Advanced

Conceptual spaces as a framework for knowledge representation

Gärdenfors, Peter LU (2004) In Mind and Matter 2(2). p.9-27
Abstract
The dominating models of information processes have been based

on symbolic representations of information and knowledge. During

the last decades, a varietyof non-symbolic models have been

proposed as superior. The prime examples of models within the

non-symbolic approach are neural networks. However, to a large

extent theylac k a higher-level theoryof representation. In this paper,

conceptual spaces are suggested as an appropriate framework

for non-symbolic models. Conceptual spaces consist of a number of

“qualitydimensions” that often are derived from perceptual mechanisms.

It will be outlined how conceptual spaces can represent

various kind of... (More)
The dominating models of information processes have been based

on symbolic representations of information and knowledge. During

the last decades, a varietyof non-symbolic models have been

proposed as superior. The prime examples of models within the

non-symbolic approach are neural networks. However, to a large

extent theylac k a higher-level theoryof representation. In this paper,

conceptual spaces are suggested as an appropriate framework

for non-symbolic models. Conceptual spaces consist of a number of

“qualitydimensions” that often are derived from perceptual mechanisms.

It will be outlined how conceptual spaces can represent

various kind of information and how theycan be used to describe

concept learning. The connections to prototype theory will also be

presented. (Less)
Please use this url to cite or link to this publication:
author
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Modeling representations Explanatory Associationism
in
Mind and Matter
volume
2
issue
2
pages
9 - 27
publisher
Imprint Academic
external identifiers
  • scopus:33845607242
ISSN
1611-8812
language
English
LU publication?
yes
id
ecf49a68-3775-48d2-bbca-784bc43cd6fd (old id 144289)
alternative location
http://www.mindmatter.de/mmabstracts2_2.htm#g%E4r
date added to LUP
2007-07-26 15:49:11
date last changed
2017-04-09 04:18:29
@article{ecf49a68-3775-48d2-bbca-784bc43cd6fd,
  abstract     = {The dominating models of information processes have been based<br/><br>
on symbolic representations of information and knowledge. During<br/><br>
the last decades, a varietyof non-symbolic models have been<br/><br>
proposed as superior. The prime examples of models within the<br/><br>
non-symbolic approach are neural networks. However, to a large<br/><br>
extent theylac k a higher-level theoryof representation. In this paper,<br/><br>
conceptual spaces are suggested as an appropriate framework<br/><br>
for non-symbolic models. Conceptual spaces consist of a number of<br/><br>
“qualitydimensions” that often are derived from perceptual mechanisms.<br/><br>
It will be outlined how conceptual spaces can represent<br/><br>
various kind of information and how theycan be used to describe<br/><br>
concept learning. The connections to prototype theory will also be<br/><br>
presented.},
  author       = {Gärdenfors, Peter},
  issn         = {1611-8812},
  keyword      = {Modeling representations
Explanatory
Associationism},
  language     = {eng},
  number       = {2},
  pages        = {9--27},
  publisher    = {Imprint Academic},
  series       = {Mind and Matter},
  title        = {Conceptual spaces as a framework for knowledge representation},
  volume       = {2},
  year         = {2004},
}