BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20250813T185209EDT-2053PBTrfi@132.216.98.100
DTSTAMP:20250813T225209Z
DESCRIPTION:Title: The Modern Mathematics of Deep Learning\n\nAbstract: Des
 pite the outstanding success of deep neural networks in real-world applica
 tions\, ranging from science to public life\, most of the related research
  is empirically driven and a comprehensive mathematical foundation is stil
 l missing. At the same time\, these methods have already shown their impre
 ssive potential in mathematical research areas such as imaging sciences\, 
 inverse problems\, or numerical analysis of partial differential equations
 \, sometimes by far outperforming classical mathematical approaches for pa
 rticular problem classes. The goal of this lecture is to first provide an 
 introduction into this new vibrant research area. We will then survey rece
 nt advances in two directions\, namely the development of a mathematical f
 oundation of deep learning and the introduction of novel deep learning-bas
 ed approaches to mathematical problem settings.\n\n \n\n \n\nTo register c
 ontact : appliedseminars [at] math.mcgill.ca\n
DTSTART:20210927T183000Z
DTEND:20210927T193000Z
SUMMARY:Gitta Kutyniok (LMU Munich)
URL:/mathstat/channels/event/gitta-kutyniok-lmu-munich
 -333649
END:VEVENT
END:VCALENDAR