ANN is a mathematical model of human perception
that can be trained to perform a particular task
based on available empirical data. Particularly, when
the relationships between data are unknown, the
ANN can efficiently establish their underlying connections.
There exist many ANN variants, which can be
categorized into 6 architectures, i.e., Multi Layer Perceptron
(MLP), Radial Basis Function (RBF), Learning
Vector Quantization (LVQ), Adaptive Resonance
Theory (ART), Auto-Associative NNs and Self Organizing
Map (SOM) [18-22]. This study focuses particularly
on MLP and RBF types