Neural network topology optimization
Identifieur interne : 006611 ( Main/Merge ); précédent : 006610; suivant : 006612Neural network topology optimization
Auteurs : Mohammed Attik [France] ; Laurent Bougrain [France] ; Frédéric Alexandre [France]Source :
- Lecture notes in computer science [ 0302-9743 ] ; 2005.
Descripteurs français
- Pascal (Inist)
- Wicri :
- topic : Intelligence artificielle, Classification.
English descriptors
- KwdEn :
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.
Links toward previous steps (curation, corpus...)
- to stream PascalFrancis, to step Corpus: 000482
- to stream PascalFrancis, to step Curation: 000551
- to stream PascalFrancis, to step Checkpoint: 000474
Links to Exploration step
Pascal:06-0067795Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">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"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
<settlement type="city" wicri:auto="agglo">Nancy</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>BRGM, 3 av Claude Guillemin - BP 6009</s1>
<s2>45060 Orléans</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
</author>
<author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
<settlement type="city" wicri:auto="agglo">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"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
<settlement type="city" wicri:auto="agglo">Nancy</settlement>
</placeName>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">06-0067795</idno>
<date when="2005">2005</date>
<idno type="stanalyst">PASCAL 06-0067795 INIST</idno>
<idno type="RBID">Pascal:06-0067795</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000482</idno>
<idno type="wicri:Area/PascalFrancis/Curation">000551</idno>
<idno type="wicri:Area/PascalFrancis/Checkpoint">000474</idno>
<idno type="wicri:explorRef" wicri:stream="PascalFrancis" wicri:step="Checkpoint">000474</idno>
<idno type="wicri:doubleKey">0302-9743:2005:Attik M:neural:network:topology</idno>
<idno type="wicri:Area/Main/Merge">006611</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">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"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
<settlement type="city" wicri:auto="agglo">Nancy</settlement>
</placeName>
</affiliation>
<affiliation wicri:level="3"><inist:fA14 i1="02"><s1>BRGM, 3 av Claude Guillemin - BP 6009</s1>
<s2>45060 Orléans</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
</author>
<author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation wicri:level="3"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
<settlement type="city" wicri:auto="agglo">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"><inist:fA14 i1="01"><s1>LORIA/INRIA-Lorraine, Campus Scientifique - BP 239</s1>
<s2>54506, Vandœuvre-lès-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
<sZ>2 aut.</sZ>
<sZ>3 aut.</sZ>
</inist:fA14>
<country>France</country>
<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>
<settlement type="city" wicri:auto="agglo">Nancy</settlement>
</placeName>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
<imprint><date when="2005">2005</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">Lecture notes in computer science</title>
<idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Artificial intelligence</term>
<term>Classification</term>
<term>Formal method</term>
<term>High performance</term>
<term>Learning algorithm</term>
<term>Network topology</term>
<term>Neural network</term>
<term>Optimal solution</term>
<term>Optimization</term>
<term>Optimization method</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Méthode formelle</term>
<term>Haute performance</term>
<term>Intelligence artificielle</term>
<term>Solution optimale</term>
<term>Classification</term>
<term>Topologie circuit</term>
<term>Réseau neuronal</term>
<term>Optimisation</term>
<term>Méthode optimisation</term>
<term>Algorithme apprentissage</term>
<term>.</term>
</keywords>
<keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Intelligence artificielle</term>
<term>Classification</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">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>
<affiliations><list><country><li>France</li>
</country>
<region><li>Centre-Val de Loire</li>
<li>Grand Est</li>
<li>Lorraine (région)</li>
<li>Région Centre</li>
</region>
<settlement><li>Nancy</li>
<li>Orléans</li>
<li>Vandœuvre-lès-Nancy</li>
</settlement>
</list>
<tree><country name="France"><region name="Grand Est"><name sortKey="Attik, Mohammed" sort="Attik, Mohammed" uniqKey="Attik M" first="Mohammed" last="Attik">Mohammed Attik</name>
</region>
<name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name>
<name sortKey="Attik, Mohammed" sort="Attik, Mohammed" uniqKey="Attik M" first="Mohammed" last="Attik">Mohammed Attik</name>
<name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
</country>
</tree>
</affiliations>
</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 006611 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 006611 | 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= Pascal:06-0067795 |texte= Neural network topology optimization }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |