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
Neste artigo mostramos que o filtro de neurônios é eficaz para relaxar a sensibilidade do coeficiente da rede neural Hopfield para problemas de otimização combinatória. Como os parâmetros da equação de movimento têm uma influência significativa no desempenho da rede neural, muitos estudos foram realizados para apoiar a determinação do valor dos parâmetros. No entanto, poucos pesquisadores determinaram experimentalmente o valor dos parâmetros. Mostramos que o uso do filtro de neurônios é eficaz para o ajuste dos parâmetros, principalmente para determinar seus valores experimentalmente através de simulações.
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
Yoichi TAKENAKA, Nobuo FUNABIKI, Teruo HIGASHINO, "Relaxation of Coefficient Sensitiveness to Performance for Neural Networks Using Neuron Filter through Total Coloring Problems" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 9, pp. 2367-2370, September 2001, doi: .
Abstract: In this paper we show that the neuron filter is effective for relaxing the coefficient sensitiveness of the Hopfield neural network for combinatorial optimization problems. Since the parameters in motion equation have a significant influence on the performance of the neural network, many studies have been carried out to support determining the value of the parameters. However, not a few researchers have determined the value of the parameters experimentally yet. We show that the use of the neuron filter is effective for the parameter tuning, particularly for determining their values experimentally through simulations.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_9_2367/_p
Copiar
@ARTICLE{e84-a_9_2367,
author={Yoichi TAKENAKA, Nobuo FUNABIKI, Teruo HIGASHINO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Relaxation of Coefficient Sensitiveness to Performance for Neural Networks Using Neuron Filter through Total Coloring Problems},
year={2001},
volume={E84-A},
number={9},
pages={2367-2370},
abstract={In this paper we show that the neuron filter is effective for relaxing the coefficient sensitiveness of the Hopfield neural network for combinatorial optimization problems. Since the parameters in motion equation have a significant influence on the performance of the neural network, many studies have been carried out to support determining the value of the parameters. However, not a few researchers have determined the value of the parameters experimentally yet. We show that the use of the neuron filter is effective for the parameter tuning, particularly for determining their values experimentally through simulations.},
keywords={},
doi={},
ISSN={},
month={September},}
Copiar
TY - JOUR
TI - Relaxation of Coefficient Sensitiveness to Performance for Neural Networks Using Neuron Filter through Total Coloring Problems
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 2367
EP - 2370
AU - Yoichi TAKENAKA
AU - Nobuo FUNABIKI
AU - Teruo HIGASHINO
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E84-A
IS - 9
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - September 2001
AB - In this paper we show that the neuron filter is effective for relaxing the coefficient sensitiveness of the Hopfield neural network for combinatorial optimization problems. Since the parameters in motion equation have a significant influence on the performance of the neural network, many studies have been carried out to support determining the value of the parameters. However, not a few researchers have determined the value of the parameters experimentally yet. We show that the use of the neuron filter is effective for the parameter tuning, particularly for determining their values experimentally through simulations.
ER -