BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Interpretability as the Inverse Machine Learning Pipeline - Prof. 
 Sarah Wiegreffe (University of Maryland)
DTSTART:20251112T150000Z
DTEND:20251112T160000Z
UID:TALK237775@talks.cam.ac.uk
CONTACT:Lucas Resck
DESCRIPTION:Bio: Prof. Sarah Wiegreffe is an natural language processing a
 nd machine learning researcher and an assistant professor in the Departmen
 t of Computer Science at the University of Maryland. She works on the expl
 ainability and interpretability of deep learning systems for language\, wi
 th a focus on understanding how language models make predictions in order 
 to make them more reliable\, safe\, and transparent to human users. She ha
 s been honored as a 3-time Rising Star in EECS\, Machine Learning\, and Ge
 nerative AI. She was previously a postdoc at the Allen Institute for AI an
 d the University of Washington and\, before that\, received her Ph.D. and 
 M.S. degrees from Georgia Tech.
LOCATION:https://cam-ac-uk.zoom.us/j/97599459216?pwd=QTRsOWZCOXRTREVnbTJBd
 XVpOXFvdz09
END:VEVENT
END:VCALENDAR