Learning-induced categorical perception in a neural network model
Learning-induced categorical perception in a neural network model
In human cognition, the expansion of perceived between-category distances and compression of within-category distances is known as categorical perception (CP). There are several hypotheses about the causes of CP (e.g., language, learning, evolution) but no functional model. Whether CP is essential to categorisation or simply a by-product of it is not yet clear, but evidence is accumulating that CP can be induced by category learning. We provide a model for learning-induced CP as expansion and compression of distances in hidden-unit space in neural nets. Basic conditions from which the current model predicts CP are described, and clues as to how these conditions might generalize to more complex kinds of categorization begin to emerge.
1-11
Christian, Thériault
e5dfac75-c0f0-460b-b4ea-7819e151ca7f
Perez-Gay, Fernanda
f0c9d458-73f6-49e7-8300-2368a85f0220
Rivas, Daniel
be9748c1-e5a6-4986-8fbe-ffa10e110b09
Harnad, Stevan
442ee520-71a1-4283-8e01-106693487d8b
Christian, Thériault
e5dfac75-c0f0-460b-b4ea-7819e151ca7f
Perez-Gay, Fernanda
f0c9d458-73f6-49e7-8300-2368a85f0220
Rivas, Daniel
be9748c1-e5a6-4986-8fbe-ffa10e110b09
Harnad, Stevan
442ee520-71a1-4283-8e01-106693487d8b
Christian, Thériault, Perez-Gay, Fernanda, Rivas, Daniel and Harnad, Stevan
(2018)
Learning-induced categorical perception in a neural network model.
TopiCS in Cognitive Science, .
Abstract
In human cognition, the expansion of perceived between-category distances and compression of within-category distances is known as categorical perception (CP). There are several hypotheses about the causes of CP (e.g., language, learning, evolution) but no functional model. Whether CP is essential to categorisation or simply a by-product of it is not yet clear, but evidence is accumulating that CP can be induced by category learning. We provide a model for learning-induced CP as expansion and compression of distances in hidden-unit space in neural nets. Basic conditions from which the current model predicts CP are described, and clues as to how these conditions might generalize to more complex kinds of categorization begin to emerge.
Text
cparticle_May11_updatefromCT_SH_2
- Author's Original
More information
In preparation date: 2018
Identifiers
Local EPrints ID: 420868
URI: http://eprints.soton.ac.uk/id/eprint/420868
PURE UUID: 95c69494-60ab-44bd-94b1-3f0df3325101
Catalogue record
Date deposited: 17 May 2018 16:30
Last modified: 16 Mar 2024 02:47
Export record
Contributors
Author:
Thériault Christian
Author:
Fernanda Perez-Gay
Author:
Daniel Rivas
Author:
Stevan Harnad
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics