Sliding mode control is a nonlinear control strategy that is well known for its robustness characteristics. However, the discontinuous control signal causes a significant problem of chattering. In this paper, a synergistic combination of neural networks with sliding mode control methodology for magnetic levitation systems is proposed. In the present approach, a neural network is utilized to estimate the equivalent control. Moreover, a new and simple approach is utilized to construct switching control term for overcome the chattering problem. As a result, the chattering is eliminated. The reduction of the chattering of sliding mode control is achieved by using a defined distance function as the switching control term which only measure the distance between the trajectory of state errors and the sliding surface. Experimental study carried out on the magnetic levitation system is presented. Experiments verified that the proposed control has the advantage of less chattering in sliding mode control.