BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20200329T030000
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:20260404T053028Z
UID:1599829200@ist.ac.at
DTSTART:20200911T150000
DTEND:20200911T160000
DESCRIPTION:Speaker: Kenji Doya\nhosted by Tim Vogels\nAbstract: Deep learn
 ing is a prime example of how brain-inspired computing can benefit develop
 ment of artificial intelligence. But what else can we learn from the brain
  for bringing AI and robotics to the next level? Energy efficiency and dat
 a efficiency are the major features of the brain and human cognition that 
 today’s deep learning has yet to deliver. The brain can be seen as a mul
 ti-agent system of heterogeneous learners using different representations 
 and algorithms. The flexible use of reactive\, model-free control and mode
 l-based “mental simulation” appears to be the basis for computational 
 and data efficiency of the brain. How the brain efficiently acquires and f
 lexibly combines prediction and control modules is a major open problem in
  neuroscience and its solution should help developments of more flexible a
 nd autonomous AI and robotics.
LOCATION:https://www.crowdcast.io/e/kenji-doyes\, ISTA
ORGANIZER:
SUMMARY:Kenji Doya: [Online] What can we further learn from the brain for a
 rtificial intelligence?
URL:https://talks-calendar.ista.ac.at/events/2854
END:VEVENT
END:VCALENDAR