BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Iterative methods for solving linear inverse problems with neural 
 network coders - Otmar Scherzer (Universität Wien)
DTSTART:20230620T150000Z
DTEND:20230620T160000Z
UID:TALK200431@talks.cam.ac.uk
DESCRIPTION:Neural networks functions are considered to be able to describ
 e the desired solution of an inverse problem&nbsp\;very efficiently\, thus
  allow for sparse encoding of the desired reconstruction. &nbsp\;In this t
 alk we consider the problem of solving linear inverse problems with neural
  network coders with a Gauss-Newton method.In an abstract setting this pro
 blem has been considered for some time\, for instance under the name of st
 ate space regularization.&nbsp\;In this paper we prove a local convergence
  results for some Gauss-Newton method.&nbsp\;\nThis is a joint work with L
 eon Frischauf\, Bernd Hofmann\, Zuhair Nashed and Cong Shi
LOCATION:Seminar Room 1\, Newton Institute
END:VEVENT
END:VCALENDAR