Stability criteria of stochastic neural network with general saturation output functions

Almost sure exponential stability of stochastic neural networks with general saturation output functions (GSCNN) is studied, the results obtained in this paper generalize some existent ones. By adopting the approach of decomposing the state space to some sub-regions and by using the theory of stochastic dynamic system, some generalized stability algebraic criteria are obtained, and the attractive domains and the convergent Lyapunov-exponent of equilibria are estimated. The results obtained in this paper need only to compute the eigenvalues or verify the negative-definite of some matrices constructed by the parameters of the neural networks. An illustrative example is given to show the effectiveness of the results in the paper.