Format

Send to

Choose Destination
Neural Netw. 2003 Sep;16(7):1019-28.

Relaxed conditions for radial-basis function networks to be universal approximators.

Author information

1
Operations Research and Industrial Engineering, North Carolina State University, Raleigh, NC 27695-7906, USA. yliao2@eos.ncsu.edu

Abstract

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 in L(p)(micro)(1 < or = p < infinity) space is also discussed. Some experimental results are reported to illustrate our findings.

PMID:
14692636
DOI:
10.1016/S0893-6080(02)00227-7
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center