title: A connectionist model for categorical perception and symbol grounding
creator: Greco, Alberto
creator: Cangelosi, Angelo
creator: Harnad, Stevan
subject: Cognitive Psychology
subject: Neural Nets
description: 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.
date: 1998
type: Conference Paper
type: NonPeerReviewed
format: text/html
identifier: http://cogprints.org/622/1/icann9~1.htm
identifier:   Greco, Alberto and Cangelosi, Angelo and Harnad, Stevan  (1998) A connectionist model for categorical perception and symbol grounding.  [Conference Paper]    (Unpublished)  
relation: http://cogprints.org/622/