BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Flux: Elegant Machine Learning with Julia - Mike Innes\, Julia Com
 puting\, Inc.
DTSTART:20181018T160000Z
DTEND:20181018T170000Z
UID:TALK113215@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:This talk will introduce Flux\, a library for machine learning
  (ML). Flux is written in Julia\, a language designed for high-performance
  numerical computing\, in around 1\,000 lines of straightforward code. Thi
 s talk will explain how to build Flux\, starting with the basics of Julia 
 and how it compiles high-level mathematical programs to tight machine code
 \, and how the compiler can be extended to support ML.\n\nDeep learning mo
 dels have become complex\, and increasingly look like "differentiable algo
 rithms"\; through this lens\, ML systems problems become language and comp
 iler problems. We illustrate how augmenting a numerical language with comp
 iler-level automatic differentiation enables an unusually flexible and hac
 kable approach to ML\, one which provides an elegant define-by-run style w
 hile supporting new kinds of models\, cutting edge hardware and state-of-t
 he-art performance.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR