人工神经网络BP算法的改进及其应用

对传统的ＢＰ算法进行了改进，提出了ＢＰ神经网络动态全参数自调整学习算法，又将其编制成计算机程序，使得隐层节点和学习速率的选取全部动态实现，减少了人为因素的干预，改善了学习速率和网络的适应能力。计算结果表明：ＢＰ神经网络动态全参数自调整算法较传统的方法优越，训练后的网络模型不仅能准确地拟合训练值，而且能较精确地预测未来趋势。

The Improvement of BP Algorithm and Its Application

In this paper, BP algorithm of artificial neural network is improved, the self adjusted algorithm of all parameters has been proposed for the back propagation learning, and programmed a C language procedure. It can make the selection of hidden layer units and rate of studying easily in the course of training, reduce ar ti ficial influence and improve the adaptive ability of rate of studying and neural network. Our conclusion shows that the self adjusted BP algorithm of all parameters is superior to the statistical modeling approach, the model of artificial neural network in training can not only exactly imitate training valuation but also make prediction accurately.