Abstract
We use replica theory to analyse layered networks of binary neurons, with lateral Hebbian-type synapses within individual layers, in combination with strictly feed-forward Hebbian-type synapses between successive layers. The competition between two qualitatively different modes of operation, feed-forward versus lateral, induces interesting transitions, and allows for the identification of an optimal value for the balance between the two synapse types.
Preview
Unable to display preview. Download preview PDF.
References
Amit D.J., Gutfreund H. and Sompolinsky H. (1985) Phys. Rev. Lett. 55 1530
Domany E., Meir R. and Kinzel W. (1986) Europhys. Lett. 2 175
Fassnacht C. and Zippelius A. (1991) Network 2 63
Kurchan J., Peliti L. and Saber M. (1994) J. Phys I (France) 4 1627
Engel A., English H. and Schütte A. (1989) Europhys. Lett. 8 393
English H., Mastropietro V. and Tirozzi B. (1995) J. Phys. I France 5, 85
Wong, K. Y. M., Campbell, C. and Sherrington D. (1995) J. Phys. A 28, 1603
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Coolen, A.C.C., Viana, L. (1997). Competition between feed-forward and lateral information processing in layered neural networks. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032483
Download citation
DOI: https://doi.org/10.1007/BFb0032483
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive