Can neural nets be universal approximators for fuzzy functions?

We first argue that the extension principle is too computationally involved to be an efficient way for a computer to evaluate fuzzy functions. We then suggest using /spl alpha/-cuts and interval arithmetic to compute the values of fuzzy functions. Using this method of computing fuzzy functions, we then show that neural nets are universal approximators for (computable) fuzzy functions, when we only input non-negative, or non-positive, fuzzy numbers.

[1]  James J. Buckley,et al.  Neural net solutions to fuzzy problems: The quadratic equation , 1997, Fuzzy Sets Syst..

[2]  Shigeo Abe,et al.  Neural Networks and Fuzzy Systems , 1996, Springer US.

[3]  Francisco Herrera,et al.  Genetic Algorithms and Soft Computing , 1996 .

[4]  J. Buckley,et al.  Backpropagation and genetic algorithms for training fuzzy neural nets , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[5]  James J. Buckley,et al.  Neural net solutions to fuzzy linear programming , 1996, Proceedings of IEEE 5th International Fuzzy Systems.

[6]  Russell Beale,et al.  Handbook of Neural Computation , 1996 .

[7]  J. Buckley,et al.  Solving fuzzy equations using neural nets , 1995, Proceedings of 3rd International Symposium on Uncertainty Modeling and Analysis and Annual Conference of the North American Fuzzy Information Processing Society.

[8]  Kevin D. Reilly,et al.  Genetic learning algorithms for fuzzy neural nets , 1994, Proceedings of 1994 IEEE 3rd International Fuzzy Systems Conference.

[9]  Stephen T. Welstead,et al.  Neural network and fuzzy logic applications in C/C++ , 1994, Wiley professional computing.

[10]  James J. Buckley,et al.  Can fuzzy neural nets approximate continuous fuzzy functions , 1994 .

[11]  James J. Buckley,et al.  Are regular fuzzy neural nets universal approximators? , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[12]  Halbert White,et al.  Artificial Neural Networks: Approximation and Learning Theory , 1992 .

[13]  James J. Buckley,et al.  On using a-cuts to evaluate fuzzy equations , 1990 .

[14]  M. Puri,et al.  Differentials of fuzzy functions , 1983 .

[15]  James J. Buckley,et al.  Neural Net Solutions to Systems of Fuzzy Linear Equations , 1998 .

[16]  Siegfried Gottwald,et al.  Fuzzy Sets and Fuzzy Logic , 1993 .

[17]  A. Neumaier.  Interval methods for systems of equations , 1990 .

[18]  Ramon E. Moore.  Methods and applications of interval analysis , 1979, SIAM studies in applied mathematics.