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
Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review
University of Skövde, School of Humanities and Informatics.
2004 (English)Report (Other academic)
Abstract [en]

Rule extraction (RE) from recurrent neural networks (RNNs) refers to finding models of the underlying RNN, typically in the form of finite state machines, that mimic the network to a satisfactory degree. RE from RNNs can be argued to allow a deeper and more profound form of analysis of RNNs than other, more or less \textit{ad hoc} methods. RE may give us understanding of RNNs in the intermediate levels between quite abstract theoretical knowledge of RNNs as a class of computing devices and quantitative performance evaluations of RNN instantiations. The development of techniques for extraction of rules from RNNs has been an active field since the early nineties. In this paper, the progress of this development is reviewed and analysed in detail. In order to structure the survey and to evaluate the techniques, a taxonomy, specifically designed for this purpose, has been developed. Moreover, important open research issues are identified, that, if addressed properly, possibly can give the field a significant push forward.

Place, publisher, year, edition, pages
Skövde: Institutionen för kommunikation och information , 2004. , 54 p.
Series
IKI Technical Reports, HS- IKI -TR-04-002
National Category
Information Science
Identifiers
URN: urn:nbn:se:his:diva-1266OAI: oai:DiVA.org:his-1266DiVA: diva2:2402
Available from: 2008-06-17 Created: 2008-06-17 Last updated: 2012-12-12Bibliographically approved

Open Access in DiVA

fulltext(362 kB)1113 downloads
File information
File name FULLTEXT01.pdfFile size 362 kBChecksum MD5
aae80b8804cb4cccd4fd1e4049db10069b64c5a5b40318ddd6873714e8887df9805bca34
Type fulltextMimetype application/pdf

Search in DiVA

By author/editor
Jacobsson, Henrik
By organisation
School of Humanities and Informatics
Information Science

Search outside of DiVA

GoogleGoogle Scholar
Total: 1113 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 118 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