State Estimation for Discrete-Time Markov Jumping Stochastic Neural Networks with Mixed Time-Delays

Abstract

This paper investigates state estimation problem for a new class of discrete-time stochastic recurrent neural networks (RNNs) with Markov jumping parameters and time-delays. The time-delays considered in this paper are mixed and include time-varying discrete delays and distributed delays. The discrete-time neural networks have a finite number of modes, and the modes may jump from one to another according to a Markov chain. We aim at designing a state estimator to estimate the neuron state through available output measurements. By using Laypunov-Krasovskii functional and linear matrix inequality (LMI) approach, a sufficient condition is established to solve the state estimation problem. The desired estimator matrix gain is characterized in terms of the solution to these LMIs. Finally, a numerical example is given to demonstrate the effectiveness of the proposed design method.