Stability of Neural Networks with Parameters Disturbed by White Noises

摘要: Almost sure exponential stability (ASES) of neural networks with parameters disturbed by noises is studied, the basis which that in implemented very large scale integration (VLSI) approaches well defined white-noise stochastic process, and an appropriate way to impose random factors on deterministic proposed. By using theory dynamical system matrix theory, some criteria are obtained ensure ASES, convergent rate estimated. Also, capacity enduring well-designed The results this paper need only compute eigenvalues or verify negative-definite matrices constructed networks. An illustrative example given show effectiveness paper.