Analysis on the Classification Error of ANNS

ANNS are efficient and objective classification methods in subject classification. It is an information processing system whose design was inspired by the structure and functioning of neuron in biology. Thus, they have been successfully applied to the numerous classification fields. Sometimes, however, classifications do not match the real world, and are subjected to errors. These problems are caused by the nature of artificial neural networks. By studying of these problems, it helps us to have a better understanding on ANNS classification and find a way to improve their performance.