BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VTIMEZONE
TZID:Europe/Vienna
BEGIN:DAYLIGHT
DTSTART:20220327T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260424T143354Z
UID:1663599600@ist.ac.at
DTSTART:20220919T170000
DTEND:20220919T180000
DESCRIPTION:Speaker: Yann LeCun\nhosted by Tom Henzinger and Ulrike Diebold
 \nAbstract: +++Registration for this event is closed.  A recording of the
  lecture will be availabie on the ISTA YouTube channel (https://www.youtu
 be.com/user/ISTAustria) after it has taken place.+++The Austrian Academy 
 of Sciences and ISTA have initiated a joint lecture series aiming to bring
  to Austria speakers of the highest international standing active in field
 s that are of mutual interest to both institutions and to a wider public.
   We are honored to welcome Yann LeCun as this year's lecture speaker.Abs
 tractHow could machines learn as efficiently as humans and animals?How cou
 ld machines learn to reason and plan?How could machines learn representati
 ons of percepts and action plans at multiple levels of abstraction\, enabl
 ing them to reason\, predict\, and plan at multiple time horizons?In his t
 alk\, Yann LeCun will propose a possible path towards autonomous intellig
 ent agents\, based on a new modular cognitive architecture and a somewhat 
 new self-supervised training paradigm. The centerpiece of the proposed a
 rchitecture is a configurable predictive world model that allows the agen
 t to plan.  Behavior and learning are driven by a set of differentiable 
 intrinsic cost functions.  The world model uses a new type of energy-bas
 ed model architecture called H-JEPA (Hierarchical Joint Embedding Predict
 ive Architecture). H-JEPA learns hierarchical abstract representations of
  the world that are simultaneously maximally informative and maximally pr
 edictable.The corresponding working paper is available here (https://openr
 eview.net/forum?id=BZ5a1r-kVsf).BioYann LeCun is VP & Chief AI Scientist a
 t Meta and Silver Professor at NYU affiliated with the Courant Institute o
 f Mathematical Sciences & the Center for Data Science. He was the founding
  Director of FAIR and of the NYU Center for Data Science. He received an E
 ngineering Diploma from ESIEE (Paris) and a PhD from Sorbonne Université.
  After a postdoc in Toronto he joined AT&T Bell Labs in 1988\, and AT&T La
 bs in 1996 as Head of Image Processing Research. He joined NYU as a profes
 sor in 2003 and Meta/Facebook in 2013. His interests include AI machine le
 arning\, computer perception\, robotics and computational neuroscience. He
  is the recipient of the 2018 ACM Turing Award (with Geoffrey Hinton and Y
 oshua Bengio) for "conceptual and engineering breakthroughs that have made
  deep neural networks a critical component of computing"\, a member of the
  National Academy of Sciences\, the National Academy of Engineering\, the 
 French Académie des Sciences.Transportation to/from campus:In addition to
  the regular ISTA shuttle bus #142 (https://ist.ac.at/en/campus/how-to-get
 -here/)\, an extra shuttle bus has been organized from U4 Schwedenplatz/n
 ight bus stop\, which will depart at 4:00 p.m. It will return to Schwedenp
 latz and depart from the ISTA campus at 7:45 p.m.ISTA Lecture Young Lounge
 If you are a highschool student and are interested to meet the speaker in 
 advance of the lecture in the ISTA Lecture Young Lounge (3:45-4:15 pm)\, p
 lease get in touch with magdalena.steinrueck@ist.ac.at (mailto:magdalena.s
 teinrueck@ist.ac.at?subject=LeCun%20Young%20Lounge%20Inquiry&body=***%20De
 ar%20student%2C%20In%20this%20email%2C%20please%20send%20us%20your%20name%
 2C%20age%2C%20class%2C%20school%2C%20and%20confirm%20that%20you%20are%20wi
 lling%20to%20attend%20both%20the%20Young%20Lounge%20and%20the%20Lecture%20
 in%20person%20and%20read%20preparatory%20material.%20We%20will%20let%20you
 %20know%20as%20soon%20as%20possible%20if%20we%20can%20offer%20you%20as%20s
 pot%20(first%20come%20first%20serve).%20Best%20wishes%2C%20Magdalena%20fro
 m%20the%20ISTA%20Science%20Education%20Team%20***) - Spots are limited! In
 terested teachers who would like to come with a small group of students ar
 e welcome to get in touch too. We will provide advance material to help yo
 u get the best out of the conversation with our speaker and the lecture.
LOCATION:Raiffeisen Lecture Hall\, ISTA
ORGANIZER:arinya.eller@ist.ac.at
SUMMARY:Yann LeCun: From machine learning to autonomous intelligence
URL:https://talks-calendar.ista.ac.at/events/3867
END:VEVENT
END:VCALENDAR