Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems

Yoichi Takenaka, Nobuo Funabiki, Seishi Nishikawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

A constraint resolution scheme of the Hopfield neural network named `Neuron Mask' is presented for a class of combinatorial optimization problems. Neuron Mask always satisfies constraints of selecting a solution candidate from each group so as to force the state of the neural network into a solution space. This paper presents the definition of Neuron Mask and the introduction into the neural network through the N-queens problem. The performance is verified by simulations on three computation modes, where Neuron Mask improves the performance of the neural network.

Original languageEnglish
Title of host publicationIEEE International Conference on Neural Networks - Conference Proceedings
PublisherIEEE
Pages1289-1294
Number of pages6
Volume2
Publication statusPublished - 1997
Externally publishedYes
EventProceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4) - Houston, TX, USA
Duration: Jun 9 1997Jun 12 1997

Other

OtherProceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4)
CityHouston, TX, USA
Period6/9/976/12/97

Fingerprint

Combinatorial optimization
Neurons
Masks
Neural networks
Hopfield neural networks

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Artificial Intelligence

Cite this

Takenaka, Y., Funabiki, N., & Nishikawa, S. (1997). Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems. In IEEE International Conference on Neural Networks - Conference Proceedings (Vol. 2, pp. 1289-1294). IEEE.

Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems. / Takenaka, Yoichi; Funabiki, Nobuo; Nishikawa, Seishi.

IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1997. p. 1289-1294.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Takenaka, Y, Funabiki, N & Nishikawa, S 1997, Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems. in IEEE International Conference on Neural Networks - Conference Proceedings. vol. 2, IEEE, pp. 1289-1294, Proceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4), Houston, TX, USA, 6/9/97.
Takenaka Y, Funabiki N, Nishikawa S. Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems. In IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2. IEEE. 1997. p. 1289-1294
Takenaka, Yoichi ; Funabiki, Nobuo ; Nishikawa, Seishi. / Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems. IEEE International Conference on Neural Networks - Conference Proceedings. Vol. 2 IEEE, 1997. pp. 1289-1294
@inproceedings{f961168e7d54459b9934da3839d673a3,
title = "Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems",
abstract = "A constraint resolution scheme of the Hopfield neural network named `Neuron Mask' is presented for a class of combinatorial optimization problems. Neuron Mask always satisfies constraints of selecting a solution candidate from each group so as to force the state of the neural network into a solution space. This paper presents the definition of Neuron Mask and the introduction into the neural network through the N-queens problem. The performance is verified by simulations on three computation modes, where Neuron Mask improves the performance of the neural network.",
author = "Yoichi Takenaka and Nobuo Funabiki and Seishi Nishikawa",
year = "1997",
language = "English",
volume = "2",
pages = "1289--1294",
booktitle = "IEEE International Conference on Neural Networks - Conference Proceedings",
publisher = "IEEE",

}

TY - GEN

T1 - Proposal of `neuron mask' in neural network algorithm for combinatorial optimization problems

AU - Takenaka, Yoichi

AU - Funabiki, Nobuo

AU - Nishikawa, Seishi

PY - 1997

Y1 - 1997

N2 - A constraint resolution scheme of the Hopfield neural network named `Neuron Mask' is presented for a class of combinatorial optimization problems. Neuron Mask always satisfies constraints of selecting a solution candidate from each group so as to force the state of the neural network into a solution space. This paper presents the definition of Neuron Mask and the introduction into the neural network through the N-queens problem. The performance is verified by simulations on three computation modes, where Neuron Mask improves the performance of the neural network.

AB - A constraint resolution scheme of the Hopfield neural network named `Neuron Mask' is presented for a class of combinatorial optimization problems. Neuron Mask always satisfies constraints of selecting a solution candidate from each group so as to force the state of the neural network into a solution space. This paper presents the definition of Neuron Mask and the introduction into the neural network through the N-queens problem. The performance is verified by simulations on three computation modes, where Neuron Mask improves the performance of the neural network.

UR - http://www.scopus.com/inward/record.url?scp=0030660003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030660003&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1289

EP - 1294

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

ER -