PIMS Network Wide Colloquium: Gunnar E. Carlsson
Topic
Topological methods for Artificial Intelligence
Speakers
Details
The recent striking developments in artificial intelligence underscore the idea that we need to (a) understand better what goes on inside neural networks, (b) thereby gain more control over them and (c) develop methods that are less expensive and apply directly to specialized situations. In this talk, I will talk about work on methods using topological methods to address these three problems. In particular, I will include numerous examples.
Additional Information
Speaker Bio:
Gunnar E. Carlsson is Professor Emeritus of Mathematics at Stanford University, where his research spans algebraic topology and its applications to data analysis. Widely recognized for his contributions to the Segal conjecture and for pioneering the field of topological data analysis, he has led major research initiatives supported by the National Science Foundation and the Defense Advanced Research Projects Agency. He is the lead organizer of the ATMCS conference series, serves on the editorial boards of several mathematics journals, and is a member of the Scientific Advisory Board of the Wallenberg AI, Autonomous Systems and Software Program in Sweden.