Multi-Topographic Neural Network Communication and Generalization for Multi-Viewpoint Analysis
Identifieur interne : 005F24 ( Main/Merge ); précédent : 005F23; suivant : 005F25Multi-Topographic Neural Network Communication and Generalization for Multi-Viewpoint Analysis
Auteurs : Shadi Al Shehabi ; Jean-Charles Lamirel [France]Source :
Abstract
This paper presents a new generic multitopographic neural network model whose main area of application is clustering and knowledge extraction tasks on documentary data. The most powefull features of this model are its generalization mechanism and its mechanism of communication between topographies. This paper shows how these mechanisms can be exploited within the framework of the SOM and NG models. An evaluation of the generalization mechanism based on original quality and propagation coherency measures is also proposed. A secondary result of this evaluation is to proof that the generalization mechanism could significantly reduce the wellknown border effect of the SOM map.
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 004482
- to stream Crin, to step Curation: 004482
- to stream Crin, to step Checkpoint: 000149
Links to Exploration step
CRIN:al_shehabi05aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="650">Multi-Topographic Neural Network Communication and Generalization for Multi-Viewpoint Analysis</title></titleStmt><publicationStmt><idno type="RBID">CRIN:al_shehabi05a</idno><date when="2005" year="2005">2005</date><idno type="wicri:Area/Crin/Corpus">004482</idno><idno type="wicri:Area/Crin/Curation">004482</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">004482</idno><idno type="wicri:Area/Crin/Checkpoint">000149</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">000149</idno><idno type="wicri:Area/Main/Merge">005F24</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Multi-Topographic Neural Network Communication and Generalization for Multi-Viewpoint Analysis</title><author><name sortKey="Al Shehabi, Shadi" sort="Al Shehabi, Shadi" uniqKey="Al Shehabi S" first="Shadi" last="Al Shehabi">Shadi Al Shehabi</name></author><author><name sortKey="Lamirel, Jean Charles" sort="Lamirel, Jean Charles" uniqKey="Lamirel J" first="Jean-Charles" last="Lamirel">Jean-Charles Lamirel</name><affiliation><country>France</country><placeName><settlement type="city">Nancy</settlement><region type="region" nuts="2">Grand Est</region><region type="region" nuts="2">Lorraine (région)</region></placeName><orgName type="team" n="7">Cortex (Loria)</orgName><orgName type="lab">Laboratoire lorrain de recherche en informatique et ses applications</orgName><orgName type="university">Université de Lorraine</orgName><orgName type="EPST">Centre national de la recherche scientifique</orgName><orgName type="EPST">Institut national de recherche en informatique et en automatique</orgName></affiliation></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2666">This paper presents a new generic multitopographic neural network model whose main area of application is clustering and knowledge extraction tasks on documentary data. The most powefull features of this model are its generalization mechanism and its mechanism of communication between topographies. This paper shows how these mechanisms can be exploited within the framework of the SOM and NG models. An evaluation of the generalization mechanism based on original quality and propagation coherency measures is also proposed. A secondary result of this evaluation is to proof that the generalization mechanism could significantly reduce the wellknown border effect of the SOM map.</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 005F24 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Merge/biblio.hfd -nk 005F24 | 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= CRIN:al_shehabi05a
|texte= Multi-Topographic Neural Network Communication and Generalization for Multi-Viewpoint Analysis
}}
| This area was generated with Dilib version V0.6.33. |  |