BEGIN:VCALENDAR
VERSION:2.0
PRODID:researchseminars.org
CALSCALE:GREGORIAN
X-WR-CALNAME:researchseminars.org
BEGIN:VEVENT
SUMMARY:Siddhartha Mishra (ETH Zurich\, Switzerland)
DTSTART:20201001T093000Z
DTEND:20201001T103000Z
DTSTAMP:20260423T004731Z
UID:WOPARA/4
DESCRIPTION:Title: <a href="https://researchseminars.org/talk/WOPARA/4/">D
 eep Learning and Computations of PDEs</a>\nby Siddhartha Mishra (ETH Zuric
 h\, Switzerland) as part of Webinar on PDE and related areas\n\n\nAbstract
 \nDeep neural networks are rapidly emerging as a key tool in en-hancing  c
 omputations  of  PDEs.   In  this  talk\,  we  survey  recent  development
 sin my research group on two related themes.  First\, we use supervised le
 arningto approximate observables for PDEs efficiently with applications to
  UQ andPDE constrained optimization.  Second\, we discuss recently introdu
 ced physicsinformed  neural  networks  (PINNs)  as  an  efficient  discret
 ization  tool  for  bothforward as well as inverse problems for certain cl
 asses of PDEs.\n
LOCATION:https://researchseminars.org/talk/WOPARA/4/
END:VEVENT
END:VCALENDAR