OpenAIR OpenAIR
 
 

OpenAIR @ RGU >
Design and Technology >
Engineering >
Theses (Engineering) >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10059/358
This item has been viewed 1800 times in the last year. View Statistics

Files in This Item:

File Description SizeFormat
viswanathan A coversheet.pdf55.32 kBAdobe PDFView/Open
Viswanathan B Title and contents.pdf15.81 kBAdobe PDFView/Open
Viswanathan C Chapter 1.pdf28 kBAdobe PDFView/Open
Viswanathan D Chapter 2.pdf24.89 kBAdobe PDFView/Open
Viswanathan E Chapter 3.pdf62.06 kBAdobe PDFView/Open
Viswanathan F Chapter 4.pdf66.55 kBAdobe PDFView/Open
Viswanathan G Chapter 5.pdf71.83 kBAdobe PDFView/Open
Viswanathan H Chapter 6.pdf73.68 kBAdobe PDFView/Open
Viswanathan I Chapter 7.pdf42.9 kBAdobe PDFView/Open
Viswanathan J Chapter 8.pdf25.33 kBAdobe PDFView/Open
Viswanathan K References.pdf14.82 kBAdobe PDFView/Open
Viswanathan L Appendix 1.pdf7.18 kBAdobe PDFView/Open
Viswanathan M Appendix 2.pdf6.87 kBAdobe PDFView/Open
Viswanathan N Appendix 3.pdf53.04 kBAdobe PDFView/Open
Viswanathan O Appendix 4.pdf54.84 kBAdobe PDFView/Open
Title: Using orthogonal arrays to train artificial neural networks.
Authors: Viswanathan, Alagappan
Supervisors: Maxwell, Grant M.
MacLeod, Christopher
Reddipogu, Ann
Keywords: Orthogonal arrays
Artificial neural networks
Taguchi methods
Issue Date: Oct-2005
Publisher: The Robert Gordon University
Citation: VISWANATHAN, A., MACLEOD, C., MAXWELL, G. and KALIDINDI, S., 2005. Training neural networks using Taguchi methods: overcoming interaction problems. In: ICANN 2005, 15th International Conference, Warsaw, Poland, September 11-15, 2005, Proceedings, Part II. Springer. pp. 103-108
Abstract: The thesis outlines the use of Orthogonal Arrays for the training of Artificial Neural Networks. Such arrays are popularly used in system optimisation and are known as Taguchi Methods. The chief advantage of the method is that the network can learn quickly. Fast training methods may be used in certain Control Systems and it has been suggested that they could find application in ‘disaster control,’ where a potentially dangerous system (for example, suffering a mechanical failure) needs to be controlled quickly. Previous work on the methods has shown that they suffer problems when used with multi-layer networks. The thesis discusses the reasons for these problems and reports on several successful techniques for overcoming them. These techniques are based on the consideration of the neuron, rather then the individual weight, as a factor to be optimised. The applications of technique and further work are also discussed.
Appears in Collections:Theses (Engineering)

All items in OpenAIR are protected by copyright, with all rights reserved.

 

 
   Disclaimer | Freedom of Information | Privacy Statement |Copyright ©2012 Robert Gordon University, Schoolhill, Aberdeen, AB10 1FR, Scotland, UK: a Scottish charity, registration No. SCO13781