Robust dissipativity analysis of neural networks with time-varying delay and randomly occurring uncertainties

This paper investigates the problem of robust dissipativity analysis for uncertain neural networks with time-varying delay. The norm-bounded uncertainties enter into the neural networks in randomly ways, and such randomly occurring uncertainties (ROUs) obey certain mutually uncorrelated Bernoulli distributed white noise sequences. By employing the linear matrix inequality (LMI) approach, a sufficient condition is established to ensure the robust stochastic stability and dissipativity of the considered neural networks. Some special cases are also considered. Two numerical examples are given to demonstrate the validness and the less conservatism of the obtained results.