This thesis investigates the application of a neural network based model reference adaptivernintelligent controller for controlling of the nonlinear systems. In this scheme, the intelligentrnsupervisory loop is incorporated into the conventional model reference adaptive controllerrnframework by utilizing an online growing multilayer back propagation neural network structurernin parallel with it. The idea is to control the plant by minimizing the tracking error between therndesired reference model and the nonlinear system using conventional model reference adaptiverncontroller by estimating the adaptation law using a multilayer back propagation neural network. rnIn the conventional model reference adaptive controller (MRAC) scheme, the controller isrndesigned to realize the plant output converges to reference model output based on the plant,rnwhich is linear. This scheme is effective for controlling the linear plant with unknownrnparameters. However, using MRAC to control the nonlinear system in real time is difficult. rnThe Neural Network is used to compensate the nonlinearity of the plant that is not taken intornconsideration in the conventional MRAC. The proposed neural network based model referencernadaptive controller can significantly improve the system behavior and force the system tornfollow the reference model and minimize the error between the model and the plant output.rnAdaptive law using Lyapunov stability criteria for updating the controller parameters onlinernhas been formulated.rnThe effectiveness of the proposed control scheme is verified by developing the simulationrnresults for simple pendulum and Vander poll oscillation as a benchmark study inrnMATLAB/SIMULINK software. It is observed from the simulation results that the proposedrnneural network based Direct MRAC has 3.13sec rise time, 5.15sec settling time for 0.1radrndisturbance and 3.12sec rise time, 5.21sec settling time for 0.2rad disturbance. Whereas, thernconventional direct model reference adaptive control has 5.42sec rise time, 15.5sec settling timernfor 0.1rad disturbance and 5.01sec rise time, 15.52sec settling time for 0.2rad disturbance.rnIt is shown that the proposed neural network based Direct MRAC has small rising time, steadystaternerror