BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Automatic differentiation and machine learning - Gunes Baydin\, Ma
 ynooth University
DTSTART:20150306T110000Z
DTEND:20150306T120000Z
UID:TALK58361@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Derivatives\, mostly in the form of gradients and Hessians\, a
 re ubiquitous in machine learning. Automatic differentiation (AD) is a tec
 hnique for calculating derivatives efficiently and accurately\, establishe
 d in fields such as computational fluid dynamics\, nuclear engineering\, a
 nd atmospheric sciences. Despite its advantages and use in other fields\, 
 machine learning practitioners have been little influenced by AD and make 
 scant use of available tools. We survey the intersection of AD and machine
  learning\, cover applications where AD has the potential to make a big im
 pact\, and report on some recent developments in the adoption of this tech
 nique. We also aim to dispel some misconceptions that we would contend hav
 e impeded the use of AD within the machine learning community.
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR