@prefix epid: .
@prefix dc: .
@prefix geo: .
@prefix bibo: .
@prefix epx: .
@prefix owl: .
@prefix void: .
@prefix event: .
@prefix skos: .
@prefix xsd: .
@prefix cc: .
@prefix ep: .
@prefix foaf: .
@prefix rdf: .
@prefix rdfs: .
@prefix eprel: .
@prefix dct: .
<>
foaf:primaryTopic ;
rdfs:comment "The repository administrator has not yet configured an RDF license."^^xsd:string .
rdfs:label "Image27.gif"^^xsd:string .
rdfs:label "icann9~1.htm"^^xsd:string .
rdfs:label "indexcodes.txt"^^xsd:string .
dc:format "text/html";
dc:title "HTML Summary of #622 \n\nA connectionist model for categorical perception and symbol grounding\n\n";
foaf:primaryTopic .
dct:hasPart ,
;
ep:hasFile ,
;
rdf:type bibo:Document,
ep:Document;
rdfs:label "A connectionist model for categorical perception and symbol grounding (HTML)"^^xsd:string .
dct:hasPart ;
ep:hasFile ;
eprel:isIndexCodesVersionOf ;
eprel:isVersionOf ;
eprel:isVolatileVersionOf ;
rdf:type ep:Document;
rdfs:label "A connectionist model for categorical perception and symbol grounding (Indexer Terms)"^^xsd:string .
rdf:_1 ;
rdf:_2 ;
rdf:_3 .
bibo:abstract "Neural network models of categorical perception can help solve the symbol-grounding problem [Harnad, 1990; 1993] by connecting analog sensory projections to symbolic representations through learned category-invariance detectors in a hybrid symbolic/nonsymbolic system. Our nets learn to categorize and name 50x50 pixel images of circles, ellipses, squares and rectangles projected onto the receptive field of a 7x7 retina. The nets first learn to do prototype matching and then entry-level naming for the four kinds of stimuli, grounding their names directly in the input patterns via hidden-unit representations. Next, a higher-order categorization (symmetric vs. asymmetric) is learned, either directly from the input, as with the entry- level categories, or from combinations of the grounded category names (symbols). We analyze the architectures and input conditions that allow grounding to be \"transferred\" from directly grounded entry-level category names to higher- order category names. Implications of such hybrid models for the evolution and learning of language are discussed."^^xsd:string;
bibo:authorList ;
bibo:status ,
;
dct:creator ,
,
;
dct:date "1998";
dct:isPartOf ;
dct:subject ,
;
dct:title "A connectionist model for categorical perception and symbol grounding"^^xsd:string;
ep:hasDocument ,
;
rdf:type bibo:Article,
ep:ConfpaperEPrint,
ep:EPrint;
rdfs:seeAlso .
rdf:type skos:Concept;
skos:prefLabel "Cognitive Psychology" .
rdf:type skos:Concept;
skos:prefLabel "Neural Nets" .
foaf:familyName "Greco"^^xsd:string;
foaf:givenName "Alberto"^^xsd:string;
foaf:name "Alberto Greco"^^xsd:string;
rdf:type foaf:Person .
foaf:familyName "Cangelosi"^^xsd:string;
foaf:givenName "Angelo"^^xsd:string;
foaf:name "Angelo Cangelosi"^^xsd:string;
rdf:type foaf:Person .
foaf:familyName "Harnad"^^xsd:string;
foaf:givenName "Stevan"^^xsd:string;
foaf:name "Stevan Harnad"^^xsd:string;
rdf:type foaf:Person .