Roles of recurrence in neural control architectures
Gintaras V. Puskorius, L.A. Feldkamp · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1993
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.