摘要
将灰色关联分析法应用到BP神经网络隐层结点数的确定中,实现了BP神经网络网络结构的优化,提高了网络的预测精度.仿真结果表明这种方法非常有效,同时也对BP神经网络的进一步研究提供了一种全新的思路.
The acting mechanism of the BP Neural Network＇ s hidden units and the number＇ s choice have been a difficult promble on the study of BP Nueral Network. By using the grey correlation analaysis on the hidden units number＇s determination of the BP Nueral Network, this method realized the optimal of BP Nueral Network, and also improve network＇ s forecasting accuracy. Its simulated result shows that the method is effective. At the same time, it also afford a new thinking to us for a fttrther study of the BP Nueral Network.
出处
《系统工程理论与实践》
EI
CSCD
北大核心
2005年第10期95-100,共6页
Systems Engineering-Theory & Practice
基金
国家自然科学基金(10171118
10471159)
教育部重点项目资助
重庆师范大学校级项目(05XLY017)
关键词
BP神经网络
灰色关联分析
网络结构的优化
BP nueral network
grey correhtion analysis
the optimal structure of the network
