Share Email Print

Proceedings Paper

Roles of recurrence in neural control architectures
Author(s): Gintaras V. Puskorius; Lee A. Feldkamp
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper we discuss the means by which recurrent connections are used in neural control system architectures. We first consider the state feedback approach to control and the role of recurrent neural networks for plant modeling and control. In this context, we provide an explicit formulation for the computation of dynamic derivatives in recurrent neural network architectures as required for training by the dynamic gradient method. For illustration, we apply dynamic gradient methods to train recurrent neural network controllers for a series of cart-pole problems with the simultaneous objectives of pole balancing and cart centering.

Paper Details

Date Published: 19 August 1993
PDF: 16 pages
Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152616
Show Author Affiliations
Gintaras V. Puskorius, Ford Motor Co. (United States)
Lee A. Feldkamp, Ford Motor Co. (United States)

Published in SPIE Proceedings Vol. 1966:
Science of Artificial Neural Networks II
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top