Courses
TTIC Core ML Course Sequence
CS 35300 Mathematical Foundations of Machine Learning
TTIC 31020 Introduction to Statistical Machine Learning
This is a graduate-level CS course with the main target audience being TTIC PhD students (for which it is required) and other CS, statistics, CAM and math PhD students with an interest in machine learning. PhD students in other departments, as well as masters students and undergraduates, with sufficient mathematical and programming background, are also welcome to take the course, at the instructor’s permission. The course relies on a good math background, as can be expected from a CS PhD student. It provides a systematic introduction to machine learning and survey of a wide range of approaches and techniques. The course this coming year will probably a bit heavier, covering slightly more material, compared to the past 2-3 years.
TTIC 31120 Statistical and Computational Learning Theory
This is a rigorous mathematical course providing an analytic view of machine learning. It requires a high degree of mathematical maturity, typical of mathematically-oriented CS and statistics PhD students or math graduates. It is typically taken by students who have already taken TTIC 31020 or a similar course, but is sometimes appropriate as a first machine learning course for very mathematical students that prefer understanding a topic through definitions and theorems rather then examples and applications.
TTIC 31230 Fundamentals of Deep Learning
Focuses specifically on deep learning and emphasizes theoretical and intuitive understanding. Requires TTIC 31020 as a prerequisite, and relies on a similar or slightly higher mathematical preparation.
UC Core Course Sequence for ML PhD Students
CS 35300 Mathematical Foundations of Machine Learning
CS 35400 Machine Learning
TTIC 31020 Introduction to Statistical Machine Learning
This is a graduate-level CS course with the main target audience being TTIC PhD students (for which it is required) and other CS, statistics, CAM and math PhD students with an interest in machine learning. PhD students in other departments, as well as masters students and undergraduates, with sufficient mathematical and programming background, are also welcome to take the course, at the instructor’s permission. The course relies on a good math background, as can be expected from a CS PhD student. It provides a systematic introduction to machine learning and survey of a wide range of approaches and techniques. The course this coming year will probably a bit heavier, covering slightly more material, compared to the past 2-3 years.