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
Este artigo propõe uma rede neural de memória associativa cujo estado limite é o ponto mais próximo em um poliedro de uma determinada entrada. Duas implementações da rede de memória associativa proposta são apresentadas com base no algoritmo de Dykstra e um teorema de ponto fixo para mapeamentos não expansivos. Por estas implementações, o conjunto de todos os erros corrigíveis pela rede é caracterizado como um cone duplo do poliedro em cada padrão a ser memorizado, o que leva a uma técnica de amplificação simples para melhorar a capacidade de correção de erros. É mostrado por exemplos numéricos que a memória associativa proposta realiza um desempenho de correção de erros muito melhor do que a convencional baseada em POCS, às custas do aumento do número necessário de iterações na etapa de recuperação.
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.
Copiar
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
Copiar
@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},}
Copiar
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 -