Sibel Senan

Global Robust Stability of Bidirectional Associative Memory Neural Networks With Multiple Time Delays

This correspondence presents a sufficient condition for the existence, uniqueness, and global robust asymptotic stability of the equilibrium point for bidirectional associative memory neural networks with discrete time delays. The results impose constraint conditions on the network parameters of the neural system independently of the delay parameter, and they are applicable to all bounded continuous nonmonotonic neuron activation functions. Some numerical examples are given to compare our results with the previous robust stability results derived in the literature.

New robust stability results for bidirectional associative memory neural networks with multiple time delays

In this paper, the robust stability problem is investigated for a class of bidirectional associative memory (BAM) neural networks with multiple time delays. By employing suitable Lyapunov functionals and using the upper bound norm for the interconnection matrices of the neural network system, some novel sufficient conditions ensuring the existence, uniqueness and global robust stability of the equilibrium point are derived. The obtained results impose constraint conditions on the system parameters of neural network independent of the delay parameters. Some numerical examples and simulation results are given to demonstrate the applicability and effectiveness of our results, and to compare the results with previous robust stability results derived in the literature.

Decentralized event-triggered synchronization of uncertain Markovian jumping neutral-type neural networks with mixed delays

In this study, we present an approach for the decentralized event-triggered synchronization of Markovian jumping neutral-type neural networks with mixed delays. We present a method for designing decentralized event-triggered synchronization, which only utilizes locally available information, in order to determine the time instants for transmission from sensors to a central controller. By applying a novel Lyapunov-Krasovskii functional, as well as using the reciprocal convex combination method and some inequality techniques such as Jensens inequality, we obtain several sufficient conditions in terms of a set of linear matrix inequalities (LMIs) under which the delayed neural networks are stochastically stable in terms of the error systems. Finally, we conclude that the drive systems synchronize stochastically with the response systems. We show that the proposed stability criteria can be verified easily using the numerically efficient Matlab LMI toolbox. The effectiveness and feasibility of the results obtained are verified by numerical examples.

New results for exponential stability of delayed cellular neural networks

This brief presents new sufficient conditions for the global exponential stability of the equilibrium point for delayed cellular neural networks (DCNNs). It is shown that the use of a more general type of Lyapunov-Krasovskii functional enables us to derive new results for exponential stability of the equilibrium point for DCNNs. The results establish a relation between the delay time and the parameters of the network. The results are also compared with one of the most recent results derived in the literature.

Robustness analysis of uncertain dynamical neural networks with multiple time delays

This paper studies the problem of global robust asymptotic stability of the equilibrium point for the class of dynamical neural networks with multiple time delays with respect to the class of slope-bounded activation functions and in the presence of the uncertainties of system parameters of the considered neural network model. By using an appropriate Lyapunov functional and exploiting the properties of the homeomorphism mapping theorem, we derive a new sufficient condition for the existence, uniqueness and global robust asymptotic stability of the equilibrium point for the class of neural networks with multiple time delays. The obtained stability condition basically relies on testing some relationships imposed on the interconnection matrices of the neural system, which can be easily verified by using some certain properties of matrices. An instructive numerical example is also given to illustrate the applicability of our result and show the advantages of this new condition over the previously reported corresponding results.

An Analysis of Global Stability of Takagi–Sugeno Fuzzy Cohen–Grossberg Neural Networks with Time Delays

This paper deals with the problem of the global asymptotic stability of Takagi–Sugeno (T–S) fuzzy Cohen–Grossberg neural networks with multiple time delays. By using Lyapunov method and some basic properties of matrices, and employing the nondecreasing and slope-bounded activation functions, an easily verifiable sufficient criterion is derived to establish the asymptotic stability of a general class of (T–S) fuzzy Cohen–Grossberg neural networks with multiple time delays. The obtained stability condition establishes some relationships between the network parameters of the neural network model independently of the delay parameters. A numerical example is also given to illustrate the effectiveness of the theoretical results.

Global Convergence Analysis of Dynamical Neural Networks with Multiple Time Delays

This paper studies the global convergence properties of continuous-time neural networks with multiple time delays. By employing suitable and more general Lyapunov functionals, we derive a new delay independent sufficient condition for the existence, uniqueness and global asymptotic stability of the equilibrium point. The results are applicable to all continuous non-monotonic neuron activation functions and do not require the interconnection matrices to be symmetric. The obtained results can be easily verified as they can be expressed in terms of the network parameters only. Some numerical examples are also given to compare our results with previous stability results derived in the literature.

Global robust stability of bidirectional associative memory neural networks

This paper presents a sufficient condition for the existence, uniqueness and global robust asymptotic stability of the equilibrium point for bidirectional associative memory (BAM) neural networks with discrete time delays. Some numerical examples are given to compare our results with the previous robust stability results derived in the literature.

Global exponential stability analysis of delayed cellular neural networks

This paper presents new sufficient conditions for the global exponential stability of the equilibrium point for delayed cellular neural networks (DCNN). It is shown that the use of a more general type of Lyapunov-Krasovskii functional enables us to derive new results for exponential stability of the equilibrium point for DCNN. The results are also compared with the most recent results derived in the literature.