| 基于人为误差的支持向量机——4E-SVM |
| |
| 引用本文： | 王炜,王淑艳,郭小明,刘丽琴.基于人为误差的支持向量机——4E-SVM[J].大连民族学院学报,2008,10(3):243-245. |
| |
| 作者姓名： | 王炜 王淑艳 郭小明 刘丽琴 |
| |
| 作者单位： | [1]辽宁师范大学数学学院,辽宁大连116029 [2]辽宁石油化工大学理学院,辽宁抚顺113001 |
| |
| 摘 要： | 传统的支持向量机是将分类问题转化成二次规划问题来解决的。针对传统的支持向量机算法及其变形算法忽略了训练集数据含有较大人为误差参与时其算法精度所存在的保障问题，提出了基于人为误差的支持向量机（artificial error-support vector machine以下称AE—SVM）的基本理论，并建立了AE—SVM的理论模型。该模型是C—SVM模型的改进和推广。
|
| 关 键 词： | 支持向量机(SVM) 统计学习理论 AE-SVM |
Support Vector Machine built on Artificial Error |
| |
| Institution: | WANG Wei , WANG Shu -yan , GUO Xiao - ming, LIU Li - qin ( School of Mathematics, Liaoning Normal University, Dalian Liaoning 116029, China; School of Science, Liaoning Shihua University, Fushun Liaoning 113001, China) |
| |
| Abstract: | Traditional support vector machine changes the sort problems into quadratic programming problems to solve. In this paper, for the traditional and deformation algorithms of Support Vector Machine neglected when the practice of extracting data with bigger participation of artificial error, we described the data from the centralized training with the participation of the artifi- cial error, emphatically transformed the experience risk measurement of the original support vector machine algorithm, introduced the basic theory of the support vector machine based on the artificial error（ called AE -SVM） , and established theoretical model of AE -SVM, which is the upswing and extension of C -SVM model. |
| |
| Keywords: | support vector machine （SVM） statistical learning theory AE - SVM |
| 本文献已被 维普 等数据库收录！ |
|
