Hostname: page-component-78c5997874-94fs2 Total loading time: 0 Render date: 2024-11-05T23:23:31.622Z Has data issue: false hasContentIssue false
  • English
  • Français

Extension of localised approximation by neural networks

Published online by Cambridge University Press:  17 April 2009

Nahmwoo Hahm  and
Bum Il Hong
Nahmwoo Hahm
Affiliation:
Institute of Natural Sciences, Kyung Hee University, Yongin, Kyunggi 449–701, Korea e-mail: [email protected]
Bum Il Hong
Affiliation:
Department of Mathematics, Kyung Hee Univeristy, Yongin, Kyunggi 449–701, Korea e-mail: [email protected]
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

We prove generalised results for localised approximation by generalised translation networks. We also show the relationship between the minimum number of neurons in the generalised translation networks with one hidden layer and the desired accuracy where the target functions are in a subset V1, p ([−1, 1]s) of the Sobolev space W1, p([−1, 1]s).

Type
Research Article
Information
Bulletin of the Australian Mathematical Society , Volume 59 , Issue 1 , February 1999 , pp. 121 - 131
Copyright
Copyright © Australian Mathematical Society 1999

References

[1]Barron, A.R., ‘Universal approximation bounds for superposition of a Sigmoidal function’, IEEE Trans. Inform. Theory 39 (1993), 930–945.CrossRefGoogle Scholar
[2]Chui, C.K. and Li, X., ‘Approximation by Ridge functions and neural networks with one hidden layer’, J. Approx. Theory 70 (1992), 131–141.CrossRefGoogle Scholar
[3]Chui, C.K., Li, X. and Mhaskar, H.N., ‘Localized approximation by neural networks’, Math. Comp. 63 (1994), 607–623.CrossRefGoogle Scholar
[4]Chui, C.K., Li, X. and Mhaskar, H.N., ‘Limitations of the approximation capabilities of neural networks with one hidden layer’, Adv. Comput. Math. 5 (1996), 233–243.CrossRefGoogle Scholar
[5]Leshno, M., Lin, V., Pinkus, A. and Schocken, S., ‘Multilayer feedforward networks with a nonpolynomial activation function can approximate any function’, Neural Networks 6 (1993), 861–867.CrossRefGoogle Scholar
[6]Mhaskar, H.N., ‘Approximation properties of a multilayered feedforward artificial neural network’, Adv. Comput. Math. 1 (1993), 61–80.CrossRefGoogle Scholar
[7]Mhaskar, H.N., ‘Neural networks for optimal approximation of smooth and analytic functions’, Neural Computation 8 (1996), 164–177.CrossRefGoogle Scholar
[8]Mhaskar, H.N. and Hahm, N., ‘Neural networks for functional approximation and system identification’, Neural Computation 9 (1997), 143–159.CrossRefGoogle ScholarPubMed
[9]Stein, E.M., Singular integrals and differentiability properties of functions (Princeton Univ. Press, Princeton, 1970).Google Scholar