Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding


Harnad, Stevan (1995) Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding. In, Honavar, V. and Uhr, L. (eds.) UNSPECIFIED Symbol Processors and Connectionist Network Models in Artificial Intelligence and Cognitive Modelling: Steps Toward Principled Integration , Academic Press, 191-206.

Download

[img] HTML
Download (23Kb)

Description/Abstract

After people learn to sort objects into categories they see them differently. Members of the same category look more alike and members of different categories look more different. This phenomenon of within-category compression and between-category separation in similarity space is called categorical perception (CP). It is exhibited by human subjects, animals and neural net models. In backpropagation nets trained first to auto-associate 12 stimuli varying along a one-dimensional continuum and then to sort them into 3 categories, CP arises as a natural side-effect because of four factors: (1) Maximal interstimulus separation in hidden-unit space during auto-association learning, (2) movement toward linear separability during categorization learning, (3) inverse-distance repulsive force exerted by the between-category boundary, and (4) the modulating effects of input iconicity, especially in interpolating CP to untrained regions of the continuum. Once similarity space has been "warped" in this way, the compressed and separated "chunks" have symbolic labels which could then be combined into symbol strings that constitute propositions about objects. The meanings of such symbolic representations would be "grounded" in the system's capacity to pick out from their sensory projections the object categories that the propositions were about.

Item Type: Book Section
Divisions: Faculty of Physical Sciences and Engineering > Electronics and Computer Science > Web & Internet Science
ePrint ID: 253357
Date Deposited: 25 May 2000
Last Modified: 27 Mar 2014 19:55
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/253357

Actions (login required)

View Item View Item

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