A novel fuzzy neural network and its approximation capability

  • Liu Puyin 
Scientific Papers


The polygonal fuzzy numbers are employed to define a new fuzzy arithmetic. A novel extension principle is also introduced for the increasing function σ: ℝ → ℝ. Thus it is convenient to construct a fuzzy neural network model with succinct learning algorithms. Such a system possesses some universal approximation capabilities, that is, the corresponding three layer feedforward fuzzy neural networks can be universal approximators to the continuously increasing fuzzy functions.


n polygonal fuzzy number fuzzy neural network universal approximator fuzzy arithmetic 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Stinchcombe, M. B., Neural network approximation of continuous functionals and continuous functions on compactifications, Neural Networks, 1999, 12: 467.CrossRefGoogle Scholar
  2. 2.
    Scarselli, F., Tsoi, A. C., Universal approximation using feedforward neural networks: a survey of some existing methods and some new results, Neural Networks, 1998, 11: 15.CrossRefGoogle Scholar
  3. 3.
    Chen, T. P., Chen, H., Liu, R. W., Approximation using capability in C(Open image in new window) by multilayer feedforward networks and related problems, IEEE Trans. on Neural Networks, 1995, 6: 25.MATHCrossRefGoogle Scholar
  4. 4.
    Chen Tianping, Liang Yuan, Output capability of neural network to dynomical system defined in whole space, Science in China (in Chinese), Ser. E, 1998, 28(4): 338.MathSciNetGoogle Scholar
  5. 5.
    Buckley, J. J., Hayashi, Y., Can neural nets be universal approximators for fuzzy functions? Fuzzy Sets and Systems, 1999, 101: 323.MATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Buckley, J. J., Hayashi, Y., Can fuzzy neural nets approximate continuous fuzzy functions, Fuzzy Sets and Systems, 1994, 61: 43.MATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Feuring, T., Lippe, W. M., The fuzzy neural network approximation lemma, Fuzzy Sets and Systems, 1999, 102: 227.MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Liu Puyin, Wang Huaxing, Universal approximation of a class of fuzzy valued functions by regular fuzzy neural networks, Acta Elect. Sinica(in Chinese), 1997, 25(11): 41.Google Scholar
  9. 9.
    Liu Puyin, Wang Hao, Approximation capability of regular fuzzy neural networks to continuous fuzzy functions, Science in China, Ser. E, 1999, 42(2): 175.MATHCrossRefGoogle Scholar
  10. 10.
    Liu Puyin, Analyses of regular fuzzy neural networks for approximation capabilities, Fuzzy Sets and Systems, 2000, 114: 329.MATHCrossRefMathSciNetGoogle Scholar
  11. 11.
    Diamond, P., Kloeden, P., Metric Spaces of Fuzzy Sets, Singapore: World Scientific Press, 1994.MATHGoogle Scholar
  12. 12.
    Nguyen, H. T., A note on the extension principle for fuzzy sets, J. Math. Anal. Appl., 1976, 64(2): 369.CrossRefGoogle Scholar
  13. 13.
    Mao Zhihong, Zhang Xuefeng, Li Yeda, Research on fuzzy system as universal approximator, Science in China (in Chinese), Ser. E, 1997, 27(4): 362.Google Scholar
  14. 14.
    Ishibuchi, H., Kwon, K., Tanaka, H., A learning algorithm of fuzzy neural networks with triangular fuzzy weights, Fuzzy Sets and Systems, 1995, 71: 277.CrossRefGoogle Scholar

Copyright information

© Science in China Press 2001

Authors and Affiliations

  • Liu Puyin 
    • 1
  1. 1.Department of MathematicsBeijing Normal UniversityBeijingChina

Personalised recommendations