Convergence of batch gradient learning algorithm with smoothing L1/2 regularization for Sigma–Pi–Sigma neural networks

Sigma–Pi–Sigma neural networks are known to provide more powerful mapping capability than traditional feed-forward neural networks. The L1/2 regularizer is very useful and efficient, and can be taken as a representative of all the Lq(0<q<1) regularizers. However, the nonsmoothness of L1/2 regu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neurocomputing (Amsterdam) Jg. 151; S. 333 - 341
Hauptverfasser:	Liu, Yan, Li, Zhengxue, Yang, Dakun, Mohamed, Kh.Sh, Wang, Jing, Wu, Wei
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 03.03.2015
Schlagworte:	Batch gradient learning algorithm Convergence Sigma–Pi–Sigma neural networks Smoothing L1/2 regularization Sigma–Pi–Sigma neural networks Batch gradient learning algorithm Convergence Smoothing L1/2 regularization
ISSN:	0925-2312, 1872-8286
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!