Delay-dependent state estimation for neural networks with time-varying delay

This paper focuses on delay-dependent state estimation problem for neural networks with a time-varying delay. An improved delay-dependent criterion is established to estimate the neuron states through available output measurements such that the dynamics of the estimation error is globally asymptotically stable. The derivative of Lyapunov-Krasovskii functional is bounded by introducing a free-matrix-based integral inequality. A modified cone complementarity linearization (CCL) algorithm is presented to compute the state estimator parameter in obtained matrix inequalities, rather than linear matrix inequalities (LMIs). Finally, two numerical examples are given to demonstrate the effectiveness and the merits over the existing ones.