Back propagation with randomized cost function for training neural networks

Authors:
H. A. Babri;Y. Q. Chen;Kamran Ahsan
Affiliations:
Lahore University of Management Sciences, Computer Science Department, DHA Lahore, Pakistan;Nanyang Technology University, School of EEE, Singapore;Stanford University, Department of Management Science and Engineering, Terman Engineering Center, Stanford, California
Venue:
RSFDGrC'03 Proceedings of the 9th international conference on Rough sets, fuzzy sets, data mining, and granular computing
Year:
2003

Citing 4
Cited 0

Accelerated learning in layered neural networks

Complex Systems
Speeding up backpropagation algorithms by using cross-entropy combined with pattern normalization

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Gradient descent learning algorithm overview: a general dynamical systems perspective

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A novel method to improve both the generalization and convergence performance of the back propagation algorithm (BP) by using multiple cost functions with a randomizing scheme is proposed in this paper. Under certain conditions, the randomized technique will converge to the global minimum with probability one. Experimental results on benchmark Encoder-Decoder problems and the NC2 classification problem show that the method is effective in enhancing BP's convergence and generalization performance