Neurosymbolic Integration : Cognitive Grounds and Computational Strategies
Identifieur interne : 001824 ( Crin/Corpus ); précédent : 001823; suivant : 001825Neurosymbolic Integration : Cognitive Grounds and Computational Strategies
Auteurs : Y. Lallement ; M. Hilario ; F. AlexandreSource :
English descriptors
- KwdEn :
Abstract
The ultimate - if implicit - goal or artificial intelligence research is to model the full range of human cognitive capabilities. Symbolic AI and connectionism, the major AI paradigms, have each tried - and failed - to attain this goal. In the meantime, the idea has gained ground that this goal might still be within reach if we could harness the respective strengths of these two paradigms in integrated neurosymbolic models. This paper attempts to lay a cognitive basis for neurosymbolic integration and describes the different strategies that have been adopted to date. Unified approaches strive to attain symbol-processing capabilities using neural network techniques alone, while hybrid approaches blend symbolic and neural models in novel architectures with the hope of gleaning the best of both paradigms.
Links to Exploration step
CRIN:lallement95aLe document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en" wicri:score="460">Neurosymbolic Integration : Cognitive Grounds and Computational Strategies</title>
</titleStmt>
<publicationStmt><idno type="RBID">CRIN:lallement95a</idno>
<date when="1995" year="1995">1995</date>
<idno type="wicri:Area/Crin/Corpus">001824</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Neurosymbolic Integration : Cognitive Grounds and Computational Strategies</title>
<author><name sortKey="Lallement, Y" sort="Lallement, Y" uniqKey="Lallement Y" first="Y." last="Lallement">Y. Lallement</name>
</author>
<author><name sortKey="Hilario, M" sort="Hilario, M" uniqKey="Hilario M" first="M." last="Hilario">M. Hilario</name>
</author>
<author><name sortKey="Alexandre, F" sort="Alexandre, F" uniqKey="Alexandre F" first="F." last="Alexandre">F. Alexandre</name>
</author>
</analytic>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>connectionism</term>
<term>hybrid model</term>
<term>symbolic</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en" wicri:score="3086">The ultimate - if implicit - goal or artificial intelligence research is to model the full range of human cognitive capabilities. Symbolic AI and connectionism, the major AI paradigms, have each tried - and failed - to attain this goal. In the meantime, the idea has gained ground that this goal might still be within reach if we could harness the respective strengths of these two paradigms in integrated neurosymbolic models. This paper attempts to lay a cognitive basis for neurosymbolic integration and describes the different strategies that have been adopted to date. Unified approaches strive to attain symbol-processing capabilities using neural network techniques alone, while hybrid approaches blend symbolic and neural models in novel architectures with the hope of gleaning the best of both paradigms.</div>
</front>
</TEI>
<BibTex type="inproceedings"><ref>lallement95a</ref>
<crinnumber>95-R-073</crinnumber>
<category>3</category>
<equipe>RFIA</equipe>
<author><e>Lallement, Y.</e>
<e>Hilario, M.</e>
<e>Alexandre, F.</e>
</author>
<title>Neurosymbolic Integration : Cognitive Grounds and Computational Strategies</title>
<booktitle>{Proceedings World Conference on the Fundamentals of Artificial Intelligence, Paris}</booktitle>
<year>1995</year>
<editor>M. DeGlas and Z. Pawlak</editor>
<month>jul</month>
<keywords><e>connectionism</e>
<e>symbolic</e>
<e>hybrid model</e>
</keywords>
<abstract>The ultimate - if implicit - goal or artificial intelligence research is to model the full range of human cognitive capabilities. Symbolic AI and connectionism, the major AI paradigms, have each tried - and failed - to attain this goal. In the meantime, the idea has gained ground that this goal might still be within reach if we could harness the respective strengths of these two paradigms in integrated neurosymbolic models. This paper attempts to lay a cognitive basis for neurosymbolic integration and describes the different strategies that have been adopted to date. Unified approaches strive to attain symbol-processing capabilities using neural network techniques alone, while hybrid approaches blend symbolic and neural models in novel architectures with the hope of gleaning the best of both paradigms.</abstract>
</BibTex>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Crin/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 001824 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Crin/Corpus/biblio.hfd -nk 001824 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Lorraine |area= InforLorV4 |flux= Crin |étape= Corpus |type= RBID |clé= CRIN:lallement95a |texte= Neurosymbolic Integration : Cognitive Grounds and Computational Strategies }}
![]() | This area was generated with Dilib version V0.6.33. | ![]() |