Parallel and distributed systems for constructive neural network learning

J. Fletcher; Z. Obradovic

doi:10.1109/HPDC.1993.263844

Parallel and distributed systems for constructive neural network learning

J. Fletcher, Z. Obradovic

Medical Informatics and Clinical Epidemiology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Scopus citations

Abstract

A constructive learning algorithm dynamically creates a problem-specific neural network architecture rather than learning on a pre-specified architecture. The authors propose a parallel version of their recently presented constructive neural network learning algorithm. Parallelization provides a computational speedup by a factor of O(t) where t is the number of training examples. Distributed and parallel implementations under p4 using a network of workstations and a Touchstone DELTA are examined. Experimental results indicate that algorithm parallelization may result not only in improved computational time, but also in better prediction quality.

Original language	English (US)
Title of host publication	Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	174-178
Number of pages	5
ISBN (Electronic)	0818639008
DOIs	https://doi.org/10.1109/HPDC.1993.263844
State	Published - 1993
Event	2nd International Symposium on High Performance Distributed Computing, HPDC 1993 - Spokane, United States Duration: Jul 20 1993 → Jul 23 1993

Publication series

Name	Proceedings of the IEEE International Symposium on High Performance Distributed Computing
ISSN (Print)	1082-8907

Conference

Conference	2nd International Symposium on High Performance Distributed Computing, HPDC 1993
Country/Territory	United States
City	Spokane
Period	7/20/93 → 7/23/93

ASJC Scopus subject areas

Software
Computer Networks and Communications

Access to Document

10.1109/HPDC.1993.263844

Cite this

Fletcher, J., & Obradovic, Z. (1993). Parallel and distributed systems for constructive neural network learning. In Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993 (pp. 174-178). Article 263844 (Proceedings of the IEEE International Symposium on High Performance Distributed Computing). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HPDC.1993.263844

Parallel and distributed systems for constructive neural network learning. / Fletcher, J.; Obradovic, Z.
Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993. Institute of Electrical and Electronics Engineers Inc., 1993. p. 174-178 263844 (Proceedings of the IEEE International Symposium on High Performance Distributed Computing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Fletcher, J & Obradovic, Z 1993, Parallel and distributed systems for constructive neural network learning. in Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993., 263844, Proceedings of the IEEE International Symposium on High Performance Distributed Computing, Institute of Electrical and Electronics Engineers Inc., pp. 174-178, 2nd International Symposium on High Performance Distributed Computing, HPDC 1993, Spokane, United States, 7/20/93. https://doi.org/10.1109/HPDC.1993.263844

Fletcher J, Obradovic Z. Parallel and distributed systems for constructive neural network learning. In Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993. Institute of Electrical and Electronics Engineers Inc. 1993. p. 174-178. 263844. (Proceedings of the IEEE International Symposium on High Performance Distributed Computing). doi: 10.1109/HPDC.1993.263844

Fletcher, J. ; Obradovic, Z. / Parallel and distributed systems for constructive neural network learning. Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993. Institute of Electrical and Electronics Engineers Inc., 1993. pp. 174-178 (Proceedings of the IEEE International Symposium on High Performance Distributed Computing).

@inproceedings{be1a678416644b75b5762af7f7ba5587,

title = "Parallel and distributed systems for constructive neural network learning",

abstract = "A constructive learning algorithm dynamically creates a problem-specific neural network architecture rather than learning on a pre-specified architecture. The authors propose a parallel version of their recently presented constructive neural network learning algorithm. Parallelization provides a computational speedup by a factor of O(t) where t is the number of training examples. Distributed and parallel implementations under p4 using a network of workstations and a Touchstone DELTA are examined. Experimental results indicate that algorithm parallelization may result not only in improved computational time, but also in better prediction quality.",

author = "J. Fletcher and Z. Obradovic",

note = "Publisher Copyright: {\textcopyright} 1993 IEEE.; 2nd International Symposium on High Performance Distributed Computing, HPDC 1993 ; Conference date: 20-07-1993 Through 23-07-1993",

year = "1993",

doi = "10.1109/HPDC.1993.263844",

language = "English (US)",

series = "Proceedings of the IEEE International Symposium on High Performance Distributed Computing",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "174--178",

booktitle = "Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993",

}

TY - GEN

T1 - Parallel and distributed systems for constructive neural network learning

AU - Fletcher, J.

AU - Obradovic, Z.

PY - 1993

Y1 - 1993

N2 - A constructive learning algorithm dynamically creates a problem-specific neural network architecture rather than learning on a pre-specified architecture. The authors propose a parallel version of their recently presented constructive neural network learning algorithm. Parallelization provides a computational speedup by a factor of O(t) where t is the number of training examples. Distributed and parallel implementations under p4 using a network of workstations and a Touchstone DELTA are examined. Experimental results indicate that algorithm parallelization may result not only in improved computational time, but also in better prediction quality.

AB - A constructive learning algorithm dynamically creates a problem-specific neural network architecture rather than learning on a pre-specified architecture. The authors propose a parallel version of their recently presented constructive neural network learning algorithm. Parallelization provides a computational speedup by a factor of O(t) where t is the number of training examples. Distributed and parallel implementations under p4 using a network of workstations and a Touchstone DELTA are examined. Experimental results indicate that algorithm parallelization may result not only in improved computational time, but also in better prediction quality.

UR - http://www.scopus.com/inward/record.url?scp=84953478623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953478623&partnerID=8YFLogxK

U2 - 10.1109/HPDC.1993.263844

DO - 10.1109/HPDC.1993.263844

M3 - Conference contribution

AN - SCOPUS:84953478623

T3 - Proceedings of the IEEE International Symposium on High Performance Distributed Computing

SP - 174

EP - 178

BT - Proceedings of the 2nd International Symposium on High Performance Distributed Computing, HPDC 1993

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2nd International Symposium on High Performance Distributed Computing, HPDC 1993

Y2 - 20 July 1993 through 23 July 1993

ER -

Parallel and distributed systems for constructive neural network learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this