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:The Archimedeans
SUMMARY:The Future of Mathematics in the Age of Artificial
Intelligence - Speaker to be confirmed
DTSTART;TZID=Europe/London:20220429T180000
DTEND;TZID=Europe/London:20220429T190000
UID:TALK173738AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/173738
DESCRIPTION:Despite the outstanding success of deep neural net
works in real-world applications\, ranging from sc
ience to public life\, most of the related researc
h is empirically driven and a comprehensive mathem
atical foundation is still missing. At the same ti
me\, these methods have already shown their impres
sive potential in mathematical research areas such
as imaging sciences\, inverse problems\, or numer
ical analysis of partial differential equations\,
sometimes by far outperforming classical mathemati
cal approaches for particular problem classes.\n\n
The goal of this lecture is to first provide an in
troduction into this new vibrant research area. We
will then survey recent advances in two direction
s\, namely the development of a mathematical found
ation of deep learning and the introduction of nov
el deep learning-based approaches to solve mathema
tical problem settings.
LOCATION:Zoom
CONTACT:
END:VEVENT
END:VCALENDAR