hh.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
Generalization by symbolic abstraction in cascaded recurrent networks
Univ Queensland, Sch Informat Technol & Elect Engn, Brisbane, Australia.
2004 (English)In: Neurocomputing, ISSN 0925-2312, E-ISSN 1872-8286, Vol. 57, no 1-4, p. 87-104Article in journal (Refereed) Published
Abstract [en]

Generalization performance in recurrent neural networks is enhanced by cascading several networks. By discretizing abstractions induced in one network, other networks can operate on a coarse symbolic level with increased performance on sparse and structural prediction tasks. The level of systematicity exhibited by the cascade of recurrent networks is assessed on the basis of three language domains.

Place, publisher, year, edition, pages
Elsevier, 2004. Vol. 57, no 1-4, p. 87-104
Keywords [en]
Recurrent neural network, Language, Generalization, Systematicity
National Category
Engineering and Technology
Identifiers
URN: urn:nbn:se:hh:diva-223DOI: 10.1016/j.neucom.2004.01.006ISI: 000220670700006Scopus ID: 2-s2.0-1542680967Local ID: 2082/518OAI: oai:DiVA.org:hh-223DiVA, id: diva2:237401
Available from: 2006-11-24 Created: 2006-11-24 Last updated: 2017-12-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus
In the same journal
Neurocomputing
Engineering and Technology

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 35 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