Tools and Methodology for Hybrid Neuro-Symbolic Models
Identifieur interne : 00B184 ( Main/Exploration ); précédent : 00B183; suivant : 00B185Tools and Methodology for Hybrid Neuro-Symbolic Models
Auteurs : Frédéric AlexandreSource :
English descriptors
- KwdEn :
Abstract
Hybrid Neuro-Symbolic models are nowadays commonly used for intelligent information processing. Nevertheless, no serious theoretical study was performed in the past to settle a solid basis to hybridization. From this idea, a european ESPRIT project, the project MIX, funded by the European Union has been proposed, in order to study hybridization, develop tools and propose strategies to better analyse and emulate hybrid models. We explore in this paper the main results (theoretical and practical) of this project. They correspond to a toolbox for the implementation and communication of neural and symbolic agents and to some taxinomic aspects for the better classification and understanding of hybrid models. Thanks to these results, we were able to propose a general methodology for hybridization and to assess it thanks to real-world applications. Both aspects are also evoked in the paper.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 002432
- to stream Crin, to step Curation: 002432
- to stream Crin, to step Checkpoint: 002432
- to stream Main, to step Merge: 00B905
- to stream Main, to step Curation: 00B184
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="156">Tools and Methodology for Hybrid Neuro-Symbolic Models</title></titleStmt><publicationStmt><idno type="RBID">CRIN:alexandre98e</idno><date when="1998" year="1998">1998</date><idno type="wicri:Area/Crin/Corpus">002432</idno><idno type="wicri:Area/Crin/Curation">002432</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">002432</idno><idno type="wicri:Area/Crin/Checkpoint">002432</idno><idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002432</idno><idno type="wicri:Area/Main/Merge">00B905</idno><idno type="wicri:Area/Main/Curation">00B184</idno><idno type="wicri:Area/Main/Exploration">00B184</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en">Tools and Methodology for Hybrid Neuro-Symbolic Models</title><author><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name></author></analytic></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>artificial intelligence</term><term>connectionism</term><term>hybrid models</term><term>model selection</term><term>real world application</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en" wicri:score="2117">Hybrid Neuro-Symbolic models are nowadays commonly used for intelligent information processing. Nevertheless, no serious theoretical study was performed in the past to settle a solid basis to hybridization. From this idea, a european ESPRIT project, the project MIX, funded by the European Union has been proposed, in order to study hybridization, develop tools and propose strategies to better analyse and emulate hybrid models. We explore in this paper the main results (theoretical and practical) of this project. They correspond to a toolbox for the implementation and communication of neural and symbolic agents and to some taxinomic aspects for the better classification and understanding of hybrid models. Thanks to these results, we were able to propose a general methodology for hybridization and to assess it thanks to real-world applications. Both aspects are also evoked in the paper.</div></front></TEI><affiliations><list></list><tree><noCountry><name sortKey="Alexandre, Frederic" sort="Alexandre, Frederic" uniqKey="Alexandre F" first="Frédéric" last="Alexandre">Frédéric Alexandre</name></noCountry></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 00B184 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 00B184 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Exploration
|type= RBID
|clé= CRIN:alexandre98e
|texte= Tools and Methodology for Hybrid Neuro-Symbolic Models
}}
| This area was generated with Dilib version V0.6.33. |  |