图书馆订阅: Guest
Begell Digital Portal Begell 数字图书馆 电子图书 期刊 参考文献及会议录 研究收集
自动化与信息科学期刊
SJR: 0.275 SNIP: 0.59 CiteScore™: 0.8

ISSN 打印: 1064-2315
ISSN 在线: 2163-9337

卷:
卷 52, 2020 卷 51, 2019 卷 50, 2018 卷 49, 2017 卷 48, 2016 卷 47, 2015 卷 46, 2014 卷 45, 2013 卷 44, 2012 卷 43, 2011 卷 42, 2010 卷 41, 2009 卷 40, 2008 卷 39, 2007 卷 38, 2006 卷 37, 2005 卷 36, 2004 卷 35, 2003 卷 34, 2002 卷 33, 2001 卷 32, 2000 卷 31, 1999 卷 30, 1998 卷 29, 1997 卷 28, 1996

自动化与信息科学期刊

DOI: 10.1615/J Automat Inf Scien.v38.i11.60
pages 56-73

Complexity of Bayesian Procedure of Inductive Inference. Discrete Case

Boris A. Beletskiy
V.M. Glushkov Institute of Cybernetics of National Academy of Sciences of Ukraine, Kiev, Ukraine
Alexandra A. Vagis
V.M. Glushkov Institute of Cybernetics of National Academy of Sciences of Ukraine, Kiev, Ukraine
Sergey V. Vasilyev
V.M. Glushkov Institute of Cybernetics of National Academy of Sciences of Ukraine, Kiev, Ukraine
Nikita A. Gupal
V.M. Glushkov Institute of Cybernetics of National Academy of Sciences of Ukraine, Kiev

ABSTRACT

Behavior of inductive procedures depending on content of learning sampling is studied. We demonstrate, that if the learning sampling contains no information about some class of objects or statistical information about a priori probabilities of classes, then any procedure works badly and its error is strictly positive. An estimate of error of Bayesian recognition procedure depending on size of learning sampling and other parameters is derived. Suboptimality of Bayesian approach is proved, complexity of class of problems is assessed.


Articles with similar content:

Comparison of Data Mining Methods while Credit Rating of Natural Persons
Journal of Automation and Information Sciences, Vol.41, 2009, issue 10
Alexander N. Terentyev, Nikolay Yu. Medin, Petr I. Bidyuk, Alexandra V. Mironova
MARGINALIZATION OF UNINTERESTING DISTRIBUTED PARAMETERS IN INVERSE PROBLEMS-APPLICATION TO DIFFUSE OPTICAL TOMOGRAPHY
International Journal for Uncertainty Quantification, Vol.1, 2011, issue 1
Ville Kolehmainen, Jari P. Kaipio, Simon R. Arridge, Tanja Tarvainen
Study of Efficiency of Fuzzy GMDH with Different Forms of Partial Descriptions and Adaptation Algorithms in Prognosis Problems
Journal of Automation and Information Sciences, Vol.40, 2008, issue 4
Yuriy P. Zaychenko, Igor O. Zayets
Estimation of Experimental Distribution Function on the Basis of Finite Samples of Random Variable
Journal of Automation and Information Sciences, Vol.51, 2019, issue 12
Bogdan P. Rusyn, Igor M. Romanyshyn, Andrey B. Lozynsky
BLIND ESTIMATION OF NOISE VARIANCE FOR 1D SIGNAL DENOISING
Telecommunications and Radio Engineering, Vol.79, 2020, issue 7
A. Kharkov, V. V. Lukin, V. Oliinyk, S. S. Krivenko