Abstract
There have been many studies on the dense theorem of approximation by radial basis feedforword neural networks, and some approximation problems by Gaussian radial basis feedforward neural networks (GRBFNs) in some special function space have also been investigated. This paper considers the approximation by the GRBFNs in continuous function space. It is proved that the rate of approximation by GRNFNs with n d neurons to any continuous function f defined on a compact subset K ⊂ ℝd can be controlled by ω(f,n −1/2), where ω(f, t) is the modulus of continuity of the function f.
Similar content being viewed by others
References
Hartman, E. J., Keeler, J. D., Kowalski, J. M.: Layered neural networks with Gaussian hidden units as universal approximations. Neural Comput., 2, 210–215 (1990)
Park, J., Sandberg, I. W.: Universal approximation using radial-basis function networks. Neural Comput., 3, 246–257 (1991)
Park, J., Sandberg, I. W.: Approximation and radial-basis function networks. Neural Comput., 5, 305–316 (1993)
Chen, T. P., Chen, H.: Approximation capability to functions of several variables, nonlinear functionals and operators by radial basis function neural networks. IEEE Trans. Neural Netw., 6, 904–910 (1995)
Jiang, C. H., Chen, T. P.: Approximation problems of translation invariant operator in Sobolev space W m2 (R d). Chin. Annals Math., Ser. A, 20, 499–504 (1999)
Jiang, C. H., Chen, T. P.: Denseness of dilations and translations of a single function. Acta Mathematica Sinica, Chinese Series, 42, 495–500 (1999)
Liao, Y., Fang, S. C., Nuttle, H. L. W.: Relaxed conditions for radial-basis function networks to be universal approximators. Neural Netw., 16, 1019–1028 (2003)
Li, X.: On simultaneous approximations by radial basis function neural networks. Appl. Math. Comput., 95, 75–89 (1998)
Powell, M. J. D.: The theory of radial basis approximation. In: Advances in Numerical Analysis (ed. W. A. Light), Vol. 2, Oxford University Press, Oxford, 1990, 105–210
Light, W. A., Wayne, H. S. J.: Some aspects of radial basis function approximation. In: Approximation Theory, Spline Functions and Applications (S. P. Singh Ed.), Kluwer Academic, Dordrecht, 1995, 163–190
Schaback, R.: Error estimates and conditions numbers for radial basis functions interpolations. Adv. Comput. Math., 3, 251–264 (1995)
Schaback, R.: Approximation by radial basis functions with finitely many centers. Constr. Approx., 12, 331–340 (1996)
Bumann, M., Dyn, N., Levin, D.: On quasi-interpolation by radial basis functions with scattered centers. Constr. Approx., 11, 239–254 (1995)
Bejancu, A.: The uniform convergence of multivariate natural splines. DAMTP Technical Report, University of Cambridge, 1997
Bejancu, A.: On the accuracy of surface spline approximation and interpolation to bump functions. DAMTP Technical Report, University of Cambridge, 2000
Wendland, H.: Optimal approximation orders on L p for radial basis functions. East J. Approx., 6, 87–102 (2000)
Maiorov, V. E.: On best approximation of classes by radial functions. J. Approx. Theory, 120, 36–70 (2003)
Maiorov, V. E.: On lower bounds in radial basis approximation. Adv. Comput. Math., 22, 103–113 (2005)
Narcowich, F. J., Ward, J. D., Wendland, H.: Sobolev error estimates and a Bernstein inequality for scattered data interpolation via radial basis functions. Constr. Approx., 24, 175–186 (2006)
Buhman, M.: Radial basis functions. Acta Numer., 9, 1–38 (2000)
Li, X., Micchelli, C. A.: Approximation by radial bases and neural networks. Numer. Algorithms, 25, 241–262 (2000)
Kainen, P. C., Kårková, V., Sanguineti, M.: Complexity of Gaussian-radial-basis networks approximating smooth functions. J. Complexity, 25, 63–74 (2009)
Thomas, H., Amos, R.: Nonlinear approximation using Gaussian kernels. J. Funct. Anal., 259, 203–219 (2010)
Mhaskar, H. N.: When is approximation by Gaussian networks necessarily a linear process? Neural Netw., 17, 989–1001 (2004)
Ditzian, Z., Totik, V.: Moduli of Smothness, SSCM 9, Springer-Verlag, New York, 1987
Author information
Authors and Affiliations
Corresponding author
Additional information
Supported by National Natural Science Foundation of China (Grant Nos. 61101240 and 61272023) and the Zhejiang Provincial Natural Science Foundation of China (Grant No. Y6110117)
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Xie, T.F., Cao, F.L. The rate of approximation of Gaussian radial basis neural networks in continuous function space. Acta. Math. Sin.-English Ser. 29, 295–302 (2013). https://doi.org/10.1007/s10114-012-1369-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10114-012-1369-4
Keywords
- Gaussian radial basis feedforward neural networks
- approximation
- rate of convergence
- modulus of continuity