Multivariate sigmoidal neural network approximation

Here we study the multivariate quantitative constructive approximation of real and complex valued continuous multivariate functions on a box or RN, N∈N, by the multivariate quasi-interpolation sigmoidal neural network operators. The "right" operators for our goal are fully and precisely described. This approximation is derived by establishing multidimensional Jackson type inequalities involving the multivariate modulus of continuity of the engaged function or its high order partial derivatives. Our multivariate operators are defined by using a multidimensional density function induced by the logarithmic sigmoidal function. The approximations are pointwise and uniform. The related feed-forward neural network is with one hidden layer.

[1]  Y. Makovoz.  Uniform Approximation by Neural Networks , 1998 .

[2]  C. Micchelli,et al.  Degree of Approximation by Neural and Translation Networks with a Single Hidden Layer , 1995 .

[3]  Feilong Cao,et al.  The approximation operators with sigmoidal functions , 2009, Comput. Math. Appl..

[4]  Hong Chen,et al.  Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems , 1995, IEEE Trans. Neural Networks.

[5]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[6]  C. Chui,et al.  Approximation by ridge functions and neural networks with one hidden layer , 1992 .

[7]  Andrew R. Barron,et al.  Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[8]  Shin Suzuki,et al.  Constructive function-approximation by three-layer artificial neural networks , 1998, Neural Networks.

[9]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[10]  Robert F. Stengel,et al.  Smooth function approximation using neural networks , 2005, IEEE Transactions on Neural Networks.

[11]  Bum Il Hong,et al.  An approximation by neural networkswith a fixed weight , 2004 .

[12]  C. Micchelli,et al.  Approximation by superposition of sigmoidal and radial basis functions , 1992 .

[13]  Natali Hritonenko,et al.  Mathematical Modeling in Economics, Ecology and the Environment , 1999 .

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

[15]  Zongben Xu,et al.  The essential order of approximation for neural networks , 2004, Science in China Series F: Information Sciences.

[16]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[17]  Allan Pinkus,et al.  Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[18]  George A. Anastassiou.  Rate of Convergence of Basic Multivariate Neural Network Operators to the Unit , 2000 .

[19]  J. Rubio,et al.  Optimal shape design for a frictionless contact problem , 1992 .

[20]  Zongben Xu,et al.  The estimate for approximation error of neural networks: A constructive approach , 2008, Neurocomputing.

[21]  F. Brauer,et al.  Mathematical Models in Population Biology and Epidemiology , 2001 .

[22]  George A. Anastassiou,et al.  Rate of Convergence of Basic Neural Network Operators to the Unit-Univariate Case , 1997 .

[23]  Ron Meir,et al.  Approximation bounds for smooth functions in C(Rd) by neural and mixture networks , 1998, IEEE Trans. Neural Networks.

[24]  G. Lorentz.  Approximation of Functions , 1966 .