Title :
A new fast algorithm for identification of non-linear dynamic systems using radial basis function networks
Author_Institution :
Intelligent Systems and Control Group, School of Electrical and Electronic Engineering, Queen´s University Belfast, Ashby Building, Stranmillis Rd., Belfast BT9 5AH, UK
Abstract :
A new fast estimation algorithm is derived for identification of non-linear dynamic systems using radial basis function networks. The new algorithm is able to both select the hidden nodes and to compute weights of the output layer in the radial basis function neural networks (RBFN) simultaneously in a stepwise forward fashion.
Keywords :
Computational modeling; Cost function; Heuristic algorithms; Mathematical model; Matrix decomposition; Radial basis function networks; Training; System identification; network construction; non-linear system; radial basis function network;
Conference_Titel :
European Control Conference (ECC), 2003
Conference_Location :
Cambridge, UK
Print_ISBN :
978-3-9524173-7-9
