DocumentCode :
928684
Title :
An upper bound on the asymptotic error probability on the k-nearest neighbor rule for multiple classes (Corresp.)
Author :
Gyorfi, Laszlo ; Gyorfi, Zoltan
Volume :
24
Issue :
4
fYear :
1978
fDate :
7/1/1978 12:00:00 AM
Firstpage :
512
Lastpage :
514
Abstract :
If 
, denotes the asymptotic error probability of the 
- nearest neighbor rule for 
classes and 
denotes the Bayes probability of error, then conditions are given that yield 
.
, denotes the asymptotic error probability of the - nearest neighbor rule for classes and denotes the Bayes probability of error, then conditions are given that yield .Keywords :
Pattern classification; Bayesian methods; Convergence; Error probability; Information theory; Nearest neighbor searches; Pattern classification; Random variables; Upper bound; Virtual manufacturing;
fLanguage :
English
Journal_Title :
Information Theory, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9448
Type :
jour
DOI :
10.1109/TIT.1978.1055900
Filename :
1055900
Link To Document :
