BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20240331T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20231029T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260424T141120Z
UID:1706524200@ist.ac.at
DTSTART:20240129T113000
DTEND:20240129T123000
DESCRIPTION:Speaker: Angelika Steger\nhosted by Uli Wagner\nAbstract: One o
 f the defining characteristics of biological intelligence is its rapid ada
 ptability to new environments\, a trait explored in cognitive science thro
 ugh reversal learning tasks.  In this talk we present a novel approach  
 for the multi-armed bandit problem\, the machine learning analogue of the 
 reversal learning paradigm\, that departs from the traditional method of e
 stimating values. Instead\, our method relies on continuously holding a be
 lief about the best current option\, coupled with a verification mechanism
  that periodically assesses this belief's validity. We demonstrate that ou
 r approach not only theoretically outperforms the best known algorithm but
  also explains well measured data across various experimental settings. 
LOCATION:Raiffeisen Lecture Hall\, ISTA
ORGANIZER:arinya.eller@ist.ac.at
SUMMARY:Angelika Steger: Efficient and robust reversal learning
URL:https://talks-calendar.ista.ac.at/events/4241
END:VEVENT
END:VCALENDAR