Synthesis of cascade recurrent neural networks using feedforward generalization properties
Identifieur interne : 002090 ( Main/Exploration ); précédent : 002089; suivant : 002091Synthesis of cascade recurrent neural networks using feedforward generalization properties
Auteurs : Khaled M. Shaaban [Égypte] ; Robert J. Schalkoff [États-Unis]Source :
- Information Sciences [ 0020-0255 ] ; 1997.
Abstract
This paper presents a new analysis and synthesis technique for a class of recurrent networks known as a Cascade Recurrent Network (CRN). In this technique, a feedforward (FF) sub-network is used with synchronous feedback to implement associative memory (AM). FF network mapping properties are shown to determine CRN stability, and, on the basis of this stability-mapping relation, a new synthesis technique is given. This technique utilizes the optimization of the FF mapping sub-network generalization as a synthesis procedure for CRN. Sample results are shown.
Url:
DOI: 10.1016/S0020-0255(97)10060-3
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002121
- to stream Istex, to step Curation: 001F79
- to stream Istex, to step Checkpoint: 001594
- to stream Main, to step Merge: 002207
- to stream Main, to step Curation: 002090
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title>Synthesis of cascade recurrent neural networks using feedforward generalization properties</title>
<author><name sortKey="Shaaban, Khaled M" sort="Shaaban, Khaled M" uniqKey="Shaaban K" first="Khaled M." last="Shaaban">Khaled M. Shaaban</name>
</author>
<author><name sortKey="Schalkoff, Robert J" sort="Schalkoff, Robert J" uniqKey="Schalkoff R" first="Robert J." last="Schalkoff">Robert J. Schalkoff</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:BFAE1DF399340EDFB8610D970827175BE905A490</idno>
<date when="1998" year="1998">1998</date>
<idno type="doi">10.1016/S0020-0255(97)10060-3</idno>
<idno type="url">https://api.istex.fr/document/BFAE1DF399340EDFB8610D970827175BE905A490/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002121</idno>
<idno type="wicri:Area/Istex/Curation">001F79</idno>
<idno type="wicri:Area/Istex/Checkpoint">001594</idno>
<idno type="wicri:doubleKey">0020-0255:1998:Shaaban K:synthesis:of:cascade</idno>
<idno type="wicri:Area/Main/Merge">002207</idno>
<idno type="wicri:Area/Main/Curation">002090</idno>
<idno type="wicri:Area/Main/Exploration">002090</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a">Synthesis of cascade recurrent neural networks using feedforward generalization properties</title>
<author><name sortKey="Shaaban, Khaled M" sort="Shaaban, Khaled M" uniqKey="Shaaban K" first="Khaled M." last="Shaaban">Khaled M. Shaaban</name>
<affiliation wicri:level="1"><country xml:lang="fr">Égypte</country>
<wicri:regionArea>Electrical and Computer Engineering, Assiut University,Asssiut</wicri:regionArea>
<wicri:noRegion>Asssiut</wicri:noRegion>
</affiliation>
</author>
<author><name sortKey="Schalkoff, Robert J" sort="Schalkoff, Robert J" uniqKey="Schalkoff R" first="Robert J." last="Schalkoff">Robert J. Schalkoff</name>
<affiliation><wicri:noCountry code="no comma">Corresponding author. Tel.: +1 864 656 5913; fax: +1 864 656 7220.</wicri:noCountry>
</affiliation>
<affiliation wicri:level="2"><country xml:lang="fr">États-Unis</country>
<wicri:regionArea>Electrical and Computer Engineering, Clemson University, Clemson, SC 29634-0915</wicri:regionArea>
<placeName><region type="state">Caroline du Sud</region>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">États-Unis</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series><title level="j">Information Sciences</title>
<title level="j" type="abbrev">INS</title>
<idno type="ISSN">0020-0255</idno>
<imprint><publisher>ELSEVIER</publisher>
<date type="published" when="1997">1997</date>
<biblScope unit="volume">108</biblScope>
<biblScope unit="issue">1–4</biblScope>
<biblScope unit="page" from="207">207</biblScope>
<biblScope unit="page" to="217">217</biblScope>
</imprint>
<idno type="ISSN">0020-0255</idno>
</series>
<idno type="istex">BFAE1DF399340EDFB8610D970827175BE905A490</idno>
<idno type="DOI">10.1016/S0020-0255(97)10060-3</idno>
<idno type="PII">S0020-0255(97)10060-3</idno>
</biblStruct>
</sourceDesc>
<seriesStmt><idno type="ISSN">0020-0255</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass></textClass>
<langUsage><language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">This paper presents a new analysis and synthesis technique for a class of recurrent networks known as a Cascade Recurrent Network (CRN). In this technique, a feedforward (FF) sub-network is used with synchronous feedback to implement associative memory (AM). FF network mapping properties are shown to determine CRN stability, and, on the basis of this stability-mapping relation, a new synthesis technique is given. This technique utilizes the optimization of the FF mapping sub-network generalization as a synthesis procedure for CRN. Sample results are shown.</div>
</front>
</TEI>
<affiliations><list><country><li>Égypte</li>
<li>États-Unis</li>
</country>
<region><li>Caroline du Sud</li>
</region>
</list>
<tree><country name="Égypte"><noRegion><name sortKey="Shaaban, Khaled M" sort="Shaaban, Khaled M" uniqKey="Shaaban K" first="Khaled M." last="Shaaban">Khaled M. Shaaban</name>
</noRegion>
</country>
<country name="États-Unis"><region name="Caroline du Sud"><name sortKey="Schalkoff, Robert J" sort="Schalkoff, Robert J" uniqKey="Schalkoff R" first="Robert J." last="Schalkoff">Robert J. Schalkoff</name>
</region>
<name sortKey="Schalkoff, Robert J" sort="Schalkoff, Robert J" uniqKey="Schalkoff R" first="Robert J." last="Schalkoff">Robert J. Schalkoff</name>
</country>
</tree>
</affiliations>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 002090 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 002090 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Ticri/CIDE |area= OcrV1 |flux= Main |étape= Exploration |type= RBID |clé= ISTEX:BFAE1DF399340EDFB8610D970827175BE905A490 |texte= Synthesis of cascade recurrent neural networks using feedforward generalization properties }}
This area was generated with Dilib version V0.6.32. |