Neural Network Topology Optimization
Identifieur interne : 006449 ( Main/Merge ); précédent : 006448; suivant : 006450Neural Network Topology Optimization
Auteurs : Mohammed Attik [France] ; Laurent Bougrain [France] ; Frédéric Alexandre [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ]
Abstract
Abstract: The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.
Url:
DOI: 10.1007/11550907_9
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 002412
- to stream Istex, to step Curation: 002381
- to stream Istex, to step Checkpoint: 001538
Links to Exploration step
ISTEX:9AD648B29476335EFDC14C71DE156BE83B98B4A4Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Neural Network Topology Optimization</title>
<author><name sortKey="Attik, Mohammed" sort="Attik, Mohammed" uniqKey="Attik M" first="Mohammed" last="Attik">Mohammed Attik</name>
</author>
<author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
</author>
<author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:9AD648B29476335EFDC14C71DE156BE83B98B4A4</idno>
<date when="2005" year="2005">2005</date>
<idno type="doi">10.1007/11550907_9</idno>
<idno type="url">https://api.istex.fr/ark:/67375/HCB-GB7X9CCC-N/fulltext.pdf</idno>
<idno type="wicri:Area/Istex/Corpus">002412</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">002412</idno>
<idno type="wicri:Area/Istex/Curation">002381</idno>
<idno type="wicri:Area/Istex/Checkpoint">001538</idno>
<idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">001538</idno>
<idno type="wicri:doubleKey">0302-9743:2005:Attik M:neural:network:topology</idno>
<idno type="wicri:Area/Main/Merge">006449</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Neural Network Topology Optimization</title>
<author><name sortKey="Attik, Mohammed" sort="Attik, Mohammed" uniqKey="Attik M" first="Mohammed" last="Attik">Mohammed Attik</name>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>LORIA/INRIA-Lorraine, Campus Scientifique, BP 239, 54506, Vandœuvre-lès-Nancy Cedex</wicri:regionArea>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>BRGM, 3 av Claude Guillemin, BP 6009, 45060, Orléans Cedex 2</wicri:regionArea>
<placeName><region type="region" nuts="2">Centre-Val de Loire</region>
<region type="old region" nuts="2">Région Centre</region>
<settlement type="city">Orléans</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="1"><country wicri:rule="url">France</country>
</affiliation>
</author>
<author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>LORIA/INRIA-Lorraine, Campus Scientifique, BP 239, 54506, Vandœuvre-lès-Nancy Cedex</wicri:regionArea>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
</affiliation>
</author>
<author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name>
<affiliation wicri:level="3"><country xml:lang="fr">France</country>
<wicri:regionArea>LORIA/INRIA-Lorraine, Campus Scientifique, BP 239, 54506, Vandœuvre-lès-Nancy Cedex</wicri:regionArea>
<placeName><region type="region" nuts="2">Grand Est</region>
<region type="old region" nuts="2">Lorraine (région)</region>
<settlement type="city">Vandœuvre-lès-Nancy</settlement>
</placeName>
</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: The determination of the optimal architecture of a supervised neural network is an important and a difficult task. The classical neural network topology optimization methods select weight(s) or unit(s) from the architecture in order to give a high performance of a learning algorithm. However, all existing topology optimization methods do not guarantee to obtain the optimal solution. In this work, we propose a hybrid approach which combines variable selection method and classical optimization method in order to improve optimization topology solution. The proposed approach suggests to identify the relevant subset of variables which gives a good classification performance in the first step and then to apply a classical topology optimization method to eliminate unnecessary hidden units or weights. A comparison of our approach to classical techniques for architecture optimization is given.</div>
</front>
</TEI>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Merge
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 006449 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 006449 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Main |étape= Merge |type= RBID |clé= ISTEX:9AD648B29476335EFDC14C71DE156BE83B98B4A4 |texte= Neural Network Topology Optimization }}
This area was generated with Dilib version V0.6.33. |