MLP modular versus yprel classifiers
Identifieur interne : 001B73 ( Istex/Curation ); précédent : 001B72; suivant : 001B74MLP modular versus yprel classifiers
Auteurs : Yves Lecourtier [France] ; Bernadette Dorizzi [France] ; Philippe Sebire [France] ; Abdel Ennaji [France]Source :
- Lecture Notes in Computer Science [ 0302-9743 ] ; 1993.
Abstract
Abstract: We present two connectionist modular approaches which are potentially able to deal with real applications as their size does not increase drastically with the size of the problem. The first model relics on a very simple cooperation of modular MLP networks specially designed for some sub-tasks. The second is based on a new methodology using a particular processing element (“neuron”) called yprel. The main characteristics of the approach are: (i) An yprel classifier is a set of yprel nets, each net being associated to a particular class; (ii) the learning is supervised and conducted class by class; (iii) the structure of the net is not a priori chosen, but is determined step by step during the learning process. Both approaches are compared on a well-known classification task (recognition of typographic characters) in terms of performance rates.
Url:
DOI: 10.1007/3-540-56798-4_204
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: Pour aller vers cette notice dans l'étape Curation :001C92
Links to Exploration step
ISTEX:D260FEB6E6E142D4DC1B93477E740961543166D0Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">MLP modular versus yprel classifiers</title><author><name sortKey="Lecourtier, Yves" sort="Lecourtier, Yves" uniqKey="Lecourtier Y" first="Yves" last="Lecourtier">Yves Lecourtier</name><affiliation wicri:level="1"><mods:affiliation>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex</wicri:regionArea></affiliation></author><author><name sortKey="Dorizzi, Bernadette" sort="Dorizzi, Bernadette" uniqKey="Dorizzi B" first="Bernadette" last="Dorizzi">Bernadette Dorizzi</name><affiliation wicri:level="1"><mods:affiliation>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex</wicri:regionArea></affiliation><affiliation wicri:level="1"><mods:affiliation>E-mail: nad@etna.int-evry.fr</mods:affiliation><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Sebire, Philippe" sort="Sebire, Philippe" uniqKey="Sebire P" first="Philippe" last="Sebire">Philippe Sebire</name><affiliation wicri:level="1"><mods:affiliation>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex</wicri:regionArea></affiliation></author><author><name sortKey="Ennaji, Abdel" sort="Ennaji, Abdel" uniqKey="Ennaji A" first="Abdel" last="Ennaji">Abdel Ennaji</name><affiliation wicri:level="1"><mods:affiliation>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex</wicri:regionArea></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:D260FEB6E6E142D4DC1B93477E740961543166D0</idno><date when="1993" year="1993">1993</date><idno type="doi">10.1007/3-540-56798-4_204</idno><idno type="url">https://api.istex.fr/document/D260FEB6E6E142D4DC1B93477E740961543166D0/fulltext/pdf</idno><idno type="wicri:Area/Istex/Corpus">001C92</idno><idno type="wicri:Area/Istex/Curation">001B73</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">MLP modular versus yprel classifiers</title><author><name sortKey="Lecourtier, Yves" sort="Lecourtier, Yves" uniqKey="Lecourtier Y" first="Yves" last="Lecourtier">Yves Lecourtier</name><affiliation wicri:level="1"><mods:affiliation>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex</wicri:regionArea></affiliation></author><author><name sortKey="Dorizzi, Bernadette" sort="Dorizzi, Bernadette" uniqKey="Dorizzi B" first="Bernadette" last="Dorizzi">Bernadette Dorizzi</name><affiliation wicri:level="1"><mods:affiliation>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex</wicri:regionArea></affiliation><affiliation wicri:level="1"><mods:affiliation>E-mail: nad@etna.int-evry.fr</mods:affiliation><country wicri:rule="url">France</country></affiliation></author><author><name sortKey="Sebire, Philippe" sort="Sebire, Philippe" uniqKey="Sebire P" first="Philippe" last="Sebire">Philippe Sebire</name><affiliation wicri:level="1"><mods:affiliation>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>Institut National des Télécommunications, 9, rue Charles Fourier, F-91011, Evry Cedex</wicri:regionArea></affiliation></author><author><name sortKey="Ennaji, Abdel" sort="Ennaji, Abdel" uniqKey="Ennaji A" first="Abdel" last="Ennaji">Abdel Ennaji</name><affiliation wicri:level="1"><mods:affiliation>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex, France</mods:affiliation><country xml:lang="fr">France</country><wicri:regionArea>UFR des Sciences et Techniques, La3i, Université de Rouen, BP 118, F-76134, Mont Saint Aignan Cedex</wicri:regionArea></affiliation></author></analytic><monogr></monogr><series><title level="s">Lecture Notes in Computer Science</title><imprint><date>1993</date></imprint><idno type="ISSN">0302-9743</idno><idno type="eISSN">1611-3349</idno><idno type="ISSN">0302-9743</idno></series><idno type="istex">D260FEB6E6E142D4DC1B93477E740961543166D0</idno><idno type="DOI">10.1007/3-540-56798-4_204</idno><idno type="ChapterID">89</idno><idno type="ChapterID">Chap89</idno></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">0302-9743</idno></seriesStmt></fileDesc><profileDesc><textClass></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: We present two connectionist modular approaches which are potentially able to deal with real applications as their size does not increase drastically with the size of the problem. The first model relics on a very simple cooperation of modular MLP networks specially designed for some sub-tasks. The second is based on a new methodology using a particular processing element (“neuron”) called yprel. The main characteristics of the approach are: (i) An yprel classifier is a set of yprel nets, each net being associated to a particular class; (ii) the learning is supervised and conducted class by class; (iii) the structure of the net is not a priori chosen, but is determined step by step during the learning process. Both approaches are compared on a well-known classification task (recognition of typographic characters) in terms of performance rates.</div></front></TEI></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Istex/Curation
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001B73 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Istex/Curation/biblio.hfd -nk 001B73 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= OcrV1
|flux= Istex
|étape= Curation
|type= RBID
|clé= ISTEX:D260FEB6E6E142D4DC1B93477E740961543166D0
|texte= MLP modular versus yprel classifiers
}}
| This area was generated with Dilib version V0.6.32. |  |