Improve Generalization Ability of Deep Wide Residual Network with A Suitable Scaling Factor

Deep Residual Neural Networks (ResNets) have demonstrated remarkable success across a wide range of real-world applications. In this paper, we identify a suitable scaling factor (denoted by \(\alpha\)) on the residual branch of deep wide ResNets to achieve good generalization ability. We show that i...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-03
Hauptverfasser:	Tian, Songtao, Yu, Zixiong
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks Degeneration Hilbert space Minimax technique Scaling factors Synthetic data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!