BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210916T132454Z
LOCATION:Lise Girardin
DTSTART;TZID=Europe/Stockholm:20210708T180000
DTEND;TZID=Europe/Stockholm:20210708T183000
UID:submissions.pasc-conference.org_PASC21_sess166_msa128@linklings.com
SUMMARY:How Can Physics Inform the Design of Intelligence?
DESCRIPTION:Minisymposium\n\nHow Can Physics Inform the Design of Intellig
 ence?\n\nToth, Rezende, Jaegle, Racaniere, Botev...\n\nBiological intellig
 ence did not evolve in a vacuum - its design and function are constrained 
 and guided by the core structures of our universe. In this talk I will pre
 sent a hypothesis that in order to build artificial intelligence, it is al
 so important to consider the fundamentals of our world structure as descri
 bed by modern physics. In particular, I will talk about the importance of 
 good representations for building robust and efficient intelligent systems
 , what these representations should look like, and how the Hamiltonian for
 malism and the idea of symmetries from physics may be helpful in learning 
 such good representations from sensory observations.\n\nDomain: CS and Mat
 h, Emerging Applications, Physics, Engineering
END:VEVENT
END:VCALENDAR