Abstract
A potential replacement for the conventional neuron is introduced. This is called a Macronet element and uses multiple channels per signal path with each channel containing two trainable non-linear structures in addition to a conventional weight. The authors show that such an architecture provides a rich spectrum of higher order powers and cross products of the inputs using less weights than earlier higher order networks. This lower number of weights does not compromise the ability of the Macronet element to generalise. Results from training a Macronet element to develop a relationship from a sparse map of Europe are given.
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
Ghosh, J. et. al. “Proceedings of the IEEE Conference on Neural Networks for Ocean Engineering” (1991).
Giles, C. L. and Maxwell. T. “Applied Optics”26, 4972–4978 (1987).
Klir, J. a. Valach, M. “Cybernetic Modelling” Iliffe Books, London. (1965).
Lundberg, J. M. and Hokfelt, T. “Neurotransmitters in Action” Elsevier Biomedical Press New York. (1985).
Picton, P. D. “2nd. International Conference on Artificial Neural Networks” 290–294 (1991).
Picton, P. D. “Neural Networks” Palgrave, New York. (2000).
Poggio, T. “Biological Cybernetics” 19, 201–209 (1975).
Rumelhart, D. E. and McClelland, J. L. “Parallel Distributed Processing” MIT Press, Cambridge, MA. (1986).
Shin, Y. and Ghosh, J. “Proceedings of the Conference on Artificial Neural Networks in Engineering” (1991).
Shin, Y. and Ghosh, J. “Proceedings of the International Joint Conference on Neural Networks” (1992).
Shin, Y. and Ghosh, J. “International Journal of Neural Systems” 3 (1992).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Hendtlass, T., Murray, G. (2002). The Macronet Element: A Substitute for the Conventional Neuron. In: Hendtlass, T., Ali, M. (eds) Developments in Applied Artificial Intelligence. IEA/AIE 2002. Lecture Notes in Computer Science(), vol 2358. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48035-8_21
Download citation
DOI: https://doi.org/10.1007/3-540-48035-8_21
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43781-9
Online ISBN: 978-3-540-48035-8
eBook Packages: Springer Book Archive