Abstract
A neural network is a complex system consisting of a large number of mutually connected elements having a simple input-output relation. Its behavior is highly non-linear, so that it is in general difficult to analyze its dynamical behavior of information processing. In order to elucidate a typical behavior, we study a network whose connection weights or synaptic efficacies of connections are randomly generated and then fixed. Given a probability law of connection weights, we have an ensemble of randomly generated networks. Statistical neurodynamics provides a theoretical method to search for macroscopic behaviors which are shared by all typical random networks in the ensemble, i.e. those networks generated by the same probability law.
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
Amari, S. [ 1971 ]: “Characteristics of randomly connected threshold element networks and network systems”, Proc. IEEE, 59, 35–47.
Amari, S. [ 1972a ]: “Characteristics of random nets of analog neuron-like elements”, IEEE Trans., SMC-2, 643–657.
Amari, S. [ 1974 ]: “A method of statistical neurodynamics”, Kybernetik, 14, 201–215.
Amari, S. Yoshida, K., and Kanatani, K. [19 7 7]: “A mathematical foundation for statistical neurodynamics”, SIAM J. App. Math., 33, 95–126.
Amari, S. andMaginu,K. [ 1988 ]: “Statistical neurodynamics of associative memory”, Neural Networks, 1, 63–73
Nakano, K. [ 1972 ]: “Association — a model of associative memory”, IEEE Trans., SMC-2, 381–388
Kohonen, T. [ 1972 ]: “Correlation matrix memories”, IEEE Trans., C-21, 353–359.
Anderson, J. A. [ 1972 ]: “A simple neural network generating interactive memory”, Math. Biosciences, 14, 197–220.
Amari, S. [ 1972 ]: “Learning patterns and pattern sequences by self-organizing nets of threshold elements”, IEEE Trans., C-21, 1197–1206.
Amari, S. [ 1977 ]: “Neural theory of association and concept-formation”, Biol. Cybernetics, 26, 175–185.
Hopfield, J. J.[ 1982 ]: “Neural networks and physical systems with emergent collective computational abilities”, P. Nat. Acad. Sci. U.S.A., vol. 79, 2445–2458.
Amit, D. J., Gutfreund, H. and Sompolinsky, H. [ 1986 ]: “Spin-glass models of neural networks”, Phys. Rev., A2, 1007–1018.
Meir, R. and Domany, E. [ 1987 ]: “Exact solution of a layered neural network memory”, Phy. Rev. Lett., 59, 359–362.
McEliece, R. J. et. al. [ 1987 ]: “The Capacity of the Hopfield associative memory”, IEEE Trans., Inf. Theory, IT-33, 461–482.
Kosko, B. [ 1987 ]: “Adaptive bilateral associative memory”, Appl. Oct., 26, 4947–4960.
Okajima, K., Tanaka, S. and Fujiwara, S. [ 1977 ]: “A heteroassociative memory network wirh feedback connection”, Proc. 1st Int. Conf. Neural Networks, II -711–II -718.
Cottrell, M. [ 1988 ]: “Stability and attractivity in associative memory networks”, Biol. Cybern, 58, 129–139.
Kinzel, W. [ 1985 ]: “Learning and pattern recognition in spin glass models”, Z. Physik, B60, 205–213.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1988 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Amari, Si. (1988). Associative Memory and Its Statistical Neurodynamical Analysis. In: Haken, H. (eds) Neural and Synergetic Computers. Springer Series in Synergetics, vol 42. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-74119-7_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-74119-7_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-74121-0
Online ISBN: 978-3-642-74119-7
eBook Packages: Springer Book Archive