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

Authors:
Yi Liao;Shu-Cherng Fang;Henry L. W. Nuttle
Affiliations:
Operations Research and Industrial Engineering, North Carolina State University, Raleigh, NC;Operations Research and Industrial Engineering, North Carolina State University, Raleigh, NC;Operations Research and Industrial Engineering, North Carolina State University, Raleigh, NC
Venue:
Neural Networks
Year:
2003

Citing 8
Cited 8

Real and complex analysis, 3rd ed.

Real and complex analysis, 3rd ed.
Approximation capabilities of multilayer feedforward networks

Neural Networks
Universal approximation using radial-basis-function networks

Neural Computation
Approximation and radial-basis-function networks

Neural Computation
Approximation by superposition of sigmoidal and radial basis functions

Advances in Applied Mathematics
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
Some new results on neural network approximation

Neural Networks
Universal approximation to nonlinear operators by neural networks with arbitrary activation functions and its application to dynamical systems

IEEE Transactions on Neural Networks

Uniform Approximation Capabilities of Sum-of-Product and Sigma-Pi-Sigma Neural Networks

ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Letter to the editor: A comment on "Relaxed conditions for radial-basis function networks to be universal approximators"

Neural Networks
Protection ellipsoids for stability analysis of feedforward neural-net controllers

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
An improved flux and torque estimation strategy of speed sensorless induction motor

CCDC'09 Proceedings of the 21st annual international conference on Chinese Control and Decision Conference
Performance improvement of direct torque control system based on dynamic parameter identification technology

CCDC'09 Proceedings of the 21st annual international conference on Chinese control and decision conference
A study on the use of imputation methods for experimentation with Radial Basis Function Network classifiers handling missing attribute values: The good synergy between RBFNs and EventCovering method

Neural Networks
Robust adaptive neural networks with an online learning technique for robot control

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Double approximate identity neural networks universal approximation in real lebesgue spaces

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

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 LP(µ)(1 ≤ p ∞) space is also discussed. Some experimental results are reported to illustrate our findings.