Fuzzy logic systems are equivalent to feedforward neural networks



Fuzzy logic systems and feedforward neural networks are equivalent in essence. First, interpolation representations of fuzzy logic systems are introduced and several important conclusions are given. Then three important kinds of neural networks are defined, i. e. linear neural networks, rectangle wave neural networks and nonlinear neural networks. Then it is proved that nonlinear neural networks can be represented by rectangle wave neural networks. Based on the results mentioned above, the equivalence between fuzzy logic systems and feedforward neural networks is proved, which will be very useful for theoretical research or applications on fuzzy logic systems or neural networks by means of combining fuzzy logic systems with neural networks.


fuzzy logic systems neural networks feedforward neural networks interpolation representation rectangle wave neural networks nonlinear neural networks linear neural networks 


  1. 1.
    Li Hongxing, The mathematical essence of fuzzy controls and fine fuzzy controllers, in Advances in Machine Intelligence and Soft-Computing (ed. Paul, P. Wang), Vol. IV, Durham: Bookwright Press, 1997, 55–74.Google Scholar
  2. 2.
    Li Hongxing, Interpolation mechanism of fuzzy control, Science in China, Ser. E, 1998, 41(3): 312.MATHCrossRefGoogle Scholar
  3. 3.
    Li Hongxing, Multifactorial functions in fuzzy sets theory, Fuzzy Sets and Systems, 1990, 35: 69.MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Wang Goujun, On the logic foundation of fuzzy reasoning, Lecture Notes in Fuzzy Mathematics and Computer Science, Omaha: Creighton Univ., 1997, 4: 1.Google Scholar
  5. 5.
    Zhang Naiyao, Structure analysis of typical fuzzy controllers, Fuzzy Systems and Mathematics (in Chinese), 1997, 11 (2): 10.Google Scholar
  6. 6.
    Mizumoto, M., The improvement of fuzzy control algorithm, part 4: (+, ·)-centroid algorithm, Proceedings of Fuzzy Systems Theory (in Japanese), 1990, 6: 9.Google Scholar
  7. 7.
    Wang, P. Z., Li Hongxing, Fuzzy Information Processing and Fuzzy Computers, New York, Beijing: Science Press, 1997.Google Scholar
  8. 8.
    Terano, T., Asai, K., Sugeno, M., Fuzzy Systems Theory and Its Applications, Tokyo: Academic Press, Inc, 1992.MATHGoogle Scholar
  9. 9.
    Sugeno, M., Fuzzy Control (in Japanese), Tokyo: Japane Industry Press, 1988.Google Scholar
  10. 10.
    Takagi, T., Sugeno, M., Fuzzy identification of systems and its applications to modeling and control, IEEE Trans. Syst. Man and Cybern., 1985, SMC-15: 1.Google Scholar
  11. 11.
    Pao, Y. H., Adaptive Pattern Recognition and Neural Networks, New York: Addison-Wesley Publishing Company, Inc., 1989.MATHGoogle Scholar
  12. 12.
    Kosko, B., Neural Networks and Fuzzy Systems, Englewood Cliffs, New Jersey: Prentice-Hall, Inc., 1992.MATHGoogle Scholar
  13. 13.
    Brown, M., Harris, C., Neurofuzzy Adaptive Modelling and Control, New York: Prentice Hall, 1994.Google Scholar

Copyright information

© Science in China Press 2000

Authors and Affiliations

  1. 1.Department of MathematicsBeijing Normal UniversityBeijingChina

Personalised recommendations