Abstract: This paper investigates the adaptive neural network control for a class of nonlinear systems. In order to improve the tracking performance, a new control scheme is proposed in this paper, which has the following characteristics:(1) The projection algorithm is used in the updating law of the weights to guarantee the boundedness of weights. (2) The inputs of the neural networks are modified by the reference error in order to compensate for the inherent network approximation errors. Simulation results are provided to demonstrate the effectiveness of the control methods.