State estimation for discrete-time neural networks with randomly occurring quantisations

This paper deals with the state estimation problem for a class of discrete-time neural networks with randomly occurring quantisations. The randomly occurring quantisation phenomenon is taken into account, which is governed by a Bernoulli distributed stochastic sequence. The purpose of the addressed problem is to design a state estimator such that the dynamics of the estimation error is exponentially stable in the mean square. By using the Lyapunov stability theory combined with the stochastic analysis techniques, sufficient conditions are first established to ensure the existence of the desired estimator. Then, the explicit expression of the desired estimator gain is described by using the semi-definite programme method. Finally, a numerical example is employed to demonstrate the effectiveness and applicability of the proposed estimator design approach.