A pruned higher-order network for knowledge extraction
Identifieur interne :
000726 ( PascalFrancis/Corpus );
précédent :
000725;
suivant :
000727
A pruned higher-order network for knowledge extraction
Auteurs : Laurent BougrainSource :
-
IEEE ... International Conference on Neural Networks [ 1098-7576 ] ; 2002.
RBID : Pascal:04-0132540
Descripteurs français
English descriptors
Abstract
Usually, the learning stage of a neural network leads to a single model. But a complex problem cannot always be solved adequately by a global system. On the other side, several systems specialized on a subspace have some difficulties to deal with situations located at the limit of two classes. This article presents a new adaptive architecture based upon higher-order computation to adjust a general model to each pattern and using a pruning algorithm to improve the generalization and extract knowledge. We use one small multi-layer perceptron to predict each weight of the model from the current pattern (we have one estimator per weight). This architecture introduces a higher-order computation, biologically inspired, similar to the modulation of a synapse between two neurons by a third neuron. The general model can then be smaller, more adaptative and more informative.
Notice en format standard (ISO 2709)
Pour connaître la documentation sur le format Inist Standard.
pA |
A01 | 01 | 1 | | @0 1098-7576 |
---|
A08 | 01 | 1 | ENG | @1 A pruned higher-order network for knowledge extraction |
---|
A09 | 01 | 1 | ENG | @1 IJCNN'02 : international joint conference on neural networks : Honolulu HI, 12-17 May 2002 |
---|
A11 | 01 | 1 | | @1 BOUGRAIN (Laurent) |
---|
A14 | 01 | | | @1 LORIA INRIA-Lorraine, B.P. 239 @2 54506 Vandoeuvre-Les-Nancy @3 FRA @Z 1 aut. |
---|
A18 | 01 | 1 | | @1 IEEE. Neural Networks Society @3 USA @9 patr. |
---|
A18 | 02 | 1 | | @1 International Neural Network Society @3 USA @9 patr. |
---|
A20 | | | | @1 1726-1729 |
---|
A21 | | | | @1 2002 |
---|
A23 | 01 | | | @0 ENG |
---|
A26 | 01 | | | @0 0-7803-7278-6 |
---|
A43 | 01 | | | @1 INIST @2 Y 37961 @5 354000117750883070 |
---|
A44 | | | | @0 0000 @1 © 2004 INIST-CNRS. All rights reserved. |
---|
A45 | | | | @0 12 ref. |
---|
A47 | 01 | 1 | | @0 04-0132540 |
---|
A60 | | | | @1 P @2 C |
---|
A61 | | | | @0 A |
---|
A64 | 01 | 1 | | @0 IEEE ... International Conference on Neural Networks |
---|
A66 | 01 | | | @0 USA |
---|
C01 | 01 | | ENG | @0 Usually, the learning stage of a neural network leads to a single model. But a complex problem cannot always be solved adequately by a global system. On the other side, several systems specialized on a subspace have some difficulties to deal with situations located at the limit of two classes. This article presents a new adaptive architecture based upon higher-order computation to adjust a general model to each pattern and using a pruning algorithm to improve the generalization and extract knowledge. We use one small multi-layer perceptron to predict each weight of the model from the current pattern (we have one estimator per weight). This architecture introduces a higher-order computation, biologically inspired, similar to the modulation of a synapse between two neurons by a third neuron. The general model can then be smaller, more adaptative and more informative. |
---|
C02 | 01 | X | | @0 001D02C06 |
---|
C03 | 01 | X | FRE | @0 Réseau multicouche @5 01 |
---|
C03 | 01 | X | ENG | @0 Multilayer network @5 01 |
---|
C03 | 01 | X | SPA | @0 Red multinivel @5 01 |
---|
C03 | 02 | 3 | FRE | @0 Perceptron multicouche @5 02 |
---|
C03 | 02 | 3 | ENG | @0 Multilayer perceptrons @5 02 |
---|
C03 | 03 | X | FRE | @0 Réseau neuronal @5 03 |
---|
C03 | 03 | X | ENG | @0 Neural network @5 03 |
---|
C03 | 03 | X | SPA | @0 Red neuronal @5 03 |
---|
C03 | 04 | X | FRE | @0 Synapse @5 04 |
---|
C03 | 04 | X | ENG | @0 Synapse @5 04 |
---|
C03 | 04 | X | SPA | @0 Sinapsis @5 04 |
---|
C03 | 05 | X | FRE | @0 Mode ordre élevé @5 05 |
---|
C03 | 05 | X | ENG | @0 High order mode @5 05 |
---|
C03 | 05 | X | SPA | @0 Modo orden elevado @5 05 |
---|
C03 | 06 | X | FRE | @0 Méthode adaptative @5 06 |
---|
C03 | 06 | X | ENG | @0 Adaptive method @5 06 |
---|
C03 | 06 | X | SPA | @0 Método adaptativo @5 06 |
---|
C03 | 07 | X | FRE | @0 Extraction connaissance @4 CD @5 96 |
---|
C03 | 07 | X | ENG | @0 Knowledge extraction @4 CD @5 96 |
---|
N21 | | | | @1 082 |
---|
N82 | | | | @1 PSI |
---|
|
pR |
A30 | 01 | 1 | ENG | @1 2002 International joint conference on neural networks @3 Honolulu HI USA @4 2002-05-12 |
---|
|
Format Inist (serveur)
NO : | PASCAL 04-0132540 INIST |
ET : | A pruned higher-order network for knowledge extraction |
AU : | BOUGRAIN (Laurent) |
AF : | LORIA INRIA-Lorraine, B.P. 239/54506 Vandoeuvre-Les-Nancy/France (1 aut.) |
DT : | Publication en série; Congrès; Niveau analytique |
SO : | IEEE ... International Conference on Neural Networks; ISSN 1098-7576; Etats-Unis; Da. 2002; Pp. 1726-1729; Bibl. 12 ref. |
LA : | Anglais |
EA : | Usually, the learning stage of a neural network leads to a single model. But a complex problem cannot always be solved adequately by a global system. On the other side, several systems specialized on a subspace have some difficulties to deal with situations located at the limit of two classes. This article presents a new adaptive architecture based upon higher-order computation to adjust a general model to each pattern and using a pruning algorithm to improve the generalization and extract knowledge. We use one small multi-layer perceptron to predict each weight of the model from the current pattern (we have one estimator per weight). This architecture introduces a higher-order computation, biologically inspired, similar to the modulation of a synapse between two neurons by a third neuron. The general model can then be smaller, more adaptative and more informative. |
CC : | 001D02C06 |
FD : | Réseau multicouche; Perceptron multicouche; Réseau neuronal; Synapse; Mode ordre élevé; Méthode adaptative; Extraction connaissance |
ED : | Multilayer network; Multilayer perceptrons; Neural network; Synapse; High order mode; Adaptive method; Knowledge extraction |
SD : | Red multinivel; Red neuronal; Sinapsis; Modo orden elevado; Método adaptativo |
LO : | INIST-Y 37961.354000117750883070 |
ID : | 04-0132540 |
Links to Exploration step
Pascal:04-0132540
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" level="a">A pruned higher-order network for knowledge extraction</title>
<author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation><inist:fA14 i1="01"><s1>LORIA INRIA-Lorraine, B.P. 239</s1>
<s2>54506 Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">INIST</idno>
<idno type="inist">04-0132540</idno>
<date when="2002">2002</date>
<idno type="stanalyst">PASCAL 04-0132540 INIST</idno>
<idno type="RBID">Pascal:04-0132540</idno>
<idno type="wicri:Area/PascalFrancis/Corpus">000726</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en" level="a">A pruned higher-order network for knowledge extraction</title>
<author><name sortKey="Bougrain, Laurent" sort="Bougrain, Laurent" uniqKey="Bougrain L" first="Laurent" last="Bougrain">Laurent Bougrain</name>
<affiliation><inist:fA14 i1="01"><s1>LORIA INRIA-Lorraine, B.P. 239</s1>
<s2>54506 Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</inist:fA14>
</affiliation>
</author>
</analytic>
<series><title level="j" type="main">IEEE ... International Conference on Neural Networks</title>
<idno type="ISSN">1098-7576</idno>
<imprint><date when="2002">2002</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
<seriesStmt><title level="j" type="main">IEEE ... International Conference on Neural Networks</title>
<idno type="ISSN">1098-7576</idno>
</seriesStmt>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Adaptive method</term>
<term>High order mode</term>
<term>Knowledge extraction</term>
<term>Multilayer network</term>
<term>Multilayer perceptrons</term>
<term>Neural network</term>
<term>Synapse</term>
</keywords>
<keywords scheme="Pascal" xml:lang="fr"><term>Réseau multicouche</term>
<term>Perceptron multicouche</term>
<term>Réseau neuronal</term>
<term>Synapse</term>
<term>Mode ordre élevé</term>
<term>Méthode adaptative</term>
<term>Extraction connaissance</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Usually, the learning stage of a neural network leads to a single model. But a complex problem cannot always be solved adequately by a global system. On the other side, several systems specialized on a subspace have some difficulties to deal with situations located at the limit of two classes. This article presents a new adaptive architecture based upon higher-order computation to adjust a general model to each pattern and using a pruning algorithm to improve the generalization and extract knowledge. We use one small multi-layer perceptron to predict each weight of the model from the current pattern (we have one estimator per weight). This architecture introduces a higher-order computation, biologically inspired, similar to the modulation of a synapse between two neurons by a third neuron. The general model can then be smaller, more adaptative and more informative.</div>
</front>
</TEI>
<inist><standard h6="B"><pA><fA01 i1="01" i2="1"><s0>1098-7576</s0>
</fA01>
<fA08 i1="01" i2="1" l="ENG"><s1>A pruned higher-order network for knowledge extraction</s1>
</fA08>
<fA09 i1="01" i2="1" l="ENG"><s1>IJCNN'02 : international joint conference on neural networks : Honolulu HI, 12-17 May 2002</s1>
</fA09>
<fA11 i1="01" i2="1"><s1>BOUGRAIN (Laurent)</s1>
</fA11>
<fA14 i1="01"><s1>LORIA INRIA-Lorraine, B.P. 239</s1>
<s2>54506 Vandoeuvre-Les-Nancy</s2>
<s3>FRA</s3>
<sZ>1 aut.</sZ>
</fA14>
<fA18 i1="01" i2="1"><s1>IEEE. Neural Networks Society</s1>
<s3>USA</s3>
<s9>patr.</s9>
</fA18>
<fA18 i1="02" i2="1"><s1>International Neural Network Society</s1>
<s3>USA</s3>
<s9>patr.</s9>
</fA18>
<fA20><s1>1726-1729</s1>
</fA20>
<fA21><s1>2002</s1>
</fA21>
<fA23 i1="01"><s0>ENG</s0>
</fA23>
<fA26 i1="01"><s0>0-7803-7278-6</s0>
</fA26>
<fA43 i1="01"><s1>INIST</s1>
<s2>Y 37961</s2>
<s5>354000117750883070</s5>
</fA43>
<fA44><s0>0000</s0>
<s1>© 2004 INIST-CNRS. All rights reserved.</s1>
</fA44>
<fA45><s0>12 ref.</s0>
</fA45>
<fA47 i1="01" i2="1"><s0>04-0132540</s0>
</fA47>
<fA60><s1>P</s1>
<s2>C</s2>
</fA60>
<fA64 i1="01" i2="1"><s0>IEEE ... International Conference on Neural Networks</s0>
</fA64>
<fA66 i1="01"><s0>USA</s0>
</fA66>
<fC01 i1="01" l="ENG"><s0>Usually, the learning stage of a neural network leads to a single model. But a complex problem cannot always be solved adequately by a global system. On the other side, several systems specialized on a subspace have some difficulties to deal with situations located at the limit of two classes. This article presents a new adaptive architecture based upon higher-order computation to adjust a general model to each pattern and using a pruning algorithm to improve the generalization and extract knowledge. We use one small multi-layer perceptron to predict each weight of the model from the current pattern (we have one estimator per weight). This architecture introduces a higher-order computation, biologically inspired, similar to the modulation of a synapse between two neurons by a third neuron. The general model can then be smaller, more adaptative and more informative.</s0>
</fC01>
<fC02 i1="01" i2="X"><s0>001D02C06</s0>
</fC02>
<fC03 i1="01" i2="X" l="FRE"><s0>Réseau multicouche</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="ENG"><s0>Multilayer network</s0>
<s5>01</s5>
</fC03>
<fC03 i1="01" i2="X" l="SPA"><s0>Red multinivel</s0>
<s5>01</s5>
</fC03>
<fC03 i1="02" i2="3" l="FRE"><s0>Perceptron multicouche</s0>
<s5>02</s5>
</fC03>
<fC03 i1="02" i2="3" l="ENG"><s0>Multilayer perceptrons</s0>
<s5>02</s5>
</fC03>
<fC03 i1="03" i2="X" l="FRE"><s0>Réseau neuronal</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="ENG"><s0>Neural network</s0>
<s5>03</s5>
</fC03>
<fC03 i1="03" i2="X" l="SPA"><s0>Red neuronal</s0>
<s5>03</s5>
</fC03>
<fC03 i1="04" i2="X" l="FRE"><s0>Synapse</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="ENG"><s0>Synapse</s0>
<s5>04</s5>
</fC03>
<fC03 i1="04" i2="X" l="SPA"><s0>Sinapsis</s0>
<s5>04</s5>
</fC03>
<fC03 i1="05" i2="X" l="FRE"><s0>Mode ordre élevé</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="ENG"><s0>High order mode</s0>
<s5>05</s5>
</fC03>
<fC03 i1="05" i2="X" l="SPA"><s0>Modo orden elevado</s0>
<s5>05</s5>
</fC03>
<fC03 i1="06" i2="X" l="FRE"><s0>Méthode adaptative</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="ENG"><s0>Adaptive method</s0>
<s5>06</s5>
</fC03>
<fC03 i1="06" i2="X" l="SPA"><s0>Método adaptativo</s0>
<s5>06</s5>
</fC03>
<fC03 i1="07" i2="X" l="FRE"><s0>Extraction connaissance</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fC03 i1="07" i2="X" l="ENG"><s0>Knowledge extraction</s0>
<s4>CD</s4>
<s5>96</s5>
</fC03>
<fN21><s1>082</s1>
</fN21>
<fN82><s1>PSI</s1>
</fN82>
</pA>
<pR><fA30 i1="01" i2="1" l="ENG"><s1>2002 International joint conference on neural networks</s1>
<s3>Honolulu HI USA</s3>
<s4>2002-05-12</s4>
</fA30>
</pR>
</standard>
<server><NO>PASCAL 04-0132540 INIST</NO>
<ET>A pruned higher-order network for knowledge extraction</ET>
<AU>BOUGRAIN (Laurent)</AU>
<AF>LORIA INRIA-Lorraine, B.P. 239/54506 Vandoeuvre-Les-Nancy/France (1 aut.)</AF>
<DT>Publication en série; Congrès; Niveau analytique</DT>
<SO>IEEE ... International Conference on Neural Networks; ISSN 1098-7576; Etats-Unis; Da. 2002; Pp. 1726-1729; Bibl. 12 ref.</SO>
<LA>Anglais</LA>
<EA>Usually, the learning stage of a neural network leads to a single model. But a complex problem cannot always be solved adequately by a global system. On the other side, several systems specialized on a subspace have some difficulties to deal with situations located at the limit of two classes. This article presents a new adaptive architecture based upon higher-order computation to adjust a general model to each pattern and using a pruning algorithm to improve the generalization and extract knowledge. We use one small multi-layer perceptron to predict each weight of the model from the current pattern (we have one estimator per weight). This architecture introduces a higher-order computation, biologically inspired, similar to the modulation of a synapse between two neurons by a third neuron. The general model can then be smaller, more adaptative and more informative.</EA>
<CC>001D02C06</CC>
<FD>Réseau multicouche; Perceptron multicouche; Réseau neuronal; Synapse; Mode ordre élevé; Méthode adaptative; Extraction connaissance</FD>
<ED>Multilayer network; Multilayer perceptrons; Neural network; Synapse; High order mode; Adaptive method; Knowledge extraction</ED>
<SD>Red multinivel; Red neuronal; Sinapsis; Modo orden elevado; Método adaptativo</SD>
<LO>INIST-Y 37961.354000117750883070</LO>
<ID>04-0132540</ID>
</server>
</inist>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/PascalFrancis/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000726 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PascalFrancis/Corpus/biblio.hfd -nk 000726 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= PascalFrancis
|étape= Corpus
|type= RBID
|clé= Pascal:04-0132540
|texte= A pruned higher-order network for knowledge extraction
}}
| This area was generated with Dilib version V0.6.33. Data generation: Mon Jun 10 21:56:28 2019. Site generation: Fri Feb 25 15:29:27 2022 | |