CSE 5105
Bayesian Methods in Machine Learning
This course will cover machine learning from a Bayesian probabilistic perspective. Bayesian probability allows us to model and reason about all types of uncertainty. The result is a powerful, consistent framework for approaching many problems that arise in machine learning, including parameter estimation, model comparison, and decision making. We will begin with a high-level introduction to Bayesian inference and then proceed to cover more advanced topics. These will include inference techniques (e.g., exact, MAP, sampling methods, the Laplace approximation), Bayesian decision theory, Bayesian model comparison, Bayesian nonparametrics, and Bayesian optimization. Prerequisites: CSE 417T and ESE 326.
Instructors
Reviews
Don't take it unless required. The class average for the midterm is 25/44. No practice exam. Homework is irrelevant to the exam and not a great supplement to lectures. I heard it was the same situation last semester and he never changed. I don't think he wants to teach at all.
12/17/2024
Impressive lecturer. Very helpful outside of classes. Homework is a bit challenging and the concept is hard, but it is not hard to do well if you know how to do Gaussian Process and Bayesian Theorem. This course leads to a different understanding of Machine Learning models.
6/6/2021
Great professor, he really made me passionate about computer science and machine learning
9/30/2019
Super nice guy , great lecturer, very passionate about his sub field. Easy A but you learn really hard material
9/12/2019
Take his class if you want an easy A, but you won't learn much. Also he's very mean in person -- meanest professor in the CSE department in my opinion.
6/30/2019