Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks

For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths’ variable learning rate algorithm for improved performance of online sequential learning of feed-f...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Automatic control and computer sciences 2022-04, Vol.56 (2), p.160-165
1. Verfasser:	Bharath, Y. K.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial neural networks Computer Science Control Structures and Microprogramming Cross correlation Machine learning Neural networks Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

container_end_page	165
container_issue	2
container_start_page	160
container_title	Automatic control and computer sciences
container_volume	56
creator	Bharath, Y. K.
description	For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths’ variable learning rate algorithm for improved performance of online sequential learning of feed-forward neural networks used for chaotic time-series prediction. Here, the learning rate is varied based on Griffiths’ cross-correlation between input training data and squared error, which facilitates better tracking of time-series data.
doi_str_mv	10.3103/S0146411622020031
format	Article
fullrecord	<record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2666539819</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2666539819</sourcerecordid><originalsourceid>FETCH-LOGICAL-c246t-30c547b970a64be27dd35df14b26eaf695194f3336fda44b701056e5b814fa2a3</originalsourceid><addsrcrecordid>eNp1kM9Kw0AQhxdRsFYfwNuC5-j-b3IsxVahtGBVvIVNM1u3pkmdTSnefA1fzydxS4UexNMcvu83M_wIueTsWnImb2aMK6M4N0IwwZjkR6TDtU4TztKXY9LZ4WTHT8lZCEvGIktNh_gReud8-xq-P7_os0VviwroGCzWvl7QB9sCndaVr4HO4H0DdettdeD9atFgjK-oa5AOAcpk2ODWYkknsMGoTqDdNvgWzsmJs1WAi9_ZJU_D28fBXTKeju4H_XEyF8q0iWRzrXpF1mPWqAJEryylLh1XhTBgnck0z5STUhpXWqWKHuNMG9BFypWzwsouudrvXWMT_w1tvmw2WMeTuTDGaJmlPIsW31tzbEJAcPka_criR85Zvms0_9NozIh9JkS3XgAeNv8f-gHjeniS</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2666539819</pqid></control><display><type>article</type><title>Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks</title><source>SpringerNature Journals</source><creator>Bharath, Y. K.</creator><creatorcontrib>Bharath, Y. K.</creatorcontrib><description>For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths’ variable learning rate algorithm for improved performance of online sequential learning of feed-forward neural networks used for chaotic time-series prediction. Here, the learning rate is varied based on Griffiths’ cross-correlation between input training data and squared error, which facilitates better tracking of time-series data.</description><identifier>ISSN: 0146-4116</identifier><identifier>EISSN: 1558-108X</identifier><identifier>DOI: 10.3103/S0146411622020031</identifier><language>eng</language><publisher>Moscow: Pleiades Publishing</publisher><subject>Algorithms ; Artificial neural networks ; Computer Science ; Control Structures and Microprogramming ; Cross correlation ; Machine learning ; Neural networks ; Training</subject><ispartof>Automatic control and computer sciences, 2022-04, Vol.56 (2), p.160-165</ispartof><rights>Allerton Press, Inc. 2022. ISSN 0146-4116, Automatic Control and Computer Sciences, 2022, Vol. 56, No. 2, pp. 160–165. © Allerton Press, Inc., 2022.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c246t-30c547b970a64be27dd35df14b26eaf695194f3336fda44b701056e5b814fa2a3</citedby><cites>FETCH-LOGICAL-c246t-30c547b970a64be27dd35df14b26eaf695194f3336fda44b701056e5b814fa2a3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.3103/S0146411622020031$$EPDF$$P50$$Gspringer$$H</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.3103/S0146411622020031$$EHTML$$P50$$Gspringer$$H</linktohtml><link.rule.ids>314,780,784,27924,27925,41488,42557,51319</link.rule.ids></links><search><creatorcontrib>Bharath, Y. K.</creatorcontrib><title>Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks</title><title>Automatic control and computer sciences</title><addtitle>Aut. Control Comp. Sci</addtitle><description>For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths’ variable learning rate algorithm for improved performance of online sequential learning of feed-forward neural networks used for chaotic time-series prediction. Here, the learning rate is varied based on Griffiths’ cross-correlation between input training data and squared error, which facilitates better tracking of time-series data.</description><subject>Algorithms</subject><subject>Artificial neural networks</subject><subject>Computer Science</subject><subject>Control Structures and Microprogramming</subject><subject>Cross correlation</subject><subject>Machine learning</subject><subject>Neural networks</subject><subject>Training</subject><issn>0146-4116</issn><issn>1558-108X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><recordid>eNp1kM9Kw0AQhxdRsFYfwNuC5-j-b3IsxVahtGBVvIVNM1u3pkmdTSnefA1fzydxS4UexNMcvu83M_wIueTsWnImb2aMK6M4N0IwwZjkR6TDtU4TztKXY9LZ4WTHT8lZCEvGIktNh_gReud8-xq-P7_os0VviwroGCzWvl7QB9sCndaVr4HO4H0DdettdeD9atFgjK-oa5AOAcpk2ODWYkknsMGoTqDdNvgWzsmJs1WAi9_ZJU_D28fBXTKeju4H_XEyF8q0iWRzrXpF1mPWqAJEryylLh1XhTBgnck0z5STUhpXWqWKHuNMG9BFypWzwsouudrvXWMT_w1tvmw2WMeTuTDGaJmlPIsW31tzbEJAcPka_criR85Zvms0_9NozIh9JkS3XgAeNv8f-gHjeniS</recordid><startdate>20220401</startdate><enddate>20220401</enddate><creator>Bharath, Y. K.</creator><general>Pleiades Publishing</general><general>Springer Nature B.V</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20220401</creationdate><title>Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks</title><author>Bharath, Y. K.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c246t-30c547b970a64be27dd35df14b26eaf695194f3336fda44b701056e5b814fa2a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Algorithms</topic><topic>Artificial neural networks</topic><topic>Computer Science</topic><topic>Control Structures and Microprogramming</topic><topic>Cross correlation</topic><topic>Machine learning</topic><topic>Neural networks</topic><topic>Training</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Bharath, Y. K.</creatorcontrib><collection>CrossRef</collection><jtitle>Automatic control and computer sciences</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Bharath, Y. K.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks</atitle><jtitle>Automatic control and computer sciences</jtitle><stitle>Aut. Control Comp. Sci</stitle><date>2022-04-01</date><risdate>2022</risdate><volume>56</volume><issue>2</issue><spage>160</spage><epage>165</epage><pages>160-165</pages><issn>0146-4116</issn><eissn>1558-108X</eissn><abstract>For online sequential training of deep neural networks, where the training data set is chaotic in nature, it becomes quite challenging for choosing a proper learning rate. This paper presents Griffiths’ variable learning rate algorithm for improved performance of online sequential learning of feed-forward neural networks used for chaotic time-series prediction. Here, the learning rate is varied based on Griffiths’ cross-correlation between input training data and squared error, which facilitates better tracking of time-series data.</abstract><cop>Moscow</cop><pub>Pleiades Publishing</pub><doi>10.3103/S0146411622020031</doi><tpages>6</tpages></addata></record>
fulltext	fulltext
identifier	ISSN: 0146-4116
ispartof	Automatic control and computer sciences, 2022-04, Vol.56 (2), p.160-165
issn	0146-4116 1558-108X
language	eng
recordid	cdi_proquest_journals_2666539819
source	SpringerNature Journals
subjects	Algorithms Artificial neural networks Computer Science Control Structures and Microprogramming Cross correlation Machine learning Neural networks Training
title	Griffiths’ Variable Learning Rate Online Sequential Learning Algorithm for Feed-Forward Neural Networks
url	https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-19T15%3A57%3A46IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Griffiths%E2%80%99%20Variable%20Learning%20Rate%20Online%20Sequential%20Learning%20Algorithm%20for%20Feed-Forward%20Neural%20Networks&rft.jtitle=Automatic%20control%20and%20computer%20sciences&rft.au=Bharath,%20Y.%20K.&rft.date=2022-04-01&rft.volume=56&rft.issue=2&rft.spage=160&rft.epage=165&rft.pages=160-165&rft.issn=0146-4116&rft.eissn=1558-108X&rft_id=info:doi/10.3103/S0146411622020031&rft_dat=%3Cproquest_cross%3E2666539819%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2666539819&rft_id=info:pmid/&rfr_iscdi=true