---
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.'
altloc: []
chapter: ~
commentary: ~
commref: ~
confdates: ~
conference: 'ICANN98 - International Conference on Artificial Neural Networks'
confloc: ~
contact_email: ~
creators_id: []
creators_name:
- family: Greco
given: Alberto
honourific: ''
lineage: ''
- family: Cangelosi
given: Angelo
honourific: ''
lineage: ''
- family: Harnad
given: Stevan
honourific: ''
lineage: ''
date: 1998
date_type: published
datestamp: 1998-03-31
department: ~
dir: disk0/00/00/06/22
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name: []
eprint_status: archive
eprintid: 622
fileinfo: /style/images/fileicons/text_html.png;/622/1/icann9~1.htm
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: unpub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: 'symbol grounding, categorical perception, categorisation, language evolution modelling, neural networks, backpropagation, geometric shapes'
lastmod: 2011-03-11 08:54:07
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: ~
pubdom: FALSE
publication: ~
publisher: ~
refereed: FALSE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 8
series: ~
source: ~
status_changed: 2007-09-12 16:32:15
subjects:
- cog-psy
- comp-sci-neural-nets
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: A connectionist model for categorical perception and symbol grounding
type: confpaper
userid: 24
volume: ~