Trajectory tracking for delayed recurrent neural networks

This paper deals with the problem of trajectory tracking for delayed recurrent neural networks. The tracking error is global asymptotic stabilized by a control law derived on the basis of a Lyapunov-Krasovsky functional. Then, it is established that this control law minimizes a meaningful cost functional. Applicability of the approach is illustrated by means of an example

[1]  M. Forti,et al.  Necessary and sufficient condition for absolute stability of neural networks , 1994 .

[2]  A. Isidori.  Nonlinear Control Systems , 1985 .

[3]  Miroslav Krstic,et al.  Stabilization of Nonlinear Uncertain Systems , 1998 .

[4]  D. Kraft.  Nonlinear system analysis by direct collocation , 1987 .

[5]  Amir F. Atiya,et al.  How delays affect neural dynamics and learning , 1994, IEEE Trans. Neural Networks.

[6]  Guanrong Chen,et al.  YET ANOTHER CHAOTIC ATTRACTOR , 1999 .

[7]  E. Sánchez,et al.  Input-to-state stability (ISS) analysis for dynamic neural networks , 1999 .

[8]  Tianguang Chu,et al.  New necessary and sufficient conditions for absolute stability of neural networks , 2005, 2005 International Conference on Control and Automation.

[9]  E.N. Sanchez,et al.  Adaptive recurrent neural control for noisy chaos synchronization , 2003, Proceedings of the 2003 American Control Conference, 2003..

[10]  Guanrong Chen,et al.  LMI-based approach for asymptotically stability analysis of delayed neural networks , 2002 .

[11]  Guanrong Chen,et al.  Using Dynamic Neural Networks to Generate Chaos: an Inverse Optimal Control Approach , 2001, Int. J. Bifurc. Chaos.

[12]  Klaus Mainzer,et al.  Cellular Neural Networks and Visual Computing , 2003, Int. J. Bifurc. Chaos.

[13]  Xiaofeng Liao,et al.  (Corr. to) Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach , 2002, Neural Networks.

[14]  Alexander S. Pozniak.  Di erential Neural Networks for Robust Nonlinear Controlby , 2001 .