摘要
When dealing with pattern recognition problems one encounters different types of prior knowledge. It is important to incorporate such knowledge into classification method at hand. A very common type of prior knowledge is many data sets are on some kinds of manifolds. Distance based classification methods can make use of this by a modified distance measure called geodesic distance.We introduce a new kind of kernels for support vector machines which incorporate geodesic distance and therefore are applicable in cases such transformation invariance is known. Experiments results show that the performance of our method is comparable to that of other state-of-the-art method.
When dealing with pattern recognition problems one encounters different types of prior knowledge. It is important to incorporate such knowledge into classification method at hand. A very common type of prior knowledge is many data sets are on some kinds of manifolds. Distance based classification methods can make use of this by a modified distance measure called geodesic distance. We introduce a new kind of kernels for support vector machines which incorporate geodesic distance and therefore are applicable in cases such transformation invariance is known. Experiments results show that the performance of our method is comparable to that of other state-of-the-art method.
出处
《自动化学报》
EI
CSCD
北大核心
2005年第2期202-208,共7页
Acta Automatica Sinica
基金
Supported by National Natural Science Foundation of P. R. China (50174038, 30170274)
关键词
测地距离
支持向量机
分类算法
核心函数
机器学习
Classification (of information)
Learning algorithms
Numerical methods
Pattern recognition
Statistical methods
