Abstract
Taguchi Methods (and other orthogonal arrays) may be used to train small Artificial Neural Networks very quickly in a variety of tasks. These include, importantly, Control Systems. Previous experimental work has shown that they could be successfully used to train single layer networks with no difficulty. However, interaction between layers precluded the successful reliable training of multi-layered networks. This paper describes a number of successful strategies which may be used to overcome this problem and demonstrates the ability of such networks to learn non-linear mappings.
An erratum to this chapter can be found at http://dx.doi.org/10.1007/11550907_163 .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
MacLeod, C., Dror, G., Maxwell, G.M.: Training Artificial Neural Networks Using Taguchi Methods. In: AI Review, vol. 3(13), pp. 177–184. Kluwer, Dordrecht (1999)
Dror, G.: Training Neural Networks Using Taguchi Methods, MSc thesis, The Robert Gordon University (1995)
Stoica, A., Blosiu, J.: Neural Learning Using Orthogonal Arrays. In: Proceedings of the International Symposium on Intelligent Systems, Reggio (Italy), pp. 418–423. IOS Press, Amsterdam (1997)
Roy, R.K.: A Primer on the Taguchi Method. Wiley, New York (1990)
Maxwell, G., MacLeod, C.: Using Taguchi Methods To Train Artificial Neural Networks In Pattern Recognition, Control And Evolutionary Applications. In: Proceedings of the International Conference on Neural Information Processing (ICONIP 2002), Singapore, vol. 1, pp. 301–305 (2002)
Viswanathan, A.: Using Orthogonal Arrays to Train Artificial Neural Networks, MPhil Thesis, forthcoming
Dey, A.: Orthogonal Fractional Factorial Designs. Wiley, New York (1985)
Owen, A.: Orthogonal Arrays for Computer Experiments. Integration and Visualization, Statistica Sinica 2, 439–452 (1992)
Capanni, N., MacLeod, C., Maxwell, G.: An Approach to Evolvable Neural Functionality. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 220–223. Springer, Heidelberg (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Viswanathan, A., MacLeod, C., Maxwell, G., Kalidindi, S. (2005). Training Neural Networks Using Taguchi Methods: Overcoming Interaction Problems. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds) Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005. ICANN 2005. Lecture Notes in Computer Science, vol 3697. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11550907_17
Download citation
DOI: https://doi.org/10.1007/11550907_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28755-1
Online ISBN: 978-3-540-28756-8
eBook Packages: Computer ScienceComputer Science (R0)