| 最小二乘支持向量机的预优共轭梯度法 |
| |
| 引用本文： | 吴青,刘三阳,张乐友.最小二乘支持向量机的预优共轭梯度法[J].系统工程与电子技术,2007,29(10):1746-1748. |
| |
| 作者姓名： | 吴青 刘三阳 张乐友 |
| |
| 作者单位： | 西安电子科技大学数学科学系,陕西,西安,710071 |
| |
| 摘 要： | 针对Suyken等人提出的最小二乘支持向量机的共轭梯度法在输入样本的个数较大时,需要求解高阶线性方程组这一缺陷,提出了一种新算法。该算法利用分块矩阵的思想将该高阶线性方程组系数矩阵降阶,为了提高收敛速度,克服数值的不稳定性,采用条件预优共轭梯度法求解低阶的线性方程组。通过仿真试验证明用本文方法训练最小二乘支持向量机比共轭梯度法的训练速度提高了将近一倍。
|
| 关 键 词： | 最小二乘法 支持向量机 分块矩阵 共轭梯度 |
| 文章编号： | 1001-506X(2007)10-1746-03 |
| 修稿时间： | 2006年10月8日 |
Preconditioning conjugate gradient method for least squares SVM |
| |
| WU Qing,LIU San-yang,ZHANG Le-you.Preconditioning conjugate gradient method for least squares SVM[J].System Engineering and Electronics,2007,29(10):1746-1748. |
| |
| Authors: | WU Qing LIU San-yang ZHANG Le-you |
| |
| Abstract: | In allusion to the shortcoming of a conjugate gradient method for training least squares SVM proposed by Suykens etc,a new algorithm is presented.Matrix partitioning is applied to reduce the system of equations.In order to improve the rate of convergence and overcome instability of numerical value,a preconditioning conjugate gradient method is presented for solving the reduced system of linear equations.Numerical results show that our approach is about twice as efficient as the conjugate gradient method for least squares SVM. |
| |
| Keywords: | least squares SVM matrix partitioning conjugate gradient |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
