The most frequently encountered decision making task for the humans is Classification. In finance, science and business, analysts are often faced with the task of classifying items based on historical or measured data. For Example Stock market analysts may wish to categorize a group of stocks as buy, sell, or hold. Neural networks are typically used for classification. Classification problem involves an input that the classifier has to identify to which output class the input most likely belongs. For classification problems, the network training is a supervised one in that the desired or target response of the network for each input pattern is always known a priori.