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

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 presented an idea on 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 was 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).

The full video of the AI talk is avaliable here: