| BP神经网络用于藻类生长预测的改进 |
| |
| 引用本文： | 杨吟冬,周永权,刘永彬.BP神经网络用于藻类生长预测的改进[J].现代计算机,2006(9):11-13,29. |
| |
| 作者姓名： | 杨吟冬 周永权 刘永彬 |
| |
| 作者单位： | [1]广西大学计算机与电子信息学院,南宁530004 [2]广西民族大学计算机与信息科学学院,南宁530006 |
| |
| 基金项目： | 国家自然科学基金，广西自然科学基金 |
| |
| 摘 要： | 针对传统的BP神经网络应用于藻类生长预测时,往往出现训练时间较长、输出数据精度低等问题.本文提出了在含有两层隐含层的BP神经网络结构中,对于数量一定的神经元,若神经元在隐含层分配合理,则BP神经网络可以达到减少训练次数并且能满足问题精度的要求.应用实例表明,该方法对预测藻类生长显得非常有效.
|
| 关 键 词： | BP神经网络 隐含层 神经元分配 藻类生长预测 |
| 收稿时间： | 2006-06-15 |
| 修稿时间： | 2006-06-15 |
An Improved Method based on BP Neural Network for Forecasting Alga's Growth |
| |
| YANG Yin-dong,ZHOU Yong-quan,LIU Yong-bin.An Improved Method based on BP Neural Network for Forecasting Alga''''s Growth[J].Modem Computer,2006(9):11-13,29. |
| |
| Authors: | YANG Yin-dong ZHOU Yong-quan LIU Yong-bin |
| |
| Affiliation: | 1. College of Computer and Electron Information, Guangxi University, Nanning 530003 China; 2. College of Computer and Information Science, Guangxi University for Nationalities, Nanning 530006 China |
| |
| Abstract: | Traditional methods based on BP neural network for forecasting alga's growth has the problems of training time is too long, and data's precision is not enough. This paper gives a method on how to distribute a certain number of neuron to a BP neural network's two hidden layers. This method can reduce BP neural network's training time and can satisfy the data's precision. Experiments are done to explain and verify this method. |
| |
| Keywords: | BP Neural Network Hidden Layers Neuron Distribute Alga Growth Forecasting |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
