Parallel training of neural networks for finite element mesh decomposition

B. H.V. Topping, A. I. Khan, A. Bahreininejad

Research output: Contribution to journalArticleResearchpeer-review

22 Citations (Scopus)

Abstract

This paper describes a parallel processing implementation for neural computing and its application to finite element mesh decomposition. The parallelized neural network software developed is based on the public domain NASA developed program NETS 2.01, which is based on the back propagation algorithm of Rumelhart et al. [Learning internal representation by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition (Edited by D. E. Rummelhart and J. L. McClelland), Vol. 1: Foundations. MIT Press, MA (1986)]. The principal focus of this research concerns the parallel implementation. Comparisons between sequential and parallel versions are given. Finally a structural design problem concerned with finite element mesh generation is solved using the parallel neural network software.

Original languageEnglish
Pages (from-to)693-707
Number of pages15
JournalComputers and Structures
Volume63
Issue number4
DOIs
Publication statusPublished - 1 Jan 1997

Cite this

Topping, B. H.V. ; Khan, A. I. ; Bahreininejad, A. / Parallel training of neural networks for finite element mesh decomposition. In: Computers and Structures. 1997 ; Vol. 63, No. 4. pp. 693-707.
@article{906327cba9d14c8faa5dcda3d30c8a9f,
title = "Parallel training of neural networks for finite element mesh decomposition",
abstract = "This paper describes a parallel processing implementation for neural computing and its application to finite element mesh decomposition. The parallelized neural network software developed is based on the public domain NASA developed program NETS 2.01, which is based on the back propagation algorithm of Rumelhart et al. [Learning internal representation by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition (Edited by D. E. Rummelhart and J. L. McClelland), Vol. 1: Foundations. MIT Press, MA (1986)]. The principal focus of this research concerns the parallel implementation. Comparisons between sequential and parallel versions are given. Finally a structural design problem concerned with finite element mesh generation is solved using the parallel neural network software.",
author = "Topping, {B. H.V.} and Khan, {A. I.} and A. Bahreininejad",
year = "1997",
month = "1",
day = "1",
doi = "10.1016/S0045-7949(96)00082-X",
language = "English",
volume = "63",
pages = "693--707",
journal = "Computers and Structures",
issn = "0045-7949",
publisher = "Elsevier",
number = "4",

}

Parallel training of neural networks for finite element mesh decomposition. / Topping, B. H.V.; Khan, A. I.; Bahreininejad, A.

In: Computers and Structures, Vol. 63, No. 4, 01.01.1997, p. 693-707.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Parallel training of neural networks for finite element mesh decomposition

AU - Topping, B. H.V.

AU - Khan, A. I.

AU - Bahreininejad, A.

PY - 1997/1/1

Y1 - 1997/1/1

N2 - This paper describes a parallel processing implementation for neural computing and its application to finite element mesh decomposition. The parallelized neural network software developed is based on the public domain NASA developed program NETS 2.01, which is based on the back propagation algorithm of Rumelhart et al. [Learning internal representation by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition (Edited by D. E. Rummelhart and J. L. McClelland), Vol. 1: Foundations. MIT Press, MA (1986)]. The principal focus of this research concerns the parallel implementation. Comparisons between sequential and parallel versions are given. Finally a structural design problem concerned with finite element mesh generation is solved using the parallel neural network software.

AB - This paper describes a parallel processing implementation for neural computing and its application to finite element mesh decomposition. The parallelized neural network software developed is based on the public domain NASA developed program NETS 2.01, which is based on the back propagation algorithm of Rumelhart et al. [Learning internal representation by error propagation. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition (Edited by D. E. Rummelhart and J. L. McClelland), Vol. 1: Foundations. MIT Press, MA (1986)]. The principal focus of this research concerns the parallel implementation. Comparisons between sequential and parallel versions are given. Finally a structural design problem concerned with finite element mesh generation is solved using the parallel neural network software.

UR - http://www.scopus.com/inward/record.url?scp=0031143162&partnerID=8YFLogxK

U2 - 10.1016/S0045-7949(96)00082-X

DO - 10.1016/S0045-7949(96)00082-X

M3 - Article

AN - SCOPUS:0031143162

VL - 63

SP - 693

EP - 707

JO - Computers and Structures

JF - Computers and Structures

SN - 0045-7949

IS - 4

ER -