Catégorie
Other seminars

Séminaire Confiance.ai/Seminar@SystemX - Yann Le Cun

Bandeau image
Séminaire Confiance.ai/Seminar@SystemX
Date de tri
Lieu de l'événement
Visioconférence (via Teams)

Partager

twlkml
Chapo
Participez au séminaire Confiance.ai, en partenariat avec le cycle Seminar@SystemX, animé par Yann Le Cun (Meta-FAIR & New-York University) sur le thème « From Machine Learning to Autonomous Intelligence » !
Contenu
Corps de texte

Lien de connexion Teams
 


Résumé : 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.