BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:ESE Seminar: Mohamed-Ali Belabbas
X-WR-TIMEZONE:Central Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260909T073136Z
UID:tag:localist.com\,2008:EventInstance_46144974348988
DTSTART:20240419T160000Z
DTEND:20240419T170000Z
DESCRIPTION:A Control Theoretic Approach to Transfer Learning\n\nAbstract: 
 A neural network has memorized a training set if\, when fed on any sample 
 from that set\, it yields the desired output. Adopting a control theoretic
  language\, we say that the system steers each point of a learning set to 
 its corresponding target with a common control. Transfer learning and fine
  tuning deal with the issue of adapting a control to memorize additional d
 ata points. We introduce here the concept of tuning without forgetting. We
  develop an iterative algorithm to tune the control or system parameters w
 hen the training set expands\, whereby points already memorized remain so\
 , and new training samples are additional memorized. We discuss the geomet
 ric structure underlying our approach and provide simulation results.
GEO:38.648794;-90.30145
LOCATION:Preston M. Green Hall\, Rodin Auditorium\, L0120
SUMMARY:ESE Seminar: Mohamed-Ali Belabbas
URL;VALUE=URI:https://happenings.washu.edu/event/ese-seminar-mohamed-ali-be
 labbas
CATEGORIES:Seminar/Colloquia
END:VEVENT
END:VCALENDAR