The 'moving targets' training algorithm

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 algorithm resembles back-propagation in that an error function is minimized using a gradient-based method, but the optimization is carried out in the hidden part of state space either instead of, or in addition to weight space. Computational results are presented for some simple dynamical training problems, one of which requires response to a signal 100 time steps in the past.

Divisions: Aston University (General)
Event Title: Advances in Neural Information Processing Systems 1990
Event Type: Other
Event Dates: 1990-08-29 - 1990-08-31
Uncontrolled Keywords: dynamical behavior,neural network,error
PURE Output Type: Paper
Published Date: 1990
Authors: Rohwer, Richard

Export / Share Citation


Statistics

Additional statistics for this record