BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260308T210612Z
UID:68776f9104d40763009008@ist.ac.at
DTSTART:20260507T110000
DTEND:20260507T120000
DESCRIPTION:Speaker: Nachi Stern\nhosted by Carl Goodrich\nAbstract: From e
 lectrically responsive neuronal networks to immune repertoires\, biologica
 l systems can learn to perform complex tasks. In this seminar\, we explore
  physical learning\, a framework inspired by computational learning theory
  and biological systems\, where networks physically adapt to applied force
 s to adopt desired functions. Unlike traditional engineering approaches or
  artificial intelligence\, physical learning is facilitated by physically 
 realizable learning rules\, requiring only local responses and no explicit
  information about the desired functionality. Our research shows that such
  local learning rules can be derived for broad classes of physical network
 s and that physical learning is indeed physically realizable\, without com
 puter aid\, through laboratory experiments. We take further inspiration fr
 om learning in the brain and demonstrate the success of physical learning 
 beyond the quasi-equilibrium regime\, enabling physical systems to adapt c
 omplex dynamical functions. By leveraging the advances of statistical lear
 ning theory in physical machines\, we propose physical learning as a promi
 sing bridge between computational machine learning and biology\, with the 
 potential to enable the development of power-efficient AI platforms\, and 
 new classes of smart metamaterials that adapt in-situ to users needs.
LOCATION:Mondi Seminar Room 2\, Central Building\, ISTA
ORGANIZER:cpetz@ist.ac.at
SUMMARY:Nachi Stern: Learning without neurons in physical systems
URL:https://talks-calendar.ista.ac.at/events/6287
END:VEVENT
END:VCALENDAR