This paper presents a new method for rotor and stator resistance estimation using atificial neural network for sensorless induction motor drive. The speed of the induction motor also is estimated using the artificial neural network. Therefore, the accurate estimation of the speed of induction motor, the rotor and stator resistance improved the quality of the sensorless induction motor drive. The results of simulation and experiment show that the estimated speed tracks the real speed of induction motor, simultaneously the error between the estimated rotor and stator resistance using neural network and the normal rotor and stator resistance is extremely small.