Graduate seminar SS 21 Graduate Seminar on Analysis
Mathematical Analysis of Machine Learning Methods
In the past decade powerful new machine learning methodologies have been developed. The mathematical analysis of these tools is a major challenge.In this seminar selected machine learning methods will be presented and rigorously investigated. A lot of these approaches rely on tools from analysis and calculus of variations. A particular focus will be on graph methods, and on applications in geometry processing.
Note: All seminar slots are filled now; auditing the seminar is still possible.