Behavioural modelling using the MOESP algorithm, dynamic neural networks and the Bartels–Stewart algorithm

• Published in: Applied numerical mathematics Vol. 58; no. 12; pp. 1972 - 1993
• Main Authors: Schilders, W.H.A., Meijer, P.B.L., Ciggaar, E.
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 01.12.2008; Elsevier
• Subjects: Bartels–Stewart algorithm; Dynamic neural networks; Eigenvalues; Exact sciences and technology; Mathematics; Model order reduction; Numerical analysis; Numerical analysis. Scientific computation; Sciences and techniques of general use; State space representation; Eigenvalues; Dynamic neural networks; Model order reduction; State space representation; Bartels–Stewart algorithm; Industry; Bartels-Stewart algorithm; Numerical analysis; Applied mathematics; State space; State space method; Neural network; Algorithm
• ISSN: 0168-9274; 1873-5460
• DOI: 10.1016/j.apnum.2007.11.013

In this paper we discuss the use of the state-space modelling MOESP algorithm to generate precise information about the number of neurons and hidden layers in dynamic neural networks developed for the behavioural modelling of electronic circuits. The Bartels–Stewart algorithm is used to transform the information from the MOESP algorithm to the neural network formalism. The technique is related to the class of model order reduction algorithms that receives much attention in recent years, especially in the electronics industry.