Number of the records: 1
GMDH Method with Genetic Selection Algorithm and Cloning
- 1.
SYSNO ASEP 0421992 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title GMDH Method with Genetic Selection Algorithm and Cloning Author(s) Jiřina, Marcel (UIVT-O) SAI, RID
Jiřina jr., M. (CZ)Source Title Neural Network World. - : Ústav informatiky AV ČR, v. v. i. - ISSN 1210-0552
Roč. 23, č. 5 (2013), s. 451-464Number of pages 14 s. Language eng - English Country CZ - Czech Republic Keywords multivariate data ; GMDH ; linear regression ; Gauss-Markov conditions ; cloning ; genetic selection ; classification Subject RIV BB - Applied Statistics, Operational Research Institutional support UIVT-O - RVO:67985807 UT WOS 000328097600005 EID SCOPUS 84894545707 DOI https://doi.org/10.14311/NNW.2013.23.028 Annotation The GMDH MIA algorithm uses linear regression for adaptation. We show that Gauss-Markov conditions are not met here and thus estimations of network parameters are biased. To eliminate this we propose to use cloning of neuron parameters in the GMDH network with genetic selection and cloning (GMC GMDH) that can outperform other powerful methods. It is demonstrated on tasks from the Machine Learning Repository. Workplace Institute of Computer Science Contact Tereza Šírová, sirova@cs.cas.cz, Tel.: 266 053 800 Year of Publishing 2014
Number of the records: 1