Proposal of an N-parallel computation method for a neural network for the N queens problem

Hiroaki Yoshio, Takayuki Baba, Nobuo Funabiki, Seishi Nishikawa

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

This paper presents an N2 neuron N-parallel computation method for a neural network for the N queens problem. In this method, the N2 neurons are partitioned into N groups of N neurons, where the states of N neurons in N different groups are updated synchronously and the states in the same group are updated sequentially. First, we compare the performance of two existing neural networks for the N queens problem in order to show that Takefuji's neural network is best in the sequential method. Then, we show that even the improved neural network using the N2-parallel method cannot provide the same performance as that using the using sequential method. Lastly, we propose an N-parallel method to achieve high performance and parallel computation simultaneously.

Original languageEnglish
Pages (from-to)12-19
Number of pages8
JournalElectronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume80
Issue number11
Publication statusPublished - Nov 1997
Externally publishedYes

Fingerprint

Neurons
Neural networks

Keywords

  • N-parallel computation
  • N-queens problem
  • Neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{eb178cf12a0c41dbbdbc5cd4264df1cb,
title = "Proposal of an N-parallel computation method for a neural network for the N queens problem",
abstract = "This paper presents an N2 neuron N-parallel computation method for a neural network for the N queens problem. In this method, the N2 neurons are partitioned into N groups of N neurons, where the states of N neurons in N different groups are updated synchronously and the states in the same group are updated sequentially. First, we compare the performance of two existing neural networks for the N queens problem in order to show that Takefuji's neural network is best in the sequential method. Then, we show that even the improved neural network using the N2-parallel method cannot provide the same performance as that using the using sequential method. Lastly, we propose an N-parallel method to achieve high performance and parallel computation simultaneously.",
keywords = "N-parallel computation, N-queens problem, Neural network",
author = "Hiroaki Yoshio and Takayuki Baba and Nobuo Funabiki and Seishi Nishikawa",
year = "1997",
month = "11",
language = "English",
volume = "80",
pages = "12--19",
journal = "Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)",
issn = "1042-0967",
publisher = "John Wiley and Sons Inc.",
number = "11",

}

TY - JOUR

T1 - Proposal of an N-parallel computation method for a neural network for the N queens problem

AU - Yoshio, Hiroaki

AU - Baba, Takayuki

AU - Funabiki, Nobuo

AU - Nishikawa, Seishi

PY - 1997/11

Y1 - 1997/11

N2 - This paper presents an N2 neuron N-parallel computation method for a neural network for the N queens problem. In this method, the N2 neurons are partitioned into N groups of N neurons, where the states of N neurons in N different groups are updated synchronously and the states in the same group are updated sequentially. First, we compare the performance of two existing neural networks for the N queens problem in order to show that Takefuji's neural network is best in the sequential method. Then, we show that even the improved neural network using the N2-parallel method cannot provide the same performance as that using the using sequential method. Lastly, we propose an N-parallel method to achieve high performance and parallel computation simultaneously.

AB - This paper presents an N2 neuron N-parallel computation method for a neural network for the N queens problem. In this method, the N2 neurons are partitioned into N groups of N neurons, where the states of N neurons in N different groups are updated synchronously and the states in the same group are updated sequentially. First, we compare the performance of two existing neural networks for the N queens problem in order to show that Takefuji's neural network is best in the sequential method. Then, we show that even the improved neural network using the N2-parallel method cannot provide the same performance as that using the using sequential method. Lastly, we propose an N-parallel method to achieve high performance and parallel computation simultaneously.

KW - N-parallel computation

KW - N-queens problem

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=0031271838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0031271838&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0031271838

VL - 80

SP - 12

EP - 19

JO - Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)

SN - 1042-0967

IS - 11

ER -