Journal of applied mathematics & informatics

The Korean Society for Computational and Applied Mathematics (한국전산응용수학회)
권호 표지

APPROXIMATION ORDER TO A FUNCTION IN $C^1$[0, 1] AND ITS DERIVATIVE BY A FEEDFOWARD NEURAL NETWORK

  • Published : 2009.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

We study the neural network approximation to a function in $C^1$[0, 1] and its derivative. In [3], we used even trigonometric polynomials in order to get an approximation order to a function in $L_p$ space. In this paper, we show the simultaneous approximation order to a function in $C^1$[0, 1] using a Bernstein polynomial and a feedforward neural network. Our proofs are constructive.

Keywords

References

  1. Gallant and H. White, On Learning the Derivatives of an Unknown Mapping with Multi-layer feedforward Networks, Neural Networks 5(1992), 129-138. https://doi.org/10.1016/S0893-6080(05)80011-5
  2. B. I. Hong and N. Hahm, Approximation Order to a Function in C(R) by Superposition of a Sigmoidal Function, Applied Mathematics Letters 15(2002), 591 - 597. https://doi.org/10.1016/S0893-9659(02)80011-8
  3. Applied Mathematics Letters N. Hahm and B. I. Hong, Approximation Order to a Function in Lp Space by Generalized Translation Networks, Honam Mathematical Journal 28(2006), 125-133.
  4. Fengjun Li and Zongben Xu, The Estimation of Simultaneous Approximation Order for Neural Networks, Chaos Solutions and Fractals 36(2008), 572-580. https://doi.org/10.1016/j.chaos.2007.01.020
  5. X. Li, Simultaneous Approximation of a Multivariate Functions and Their Derivatives by Neural Networks with One Hidden Layer, Neurocomputing 12(1996), 327-343. https://doi.org/10.1016/0925-2312(95)00070-4
  6. G. G. Lorentz, Bernstein Polynomials, Chelsea, (1986).
  7. H. N. Mhaskar and N. Hahm, Neural Networks for Functional Approximation and System Identification, Neural Computation 9(1997), 143-159. https://doi.org/10.1162/neco.1997.9.1.143
  8. I. P. Natanson, Constructive Function Theory, Frederick Ungar Publ., (1964).