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, é proposto um teorema de convergência em tempo discreto para redes Hopfield de estado contínuo com neurônios de autointeração. Este teorema difere do trabalho anterior de Wang porque a regra de atualização original é mantida enquanto a rede ainda tem a garantia de diminuir monotonicamente para um estado estável. A relação entre os parâmetros em uma classe típica de funções de energia também é investigada e, consequentemente, uma técnica de "tentativa e erro guiada" é proposta para determinar os valores dos parâmetros. O terceiro problema discutido neste artigo é o pós-processamento dos resultados, que acaba sendo bastante importante, embora nunca atraia atenção suficiente. A eficácia de todos os teoremas e métodos de pós-processamento propostos neste artigo é demonstrada por um grande número de simulações computacionais sobre o problema de atribuição e o problema da N-rainha de diferentes tamanhos.
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
Gang FENG, Christos DOULIGERIS, "On the Convergence and Parameter Relation of Discrete-Time Continuous-State Hopfield Networks with Self-Interaction Neurons" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 12, pp. 3162-3173, December 2001, doi: .
Abstract: In this paper, a discrete-time convergence theorem for continuous-state Hopfield networks with self-interaction neurons is proposed. This theorem differs from the previous work by Wang in that the original updating rule is maintained while the network is still guaranteed to monotonically decrease to a stable state. The relationship between the parameters in a typical class of energy functions is also investigated, and consequently a "guided trial-and-error" technique is proposed to determine the parameter values. The third problem discussed in this paper is the post-processing of outputs, which turns out to be rather important even though it never attracts enough attention. The effectiveness of all the theorems and post-processing methods proposed in this paper is demonstrated by a large number of computer simulations on the assignment problem and the N-queen problem of different sizes.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_12_3162/_p
Copiar
@ARTICLE{e84-a_12_3162,
author={Gang FENG, Christos DOULIGERIS, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={On the Convergence and Parameter Relation of Discrete-Time Continuous-State Hopfield Networks with Self-Interaction Neurons},
year={2001},
volume={E84-A},
number={12},
pages={3162-3173},
abstract={In this paper, a discrete-time convergence theorem for continuous-state Hopfield networks with self-interaction neurons is proposed. This theorem differs from the previous work by Wang in that the original updating rule is maintained while the network is still guaranteed to monotonically decrease to a stable state. The relationship between the parameters in a typical class of energy functions is also investigated, and consequently a "guided trial-and-error" technique is proposed to determine the parameter values. The third problem discussed in this paper is the post-processing of outputs, which turns out to be rather important even though it never attracts enough attention. The effectiveness of all the theorems and post-processing methods proposed in this paper is demonstrated by a large number of computer simulations on the assignment problem and the N-queen problem of different sizes.},
keywords={},
doi={},
ISSN={},
month={December},}
Copiar
TY - JOUR
TI - On the Convergence and Parameter Relation of Discrete-Time Continuous-State Hopfield Networks with Self-Interaction Neurons
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 3162
EP - 3173
AU - Gang FENG
AU - Christos DOULIGERIS
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E84-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2001
AB - In this paper, a discrete-time convergence theorem for continuous-state Hopfield networks with self-interaction neurons is proposed. This theorem differs from the previous work by Wang in that the original updating rule is maintained while the network is still guaranteed to monotonically decrease to a stable state. The relationship between the parameters in a typical class of energy functions is also investigated, and consequently a "guided trial-and-error" technique is proposed to determine the parameter values. The third problem discussed in this paper is the post-processing of outputs, which turns out to be rather important even though it never attracts enough attention. The effectiveness of all the theorems and post-processing methods proposed in this paper is demonstrated by a large number of computer simulations on the assignment problem and the N-queen problem of different sizes.
ER -