Arbitrarily Tight Upper and Lower Bounds on the Bayesian Probability of Error January 1996 (vol. 18 no. 1) pp. 89-91
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.476017
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. [1] P.A. Devijver, "On a new class of bounds on Bayes risk in multi-hypothesis pattern recognition," IEEE Trans. Computers, vol. 23, pp. 70-80, Jan. 1974.
Index Terms:
Bayesian decision, probability of error, statistical pattern recognition.
Citation:
Hadar Avi-Itzhak, Thanh Diep, "Arbitrarily Tight Upper and Lower Bounds on the Bayesian Probability of Error," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 18, no. 1, pp. 89-91, Jan. 1996, doi:10.1109/34.476017 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||