Fusion of Symbolic and Quantitative Processing by Conceptual Fuzzy Sets

  • Tomohiro Takagi
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 59)


The real world consists of events and continuous numeric values, while people represent and process their knowledge in terms of symbols. Fuzzy sets provide a strong notation connecting the symbolic representation to the real world. In this paper, we discuss Conceptual Fuzzy Sets (CFS), a new type of fuzzy sets which conform to Wittgenstein’s ideas[7]. In CFS the meaning of a concept is represented by the distribution of activation of labels in associative memory, and is capable of simultaneous symbolic and quantitative processing. In particular, a multi-layered structured CFS represents the meaning of the same concept as it is used in various expressions in each layer. As the propagation of activations corresponds to reasoning, multi-layered reasoning in CFS has following features; 1) capable of simultaneous top-down and bottom-up processing, 2) capable of context sensitive knowledge processing.


Facial Expression Lower Layer Associative Memory Parking Space Hebbian Learning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    L.A. Zadeh, A Fuzzy-Algorithmic Approach to the Definition of Complex or Imprecise Concepts, Int. J. Man-Machine Studies, Vol. 8, pp. 249–291 (1976)MathSciNetMATHCrossRefGoogle Scholar
  2. 2.
    R.A.Brooks, A Robust Layered Control System for a Mobile Robot, IEEE Journal of Robotics and Automation, 2- (1986)Google Scholar
  3. 3.
    J. Russmussen, Skills, Rules, and Knowledge: Signals, Signs, and Symbols, and Other Distinctions in Human Performance Models, IEEE Trans. on System, Man and Cybernetics, SMC-13–3, pp. 257–266 (1983)Google Scholar
  4. 4.
    G.N. Saridis, “Intelligent Robotic Control, IEEE Trans. on Automatic Control, AC-28–5, pp. 547–557 (1983)Google Scholar
  5. 5.
    T. Sawaragi, T. Norita and T. Takagi, Fuzzy Theory, Journal of the Robotics Society of Japan, Vol. 9 No. 2, pp. 238–255 (1991) (in Japanese)CrossRefGoogle Scholar
  6. 6.
    T. Sawaragi, S. Iwai and O.Katai, Self-Organization of Conceptual Generalities and Pattern-Directed Learning, Automatica, 26–6, pp. 1009–1023 (1990)CrossRefGoogle Scholar
  7. 7.
    Wittgenstein, Philosophical Investigations, Basil Blackwell, Oxford (1953)Google Scholar
  8. 8.
    T. Takagi, A. Imura, H. Ushida and T. Yamaguchi, Conceptual Fuzzy Sets as a Meaning Representation and their Inductive Construction, International Journal of Intelligent Systems, Vol. 10, pp. 929–945 (1995)CrossRefGoogle Scholar
  9. 9.
    T. Takagi, A. Imura, H. Ushida and T. Yamaguchi, Multilayered Reasoning by Means of Conceptual Fuzzy Sets, International Journal of Intelligent Systems, Vol. 11, pp. 97–111 (1996)CrossRefGoogle Scholar
  10. 10.
    B.Kosko, Adaptive Bidirectional Associative Memories, Applied Optics, Vol. 26, No 23, pp. 4947–4960 (1987)CrossRefGoogle Scholar
  11. 11.
    B.Kosko, Neural Network and Fuzzy Systems, Prentice HALL (1992)Google Scholar
  12. 12.
    T. Takagi, A. Imura, H. Ushida and T. Yamaguchi, “Inductive learning of Conceptual Fuzzy Sets, 2nd International Conference on Fuzzy Logic and Neural Networks IIZUKA92, VOL.I, pp. 375–380 (1992)Google Scholar
  13. 13.
    S. Yamamoto, T. Yamaguchi, T. Takagi, Fuzzy Associative Inference System and its Features, IEEE International Conference on System Engineering, pp. 155–158 (1992)Google Scholar
  14. 14.
    T. Yamaguchi, M. Tanabe, K. Kuriyama and T. Mita, Fuzzy Adaptive Control with An Associative Memory System, IEE CONTROL91 No.332, Vol. 2, pp. 944–947 (1991)Google Scholar
  15. 15.
    Kobayashi and Hara, The Recognition of Basic Facial Expressions by Neural Network,“ International Joint conference on Neural Network, pp 460–466 (1991)Google Scholar

Copyright information

© Physica-Verlag Heidelberg 2001

Authors and Affiliations

  • Tomohiro Takagi
    • 1
  1. 1.Department of Computer ScienceMeiji University 1-1-1 Higashi-MitaTama-ku, Kawasaki-shi Kanagawa-kenJapan

Personalised recommendations