CS 598 DLT - Special Topics - Deep Learning Theory
Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.
All class meetings will be online and synchronous. This course will overview deep learning theory, with a goal of providing students everything they need to consume and produce research in the field. Topics will include (but are not limited to): approximation, generalization, and optimization properties of deep networks. The course will provide very brief background in learning theory (e.g., an overview of Rademacher complexity); students are expected to have taken probability, linear algebra, and an introductory course in machine learning. Evaluation is based both on homeworks (in the first 50-70% of lectures, presented by the instructor), and on an in-depth course presentation. For up-to-date information about CS course restrictions, please see the following link: http://go.cs.illinois.edu/csregister
Option 1Number of Required Visit(s): 0
Course Level: Graduate