BulDML at Institute of Mathematics and Informatics >
International Journal ITA >
2006 >
Volume 13 Number 3 >

Please use this identifier to cite or link to this item:

Title: Evaluating Misclassification Probability Using Empirical Risk
Authors: Nedel’ko, Victor
Keywords: Pattern Recognition
Statistical Robustness
Deciding Functions
Overtraining Problem
Issue Date: 2006
Publisher: Institute of Information Theories and Applications FOI ITHEA
Abstract: The goal of the paper is to estimate misclassification probability for decision function by training sample. Here are presented results of investigation an empirical risk bias for nearest neighbours, linear and decision tree classifier in comparison with exact bias estimations for a discrete (multinomial) case. This allows to find out how far Vapnik–Chervonenkis risk estimations are off for considered decision function classes and to choose optimal complexity parameters for constructed decision functions. Comparison of linear classifier and decision trees capacities is also performed.
Description: * The work is supported by RFBR, grant 04-01-00858-a
ISSN: 1313-0463
Appears in Collections:Volume 13 Number 3

Files in This Item:

File Description SizeFormat
ijita13-3-p15.pdf140 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License