Fourier series neural networks for regression

Yung Ming Wang, Li Jeng Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

An innovative efficient and fast neural networks in which hidden neurons are constructed based on Fourier series expansions (FSNN), half-range cosine (FCSNN) and sine expansions (FSSNN) are proposed and tested for linear and nonlinear regulation problems. The results of numerical examples using FSNN are compared with those obtained from traditional linear regression (LP), nonlinear regression (NLP), backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). The results obtained from FSNN agree well with those obtained from LP, NLP, BPANN and RBFNN and show global approximation features to the fitting data. Only a few hidden neurons are required to obtain very good and fast convergence of regression as compared with BPANN and RBFNN.

Original languageEnglish
Title of host publicationProceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018
EditorsArtde Donald Kin-Tak Lam, Stephen D. Prior, Teen-Hang Meen
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages716-719
Number of pages4
ISBN (Electronic)9781538643426
DOIs
Publication statusPublished - 2018 Jun 22
Event4th IEEE International Conference on Applied System Innovation, ICASI 2018 - Chiba, Japan
Duration: 2018 Apr 132018 Apr 17

Publication series

NameProceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018

Other

Other4th IEEE International Conference on Applied System Innovation, ICASI 2018
CountryJapan
CityChiba
Period18-04-1318-04-17

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Hardware and Architecture
  • Energy Engineering and Power Technology
  • Control and Systems Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Modelling and Simulation
  • Biomedical Engineering

Fingerprint Dive into the research topics of 'Fourier series neural networks for regression'. Together they form a unique fingerprint.

Cite this