|
|||||
|
|
| 前馈神经网络的一种简单共轭梯度学习算法 | |
| 引用本文： | 梁久祯,何新贵,黄德双.前馈神经网络的一种简单共轭梯度学习算法[J].北京航空航天大学学报,2000,26(5):596-599. |
| 作者姓名： | 梁久祯 何新贵 黄德双 |
| 作者单位： | 1. 北京航空航天大学 计算机系; 2. 北京系统工程研究所 |
| 基金项目： | 国家自然科学基金;69705001; |
| 摘 要： | 针对前馈神经网络学习误差函数维数高、计算复杂度大的特点,对梯度下降BP算法加以改进从而构造出一种简单共轭梯度下降算法(MPARTAN算法).该算法计算复杂度不高于动量BP算法, 与FR共轭梯度法相比,该算法的稳定性好,又具有共轭梯度法的优点,收敛速度快.文中给出了该算法的收敛定理,并用2个实验例子比较了动量BP算法、FR共轭梯度法和MPARTAN算法的计算结果. |
| 关 键 词： | 神经网络 收敛 共轭梯度法 BP算法 MPARTAN算法 |
| 文章编号： | ： |
| 收稿时间： | 1999-03-25 |
Simple Conjugation-Gradient BP Algorithm for Feedforward Neural Networks |
|
| LIANG Jiu-zhen,HE Xin-gui,HUANG De-shuang.Simple Conjugation-Gradient BP Algorithm for Feedforward Neural Networks[J].Journal of Beijing University of Aeronautics and Astronautics,2000,26(5):596-599. | |
| Authors: | LIANG Jiu-zhen HE Xin-gui HUANG De-shuang |
| Institution: | 1. Beijing University of Aeronautics and Astronautics, Dept. of Computer Science and Engineering; 2. Beijing Institute of System Engineering |
| Abstract: | The high dimension of the learning error function for BP networks and the difficult computation complexity are investigated. A simple modified conjugation gradient decent algorithm (MPARTAN) is proposed based on improving the gradient BP algorithm. The computational complexity of this algorithm is not higher than that of the BP momentum algorithm. Compared with FR conjugation algorithm, this algorithm has better stability and fast speed quality of convergence. It is also investigated that the convergence theorems for this algorithm and comparison of the computing results by two examples for the promoted three algorithms: BP momentum algorithm, FR conjugation gradient algorithm and the novel MPARTAN algorithm. |
| Keywords: | neural networks convergence conjugate gradient method BP algorithm MPARTAN algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ | |
| 点击此处可从《北京航空航天大学学报》浏览原始摘要信息 | |
| 点击此处可从《北京航空航天大学学报》下载免费的PDF全文 | |