BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Bayesian Deep Learning: From Reliable Neural Networks to Interpret
 able Foundation Models - Hao Wang - Rutgers University
DTSTART:20241101T150000Z
DTEND:20241101T160000Z
UID:TALK224002@talks.cam.ac.uk
CONTACT:Andreas Bedorf
DESCRIPTION:While perception tasks such as visual object recognition and t
 ext understanding play an important role in human intelligence\, the subse
 quent tasks that involve inference\, reasoning\, and planning require an e
 ven higher level of intelligence.  The past decade has seen major advances
  in many perception tasks using deep learning models. In terms of higher-l
 evel inference\, however\, probabilistic graphical models\, with their abi
 lity to expressively describe properties of variables and various probabil
 istic relations among variables\, are still more powerful and flexible. To
  achieve integrated intelligence that involves both perception and inferen
 ce\, we have been exploring along a research direction\, which we call Bay
 esian deep learning\, to tightly integrate deep learning and Bayesian mode
 ls within a principled probabilistic framework. In this talk\, I will pres
 ent the proposed unified framework and some of our recent work on Bayesian
  deep learning with various applications including interpretable large lan
 guage models\, network analysis\, and healthcare.\n\nBio: Hao Wang is curr
 ently an Assistant Professor in the Department of Computer Science at Rutg
 ers University. Previously he was a Postdoctoral Associate at the Computer
  Science & Artificial Intelligence Lab (CSAIL) of MIT\, working with Dina 
 Katabi and Tommi Jaakkola. He received his PhD degree from the Hong Kong U
 niversity of Science and Technology\, as the sole recipient of the School 
 of Engineering PhD Research Excellence Award in 2017. He has been a visiti
 ng researcher in the Machine Learning Department of Carnegie Mellon Univer
 sity. His research focuses on statistical machine learning\, deep learning
 \, and data mining\, with broad applications on healthcare\, network analy
 sis\, time series analysis\, etc. His work on Bayesian deep learning for r
 ecommender systems has inspired hundreds of follow-up works at ICML\, NIPS
 \, ICLR\, KDD\, etc.\, becoming the most cited paper at KDD 2015. His rese
 arch was recognized and supported by the Microsoft Fellowship in Asia\, th
 e Baidu Research Fellowship\, the Amazon Faculty Research Award\, the Micr
 osoft AI & Society Fellowship\, the NSF CAREER Award\, and an NIH R01 Awar
 d.
LOCATION:https://cam-ac-uk.zoom.us/j/84052240463?pwd=34DFKKU7JTsjVcayH5eAl
 63UCZFJk0.1
END:VEVENT
END:VCALENDAR