A modified gradient-based backpropagation training method for neural networks

A improved gradient-based backpropagation training method is proposed for neural networks in this paper. Based on the Barzilai and Borwein steplength update and some technique of Resilient Propagation method, we adapt the new learning rate to improves the speed and the success rate. Experimental res...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2009 IEEE International Conference on Granular Computing S. 450 - 453
Hauptverfasser:	Xuewen Mu, Yaling Zhang
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 01.08.2009
Schlagworte:	Artificial neural networks Backpropagation algorithms backpropagation training method Barzilai and Borwein steplength Biology Computer science Convergence Information processing Iterative algorithms Mathematics Neural networks Resilient Propagation method Testing
ISBN:	9781424448302, 1424448301
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!