Tools and experiments for hybrid neuro-symbolic processing
Identifieur interne : 00BB06 ( Main/Exploration ); précédent : 00BB05; suivant : 00BB07Tools and experiments for hybrid neuro-symbolic processing
Auteurs : Frédéric AlexandreSource :
English descriptors
- KwdEn :
Abstract
Symbolic and connectionist tools are widely used in the Artificial Intelligence (AI) domain. Both approaches report weaknesses to address the full range of capabilities required by this domain, and are often one with the other to overcome some limitations, but no extensive efforts have been done to give a wider view of the problem. More precisely, many ad hoc hybrid models were built from symbolic and connectionist tools, but few was said about the choice, integration and combination of such tools. Such was the goal of the European ESPRIT project MIX. We report here the main conclusions of the project, together with its results on a real-world application.
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Crin, to step Corpus: 001D10
- to stream Crin, to step Curation: 001D10
- to stream Crin, to step Checkpoint: 002829
- to stream Main, to step Merge: 00C283
- to stream Main, to step Curation: 00BB06
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="105">Tools and experiments for hybrid neuro-symbolic processing</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:alexandre97c</idno>
<date when="1997" year="1997">1997</date>
<idno type="wicri:Area/Crin/Corpus">001D10</idno>
<idno type="wicri:Area/Crin/Curation">001D10</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Curation">001D10</idno>
<idno type="wicri:Area/Crin/Checkpoint">002829</idno>
<idno type="wicri:explorRef" wicri:stream="Crin" wicri:step="Checkpoint">002829</idno>
<idno type="wicri:Area/Main/Merge">00C283</idno>
<idno type="wicri:Area/Main/Curation">00BB06</idno>
<idno type="wicri:Area/Main/Exploration">00BB06</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Tools and experiments for hybrid neuro-symbolic processing</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>hybridization</term>
<term>knowledge and data</term>
<term>neuro-symbolic integration</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="2261">Symbolic and connectionist tools are widely used in the Artificial Intelligence (AI) domain. Both approaches report weaknesses to address the full range of capabilities required by this domain, and are often one with the other to overcome some limitations, but no extensive efforts have been done to give a wider view of the problem. More precisely, many ad hoc hybrid models were built from symbolic and connectionist tools, but few was said about the choice, integration and combination of such tools. Such was the goal of the European ESPRIT project MIX. We report here the main conclusions of the project, together with its results on a real-world application.</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 00BB06 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 00BB06 | 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:alexandre97c |texte= Tools and experiments for hybrid neuro-symbolic processing }}
This area was generated with Dilib version V0.6.33. |