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
Cet article propose un réseau neuronal à mémoire associative dont l'état limite est le point le plus proche d'un polyèdre à partir d'une entrée donnée. Deux implémentations du réseau de mémoire associative proposé sont présentées, basées sur l'algorithme de Dykstra et un théorème du point fixe pour les mappages non expansifs. Par ces implémentations, l'ensemble de toutes les erreurs corrigibles par le réseau est caractérisé comme un double cône du polyèdre au niveau de chaque motif à mémoriser, ce qui conduit à une technique d'amplification simple pour améliorer la capacité de correction d'erreurs. Il est montré par des exemples numériques que la mémoire associative proposée réalise de bien meilleures performances de correction d'erreurs que la mémoire conventionnelle basée sur POCS au détriment de l'augmentation du nombre nécessaire d'itérations dans l'étape de rappel.
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.
Copier
Isao YAMADA, Satoshi IINO, Kohichi SAKANIWA, "An Associative Memory Neural Network to Recall Nearest Pattern from Input" in IEICE TRANSACTIONS on Fundamentals,
vol. E82-A, no. 12, pp. 2811-2817, December 1999, doi: .
Abstract: This paper proposes an associative memory neural network whose limiting state is the nearest point in a polyhedron from a given input. Two implementations of the proposed associative memory network are presented based on Dykstra's algorithm and a fixed point theorem for nonexpansive mappings. By these implementations, the set of all correctable errors by the network is characterized as a dual cone of the polyhedron at each pattern to be memorized, which leads to a simple amplifying technique to improve the error correction capability. It is shown by numerical examples that the proposed associative memory realizes much better error correction performance than the conventional one based on POCS at the expense of the increase of necessary number of iterations in the recalling stage.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e82-a_12_2811/_p
Copier
@ARTICLE{e82-a_12_2811,
author={Isao YAMADA, Satoshi IINO, Kohichi SAKANIWA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={An Associative Memory Neural Network to Recall Nearest Pattern from Input},
year={1999},
volume={E82-A},
number={12},
pages={2811-2817},
abstract={This paper proposes an associative memory neural network whose limiting state is the nearest point in a polyhedron from a given input. Two implementations of the proposed associative memory network are presented based on Dykstra's algorithm and a fixed point theorem for nonexpansive mappings. By these implementations, the set of all correctable errors by the network is characterized as a dual cone of the polyhedron at each pattern to be memorized, which leads to a simple amplifying technique to improve the error correction capability. It is shown by numerical examples that the proposed associative memory realizes much better error correction performance than the conventional one based on POCS at the expense of the increase of necessary number of iterations in the recalling stage.},
keywords={},
doi={},
ISSN={},
month={December},}
Copier
TY - JOUR
TI - An Associative Memory Neural Network to Recall Nearest Pattern from Input
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2811
EP - 2817
AU - Isao YAMADA
AU - Satoshi IINO
AU - Kohichi SAKANIWA
PY - 1999
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E82-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 1999
AB - This paper proposes an associative memory neural network whose limiting state is the nearest point in a polyhedron from a given input. Two implementations of the proposed associative memory network are presented based on Dykstra's algorithm and a fixed point theorem for nonexpansive mappings. By these implementations, the set of all correctable errors by the network is characterized as a dual cone of the polyhedron at each pattern to be memorized, which leads to a simple amplifying technique to improve the error correction capability. It is shown by numerical examples that the proposed associative memory realizes much better error correction performance than the conventional one based on POCS at the expense of the increase of necessary number of iterations in the recalling stage.
ER -