Record Details

A recurrent network for dynamic system identification

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title A recurrent network for dynamic system identification
 
Creator ADWANKAR, S
BANAVAR, RN
 
Subject neural networks
 
Description This paper presents a type of recurrent artificial neural network architecture for identification of an arbitrary, continuous dynamic system. The recurrent network is shown to be stable for a constant input with certain conditions on the parameters of the network. The proposed network has significant advantages over similar models in continuous time nonlinear system identification and is used to identify three nonlinear dynamic systems. Finally, the applicability of the radial basis function networks using the same network architecture to reduce the time-complexity of the training task is presented.
 
Publisher TAYLOR & FRANCIS LTD
 
Date 2011-08-30T20:02:53Z
2011-12-26T12:59:09Z
2011-12-27T05:50:07Z
2011-08-30T20:02:53Z
2011-12-26T12:59:09Z
2011-12-27T05:50:07Z
1997
 
Type Article
 
Identifier INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE, 28(12), 1239-1250
0020-7721
http://dx.doi.org/10.1080/00207729708929481
http://dspace.library.iitb.ac.in/xmlui/handle/10054/12448
http://hdl.handle.net/10054/12448
 
Language en