CS 761 covers advanced theory and methods in machine learning, including probabilistic modeling, hypothesis testing, classification and regression, maximum likelihood and Bayesian inference, PAC learning and VC theory, nonparametric methods, and state-of-the-art machine learning algorithms.
Open to all students with advanced computing and mathematics/statistics background.
Instructor:
Robert Nowak
Lectures:
Monday and Wednesday, 11:00am-12:15pm, location: 1140 Gym-Nat
Grading: 25% midterm, 25% project, 50% homework
Office Hours:
Monday 12:15-1:15pm 1140 Gym-Nat
Wednesday 10-11am 3539 Engineering Hall
Course Outline:
Part 1: Basic Theory (Weeks 1-7)
Probabilistic Decision Making
Probabilistic Inference and Model Selection
Statistical Learning Theory
Midterm Exam
Part 2: Methods, Algorithms, and Applications (Weeks 8-15)
Recommended Textbooks (both free online): Understanding Machine Learning, Statistical Learning Theory