PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks

Gerrit A. RIESSEN; Graham J. WILLIAMS; Xin YAO

PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks

Gerrit A. RIESSEN, Graham J. WILLIAMS, Xin YAO

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

9 Citations (Scopus)

Abstract

This paper presents a description of an evolutionary artificial neural network algorithm, EPNet and its extension taking advantage of a High Performance Computing Environment. PEPNet, Parallel EPNet, implements four forms of parallelism and this paper describes two of those parallelisms. Experimental studies have shown promising results with better time and prediction performance. © Springer-Verlag Berlin Heidelberg 1997.

Original language	English
Title of host publication	Proceedings of the 6th International Conference on Evolutionary Programming VI
Editors	Peter J. ANGELINE, Robert G. REYNOLDS, John R. MCDONNELL, Russell C. EBERHART
Publisher	Springer-Verlag, Berlin, Heidelberg
Pages	35-46
Number of pages	11
Volume	1213
ISBN (Print)	9783540627883
Publication status	Published - Apr 1997
Externally published	Yes

Cite this

RIESSEN, Gerrit A. ; WILLIAMS, Graham J. ; YAO, Xin. / PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks. Proceedings of the 6th International Conference on Evolutionary Programming VI. editor / Peter J. ANGELINE ; Robert G. REYNOLDS ; John R. MCDONNELL ; Russell C. EBERHART. Vol. 1213 Springer-Verlag, Berlin, Heidelberg, 1997. pp. 35-46

@inproceedings{09dcf339746547949b43680832ab4fb2,

title = "PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks",

abstract = "This paper presents a description of an evolutionary artificial neural network algorithm, EPNet and its extension taking advantage of a High Performance Computing Environment. PEPNet, Parallel EPNet, implements four forms of parallelism and this paper describes two of those parallelisms. Experimental studies have shown promising results with better time and prediction performance. {\textcopyright} Springer-Verlag Berlin Heidelberg 1997.",

author = "RIESSEN, {Gerrit A.} and WILLIAMS, {Graham J.} and Xin YAO",

year = "1997",

month = apr,

language = "English",

isbn = "9783540627883",

volume = "1213",

pages = "35--46",

editor = "ANGELINE, {Peter J.} and REYNOLDS, {Robert G.} and MCDONNELL, {John R.} and EBERHART, {Russell C.}",

booktitle = "Proceedings of the 6th International Conference on Evolutionary Programming VI",

publisher = "Springer-Verlag, Berlin, Heidelberg",

}

PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks. / RIESSEN, Gerrit A.; WILLIAMS, Graham J.; YAO, Xin.
Proceedings of the 6th International Conference on Evolutionary Programming VI. ed. / Peter J. ANGELINE; Robert G. REYNOLDS; John R. MCDONNELL; Russell C. EBERHART. Vol. 1213 Springer-Verlag, Berlin, Heidelberg, 1997. p. 35-46.

Research output: Book Chapters | Papers in Conference Proceedings › Conference paper (refereed) › Research › peer-review

TY - GEN

T1 - PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks

AU - RIESSEN, Gerrit A.

AU - WILLIAMS, Graham J.

AU - YAO, Xin

PY - 1997/4

Y1 - 1997/4

N2 - This paper presents a description of an evolutionary artificial neural network algorithm, EPNet and its extension taking advantage of a High Performance Computing Environment. PEPNet, Parallel EPNet, implements four forms of parallelism and this paper describes two of those parallelisms. Experimental studies have shown promising results with better time and prediction performance. © Springer-Verlag Berlin Heidelberg 1997.

AB - This paper presents a description of an evolutionary artificial neural network algorithm, EPNet and its extension taking advantage of a High Performance Computing Environment. PEPNet, Parallel EPNet, implements four forms of parallelism and this paper describes two of those parallelisms. Experimental studies have shown promising results with better time and prediction performance. © Springer-Verlag Berlin Heidelberg 1997.

UR - http://www.scopus.com/inward/record.url?scp=84955574430&partnerID=8YFLogxK

M3 - Conference paper (refereed)

SN - 9783540627883

VL - 1213

SP - 35

EP - 46

BT - Proceedings of the 6th International Conference on Evolutionary Programming VI

A2 - ANGELINE, Peter J.

A2 - REYNOLDS, Robert G.

A2 - MCDONNELL, John R.

A2 - EBERHART, Russell C.

PB - Springer-Verlag, Berlin, Heidelberg

ER -

PEPNet: Parallel Evolutionary Programming for Constructing Artificial Neural Networks

Abstract

Other files and links

Fingerprint

Cite this