Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications

G. M. Maxwell; C. MacLeod

doi:10.1109/ICONIP.2002.1202182

Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications

G. M. Maxwell, C. MacLeod

UHI North West and Hebrides

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

4 Citations (Scopus)

Abstract

Taguchi methods are commonly used to optimise industrial systems, particularly in manufacturing. We have shown that they may also be used to optimise neural network weights and therefore train the network. This paper builds on previous work and explains the application of the method to network training in several important areas, including pattern recognition, neurocontrol, evolutionary or genetic networks and nonlinear neurons. Consideration is also given to the training of networks for failure and fault control systems.

Original language	English
Title of host publication	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
Subtitle of host publication	Computational Intelligence for the E-Age
Editors	Jagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	301-305
Number of pages	5
ISBN (Electronic)	9810475241, 9789810475246
DOIs	https://doi.org/10.1109/ICONIP.2002.1202182
Publication status	Published - 2002
Event	9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore Duration: 18 Nov 2002 → 22 Nov 2002

Publication series

Name	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age
Volume	1

Conference

Conference	9th International Conference on Neural Information Processing, ICONIP 2002
Country/Territory	Singapore
City	Singapore
Period	18/11/02 → 22/11/02

Access to Document

10.1109/ICONIP.2002.1202182

Cite this

Maxwell, G. M., & MacLeod, C. (2002). Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications. In J. C. Rajapakse, X. Yao, L. Wang, K. Fukushima, & S.-Y. Lee (Eds.), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (pp. 301-305). Article 1202182 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; Vol. 1). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICONIP.2002.1202182

Maxwell, G. M. ; MacLeod, C. / Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications. ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. editor / Jagath C. Rajapakse ; Xin Yao ; Lipo Wang ; Kunihiko Fukushima ; Soo-Young Lee. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 301-305 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age).

@inproceedings{05b61df5813b4ca48aa72337b7c2bed2,

title = "Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications",

abstract = "Taguchi methods are commonly used to optimise industrial systems, particularly in manufacturing. We have shown that they may also be used to optimise neural network weights and therefore train the network. This paper builds on previous work and explains the application of the method to network training in several important areas, including pattern recognition, neurocontrol, evolutionary or genetic networks and nonlinear neurons. Consideration is also given to the training of networks for failure and fault control systems.",

author = "Maxwell, {G. M.} and C. MacLeod",

note = "Publisher Copyright: {\textcopyright} 2002 Nanyang Technological University.; 9th International Conference on Neural Information Processing, ICONIP 2002 ; Conference date: 18-11-2002 Through 22-11-2002",

year = "2002",

doi = "10.1109/ICONIP.2002.1202182",

language = "English",

series = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age",

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

pages = "301--305",

editor = "Rajapakse, {Jagath C.} and Xin Yao and Lipo Wang and Kunihiko Fukushima and Soo-Young Lee",

booktitle = "ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing",

address = "United States",

}

Maxwell, GM & MacLeod, C 2002, Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications. in JC Rajapakse, X Yao, L Wang, K Fukushima & S-Y Lee (eds), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age., 1202182, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age, vol. 1, Institute of Electrical and Electronics Engineers Inc., pp. 301-305, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, 18/11/02. https://doi.org/10.1109/ICONIP.2002.1202182

Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications. / Maxwell, G. M.; MacLeod, C.
ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. ed. / Jagath C. Rajapakse; Xin Yao; Lipo Wang; Kunihiko Fukushima; Soo-Young Lee. Institute of Electrical and Electronics Engineers Inc., 2002. p. 301-305 1202182 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; Vol. 1).

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

TY - GEN

T1 - Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications

AU - Maxwell, G. M.

AU - MacLeod, C.

PY - 2002

Y1 - 2002

N2 - Taguchi methods are commonly used to optimise industrial systems, particularly in manufacturing. We have shown that they may also be used to optimise neural network weights and therefore train the network. This paper builds on previous work and explains the application of the method to network training in several important areas, including pattern recognition, neurocontrol, evolutionary or genetic networks and nonlinear neurons. Consideration is also given to the training of networks for failure and fault control systems.

AB - Taguchi methods are commonly used to optimise industrial systems, particularly in manufacturing. We have shown that they may also be used to optimise neural network weights and therefore train the network. This paper builds on previous work and explains the application of the method to network training in several important areas, including pattern recognition, neurocontrol, evolutionary or genetic networks and nonlinear neurons. Consideration is also given to the training of networks for failure and fault control systems.

UR - http://www.scopus.com/inward/record.url?scp=84964999920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84964999920&partnerID=8YFLogxK

U2 - 10.1109/ICONIP.2002.1202182

DO - 10.1109/ICONIP.2002.1202182

M3 - Conference contribution

AN - SCOPUS:84964999920

T3 - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age

SP - 301

EP - 305

BT - ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing

A2 - Rajapakse, Jagath C.

A2 - Yao, Xin

A2 - Wang, Lipo

A2 - Fukushima, Kunihiko

A2 - Lee, Soo-Young

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th International Conference on Neural Information Processing, ICONIP 2002

Y2 - 18 November 2002 through 22 November 2002

ER -

Maxwell GM, MacLeod C. Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications. In Rajapakse JC, Yao X, Wang L, Fukushima K, Lee SY, editors, ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age. Institute of Electrical and Electronics Engineers Inc. 2002. p. 301-305. 1202182. (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age). doi: 10.1109/ICONIP.2002.1202182

Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this