A Parallel Incremental Learning Algorithm for Neural Networks with Fault Tolerance
Identifieur interne : 004432 ( Main/Exploration ); précédent : 004431; suivant : 004433A Parallel Incremental Learning Algorithm for Neural Networks with Fault Tolerance
Auteurs : Jacques M. Bahi [France] ; Sylvain Contassot-Vivier [France] ; Marc Sauget [France] ; Aurélien Vasseur [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ]
Abstract
Abstract: This paper presents a parallel and fault tolerant version of an incremental learning algorithm for feed-forward neural networks used as function approximators. It has been shown in previous works that our incremental algorithm builds networks of reduced size while providing high quality approximations for real data sets. However, for very large sets, the use of our learning process on a single machine may be quite long and even sometimes impossible, due to memory limitations. The parallel algorithm presented in this paper is usable in any parallel system, and in particular, with large dynamical systems such as clusters and grids in which faults may occur. Finally, the quality and performances (without and with faults) of that algorithm are experimentally evaluated.
Url:
DOI: 10.1007/978-3-540-92859-1_17
Affiliations:
- France
- Bourgogne-Franche-Comté, Franche-Comté, Grand Est, Lorraine (région)
- Belfort, Montbéliard, Nancy
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000302
- to stream Istex, to step Curation: 000301
- to stream Istex, to step Checkpoint: 000E60
- to stream Main, to step Merge: 004543
- to stream Main, to step Curation: 004432
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">A Parallel Incremental Learning Algorithm for Neural Networks with Fault Tolerance</title><author><name sortKey="Bahi, Jacques M" sort="Bahi, Jacques M" uniqKey="Bahi J" first="Jacques M." last="Bahi">Jacques M. Bahi</name></author><author><name sortKey="Contassot Vivier, Sylvain" sort="Contassot Vivier, Sylvain" uniqKey="Contassot Vivier S" first="Sylvain" last="Contassot-Vivier">Sylvain Contassot-Vivier</name></author><author><name sortKey="Sauget, Marc" sort="Sauget, Marc" uniqKey="Sauget M" first="Marc" last="Sauget">Marc Sauget</name></author><author><name sortKey="Vasseur, Aurelien" sort="Vasseur, Aurelien" uniqKey="Vasseur A" first="Aurélien" last="Vasseur">Aurélien Vasseur</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:0DD1B8B36535C0B99C70EB4948B6008F224D5915</idno><date when="2008" year="2008">2008</date><idno type="doi">10.1007/978-3-540-92859-1_17</idno><idno type="url">https://api.istex.fr/ark:/67375/HCB-1RLNV1LP-G/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">000302</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000302</idno><idno type="wicri:Area/Istex/Curation">000301</idno><idno type="wicri:Area/Istex/Checkpoint">000E60</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000E60</idno><idno type="wicri:doubleKey">0302-9743:2008:Bahi J:a:parallel:incremental</idno><idno type="wicri:Area/Main/Merge">004543</idno><idno type="wicri:Area/Main/Curation">004432</idno><idno type="wicri:Area/Main/Exploration">004432</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">A Parallel Incremental Learning Algorithm for Neural Networks with Fault Tolerance</title><author><name sortKey="Bahi, Jacques M" sort="Bahi, Jacques M" uniqKey="Bahi J" first="Jacques M." last="Bahi">Jacques M. Bahi</name><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>LIFC, University of Franche-Comté, Belfort</wicri:regionArea><placeName><region type="region">Bourgogne-Franche-Comté</region><region type="old region">Franche-Comté</region><settlement type="city">Belfort</settlement></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Contassot Vivier, Sylvain" sort="Contassot Vivier, Sylvain" uniqKey="Contassot Vivier S" first="Sylvain" last="Contassot-Vivier">Sylvain Contassot-Vivier</name><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>LORIA, University Henri Poincaré, Nancy</wicri:regionArea><placeName><region type="region">Grand Est</region><region type="old region">Lorraine (région)</region><settlement type="city">Nancy</settlement></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Sauget, Marc" sort="Sauget, Marc" uniqKey="Sauget M" first="Marc" last="Sauget">Marc Sauget</name><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>LIFC, University of Franche-Comté, Belfort</wicri:regionArea><placeName><region type="region">Bourgogne-Franche-Comté</region><region type="old region">Franche-Comté</region><settlement type="city">Belfort</settlement></placeName></affiliation><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>Femto-St, University of Franche-Comté, Montbéliard</wicri:regionArea><placeName><region type="region">Bourgogne-Franche-Comté</region><region type="old region">Franche-Comté</region><settlement type="city">Montbéliard</settlement></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Vasseur, Aurelien" sort="Vasseur, Aurelien" uniqKey="Vasseur A" first="Aurélien" last="Vasseur">Aurélien Vasseur</name><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>Femto-St, University of Franche-Comté, Montbéliard</wicri:regionArea><placeName><region type="region">Bourgogne-Franche-Comté</region><region type="old region">Franche-Comté</region><settlement type="city">Montbéliard</settlement></placeName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">France</country></affiliation></author></analytic><monogr></monogr><series><title level="s" type="main" xml:lang="en">Lecture Notes in Computer Science</title><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: This paper presents a parallel and fault tolerant version of an incremental learning algorithm for feed-forward neural networks used as function approximators. It has been shown in previous works that our incremental algorithm builds networks of reduced size while providing high quality approximations for real data sets. However, for very large sets, the use of our learning process on a single machine may be quite long and even sometimes impossible, due to memory limitations. The parallel algorithm presented in this paper is usable in any parallel system, and in particular, with large dynamical systems such as clusters and grids in which faults may occur. Finally, the quality and performances (without and with faults) of that algorithm are experimentally evaluated.</div></front></TEI><affiliations><list><country><li>France</li></country><region><li>Bourgogne-Franche-Comté</li><li>Franche-Comté</li><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Belfort</li><li>Montbéliard</li><li>Nancy</li></settlement></list><tree><country name="France"><region name="Bourgogne-Franche-Comté"><name sortKey="Bahi, Jacques M" sort="Bahi, Jacques M" uniqKey="Bahi J" first="Jacques M." last="Bahi">Jacques M. Bahi</name></region><name sortKey="Bahi, Jacques M" sort="Bahi, Jacques M" uniqKey="Bahi J" first="Jacques M." last="Bahi">Jacques M. Bahi</name><name sortKey="Contassot Vivier, Sylvain" sort="Contassot Vivier, Sylvain" uniqKey="Contassot Vivier S" first="Sylvain" last="Contassot-Vivier">Sylvain Contassot-Vivier</name><name sortKey="Contassot Vivier, Sylvain" sort="Contassot Vivier, Sylvain" uniqKey="Contassot Vivier S" first="Sylvain" last="Contassot-Vivier">Sylvain Contassot-Vivier</name><name sortKey="Sauget, Marc" sort="Sauget, Marc" uniqKey="Sauget M" first="Marc" last="Sauget">Marc Sauget</name><name sortKey="Sauget, Marc" sort="Sauget, Marc" uniqKey="Sauget M" first="Marc" last="Sauget">Marc Sauget</name><name sortKey="Sauget, Marc" sort="Sauget, Marc" uniqKey="Sauget M" first="Marc" last="Sauget">Marc Sauget</name><name sortKey="Vasseur, Aurelien" sort="Vasseur, Aurelien" uniqKey="Vasseur A" first="Aurélien" last="Vasseur">Aurélien Vasseur</name><name sortKey="Vasseur, Aurelien" sort="Vasseur, Aurelien" uniqKey="Vasseur A" first="Aurélien" last="Vasseur">Aurélien Vasseur</name></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 004432 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 004432 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:0DD1B8B36535C0B99C70EB4948B6008F224D5915
|texte= A Parallel Incremental Learning Algorithm for Neural Networks with Fault Tolerance
}}
| This area was generated with Dilib version V0.6.33. |  |