| BP神经网络的MATLAB编程实现及讨论 |
| |
| 引用本文： | 余晓红. BP神经网络的MATLAB编程实现及讨论[J]. 浙江交通职业技术学院学报, 2007, 8(4): 45-48 |
| |
| 作者姓名： | 余晓红 |
| |
| 作者单位： | 杭州职业技术学院,信息电子工程系,浙江杭州,310018 |
| |
| 摘 要： | BP神经网络具有很强的非线性函数逼近能力。通过Matlab编程实现了BP网络对一个二元函数的逼近,针对BP网络学习速度慢的缺点,采用含动量项的学习算法提高了收敛速度。通过Matlab仿真方法,研究了学习率和动量因子对算法学习速度的影响。
|
| 关 键 词： | 神经网络 BP网络 学习算法 |
| 文章编号： | 1671-234X（2007）04-0045-04 |
| 收稿时间： | 2007-07-22 |
| 修稿时间： | 2007-07-22 |
Matlab Implementation and Discussion of BP Neural Network |
| |
| YU Xiao-hong. Matlab Implementation and Discussion of BP Neural Network[J]. Journal of Zhejiang Vocational and Technical Institute of Transportation, 2007, 8(4): 45-48 |
| |
| Authors: | YU Xiao-hong |
| |
| Abstract: | BP neural network has strong ability of approaching nonlinear function.Matlab programming of BP network was implemented to approach a 2-dimentional function.The convergence speed was expedited via the momentum in the learning algorithm.The influence of learning rate and momentum against the learning speed were discussed. |
| |
| Keywords: | Matlab |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
