In this paper, a nonlinear proportional-derivative controller plus adaptive neuronal network compensation is proposed. With the aim of estimating the desired applied torque, a neural network is used. Then, adaptation laws for the input and output weights are derived. Asymptotic convergence of the position and velocity tracking errors is proven, while the input and output weights of the neural network are showed to be uniformly bounded. The proposed scheme has been experimentally validated in real time in a horizontal two degrees-of-freedom robot Experimental results confirmed the practical feasibility of the proposed adaptive neural network-based controller.