Presentation 2022-11-25
A biobjective optimization problem in hysteresis associative memories
Shinya Kujirai, Toshimichi Saito,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper studies a biobjective optimization problem in hysteresis neural networks as associative memories. The networks are simple continuous-time recurrent neural networks characterized by ternary cross-connection parameters and a binary hysteresis activation function. We have a correlation-based parameters setting method that guarantees storage of desired memories. In the optimization problem, the first objective evaluates sparsity of cross-connection parameters and second objective evaluate the number of spurious memories. Presenting a simple evolutionary algorithm, we obtain the pareto front that guarantees existence of the trade-off between two objectives.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) hysteresis neural networks / associative memories / biobjective optimization problem
Paper # NLP2022-73
Date of Issue 2022-11-17 (NLP)

Conference Information
Committee NLP
Conference Date 2022/11/24(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Akio Tsuneda(Kumamoto Univ.)
Vice Chair Hiroyuki Torikai(Hosei Univ.)
Secretary Hiroyuki Torikai(Sojo Univ.)
Assistant Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.)

Paper Information
Registration To Technical Committee on Nonlinear Problems
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A biobjective optimization problem in hysteresis associative memories
Sub Title (in English)
Keyword(1) hysteresis neural networks
Keyword(2) associative memories
Keyword(3) biobjective optimization problem
1st Author's Name Shinya Kujirai
1st Author's Affiliation HOSEI University(HU)
2nd Author's Name Toshimichi Saito
2nd Author's Affiliation HOSEI University(HU)
Date 2022-11-25
Paper # NLP2022-73
Volume (vol) vol.122
Number (no) NLP-280
Page pp.pp.73-76(NLP),
#Pages 4
Date of Issue 2022-11-17 (NLP)