Robust asymptotic neuro observer for unknown nonlinear systems

This paper concerns the development of a robust asymptotic neuro observer for a class of unknown nonlinear systems. The Luenberger type observer in this system have two important terms, the first term assures the boundness of the weights and in second term has a time delayed term, which approximates the derivatives of the measurable states. The Lyapunov-Krasovskii technique is used to proof the robust asymptotic stability on average of the neuro observer as well as boundness of the observation error.