Adaptive individual handling for neural network synthesis

Vařacha, Pavel

dc.title	Adaptive individual handling for neural network synthesis	en
dc.contributor.author	Vařacha, Pavel
dc.relation.ispartof	MATEC Web of Conferences 20th International Conference on Circuits, Systems, Communications and Computers (CSCC 2016)
dc.identifier.issn	2261-236X Scopus Sources, Sherpa/RoMEO, JCR
dc.date.issued	2016
utb.relation.volume	76
dc.event.title	20th International Conference on Circuits, Systems, Communications and Computers (CSCC)
dc.event.location	Corfu
utb.event.state-en	Greece
utb.event.state-cs	Řecko
dc.event.sdate	2016-07-14
dc.event.edate	2016-07-17
dc.type	conferenceObject
dc.language.iso	en
dc.publisher	EDP Sciences
dc.identifier.doi	10.1051/matecconf/20167604035
dc.relation.uri	https://www.matec-conferences.org/articles/matecconf/abs/2016/39/matecconf_cscc2016_04035/matecconf_cscc2016_04035.html
dc.subject	neural	en
dc.subject	network	en
dc.subject	synthesys	en
dc.subject	SOMA	en
dc.subject	adaptive	en
dc.subject	strategy	en
dc.subject	structural	en
dc.subject	optimization	en
dc.description.abstract	Neural Network Synthesis is an algorithm capable of creating and learning and artificial neural networks as well as optimizing their structures and connections. The method is based on Analytic Programming and asynchronous implementation of Self-Organising Migration Algorithm. Such approach already recorded several successful application considering practical casers of modelling and simulation. This results vindicate efforts for its further development. This paper explores a possibility to make it more effective by adaptive individual handling. The main idea is an intelligent control the process based on complexity of processed neural network structure. (C) 2016 The Authors. Published by Elsevier Ltd.	en
utb.faculty	Faculty of Applied Informatics
dc.identifier.uri	http://hdl.handle.net/10563/1007019
utb.identifier.obdid	43876393
utb.identifier.scopus	2-s2.0-85016123006
utb.identifier.wok	000392332200112
utb.source	d-wok
dc.date.accessioned	2017-07-25T08:54:46Z
dc.date.available	2017-07-25T08:54:46Z
dc.description.sponsorship	Ministry of Education, Youth and Sports of the Czech Republic within the National Sustainability Programme [LO1303 (MSMT-7778/2014)]
dc.rights	Attribution 4.0 International
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/
dc.rights.access	openAccess
utb.contributor.internalauthor	Vařacha, Pavel
utb.fulltext.affiliation	Pavel Vařacha 1,a 1 Tomas Bata University in Zlín, Faculty of Applied Informatic, nám. T. G. Masaryka 5555 760 01 Zlín, Czech Republic a Corresponding author: [email protected]
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).