Design of risk-sensitive optimal control for stochastic recurrent neural networks by using Hamilton-Jacobi-Bellman equation

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.

[1]  Miroslav Krstic,et al.  Inverse optimal stabilization of a rigid spacecraft , 1999, IEEE Trans. Autom. Control..

[2]  Fabrice Druaux,et al.  STABLE ADAPTIVE CONTROL WITH RECURRENT NEURAL NETWORKS , 2005 .

[3]  Jun Wang,et al.  Global asymptotic stability and global exponential stability of continuous-time recurrent neural networks , 2002, IEEE Trans. Autom. Control..

[4]  P. Kokotovic,et al.  Inverse Optimality in Robust Stabilization , 1996 .

[5]  Sabri Arik,et al.  Global stability analysis of neural networks with multiple time varying delays , 2005, IEEE Transactions on Automatic Control.

[6]  T. Başar,et al.  Locally optimal risk-sensitive controllers for strict-feedback nonlinear systems , 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304).

[7]  Eduardo D. Sontag,et al.  Complete controllability of continuous-time recurrent neural networks , 1997 .

[8]  T. Basar,et al.  H∞-0ptimal Control and Related Minimax Design Problems: A Dynamic Game Approach , 1996, IEEE Trans. Autom. Control..

[9]  Eduardo D. Sontag,et al.  Further results on controllability of recurrent neural networks 1 1 Supported in part by US Air Forc , 1999 .

[10]  J. Tsinias Stochastic input-to-state stability and applications to global feedback stabilization , 1998 .

[11]  P. Whittle Risk-Sensitive Optimal Control , 1990 .

[12]  Mietek A. Brdys,et al.  Stable adaptive control with recurrent networks , 1997, 1997 European Control Conference (ECC).

[13]  Edgar N. Sánchez,et al.  Input-to-state stabilization of dynamic neural networks , 2003, IEEE Trans. Syst. Man Cybern. Part A.

[14]  J. Doyle,et al.  NONLINEAR OPTIMAL CONTROL: A CONTROL LYAPUNOV FUNCTION AND RECEDING HORIZON PERSPECTIVE , 1999 .

[15]  Soumitra Das,et al.  Noisy recurrent neural networks: the continuous-time case , 1998, IEEE Trans. Neural Networks.

[16]  Paul J. Werbos,et al.  2009 Special Issue: Intelligence in the brain: A theory of how it works and how to build it , 2009 .

[17]  Qunjing Wang,et al.  Further Development of Input-to-State Stabilizing Control for Dynamic Neural Network Systems , 2008, IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans.

[18]  S. Arik Global asymptotic stability of a class of dynamical neural networks , 2000 .

[19]  Qunjing Wang,et al.  Inverse optimal noise-to-state stabilization of stochastic recurrent neural networks driven by noise of unknown covariance , 2009 .

[20]  Alberto Tesi,et al.  On absolute stability of convergence for nonlinear neural network models , 2003 .

[21]  Miltiadis Kotinis,et al.  Risk-sensitive optimal control for stochastic recurrent neural networks , 2010, 2010 53rd IEEE International Midwest Symposium on Circuits and Systems.

[22]  Jun Wang,et al.  Global exponential stability of continuous-time interval neural networks. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.