Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks

A major problem encountered by researchers of dynamic neural networks is the computational complexity increasing the learning time. In this paper the parallel realization of the RTRN and the Elman networks are discussed. Both networks are examples of dynamic neural networks. Inherent parallelism of...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on parallel and distributed systems 2015-09, Vol.26 (9), p.2561-2570
Hauptverfasser:	Bilski, Jarosław, Smolag, Jacek
Format:	Artikel
Sprache:	eng
Schlagworte:	Architecture Biological neural networks Computer architecture Dynamics Hardware Heuristic algorithms Learning Mathematical analysis Networks Neural networks Neurons Parallel processing Three dimensional Vectors
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	2570
container_issue	9
container_start_page	2561
container_title	IEEE transactions on parallel and distributed systems
container_volume	26
creator	Bilski, Jarosław Smolag, Jacek
description	A major problem encountered by researchers of dynamic neural networks is the computational complexity increasing the learning time. In this paper the parallel realization of the RTRN and the Elman networks are discussed. Both networks are examples of dynamic neural networks. Inherent parallelism of dynamic neural networks has been employed to accelerate the learning process. The proposed solution is based on a highly parallel three dimensional architecture to speed up the learning performance. The presented structures are suitable for efficient parallel realization in digital hardware or vector processors.
doi_str_mv	10.1109/TPDS.2014.2357019
format	Article
fullrecord	<record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_1702773885</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6898879</ieee_id><sourcerecordid>1793279121</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-586fb98d7f5601081be5266b38d35cdca8a424e242bfe542cc49ba9c1382d3873</originalsourceid><addsrcrecordid>eNpdkMtOwzAQRSMEEqXwAYiNJTZsUvxM7GXVlodUlaqUteU4E5qSR7ETof49rlqxYHVnce7M6ETRLcEjQrB6XC-n7yOKCR9RJlJM1Fk0IELImBLJzsOMuYgVJeoyuvJ-iwMpMB9Ei6VxpqqgQmNnN2UHtusdeFS0Ds3BuKZsPlG3AbRarxbINDmaVbVp0HTfmLq0aAF96Ifoflr35a-ji8JUHm5OOYw-nmbryUs8f3t-nYznsWU06WIhkyJTMk8LkWCCJclA0CTJmMyZsLk10nDKgXKaFSA4tZarzChLmKQ5kykbRg_HvTvXfvfgO12X3kJVmQba3muSKkZTRSgJ6P0_dNv2rgnfBQrTNGVSikCRI2Vd672DQu9cWRu31wTrg2F9MKwPhvXJcOjcHTslAPzxiVRShvO_cap1rw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1702773885</pqid></control><display><type>article</type><title>Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks</title><source>IEEE Electronic Library (IEL)</source><creator>Bilski, Jarosław ; Smolag, Jacek</creator><creatorcontrib>Bilski, Jarosław ; Smolag, Jacek</creatorcontrib><description>A major problem encountered by researchers of dynamic neural networks is the computational complexity increasing the learning time. In this paper the parallel realization of the RTRN and the Elman networks are discussed. Both networks are examples of dynamic neural networks. Inherent parallelism of dynamic neural networks has been employed to accelerate the learning process. The proposed solution is based on a highly parallel three dimensional architecture to speed up the learning performance. The presented structures are suitable for efficient parallel realization in digital hardware or vector processors.</description><identifier>ISSN: 1045-9219</identifier><identifier>EISSN: 1558-2183</identifier><identifier>DOI: 10.1109/TPDS.2014.2357019</identifier><identifier>CODEN: ITDSEO</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Architecture ; Biological neural networks ; Computer architecture ; Dynamics ; Hardware ; Heuristic algorithms ; Learning ; Mathematical analysis ; Networks ; Neural networks ; Neurons ; Parallel processing ; Three dimensional ; Vectors</subject><ispartof>IEEE transactions on parallel and distributed systems, 2015-09, Vol.26 (9), p.2561-2570</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2015</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c326t-586fb98d7f5601081be5266b38d35cdca8a424e242bfe542cc49ba9c1382d3873</citedby><cites>FETCH-LOGICAL-c326t-586fb98d7f5601081be5266b38d35cdca8a424e242bfe542cc49ba9c1382d3873</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6898879$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6898879$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Bilski, Jarosław</creatorcontrib><creatorcontrib>Smolag, Jacek</creatorcontrib><title>Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks</title><title>IEEE transactions on parallel and distributed systems</title><addtitle>TPDS</addtitle><description>A major problem encountered by researchers of dynamic neural networks is the computational complexity increasing the learning time. In this paper the parallel realization of the RTRN and the Elman networks are discussed. Both networks are examples of dynamic neural networks. Inherent parallelism of dynamic neural networks has been employed to accelerate the learning process. The proposed solution is based on a highly parallel three dimensional architecture to speed up the learning performance. The presented structures are suitable for efficient parallel realization in digital hardware or vector processors.</description><subject>Architecture</subject><subject>Biological neural networks</subject><subject>Computer architecture</subject><subject>Dynamics</subject><subject>Hardware</subject><subject>Heuristic algorithms</subject><subject>Learning</subject><subject>Mathematical analysis</subject><subject>Networks</subject><subject>Neural networks</subject><subject>Neurons</subject><subject>Parallel processing</subject><subject>Three dimensional</subject><subject>Vectors</subject><issn>1045-9219</issn><issn>1558-2183</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2015</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNpdkMtOwzAQRSMEEqXwAYiNJTZsUvxM7GXVlodUlaqUteU4E5qSR7ETof49rlqxYHVnce7M6ETRLcEjQrB6XC-n7yOKCR9RJlJM1Fk0IELImBLJzsOMuYgVJeoyuvJ-iwMpMB9Ei6VxpqqgQmNnN2UHtusdeFS0Ds3BuKZsPlG3AbRarxbINDmaVbVp0HTfmLq0aAF96Ifoflr35a-ji8JUHm5OOYw-nmbryUs8f3t-nYznsWU06WIhkyJTMk8LkWCCJclA0CTJmMyZsLk10nDKgXKaFSA4tZarzChLmKQ5kykbRg_HvTvXfvfgO12X3kJVmQba3muSKkZTRSgJ6P0_dNv2rgnfBQrTNGVSikCRI2Vd672DQu9cWRu31wTrg2F9MKwPhvXJcOjcHTslAPzxiVRShvO_cap1rw</recordid><startdate>20150901</startdate><enddate>20150901</enddate><creator>Bilski, Jarosław</creator><creator>Smolag, Jacek</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20150901</creationdate><title>Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks</title><author>Bilski, Jarosław ; Smolag, Jacek</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-586fb98d7f5601081be5266b38d35cdca8a424e242bfe542cc49ba9c1382d3873</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2015</creationdate><topic>Architecture</topic><topic>Biological neural networks</topic><topic>Computer architecture</topic><topic>Dynamics</topic><topic>Hardware</topic><topic>Heuristic algorithms</topic><topic>Learning</topic><topic>Mathematical analysis</topic><topic>Networks</topic><topic>Neural networks</topic><topic>Neurons</topic><topic>Parallel processing</topic><topic>Three dimensional</topic><topic>Vectors</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bilski, Jarosław</creatorcontrib><creatorcontrib>Smolag, Jacek</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on parallel and distributed systems</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Bilski, Jarosław</au><au>Smolag, Jacek</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks</atitle><jtitle>IEEE transactions on parallel and distributed systems</jtitle><stitle>TPDS</stitle><date>2015-09-01</date><risdate>2015</risdate><volume>26</volume><issue>9</issue><spage>2561</spage><epage>2570</epage><pages>2561-2570</pages><issn>1045-9219</issn><eissn>1558-2183</eissn><coden>ITDSEO</coden><abstract>A major problem encountered by researchers of dynamic neural networks is the computational complexity increasing the learning time. In this paper the parallel realization of the RTRN and the Elman networks are discussed. Both networks are examples of dynamic neural networks. Inherent parallelism of dynamic neural networks has been employed to accelerate the learning process. The proposed solution is based on a highly parallel three dimensional architecture to speed up the learning performance. The presented structures are suitable for efficient parallel realization in digital hardware or vector processors.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TPDS.2014.2357019</doi><tpages>10</tpages></addata></record>
fulltext	fulltext_linktorsrc
identifier	ISSN: 1045-9219
ispartof	IEEE transactions on parallel and distributed systems, 2015-09, Vol.26 (9), p.2561-2570
issn	1045-9219 1558-2183
language	eng
recordid	cdi_proquest_journals_1702773885
source	IEEE Electronic Library (IEL)
subjects	Architecture Biological neural networks Computer architecture Dynamics Hardware Heuristic algorithms Learning Mathematical analysis Networks Neural networks Neurons Parallel processing Three dimensional Vectors
title	Parallel Architectures for Learning the RTRN and Elman Dynamic Neural Networks
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-28T20%3A36%3A14IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Parallel%20Architectures%20for%20Learning%20the%20RTRN%20and%20Elman%20Dynamic%20Neural%20Networks&rft.jtitle=IEEE%20transactions%20on%20parallel%20and%20distributed%20systems&rft.au=Bilski,%20Jaros%C5%82aw&rft.date=2015-09-01&rft.volume=26&rft.issue=9&rft.spage=2561&rft.epage=2570&rft.pages=2561-2570&rft.issn=1045-9219&rft.eissn=1558-2183&rft.coden=ITDSEO&rft_id=info:doi/10.1109/TPDS.2014.2357019&rft_dat=%3Cproquest_RIE%3E1793279121%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=1702773885&rft_id=info:pmid/&rft_ieee_id=6898879&rfr_iscdi=true