计算机与现代化Issue(2)：5-7,3.DOI:10.3969/j.issn.1006-2475.2012.02.002
支持向量机的缺陷及改进算法
Deficiencies of Support Vector Machines and Its Improved Algorithm
郭光绪1
作者信息
- 1. 南京航空航天大学计算机科学与技术学院,江苏南京 210016
- 折叠
摘要
Abstract
Traditionary support vector machines (SVMs) usually focus on edge patterns of data distribution, and support vectors (SVs) usually generates from these patterns. This paper proposes an alternative algorithm, which generates SVs from all training patterns. The sparsity of the algorithm is validated on most data sets far better than typical SVMs. The complexity of the algorithm in multi-class problems is merely equivalent to two class SVMs, which greatly solves the problems of too many variables or too many binary classifiers in multi-class SVMs.关键词
支持向量机/稀疏性/多类问题/推广性能Key words
support vector machines/sparsity/multi-class problems/generalization分类
信息技术与安全科学引用本文复制引用
郭光绪..支持向量机的缺陷及改进算法[J].计算机与现代化,2012,(2):5-7,3.
