In this paper, we investigate the universal approximation property of Radial Basis Function (RBF) networks. We show that RBFs are not required to be integrable for the REF networks to be universal approximators. Instead, RBF networks can uniformly approximate any continuous function on a compact set provided that the radial basis activation function is continuous almost everywhere, locally essentially bounded, and not a polynomial. The approximation is also discussed. Some experimental results are reported to illustrate our findings. © 2012 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Nong, J. (2012). Conditions for RBF neural networks to universal approximation and numerical experiments. In Communications in Computer and Information Science (Vol. 289 CCIS, pp. 299–308). https://doi.org/10.1007/978-3-642-31968-6_36
Mendeley helps you to discover research relevant for your work.