The Topos of Transformer Networks

The transformer neural network has significantly out-shined all other neural network architectures as the engine behind large language models. We provide a theoretical analysis of the expressivity of the transformer architecture through the lens of topos theory. From this viewpoint, we show that man...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Villani, Mattia Jacopo, McBurney, Peter
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Learning Mathematics - Category Theory
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!