BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:35626135-3565-4332-b837-636234643937
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:CVL Talk: Biologically Plausible Learning Using Local Activity
  Perturbation - Mengye Ren\, NYU
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20250309T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20221106T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20231105T020000
RDATE:20241103T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20230312T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20240310T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:bead1dce-417a-434a-99fc-f26f9ca61ac5
DTSTAMP:20260527T010041Z
CLASS:PUBLIC
CREATED:20230614T222912Z
DESCRIPTION:Abstract: Backprop is usually considered biologically implausib
 le due to the issues of weight transport and global synchronization. Pertu
 rbation learning is potentially a good candidate for a biologically plausi
 ble alternative\, since it does not require explicit backward weights\, an
 d recent advances in local greedy learning has suggested that deep network
 s can be trained well without global end-to-end learning. Forward-mode aut
 omatic differentiation can also be used to compute the effect of perturbat
 ion and can be viewed as the time derivative of an analog signal. These to
 ols have shown us new…
DTSTART;TZID=America/Vancouver:20230623T150000
DTEND;TZID=America/Vancouver:20230623T160000
LAST-MODIFIED:20230615T174021Z
LOCATION:UBC Vancouver Campus\, ICCS X836
SUMMARY:CVL Talk: Biologically Plausible Learning Using Local Activity Pert
 urbation - Mengye Ren\, NYU
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/cvl-talk-biologically-plausible-learning-usi
 ng-local-activity-perturbation-mengye-ren-nyu
END:VEVENT
END:VCALENDAR