Application
Adaptive behavior from fixed weight networks

https://doi.org/10.1016/S0020-0255(96)00216-2Get rights and content

Abstract

An attribute often associated with intelligent systems is the capability of exhibiting adaptive behavior. For the purposes of this paper, we define adaptation as a system's ability to recognize change through its sensed inputs, and to approximately adjust its behavior in response to the perceived change. This paper explores the notion that a fixed weight, time-lagged recurrent network architecture can be made to exhibit adaptive behavior in the manner defined above after network training has been completed, i.e., to exhibit adaptation in the absence of an explicit learning mechanism. We describe in this paper network training procedures that enable the learning of adaptive behaviors, and we provide empirical evidence of the adaptive capability for a single recurrent network that has been trained to perform one-time-step prediction for any one of several distinct time series.

References (14)

  • M.I. Jordan et al.

    Hierarchical mixtures of experts and the EM algorithm

    Neural Computation

    (1994)
  • M. Mangeas et al.

    First experiments using a mixture of nonlinear experts for time series prediction

  • N.E. Cotter et al.

    Fixed-weight networks can learn

  • N.E. Cotter et al.

    Learning algorithms and fixed dynamics

  • J.T.H. Lo et al.

    Adaptive neural filtering by using the innovations process

  • G.V. Puskorius et al.

    Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks

    IEEE Trans. Neural Networks

    (1994)
  • J. Hale et al.

    Dynamics and Bifurcations

    (1991)
There are more references available in the full text version of this article.

Cited by (0)

View full text