OcrV1, Istex, Corpus, bibRecord, 003758

Can periodic perceptrons replace multi-layer perceptrons?

Identifieur interne : 003758 ( Istex/Corpus ); précédent : 003757; suivant : 003759

Can periodic perceptrons replace multi-layer perceptrons?

Source :

Pattern Recognition Letters [ 0167-8655 ] ; 1998.

RBID : ISTEX:E89BCA8DAFA60821F125882C90A563B5CF44F362

Abstract

We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP and test it on academic and realistic problems.

Url:

https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/fulltext/pdf

DOI: 10.1016/S0167-8655(00)00057-X

Links to Exploration step

ISTEX:E89BCA8DAFA60821F125882C90A563B5CF44F362

Le document en format XML

<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Can periodic perceptrons replace multi-layer perceptrons?</title>
<author><name sortKey="Racca, Robert" sort="Racca, Robert" uniqKey="Racca R" first="Robert" last="Racca">Robert Racca</name>
<affiliation><mods:affiliation>Université des Antilles et de la Guyane, French West Indies, UFR Sciences Exactes & Naturelles, 97159 Pointe a Pitre Cedex, France</mods:affiliation>
</affiliation>
<affiliation><mods:affiliation>E-mail: robert.racca@univ-ag.fr</mods:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:E89BCA8DAFA60821F125882C90A563B5CF44F362</idno>
<date when="2000" year="2000">2000</date>
<idno type="doi">10.1016/S0167-8655(00)00057-X</idno>
<idno type="url">https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">003758</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Can periodic perceptrons replace multi-layer perceptrons?</title>
<author><name sortKey="Racca, Robert" sort="Racca, Robert" uniqKey="Racca R" first="Robert" last="Racca">Robert Racca</name>
<affiliation><mods:affiliation>Université des Antilles et de la Guyane, French West Indies, UFR Sciences Exactes & Naturelles, 97159 Pointe a Pitre Cedex, France</mods:affiliation>
</affiliation>
<affiliation><mods:affiliation>E-mail: robert.racca@univ-ag.fr</mods:affiliation>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Pattern Recognition Letters</title>
<title level="j" type="abbrev">PATREC</title>
<idno type="ISSN">0167-8655</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="1998">1998</date>
<biblScope unit="volume">21</biblScope>
<biblScope unit="issue">12</biblScope>
<biblScope unit="page" from="1019">1019</biblScope>
<biblScope unit="page" to="1025">1025</biblScope>
</imprint>
<idno type="ISSN">0167-8655</idno>
</series>
<idno type="istex">E89BCA8DAFA60821F125882C90A563B5CF44F362</idno>
<idno type="DOI">10.1016/S0167-8655(00)00057-X</idno>
<idno type="PII">S0167-8655(00)00057-X</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0167-8655</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP and test it on academic and realistic problems.</div>
</front>
</TEI>
<istex><corpusName>elsevier</corpusName>
<author><json:item><name>Robert Racca</name>
<affiliations><json:string>Université des Antilles et de la Guyane, French West Indies, UFR Sciences Exactes & Naturelles, 97159 Pointe a Pitre Cedex, France</json:string>
<json:string>E-mail: robert.racca@univ-ag.fr</json:string>
</affiliations>
</json:item>
</author>
<subject><json:item><lang><json:string>eng</json:string>
</lang>
<value>Multi-layer perceptron</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Periodic perceptron</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Learning algorithm</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Parity problem</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Character recognition</value>
</json:item>
<json:item><lang><json:string>eng</json:string>
</lang>
<value>Speech synthesis</value>
</json:item>
</subject>
<language><json:string>eng</json:string>
</language>
<abstract>We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP and test it on academic and realistic problems.</abstract>
<qualityIndicators><score>3.171</score>
<pdfVersion>1.2</pdfVersion>
<pdfPageSize>544 x 743 pts</pdfPageSize>
<refBibsNative>true</refBibsNative>
<keywordCount>6</keywordCount>
<abstractCharCount>264</abstractCharCount>
<pdfWordCount>2691</pdfWordCount>
<pdfCharCount>14411</pdfCharCount>
<pdfPageCount>7</pdfPageCount>
<abstractWordCount>40</abstractWordCount>
</qualityIndicators>
<title>Can periodic perceptrons replace multi-layer perceptrons?</title>
<pii><json:string>S0167-8655(00)00057-X</json:string>
</pii>
<genre><json:string>brief communication</json:string>
</genre>
<host><volume>21</volume>
<pii><json:string>S0167-8655(00)X0067-0</json:string>
</pii>
<pages><last>1025</last>
<first>1019</first>
</pages>
<issn><json:string>0167-8655</json:string>
</issn>
<issue>12</issue>
<genre><json:string>Journal</json:string>
</genre>
<language><json:string>unknown</json:string>
</language>
<title>Pattern Recognition Letters</title>
<publicationDate>2000</publicationDate>
</host>
<categories><wos><json:string>COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</json:string>
</wos>
</categories>
<publicationDate>1998</publicationDate>
<copyrightDate>2000</copyrightDate>
<doi><json:string>10.1016/S0167-8655(00)00057-X</json:string>
</doi>
<id>E89BCA8DAFA60821F125882C90A563B5CF44F362</id>
<fulltext><json:item><original>true</original>
<mimetype>application/pdf</mimetype>
<extension>pdf</extension>
<uri>https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/fulltext/pdf</uri>
</json:item>
<json:item><original>true</original>
<mimetype>text/plain</mimetype>
<extension>txt</extension>
<uri>https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/fulltext/txt</uri>
</json:item>
<json:item><original>false</original>
<mimetype>application/zip</mimetype>
<extension>zip</extension>
<uri>https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/fulltext/zip</uri>
</json:item>
<istex:fulltextTEI uri="https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/fulltext/tei"><teiHeader><fileDesc><titleStmt><title level="a">Can periodic perceptrons replace multi-layer perceptrons?</title>
</titleStmt>
<publicationStmt><authority>ISTEX</authority>
<publisher>ELSEVIER</publisher>
<availability><p>ELSEVIER</p>
</availability>
<date>2000</date>
</publicationStmt>
<notesStmt><note type="content">Fig. 1: Notations.</note>
<note type="content">Fig. 2: The crenel function.</note>
<note type="content">Fig. 3: The periodic perceptron PP1.</note>
<note type="content">Fig. 4: PP1 calculates XOR.</note>
<note type="content">Fig. 5: The activation function fγ.</note>
<note type="content">Fig. 6: The ranges of right values for Wi,3.</note>
<note type="content">Fig. 7: A (n, 2) periodic perceptron.</note>
<note type="content">Fig. 8: Two (n, 1) periodic perceptrons.</note>
<note type="content">Fig. 9: Learning the 16 bit parity problem.</note>
<note type="content">Fig. 10: Learning with an activation function of periodicity 3.</note>
<note type="content">Fig. 11: Characters with random distortion.</note>
<note type="content">Fig. 12: Compared performances of PP and MLP.</note>
</notesStmt>
<sourceDesc><biblStruct type="inbook"><analytic><title level="a">Can periodic perceptrons replace multi-layer perceptrons?</title>
<author><persName><forename type="first">Robert</forename>
<surname>Racca</surname>
</persName>
<email>robert.racca@univ-ag.fr</email>
<note type="biography">Tel.: +590-938-694; fax: +590-938-698</note>
<affiliation>Tel.: +590-938-694; fax: +590-938-698</affiliation>
<affiliation>Université des Antilles et de la Guyane, French West Indies, UFR Sciences Exactes & Naturelles, 97159 Pointe a Pitre Cedex, France</affiliation>
</author>
</analytic>
<monogr><title level="j">Pattern Recognition Letters</title>
<title level="j" type="abbrev">PATREC</title>
<idno type="pISSN">0167-8655</idno>
<idno type="PII">S0167-8655(00)X0067-0</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="1998"></date>
<biblScope unit="volume">21</biblScope>
<biblScope unit="issue">12</biblScope>
<biblScope unit="page" from="1019">1019</biblScope>
<biblScope unit="page" to="1025">1025</biblScope>
</imprint>
</monogr>
<idno type="istex">E89BCA8DAFA60821F125882C90A563B5CF44F362</idno>
<idno type="DOI">10.1016/S0167-8655(00)00057-X</idno>
<idno type="PII">S0167-8655(00)00057-X</idno>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><creation><date>2000</date>
</creation>
<langUsage><language ident="en">en</language>
</langUsage>
<abstract xml:lang="en"><p>We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP and test it on academic and realistic problems.</p>
</abstract>
<textClass><keywords scheme="keyword"><list><head>Keywords</head>
<item><term>Multi-layer perceptron</term>
</item>
<item><term>Periodic perceptron</term>
</item>
<item><term>Learning algorithm</term>
</item>
<item><term>Parity problem</term>
</item>
<item><term>Character recognition</term>
</item>
<item><term>Speech synthesis</term>
</item>
</list>
</keywords>
</textClass>
</profileDesc>
<revisionDesc><change when="1998-07-08">Received</change>
<change when="2000-04-20">Modified</change>
<change when="1998">Published</change>
</revisionDesc>
</teiHeader>
</istex:fulltextTEI>
</fulltext>
<metadata><istex:metadataXml wicri:clean="Elsevier, elements deleted: ce:floats; body; tail"><istex:xmlDeclaration>version="1.0" encoding="utf-8"</istex:xmlDeclaration>
<istex:docType PUBLIC="-//ES//DTD journal article DTD version 4.5.2//EN//XML" URI="art452.dtd" name="istex:docType"><istex:entity SYSTEM="gr1" NDATA="IMAGE" name="gr1"></istex:entity>
<istex:entity SYSTEM="gr2" NDATA="IMAGE" name="gr2"></istex:entity>
<istex:entity SYSTEM="gr3" NDATA="IMAGE" name="gr3"></istex:entity>
<istex:entity SYSTEM="gr4" NDATA="IMAGE" name="gr4"></istex:entity>
<istex:entity SYSTEM="gr5" NDATA="IMAGE" name="gr5"></istex:entity>
<istex:entity SYSTEM="gr6" NDATA="IMAGE" name="gr6"></istex:entity>
<istex:entity SYSTEM="gr7" NDATA="IMAGE" name="gr7"></istex:entity>
<istex:entity SYSTEM="gr8" NDATA="IMAGE" name="gr8"></istex:entity>
<istex:entity SYSTEM="gr9" NDATA="IMAGE" name="gr9"></istex:entity>
<istex:entity SYSTEM="gr10" NDATA="IMAGE" name="gr10"></istex:entity>
<istex:entity SYSTEM="gr11" NDATA="IMAGE" name="gr11"></istex:entity>
<istex:entity SYSTEM="gr12" NDATA="IMAGE" name="gr12"></istex:entity>
</istex:docType>
<istex:document><converted-article version="4.5.2" docsubtype="sco"><item-info><jid>PATREC</jid>
<aid>2639</aid>
<ce:pii>S0167-8655(00)00057-X</ce:pii>
<ce:doi>10.1016/S0167-8655(00)00057-X</ce:doi>
<ce:copyright type="full-transfer" year="2000">Elsevier Science B.V.</ce:copyright>
</item-info>
<head><ce:title>Can periodic perceptrons replace multi-layer perceptrons?</ce:title>
<ce:author-group><ce:author><ce:given-name>Robert</ce:given-name>
<ce:surname>Racca</ce:surname>
<ce:cross-ref refid="CORR1">*</ce:cross-ref>
<ce:e-address>robert.racca@univ-ag.fr</ce:e-address>
</ce:author>
<ce:affiliation><ce:textfn>Université des Antilles et de la Guyane, French West Indies, UFR Sciences Exactes & Naturelles, 97159 Pointe a Pitre Cedex, France</ce:textfn>
</ce:affiliation>
<ce:correspondence id="CORR1"><ce:label>*</ce:label>
<ce:text>Tel.: +590-938-694; fax: +590-938-698</ce:text>
</ce:correspondence>
</ce:author-group>
<ce:date-received day="8" month="7" year="1998"></ce:date-received>
<ce:date-revised day="20" month="4" year="2000"></ce:date-revised>
<ce:abstract><ce:section-title>Abstract</ce:section-title>
<ce:abstract-sec><ce:simple-para>We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP and test it on academic and realistic problems.</ce:simple-para>
</ce:abstract-sec>
</ce:abstract>
<ce:keywords class="keyword"><ce:section-title>Keywords</ce:section-title>
<ce:keyword><ce:text>Multi-layer perceptron</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Periodic perceptron</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Learning algorithm</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Parity problem</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Character recognition</ce:text>
</ce:keyword>
<ce:keyword><ce:text>Speech synthesis</ce:text>
</ce:keyword>
</ce:keywords>
</head>
</converted-article>
</istex:document>
</istex:metadataXml>
<mods version="3.6"><titleInfo><title>Can periodic perceptrons replace multi-layer perceptrons?</title>
</titleInfo>
<titleInfo type="alternative" contentType="CDATA"><title>Can periodic perceptrons replace multi-layer perceptrons?</title>
</titleInfo>
<name type="personal"><namePart type="given">Robert</namePart>
<namePart type="family">Racca</namePart>
<affiliation>Université des Antilles et de la Guyane, French West Indies, UFR Sciences Exactes & Naturelles, 97159 Pointe a Pitre Cedex, France</affiliation>
<affiliation>E-mail: robert.racca@univ-ag.fr</affiliation>
<description>Tel.: +590-938-694; fax: +590-938-698</description>
<role><roleTerm type="text">author</roleTerm>
</role>
</name>
<typeOfResource>text</typeOfResource>
<genre type="brief communication" displayLabel="Short communication"></genre>
<originInfo><publisher>ELSEVIER</publisher>
<dateIssued encoding="w3cdtf">1998</dateIssued>
<dateCaptured encoding="w3cdtf">1998-07-08</dateCaptured>
<dateModified encoding="w3cdtf">2000-04-20</dateModified>
<copyrightDate encoding="w3cdtf">2000</copyrightDate>
</originInfo>
<language><languageTerm type="code" authority="iso639-2b">eng</languageTerm>
<languageTerm type="code" authority="rfc3066">en</languageTerm>
</language>
<physicalDescription><internetMediaType>text/html</internetMediaType>
</physicalDescription>
<abstract lang="en">We propose an efficient alternative to multi-layer perceptron (MLP): two-layer periodic perceptron (PP). We prove then that PP can compute every binary boolean function, we give an efficient learning algorithm for PP and test it on academic and realistic problems.</abstract>
<note type="content">Fig. 1: Notations.</note>
<note type="content">Fig. 2: The crenel function.</note>
<note type="content">Fig. 3: The periodic perceptron PP1.</note>
<note type="content">Fig. 4: PP1 calculates XOR.</note>
<note type="content">Fig. 5: The activation function fγ.</note>
<note type="content">Fig. 6: The ranges of right values for Wi,3.</note>
<note type="content">Fig. 7: A (n, 2) periodic perceptron.</note>
<note type="content">Fig. 8: Two (n, 1) periodic perceptrons.</note>
<note type="content">Fig. 9: Learning the 16 bit parity problem.</note>
<note type="content">Fig. 10: Learning with an activation function of periodicity 3.</note>
<note type="content">Fig. 11: Characters with random distortion.</note>
<note type="content">Fig. 12: Compared performances of PP and MLP.</note>
<subject><genre>Keywords</genre>
<topic>Multi-layer perceptron</topic>
<topic>Periodic perceptron</topic>
<topic>Learning algorithm</topic>
<topic>Parity problem</topic>
<topic>Character recognition</topic>
<topic>Speech synthesis</topic>
</subject>
<relatedItem type="host"><titleInfo><title>Pattern Recognition Letters</title>
</titleInfo>
<titleInfo type="abbreviated"><title>PATREC</title>
</titleInfo>
<genre type="Journal">journal</genre>
<originInfo><dateIssued encoding="w3cdtf">200011</dateIssued>
</originInfo>
<identifier type="ISSN">0167-8655</identifier>
<identifier type="PII">S0167-8655(00)X0067-0</identifier>
<part><date>200011</date>
<detail type="volume"><number>21</number>
<caption>vol.</caption>
</detail>
<detail type="issue"><number>12</number>
<caption>no.</caption>
</detail>
<extent unit="issue pages"><start>1019</start>
<end>1092</end>
</extent>
<extent unit="pages"><start>1019</start>
<end>1025</end>
</extent>
</part>
</relatedItem>
<identifier type="istex">E89BCA8DAFA60821F125882C90A563B5CF44F362</identifier>
<identifier type="DOI">10.1016/S0167-8655(00)00057-X</identifier>
<identifier type="PII">S0167-8655(00)00057-X</identifier>
<accessCondition type="use and reproduction" contentType="">© 2000Elsevier Science B.V.</accessCondition>
<recordInfo><recordContentSource>ELSEVIER</recordContentSource>
<recordOrigin>Elsevier Science B.V., ©2000</recordOrigin>
</recordInfo>
</mods>
</metadata>
<enrichments><istex:catWosTEI uri="https://api.istex.fr/document/E89BCA8DAFA60821F125882C90A563B5CF44F362/enrichments/catWos"><teiHeader><profileDesc><textClass><classCode scheme="WOS">COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE</classCode>
</textClass>
</profileDesc>
</teiHeader>
</istex:catWosTEI>
</enrichments>
<serie></serie>
</istex>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Corpus

HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 003758 | SxmlIndent | more

HfdSelect -h $EXPLOR_AREA/Data/Istex/Corpus/biblio.hfd -nk 003758 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    Istex
   |étape=   Corpus
   |type=    RBID
   |clé=     ISTEX:E89BCA8DAFA60821F125882C90A563B5CF44F362
   |texte=   Can periodic perceptrons replace multi-layer perceptrons?
}}

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024

	Serveur d'exploration sur l'OCR
	Attention, ce site est en cours de développement ! Attention, site généré par des moyens informatiques à partir de corpus bruts. Les informations ne sont donc pas validées.

Serveur d'exploration sur l'OCR

Can periodic perceptrons replace multi-layer perceptrons?

Can periodic perceptrons replace multi-layer perceptrons?

Source :

Abstract

Links to Exploration step

Le document en format XML

Pour manipuler ce document sous Unix (Dilib)

Pour mettre un lien sur cette page dans le réseau Wicri