BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Algorithmic Differentiation (AD) Beyond Back Propagation - Uwe Nau
 mann\, RWTH Aachen University\, and NAG Ltd.\, Oxford\, UK
DTSTART:20200123T113000Z
DTEND:20200123T123000Z
UID:TALK138466@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Back propagation amounts to adjoint AD of neural networks. It 
 is relatively simple to understand and implement. First- and higher-order 
 AD of large-scale numerical simulation programs yields a number of challen
 ges some of which will be discussed during this presentation. Topics to be
  commented on include the use of symbolic adjoints inside of algorithmic a
 djoints\, the validation of derivative code using differential invariants\
 , and parallel AD.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR