Analysis of Recurrent Analog Neural Networks

Simple item page
dc.contributor.authorTobes, Z.
dc.contributor.authorRaida, Zbyněk
dc.coverage.issue2cs
dc.coverage.volume7cs
dc.date.accessioned2016-05-05T10:58:10Z
dc.date.available2016-05-05T10:58:10Z
dc.date.issued1998-06cs
dc.description.abstractIn this paper, an original rigorous analysis of recurrent analog neural networks, which are built from opamp neurons, is presented. The analysis, which comes from the approximate model of the operational amplifier, reveals causes of possible non-stable states and enables to determine convergence properties of the network. Results of the analysis are discussed in order to enable development of original robust and fast analog networks. In the analysis, the special attention is turned to the examination of the influence of real circuit elements and of the statistical parameters of processed signals to the parameters of the network.en
dc.formattextcs
dc.format.extent9-14cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationRadioengineering. 1998, vol. 7, č. 2, s. 9-14. ISSN 1210-2512cs
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/58333
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttp://www.radioeng.cz/fulltexts/1998/98_02_02.pdfcs
dc.rightsCreative Commons Attribution 3.0 Unported Licenseen
dc.rights.accessopenAccessen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/en
dc.subjectanalog recurrent networksen
dc.subjectconvergence propertiesen
dc.subjectstabilityen
dc.subjectmodelling of operational amplifiersen
dc.titleAnalysis of Recurrent Analog Neural Networksen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
98_02_02.pdf
Size:
534.04 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
1998/2