Extended state estimator design method for neutral-type neural networks with time-varying delays

The problem of designing a state estimator having a global exponential convergence for a class of delayed neural networks of neutral-type is investigated in this paper. The time-delay pattern is a bounded differentiable time-varying function. The activation functions are globally Lipschitz. A linear estimator of Luenberger-type is developed and by properly constructing a new Lyapunov-Krasovskii functional coupled with the integral inequality, the global exponential stability conditions of the error system are derived. The unknown gain matrix is determined by solving a delay-dependent linear matrix inequality. The developed results are shown to be less conservative than previous published ones in the literature, which is illustrated by a representative numerical example.