Comparisons of Seven Neural Network Models on Traffic Control Problems in Multistage Interconnection Networks

Nobuo Funabiki, Yoshiyasu Takefuji, Kuo Chun Lee

Research output: Contribution to journalArticle

14 Citations (Scopus)

Abstract

This paper presents performance comparisons of seven neural network models on traffic control problems in multistage interconnection networks. The decay term, three neuron models, and two heuristics were evaluated. The goal of the traffic control problems is to find conflict-free switching configurations with the maximum throughput. Our simulation results show that the hysteresis McCulloch-Pitts neuron model without the decay term and with two heuristics has the best performance.

Original languageEnglish
Pages (from-to)497-501
Number of pages5
JournalIEEE Transactions on Computers
Volume42
Issue number4
DOIs
Publication statusPublished - 1993
Externally publishedYes

Fingerprint

Multistage Interconnection Networks
Neuron Model
Traffic Control
Traffic control
Neural Network Model
Control Problem
Heuristics
Decay
Neural networks
Neurons
Performance Comparison
Term
Hysteresis
Throughput
Configuration
Simulation
Conflict

Keywords

  • Decay term
  • hysteresis McCulloch-Pitts neuron model
  • McCulloch-Pitts neuron model
  • multistage interconnection network
  • neural network
  • optimization
  • parallel algorithm
  • sigmoid neuron model

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Hardware and Architecture
  • Software
  • Theoretical Computer Science
  • Electrical and Electronic Engineering

Cite this

Comparisons of Seven Neural Network Models on Traffic Control Problems in Multistage Interconnection Networks. / Funabiki, Nobuo; Takefuji, Yoshiyasu; Lee, Kuo Chun.

In: IEEE Transactions on Computers, Vol. 42, No. 4, 1993, p. 497-501.

Research output: Contribution to journalArticle

@article{2cd9b4f22c134fbaa27e2ce49b898c14,
title = "Comparisons of Seven Neural Network Models on Traffic Control Problems in Multistage Interconnection Networks",
abstract = "This paper presents performance comparisons of seven neural network models on traffic control problems in multistage interconnection networks. The decay term, three neuron models, and two heuristics were evaluated. The goal of the traffic control problems is to find conflict-free switching configurations with the maximum throughput. Our simulation results show that the hysteresis McCulloch-Pitts neuron model without the decay term and with two heuristics has the best performance.",
keywords = "Decay term, hysteresis McCulloch-Pitts neuron model, McCulloch-Pitts neuron model, multistage interconnection network, neural network, optimization, parallel algorithm, sigmoid neuron model",
author = "Nobuo Funabiki and Yoshiyasu Takefuji and Lee, {Kuo Chun}",
year = "1993",
doi = "10.1109/12.214695",
language = "English",
volume = "42",
pages = "497--501",
journal = "IEEE Transactions on Computers",
issn = "0018-9340",
publisher = "IEEE Computer Society",
number = "4",

}

TY - JOUR

T1 - Comparisons of Seven Neural Network Models on Traffic Control Problems in Multistage Interconnection Networks

AU - Funabiki, Nobuo

AU - Takefuji, Yoshiyasu

AU - Lee, Kuo Chun

PY - 1993

Y1 - 1993

N2 - This paper presents performance comparisons of seven neural network models on traffic control problems in multistage interconnection networks. The decay term, three neuron models, and two heuristics were evaluated. The goal of the traffic control problems is to find conflict-free switching configurations with the maximum throughput. Our simulation results show that the hysteresis McCulloch-Pitts neuron model without the decay term and with two heuristics has the best performance.

AB - This paper presents performance comparisons of seven neural network models on traffic control problems in multistage interconnection networks. The decay term, three neuron models, and two heuristics were evaluated. The goal of the traffic control problems is to find conflict-free switching configurations with the maximum throughput. Our simulation results show that the hysteresis McCulloch-Pitts neuron model without the decay term and with two heuristics has the best performance.

KW - Decay term

KW - hysteresis McCulloch-Pitts neuron model

KW - McCulloch-Pitts neuron model

KW - multistage interconnection network

KW - neural network

KW - optimization

KW - parallel algorithm

KW - sigmoid neuron model

UR - http://www.scopus.com/inward/record.url?scp=0027576251&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027576251&partnerID=8YFLogxK

U2 - 10.1109/12.214695

DO - 10.1109/12.214695

M3 - Article

AN - SCOPUS:0027576251

VL - 42

SP - 497

EP - 501

JO - IEEE Transactions on Computers

JF - IEEE Transactions on Computers

SN - 0018-9340

IS - 4

ER -