Adaptive RBF neural network training algorithm for nonlinear and nonstationary signal

Seng Kah Phooi*, L. M. Ang

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

16 Citations (Scopus)

Abstract

This paper presents an improved adaptive radial basis function neural network (RBF NN) for nonlinear and nonstationary signal. The proposed method possesses distinctive properties of Lyapunov Theorybased Adaptive Filtering (LAF) in [1]-[2]. This method is different from many RBF NN training methods using gradient search techniques. 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 proper design of the weight adaptation law in Lyapunov sense. In this paper, we have proved that the design is independent of statistic properties of the input and output signals. The proposed method has better tracking capability compared with the LAF in [1]-[2]. The performance of the proposed technique is illustrated through the nonlinear adaptive prediction of nonstationary speech signals.

Original languageEnglish
Title of host publication2006 International Conference on Computational Intelligence and Security, ICCIAS 2006
PublisherIEEE Computer Society
Pages433-436
Number of pages4
ISBN (Print)1424406056, 9781424406050
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 International Conference on Computational Intelligence and Security, ICCIAS 2006 - Guangzhou, China
Duration: 3 Oct 20066 Oct 2006

Publication series

Name2006 International Conference on Computational Intelligence and Security, ICCIAS 2006
Volume1

Conference

Conference2006 International Conference on Computational Intelligence and Security, ICCIAS 2006
Country/TerritoryChina
CityGuangzhou
Period3/10/066/10/06

Cite this