian workflow – model building and checking

The main tool for analysis in this course will be Stan, a probabilistic programming language designed for Bayesian inference. No prior experience with Stan is assumed, but students should have experience with R or a similar language. I will assume that students have prior experience with statistical modelling (regression models, GLMs, etc.) and some experience with mathematical statistics (expectations, conditional probability, probability distributions, etc.). Graduate students will have additional responsibilities.

MATH*4060 & MATH*6181 (Introduction to Markov Decision Processes and Reinforcement Learning)

This course will be taught by Dr. Mihai Nica.

Reinforcement learning (RL) is a machine learning paradigm that deals with training autonomous agents to maximize observed rewards. This forms the basis of recent famous AI algorithms that play games like Chess and Go. This course provides a mathematical introduction to the theory of RL and related topics in probability theory by starting with Markov chains and building up. Topics include: Markov chains, Markov decision processes, multi-armed bandit problems, dynamic programming, Monte Carlo methods, temporal difference learning. Students will develop AI algorithms using the methods from the course as part of a final project.

Aside from some mathematical maturity, the only technical prerequisites are a basic understanding of probability theory (at around the level of MathStats 1) and basic programming skills (projects are required to be completed in Python and Google Collab). If you would like to take the course and are unsure about prerequisites please contact me and we can chat! (nicam@uoguelph.ca)

Course content will be delivered both by recorded lectures (which go over definitions/basic examples) as well as in-person discussions and problem solving sessions. There will also be in-class programming labs where we will implement course ideas. Other course assessments will be mostly project based.

The only text that will be used in this course is "Reinforcement Learning: An Introduction" by Richard S. Sutton and Andrew G. Barto. Available for free online from the authors here.