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
Learning the Dynamics of Embedded Clauses
Sch. of Info. Technol. Elec. Eng., University of Queensland, Brisbane, Australia.
Sch. of Computer Science and Eng., University of New South Wales, Sydney, Australia.
2003 (English)In: Applied intelligence (Boston), ISSN 0924-669X, E-ISSN 1573-7497, Vol. 19, no 1-2, p. 51-63Article in journal (Refereed) Published
Abstract [en]

Recent work by Siegelmann has shown that the computational power of recurrent neural networks matches that of Turing Machines. One important implication is that complex language classes (infinite languages with embedded clauses) can be represented in neural networks. Proofs are based on a fractal encoding of states to simulate the memory and operations of stacks.

In the present work, it is shown that similar stack-like dynamics can be learned in recurrent neural networks from simple sequence prediction tasks. Two main types of network solutions are found and described qualitatively as dynamical systems: damped oscillation and entangled spiraling around fixed points. The potential and limitations of each solution type are established in terms of generalization on two different context-free languages. Both solution types constitute novel stack implementations—generally in line with Siegelmann's theoretical work—which supply insights into how embedded structures of languages can be handled in analog hardware.

Place, publisher, year, edition, pages
Springer Netherlands , 2003. Vol. 19, no 1-2, p. 51-63
Keywords [en]
Recurrent neural network, Dynamical system, Stack, Context-free language, Analysis, Computation, Learning
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:hh:diva-220DOI: 10.1023/A:1023816706954ISI: 000183042800005Scopus ID: 2-s2.0-0037589871Local ID: 2082/515OAI: oai:DiVA.org:hh-220DiVA, id: diva2:237398
Available from: 2006-11-24 Created: 2006-11-24 Last updated: 2018-01-13Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus
In the same journal
Applied intelligence (Boston)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 54 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