TBU Publications
Repository of TBU Publications

Adaptive strategy for neural network synthesis constant estimation

DSpace Repository

Show simple item record


dc.title Adaptive strategy for neural network synthesis constant estimation en
dc.contributor.author Vařacha, Pavel
dc.relation.ispartof Annals of DAAAM and Proceedings of the International DAAAM Symposium
dc.identifier.issn 1726-9679 OCLC, Ulrich, Sherpa/RoMEO, JCR
dc.identifier.isbn 978-3-902734-07-5
dc.date.issued 2015
utb.relation.volume 2015-January
dc.citation.spage 358
dc.citation.epage 364
dc.event.title 26th DAAAM International Symposium on Intelligent Manufacturing and Automation, DAAAM 2015
dc.event.location Zadar
utb.event.state-en Croatia
utb.event.state-cs Chorvatsko
dc.event.sdate 2015-10-21
dc.event.edate 2015-10-24
dc.type conferenceObject
dc.language.iso en
dc.publisher Danube Adria Association for Automation and Manufacturing, DAAAM
dc.identifier.doi 10.2507/26th.daaam.proceedings.048
dc.relation.uri http://doi.org/10.2507/26th.daaam.proceedings.045
dc.subject Adaptive en
dc.subject Network en
dc.subject Neural en
dc.subject Optimization en
dc.subject Soma en
dc.subject Strategy en
dc.subject Structural en
dc.subject Synthesis en
dc.description.abstract Neural Network Synthesis is a new innovative method for an artificial neural network learning and structural optimization. It is based on two other already very successful algorithms: Analytic Programming and Self-Organizing Migration Algorithm (SOMA). The method already recorded several theoretical as well as industrial application to prove itself as a useful tool of modelling and simulation. This paper explores promising possibility to farther improve the method by application of an adaptive strategy for SOMA. The new idea of adaptive strategy is explained here and tested on a theoretical experimental case for the first time. Obtained data are statistically evaluated and ability of adaptive strategy to improve neural network synthesis is proved in conclusion. en
utb.faculty Faculty of Applied Informatics
dc.identifier.uri http://hdl.handle.net/10563/1006781
utb.identifier.obdid 43873994
utb.identifier.scopus 2-s2.0-84987677267
utb.source d-scopus
dc.date.accessioned 2016-12-22T16:19:11Z
dc.date.available 2016-12-22T16:19:11Z
utb.contributor.internalauthor Vařacha, Pavel
utb.fulltext.affiliation Pavel Vařacha Tomas Bata University in Zlín, Faculty of Applied Informatic, nám. T. G. Masaryka 5555, 760 01 Zlín, Czech Republic
utb.fulltext.dates -
utb.fulltext.sponsorship This work was supported by the Ministry of Education, Youth and Sports of the Czech Republic within the National Sustainability Programme project No. LO1303 (MSMT-7778/2014) and by the Technology Agency of the Czech Republic as a part of the project called TA03010724 AV and EV LED liminaire with a higher degree of protection.
Find Full text

Files in this item

Show simple item record