Removal of hidden units and weights for back propagation networks

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

25 Citations (Scopus)

Abstract

The objective of this paper is to present a simple and effective method for removal of both hidden units and weights. In this paper, we propose two methods, 'Consuming energy' method and 'Weights power' method, and compare them with the conventional method. According to our computer simulations using the mirror symmetry problem, the Weights power method has shown the best performance in respect of size reduction (removal of units and weights), generalization performance, and the amount of computation required. For example, the number of hidden units reduced to about 40% of the initial state, and the number of weights reduced to less than a fourth of the initial state. In addition, generalization performance was improved more than 10%.

Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks
PublisherPubl by IEEE
Pages351-353
Number of pages3
Volume1
ISBN (Print)0780314212, 9780780314214
Publication statusPublished - 1993
EventProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3) - Nagoya, Jpn
Duration: 1993 Oct 251993 Oct 29

Other

OtherProceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3)
CityNagoya, Jpn
Period93/10/2593/10/29

Fingerprint

Backpropagation
Mirrors
Computer simulation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hagiwara, M. (1993). Removal of hidden units and weights for back propagation networks. In Proceedings of the International Joint Conference on Neural Networks (Vol. 1, pp. 351-353). Publ by IEEE.

Removal of hidden units and weights for back propagation networks. / Hagiwara, Masafumi.

Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. p. 351-353.

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

Hagiwara, M 1993, Removal of hidden units and weights for back propagation networks. in Proceedings of the International Joint Conference on Neural Networks. vol. 1, Publ by IEEE, pp. 351-353, Proceedings of 1993 International Joint Conference on Neural Networks. Part 1 (of 3), Nagoya, Jpn, 93/10/25.
Hagiwara M. Removal of hidden units and weights for back propagation networks. In Proceedings of the International Joint Conference on Neural Networks. Vol. 1. Publ by IEEE. 1993. p. 351-353
Hagiwara, Masafumi. / Removal of hidden units and weights for back propagation networks. Proceedings of the International Joint Conference on Neural Networks. Vol. 1 Publ by IEEE, 1993. pp. 351-353
@inproceedings{84ae46f6b1b447d9a14751ccc22141e5,
title = "Removal of hidden units and weights for back propagation networks",
abstract = "The objective of this paper is to present a simple and effective method for removal of both hidden units and weights. In this paper, we propose two methods, 'Consuming energy' method and 'Weights power' method, and compare them with the conventional method. According to our computer simulations using the mirror symmetry problem, the Weights power method has shown the best performance in respect of size reduction (removal of units and weights), generalization performance, and the amount of computation required. For example, the number of hidden units reduced to about 40{\%} of the initial state, and the number of weights reduced to less than a fourth of the initial state. In addition, generalization performance was improved more than 10{\%}.",
author = "Masafumi Hagiwara",
year = "1993",
language = "English",
isbn = "0780314212",
volume = "1",
pages = "351--353",
booktitle = "Proceedings of the International Joint Conference on Neural Networks",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Removal of hidden units and weights for back propagation networks

AU - Hagiwara, Masafumi

PY - 1993

Y1 - 1993

N2 - The objective of this paper is to present a simple and effective method for removal of both hidden units and weights. In this paper, we propose two methods, 'Consuming energy' method and 'Weights power' method, and compare them with the conventional method. According to our computer simulations using the mirror symmetry problem, the Weights power method has shown the best performance in respect of size reduction (removal of units and weights), generalization performance, and the amount of computation required. For example, the number of hidden units reduced to about 40% of the initial state, and the number of weights reduced to less than a fourth of the initial state. In addition, generalization performance was improved more than 10%.

AB - The objective of this paper is to present a simple and effective method for removal of both hidden units and weights. In this paper, we propose two methods, 'Consuming energy' method and 'Weights power' method, and compare them with the conventional method. According to our computer simulations using the mirror symmetry problem, the Weights power method has shown the best performance in respect of size reduction (removal of units and weights), generalization performance, and the amount of computation required. For example, the number of hidden units reduced to about 40% of the initial state, and the number of weights reduced to less than a fourth of the initial state. In addition, generalization performance was improved more than 10%.

UR - http://www.scopus.com/inward/record.url?scp=0027850951&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027850951&partnerID=8YFLogxK

M3 - Conference contribution

SN - 0780314212

SN - 9780780314214

VL - 1

SP - 351

EP - 353

BT - Proceedings of the International Joint Conference on Neural Networks

PB - Publ by IEEE

ER -