A Trade-Off between Memory Stability and Connection Sparsity in Simple Binary Associative Memories
Summary :
This letter studies a biobjective optimization problem in binary associative memories characterized by ternary connection parameters. First, we introduce a condition of parameters that guarantees storage of any desired memories and suppression of oscillatory behavior. Second, we define a biobjective problem based on two objectives that evaluate uniform stability of desired memories and sparsity of connection parameters. Performing precise numerical analysis for typical examples, we have clarified existence of a trade-off between the two objectives.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E105-A No.9 pp.1377-1380
- Publication Date
- 2022/09/01
- Publicized
- 2022/03/29
- Online ISSN
- 1745-1337
- DOI
- 10.1587/transfun.2021EAL2113
- Type of Manuscript
- LETTER
- Category
- Nonlinear Problems
Authors
Kento SAKA
the Hosei University
Toshimichi SAITO
the Hosei University
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Kento SAKA, Toshimichi SAITO, "A Trade-Off between Memory Stability and Connection Sparsity in Simple Binary Associative Memories" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 9, pp. 1377-1380, September 2022, doi: 10.1587/transfun.2021EAL2113.
Abstract: This letter studies a biobjective optimization problem in binary associative memories characterized by ternary connection parameters. First, we introduce a condition of parameters that guarantees storage of any desired memories and suppression of oscillatory behavior. Second, we define a biobjective problem based on two objectives that evaluate uniform stability of desired memories and sparsity of connection parameters. Performing precise numerical analysis for typical examples, we have clarified existence of a trade-off between the two objectives.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2021EAL2113/_p
Copy
@ARTICLE{e105-a_9_1377,
author={Kento SAKA, Toshimichi SAITO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Trade-Off between Memory Stability and Connection Sparsity in Simple Binary Associative Memories},
year={2022},
volume={E105-A},
number={9},
pages={1377-1380},
abstract={This letter studies a biobjective optimization problem in binary associative memories characterized by ternary connection parameters. First, we introduce a condition of parameters that guarantees storage of any desired memories and suppression of oscillatory behavior. Second, we define a biobjective problem based on two objectives that evaluate uniform stability of desired memories and sparsity of connection parameters. Performing precise numerical analysis for typical examples, we have clarified existence of a trade-off between the two objectives.},
keywords={},
doi={10.1587/transfun.2021EAL2113},
ISSN={1745-1337},
month={September},}
Copy
TY - JOUR
TI - A Trade-Off between Memory Stability and Connection Sparsity in Simple Binary Associative Memories
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1377
EP - 1380
AU - Kento SAKA
AU - Toshimichi SAITO
PY - 2022
DO - 10.1587/transfun.2021EAL2113
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2022
AB - This letter studies a biobjective optimization problem in binary associative memories characterized by ternary connection parameters. First, we introduce a condition of parameters that guarantees storage of any desired memories and suppression of oscillatory behavior. Second, we define a biobjective problem based on two objectives that evaluate uniform stability of desired memories and sparsity of connection parameters. Performing precise numerical analysis for typical examples, we have clarified existence of a trade-off between the two objectives.
ER -
English
