Today automatic control systems have become an integrated part of our life. They appear in every things from simple electronic household products to air planes and spacecrafts. Automatic control systems can take highly different shapes but common to them all, is their function to manipulate a system so that it behaves in a desired fashion. Control of nonlinear systems is a major application area for neural networks. The control design problem will be approached in two ways: direct design methods and indirect design methods, and the network must be trained as the controller according to some kind of relevant criterion. In this thesis, nonlinear neuro-controller using neural network based actuator compensation scheme for nonlinear dynamical control system is presented. The scheme that leads to stability, target following, tracking error and filtered error is proved . The tuning of artificial neural network weights for controller are derived and adjusted based on Lypanove function approach. The verification of this scheme has been implemented using first order, 2-dymensional, nonlinear dynamical Pendulum problem and 1st order 3-dymensional nonlinear dynamical control system. The simulation can effectively compensate for the uncertain nonlinearity in the nonlinear uncertain dynamical control system. Necessary mathematical concepts, comments, concluding remarks, future works, figures and graphers, have also been presented.