Abstract
We consider approximation of multidimensional functions by feedforward neural networks with one hidden layer of Sigmoidal units and a linear output. Under the Orthogonal polynomials basis and certain assumptions of activation functions in the neural network, the upper bounds on the degree of approximation are obtained in the class of functions considered in this paper. The order of approximation \(O(n^{-\frac{r}{d}}),\) d being dimension, n the number of hidden neurons, and r the natural number.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Cybenko, G.: Approximation by Superpositions of a Sigmoidal Function. Math. Contr. Signals. Syst. 2, 303–314 (1989)
Ito, Y.: Approximation of Continuous Functions on Rd by Linear Combination of Shifted Rotations of Sigmoid Function with and without Scaling Neural Networks. Neural Networks 5, 105–115 (1992)
Chen, T.P., Chen, H.: Approximation Capability to Functions of Several Variables, Nonlinear Functions, and Operators by Radial Function Neural Networks. IEEE Trans. Neural Networks 6, 904–910 (1995)
Barron, A.R.: Universal Approximation Bound for Superpositions of a Sigmoidal Function. IEEE Trans. Inform. Theory 39, 930–945 (1993)
Mhaskar, H.N.: Neural Networks for Optimal Approximation for Smooth and Analytic Functions. Neural Comput. 8, 164–177 (1996)
Maiorov, V., Meir, R.S.: Approximation Bounds for Smooth Functions in C(Rd) by Neural and Mixture Networks. IEEE Trans. Neural Networks 9, 969–978 (1998)
Burger, M., Neubauer, A.: Error Bounds for Approximation with Neurnal Networks. J. Approx. Theory. 112, 235–250 (2001)
Kurkova, V., Sanguineti, M.: Comparison of Worst Case Errors in Linear and Neural Network Approximation. IEEE Trans. Inform. Theory 48, 264–275 (2002)
Wang, J.L., Sheng, B.H., Zhou, S.P.: On Approximation by Non-periodic Neural and Translation Networks in Lp ω Spaces. ACTA Mathematica Sinica (in chinese) 46, 65–74 (2003)
Timan, A.F.: Theory of Approximation of Functions of a Real Variable. Macmillan, New York (1963)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wang, J., Xu, Z., Xu, W. (2004). Approximation Bounds by Neural Networks in L ω p [-4pt]. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_1
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive