A new two-step gradient-based backpropagation training method for neural networks

Authors:
Xuewen Mu;Yaling Zhang
Affiliations:
Department of Applied Mathematics, Xidian University, Xi'an, China;Department of Computer Science, Xi'an Science and Technology University, Xi'an, China
Venue:
ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Year:
2010

Citing 3
Cited 0

Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Supervised Neural Gas with General Similarity Measure

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new two step gradient-based backpropagation training method is proposed for neural networks in this paper Based on the Barzilai and Borwein steplength update rule and the technique of Resilient Gradient Descent method, we give a new descent direction and steplength update rule The new two step learning rate improves the speed and the success rate Experimental results show that the proposed method has considerably improved convergence speed, and for the chosen test problems, outperforms other well-known training methods.