Abstract
Neural network techniques for encoding-decoding processes have been developed. The net we have devised can work like a memory retrieval system in the sense of Hopfield, Feinstein and Palmer. Its behaviour for 2R (R ∈ N) input units has some special interesting features. In particular, the accessibilities for each initial symbol may be explicitly computed. Although thermal noise may muddle the code, we show how it can statistically rid the result of unwanted sequences while maintaining the network accuracy within a given bound.
Preview
Unable to display preview. Download preview PDF.
References
Minsky, M. & Papert, S. Perceptrons, (MIT, Cambridge 1969).
Rumelhart, D.E., McClelland, J.L., and the PDP research group, Parallel Distributed Processing: Explorations in the Microstructure of cognition. Vols 1 and 2., (MIT, Cambridge, 1986).
Rumelhart, D.E., Hinton, G.E. & Williams, R.J., Nature 323 533–536 (1986).
Elizalde, E., Gómez, S. and Romeo, A., to be published (1991).
Hopfield, J.J., Feinstein, D.I. & Palmer, R.G. Nature 304 158–159 (1983).
Denby, B., Campbell, M., Bedeschi, F., Chris, N., Bowers, C. & Nesti, F., to be published.
Stimpfi-Abele, G. & Garrido, L. Computer Phys. Commun., to appear (1990).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Elizalde, E., Gómez, S., Romeo, A. (1991). Methods for encoding in multilayer feed-forward neural networks. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035888
Download citation
DOI: https://doi.org/10.1007/BFb0035888
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54537-8
Online ISBN: 978-3-540-38460-1
eBook Packages: Springer Book Archive