Feature-wise scaling and shifting: Improving the generalization capability of neural networks through capturing independent information of features

From the perspective of input features, information can be divided into independent information and correlation information. Current neural networks mainly concentrate on the capturing of correlation information through connection weight parameters supplemented by bias parameters. This paper introdu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 2024-02, Vol.170, p.453-467
Hauptverfasser:	Sun, Tongfeng, Wang, Xiurui, Li, Zhongnian, Ding, Shifei
Format:	Artikel
Sprache:	eng
Schlagworte:	Correlation information Feature-wise scaling and shifting Generalization capability Independent information Neural networks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!