Structured World Representations in Maze-Solving Transformers

Transformer models underpin many recent advances in practical machine learning applications, yet understanding their internal behavior continues to elude researchers. Given the size and complexity of these models, forming a comprehensive picture of their inner workings remains a significant challeng...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-12
Hauptverfasser:	Ivanitskiy, Michael Igorevich, Spies, Alex F, Räuker, Tilman, Corlouer, Guillaume, Mathwin, Chris, Quirke, Lucia, Rager, Can, Shah, Rusheb, Valentine, Dan, Cecilia Diniz Behn, Inoue, Katsumi, Samy Wu Fung
Format:	Artikel
Sprache:	eng
Schlagworte:	Machine learning Representations Topology Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!