Fourier series neural networks for classification

Li Jeng Huang, Yung Ming Wang

研究成果: Conference contribution

摘要

This paper presents classification of linearly separable and non-separable problems using neural networks in which hidden neurons are constructed based on double Fourier series expansions (FSNN). The results of numerical examples including classification problems of logical AND, logical XOR, cows and wolves, as well as 3-category problem such as IRIS classification. All the FSNN results are compared with those obtained from backward propagation neural networks (BPANN) and radial basis function neural networks (RBFNN). Root mean squared errors (RMSE) of the algorithms during the training process are also compared. The classification results obtained from FSNN agree well with those obtained from BPANN and RBFNN. Only a few hidden neurons in FSNNs are required for very good and fast convergence of training as compared with BPANN and RBFNN.

原文English
主出版物標題Proceedings of 4th IEEE International Conference on Applied System Innovation 2018, ICASI 2018
編輯Artde Donald Kin-Tak Lam, Stephen D. Prior, Teen-Hang Meen
發行者Institute of Electrical and Electronics Engineers Inc.
頁面881-884
頁數4
ISBN(電子)9781538643426
DOIs
出版狀態Published - 2018 六月 22
事件4th IEEE International Conference on Applied System Innovation, ICASI 2018 - Chiba, Japan
持續時間: 2018 四月 132018 四月 17

出版系列

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

Other

Other4th IEEE International Conference on Applied System Innovation, ICASI 2018
國家Japan
城市Chiba
期間18-04-1318-04-17

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

指紋 深入研究「Fourier series neural networks for classification」主題。共同形成了獨特的指紋。

引用此