State estimation for neural networks of neutral-type with interval time-varying delays (Q2518711)

A class of neutral networks with interval time-varying delays described by a nonlinear delay differential equation of neutral-type is considered. The interval time-varying delay does not have the constraint that its derivative is less than 1. The neuron state is estimated via available output measurements such that the estimation error converges to zero. By constructing a suitable Lyapunov functional, a new condition for the existence of a state estimator for the networks is given in terms linear matrix inequality. The advantage of the proposed approach is that the resulting stability criterion can be used efficiently via existing numerical convex optimization algorithms. A numerical example is given to show the effectiveness of proposed method.