BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20210328T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20201025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260404T145219Z
UID:1611327600@ist.ac.at
DTSTART:20210122T160000
DTEND:20210122T170000
DESCRIPTION:Speaker: Dan Goodman\nhosted by Everton Agnes\nAbstract: The br
 ain has a hugely diverse\, heterogeneous structure. By contrast\, many fun
 ctional neural models are homogeneous. We compared the performance of spik
 ing neural networks trained to carry out difficult tasks\, with varying de
 grees of heterogeneity. Introducing heterogeneity in membrane and synapse 
 time constants substantially improved task performance\, and made learning
  more stable and robust across multiple training methods\, particularly fo
 r tasks with a rich temporal structure. In addition\, the distribution of 
 time constants in the trained networks closely matches those observed expe
 rimentally. We suggest that the heterogeneity observed in the brain may be
  more than just the byproduct of noisy processes\, but rather may serve an
  active and important role in allowing animals to learn in changing enviro
 nments. 
LOCATION:Online\, ISTA
ORGANIZER:
SUMMARY:Dan Goodman: Neural heterogeneity promotes robust learning
URL:https://talks-calendar.ista.ac.at/events/3003
END:VEVENT
END:VCALENDAR