AI-Talk by Yann LeCun: From Machine Learning to Autonomous Intelligence

29 September 2023, 14:15 to 15:30

Watch this LMU AI Talk as part of the CAS Research Focus "Next Generation AI" and supported by baiosphere – the Bavarian AI Network

Image of poster reading 'CAS Research Focus: NEXT GENERATION AI'

How could machines learn as efficiently as humans and animals? How could machines learn to reason and plan? How could machines learn representations 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 Professor 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 configurable predictive world model that allows the agent to plan. Behavior and learning are driven by a set of differentiable intrinsic cost functions. The world model uses a new type of energy-based model architecture called H-JEPA (Hierarchical Joint Embedding Predictive Architecture). H-JEPA learns hierarchical abstract representations of the world that are simultaneously maximally informative and maximally predictable.

The event is organized by Prof. Dr. Gitta Kutyniok, Bavarian AI-Chair for Mathematical Foundations of Artificial Intelligence at the Ludwig-Maximilians-Universität München, the professorship is funded by the Hightech Agenda Bayern. She is spokesperson of the CAS Research Focus "Next Generation AI" at the Center for Advanced Studies at LMU and LMU-Director of the Konrad Zuse School of Excellence for Reliable AI (relAI). The following ecosystem-partners support the event: Center for Advanced Studies (CAS) at LMU, baiosphere – the Bavarian AI Network, BAdW – Bayerische Akademie der Wissenschaften, bidt – Bavarian Research Institute for Digital Transformation, MCML – Munich Center for Machine Learning, Konrad Zuse School of Excellence in Reliable AI (relAI).

CAS logo MCML logo Baiosphere Logo

MCML logo Bayerisches Forschungsinstitut für Digitale Transformation (bidt) logo Baiosphere Logo

Registration to attend in person has closed. You can watch the livestream here:

Prof. Dr. Yann LeCun

Courant Institute of Mathematical Sciences at New York University, Meta

Prof. Dr. Yann LeCun serves as the Silver Professor at the Courant Institute of Mathematical Sciences at New York University and as Vice-President, Chief AI Scientist at Meta. LeCun's groundbreaking work includes the development of convolutional neural networks (CNNs) used in optical character recognition and computer vision, the creation of the DjVu image compression technology and the Lush programming language. He, along with Yoshua Bengio and Geoffrey Hinton, won the 2018 Turing Award for their work on deep learning, earning them the title "Godfathers of AI" and "Godfathers of Deep Learning."

Subscribe to our newsletter

Wonach suchen Sie?