New Radial Basis Function Neural Network Training for Nonlinear and Nonstationary Signals

Authors:
Seng Kah Phooi;Ang L. M
Affiliations:
University of Nottingham, Malaysia Campus, Faculty of Engineering & Computer Science, Jalan Broga, 43500, Semenyih, Selangor, Malaysia;University of Nottingham, Malaysia Campus, Faculty of Engineering & Computer Science, Jalan Broga, 43500, Semenyih, Selangor, Malaysia
Venue:
Computational Intelligence and Security
Year:
2007

Citing 13
Cited 0

Theory and design of adaptive filters

Theory and design of adaptive filters
Interference cancellation using radial basis function networks

Signal Processing
On-line supervised adaptive training using radial basis function networks

Neural Networks
Radial basis function network configuration using mutual information and the orthogonal least squares algorithm

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Adaptive Filtering: Algorithms and Practical Implementation

Adaptive Filtering: Algorithms and Practical Implementation
A new algorithm for online structure and parameter adaptation of RBF networks

Neural Networks
Fast learning in networks of locally-tuned processing units

Neural Computation
Nonlinear adaptive prediction of speech with a pipelined recurrentneural network

IEEE Transactions on Signal Processing
Nonlinear adaptive prediction of nonstationary signals

IEEE Transactions on Signal Processing
A dynamic regularized radial basis function network for nonlinear,nonstationary time series prediction

IEEE Transactions on Signal Processing
Growing radial basis neural networks: merging supervised and unsupervised learning with network growth techniques

IEEE Transactions on Neural Networks
Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper deals with the problem of adaptation of radial basis function neural networks (RBF NN). A new RBF NN supervised training algorithm is proposed. This method possesses the distinctive properties of Lyapunov Theory-based Adaptive Filtering (LAF) in [1]-[2]. The method is different from many RBF NN training using gradient search methods. A new Lyapunov function of the error between the desired output and the RBF NN output is first defined. The output asymptotically converges to the desired output by designing the adaptation law in Lyapunov sense. Error convergence analysis in this paper has proven that the design of the new RBF NN training algorithm is independent of statistic properties of input and output signals. The new adaptation law has better tracking capability compared with the tracking performance of LAF in [1]-[2]. The performance of the proposed technique is illustrated through the adaptive prediction of nonlinear and nonstationary speech signals.