BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep and reliable – Uncertainty quantification using Empirical B
 ayesian deep neural networks. - Stefan Franssen (TU Delft)
DTSTART:20220126T140000Z
DTEND:20220126T150000Z
UID:TALK167080@talks.cam.ac.uk
CONTACT:Randolf Altmeyer
DESCRIPTION:Deep learning is a popular tool for making inferences\, as it 
 has good performance in many practical applications. Since data scientists
  use deep learning\, we should give theoretical guarantees on the quality 
 of the constructed estimator. For some applications\, it is not enough to 
 have theoretical guarantees on the estimation error\, but\, in addition\, 
 practitioners need to quantify uncertainty. To quantify that\, a practitio
 ner can construct confidence sets. Researchers have only recently started 
 giving theoretical guarantees on the accuracy of deep learning. The constr
 uction of confidence statements is still an open problem. In this talk\, I
  will first go over the general ideas and concepts\, discussing some earli
 er proposed methods for uncertainty quantification before diving into my c
 ontribution. I introduce a new Bayesian methodology: Empirical Bayesian de
 ep neural networks (EBDNN). EBDNN is the first methodology with theoretica
 l guarantees: the uncertainty quantification produced is valid from a freq
 uentist point of view. Moreover\, EBDNN is much faster to compute than alt
 ernative methods proposed for uncertainty quantification. Joint work with 
 Botond Szabó.\n\n\n\n*Join Zoom Meeting*\nhttps://maths-cam-ac-uk.zoom.us
 /j/99412853967?pwd=enFwNFpZcG0zM0o2WVlRQm1LdEttdz09\n\nMeeting ID: 994 128
 5 3967\nPasscode: 026816
LOCATION:Virtual (Zoom details under abstract)
END:VEVENT
END:VCALENDAR