Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding

Harnad, Stevan; Hanson, S.J. et Lubin, J. (1995). « Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding », dans Symbol Processors and Connectionist Network Models in Artificial Intelligence and Cognitive Modelling: Steps Toward Principled Integration, sous la dir. de Honavar, V. et Uhr, L.. États-Unis, Academic Press, pp. 191-206.

Fichier(s) associé(s) à ce document :

	HTML Télécharger (24kB)

Résumé

After people learn to sort objects into categories they see them differently. Members of the same category look more alike and members of different categories look more different. This phenomenon of within-category compression and between-category separation in similarity space is called categorical perception (CP). It is exhibited by human subjects, animals and neural net models. In backpropagation nets trained first to auto-associate 12 stimuli varying along a one-dimensional continuum and then to sort them into 3 categories, CP arises as a natural side-effect because of four factors: (1) Maximal interstimulus separation in hidden-unit space during auto-association learning, (2) movement toward linear separability during categorization learning, (3) inverse-distance repulsive force exerted by the between-category boundary, and (4) the modulating effects of input iconicity, especially in interpolating CP to untrained regions of the continuum. Once similarity space has been "warped" in this way, the compressed and separated "chunks" have symbolic labels which could then be combined into symbol strings that constitute propositions about objects. The meanings of such symbolic representations would be "grounded" in the system's capacity to pick out from their sensory projections the object categories that the propositions were about.

Type:	Chapitre de livre
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/164

Modifier les métadonnées (propriétaire du document)

Statistiques