Presentation 1995/9/29
A Model of Dynamic Associative Memory and Its Analysis
Hideki Kobori, Kazushi Ikeda, Kenji Nakayama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The chaotic neural network which uses chaotic neuron; shows the nonperiodic associative dynamics, but retrieval frequency of the stored patterns is small and to distinguish the unstored patterns from the stored patterns is difficult. In this paper, we suggest a recurrent neural network composed of neurons Which have a characteristic that the state of neurons is reversed when the same state is continued. In this network, we confirm that the state of the network travels around the stored pattern and stays at the stored pattern during some period. Accordingly, it is shown that the stored patterns can be distinguished from the unstored patterns by using average period of staying at the same state.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Recurrent neural network / Associative memory / Reversed neuron / State transition / Dynamics / threshold
Paper # NLP95-47
Date of Issue

Conference Information
Committee NLP
Conference Date 1995/9/29(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 JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Model of Dynamic Associative Memory and Its Analysis
Sub Title (in English)
Keyword(1) Recurrent neural network
Keyword(2) Associative memory
Keyword(3) Reversed neuron
Keyword(4) State transition
Keyword(5) Dynamics
Keyword(6) threshold
1st Author's Name Hideki Kobori
1st Author's Affiliation Dept. of Electrical and Computer Eng., Faculty of Eng., Kanazawa Univ.()
2nd Author's Name Kazushi Ikeda
2nd Author's Affiliation Dept. of Electrical and Computer Eng., Faculty of Eng., Kanazawa Univ.
3rd Author's Name Kenji Nakayama
3rd Author's Affiliation Dept. of Electrical and Computer Eng., Faculty of Eng., Kanazawa Univ.
Date 1995/9/29
Paper # NLP95-47
Volume (vol) vol.95
Number (no) 280
Page pp.pp.-
#Pages 8
Date of Issue