Delay-Dependent Filtering of Markovian Jumping Neural Networks With Mode-Dependent Time Delays

This paper is concerned with the problem of delay-dependent L-2 - L-infinity filter design of Markovian jumping neural networks with mode-dependent time delays. By constructing a suitable stochastic Lyapunov functional, a delay-dependent condition is established such that the filtering error system is stochastically stable and a prescribed L-2 - L-infinity performance is achieved. Furthermore, it is shown that the gain matrices and the optimal L-2 - L-infinity performance index are obtained by solving a convex optimization problem subject to some linear matrix inequalities. An example is finally provided to demonstrate the effectiveness of the developed result,