Increasing the number of hidden layers of the artificial neural network would increase the ability of the system to effectively learn from the input and update its weight according to the statistics of the input data in order to achieve the desire signal and reduce the error of the system. In other words the training process is the process of changing the weight of the system according to the changes of the input. When we increase the number of hidden layers the weight update (training process) of the system will be improved and the performance of the neural network will be increased.