creators_name: Greco, Alberto
creators_name: Cangelosi, Angelo
creators_name: Harnad, Stevan
type: confpaper
datestamp: 1998-03-31
lastmod: 2011-03-11 08:54:07
metadata_visibility: show
title: A connectionist model for categorical perception and symbol grounding
ispublished: unpub
subjects: cog-psy
subjects: comp-sci-neural-nets
full_text_status: public
keywords: symbol grounding, categorical perception, categorisation, language evolution modelling, neural networks, backpropagation, geometric shapes
abstract: 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
date_type: published
refereed: FALSE
citation:   Greco, Alberto and Cangelosi, Angelo and Harnad, Stevan  (1998) A connectionist model for categorical perception and symbol grounding.  [Conference Paper]    (Unpublished)  
document_url: http://cogprints.org/622/1/icann9~1.htm