Arbitrarily tight upper and lower bounds on the Bayesian probability of error

被引:32
|
作者
AviItzhak, H [1 ]
Diep, T [1 ]
机构
[1] CANON RES CTR,PALO ALTO,CA 94304
关键词
Bayesian decision; probability of error; statistical pattern recognition;
D O I
10.1109/34.476017
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper presents new upper and lower bounds on the minimum probability of error of Bayesian decision systems for the two-class problem. These bounds can be made arbitrarily close to the exact minimum probability of error, making them tighter than any previously known bounds.
引用
收藏
页码:89 / 91
页数:3
相关论文
共 50 条