Approximation properties of fuzzy systems for smooth functions and their first-order derivative

The problem of simultaneous approximations of a given function and its derivatives, has been addressed frequently in pure and applied mathematics. In pure mathematics, Bernstein polynomials get their importance from the fact that they provide simultaneous approximation of a function and its derivatives. In neural network theory, feedforward networks were shown to be universal approximators of an unknown function and its derivatives. In this paper, we consider fuzzy logic systems with the membership functions of each input variables are chosen as the translations and dilations of one appropriately fixed function. We prove, by a constructive proof based on discretization of the convolution operator, that under certain conditions made on the input variables membership functions, fuzzy logic systems of Sugeno type are universal approximators of a given function and its derivatives.

[1]  Adel M. Alimi,et al.  Evolutionary Computation for the Recognition of On-Line Cursive Handwriting , 2002 .

[2]  L X Wang,et al.  Fuzzy basis functions, universal approximation, and orthogonal least-squares learning , 1992, IEEE Trans. Neural Networks.

[3]  Bart Kosko,et al.  Fuzzy Systems as Universal Approximators , 1994, IEEE Trans. Computers.

[4]  Adel M. Alimi,et al.  Beta fuzzy logic systems approximation properties in the mimo case , 2003 .

[5]  W. Pedrycz.  Why triangular membership functions , 1994 .

[6]  B. Bouchon-Meunier,et al.  Sur l'approximation universelle des systèmes flous , 1996 .

[7]  Hao Ying,et al.  Constructing nonlinear variable gain controllers via the Takagi-Sugeno fuzzy control , 1998, IEEE Trans. Fuzzy Syst..

[8]  Manuel Landajo,et al.  A note on smooth approximation capabilities of fuzzy systems , 2001, IEEE Trans. Fuzzy Syst..

[9]  J. Buckley.  Sugeno type controllers are universal controllers , 1993 .

[10]  Hao Ying,et al.  General SISO Takagi-Sugeno fuzzy systems with linear rule consequent are universal approximators , 1998, IEEE Trans. Fuzzy Syst..

[11]  Xiao-Jun Zeng,et al.  Approximation theory of fuzzy systems-SISO case , 1994, IEEE Trans. Fuzzy Syst..

[12]  M. Newman,et al.  Interpolation and approximation , 1965 .

[13]  Michael I. Jordan,et al.  Generic constraints on underspecified target trajectories , 1989, International 1989 Joint Conference on Neural Networks.

[14]  Fengming Song,et al.  Constructive theory for fuzzy systems , 1997, Fuzzy Sets Syst..

[15]  Brian Birge,et al.  PSOt - a particle swarm optimization toolbox for use with Matlab , 2003, Proceedings of the 2003 IEEE Swarm Intelligence Symposium. SIS'03 (Cat. No.03EX706).

[16]  Chi-Hsu Wang,et al.  Fuzzy B-spline membership function (BMF) and its applications in fuzzy-neural control , 1995, IEEE Trans. Syst. Man Cybern..

[17]  Zhi-Hong Mao,et al.  Approximation capability of fuzzy systems using translations and dilations of one fixed function as membership functions , 1997, IEEE Trans. Fuzzy Syst..

[18]  M. J. Box,et al.  Non-linear optimization techniques; , 1969 .

[19]  A. Ullah.  Non-parametric estimation of econometric functionals , 1988 .

[20]  Chuen-Chien Lee.  FUZZY LOGIC CONTROL SYSTEMS: FUZZY LOGIC CONTROLLER - PART I , 1990 .

[21]  Xiao-Jun Zeng,et al.  Approximation theory of fuzzy systems-MIMO case , 1995, IEEE Trans. Fuzzy Syst..

[22]  Kurt Hornik,et al.  Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks , 1990, Neural Networks.

[23]  Hrishikesh D. Vinod,et al.  Flexible Production Function Estimation by Nonparametric Kernel Estimators , 1987 .

[24]  R. E. Dominy,et al.  A general explanation and interrogation system for neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[25]  Adel M. Alimi,et al.  A Genetic Designed Beta Basis Function Neural Network for Approximating Multi-Variables Functions , 2001 .

[26]  I. Badawi.  An elasticity can be estimated consistently without a priori knowledge of functional form , 1983 .

[27]  Vladik Kreinovich,et al.  Fuzzy systems are universal approximators for a smooth function and its derivatives , 2000, Int. J. Intell. Syst..