BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:What do regularisers do? - Tuomo Valkonen (University of Liverpool
 )
DTSTART:20171102T172000Z
DTEND:20171102T181000Z
UID:TALK94372@talks.cam.ac.uk
CONTACT:INI IT
DESCRIPTION:Which regulariser is the best? Is any of them any good? Do the
 y introduce artefacts? What other qualitative properties do they&nbsp\;hav
 e? These are some questions\, on which I want to shed some light of the ea
 rly dawn. Specifically\, I will firstly discuss recent work on&nbsp\;natur
 al conditions\, based on an analytical study of a bilevel learning approac
 h\, to ensure that regularisation does indeed improve an image. Based on a
  more computational study\, based on bilevel learning\, I will also try to
  answer the question\, which constructed regulariser is the best one.&nbsp
 \;Secondly\, I will discuss geometrical aspects of the solutions to higher
 -order regularised imaging problems.
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR