Abstract
Conventional artificial neural networks are based on greatly simplified models of biological neurons. In particular only one path exists to carry an input signal to the neuron body. The design of a parallel path artificial micro-net is described which can be used as the basic building block to construct networks. Preliminary training results are presented.
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
Boers, E.J.W., Kuiper, H.: Biological metaphors and the design of modular artificial neural networks. Masters’ thesis, Leiden Univesity, Netherlands
Jordan, J.M., Jacobs, R.A.: Hierarchical Mixtures of Experts and the EM Algorithm. Neural Computation 6, 181–214
Lundberg, J.M., Hokfelt, T.: Neurotransmitters in Action, p. 113. Elsevier Biomedical Press, New York (1985)
Rocha, A.F., Machado, R.J., Gomide, F.: Updating the Biology of the Artiicial Neuron. Fuzzy Logic, pp. 237–249. Kluwer Academic Publishers, Dordrecht
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Murray, G., Hendtlass, T., Podlena, J. (1999). The Parallel Path Artificial Micronet. In: Imam, I., Kodratoff, Y., El-Dessouki, A., Ali, M. (eds) Multiple Approaches to Intelligent Systems. IEA/AIE 1999. Lecture Notes in Computer Science(), vol 1611. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-48765-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-540-48765-4_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66076-7
Online ISBN: 978-3-540-48765-4
eBook Packages: Springer Book Archive