Selecting radial basis function network centers with recursive orthogonal least squares training

Authors:
J. B. Gomm;D. L. Yu
Affiliations:
Control Syst. Res. Group, Liverpool John Moores Univ.;-
Venue:
IEEE Transactions on Neural Networks
Year:
2000

Citing 0
Cited 22

Nonlinear Fisher discriminant analysis using a minimum squared error cost function and the orthogonal least squares algorithm

Neural Networks
Improvement of Cluster Detection and Labeling Neural Network by Introducing Elliptical Basis Function

ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Neural and Wavelet Network Models for Financial Distress Classification

Data Mining and Knowledge Discovery
Symbolic adaptive neuro-fuzzy inference for data mining of heterogenous data

Intelligent Data Analysis
Detection and localization of power quality disturbances based on wavelet network

ISPRA'07 Proceedings of the 6th WSEAS International Conference on Signal Processing, Robotics and Automation
Detection and localization of power quality disturbances based on wavelet network

ISPRA'07 Proceedings of the 6th WSEAS International Conference on Signal Processing, Robotics and Automation
Improving the generalization performance of RBF neural networks using a linear regression technique

Expert Systems with Applications: An International Journal
Two-stage mixed discrete-continuous identification of radial basis function (RBF) neural models for nonlinear systems

IEEE Transactions on Circuits and Systems Part I: Regular Papers
Research on the diagnosis of insulator operating state based on improved neural networks

ICNC'09 Proceedings of the 5th international conference on Natural computation
A fast multi-output RBF neural network construction method

Neurocomputing
A hybrid particle swarm optimization and its application in neural networks

Expert Systems with Applications: An International Journal
A novel RBF neural network with fast training and accurate generalization

CIS'04 Proceedings of the First international conference on Computational and Information Science
Bark classification based on gabor filter features using RBPNN neural network

ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
Adaptive pseudo linear RBF model for process control

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
A novel approach for high dimension 3D object representation using Multi-Mother Wavelet Network

Multimedia Tools and Applications
A novel locally regularized automatic construction method for RBF neural models

Neurocomputing
Model selection for RBF network via generalized degree of freedom

Neurocomputing
Nonlinear identification of a gasoline HCCI engine using neural networks coupled with principal component analysis

Applied Soft Computing
Loose particle classification using a new wavelet fisher discriminant method

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
A Novel Radial Basis Function Networks Locally Tuned with Differential Evolution for Classification: An Application in Medical Science

International Journal of Systems Biology and Biomedical Technologies
Fault detection and isolation for PEM fuel cell stack with independent RBF model

Engineering Applications of Artificial Intelligence
A multi-output two-stage locally regularized model construction method using the extreme learning machine

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Recursive orthogonal least squares (ROLS) is a numerically robust method for solving for the output layer weights of a radial basis function (RBF) network, and requires less computer memory than the batch alternative. In the paper, the use of ROLS is extended to selecting the centers of an RBF network. It is shown that the information available in an ROLS algorithm after network training can be used to sequentially select centers to minimize the network output error. This provides efficient methods for network reduction to achieve smaller architectures with acceptable accuracy and without retraining. Two selection methods are developed, forward and backward. The methods are illustrated in applications of RBF networks to modeling a nonlinear time series and a real multiinput-multioutput chemical process. The final network models obtained achieve acceptable accuracy with significant reductions in the number of required centers