Self-learning And Application Of Neural Network

In recent years,the neural network model has made great progress in the fields of computer vision and image recognition,and has significantly improved the industry standards in various fields.In this paper,we review BP neural network and the con-volutional neural network in detail.Meanwhile,we build a neural network model to predict the house price.In this paper,we combine different neural network models to predict house prices.We also apply a multiple linear regression model to compare with the neural network model.There are six indicators adopted for housing prices prediction in this paper.They include that the total urban population,urbanization rate,GDP,five-year loan interest rate,money supply,and consumer price index(CPI).From the empirical results implied by our model,we found that the simplest multivariate linear regression model has the best prediction of house prices,while the neural network prediction ability does not increase when one increases the network layers.This may lead that the neural network may become overfitting.