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
É apresentado um algoritmo de aprendizagem por subida gradiente das redes neurais Hopfield para planarização de grafos. Este algoritmo de aprendizagem usa a rede neural Hopfield para obter um subgrafo planar quase máximo e aumenta a energia modificando os parâmetros em uma direção de subida gradiente para ajudar a rede a escapar do estado do subgrafo planar quase máximo para o estado do máximo. subgrafo planar ou melhor. O algoritmo proposto é aplicado a diversos grafos de até 150 vértices e 1064 arestas. O desempenho do nosso algoritmo é comparado com o do método de Takefuji/Lee. Os resultados da simulação mostram que o algoritmo proposto é muito melhor que o método de Takefuji/Lee em termos de qualidade da solução para cada gráfico testado.
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
Zheng TANG, Rong Long WANG, Qi Ping CAO, "A Hopfield Network Learning Algorithm for Graph Planarization" in IEICE TRANSACTIONS on Fundamentals,
vol. E84-A, no. 7, pp. 1799-1802, July 2001, doi: .
Abstract: A gradient ascent learning algorithm of the Hopfield neural networks for graph planarization is presented. This learning algorithm uses the Hopfield neural network to get a near-maximal planar subgraph, and increases the energy by modifying parameters in a gradient ascent direction to help the network escape from the state of the near-maximal planar subgraph to the state of the maximal planar subgraph or better one. The proposed algorithm is applied to several graphs up to 150 vertices and 1064 edges. The performance of our algorithm is compared with that of Takefuji/Lee's method. Simulation results show that the proposed algorithm is much better than Takefuji/Lee's method in terms of the solution quality for every tested graph.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e84-a_7_1799/_p
Copiar
@ARTICLE{e84-a_7_1799,
author={Zheng TANG, Rong Long WANG, Qi Ping CAO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Hopfield Network Learning Algorithm for Graph Planarization},
year={2001},
volume={E84-A},
number={7},
pages={1799-1802},
abstract={A gradient ascent learning algorithm of the Hopfield neural networks for graph planarization is presented. This learning algorithm uses the Hopfield neural network to get a near-maximal planar subgraph, and increases the energy by modifying parameters in a gradient ascent direction to help the network escape from the state of the near-maximal planar subgraph to the state of the maximal planar subgraph or better one. The proposed algorithm is applied to several graphs up to 150 vertices and 1064 edges. The performance of our algorithm is compared with that of Takefuji/Lee's method. Simulation results show that the proposed algorithm is much better than Takefuji/Lee's method in terms of the solution quality for every tested graph.},
keywords={},
doi={},
ISSN={},
month={July},}
Copiar
TY - JOUR
TI - A Hopfield Network Learning Algorithm for Graph Planarization
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1799
EP - 1802
AU - Zheng TANG
AU - Rong Long WANG
AU - Qi Ping CAO
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E84-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2001
AB - A gradient ascent learning algorithm of the Hopfield neural networks for graph planarization is presented. This learning algorithm uses the Hopfield neural network to get a near-maximal planar subgraph, and increases the energy by modifying parameters in a gradient ascent direction to help the network escape from the state of the near-maximal planar subgraph to the state of the maximal planar subgraph or better one. The proposed algorithm is applied to several graphs up to 150 vertices and 1064 edges. The performance of our algorithm is compared with that of Takefuji/Lee's method. Simulation results show that the proposed algorithm is much better than Takefuji/Lee's method in terms of the solution quality for every tested graph.
ER -