CONVERGENCE OF GRADIENT METHOD WITH MOMENTUM FOR BACK-PROPAGATION NEURAL NETWORKS

CONVERGENCE OF GRADIENT METHOD WITH MOMENTUM FOR BACK-PROPAGATION NEURAL NETWORKS

In this work, a gradient method with momentum for BP neural networks is considered. The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the learning procedure of the network weights. Corresponding convergence results are proved.

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Journal of computational mathematics 2008-07, Vol.26 (4), p.613-623
Hauptverfasser: Wu, Wei, Zhang, Naimin, Li, Zhengxue, Li, Long, Liu, Yan
Format: Artikel
Sprache:eng
Schlagworte:
Artificial neural networks
Biological neural networks
Computational mathematics
Error function
Gradient method
Learning rate
Local minimum
Neurons
Sonar
Training
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this work, a gradient method with momentum for BP neural networks is considered. The momentum coefficient is chosen in an adaptive manner to accelerate and stabilize the learning procedure of the network weights. Corresponding convergence results are proved.
ISSN:0254-9409
1991-7139