ABSTRACT

Artificial neural networks (ANNs) are a broad category of computer algorithms which have the ability to learn some target values (desired output) from a set of chosen input data that has been introduced to the network under both supervised and self-adjusted or unsupervised learning algorithms. The learning or training process is achieved by minimizing the error between the desired output and the output computed by the neural network using different learning algorithms. The predictive ability of the trained neural network can be tested by adding observations not included previously.