| 共轭梯度与牛顿混杂算法及在神经网络的应用 |
| |
| 引用本文： | 孟江,王耀才,洪留荣.共轭梯度与牛顿混杂算法及在神经网络的应用[J].计算机工程与应用,2004,40(35):84-86,172. |
| |
| 作者姓名： | 孟江 王耀才 洪留荣 |
| |
| 作者单位： | 中国矿业大学信电学院高科技应用研究所,徐州,221008 |
| |
| 摘 要： | 在Powell重启动共轭梯度法基础上,利用共轭迭代过程产生的二阶导数信息,构造出当前点的牛顿方向,从而得出一类快速共轭梯度法。用于神经网络逼近非线性函数的学习结果表明,该算法的收敛速度均高于使用相同构造公式的共轭梯度算法。
|
| 关 键 词： | 共轭梯度与牛顿混杂算法 收敛速度 神经网络 |
| 文章编号： | 1002-8331-(2004)35-0084-03 |
Conjugate-Gradient-and-Newton Hybrid Method and Application in Neural Network |
| |
| Meng Jiang Wang Yaocai,Hong Liurong.Conjugate-Gradient-and-Newton Hybrid Method and Application in Neural Network[J].Computer Engineering and Applications,2004,40(35):84-86,172. |
| |
| Authors: | Meng Jiang Wang Yaocai Hong Liurong |
| |
| Abstract: | Based on the restart conjugate gradient method by Powell,the current point's Newton direction has been con-structed according to the information of second derivative in the course of conjugate-gradient calculation,which produces Conjugate-Gradient-and-Newton Hybrid(CGNH)method.The learning result applied in neural network to approach to non-linear function shows that the rate of convergence of CGNH method is better than that of conjugate gradient method using the same constructing equation. |
| |
| Keywords: | Conjugate-Gradient-and-Newton Hybrid method the rate of convergence neural network |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
