Information Theory and Learning

1 Unit · Graduate

This course gives students analytical tools to quantify information, perform inference, and study the relationship of information and learning. The course covers information measures, the source and the channel coding theorems, statistical inference, and learning with neural networks. In particular, the course explores a common set of models and tools used by both machine learning and state-of-the-art data compression and error-control codes. This course is aimed at students in engineering, science, mathematics, and computing. It expects familiarity with undergraduate-level calculus, probability theory, and linear algebra. Perquisite: Students must have graduate standing to register for this course.