ABSTRACT
Neural networks are consisting of one or more layers of interconnected nodes. These individual nodes are known as perceptrons. In a Multi Layered Perceptron (MLP) perceptrons are arranged into layers and layers are connected with other another. In the MLP there are three types of layers namely, the input layer, hidden layer(s), and the output layer. The objective of the neural network is to minimize some measure of error. In Neural networks, samples with known features are used for training purposes. Usually training data set includes a number of cases, each containing values for a range of input and output variables and generate different classes. This operation requires few decisions like: which samples to use, and how many (and which) samples to gather. After training, the purpose of the network is to assign each test (unknown) sample to one of the number of class generated using training process (classification).
