Abstract
We study the macroscopic dynamics of a three-state mean- field neural network, by using information theory principles. The results are expressed in terms of the relevant order parameters of the system, The network is composed by bilinear and biquadratic synaptic inter- actions, which yields an improvement of the storage and information properties of the network, measured by the mutual information and the basins of attraction. The introduction of a self-adaptive mechanism in the synapses is analyzed. The coexistence of the usual retrieval phase with a quadrupolar phase, as well as with a new informative anti-quadrupolar phase, is observed.
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
D. Dominguez and D. Bollé, Phys. Rev. Lett. 80, 2961 (1998).
D. Dominguez and E. Korutcheva, Phys.Rev.E 62(2), (2000) 2620–2628
D. Bollé, D. Dominguez and S. Amari, Neural Networks 13, 455 (2000); D.Bollé and D.Dominguez, Physica A 286, 401 (2000).
C.E. Shannon, A Mathematical Theory of Communication, The Bell System Technical Journal, v.27 (1948).
D. Bollé, G.M. Shim, B. Vinck, and V. A. Zagrebnov, J. Stat. Phys. 74, 565 (1994).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dominguez, D.R.C. (2003). The Antiquadrupolar Phase of the Biquadratic Neural Network. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_59
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_59
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive