Analysis of an impact linear relationship between input variables having on prediction of BP neural network

Since the artificial neural networks were put forward, they have been used widely in predicting, and achieved good effect. But few pay attention to what an effect input variables with the linear correlation will have on the artificial neural network. Based on one example, I analyzed and studied an influence which the input variables with linear relation have on stability and prediction effect of BP neural networks predictive model. The results show that when the linear correlation between input variables is eliminated linear correlation, prediction accuracy and stability of BP neural networks can be improved.