DocumentCode :
3724130
Title :
Theoretical and Empirical Criteria for the Edited Nearest Neighbour Classifier
Author :
Ludmila I. Kuncheva;Mikel Galar
Author_Institution :
Sch. of Comput. Sci., Bangor Univ., Bangor, UK
fYear :
2015
Firstpage :
817
Lastpage :
822
Abstract :
We aim to dispel the blind faith in theoretical criteria for optimisation of the edited nearest neighbour classifier and its version called the Voronoi classifier. Three criteria from past and recent literature are considered: two bounds using Vapnik-Chervonenkis (VC) dimension and a probabilistic criterion derived by a Bayesian approach. We demonstrate the shortcomings of these criteria for selecting the best reference set, and summarise alternative empirical criteria found in the literature.
Keywords :
"Prototypes","Training","Data mining","Bayes methods","Upper bound","Electronic mail","Probabilistic logic"
Publisher :
ieee
Conference_Titel :
Data Mining (ICDM), 2015 IEEE International Conference on
ISSN :
1550-4786
Type :
conf
DOI :
10.1109/ICDM.2015.36
Filename :
7373395
Link To Document :
بازگشت