Presentation 1994/5/20
NON-UNIFORM DISCRETE-TIME CELLULAR NEURAL NETWORKS AND MULTI-PATTERNS RECOGNIZATION
Chen He, Akio Ushita,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In previous paper£12!,we presented a synchronous-updating and di screte-time cenular neural network.Then we analyzed their dynamical characters and stability properties,and provided two sufficient convergent theorems.In this study,based on the analysis mentioned above,we construct a discrete-time cellular neural network with non-reciprocal weight matrix.As contrasted with uniform CNN,it is a variable-space non-uniform DTCNN,and can be used for pattern-recognitions and associative memories and others. The demonstration shows that,for multi different types of texture elements inlaid within a two-dimensional image,the non-uniform DTCNN is capable of extracting them all at once.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) pattern recognition / non-uniform weight / DTCNN / neuron
Paper # NLP94-11
Date of Issue

Conference Information
Committee NLP
Conference Date 1994/5/20(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) NON-UNIFORM DISCRETE-TIME CELLULAR NEURAL NETWORKS AND MULTI-PATTERNS RECOGNIZATION
Sub Title (in English)
Keyword(1) pattern recognition
Keyword(2) non-uniform weight
Keyword(3) DTCNN
Keyword(4) neuron
1st Author's Name Chen He
1st Author's Affiliation University of Tokushima()
2nd Author's Name Akio Ushita
2nd Author's Affiliation University of Tokushima
Date 1994/5/20
Paper # NLP94-11
Volume (vol) vol.94
Number (no) 45
Page pp.pp.-
#Pages 8
Date of Issue