Skip to content

Detail of publication


Šimandl, M. and Hering, P. : Recursive parameters estimation and structure adaptation of neural network . Modelling, identification and control, Intelligent Systems and Control 2005, p. 78-83, ACTA Press, Anaheim, 2005.


Application of neural networks in identification of nonlin- ear stochastic systems is treated. The stress is laid on a parameters estimation and structure adaptation of the net- works. They are trained by a global filtering method allow- ing to determine conditional probability density functions of network parameters. The Gaussian sum approach used for parameters estimation of network gives better results than the commonly used prediction error methods, and it is an interesting alternative to sequential Monte Carlo meth- ods. The approach also enables structure adaptation which is given by pruning of insignificant connections from an a priori chosen large network. The designed structure adap- tation method utilizes conditional probability density func- tions of the parameters obtained from the estimation algo- rithm to measure saliency of the network connections and it represents a generalization of the extended Kalman filter based pruning method.

Detail of publication

Title: Recursive parameters estimation and structure adaptation of neural network
Author: Šimandl, M. ; Hering, P.
Language: English
Date of publication: 31 Oct 2005
Year: 2005
Type of publication: Papers in journals
Title of journal or book: Modelling, identification and control
Series: Intelligent Systems and Control 2005
Page: 78 - 83
ISBN: 1025-8973
ISSN: 1025-8973
Publisher: ACTA Press
Address: Anaheim
Date: 31 Oct 2005 - 2 Nov 2005
/ /


system identification, nonlinear parameters estimation, structure adaptation, probability density function, multi- layer perceptron network.


 author = {\v{S}imandl, M. and Hering, P.},
 title = {Recursive parameters estimation and structure adaptation of neural network},
 year = {2005},
 publisher = {ACTA Press},
 journal = {Modelling, identification and control},
 address = {Anaheim},
 pages = {78-83},
 series = {Intelligent Systems and Control 2005},
 ISBN = {1025-8973},
 ISSN = {1025-8973},
 url = {},