ABSTRACT
Neural Network (ANNs) as a forecasting method.
ANNs has been widely applied to various areas.
ANN is developed in three layers; an input layer,
middle or hidden layer(s), and an output layer.
Each layer consists of several neurons, which are
interconnected by sets of correlation weights. The
input layer’s neurons receive their activation from
the environment, while the activation levels of
neurons in the hidden and output layers are com-
puted as a function of the activation levels of the
neurons feeding into them. The information which
is received as inputs will be transferred to the hid-
den layer, and produce an output with the trans-
fer function. Additionally, the learning processing
(or training) is formed by adjusting the weight of
interconnectivity neurons. (Al-Tabtabi, 1998).