Least squares support vector machine classifiers

Least squares support vector machine classifiers
复制标题

DOI:
10.1023/a:1018628609742
复制
发表时间:
1999-06-01
影响因子:
3.1
通讯作者:
Vandewalle, J
Vandewalle, J
中科院分区:
计算机科学4区
文献类型:
--
作者:
Suykens, JAK;Vandewalle, J

文献摘要

被引文献

相似文献

在这封信中,我们讨论了支持向量机(SVM)分类器的最小二乘版本。由于公式中的等式类型约束,解决方案遵循求解一组线性方程,而不是经典SVM的二次规划。该方法说明了一个双螺旋基准分类问题。
In this letter we discuss a least squares version for support vector machine (SVM) classifiers. Due to equality type constraints in the formulation, the solution follows from solving a set of linear equations, instead of quadratic programming for classical SVM's. The approach is illustrated on a two-spiral benchmark classification problem.