The objective of this paper is to show the results of the practical implementation of a neural network (NN) tracking controller on a single flexible link and compare its performance to that of proportional derivative (PD) and proportional integral derivative (PID) standard controllers. The NN controller is composed of an outer PD tracking loop, a singular perturbation inner loop for stabilization of the fast flexible-mode dynamics, and an NN inner loop used to feedback linearize the slow pointing dynamics. No off-line training or learning is needed for the NN. It is shown that the tracking performance of the NN controller is far better than that of the PD or PID standard controllers. An extra friction term was added in the tests to demonstrate the ability of the NN to learn unmodeled nonlinear dynamics.