In this paper, a neural networks (NN) based adaptive sliding mode controller (SMC) is introduced. The selection of SMC feedback gains is normally based on one operating point and thus the performance of the controller away from the design operating point is, of necessity, a compromise. The adaptive SMC is proposed to overcome the limitations imposed on the effectiveness of the SMC under different operating conditions. Neural networks are used for online prediction of the optimal SMC gains when the operating point changes. The proposed method has been applied to a power system stabilizer (PSS) of a single machine power system. Simulation results are included to demonstrate the performance of the proposed control scheme. (C) 2010 Published by Elsevier Ltd.