BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Applications of deep learning in Bayesian inversion - Ozan Öktem 
 (KTH and Alan Turing Institute)
DTSTART:20181120T130000Z
DTEND:20181120T140000Z
UID:TALK114589@talks.cam.ac.uk
CONTACT:Carola-Bibiane Schoenlieb
DESCRIPTION:The talk will show how deep neural networks can be used to com
 pute a Bayes estimator in a computationally feasible manner without explic
 itly specifying a prior or probability of data. The prior and probability 
 of data are implicitly contained in supervised data that is used to train 
 the deep neural network\, whereas the data likelihood is explicitly includ
 ed into the network architecture. Next\, we also show how to use generativ
 e adversarial networks to sample from the posterior in a computationally f
 easible manner. Both these approaches are generic\, and their performance 
 is demonstrated for tomographic reconstruction in a clinical setting.
LOCATION:MR5\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR