Bahman Gharesifard (Queen's University)

Math & Stats Department Colloquium
Friday, September 6, 2024

Time: 2:30 p.m.  Place: Jeffery Hall, Room 234

Speaker: Bahman Gharesifard (Queen's University)

Title: Universal Approximation

Abstract: Bahman Gharesifard will provide a historical overview of the universal approximation theory for neural networks and offer some geometric results for the challenging case of deep neural networks, which have bounded width.

Bio: Bahman Gharesifard obtained his Ph.D. in Mathematics from Queen’s University in 2009. He held postdoctoral positions at the University of California, San Diego, and at the University of Illinois at Urbana-Champaign. He joined Queen’s University from 2013 to 2021, and was an Alexander von Humboldt Foundation Fellow at the University of Stuttgart from 2019-2020. He then moved to University of California, Los Angeles, as Professor with the Electrical & Computer Engineering Department. In 2024, he re-joined Queen’s as Professor of Mathematics with the Department of Mathematics and Statistics.