| 支持向量机分类与回归算法的关系研究 |
| |
| 引用本文： | 孙德山. 支持向量机分类与回归算法的关系研究[J]. 计算机应用与软件, 2008, 25(2) |
| |
| 作者姓名： | 孙德山 |
| |
| 作者单位： | 辽宁师范大学数学学院,辽宁,大连,116029 |
| |
| 基金项目： | 辽宁省教育厅科学研究计划 |
| |
| 摘 要： | 基于统计学习理论的支持向量机算法以其优秀的学习性能已广泛用于解决分类与回归问题.分类算法通过求两类样本之间的最大间隔来获得最优分离超平面,其几何意义相当直观,而回归算法的几何意义就不那么直观了.另外,有些适用于分类问题的快速优化算法却不能用于回归算法中.研究了分类与回归算法之间的关系,为快速分类算法应用于回归模型提供了一定的理论依据.
|
| 关 键 词： | 支持向量机 分类 回归 核函数 |
RESEARCH ON THE RELATIONSHIP BETWEEN SUPPORT VECTOR MACHINE CLASSIFICATION AND REGRESSION ALGORITHMS |
| |
| Sun Deshan. RESEARCH ON THE RELATIONSHIP BETWEEN SUPPORT VECTOR MACHINE CLASSIFICATION AND REGRESSION ALGORITHMS[J]. Computer Applications and Software, 2008, 25(2) |
| |
| Authors: | Sun Deshan |
| |
| Affiliation: | Sun Deshan (Institute of Mathematics,Liaoning Normal University,Dalian 116029,Liaoning,China) |
| |
| Abstract: | Support vector machine algorithms based on statistical learning theory have been widely applied to solve classification and regression problems.Classification algorithms get the optimal separating hyperplane by the maximum distance between two samples.The geometric meaning of classification algorithms is very intuitive,but the geometric meaning of regression algorithms is not very intuitive.Additionally,a few fast optimization algorithms suitable for classification algorithms could not be applied to regress... |
| |
| Keywords: | Support vector machine Classification Regression Kernel function |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
