🚀 go-pugleaf

         Dynamic System Modelling Using Partially Recurrent
                     Neural Networks 

            (J. of Systems Engineering, 2:2, 90-97, 1992)

                  D.T. Pham and X. Liu 

        This paper presents the results of applying partially recurrent
        neural networks for linear dynamic systems modelling. The nets 
        adopted for the modelling were Elman nets. It was found that in
        their basic form such nets were only capable of modelling first
        -order systems. A modification was made to the net structure 
        enabling systems of higher orders to be modelled. Satisfactory 
        results were obtained for systems of up to the third order. The
        paper also discusses the differences between the tapped-delay-
        line method and recurrent net method for dynamic systems
        modelling.

Correspondence and offprint requests to: 
        
        D.T. Pham
        e-mail: phamdt@uk.ac.cardiff
        X. Liu
        e-mail: liux@uk.ac.cardiff.taff

        Intelligent Systems Research Laboratory, School of 
        Electrical, Electronic and Systems Engineering,
        University of Wales College of Cardiff
        P.O. Box 904, Cardiff CF1 3YH, U.K.