Conventional computers have been successful for solving many real world problems but the algorithmic requirement limits their usefulness in applications where no exact mathematical relationship between input-output variables can be established. One such problem is the effects of noise pollution on human work efficiency. From the literature survey, it is observed that the human work efficiency depends to a large extent on noise level, type of task, and exposure time. The cause-effect relationships of these parameters are complex and highly non-linear in nature. It is difficult to develop a mathematical model in such situations. Artificial neural network are model-free estimators that do not require articulating a mathematical relationship. They "learn from experience" with numerical data. Hence, an attempt is made in this paper to develop a model for predicting the effects of noise pollution on human work efficiency using neural networks