General Parameter Radial Basis Function Neural Network Based Adaptive Fuzzy Systems

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper an automatic fuzzy rule generation problem through the artificial neural network (ANN) approach is considered. The unknown fuzzy relation reconstruction problem is treated as an optimization of the structure and parameters of the neural network. The functional equivalence between some classes of fuzzy systems and radial basis function networks (RBFNs), namely, their localized sensitivity to input value, is a background of the proposed approach. RBFN with improved structure and advanced learning feature is developed based on General Parameter (GP) method of complex system identification. Main characteristics of the GP method are independence of the learning speed from the dimensionality of the unknown parameter vector, high convergence speed, realization simplicity and ability of the achieved accuracy estimation. The accuracy analysis is based on general parameter average and variance estimation during the learning procedure steady state (after GP statistics stabilization). The structure optimality criterion for the GP RBFN (General Parameter Radial Basis Function Network) is derived using the GP average and variance values. The derived criterion is used then for the development of the GP RBFN structure self-organization procedure. As a result, an Adaptive Fuzzy System (AFS) with capability to extract fuzzy If-Then rules from input and output sample data is proposed. Simulation examples are given.

• 日本知能情報ファジィ学会の論文
• 1998-10-15

著者

• Suzuki Yukinori

  室蘭工業大学情報工学科

• Saga Sato

  室蘭工業大学情報工学科

• AKHMETOV Daouren

  室蘭工業大学情報工学科

• DOTE Yasuhiko

  室蘭工業大学情報工学科

• Akhmetov D

  室蘭工業大学情報工学科

• Dote Y

  Muroran Inst. Technol. Muroran Jpn

関連論文

• General Parameter Radial Basis Function Neural Network Based Adaptive Fuzzy Systems

スポンサーリンク