Constructive Approximation by Superposition of Sigmoidal Functions

In this paper, a constructive theory is developed for approximating func- tions of one or more variables by superposition of sigmoidal functions. This is done in the uniform norm as well as in the L p norm. Results for the simultaneous approx- imation, with the same order of accuracy, of a function and its derivatives (whenever these exist), are obtained. The relation with neural networks and radial basis func- tions approximations is discussed. Numerical examples are given for the purpose of illustration.

[1]  L. Jones.  Constructive approximations for neural networks by sigmoidal functions , 1990, Proc. IEEE.

[2]  Jooyoung Park,et al.  Universal Approximation Using Radial-Basis-Function Networks , 1991, Neural Computation.

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

[4]  Tianping Chen,et al.  A Constructive Proof and An Extension of Cybenko’s Approximation Theorem , 1992 .

[5]  Burkhard Lenze,et al.  Constructive Multivariate Approximation with Sigmoidal Functions and Applications to Neural Networks , 1992 .

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

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

[8]  Chen Debao.  Degree of approximation by superpositions of a sigmoidal function , 1993, Approximation Theory and its Applications.

[9]  Yuan Xu,et al.  Univariant approximation by superpositions of a sigmoidal function , 1993 .

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

[11]  Xin Li,et al.  Simultaneous approximations of multivariate functions and their derivatives by neural networks with one hidden layer , 1996, Neurocomputing.

[12]  Xin Li,et al.  On simultaneous approximations by radial basis function neural networks , 1998, Appl. Math. Comput..

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

[14]  Bum Il Hong,et al.  Approximation order to a function in Image(Image) by superposition of a sigmoidal function , 2002, Appl. Math. Lett..

[15]  G. Lewicki,et al.  Approximation by Superpositions of a Sigmoidal Function , 2003 .

[16]  Grzegorz Lewicki,et al.  Approximation of functions of finite variation by superpositions of a Sigmoidal function , 2004, Appl. Math. Lett..

[17]  Xin Li,et al.  Approximation by radial bases and neural networks , 2004, Numerical Algorithms.

[18]  Zongben Xu,et al.  Simultaneous Lp-approximation order for neural networks , 2005, Neural Networks.

[19]  Ismo Strandén,et al.  Estimation of non-linear growth models by linearization: a simulation study using a Gompertz function , 2005, Genetics Selection Evolution.

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

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

[22]  E. S. Chumerina.  Choice of optimal strategy of tumor chemotherapy in Gompertz model , 2009 .

[23]  Rui Zhang,et al.  The errors of approximation for feedforward neural networks in the Lp metric , 2009, Math. Comput. Model..

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

[25]  Feilong Cao,et al.  Interpolation and rates of convergence for a class of neural networks , 2009 .

[26]  Virginia Giorno,et al.  On the First Exit Time Problem for a Gompertz-Type Tumor Growth , 2009, EUROCAST.

[27]  H. Brezis.  Functional Analysis, Sobolev Spaces and Partial Differential Equations , 2010 .