摘要
本文提出了一种改进的 BP神经网络预测方法。该方法的主要优点有 :网络结构简单 ,收敛速度快 ,预测精度高 ,减少了输入参数和样本量。笔者通过对具有高度非线性的股票价格变化进行短期预测 ,证明该方法优于传统的 BP神经网络方法。
In this paper,a redesigned BP network is been put forward to be used in forecasting.The main advantages of it include simple structure,efficient convergence,precise forecasting,etc,and what's more,the parameters and samples'input is less then before.In order to prove that it is better than the traditional BP network,the paper makes a short time forecasting for the hign non linear stock price and the result is accepted.
出处
《系统工程》
CSCD
2000年第5期76-78,75,共4页
Systems Engineering
