27 juin 2022

Base Documentaire : Doctrine

LeCun, Yann🕴️

📝A Path Towards Autonomous Machine Intelligence

Référence complète : LeCun, Y., A Path Towards Autonomous Machine Intelligence, Position Paper,  Version 0.9.2,  27 juin 2022.

____

 

📝Lire l'article. 

 

⚔️Lire la discussion ouverte par l'auteur autour de son papier

___

 

Résumé de l'article (fait par l'auteur) : 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? This position paper proposes an architecture and training paradigms with which to construct autonomous intelligent agents. It combines concepts such as configurable predictive world model, behavior driven through intrinsic motivation, and hierarchical joint embedding architectures trained with self-supervised learning. 

________

les commentaires sont désactivés pour cette fiche