BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:33616435-3438-4933-b061-303734623634
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:Computational Visual Pathways for Multi-Task Learning and Simu
 lation - Rogerio Feris\, Principal Scientist and Manager\, MIT-IBM Watson 
 AI Lab
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20231105T090000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20211107T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20221106T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20210314T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20220313T020000
RDATE:20230312T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:8ce06902-a478-409d-baa5-65c05a0fac1f
DTSTAMP:20260125T043445Z
CLASS:PUBLIC
CREATED:20211103T003412Z
DESCRIPTION:Please register for this event here. Abstract: In this talk\, I
  will describe approaches that learn data-dependent computational pathways
  for visual recognition. First\, in the context of multi-task learning\, I
  will show a method that learns separate computational pathways for differ
 ent tasks within a unified deep neural network model\, effectively decidin
 g which features should be shared across tasks\, and which features should
  be task-specific\, in order to prevent negative interference. Then\, I wi
 ll show how this approach can be extended to optimize for synthetic traini
 ng data generation…
DTSTART;TZID=America/Vancouver:20211130T140000
DTEND;TZID=America/Vancouver:20211130T150000
LAST-MODIFIED:20211103T011334Z
LOCATION:Please register to receive the Zoom link
SUMMARY:Computational Visual Pathways for Multi-Task Learning and Simulatio
 n - Rogerio Feris\, Principal Scientist and Manager\, MIT-IBM Watson AI La
 b
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/computational-visual-pathways-multi-task-lea
 rning-and-simulation-rogerio-feris-principal
END:VEVENT
END:VCALENDAR