The problem of tracking control is studied for a class of uncertain strict-feedback nonlinear systems. A new
robust adaptive control design approach is presented by approximating all the unknown parts of the system with a single
neural network. By using this approach, the actual control law and the adaptive law of the controller can be given directly,
and the problems, such as control design complexity and high computational burden, are dealt with effectively. The stability
analysis shows that the closed-loop system signals are semi-globally uniformly ultimately bounded, and the tracking error can
be made arbitrary small by choosing control parameters. Simulation results show the effectiveness of the proposed approach.