Categorical Perception and the Evolution of Supervised Learning in Neural Nets

Harnad, S.; Hanson, S.J. et Lubin, J. (1982). « Categorical Perception and the Evolution of Supervised Learning in Neural Nets ». Cognition and Brain Theory, 5, pp. 29-47.

Fichier(s) associé(s) à ce document :

	HTML Télécharger (29kB)

Résumé

Some of the features of animal and human categorical perception (CP) for color, pitch and speech are exhibited by neural net simulations of CP with one-dimensional inputs: When a backprop net is trained to discriminate and then categorize a set of stimuli, the second task is accomplished by "warping" the similarity space (compressing within-category distances and expanding between-category distances). This natural side-effect also occurs in humans and animals. Such CP categories, consisting of named, bounded regions of similarity space, may be the ground level out of which higher-order categories are constructed; nets are one possible candidate for the mechanism that learns the sensorimotor invariants that connect arbitrary names (elementary symbols?) to the nonarbitrary shapes of objects. This paper examines how and why such compression/expansion effects occur in neural nets.

Type:	Article de revue scientifique
Informations complémentaires:	directeurs de publication: Powers, D. W. et Reeker, L.
Mots-clés ou Sujets:	catégorisation, computation, apprentissage, langage, ancrage symbolique, évolution, intelligence artificielle, cognition, réseaux neuronaux, perception categorielle, Searle, Turing, sciences cognitives
Unité d'appartenance:	Faculté des sciences humaines > Département de psychologie Instituts > Institut des sciences cognitives (ISC)
Déposé par:	Stevan Harnad
Date de dépôt:	24 sept. 2007
Dernière modification:	20 avr. 2009 14:27
Adresse URL :	http://archipel.uqam.ca/id/eprint/133

Modifier les métadonnées (propriétaire du document)

Statistiques