BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:634@fds.yale.edu
DTSTART;TZID=America/New_York:20241002T113000
DTEND;TZID=America/New_York:20241002T130000
DTSTAMP:20250916T142139Z
URL:https://fds.yale.edu/events/fds-colloquium-song-mei-berkeley/
SUMMARY:FDS Colloquium: Song Mei (Berkeley)\, "Revisiting neural network ap
 proximation theory in the age of generative AI"
DESCRIPTION:Optional Zoom link: https://yale.zoom.us/j/97222935172 \n\n\n\n
 Abstract: Textbooks on deep learning theory primarily perceive neural net
 works as universal function approximators. While this classical viewpoint 
 is fundamental\, it inadequately explains the impressive capabilities of m
 odern generative AI models such as language models and diffusion models. T
 his 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 suc
 cess of modern generative AI models.\n\n\n\nBio: Song Mei is an assista
 nt 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 stat
 istics 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. \
 n
CATEGORIES:FDS Events,Colloquium
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
END:VCALENDAR