Convergence rates for a class of neural networks with logarithmic function

The aim of this paper is to estimate the approximation error which results from the method of feedforward neural networks (FNNs) with logarithmic sigmoidal function s(x) = (1+e−x)−1. By means of an extending function approach, a class of FNNs with single hidden layer and the active function s(x) is constructed to approximate the continuous function defined on a compact interval. By using the modulus of continuity of function as metric, the rate of convergence of the FNNs is estimated. Also, a numerical examples for illustrating the theoretical results is given.

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

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

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

[4]  P. Heywood.  Trigonometric Series , 1968, Nature.

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

[6]  Nahmwoo Hahm,et al.  Degree of approximation by neural networks , 1996 .

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

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

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

[10]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

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

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

[13]  XUZongben,et al.  The essential order of approximation for neural networks , 2004 .

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

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

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

[17]  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.

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

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

[20]  Halbert White,et al.  On learning the derivatives of an unknown mapping with multilayer feedforward networks , 1992, Neural Networks.

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

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

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

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