Presentation 1996/3/18
Chaotic Bidirectional Associative Memory
Yuko OSANA, Motonobu HATTORI, Masafumi HAGIWARA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose Chaotic Bidirectional Associative Memory (CBAM). Most of the conventional associative memory models can not deal with one-to-many associations because the stored common data cause superimposed patterns. Although only a few models enable the one-to-many associations, they require manual con-trols or extra networks to separate the superimposed patterns. As a result, they have very complicated structures. In contrast, the structure of the proposed CBAM is very simple because it merely uses chaotic neurons in a part of the conventional Bidirectional Associative Memory (BAM). In the CBAM, each training pair is memorized together with its own context information. Since the chaotic neurons corresponding to the context information change their states by chaos, the one-to-many associations can be realized in the CBAM. A series of computer simulations shows the effectiveness of the proposed CBAM.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Associative Memory / Chaotic Neuron / One-to-many Association
Paper # NC-95-125
Date of Issue

Conference Information
Committee NC
Conference Date 1996/3/18(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) Chaotic Bidirectional Associative Memory
Sub Title (in English)
Keyword(1) Associative Memory
Keyword(2) Chaotic Neuron
Keyword(3) One-to-many Association
1st Author's Name Yuko OSANA
1st Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University()
2nd Author's Name Motonobu HATTORI
2nd Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University
3rd Author's Name Masafumi HAGIWARA
3rd Author's Affiliation Department of Electrical Engineering, Faculty of Science and Technology, Keio University
Date 1996/3/18
Paper # NC-95-125
Volume (vol) vol.95
Number (no) 598
Page pp.pp.-
#Pages 8
Date of Issue