BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:830-199@badw.de
CLASS: PUBLIC
SUMMARY:Next Generation. From Machine Learning to Autonomous Intelligence
DESCRIPTION:How could machines learn as efficiently as humans and animals? 
 How could machines learn to reason and plan? How could machines learn repre
 sentations of percepts and action plans at multiple levels of abstraction, 
 enabling them to reason, predict, and plan at multiple time horizons? Prof.
  Dr. Yann LeCun, Chief AI Scientist for Meta AI Research and Silver Profess
 or at the Courant Institute of Mathematical Sciences at New York University
  will propose a possible path towards autonomous intelligent agents, based 
 on a new modular cognitive architecture and a somewhat new self-supervised 
 training paradigm. The centerpiece of the proposed architecture is a config
 urable predictive world model that allows the agent to plan. Behavior and l
 earning are driven by a set of differentiable intrinsic cost functions. The
  world model uses a new type of energy-based model architecture called H-JE
 PA (Hierarchical Joint Embedding Predictive Architecture). H-JEPA learns hi
 erarchical abstract representations of the world that are simultaneously ma
 ximally informative and maximally predictable. The event is organized by Pr
 of. Dr. Gitta Kutyniok, Bavarian AI-Chair for Mathematical Foundations of A
 rtificial Intelligence at the Ludwig-Maximilians-Universität München, the p
 rofessorship is funded by the Hightech Agenda Bayern. She is spokesperson o
 f the CAS Research Focus "Next Generation AI" at the Center for Advanced St
 udies at LMU and LMU-Director of the Konrad Zuse School of Excellence for R
 eliable AI (relAI). The following ecosystem-partners support the event: Cen
 ter for Advanced Studies (CAS) at LMU, baiosphere – the Bavarian AI Network
 , BAdW – Bayerische Akademie der Wissenschaften, bidt – Bavarian Research I
 nstitute for Digital Transformation, MCML – Munich Center for Machine Learn
 ing, Konrad Zuse School of Excellence in Reliable AI (relAI). The LMU AI Ta
 lk is part of the CAS Research Focus "Next Generation AI" and supported by 
 baiosphere – the Bavarian AI Network
LOCATION:Bayerische Akademie der Wissenschaften
DTSTAMP:20251111T140042Z
DTSTART:20230929T121500Z
END:VEVENT
END:VCALENDAR