Using bayes error rate estimation to analyze feature spaces (Conference Presentation)

2020 ◽  
Author(s):  
Sriram Bapatla ◽  
Edmund G. Zelnio ◽  
Elizabeth Sudkamp
Keyword(s):  
Error Rate ◽  
Rate Estimation ◽  
Bayes Error Rate ◽  
Feature Spaces ◽  
Bayes Error

COMBINATION OF MULTIPLE CLASSIFIERS BY MINIMIZING THE UPPER BOUND OF BAYES ERROR RATE FOR UNCONSTRAINED HANDWRITTEN NUMERAL RECOGNITION

2005 ◽  
Vol 19 (03) ◽  
pp. 395-413 ◽  
Author(s):  
HEE-JOONG KANG ◽  
SEONG-WHAN LEE
Keyword(s):  
Probability Distribution ◽  
Error Rate ◽  
Upper Bound ◽  
Approximation Scheme ◽  
Combination Method ◽  
New Combination ◽  
High Dimensional ◽  
Multiple Classifiers ◽  
Bayes Error Rate ◽  
Bayes Error

In order to raise a class discrimination power by the combination of multiple classifiers, the upper bound of Bayes error rate which is bounded by the conditional entropy of a class and decisions should be minimized. Based on the minimization of the upper bound of the Bayes error rate, Wang and Wong proposed only a tree dependence approximation scheme of a high-dimensional probability distribution composed of a class and patterns. This paper extends such a tree dependence approximation scheme to higher order dependency for improving the classification performance and thus optimally approximates the high-dimensional probability distribution with a product of low-dimensional distributions. And then, a new combination method by the proposed approximation scheme is presented and evaluated with classifiers recognizing unconstrained handwritten numerals.

Expected Bayes Error Rate in Supervised Classification of Spatial Gaussian Data

Informatica ◽  
2011 ◽  
Vol 22 (3) ◽  
pp. 371-381 ◽  
Author(s):  
Kęstutis Dučinskas ◽  
Lijana Stabingienė
Keyword(s):  
Error Rate ◽  
Supervised Classification ◽  
Bayes Error Rate ◽  
Bayes Error ◽  
Gaussian Data
Sign in / Sign up

Export Citation Format

Share Document