his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Dynamic liquid association: Complex learning without implausible guidance
University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
University of Skövde, School of Humanities and Informatics. University of Skövde, The Informatics Research Centre.
2009 (English)In: Neural Networks, ISSN 0893-6080, E-ISSN 1879-2782, Vol. 22, no 7, 875-889 p.Article in journal (Refereed) Published
Abstract [en]

Simple associative networks have many desirable properties, but are fundamentally limited by their inability to accurately capture complex relationships. This paper presents a solution significantly extending the abilities of associative networks by using an untrained dynamic reservoir as an input filter. The untrained reservoir provides complex dynamic transformations, and temporal integration, and can be viewed as a complex non-linear feature detector from which the associative network can learn. Typically reservoir systems utilize trained single layer perceptrons to produce desired output responses. However given that both single layer perceptions and simple associative learning have the same computational limitations, i.e. linear separation, they should perform similarly in terms of pattern recognition ability. Further to this the extensive psychological properties of simple associative networks and the lack of explicit supervision required for associative learning motivates this extension overcoming previous limitations. Finally, we demonstrate the resulting model in a robotic embodiment, learning sensorimotor contingencies, and matching a variety of psychological data. (C) 2008 Elsevier Ltd. All rights reserved.

Place, publisher, year, edition, pages
Elsevier, 2009. Vol. 22, no 7, 875-889 p.
Identifiers
URN: urn:nbn:se:his:diva-7799DOI: 10.1016/j.neunet.2008.10.008ISI: 000270524500004Scopus ID: 2-s2.0-69449104579OAI: oai:DiVA.org:his-7799DiVA: diva2:613458
Available from: 2013-03-28 Created: 2013-03-21 Last updated: 2016-12-23Bibliographically approved

Open Access in DiVA

No full text

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Morse, AnthonyAktius, Malin
By organisation
School of Humanities and InformaticsThe Informatics Research Centre
In the same journal
Neural Networks

Search outside of DiVA

GoogleGoogle Scholar

Altmetric score

Total: 17 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf