Dear Colleagues,
The ASA Statistical Learning and Data Science Section is pleased to announce its first webinar in 2025, featured by Prof. Song Mei from UC Berkerley. Prof. Mei will give a deep insight into the success of modern generative AI models through the perspective of algorithm approximator. Hope to see you there!
Title: Revisiting neural network approximation theory in the age of generative AI
Speakers: Dr. Song Mei, Department of Statistics and Department of Electrical Engineering and Computer Sciences, University of California, Berkeley
Date and Time: January 22, 2025, 2:00 to 3:30 pm Eastern Time
Registration Link: ASA SLDS Webinar Registration Link [eventbrite.com]
Abstract: Textbooks on deep learning theory primarily perceive neural networks as universal function approximators. While this classical viewpoint is fundamental, it inadequately explains the impressive capabilities of modern generative AI models such as language models and diffusion models. This talk puts forth a refined perspective: neural networks often serve as algorithm approximators, going beyond mere function approximation. I will explain how this refined perspective offers a deeper insight into the success of modern generative AI models.
Presenter: Song Mei is an assistant professor of statistics and EECS at UC Berkeley. He received his Ph. D. from Stanford in June 2020. His research lies at the intersection of statistics and machine learning. His recent research focuses on the theory of deep learning and generative AI models. Song has received an NSF career award, an Amazon Research Award, and a Google Research Scholar Award.
------------------------------
Zhihua Su, PhD
Associate Professor
Department of Statistics
University of Florida
zhihuasu@stat.ufl.edu------------------------------