Högskolan i Skövde

his.sePublications
Change search
Refine search result
1 - 5 of 5
CiteExportLink to result list
Permanent 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
Rows per page
  • 5
  • 10
  • 20
  • 50
  • 100
  • 250
Sort
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
  • Standard (Relevance)
  • Author A-Ö
  • Author Ö-A
  • Title A-Ö
  • Title Ö-A
  • Publication type A-Ö
  • Publication type Ö-A
  • Issued (Oldest first)
  • Issued (Newest first)
  • Created (Oldest first)
  • Created (Newest first)
  • Last updated (Oldest first)
  • Last updated (Newest first)
  • Disputation date (earliest first)
  • Disputation date (latest first)
Select
The maximal number of hits you can export is 250. When you want to export more records please use the Create feeds function.
  • 1.
    Jacobsson, Henrik
    University of Skövde, School of Humanities and Informatics.
    Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review2005In: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 17, no 6, p. 1223-1263Article in journal (Refereed)
    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 while having the advantage of being more transparent. RE from RNNs can be argued to allow a deeper and more profound form of analysis of RNNs than other, more or less 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 1990s. This article reviews the progress of this development and analyzes it in detail. In order to structure the survey and 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.

  • 2.
    Jacobsson, Henrik
    University of Skövde, School of Humanities and Informatics.
    Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review2004Report (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 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.

    Download full text (pdf)
    FULLTEXT01
  • 3.
    Jacobsson, Henrik
    University of Skövde, School of Humanities and Informatics.
    The Crystallizing Substochastic Sequential Machine Extractor: CrySSMEx2006In: Neural Computation, ISSN 0899-7667, E-ISSN 1530-888X, Vol. 18, no 9, p. 2211-2255Article in journal (Refereed)
    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.

  • 4.
    Jakobsson, Henrik
    et al.
    University of Skövde, School of Humanities and Informatics.
    Ziemke, Tom
    University of Skövde, School of Humanities and Informatics.
    CrySSMEx, a novel rule extractor for recurrent neural networks: Overview and case study2005In: Artificial Neural Networks: Formal Models and Their Applications: ICANN 2005 15th International Conference, Warsaw, Poland, September 11-15, 2005, Proceedings, Part II / [ed] Włodzisław Duch, Janusz Kacprzyk, Erkki Oja, Sławomir Zadrożny, Springer Berlin/Heidelberg, 2005, p. 503-508Conference paper (Refereed)
    Abstract [en]

    In this paper, it will be shown that it is feasible to extract finite state machines in a domain of, for rule extraction, previously unencountered complexity. The algorithm used is called the Crystallizing Substochastic Sequential Machine Extractor, or CrySSMEx. It extracts the machine from sequence data generated from the RNN in interaction with its domain. CrySSMEx is parameter free, deterministic and generates a sequence of increasingly deterministic extracted stochastic models until a fully deterministic machine is found.

  • 5.
    Stening, John
    et al.
    University of Skövde, School of Humanities and Informatics.
    Jacobsson, Henrik
    University of Skövde, School of Humanities and Informatics.
    Ziemke, Tom
    University of Skövde, School of Humanities and Informatics.
    Imagination and Abstraction of Sensorimotor Flow: Towards a Robot Model2005In: AISB'05 Convention: Proceedings of the Symposium on Next Generation Approaches to Machine Consciousness: Imagination, Development, Intersubjectivity and Embodiment, The Society for the Study of Artificial Intelligence and the Simulation of Behaviour , 2005, p. 50-58Conference paper (Refereed)
1 - 5 of 5
CiteExportLink to result list
Permanent 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