QR Code

Circuit explained: How does a transformer perform compositional generalization.

Compositional generalization-the systematic combination of known components into novel structures-is fundamental to flexible human cognition, yet the mechanisms that enable it in neural networks remain poorly understood in both machine learning and cognitive science. [1] showed that a compact encode...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Cheng Tang, Brenden Lake, Mehrdad Jazayeri
Format: Artigo
Langue:Inglês
Publié: Public Library of Science (PLoS) 2026-01-01
Collection:PLoS ONE
Accès en ligne:https://doi.org/10.1371/journal.pone.0340088
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!