Journal of applied mathematics & informatics

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

NOTES ON EXTENDED NEURAL NETWORK APPROXIMATION

  • Hahm, Nahm-Woo (Institute of Natural Sciences Kyung Hee University) ;
  • Hong, Bum-Il (Dept. of Math and Institute of Natural Sciences Kyung Hee University) ;
  • Choi, Sung-Hee (Division of Information and Computer Science Sun Moon University)
  • Published : 1998.09.01

⟨ Previous Next ⟩

Abstract

In this paper we prove that any continuous function on a bounded closed interval of can be approximated by the superposition of a bounded sigmoidal function with a fixed weight. In addition we show that any continuous function over $\mathbb{R}$ which vanishes at infinity can be approximated by the superposition f a bounded sigmoidal function with a weighted norm. Our proof is constructive.

Keywords

References

  1. IEEE Trans. Informatin Theory v.39 Universal Approximation Bounds for Superposition of a Sigmoidal Function A.R.Barron
  2. IEEE Trans. Neural Networks v.6 Universal Approximation to Nonlinear Operators by Neural Networks with Arbitrary Activation Functions and Its Application to Dynamical Systems T.Chen;H.Chen
  3. IEEE Trans. Neural Networks v.6 Approximation Capability to Functions of Several Variables, Nonlinear Functionals, and Operators by Radial Basis Function Neural Networks T.Chen;H.Chen
  4. J. Approx. Theory v.70 Approximation by Ridge Functions and Neural Networks with One Hidden Layer C.K.Chui;X.Li
  5. Manuscripta Mathematica v.63 Optimal Nonlinear Approximation R.Devore;R.Howard;C.A.Micchelli
  6. First Coures in Functional Analysis C.Goffman;G.Pedrick
  7. PH.D.Dissertation Univ. of Texas at Austin Degree of Approximation by Neural Networks N.Hahm
  8. Neural Networks v.4 Approximation of Functions on a Compact Set by Finite Sums of a Sigmoidal Function Without Scaling Y.Ito
  9. Approximation of Functions G.G.Lorentz
  10. Advances in Applied Mathematics v.16 Degree of Approximation by Neural and Translation Networks with a Single Hidden Layer H.N.Mhaskar;C.A.Michelli
  11. Neural Computation v.3 Universal Approximation Using radial Basis Function Networks J.Park;I.W.Sandberg
  12. Theory of Approximation of Functions of a Real Varable A.F.Timan