Letters: Training RBF network to tolerate single node fault

Authors:
Kevin Ho;Chi-sing Leung;John Sum
Affiliations:
Department of Computer Science and Communication Engineering, Providence University, Sha-Lu, Taiwan;Department of Electronic Engineering, City University of Hong Kong, Kowloon Tong, KLN, Hong Kong;Institute of Technology Management, National Chung Hsing University, 250 Kuo Kuang Road, Taichung 40227, Taiwan
Venue:
Neurocomputing
Year:
2011

Citing 10
Cited 1

A novel learning algorithm which improves the partial fault tolerance of multilayer neural networks

Neural Networks
On objective function, regularizer, and prediction error of a learning algorithm for dealing with multiplicative weight noise

IEEE Transactions on Neural Networks
Local regularization assisted orthogonal least squares regression

Neurocomputing
LMS learning algorithms: misconceptions and new results on converence

IEEE Transactions on Neural Networks
Distributed fault tolerance in optimal interpolative nets

IEEE Transactions on Neural Networks
Multiple model regression estimation

IEEE Transactions on Neural Networks
Maximally fault tolerant neural networks

IEEE Transactions on Neural Networks
Determining and improving the fault tolerance of multilayer perceptrons in a pattern-recognition application

IEEE Transactions on Neural Networks
Complete and partial fault tolerance of feedforward neural nets

IEEE Transactions on Neural Networks
Fault-tolerant training for optimal interpolative nets

IEEE Transactions on Neural Networks

A Novel Structure for Radial Basis Function Networks--WRBF

Neural Processing Letters

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, an objective function for training a radial basis function (RBF) network to handle single node open fault is presented. Based on the definition of this objective function, we propose a training method in which the computational complexity is the same as that of the least mean squares (LMS) method. Simulation results indicate that our method could greatly improve the fault tolerance of RBF networks, as compared with the one trained by LMS method. Moreover, even if the tuning parameter is misspecified, the performance deviation is not significant.