An adaptive stability-growth (ASG) learning algorithm is proposed for improving, as much as possible, the stability of a Hopfield-type associative memory. While the ASG algorithm can be used to determine the optimal stability instead of the well-known minimum-overlap (MO) learning algorithm with sufficiently large lower bound for MO value, it converges much more quickly than the MO algorithm in real implementation. Therefore, the proposed ASG algorithm is more suitable than the MO algorithm for real-world design of an optimal Hopfield-type associative memory.
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.
Copy
Xue-Bin LIANG, Toru YAMAGUCHI, "Optimal Design of Hopfield-Type Associative Memory by Adaptive Stability-Growth Method" in IEICE TRANSACTIONS on Information,
vol. E81-D, no. 1, pp. 148-150, January 1998, doi: .
Abstract: An adaptive stability-growth (ASG) learning algorithm is proposed for improving, as much as possible, the stability of a Hopfield-type associative memory. While the ASG algorithm can be used to determine the optimal stability instead of the well-known minimum-overlap (MO) learning algorithm with sufficiently large lower bound for MO value, it converges much more quickly than the MO algorithm in real implementation. Therefore, the proposed ASG algorithm is more suitable than the MO algorithm for real-world design of an optimal Hopfield-type associative memory.
URL: https://global.ieice.org/en_transactions/information/10.1587/e81-d_1_148/_p
Copy
@ARTICLE{e81-d_1_148,
author={Xue-Bin LIANG, Toru YAMAGUCHI, },
journal={IEICE TRANSACTIONS on Information},
title={Optimal Design of Hopfield-Type Associative Memory by Adaptive Stability-Growth Method},
year={1998},
volume={E81-D},
number={1},
pages={148-150},
abstract={An adaptive stability-growth (ASG) learning algorithm is proposed for improving, as much as possible, the stability of a Hopfield-type associative memory. While the ASG algorithm can be used to determine the optimal stability instead of the well-known minimum-overlap (MO) learning algorithm with sufficiently large lower bound for MO value, it converges much more quickly than the MO algorithm in real implementation. Therefore, the proposed ASG algorithm is more suitable than the MO algorithm for real-world design of an optimal Hopfield-type associative memory.},
keywords={},
doi={},
ISSN={},
month={January},}
Copy
TY - JOUR
TI - Optimal Design of Hopfield-Type Associative Memory by Adaptive Stability-Growth Method
T2 - IEICE TRANSACTIONS on Information
SP - 148
EP - 150
AU - Xue-Bin LIANG
AU - Toru YAMAGUCHI
PY - 1998
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E81-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 1998
AB - An adaptive stability-growth (ASG) learning algorithm is proposed for improving, as much as possible, the stability of a Hopfield-type associative memory. While the ASG algorithm can be used to determine the optimal stability instead of the well-known minimum-overlap (MO) learning algorithm with sufficiently large lower bound for MO value, it converges much more quickly than the MO algorithm in real implementation. Therefore, the proposed ASG algorithm is more suitable than the MO algorithm for real-world design of an optimal Hopfield-type associative memory.
ER -