Skip to content

Detail of publication


Šimandl, M. and Hering, P. and Král, L. : Identification of nonlinear non-gaussian systems by neural networks . Nonlinear control systems 2004 (NOLCOS 2004), p. 1307-1312, Elsevier , Oxford, 2005.


Application of neural networks in identification of nonlinear non-Gaussian systems is treated. Stress is laid on a parameter estimation of the networks. They are trained by the Gaussian sum method which is a global filtering method allowing to determine conditional probability density functions of network weights. Proposed approach to estimation of network weights (parameters) based on Gaussian sum filtering method overcomes commonly used prediction error methods and it is an interesting alternative to sequential Monte Carlo methods. The considered training approach is demonstrated by an illustration example.

Detail of publication

Title: Identification of nonlinear non-gaussian systems by neural networks
Author: Šimandl, M. ; Hering, P. ; Král, L.
Language: English
Date of publication: 1 Sep 2004
Year: 2005
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Nonlinear control systems 2004 (NOLCOS 2004)
Page: 1307 - 1312
ISBN: 0-08-044303-6
Publisher: Elsevier
Address: Oxford
Date: 1 Sep 2004 - 3 Sep 2004
/ /


system identification, nonlinear non-Gaussian stochastic system, non-Gaussian disturbance, neural network training, Gaussian sum, Bayesian relations, multilayer perceptron network


 author = {\v{S}imandl, M. and Hering, P. and Kr\'{a}l, L.},
 title = {Identification of nonlinear non-gaussian systems by neural networks},
 year = {2005},
 publisher = {Elsevier },
 journal = {Nonlinear control systems 2004 (NOLCOS 2004)},
 address = {Oxford},
 pages = {1307-1312},
 ISBN = {0-08-044303-6},
 url = {},