An input-to-state stability approach to filter design for neural networks with noise disturbance

In this paper, an input-to-state stability (ISS) approach is introduced to derive a new state estimation filter for Hopfield neural networks with noise disturbance. A new ISS filtering method is developed such that the filtering error system is exponentially stable and input-to-state stable for the noise disturbance. The proposed filter can be obtained by solving a linear matrix inequality (LMI), which can be easily facilitated by using some standard numerical packages. An illustrative example is given to demonstrate the effectiveness of the proposed filter.