| 动态全参数自调整BP神经网络预测模型的建立 |
| |
| 引用本文： | 李晓峰.动态全参数自调整BP神经网络预测模型的建立[J].预测,2001,20(3):69-71. |
| |
| 作者姓名： | 李晓峰 |
| |
| 作者单位： | 四川大学,管理科学与工程系,四川,成都,610065 |
| |
| 摘 要： | 本文从减少干预的思想出发，提出了BP神经网络动态全参数自调整学习算法，使得隐层节点和学习速率的选取全部动态实现，实现了学习速率和网络的适应能力，最后又将改善后的BP神经网络应用到经济领域中，得到了比常规经济学模型更优的效果。
|
| 关 键 词： | 神经网络 BP算法 自调整 自组织方法 预测模型 |
| 文章编号： | 1003-5192(2001)03-0069-03 |
The Establishment of Forecasting Model Based on BP Neural Network of Self-Adjusted All Parameters |
| |
| LI Xiao,feng.The Establishment of Forecasting Model Based on BP Neural Network of Self-Adjusted All Parameters[J].Forecasting,2001,20(3):69-71. |
| |
| Authors: | LI Xiao feng |
| |
| Abstract: | In this paper, in order to reduce the external influence, the self adjusted algorithm of all parameters has been proposed for the back propagation learning.It can make the seleetion of hidden layer units and rate of studying easily in the course of training,and improve the adaptive ability of rate of studying and neural network.At last,we put it use into the economic fields,our conclusion shows that the self adjusted BP algorithm of all parameters is superior to the statistical modeling approach. |
| |
| Keywords: | neural network BP algorithm self adjusted group method of data handling(GMDH) |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
