SeminarRecording AvailableArtificial Intelligence

From Machine Learning to Autonomous Intelligence

Schedule
Wednesday, October 19, 2022
05:00 UTC
Yann Le Cun

Meta-FAIR & Meta AI

Host: van Vreeswijk TNS

Recording

Event Information

Recording

Available

Host

van Vreeswijk TNS

Duration

70 minutes

Abstract

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? I 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.

We use essential cookies to run the site. Analytics cookies are optional and help us improve World Wide. Learn more.