BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:RSE Seminars
SUMMARY:Automatic differentiation - an RSE's eye view - Ma
 tt Graham - ARC\, UCL
DTSTART;TZID=Europe/London:20251120T130000
DTEND;TZID=Europe/London:20251120T140000
UID:TALK234403AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/234403
DESCRIPTION:Automatic or algorithmic differentiation (AD) unde
 rpins much of the current boom in use of machine l
 earning methods but is also widely used in other s
 cientific computing contexts.\n\nIn this talk I wi
 ll give an overview of what automatic differentiat
 ion is and a brief summary of its history. I will 
 then review how it relates to symbolic and numeric
 al differentiation\, how forward- and reverse-mode
  AD differ and some of the different approaches to
  implementing AD frameworks\, before demonstrating
  how AD is used in practice with some applied exam
 ples. I will conclude with some discussion of my e
 xperiences of using various automatic differentiat
 ion implementations in research software projects 
 I have worked on\, particularly from a context of 
 the trade-offs between ease of use and maintainabi
 lity and generality of code a framework can differ
 entiate.
LOCATION:Room A\, West Hub
CONTACT:Jack Atkinson
END:VEVENT
END:VCALENDAR