Presentation 2017-01-26
Associative memory model storing memory patterns with nonuniform learning frequency and correlation structure
Akinori Takemoto, Tomoyuki Kimoto,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this study, we analyze stable states of an autocorrelation associative memory model storing memory patterns with nonuniform learning frequency and correlation structure by statistical mechanics and computer simulation. We use abstract memory pattern possessing two information such as the difference of the individuals and the observation direction in 2D observation image like human faces. In addition, we use abstract difference of learning frequency of memory patterns by observation direction difference. As the result of analysis, we found that there are several types of stable states, one is a state possessing information of differences among individual, and the others are the state losting the information. We found that individual identification that does not depend on observation direction is possible by the stable state possessing individual information. We also found that the stability of the stable state possessing individual information is increased by the influence of nonuniform learning frequency.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Hopfield model / nonuniform learning frequency / correlation structure pattern / mixed state
Paper # NC2016-49
Date of Issue 2017-01-19 (NC)

Conference Information
Committee NC / NLP
Conference Date 2017/1/26(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Kitakyushu Foundation for the Advanement of Ind. Sci. and Tech.
Topics (in Japanese) (See Japanese page)
Topics (in English) Implementation of Neuro Computing,Analysis and Modeling of Human Science, etc
Chair Shigeo Sato(Tohoku Univ.) / Hisato Fujisaka(Hiroshima City Univ.)
Vice Chair Masafumi Hagiwara(Keio Univ.) / Masaharu Adachi(Tokyo Denki Univ.)
Secretary Masafumi Hagiwara(Kyoto Sangyo Univ.) / Masaharu Adachi(Tokyo Inst. of Tech.)
Assistant Hisanao Akima(Tohoku Univ.) / Yoshihisa Shinozawa(Keio Univ.) / Hiroyuki Asahara(Okayama Univ. of Science) / Toshihiro Tachibana(Shonan Inst. of Tech.)

Paper Information
Registration To Technical Committee on Neurocomputing / Technical Committee on Nonlinear Problems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Associative memory model storing memory patterns with nonuniform learning frequency and correlation structure
Sub Title (in English)
Keyword(1) Hopfield model
Keyword(2) nonuniform learning frequency
Keyword(3) correlation structure pattern
Keyword(4) mixed state
1st Author's Name Akinori Takemoto
1st Author's Affiliation National Institute of Technology, Oita College(NIT, Oita College)
2nd Author's Name Tomoyuki Kimoto
2nd Author's Affiliation National Institute of Technology, Oita College(NIT, Oita College)
Date 2017-01-26
Paper # NC2016-49
Volume (vol) vol.116
Number (no) NC-424
Page pp.pp.7-12(NC),
#Pages 6
Date of Issue 2017-01-19 (NC)