Korean Journal of Mathematics

The Kangwon-Kyungki Mathematical Society (강원경기수학회)
권호 표지
DOI QR코드

DOI QR Code

CONSTRUCTIVE APPROXIMATION BY NEURAL NETWORKS WITH POSITIVE INTEGER WEIGHTS

  • HONG, BUM IL (Department of Applied Mathematics and The Institute of Natural Sciences Kyung Hee University) ;
  • HAHM, NAHMWOO (Department of Mathematics Incheon National University)
  • Received : 2015.06.29
  • Accepted : 2015.07.31
  • Published : 2015.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we study a constructive approximation by neural networks with positive integer weights. Like neural networks with real weights, we show that neural networks with positive integer weights can even approximate arbitrarily well for any continuous functions on compact subsets of $\mathbb{R}$. We give a numerical result to justify our theoretical result.

Keywords

References

  1. D. Chen, Degree of Approximation by Superpositions of a Sigmoidal Function, Approx. Theory and Appl., 9 (3) (1993), 17-28.
  2. C. K. Chui and X. Li, Approximation by Ridge Functions and Neural Networks with One Hidden Layer, J. Approx. Theory, 70 (1992), 17-28.
  3. N. Hahm and B. I. Hong, Degree of Approximation by Periodic Neural Networks, Korean J. Math., 22 (2) (2014), 307-315. https://doi.org/10.11568/kjm.2014.22.2.307
  4. N. Hahm and B. I. Hong, The Capability of Localized Neural Network Approximation, Honam Math. J., 34 (3) (2012), 341-349. https://doi.org/10.5831/HMJ.2012.34.3.341
  5. B. L. Kalman and S. C. Kwasny, Why Tanh : Choosing a Sigmoidal Function, Lect. Notes Comput. Sc., 600 (1995), 303-312.
  6. J. Killian and H. T. Siegelmann, The Dynamic Universality of Sigmoidal Neural Networks, Inform. Comput., 128 (1996), 48-56. https://doi.org/10.1006/inco.1996.0062
  7. M. Leshno, V. Y. Lin, A. Pinkus and S. Schoken, Multilayer Feedforward Networks with a Nonpolynomial Activation Function Can Approximate Any Function, Neural Networks, 7 (1995), 861-867.
  8. G. Lewicki and G. Marino, Approximation of Functions of Finite Variation by Superpositions of a Sigmoidal Function, Appl. Math. Lett. 17, (2004), 1147-1152. https://doi.org/10.1016/j.aml.2003.11.006
  9. M. V. Medvedeva, On Sigmoidal Functions, Mosc. Univ. Math. Bull., 53 (1) (1998), 16-19.

Cited by

  1. Measure Theoretic Results for Approximation by Neural Networks with Limited Weights vol.38, pp.7, 2017, https://doi.org/10.1080/01630563.2016.1254654