DocumentCode :
1502207
Title :
Data compression and local metrics for nearest neighbor classification
Author :
Ricci, Francesco ; Avesani, Paolo
Author_Institution :
Ist. per la Ricerca Sci. e Tecnologica, Povo, Italy
Volume :
21
Issue :
4
fYear :
1999
fDate :
4/1/1999 12:00:00 AM
Firstpage :
380
Lastpage :
384
Abstract :
A local distance measure for the nearest neighbor classification rule is shown to achieve high compression rates and high accuracy on real data sets. In the approach proposed here, first, a set of prototypes is extracted during training and, then, a feedback learning algorithm is used to optimize the metric. Even if the prototypes are randomly selected, the proposed metric outperforms, both in compression rate and accuracy, common editing procedures like ICA, RNN, and PNN. Finally, when accuracy is the major concern, we show how compression can be traded for accuracy by exploiting voting techniques. That indicates how voting can be successfully integrated with instance-based approaches, overcoming previous negative results
Keywords :
data compression; feedback; learning (artificial intelligence); optimisation; pattern classification; data compression; editing procedures; feedback learning algorithm; local distance measure; local metrics; metric optimization; nearest neighbor classification; voting techniques; Data compression; Data mining; Feedback; Independent component analysis; Machine learning; Nearest neighbor searches; Neural networks; Prototypes; Recurrent neural networks; Voting;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/34.761268
Filename :
761268
Link To Document :
بازگشت