A fuzzy sliding mode controller based on radial basis function neural network (RBFNN) is proposed in this paper. In the applications of sliding mode controllers the main problem is that a whole knowledge of the system dynamics and system parameters is required to be able to compute equivalent control. In this paper, a RBFNN is used to compute the equivalent control. The weights of the RBFNN are changed according to adaptive algorithm for the system state to hit the sliding surface and slide along it. The initial weights of the RBFNN set to zero, and then tune online, no supervised learning procedures are needed. Computer simulations of three link robot manipulator for trajectory tracking verify the validity of the proposed adaptive neural network based fuzzy sliding mode controller in the presence of uncertainties.