-
[show abstract]
[hide abstract]
ABSTRACT: This brief addresses the global asymptotic stability (GAS) of delayed neural networks. Based on the Lyapunov method, using some existing results for the existence and uniqueness of the equilibrium point, some sufficient conditions are obtained for checking the GAS without demanding the boundedness and differentiability hypotheses for activation functions. Through comparison, it is illustrated that our conditions extend and improve some recent results.
Circuits and Systems II: Express Briefs, IEEE Transactions on 08/2007; · 1.41 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: This letter considers the problem of asymptotic stability of Cohen–Grossberg neural networks with time-varying delays. The stability condition is given in terms of a linear matrix inequality (LMI). Comparison between our results and previous results admits that our results establish a new set of stability criteria for delayed Cohen–Grossberg neural networks.
Neurocomputing. 01/2007;
-
[show abstract]
[hide abstract]
ABSTRACT: The global robust asymptotic stability of bi-directional associative memory (BAM) neural networks with constant or time-varying delays is studied. An approach combining the Lyapunov-Krasovskii functional with the linear matrix inequality (LMI) is taken to study the problem. Some a criteria for the global robust asymptotic stability, which gives information on the delay-dependent property, are derived. Some illustrative examples are given to demonstrate the effectiveness of the obtained results.
New Mathematics and Natural Computation (NMNC). 01/2007; 03(01):57-68.
-
[show abstract]
[hide abstract]
ABSTRACT: The passivity conditions for stochastic neural networks with time-varying delays and random abrupt changes are considered in this paper. Sufficient conditions on passivity of stochastic neural networks with time-varying delays and random abrupt changes are developed in the linear matrix inequality (LMI) setting. The results obtained in this paper improve and extend some of the previous results.
New Mathematics and Natural Computation (NMNC). 01/2007; 03(03):321-330.
-
[show abstract]
[hide abstract]
ABSTRACT: By constructing suitable Lyapunov functional and using matrix theory, the global asymptotic stability of delay bi-directional associative memory neural networks with impulses is studied. This paper gives a sufficient condition which is independent with the delayed quantity for the global asymptotic stability of these networks. An illustrative example is given to demonstrate the effectiveness of the obtained results.
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on; 09/2005
-
[show abstract]
[hide abstract]
ABSTRACT: This paper presented a fault diagnostic method for polymeric reaction process by means of the technique of adopted fuzzy pattern recognition. Based on soft measuring hybrid model, a threshold value principle and maximum membership degree principle are combined to diagnose faults. The fault diagnostic method is used for a typical polymeric reaction productive process - Polyacrylonitrile productive process, and it is proved that it can not only get accurate diagnosis results but also rectify the output of the hybrid model with the help of the information from morbid symptom set.
Machine Learning and Cybernetics, 2005. Proceedings of 2005 International Conference on; 09/2005
-
Control, Automation, Robotics and Vision Conference, 2004. ICARCV 2004 8th; 01/2005
-
[show abstract]
[hide abstract]
ABSTRACT: The variable structure control problems of a class of uncertain distributed parameter systems with nonlinear input under the Neumann boundary conditions are studied by using inequality analysis as the main mathematical tool, and a robust variable structure controller is derived.
Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on; 07/2004
-
[show abstract]
[hide abstract]
ABSTRACT: This paper discusses a generalized model of high-order Hopfield-type neural networks with time-varying delays. Some novel global stability criteria of the system is derived by using Lyapunov method, linear matrix inequality (LMI) and analytic technique. The LMI-based criteria obtained here are computationally more flexible and more generic than many other existing criteria. A numerical example is given to illustrate our result.
Journal of Mathematical Analysis and Applications.
-
[show abstract]
[hide abstract]
ABSTRACT: The global asymptotic stability of delay bi-directional associative memory neural networks with impulses are studied by constructing suitable Lyapunov functional. Sufficient conditions, which are independent to the delayed quantity, are obtained for the global asymptotic stability of the neural networks. Some illustrative examples are given to demonstrate the effectiveness of the obtained results.
Chaos, Solitons & Fractals.
-
Journal of Computational and Applied Mathematics 180(2):365-375. · 1.11 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: The global asymptotic stability of bi-directional associative memory neural networks with distributed delays and reaction–diffusion terms are studied by using the analysis technique and Lyapunov functional. A sufficient condition is proposed. Two numerical examples are given to show the correctness of our analysis.
Chaos, Solitons & Fractals.
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, the global robust dissipativity of integro-differential systems modeling neural networks with time-varying delays are studied. Proper Lyapunov functionals and some analytic techniques are employed to derive the sufficient conditions under which the networks proposed are the global robust dissipativity. The results are shown to improve the previous global dissipativity results derived in the literature. Some examples are given to illustrate the correctness of our results.
Chaos, Solitons & Fractals.
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper, the problem of asymptotic synchronization for a class of neural networks with reaction-diffusion terms and time-varying delays is investigated. Using the drive-response concept, a control law is derived to achieve the state synchronization of two identical neural networks with reaction-diffusion terms. Moreover, we derive a sufficient asymptotic synchronization condition for the neural networks with reaction-diffusion terms if reaction-diffusion terms satisfy a weaker condition. The synchronization condition is easy to verify and relies on the connection matrix in the driven networks and the suitable designed controller gain matrix in the response networks.
Computers & Mathematics with Applications.
-
[show abstract]
[hide abstract]
ABSTRACT: In this letter, the global asymptotic stability of a class of Cohen–Grossberg neural networks with time-varying delays is discussed. A new set of sufficient conditions for the neural networks are proposed to guarantee the global asymptotic convergence. Our criteria represent an extension of the existing results in literatures. An example is also presented to compare our results with the previous results.
Chaos, Solitons & Fractals.