The 'moving targets' training algorithm

Richard Rohwer, J. Kindermann (Editor), A. Linden (Editor)

    Research output: Contribution to conferencePaper

    Abstract

    A simple method for training the dynamical behavior of a neural network is derived. It is applicable to any training problem in discrete-time networks with arbitrary feedback. The method resembles back-propagation in that it is a least-squares, gradient-based optimization method, but the optimization is carried out in the hidden part of state space instead of weight space. A straightforward adaptation of this method to feedforward networks offers an alternative to training by conventional back-propagation. Computational results are presented for simple dynamical training problems, with varied success. The failures appear to arise when the method converges to a chaotic attractor. A patch-up for this problem is proposed. The patch-up involves a technique for implementing inequality constraints which may be of interest in its own right.
    Original languageEnglish
    Publication statusUnpublished - 1990
    EventDistributed Adaptive Information Processing (DANIP) -
    Duration: 1 Jan 19901 Jan 1990

    Other

    OtherDistributed Adaptive Information Processing (DANIP)
    Period1/01/901/01/90

    Bibliographical note

    Figures unavailable electronically

    Keywords

    • dynamical behavior
    • neural network
    • networks
    • back-propagation

    Fingerprint Dive into the research topics of 'The 'moving targets' training algorithm'. Together they form a unique fingerprint.

    Cite this