The 'moving targets' training algorithm


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.

Divisions: Aston University (General)
Additional Information: Figures unavailable electronically
Event Title: Distributed Adaptive Information Processing (DANIP)
Event Type: Other
Event Dates: 1990-01-01 - 1990-01-01
Last Modified: 29 Nov 2023 14:12
Date Deposited: 11 Mar 2019 20:32
PURE Output Type: Paper
Published Date: 1990
Authors: Rohwer, Richard

Export / Share Citation


Additional statistics for this record