Högskolan i Skövde

his.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • 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
The Crystallizing Substochastic Sequential Machine Extractor: CrySSMEx
University of Skövde, School of Humanities and Informatics.
2006 (English)In: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 18, no 9, p. 2211-2255Article in journal (Refereed) Published
Abstract [en]

This letter presents an algorithm, CrySSMEx, for extracting minimal finite state machine descriptions of dynamic systems such as recurrent neural networks. Unlike previous algorithms, CrySSMEx is parameter free and deterministic, and it efficiently generates a series of increasingly refined models. A novel finite stochastic model of dynamic systems and a novel vector quantization function have been developed to take into account the state-space dynamics of the system. The experiments show that (1) extraction from systems that can be described as regular grammars is trivial, (2) extraction from high-dimensional systems is feasible, and (3) extraction of approximative models from chaotic systems is possible. The results are promising, and an analysis of shortcomings suggests some possible further improvements. Some largely overlooked connections, of the field of rule extraction from recurrent neural networks, to other fields are also identified.

Place, publisher, year, edition, pages
MIT Press, 2006. Vol. 18, no 9, p. 2211-2255
Identifiers
URN: urn:nbn:se:his:diva-1908DOI: 10.1162/neco.2006.18.9.2211ISI: 000239341000007PubMedID: 16846391Scopus ID: 2-s2.0-33748305559OAI: oai:DiVA.org:his-1908DiVA, id: diva2:32184
Available from: 2007-09-21 Created: 2007-09-21 Last updated: 2017-12-12Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textPubMedScopus

Authority records

Jacobsson, Henrik

Search in DiVA

By author/editor
Jacobsson, Henrik
By organisation
School of Humanities and Informatics
In the same journal
Neural Computation

Search outside of DiVA

GoogleGoogle Scholar

doi
pubmed
urn-nbn

Altmetric score

doi
pubmed
urn-nbn
Total: 112 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • apa-cv
  • 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