Orthogonal RBF neural network approximation

Andras, Peter

Abstract

The approximation properties of the RBF neural networks are investigated in this paper. A new approach is proposed, which is based on approximations with orthogonal combinations of functions. An orthogonalization framework is presented for the Gaussian basis functions. It is shown how to use this framework to design efficient neural networks. Using this method we can estimate the necessary number of the hidden nodes, and we can evaluate how appropriate the use of the Gaussian RBF networks is for the approximation of a given function.

Citation

Andras, P. (1999). Orthogonal RBF neural network approximation. Neural Processing Letters, 9, 141-151. https://doi.org/10.1023/A%3A1018621308457

• Journal Article Type: Article
• Publication Date: 1999-04
• Deposit Date: Nov 4, 2021
• Journal: Neural Processing Letters
• Print ISSN: 1370-4621
• Electronic ISSN: 1573-773X
• Publisher: Springer
• Peer Reviewed: Peer Reviewed
• Volume: 9
• Pages: 141-151
• DOI: https://doi.org/10.1023/A%3A1018621308457
• Keywords: approximation, neural network design, orthogonalization, RBF neural networks, spectral analysis
• Public URL: http://researchrepository.napier.ac.uk/Output/2808988