Abstract
In this paper, a generalised entropy based associative memory model will be proposed and applied to memory retrievals with analogue embedded vectors instead of the binary ones in order to compare with the conventional autoassociative model with a quadratic Lyapunov functionals. In the present approach, the updating dynamics will be constructed on the basis of the entropy minimization strategy which may be reduced asymptotically to the autocorrelation dynamics as a special case. From numerical results, it will be found that the presently proposed novel approach realizes the larger memory capacity even for the analogue memory retrievals in comparison with the autocorrelation model based on dynamics such as associatron according to the higher-order correlation involved in the proposed dynamics.
This is a preview of subscription content, log in via an institution to check access.
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
Anderson, J.A.: A Simple Neural Network Generating Interactive Memory. Mathematical Biosciences 14, 197–220 (1972)
Kohonen, T.: Correlation Matrix Memories. IEEE Transaction on Computers C-21, 353–359 (1972)
Nakano, K.: Associatron-a Model of Associative Memory. IEEE Trans. SMC-2, 381–388 (1972)
Amari, S.: Neural Theory of Association and Concept Formation. Biological Cybernetics 26, 175–185 (1977)
Amit, D.J., Gutfreund, H., Sompolinsky, H.: Storing Infinite Numbers of Patternsin a Spin-glass Model of Neural Networks. Physical Review Letters 55, 1530–1533 (1985)
Gardner, E.: Structure of Metastable States in the Hopfield Model. Journal of Physics A19, L1047–L1052 (1986)
Kohonen, T., Ruohonen, M.M.: Representation of Associated Pairs by Matrix Operators. IEEE Transaction C-22, 701–702 (1973)
Amari, S., Maginu, K.: Statistical Neurodynamics of Associative Memory. Neural Networks 1, 63–73 (1988)
Morita, M.: Neural Networks. Associative Memory with Nonmonotone Dynamics 6, 115–126 (1993)
Yanai, H.-F., Amari, S.: Auto-associative Memory with Two-stage Dynamics of non-monotonic neurons. IEEE Transactions on Neural Networks 7, 803–815 (1996)
Shiino, M., Fukai, T.: Self-consistent Signal-to-noise Analysis of the Statistical Behaviour of Analogu Neural Networks and Enhancement of the Storage Capacity. Phys. Rev. E48, 867 (1993)
Kanter, I., Sompolinski, H.: Associative Recall of Memory without Errors. Phys. Rev. A 35, 380–392 (1987)
Personnaz, L., Guyon, I., Dreyfus, D.: Information Storage and Retrieval in Spin-Glass like Neural Networks. J. Phys(Paris) Lett. 46, L-359 (1985)
Nakagawa, M.: Chaos and Fractals in Engineering, p. 944. World Scientific Inc., Singapore (1999)
Nakagawa, M.: Autoassociation Model based on Entropy Functionals. In: Proc. of NOLTA 2006, pp. 627–630 (2006)
Nakagawa, M.: Entropy based Associative Model. IEICE Trans. Fundamentals EA-89(4), 895–901 (2006)
Fuchs, A., Haken, H.: Pattern Recognition and Associative Memory as Dynamical Processes in a Synergetic System I. Biological Cybernetics 60, 17–22 (1988)
Fuchs, A., Haken, H.: Pattern Recognition and Associative Memory as Dynamical Processes in a Synergetic System II. Biological Cybernetics 60, 107–109 (1988)
Fuchs, A., Haken, H.: Dynamic Patterns in Complex Systems. In: Kelso, J.A.S., Mandell, A.J., Shlesinger, M.F. (eds.), World Scientific, Singapore (1988)
Haken, H.: Synergetic Computers and Cognition. Springer, Heidelberg (1991)
Nakagawa, M.: A study of Association Model based on Synergetics. In: Proceedings of International Joint Conference on Neural Networks 1993 NAGOYA, JAPAN, pp. 2367–2370 (1993)
Nakagawa, M.: A Synergetic Neural Network. IEICE Fundamentals E78-A, 412–423 (1995)
Nakagawa, M.: A Synergetic Neural Network with Crosscorrelation Dynamics. IEICE Fundamentals E80-A, 881–893 (1997)
Nakagawa, M.: A Circularly Connected Synergetic Neural Networks. IEICE Fundamentals E83-A, 881–893 (2000)
Nakagawa, M.: Entropy based Associative Model. In: Proceedings of ICONIP 2006, pp. 397–406. Springer, Heidelberg (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nakagawa, M. (2008). A Generalised Entropy Based Associative Model. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_21
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_21
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)