New Paradigm toward Deep Fusion of Computational and Symbolic Processing

  • Shun’ichi Tano
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 59)


The computational processing methods appeared to overcome the drawbacks of the symbolic processing method. Recently the serious limitations of the computational processing methods have been found through the development of the highly intelligent user interface systems. The simple solutions to the limitations are the return to the symbolism or the pursue of the hierarchical system architecture. However it is indispensable to deeply combine the symbolic and computational processing in order to realize the highly intelligent system. This paper analyzes the leading models, which use symbolic and computational processing, and clarifies the problems of them. The level of the combination is not deep, high and wide enough. Based on the analysis, we propose a new paradigm toward deep fusion of computational and symbolic processing and show the new model as the first step of the paradigm. The model is realized by “Symbol Emergence Method for Q-Learning Neural Network”. We testified the validity of the new method.


Computational Processing Fuzzy Theory Fuzzy Reasoning Combination Function Generation User Interface 
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]
    Kruger, W., et. al. The Responsible Workbench: A Virtual Work Environment, COMPUTER, Vol. 28, No. 7, pp. 42–48, 1995.CrossRefGoogle Scholar
  2. [2]
    Wellner, P. Interactive With Papers on the DigitalDesk, Communications of the ACM, Vol. 36, No. 7, pp. 87–97, 1993.CrossRefGoogle Scholar
  3. [3]
    Maes, P. Agent that Reduce Work and Information Overload, CACM, Vol. 37, No. 7, 30–40, 1994.Google Scholar
  4. [4]
    Tano, S. Research Trend of Next Generation User Interface, Journal of Japan Society for Fuzzy Theory and Systems, Vol. 8, No. 2, pp. 216–228, 1996 (in Japanese).MathSciNetGoogle Scholar
  5. [5]
    Tano: Potential of Fuzzy Symbolic and Computational Inference for Multi Modal User Interface, IFSA-97, pp. 407–412, 1997.Google Scholar
  6. [6]
    Tano, S., et. al. Design Concept Based on Real-Virtual-Intelligent User Interface and Its Software Architecture, HCI-97, pp. 901–904, 1997.Google Scholar
  7. [7]
    Namba, Y., et. al. Complex Chained Function Structure for Human-Computer Interface, HCI International ‘85 Poster Session, pp. 32–32, 1995.Google Scholar
  8. [8]
    R.Sun, T.Peterson, “Hybrid Learning Incorporating Neural and Symbolic Processes”, FUZZ-IEEE’98, pp. 727–732, 1998Google Scholar
  9. [9]
    T.Omori, N.Yamanashi, “PATON A Model of Concept Representation and Operation in Brain”, Proc.of Int’l Vonfon NeuralNetwork94, pp. 2227–2232, 1994Google Scholar
  10. [10]
    I. Takeuchi, T. Furuhashi: A Study on Inference between Patterns and Symbols, 13`h Fuzzy System Symposium, pp. 573–576, 1997 (in Japanese)Google Scholar
  11. [11]
    T.Takagi,A.Imura,H.Ushida,T.Yamgaguchi, “Computational Fuzzy Sets as a Meaning Representation and Their Inductive Construction”, International journal of intelligent systems Vol. 10, No. 11, pp. 929–945, November 1995CrossRefGoogle Scholar
  12. [12]
    S.Ohsuga, “Symbol processing by Non-Symbol Processor”, Proc.4 th Pacific Rim International Conference on Artificial Intelligence, Cairns, Australia, 1996Google Scholar
  13. [13]
    S.Tano, “Synergetic Effect by Deep Fusion of Computational and Symbolic Processing”, FUZZ-IEEE’98, pp. 744–749, 1998Google Scholar
  14. [14]
    Y. Uemura, S. Tano: Analysis of symbolic and computational processing and a new fusion method, 14`h Fuzzy System Symposium, pp. 179–180, 1998 (in Japanese)Google Scholar
  15. [15]
    Y. Uemura, D. Futamura, S. Tano: Proposal of Symbolic and Computational Processing and Initial Evaluation by Simulation, 15th Fuzzy System Symposium, pp. 471–474,1999 (in Japanese)Google Scholar
  16. [16]
    Papers in the organized session “Deep Fusion of Computational and Symbolic Processing” of FUZZ-IEEE 98 at World Congress on Computational Intelligence (WCCI’ 98), pp. 709–749, 1998.Google Scholar
  17. [17]
    Tano, Miyoshi, Kato, Oyama, Arnould and Bastian: Fuzzy Inference Software–FINEST: Overview and Application Examples, IEEE International Conference on Fuzzy Systems–FUZZ-IEEE’95, pp. 1051–1056, 1995.Google Scholar
  18. [18]
    Tano, Oyama and Arnould: Deep Combination of Fuzzy Inference and Neural Network in Fuzzy Inference Software–FINEST, International Journal of Fuzzy Set and Systems, Vol. 82 No. 2, pp. 151–160, 1996.CrossRefGoogle Scholar
  19. [19]
    Tano, Okamoto and Iwatani: New Design Concepts for the FLINS-Fuzzy Lingual System: Text-based and Fuzzy-centered Architectures, International Symposium on Methodologies for Intelligent Systems-ISMIS ‘83, pp. 285–294, 1993.Google Scholar
  20. [20]
    Tano, S., et. al. Three-layered Fuzzy Inference and Self-wondering Mechanism as Natural Language Processing Engine of FLINS, IEEE International Conference on Tools with Artificial Intelligence–TAI’94, pp. 212–218, 1994.Google Scholar

Copyright information

© Physica-Verlag Heidelberg 2001

Authors and Affiliations

  • Shun’ichi Tano
    • 1
  1. 1.Graduate School of Information SystemsUniversity of Electro-CommunicationsChofu, TokyoJapan

Personalised recommendations