BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Hardware for Neural Networks - Rune Holm\, Senior Principal Engine
 er\, Machine Learning Group\, ARM
DTSTART:20171127T150000Z
DTEND:20171127T160000Z
UID:TALK95185@talks.cam.ac.uk
CONTACT:Damon Wischik
DESCRIPTION:The use of neural networks has advanced the state of the art i
 n many\nfields\, including computer vision\, speech processing and machine
 \ntranslation\, and there is reason to believe that more is yet to come.\n
 To enable all this\, one of the key challenges is to find ways to\nexecute
  neural networks efficiently on computer hardware.\n\nIn this talk\, we wi
 ll discuss how neural networks map onto\nconventional and unconventional c
 omputer architectures\, including case\nstudies for CPUs\, GPUs and dedica
 ted accelerators. We will also look\nat accelerator techniques for further
  improving performance\, as well\nas look at the challenge of keeping some
  programmability to deal with\nfuture changes in the state of the art of n
 eural networks.
LOCATION: SW01\, Computer Laboratory
END:VEVENT
END:VCALENDAR