Matches in SemOpenAlex for { <https://semopenalex.org/work/W102790483> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W102790483 abstract "This thesis draws together a number of areas of cognitive computational research including symbolic connectionism and the modelling of concept formation and analogy. Central to the work is the processing of relations in a hybrid neural symbolic architecture. Models of analogy have recognised the importance of relational representations for some time now, and psychological research into concept formation has investigated the role of relational knowledge. However computational models of concept formation have typically not incorporated this into their architectures. This thesis formalises a tensor representation of relations and develops two models based on this formulation. One model is the Relcon model that applies an iterative procedure to a tensor representation of relations in order to converge to a stable representation of concepts. In addition to incorporating relational knowledge, the model accounts for typicality ratings of concept members and models a family resemblance-typicality correlation consistent with empirical research (Rosch & Mervis, 1975). The model also facilitates the formation of concepts of different granularity. Context sensitivity of the typicality of concept members is modelled by the postulation of the implied feature hypothesis: context implies a number of features and the typicality of concept members is increased/decreased according to their association to implied features. The second model, the STAR2000 model, is both the first computational model of theory-based concept formation to date and a unified model of theory-based concept formation and analogical mapping/retrieval. The model groups items into concepts according to an overarching theory that defines a relational structure relating theory-based concepts. Additionally the model retrieves analogs and forms mappings between corresponding members of analogous domain. Both models display an ability to rapidly retrieve adaptable concept representations, and in the case of the Relcon model, the need for a time consuming concept learning process is completely bypassed. Due to the models' ability to operate over relational knowledge and the rapid and adaptable nature of the concept retrieval processes, the argument is made that these models represent an integration of the concept formation process with higher cognitive processing." @default.
- W102790483 created "2016-06-24" @default.
- W102790483 creator A5017431068 @default.
- W102790483 date "2003-01-01" @default.
- W102790483 modified "2023-09-24" @default.
- W102790483 title "Relational models of feature based concept formation, theory-based concept formation and analogical retrieval/mapping" @default.
- W102790483 hasPublicationYear "2003" @default.
- W102790483 type Work @default.
- W102790483 sameAs 102790483 @default.
- W102790483 citedByCount "2" @default.
- W102790483 crossrefType "journal-article" @default.
- W102790483 hasAuthorship W102790483A5017431068 @default.
- W102790483 hasConcept C111472728 @default.
- W102790483 hasConcept C111919701 @default.
- W102790483 hasConcept C121332964 @default.
- W102790483 hasConcept C124101348 @default.
- W102790483 hasConcept C138885662 @default.
- W102790483 hasConcept C151730666 @default.
- W102790483 hasConcept C154945302 @default.
- W102790483 hasConcept C15744967 @default.
- W102790483 hasConcept C17744445 @default.
- W102790483 hasConcept C177774035 @default.
- W102790483 hasConcept C177877439 @default.
- W102790483 hasConcept C188147891 @default.
- W102790483 hasConcept C199539241 @default.
- W102790483 hasConcept C2776359362 @default.
- W102790483 hasConcept C2776401178 @default.
- W102790483 hasConcept C2779343474 @default.
- W102790483 hasConcept C41008148 @default.
- W102790483 hasConcept C41895202 @default.
- W102790483 hasConcept C50644808 @default.
- W102790483 hasConcept C521332185 @default.
- W102790483 hasConcept C52268767 @default.
- W102790483 hasConcept C5655090 @default.
- W102790483 hasConcept C62520636 @default.
- W102790483 hasConcept C80444323 @default.
- W102790483 hasConcept C8521452 @default.
- W102790483 hasConcept C86803240 @default.
- W102790483 hasConcept C94625758 @default.
- W102790483 hasConceptScore W102790483C111472728 @default.
- W102790483 hasConceptScore W102790483C111919701 @default.
- W102790483 hasConceptScore W102790483C121332964 @default.
- W102790483 hasConceptScore W102790483C124101348 @default.
- W102790483 hasConceptScore W102790483C138885662 @default.
- W102790483 hasConceptScore W102790483C151730666 @default.
- W102790483 hasConceptScore W102790483C154945302 @default.
- W102790483 hasConceptScore W102790483C15744967 @default.
- W102790483 hasConceptScore W102790483C17744445 @default.
- W102790483 hasConceptScore W102790483C177774035 @default.
- W102790483 hasConceptScore W102790483C177877439 @default.
- W102790483 hasConceptScore W102790483C188147891 @default.
- W102790483 hasConceptScore W102790483C199539241 @default.
- W102790483 hasConceptScore W102790483C2776359362 @default.
- W102790483 hasConceptScore W102790483C2776401178 @default.
- W102790483 hasConceptScore W102790483C2779343474 @default.
- W102790483 hasConceptScore W102790483C41008148 @default.
- W102790483 hasConceptScore W102790483C41895202 @default.
- W102790483 hasConceptScore W102790483C50644808 @default.
- W102790483 hasConceptScore W102790483C521332185 @default.
- W102790483 hasConceptScore W102790483C52268767 @default.
- W102790483 hasConceptScore W102790483C5655090 @default.
- W102790483 hasConceptScore W102790483C62520636 @default.
- W102790483 hasConceptScore W102790483C80444323 @default.
- W102790483 hasConceptScore W102790483C8521452 @default.
- W102790483 hasConceptScore W102790483C86803240 @default.
- W102790483 hasConceptScore W102790483C94625758 @default.
- W102790483 hasLocation W1027904831 @default.
- W102790483 hasOpenAccess W102790483 @default.
- W102790483 hasPrimaryLocation W1027904831 @default.
- W102790483 hasRelatedWork W1525397335 @default.
- W102790483 hasRelatedWork W1550086563 @default.
- W102790483 hasRelatedWork W1551494357 @default.
- W102790483 hasRelatedWork W1607019648 @default.
- W102790483 hasRelatedWork W1775052402 @default.
- W102790483 hasRelatedWork W2014563647 @default.
- W102790483 hasRelatedWork W2024442994 @default.
- W102790483 hasRelatedWork W2056231239 @default.
- W102790483 hasRelatedWork W2113715474 @default.
- W102790483 hasRelatedWork W2134002159 @default.
- W102790483 hasRelatedWork W2161441472 @default.
- W102790483 hasRelatedWork W2285675326 @default.
- W102790483 hasRelatedWork W2374694206 @default.
- W102790483 hasRelatedWork W2558053341 @default.
- W102790483 hasRelatedWork W2902819929 @default.
- W102790483 hasRelatedWork W3150562944 @default.
- W102790483 hasRelatedWork W40176063 @default.
- W102790483 hasRelatedWork W970973436 @default.
- W102790483 hasRelatedWork W1776297523 @default.
- W102790483 hasRelatedWork W2144762193 @default.
- W102790483 isParatext "false" @default.
- W102790483 isRetracted "false" @default.
- W102790483 magId "102790483" @default.
- W102790483 workType "article" @default.