BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Modern Deep Learning through Bayesian Eyes - Yarin Gal\, Universit
 y of Cambridge
DTSTART:20160212T120000Z
DTEND:20160212T130000Z
UID:TALK62786@talks.cam.ac.uk
CONTACT:Kris Cao
DESCRIPTION:Bayesian models are rooted in Bayesian statistics\, and easily
  benefit from the vast literature in the field. In contrast\, deep learnin
 g lacks a solid mathematical grounding. Instead\, empirical developments i
 n deep learning are often justified by metaphors\, evading the unexplained
  principles at play. These two fields are perceived as fairly antipodal to
  each other in their respective communities. It is perhaps astonishing the
 n that most modern deep learning models can be cast as performing approxim
 ate inference in a Bayesian setting. The implications of this statement ar
 e profound: we can use the rich Bayesian statistics literature with deep l
 earning models\, explain away many of the curiosities with these\, combine
  results from deep learning into Bayesian modelling\, and much more. \n\nI
 n this talk I will explore the new theory linking Bayesian modelling and d
 eep learning. The practical impact of the framework will be demonstrated w
 ith a range of real-world applications: from uncertainty modelling in deep
  learning\, through training on small datasets\, to state-of-the-art resul
 ts in image processing. I will finish by surveying open problems to resear
 ch\, problems which stand at the forefront of a new and exciting field com
 bining modern deep learning and Bayesian techniques.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR