Abstract
We study Ising spin models for neural networks with spatial structure, in which patterns are stored according to Hebb's rule. From the microscopic dynamics given by the master equation we derive a partial differential equation for the position- and time-dependent correlations between the system state and the stored patterns. This equation can be used to study networks with finite range connections (not necessarily symmetric), the behaviour of domain boundaries and information transport. For systems with finite range connections we can compute the range of macroscopic order.
Preview
Unable to display preview. Download preview PDF.
References
W.A. Little, Math. Biosci. 19 (1974) 101
J.J. Hopfield, Proc. Natl. Acad. Sci. U.S.A. 79 (1982) 2554
D.O. Hebb, The organization of behaviour (1949). New York, Wiley
D.J. Amit, H. Gutfreund & H. Sompolinsky, Phys. Rev. A32 (1985) 1007
D.J. Amit, H. Gutfreund & H. Sompolinsky, Phys. Rev. Lett. 55 (1985) 1530
D.J. Amit, H. Gutfreund & H. Sompolinsky, Phys. Rev. A35 (1987) 2293
J.L. van Hemmen, D. Grensing, A. Huber & R. Kuehn, Z. Phys. B65 (1986) 53
B. Derrida, E. Gardner & A. Zippelius, Europhys. Lett. 4 (1987) 167
A.C.C. Coolen & Th.W. Ruijgrok, Phys. Rev. A38 (1988) 4253
A.J. Noest, Phys. Rev. Lett. 63 (1989) 1739
I. Kanter, Phys. Rev. Lett. 60 (1988) 1891
A. Canning & E. Gardner, J. Phys. A21 (1988) 3275
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1990 Springer-Verlag
About this paper
Cite this paper
Coolen, A.C.C. (1990). Ising-spin neural networks with spatial structure. In: Garrido, L. (eds) Statistical Mechanics of Neural Networks. Lecture Notes in Physics, vol 368. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3540532676_63
Download citation
DOI: https://doi.org/10.1007/3540532676_63
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-53267-5
Online ISBN: 978-3-540-46808-0
eBook Packages: Springer Book Archive