Presentation 1997/3/17
Method of Search of Associative Memory in Chaotic Neural Network with Internal Patterns
Toshinori Deguchi, Naohiro Ishii,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We reported that applying presynaptic inhibition to chaotic neural network realized the search of associative memory by matching features with chaos. But, the patterns in former works are special set. Then, network doesn't work with general patterns. In this paper, we discuss the methods for generating the patterns for search with chaos. We investigate a rate of success by computer simulations, from the relation of the generated pattern and the rate of success, improve the pattern generating method, and show that the pattern generation and check give high successful rate. From that results, using the patterns with high successful rate for internal patterns, and translating to output pattern, search with chaos works well in general output patterns.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / associative memory / chaos / search access / internal code
Paper # NC96-129
Date of Issue

Conference Information
Committee NC
Conference Date 1997/3/17(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Method of Search of Associative Memory in Chaotic Neural Network with Internal Patterns
Sub Title (in English)
Keyword(1) neural network
Keyword(2) associative memory
Keyword(3) chaos
Keyword(4) search access
Keyword(5) internal code
1st Author's Name Toshinori Deguchi
1st Author's Affiliation Gifu National College of Technology()
2nd Author's Name Naohiro Ishii
2nd Author's Affiliation Dept. of Intelligence & Computer Science Nagoya Institute of Technology
Date 1997/3/17
Paper # NC96-129
Volume (vol) vol.96
Number (no) 583
Page pp.pp.-
#Pages 6
Date of Issue