DocumentCode :
1238660
Title :
Learning vector quantization with training data selection
Author :
Pedreira, Carlos E.
Author_Institution :
Univ. Fed. do Rio de Janeiro, Brazil
Volume :
28
Issue :
1
fYear :
2006
Firstpage :
157
Lastpage :
162
Abstract :
In this paper, we propose a method that selects a subset of the training data points to update LVQ prototypes. The main goal is to conduct the prototypes to converge at a more convenient location, diminishing misclassification errors. The method selects an update set composed by a subset of points considered to be at the risk of being captured by another class prototype. We associate the proposed methodology to a weighted norm, instead of the Euclidean, in order to establish different levels of relevance for the input attributes. The technique was implemented on a controlled experiment and on Web available data sets.
Keywords :
learning (artificial intelligence); pattern classification; vector quantisation; data selection; learning vector quantization; pattern classification; weighted norm; Approximation algorithms; Clustering algorithms; Cost function; Data preprocessing; Neural networks; Pattern classification; Prototypes; Self organizing feature maps; Training data; Vector quantization; Index Terms- Learning vector quantization LVQ; clustering; data selection; neural networks.; pattern classification; Algorithms; Artificial Intelligence; Computer Simulation; Computing Methodologies; Models, Theoretical; Pattern Recognition, Automated; Systems Theory;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2006.14
Filename :
1542041
Link To Document :
بازگشت