Improving the input of classified neural networks through feature construction

A general classification algorithm of neural networks is unable to obtain satisfied results because of the uncertain by existing among the features in most classificatio programs, such as interaction. With new features constructed by optimizing decision trees of examples, the input of neural networks is improved and an optimized classification algorithm based on natural networks is presented. A concept of dispersion of a classification program is also introduced too in this paper. At the end of the paper, an analysis is made 'with an example.