NEW ERROR BOUNDS WITH THE NEAREST NEIGHBOR RULE

被引:12
作者
DEVIJVER, PA
机构
[1] Philips Research Laboratory, Brussels, 2 Av. Van Becelaere
关键词
D O I
10.1109/TIT.1979.1056099
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A distribution-free lower bound on the Bayes error rate is formulated In terms of the asymptotic error rate of the nearest neighbor rule with a reject option. Next, a closed form expression for an upper bound of the kth nearest neighbor error rate in terms of the Bayes rate is established. These results are discussed in the framework of recent works on nonparametric estimation of the Bayes error rate. ©1979 IEEE
引用
收藏
页码:749 / 753
页数:5
相关论文
共 12 条