Investigation of neural networks for function approximation

Sibo Yang, T. O. Ting*, K. L. Man, Sheng Uei Guan

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

63 Citations (Scopus)

Abstract

In this work, some ubiquitous neural networks are applied to model the landscape of a known problem function approximation. The performance of the various neural networks is analyzed and validated via some well-known benchmark problems as target functions, such as Sphere, Rastrigin, and Griewank functions. The experimental results show that among the three neural networks tested, Radial Basis Function (RBF) neural network is superior in terms of speed and accuracy for function approximation in comparison with Back Propagation (BP) and Generalized Regression Neural Network (GRNN).

Original languageEnglish
Pages (from-to)586-594
Number of pages9
JournalProcedia Computer Science
Volume17
DOIs
Publication statusPublished - 2013
Event1st International Conference on Information Technology and Quantitative Management, ITQM 2013 - Suzhou, China
Duration: 16 May 201318 May 2013

Keywords

  • Benchmark function
  • Function approximation
  • Neural network

Fingerprint

Dive into the research topics of 'Investigation of neural networks for function approximation'. Together they form a unique fingerprint.

Cite this