Presentation 1998/12/7
A Design Method of Cellular Neural Networks using Fuzzy Inference
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a new design method of cloning templates which define the function of a cellular neural network. Firstly, we utilize Fuzzy inference method in a CNN simulation to make necessary sample data for the calculation of templates. Secondly, we use the least-squares approximation to calculate templates for simple image processing. Thirdly, for complicated image processing, we introduce pattern separation vector to enable the calculation of templates using relaxation method. As examples of design, we describe edge detection, hollow and skeltonization.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) cellular neural networks / template design / fuzzy inference / least-squares approximation / relaxation method
Paper # NLP98-89
Date of Issue

Conference Information
Committee NLP
Conference Date 1998/12/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Vice Chair

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Design Method of Cellular Neural Networks using Fuzzy Inference
Sub Title (in English)
Keyword(1) cellular neural networks
Keyword(2) template design
Keyword(3) fuzzy inference
Keyword(4) least-squares approximation
Keyword(5) relaxation method
1st Author's Name Kazuhiro SUMITOMO
1st Author's Affiliation Dept. of Electronics, Takuma National College of Technology()
2nd Author's Name Akio USHIDA
2nd Author's Affiliation Dept.of Electrical and Electronic Eng., Faculty of Engineering, Tokushima University
Date 1998/12/7
Paper # NLP98-89
Volume (vol) vol.98
Number (no) 443
Page pp.pp.-
#Pages 8
Date of Issue