Title :
Passivity Analysis for Uncertain Time-Varying Delayed Neural Networks with Neutral Type
Author :
Liao, Chin-Wen ; Lu, Chien-Yu
Author_Institution :
Nat. Chandhua Univ. of Educ., Changhua
Abstract :
This paper considers the problem of robust delay-dependent passivity analysis for time-varying delayed neural networks described by nonlinear delay differential equations of the neutral type, which is subject to norm-bounded time-varying parameter uncertainties. The activation functions are supposed to be bounded and globally Lipschitz continuous. Both delay-dependent and delay-independent passivity conditions are proposed by using more general Lyapunov-Krasovskii functionals. These passivity conditions are obtained in terms of linear matrix inequalities, which can be investigated easily by recently using standard algorithms. An illustrative example is provided to demonstrate the effectiveness and the reduced conservatism of the proposed method.
Keywords :
delays; linear matrix inequalities; neural nets; nonlinear differential equations; time-varying systems; uncertain systems; Lipschitz continuous; Lyapunov-Krasovskii functionals; linear matrix inequalities; nonlinear delay differential equations; norm-bounded time-varying parameter uncertainties; robust delay-dependent passivity analysis; standard algorithms; uncertain time-varying delayed neural networks; Artificial neural networks; Delay effects; Differential equations; Linear matrix inequalities; Multi-layer neural network; Neural networks; Neurons; Robust stability; Robustness; Uncertain systems;
Conference_Titel :
Innovative Computing, Information and Control, 2007. ICICIC '07. Second International Conference on
Conference_Location :
Kumamoto
Print_ISBN :
0-7695-2882-1
DOI :
10.1109/ICICIC.2007.444