Replica symmetry breaking in dense neural networks

Understanding the glassy nature of neural networks is pivotal both for theoretical and computational advances in Machine Learning and Theoretical Artificial Intelligence. Keeping the focus on dense associative Hebbian neural networks, the purpose of this paper is two-fold: at first we develop rigoro...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-11
Hauptverfasser:	Albanese, Linda, Alemanno, Francesco, Alessandrelli, Andrea, Barra, Adriano
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial intelligence Broken symmetry Free energy Interpolation Machine learning Mathematics - Mathematical Physics Neural networks Physics - Disordered Systems and Neural Networks Physics - Mathematical Physics Spin glasses Storage capacity Symmetry
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!