Rolling element bearings are critical mechanical components in rotating machinery. Fault detection and diagnosis in the early stages of damage is necessary to prevent their malfunctioning and failure during operation. Vibration monitoring is the most widely used and cost-effective monitoring technique to detect, locate and distinguish faults in rolling element bearings. This paper presents an algorithm using feed forward neural network for automated diagnosis of localized faults in rolling element bearings. Normal negative log-likelihood value and kurtosis value extracted from time-domain vibration signals are used as input features for the neural network. Trained neural networks are able to classify different states of the bearing with 100% accuracy. The proposed procedure requires only a few input features, resulting in simple preprocessing and faster training. Effectiveness of the proposed method is illustrated using the bearing vibration data obtained experimentally.