Abstract
Bidirectionally trained neural networks would be very useful in many circumstances. Often, we have data available for a prediction problem, but prediction of properties for unknown or new situations is only part of the story. In many cases we know the effect we wish to achieve on the output, but what we do not know is how to modify the inputs to achieve this goal. A basic problem in this area is the inversion of many to one mappings. Our work is based on the popular backpropagation neural network to predict the GDP of developing countries. These networks are integrated with a Self-Organising Map to allow the inversion of many to one mappings.
This is a preview of subscription content, log in via an institution to check access.
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
Kosko, B.: Bidirectional Associative Memories. IEEE Transactions on Systems, Man and Cybernetics SMC-18, 49–60 (1988)
Kosko, B.: Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence. Prince-Hall, Inc., Englewood Cliffs (1992)
Hecht-Nielsen, R.: Counterpropagation Networks. Applied Optics 26(3), 4979–4984 (1987)
Gedeon, T.D.: Stochastic bidirectional training. In: IEEE International Conference on System Man and Cybernetics (SMC 1998), San Diego, pp. 1968–1971 (1998)
Nejad, A.F., Gedeon, T.D.: BiDirectional MLP Neural Networks. In: Proceedings International Symposium on Artificial Neural Networks, Taiwan, pp. 308–313 (1994)
Gedeon, T.D., Harris, D.: Hidden Units in a Plateau. In: 1st International Conference on Intelligent Systems, Singapore, pp. 391–395 (1992)
Gedeon, T.D., Harris, D.: Network Reduction Techniques. In: International Conference on Neural Networks Methodologies and Applications, San Diego, vol. 1, pp. 119–126 (1991)
UNCTAD Statistical Pocket Book, United Nations, New York (1984)
McClelland, J.L., Rumelhart, D.E.: Explorations in Parallel Distributed Processing. MIT Press, Cambridge (1988)
Gedeon, T.D., Good, R.P.: Interactive modelling of a neural network model of GDP. In: International Conference on Modelling and Simulation, Perth, pp. 355–360 (1993)
Slade, P., Gedeon, T.D.: Bimodal Distribution Removal. In: Mira, J., Cabestany, J., Prieto, A.G. (eds.) IWANN 1993. LNCS, vol. 686, pp. 249–254. Springer, Heidelberg (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mus, A.O. (2010). Inversion of Many-to-one Mappings Using Self-Organising Maps. In: Wong, K.W., Mendis, B.S.U., Bouzerdoum, A. (eds) Neural Information Processing. Models and Applications. ICONIP 2010. Lecture Notes in Computer Science, vol 6444. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17534-3_55
Download citation
DOI: https://doi.org/10.1007/978-3-642-17534-3_55
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17533-6
Online ISBN: 978-3-642-17534-3
eBook Packages: Computer ScienceComputer Science (R0)