摘要
综述了基于超曲面的分类算法,该算法通过区域合并计算获得多个超平面组成的双侧闭曲面作为分类超曲面对空间进行划分.分类超曲面可以有效地解决在有限连通区域分布很复杂的非线性数据多类分类问题,分析了算法准确率与极小样本集的关系,总结了已有成就和最新进展,指出了基于超曲面的分类算法进一步发展的方向.
In this paper, a classification method based on Hyper Surface ("HSC" for short) is introduced. In this method, the space is partitioned through classification hyper-surface which are double-sided closed surfaces consisting of several hyper-surfaces by merging the connected regions. HSC can efficiently solve the nonlinear multi-class classification problems, in which the sample data distributions are very complicated within the finite connected regions. The relationship between accuracy and the minimal consistent subset is analyzed. Finally, the existing achievements and the latest progresses in this subject are summarized, and the future research directions are pointed out.
出处
《智能系统学报》
2007年第6期1-7,共7页
CAAI Transactions on Intelligent Systems
基金
国家自然科学基金资助项目(60435010
60675010)
国家重点基础研究发展计划资助项目(2006AA01Z128)
北京市自然科学基金资助项目(4052025).
关键词
超曲面
分类算法
机器学习
hyper surface
classification algorithm
machine learning