The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
히스테리시스 신경망의 모든 안정 평형점을 명확하게 하기 위해 모든 해를 찾는 알고리즘을 고려합니다. 알고리즘에는 부호 테스트, 선형 프로그래밍 테스트 및 솔루션 영역을 효율적으로 분할하는 새로운 서브루틴이 포함됩니다. 히스테리시스 네트워크를 사용하여 교차 연결 매개변수가 삼중화되는 연관 메모리를 합성합니다. 원하는 메모리 10개가 77개의 셀 네트워크에 저장되어 있는 경우에 알고리즘을 적용하면 모든 해결 방법이 명확해졌습니다. 특히, 삼위일체화가 적합하여 가짜 기억이 존재하지 않음을 확인했습니다.
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.
부
Yuji KOBAYASHI, Kenya JIN'NO, Toshimichi SAITO, "An Algorithm for Finding All Solutions of a Hysteresis Neural Network" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 1, pp. 167-172, January 1999, doi: .
Abstract: We consider an algorithm for finding all solutions in order to clarify all the stable equilibrium points of a hysteresis neural network. The algorithm includes sign test, linear programming test and a novel subroutine that divides the solution domain efficiently. Using the hysteresis network, we synthesize an associative memory whose cross connection parameters are trinalized. Applying the algorithm to the case where 10 desired memories are stored into 77 cells network, we have clarified all the solutions. Especially, we have confirmed that no spurious memory exists as the trinalization is suitable.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_1_167/_p
부
@ARTICLE{e82-a_1_167,
author={Yuji KOBAYASHI, Kenya JIN'NO, Toshimichi SAITO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Algorithm for Finding All Solutions of a Hysteresis Neural Network},
year={1999},
volume={E82-A},
number={1},
pages={167-172},
abstract={We consider an algorithm for finding all solutions in order to clarify all the stable equilibrium points of a hysteresis neural network. The algorithm includes sign test, linear programming test and a novel subroutine that divides the solution domain efficiently. Using the hysteresis network, we synthesize an associative memory whose cross connection parameters are trinalized. Applying the algorithm to the case where 10 desired memories are stored into 77 cells network, we have clarified all the solutions. Especially, we have confirmed that no spurious memory exists as the trinalization is suitable.},
keywords={},
doi={},
ISSN={},
month={January},}
부
TY - JOUR
TI - An Algorithm for Finding All Solutions of a Hysteresis Neural Network
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 167
EP - 172
AU - Yuji KOBAYASHI
AU - Kenya JIN'NO
AU - Toshimichi SAITO
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 1
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - January 1999
AB - We consider an algorithm for finding all solutions in order to clarify all the stable equilibrium points of a hysteresis neural network. The algorithm includes sign test, linear programming test and a novel subroutine that divides the solution domain efficiently. Using the hysteresis network, we synthesize an associative memory whose cross connection parameters are trinalized. Applying the algorithm to the case where 10 desired memories are stored into 77 cells network, we have clarified all the solutions. Especially, we have confirmed that no spurious memory exists as the trinalization is suitable.
ER -