Abstract
For the multivariate continuous function, using constructive feedforward \( L^{2} (\mathbb{R}) \) radial basis function (RBF) neural network, we prove that a \( L^{2} (\mathbb{R}) \) RBF neural network with n + 1 hidden neurons can interpolate n + 1 multivariate samples with zero error. Then, we prove that the \( L^{2} (\mathbb{R}) \) RBF neural network can uniformly approximate any continuous multivariate function with arbitrary precision. The correctness and effectiveness are verified through eight numeric experiments.
Similar content being viewed by others
References
Sontag ED (1992) Feedforward nets for interpolation and classification. J Comp Syst Sci 45(1992):20–48
Guo-Wei Y, Shou-Jue W, Qing-Xu Y (2007) Research of fractional linear neural network and its ability for nonlinear approach. Chin J Comput 30(2):189–199
Chui CK, Li X, Mhaskar HN (1994) Neural networks for localized approximation. Math Comput 63:607–623
Chui CK, Li X, Mhaskar HN (1996) Limitations of the approximation capabilities of neural networks with one hidden layer. Adv Comput Math 5:233–243
Llanas B, Sainz FJ (2006) Constructive approximate interpolation by neural networks. J Comput Appl Math 188:283–308
Xuli H, Muzhou H (2007) Neural networks for approximation of real functions with the Gaussion functions. Proceedings of the third international conference on natural computation. IEEE Computer Society Press, Los Alamitos, August, 2007, vol 1, P601–P605
Xu ZB, Cao FL (2005) Simultaneous Lp-approximation order for neural networks. Neural Netw 18:914–923
Muzhou H, Xuli H (2010) Constructive approximation to multivariate function bydecay RBF neural network. IEEE Trans Neural Netw 21(9):1515–1523
Bao-tong M, Fa-lai C (2001) Applications of radius basis function neural networks in scattered data interpolation. J Univ Sci Technol China 31(2):136–142
Xuli H, Muzhou H (2008) Quasi-interpolation for data fitting by the radial basis functions. Lecture Notes in Computer Science, LNCS 4975, pp 541–547
Huang GB, Saratchandran P, Sundararajan N (2005) A generalized growing and pruning RBF (GGAP-RBF) neural network for function approximation. IEEE Trans Neural Netw 16(1):57–67
Duy NM, Cong TT (2003) Approximation of function and its derivatives using radial basis function networks. Appl Math Model 27:197–220
Gholizadeh S, Salajegheh E, Torkzadeh P (2008) Structural optimization with frequency constraints by genetic algorithm using wavelet radial basis function neural network. J Sound Vib 312:316–331
Mhaskar HN, ChA Michelli (1992) Approximation by superposition of sigmoidal and radial basis functions. Adv Appl Math 13:350–373
Ding XH, Deng SX, Li LL (2002) Algorithm of wavelet RBF neural network. Proceedings of the second international symposium on instrumentation science and technology, vol 3, pp 756–760
Chui CK (1994) An introduction to wavelets. Academic Press, Boston
Kai-ping Y, Jing-xiang1 Z, Bing-yuan Y (2000) Study on performance and application of the wavelet function. J Harbin Inst Technol 32(2):36–39 (in Chinese)
Delyon B, Juditsky A, Benveniste A (1995) Accuracy analysis for wavelet approximations. IEEE Trans Neural Netw 6:332–348
Acknowledgments
This work was supported by the Natural Science Foundation of China under Grants 10871208, 60970097 and 70871122, and was supported by the ZNDXQYYJJH under grant No. 2010QZZD015.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Muzhou, H., Xuli, H. Multivariate numerical approximation using constructive \( L^{2} (\mathbb{R}) \) RBF neural network. Neural Comput & Applic 21, 25–34 (2012). https://doi.org/10.1007/s00521-011-0604-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0604-8