The Application Of Artificial Neural Network In Data Mining

Because of the chanciness and abnormity of the history data, Data Mining is confronted with the data, which is often noisy, non- linear, unorderly. However, Neural Network has the advantage to process these data. Its processing need a great deal of data which is used for producing sufficient learning and test set in order to learn and evaluate effectively the performance of Neural Network. And the data mentioned above can be provided by the data mining, which is based on the data warehouse or big database. Because they have their own advantages, the research on data mining based on Neural Network has the great significance.Presently, the research on methods of data mining is an innovative direction in the field of artificial intelligent, also is the orientation of future intelligent decision technology. A good DM method will not only result in a great change for software industry, but also have much influence on the processing of other industry, world economy and society advancing.Based on the analysis of all kinds of DM (data mining) technology, this paper has researched the application of ANN (artificial neural network) in DM. In the paper, data preparative and Artificial Neural Network parameter in DM is discussed mainly. To the existed problem of standard BP arithmetic, inefficient and easy getting into local minimum, an improved BP arithmetic is put forward. And the adjusted frequency and study efficiency of this arithmetic is advanced in stress. Paper has reasoned it not only in theories, but also in experiments: using the math logic problem, "and" problem. Experiments results show that the improved BP arithmetic has shorted the study time, improved the study efficiency and averted from getting into local minimum in some degree.