Fall 2019 Course Descriptions
The emerging research area of Bayesian Deep Learning seeks to combine the benefits of modern deep learning (scalable gradient-based training of flexible neural networks for regression and classification) with the benefits of modern Bayesian statistical methods to estimate probabilities and make decisions under uncertainty. The goal of this course is to bring students to the forefront of knowledge in this area through coding exercises, student-led discussion of recent literature, and an in-depth project. Covered topics include key modeling innovations (e.g. function approximation and deep generative models), learning paradigms (e.g. variational inference), and implementation using modern automatic differentiation frameworks. By completing a 2-month self-designed research project, students will gain experience with designing, implementing, and evaluating new contributions in this exciting research space.
Approved as a category 2 elective in Data Science (analysis and interfaces).
Prerequisite: COMP 135 (Introduction to Machine Learning) or COMP 136 (Statistical Pattern Recognition) or permission of the instructor