The success of strategic and detailed planning of public transportation highly depends on accurate demand information data. Short-term forecasting is the key to the success of transportation operations planning such as time-tabling and seat allocation. This study adopts neural networks to develop short-term passenger demand forecasting models to be used in operational management of light rail services. A multi-layer perceptron (MLP) model is preferred due to not only its simple architecture but also proven success of solving approximation problems. For eliminating the significant seasonality in time slots, each time slot is handled independent of the others, and an artificial neural network based on daily data is developed for each. Regarding to the 74 different time slots, 74 different neural networks are trained by history data. Three illustrative examples are demonstrated on one of the time slots and performance of the forecast models are evaluated based on mean square errors (MSE) and mean absolute percentage errors (MAPE).