State observation design for time-delay neural networks systems

Abstract

In order to solve the immeasurable problem of the neuron states, and the universal time-delay occurrence in the neural networks systems, this paper studies the state observation problem for time-delay neural networks systems, constructs a new Lapunov-krasovskii functional, designs an efficient delay-dependent observation algorithm to observe the neuron states from the available network outputs. Distinguishing from the exiting results in terms of nonlinear matrix inequalities, the results of our method are formulated in the form of linear matrix inequalities (LMI). An illustrative example is given in the end to show that the design method of the observation given is effective and easy to apply.