Sigmoidal radial basis function neural network for function approximation

Jea Rong Tsai, Pau-Choo Chung, Chein I. Chang

Research output: Contribution to conferencePaperpeer-review

9 Citations (Scopus)

Abstract

A traditional Radial basis function (RBF) network takes Gaussian functions as its basis functions and adopts the least squares(LS) criterion as the objective function. However, it is difficult to use Gaussian functions to approximate constant values. If a function has nearly constant values in some intervals, the RBF network will be found inefficient in approximating these values. In this paper an RBF network which uses composite of sigmoidal functions to replace the Gaussian functions as the basis function of the network is proposed. It is also illustrated that the shape of the activation function can be constructed to be a similar rectangular or Gaussian function. Thus, the constant-valued functions can be approximated accurately by an RBF network. A robust objective function is also adopted in the network to replace the LS objective function. Experimental results demonstrated that the proposed network has better capability of approximation to underlying functions with a fast learning speed and high robustness to outliers.

Original languageEnglish
Pages496-501
Number of pages6
Publication statusPublished - 1996 Jan 1
EventProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4) - Washington, DC, USA
Duration: 1996 Jun 31996 Jun 6

Other

OtherProceedings of the 1996 IEEE International Conference on Neural Networks, ICNN. Part 1 (of 4)
CityWashington, DC, USA
Period96-06-0396-06-06

All Science Journal Classification (ASJC) codes

  • Software

Fingerprint Dive into the research topics of 'Sigmoidal radial basis function neural network for function approximation'. Together they form a unique fingerprint.

Cite this