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

نتاج البحث: Conference contribution

4 اقتباسات (Scopus)

ملخص

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.

اللغة الأصلية	English
عنوان منشور المضيف	ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing
العنوان الفرعي لمنشور المضيف	Computational Intelligence for the E-Age
المحررون	Jagath C. Rajapakse, Xin Yao, Lipo Wang, Kunihiko Fukushima, Soo-Young Lee
ناشر	Institute of Electrical and Electronics Engineers Inc.
الصفحات	301-305
عدد الصفحات	5
رقم المعيار الدولي للكتب (الإلكتروني)	9810475241, 9789810475246
المعرِّفات الرقمية للأشياء	https://doi.org/10.1109/ICONIP.2002.1202182
حالة النشر	Published - 2002
الحدث	9th International Conference on Neural Information Processing, ICONIP 2002 - Singapore, Singapore المدة: ١٨ نوفمبر ٢٠٠٢ → ٢٢ نوفمبر ٢٠٠٢

سلسلة المنشورات

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

Conference

Conference	9th International Conference on Neural Information Processing, ICONIP 2002
الدولة/الإقليم	Singapore
المدينة	Singapore
المدة	١٨/١١/٠٢ → ٢٢/١١/٠٢

أهداف الأمم المتحدة للتنمية المستدامة

يساهم هذا المخرج في تحقيق أهداف الأمم المتحدة للتنمية المستدامة التالية (SDGs)

Industry innovation and infrastructure

الوصول إلى المستند

10.1109/ICONIP.2002.1202182

الملفات والروابط الأخرى

قم بذكر هذا

Maxwell, G. M., & MacLeod, C. (2002). Using Taguchi methods to train artificial neural networks in pattern recognition, control and evolutionary applications. في J. C. Rajapakse, X. Yao, L. Wang, K. Fukushima, & S.-Y. Lee (المحررون), ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age (الصفحات 301-305). المقال 1202182 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; المجلد 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. محرر / Jagath C. Rajapakse ; Xin Yao ; Lipo Wang ; Kunihiko Fukushima ; Soo-Young Lee. Institute of Electrical and Electronics Engineers Inc., 2002. الصفحات 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. في JC Rajapakse, X Yao, L Wang, K Fukushima & S-Y Lee (المحررون), 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, المجلد 1, Institute of Electrical and Electronics Engineers Inc., الصفحات 301-305, 9th International Conference on Neural Information Processing, ICONIP 2002, Singapore, Singapore, ١٨/١١/٠٢. 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. محرر / Jagath C. Rajapakse; Xin Yao; Lipo Wang; Kunihiko Fukushima; Soo-Young Lee. Institute of Electrical and Electronics Engineers Inc., 2002. صفحة 301-305 1202182 (ICONIP 2002 - Proceedings of the 9th International Conference on Neural Information Processing: Computational Intelligence for the E-Age; المجلد 1).

نتاج البحث: 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 - https://www.scopus.com/pages/publications/84964999920

UR - https://www.scopus.com/pages/publications/84964999920#tab=citedBy

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. في Rajapakse JC, Yao X, Wang L, Fukushima K, Lee SY, المحررون, 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. صفحة 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

ملخص

سلسلة المنشورات

Conference

أهداف الأمم المتحدة للتنمية المستدامة

الوصول إلى المستند

الملفات والروابط الأخرى

بصمة

قم بذكر هذا