---
abstract: |-
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.
altloc:
- http://www.cogsci.soton.ac.uk/~harnad/Papers/Harnad/harnad91.cpnets.html
chapter: ~
commentary: ~
commref: ~
confdates: ~
conference: ~
confloc: ~
contact_email: ~
creators_id: []
creators_name:
- family: Harnad
given: Stevan
honourific: ''
lineage: ''
- family: Hanson
given: S.J.
honourific: ''
lineage: ''
- family: Lubin
given: J.
honourific: ''
lineage: ''
date: 1991
date_type: published
datestamp: 2001-06-18
department: ~
dir: disk0/00/00/15/79
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name:
- family: Powers
given: D. W.
honourific: ''
lineage: ''
- family: Reeker
given: L.
honourific: ''
lineage: ''
eprint_status: archive
eprintid: 1579
fileinfo: /style/images/fileicons/text_html.png;/1579/1/harnad91.cpnets.html
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: pub
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: 'categorical perception, neural nets, learning '
lastmod: 2011-03-11 08:54:40
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: 65-74
pubdom: FALSE
publication: Working Papers of the AAAI Spring Symposium on Machine Learning of Natural Language and Ontology
publisher: 'Symposium on Symbol Grounding: Problems and Practice, Stanford University'
refereed: FALSE
referencetext: |
Cottrell, Munro & Zipser (1987) Image compression by back propagation: an
example of extensional programming. ICS Report 8702, Institute for Cognitive
Science, UCSD.
Hanson & Burr (1990) What connectionist models learn: Learning and
Representation in connectionist networks. Behavioral and Brain Sciences
13:471-518.
Hanson, S. J. and Kegl, J. (1987) Parsnip: A Connectionist Model that Learns
Natural Language Grammar from Exposure to Natural Language Sentences. "Ninth
Annual Cognitive Science Conference, Seattle."
Harnad, S. (ed.) (1987) "Categorical Perception: The Groundwork of Cognition" .
New York: Cambridge University Press.
Harnad, S. (1990) The Symbol Grounding Problem. "Physica D" 42: 335-346.
McClelland, J.L., Rumelhart, D. E., and the PDP Research Group (1986) "Parallel
distributed processing: Explorations in the microstructure of cognition," Volume 1.
Cambridge MA: MIT/Bradford.
Miller, G. A. (1956) The magical number seven, plus or minus two: Some limits on
our capacity for processing information. "Psychological Review" 63: 81 - 97.
relation_type: []
relation_uri: []
reportno: ~
rev_number: 8
series: ~
source: ~
status_changed: 2007-09-12 16:38:47
subjects:
- comp-sci-neural-nets
- percep-cog-psy
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: Categorical Perception and the Evolution of Supervised Learning in Neural Nets
type: bookchapter
userid: 63
volume: ~