Search

Abstract: This Letter concerns with the mean square exponential stability of uncertain stochastic delayed neural networks. By applying Lyapunov functional method, new delay-dependent/independent mean square exponential stability criteria are derived in terms of linear matrix inequalities. Two examples are presented which show our result are less conservative than the existing stability criteria. [Copyright &y& Elsevier]

Abstract: This Letter provides new exponential stability criteria for discrete-time neural networks with variable delays. The main technique is to reduce exponential convergence estimation of the neural network solution to that of one component of the corresponding solution by constructing Lyapunov function based on M-matrix. By introducing the tuning parameter diagonal matrix, the delay-independent and delay-dependent exponential stability conditions have been unified in the same mathematical formula. The effectiveness of the new results are illustrated by three examples. [Copyright &y& Elsevier]

Abstract: This Letter provides new exponential stability criteria for neural networks with variable delays. By applying the properties of M-matrix properties and inequality techniques, simple and improved delay-dependent exponential stability criteria are derived. These criteria extend and improve the existing ones, which is important in the design of neural networks. [Copyright &y& Elsevier]

In this Letter, a thorough analysis of existence, uniqueness and globally exponential stability of the equilibrium point of neural networks with variable delays is presented. By applying M-matrix theory and some new analysis techniques, a new delay-dependent sufficient condition for global exponential stability is derived. The criteria obtained in this Letter extend and improve the existing ones, and a numerical example illustrate the effectiveness of our results. [Copyright &y& Elsevier]