Title :
Design of risk-sensitive optimal control for stochastic recurrent neural networks by using Hamilton-Jacobi-Bellman equation
Author :
Liu, Ziqian ; Ansari, Nirwan ; Kotinis, Miltiadis ; Shih, Stephen C.
Author_Institution :
Eng. Dept., State Univ. of New York Maritime Coll., Throggs Neck, NY, USA
Abstract :
This paper presents a theoretical design for the stabilization of stochastic recurrent neural networks with respect to a risk-sensitive optimality criterion. This approach is developed by using the Hamilton-Jacobi-Bellman equation, Lyapunov technique, and inverse optimality, to obtain a risk-sensitive state feedback controller, which guarantees an achievable meaningful cost for a given risk-sensitivity parameter. Finally, a numerical example is given to demonstrate the effectiveness of the proposed approach.
Keywords :
Lyapunov methods; control system synthesis; optimal control; recurrent neural nets; stability; state feedback; stochastic processes; Hamilton-Jacobi-Bellman equation; Lyapunov technique; inverse optimality; optimal control; risk-sensitive optimality criterion; stability; state feedback controller; stochastic recurrent neural networks; Biological neural networks; Equations; Mathematical model; Nonlinear systems; Recurrent neural networks; Stochastic processes; USA Councils;
Conference_Titel :
Decision and Control (CDC), 2010 49th IEEE Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4244-7745-6
DOI :
10.1109/CDC.2010.5717009