2 September 1993 Roles of recurrence in neural control architectures
Author Affiliations +
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 content, we provide an explicit formation 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.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Gintaras V. Puskorius, Lee A. Feldkamp, "Roles of recurrence in neural control architectures", Proc. SPIE 1965, Applications of Artificial Neural Networks IV, (2 September 1993); doi: 10.1117/12.152522; https://doi.org/10.1117/12.152522
PROCEEDINGS
16 PAGES


SHARE
KEYWORDS
Neural networks

Network architectures

Control systems

Computer architecture

Artificial neural networks

Feedback control

Dynamical systems

RELATED CONTENT

Roles of recurrence in neural control architectures
Proceedings of SPIE (August 19 1993)
Neural network topology design for nonlinear control
Proceedings of SPIE (March 21 2001)
Two-time-scale control designs for large flexible structures
Proceedings of SPIE (October 01 1990)
Implementation of feedback linearizable controllers
Proceedings of SPIE (September 16 1992)
Neural Networks In Dynamical Systems
Proceedings of SPIE (February 01 1990)

Back to Top