|
|
|
Article de revue:
|
ID no. (ISBN etc.): 0033-295X
|
Clé de citation BibTeX: Hummel2003
|
|
Hummel, J. E., & Holyoak, K. J. (2003). A symbolic-connectionist theory of relational inference and generalization. Psychological Review, 110(2), p. p220–264.
Ajoutée par: Sterenn Audo 2008-01-08 11:50:23 Dernièrement modifiée par: Sterenn Audo 2008-01-08 12:34:59
|
|
|
Catégories: Analogie, COEFF, Full text
Descripteurs: analogical inference, Analogy, cognitive architecture, computer simulation model, Generalization (Learning), INFERENCE, Learning & Inference with Schemas & Analogies, Neural Networks, relational generalization, relational inference, schema, schemas, symbolic connectionism
Auteurs: Holyoak, Hummel
Collection: Psychological Review
|
Nombre de vues: 348
Popularité: 31.61%
|
|
|
|
|
Résumé
The authors present a theory of how relational inference and generalization can be accomplished within a cognitive architecture that is psychologically and neurally realistic. Their proposal is a form of symbolic connectionism: a connectionist system based on distributed representations of concept meanings, using temporal synchrony to bind fillers and roles into relational structures. The authors present a specific instantiation of their theory in the form of a computer simulation model, Learning and Inference with Schemas and Analogies (LISA). By using a kind of self-supervised learning, LISA can make specific inferences and form new relational generalizations and can hence acquire new schemas by induction from examples. The authors demonstrate the sufficiency of the model by using it to simulate a body of empirical phenomena concerning analogical inference and relational generalization. (PsycINFO Database Record (c) 2006 APA, all rights reserved)(from the journal abstract)
Ajoutée par: Sterenn Audo Dernièrement modifiée par: Sterenn Audo
|
|
Informations supplémentaires en ligne :
|
|
|
|
|
|
|
|
|
|
|
Idées
pdf dispo
Ajoutée par: Sterenn Audo
|
|
|
