Neural network architectures for parameter estimation of dynamical systems

Raol, JR and Madhuranath, H (1996) Neural network architectures for parameter estimation of dynamical systems. IEE Proceedings: Control Theory and Applications, 143 (4). pp. 387-394.

Full text available as:
[img] PDF
Download (915Kb)
    Official URL: http://www.theiet.org

    Abstract

    Various recurrent neural network architectures for solving the problems of parameter estimation in dynamical systems are presented. The architectures based on precomputation of weight/bias information (Hopfield neural network), direct gradient computation with and without normalisation and output error method are developed. A typical computer simulation result is given.

    Item Type: Journal Article
    Additional Information: Copyright for this article belongs to IEE
    Uncontrolled Keywords: Neural network;Parameter estimation;Parallel computing; Dynamical system
    Subjects: MATHEMATICAL AND COMPUTER SCIENCES > Systems analysis and Operations Research
    Division/Department: Flight Mechanics and Control Division, Other
    Depositing User: M/S ICAST NAL
    Date Deposited: 22 Feb 2008
    Last Modified: 17 Jun 2010 10:28
    URI: http://nal-ir.nal.res.in/id/eprint/4620

    Actions (login required)

    View Item