Title :
Arbitrarily tight upper and lower bounds on the Bayesian probability of error
Author :
Avi-Itzhak, H. ; Diep, Thanh
Author_Institution :
Canon Res. Center America, Palo Alto, CA, USA
fDate :
1/1/1996 12:00:00 AM
Abstract :
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
Keywords :
Bayes methods; decision theory; error statistics; optimisation; pattern recognition; probability; statistical analysis; Bayesian decision systems; Bayesian probability; error probability; lower bounds; minimum probability; statistical pattern recognition; two-class problem; upper bound; Bayesian methods; Closed-form solution; Density functional theory; Entropy; Information analysis; Information systems; Laboratories; Machine intelligence; Pattern recognition; Probability density function;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
