BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Automatic differentiation - an RSE's eye view - Matt Graham - ARC\
 , UCL
DTSTART:20251120T130000Z
DTEND:20251120T140000Z
UID:TALK234403@talks.cam.ac.uk
CONTACT:Jack Atkinson
DESCRIPTION:Automatic or algorithmic differentiation (AD) underpins much o
 f the current boom in use of machine learning methods but is also widely u
 sed in other scientific computing contexts.\n\nIn this talk I will give an
  overview of what automatic differentiation is and a brief summary of its 
 history. I will then review how it relates to symbolic and numerical diffe
 rentiation\, how forward- and reverse-mode AD differ and some of the diffe
 rent approaches to implementing AD frameworks\, before demonstrating how A
 D is used in practice with some applied examples. I will conclude with som
 e discussion of my experiences of using various automatic differentiation 
 implementations in research software projects I have worked on\, particula
 rly from a context of the trade-offs between ease of use and maintainabili
 ty and generality of code a framework can differentiate.
LOCATION:Room A\, West Hub
END:VEVENT
END:VCALENDAR