The connections between neurons are known as ‘weights’. The objective of developing a neural network is to assign suitable numerical values to these weights. This is done through the training process where the network is fed a set of input and output data. The network learns through these input-output combinations adjust the weights accordingly. The ANNs can learn from historical pattern during the training process. In this study, a typical feedforward neural network is used. A feedforward network is the one in which the information moves in only one direction, forward, from the input neurons, through the hidden neurons (if any) and to the output neurons.