A proposal of neuron filter

A constraint resolution scheme of neural networks for combinatorial optimization problems

Yoichi Takenaka, Nobuo Funabiki, Teruo Higashino

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

A constraint resolution scheme in the Hopfield-type neural network named Neuron Filter is presented for efficiently solving combinatorial optimization problems. The neuron filter produces an output that satisfies the constraints of the problem as best as possible according to both neuron inputs and outputs. This paper defines the neuron filter and shows its introduction into existing neural networks for N-queens problems and FPGA board-level routing problems. The performance is evaluated through simulations where the results show that our neuron filter improves the searching capability of the neural network with the shorter computation time.

Original languageEnglish
Pages (from-to)1815-1822
Number of pages8
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE83-A
Issue number9
Publication statusPublished - 2000
Externally publishedYes

Fingerprint

Combinatorial optimization
Combinatorial Optimization Problem
Neurons
Neuron
Neural Networks
Filter
Neural networks
Output
Routing Problem
Field Programmable Gate Array
Field programmable gate arrays (FPGA)
Simulation

Keywords

  • Board-level routing problem
  • Combinatorial optimization problem
  • Hopfileld-type neural network
  • N-queens problem
  • Neuron filter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Hardware and Architecture
  • Information Systems

Cite this

@article{bc87590c90b942e69e57f63da2a5fd0c,
title = "A proposal of neuron filter: A constraint resolution scheme of neural networks for combinatorial optimization problems",
abstract = "A constraint resolution scheme in the Hopfield-type neural network named Neuron Filter is presented for efficiently solving combinatorial optimization problems. The neuron filter produces an output that satisfies the constraints of the problem as best as possible according to both neuron inputs and outputs. This paper defines the neuron filter and shows its introduction into existing neural networks for N-queens problems and FPGA board-level routing problems. The performance is evaluated through simulations where the results show that our neuron filter improves the searching capability of the neural network with the shorter computation time.",
keywords = "Board-level routing problem, Combinatorial optimization problem, Hopfileld-type neural network, N-queens problem, Neuron filter",
author = "Yoichi Takenaka and Nobuo Funabiki and Teruo Higashino",
year = "2000",
language = "English",
volume = "E83-A",
pages = "1815--1822",
journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
issn = "0916-8508",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "9",

}

TY - JOUR

T1 - A proposal of neuron filter

T2 - A constraint resolution scheme of neural networks for combinatorial optimization problems

AU - Takenaka, Yoichi

AU - Funabiki, Nobuo

AU - Higashino, Teruo

PY - 2000

Y1 - 2000

N2 - A constraint resolution scheme in the Hopfield-type neural network named Neuron Filter is presented for efficiently solving combinatorial optimization problems. The neuron filter produces an output that satisfies the constraints of the problem as best as possible according to both neuron inputs and outputs. This paper defines the neuron filter and shows its introduction into existing neural networks for N-queens problems and FPGA board-level routing problems. The performance is evaluated through simulations where the results show that our neuron filter improves the searching capability of the neural network with the shorter computation time.

AB - A constraint resolution scheme in the Hopfield-type neural network named Neuron Filter is presented for efficiently solving combinatorial optimization problems. The neuron filter produces an output that satisfies the constraints of the problem as best as possible according to both neuron inputs and outputs. This paper defines the neuron filter and shows its introduction into existing neural networks for N-queens problems and FPGA board-level routing problems. The performance is evaluated through simulations where the results show that our neuron filter improves the searching capability of the neural network with the shorter computation time.

KW - Board-level routing problem

KW - Combinatorial optimization problem

KW - Hopfileld-type neural network

KW - N-queens problem

KW - Neuron filter

UR - http://www.scopus.com/inward/record.url?scp=0034270883&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034270883&partnerID=8YFLogxK

M3 - Article

VL - E83-A

SP - 1815

EP - 1822

JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

SN - 0916-8508

IS - 9

ER -