BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Learning Posterior Distributions in Underdetermined Inverse Proble
 ms - Christina Runkel\, DAMTP\, Cambridge Image Analysis.
DTSTART:20240522T090000Z
DTEND:20240522T100000Z
UID:TALK217087@talks.cam.ac.uk
CONTACT:Dr Priscilla Canizares
DESCRIPTION:In recent years\, classical knowledge-driven approaches for in
 verse problems have been complemented by data-driven methods exploiting th
 e power of machine and especially deep learning. Purely data-driven method
 s\, however\, come with the drawback of disregarding prior knowledge of th
 e problem even though it has shown to be beneficial to incorporate this kn
 owledge into the problem-solving process.\n\nIn this talk\, we thus introd
 uce an unpaired learning approach for learning posterior distributions of 
 underdetermined inverse problems. It combines advantages of deep generativ
 e modeling with established ideas of knowledge-driven approaches by incorp
 orating prior information about the inverse problem\n
LOCATION:Martin Ryle Seminar Room\, KICC
END:VEVENT
END:VCALENDAR