Neural network routing for multiple stage interconnection networks

Mark W. Goudreau, C. Lee Giles

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

Abstract

Summary form only given, a follows. A Hopfield model neural network can be useful as a form of parallel computer. Such a neural network may be capable of arriving at a problem solution with much more speed than conventional, sequential approaches. This concept has been applied to the problem of generating control bits for a multistage interconnection network. A Hopfield model neural network has been designed that is capable of routing a set of messages. This neural network solution is especially useful for interconnection networks that are not self-routing and interconnection networks that have an irregular structure. Furthermore, the neural network routing scheme is fault-tolerant. Results were obtained on generating routes in a 4 × 4 Benes interconnection network.

Original languageEnglish (US)
Title of host publicationProceedings. IJCNN - International Joint Conference on Neural Networks
Editors Anon
PublisherPubl by IEEE
Number of pages1
ISBN (Print)0780301641
StatePublished - Jan 1 1992
EventInternational Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA
Duration: Jul 8 1991Jul 12 1991

Publication series

NameProceedings. IJCNN - International Joint Conference on Neural Networks

Other

OtherInternational Joint Conference on Neural Networks - IJCNN-91-Seattle
CitySeattle, WA, USA
Period7/8/917/12/91

Fingerprint

Network routing
Neural networks

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Goudreau, M. W., & Giles, C. L. (1992). Neural network routing for multiple stage interconnection networks. In Anon (Ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks (Proceedings. IJCNN - International Joint Conference on Neural Networks). Publ by IEEE.
Goudreau, Mark W. ; Giles, C. Lee. / Neural network routing for multiple stage interconnection networks. Proceedings. IJCNN - International Joint Conference on Neural Networks. editor / Anon. Publ by IEEE, 1992. (Proceedings. IJCNN - International Joint Conference on Neural Networks).
@inproceedings{d6cd8294625b4c959cb17b52ecbcf811,
title = "Neural network routing for multiple stage interconnection networks",
abstract = "Summary form only given, a follows. A Hopfield model neural network can be useful as a form of parallel computer. Such a neural network may be capable of arriving at a problem solution with much more speed than conventional, sequential approaches. This concept has been applied to the problem of generating control bits for a multistage interconnection network. A Hopfield model neural network has been designed that is capable of routing a set of messages. This neural network solution is especially useful for interconnection networks that are not self-routing and interconnection networks that have an irregular structure. Furthermore, the neural network routing scheme is fault-tolerant. Results were obtained on generating routes in a 4 × 4 Benes interconnection network.",
author = "Goudreau, {Mark W.} and Giles, {C. Lee}",
year = "1992",
month = "1",
day = "1",
language = "English (US)",
isbn = "0780301641",
series = "Proceedings. IJCNN - International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",
editor = "Anon",
booktitle = "Proceedings. IJCNN - International Joint Conference on Neural Networks",

}

Goudreau, MW & Giles, CL 1992, Neural network routing for multiple stage interconnection networks. in Anon (ed.), Proceedings. IJCNN - International Joint Conference on Neural Networks. Proceedings. IJCNN - International Joint Conference on Neural Networks, Publ by IEEE, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 7/8/91.

Neural network routing for multiple stage interconnection networks. / Goudreau, Mark W.; Giles, C. Lee.

Proceedings. IJCNN - International Joint Conference on Neural Networks. ed. / Anon. Publ by IEEE, 1992. (Proceedings. IJCNN - International Joint Conference on Neural Networks).

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

TY - GEN

T1 - Neural network routing for multiple stage interconnection networks

AU - Goudreau, Mark W.

AU - Giles, C. Lee

PY - 1992/1/1

Y1 - 1992/1/1

N2 - Summary form only given, a follows. A Hopfield model neural network can be useful as a form of parallel computer. Such a neural network may be capable of arriving at a problem solution with much more speed than conventional, sequential approaches. This concept has been applied to the problem of generating control bits for a multistage interconnection network. A Hopfield model neural network has been designed that is capable of routing a set of messages. This neural network solution is especially useful for interconnection networks that are not self-routing and interconnection networks that have an irregular structure. Furthermore, the neural network routing scheme is fault-tolerant. Results were obtained on generating routes in a 4 × 4 Benes interconnection network.

AB - Summary form only given, a follows. A Hopfield model neural network can be useful as a form of parallel computer. Such a neural network may be capable of arriving at a problem solution with much more speed than conventional, sequential approaches. This concept has been applied to the problem of generating control bits for a multistage interconnection network. A Hopfield model neural network has been designed that is capable of routing a set of messages. This neural network solution is especially useful for interconnection networks that are not self-routing and interconnection networks that have an irregular structure. Furthermore, the neural network routing scheme is fault-tolerant. Results were obtained on generating routes in a 4 × 4 Benes interconnection network.

UR - http://www.scopus.com/inward/record.url?scp=0026762019&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026762019&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026762019

SN - 0780301641

T3 - Proceedings. IJCNN - International Joint Conference on Neural Networks

BT - Proceedings. IJCNN - International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -

Goudreau MW, Giles CL. Neural network routing for multiple stage interconnection networks. In Anon, editor, Proceedings. IJCNN - International Joint Conference on Neural Networks. Publ by IEEE. 1992. (Proceedings. IJCNN - International Joint Conference on Neural Networks).