Event Date
Speaker: Song Mei, Assistant Professor, Dept. Statistics / Dept. Electrical Engineering and Computer Sciences, UC Berkeley
Title: "Revisiting neural network approximation theory in the age of generative AI"
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.
Faculty webpage (links to UC Berkeley): https://www.stat.berkeley.edu/~songmei/
Seminar Date/Time: Thursday February 15th, 4:10pm (Refreshments: 3:30pm)
Location: MSB 1147 (Colloquium Room)