Abstract
This paper addresses the following main topics:
-
Definition of the associative memory tasks, auto-association and hetero-association.
-
Use of neural networks and local learning rules for the realization of associative memory.
-
Derivation of the information capacity as an evaluation criterion.
-
Comparision and optimization of local learning rules for associative memory.
-
Sparse, distributed, similarity preserving data representation.
For auto-association and hetero-association the most plausible implementation of an associative memory by means of a neural network with modifiable connections is presented.
The evaluation of the memory’s performance in storing and retrieving information is discussed and the information storage capacity is defined. With respect to this criterion one can optimize the local rules for synaptic modification and the statistical format of the patterns to be stored.
The result is that the patterns should be sparse (i.e. they should contain mostly zeros) and the learning rule should be Hebbian. In the optimal case one can achieve a storage capacity of about 0.7 bit/synapse in hetero-association and 0.35 bit/synapse in auto-association. The second value can not be reached with realistic iterative retrieval procedures, but in practice values of 0.18 bit/synapse can be achieved for auto-association and above 0.6 bit/synapse for hetero-association. We derive some of these results mathematically and present some simulation studies illustrating the asymptotic mathematical calculations.
Finally we present some basic ideas on the construction of sparse, distributed, similarity preserving representation of data.
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. J. Amit. Modelling Brain Function. Cambridge University Press, Cambridge, 1989.
J. A. Anderson. A simple neural network generating an interactive memory. Mathematical Biosciences, 14:197–220, 1972.
O. Ekeberg. Robust dictionary lookup using associative networks. Int. Journal Man-Machine Studies, 28:29–43, 1988.
D.O. Hebb. The Organization of Behavior. Wiley, New York, 1949.
J. Hertz, A. Krogh, and R. G. Palmer. Introduction to the Theory of Neural Computation. Addison Wesley, New York, 1991.
J.J. Hopfield. Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, USA, 79, 1982.
T. Kohonen. Correlation matrix memory. IEEE Transactions on Computers, C-21(4):353–359, 1972.
T. Kohonen. Associative Memory. Springer, Berlin, 1977.
W.A. Little. The existence of persistent states in the brain. Mathematical Biosciences, 19:101–120, 1974.
G. Palm. On associative memory. Biological Cybernetics, 36:19–31, 1980.
G. Palm. Neural Assemblies. Springer, Berlin, 1982.
G. Palm. Local synaptic rules with maximal information storage capacity. Neural and synergetic Computers, 42:100–110, 1988.
G. Palm. Memory capacities of local rules for synaptic modification. Concepts in Neuroscience, 2:97–128, 1991.
G. Palm. On the information storage capacity of local learning rules. Neural Computation, 1992.
G. Palm and F. T. Sommer. Information capacity in recurrent McCulloch-Pitts networks with sparsely coded memory states. Network, 3:1–10, 1992.
F. Schwenker, F. T. Sommer, and G. Palm. Iterative retrieval of sparsely coded associative memory patterns. submitted to Neural Networks, 1993.
C.E. Shannon and I. Mc Carthy, editors. Automata Studies. University Press, Princeton NJ, 1956.
G.L. Shaw and G. Palm, editors. Brain Theory, volume 1 of Advanced Series in Neuroscience. World Scientific, Singapore, 1988.
K. Steinbuch. Mensch und Automat. Springer, Heidelberg, 1961.
U. Stellmann. Ähnlichkeitserhaltende Codierung. PhD thesis, University of Ulm, 1992.
F. T. Sommer. Theorie neuronaler Assoziativspeicher: Lokales Lernen und iteratives Retrieval von Information. PhD thesis, University of Düsseldorf, 1993.
A.M. Uttley. Conditional probability machines and conditioned refexes. In Automata Studies, pages 237–252. University Press, Princeton NJ, 1956.
A. M. Uttley. Temporal and spatial patterns in a contitional probability machine. In Automata Studies, page 277ff. University Press, Princeton NJ, 1956.
D. J. Willshaw, O. P. Buneman, and H. C. Longuet-Higgins. Nonholo-graphic associative memory. Nature, 222:960–962, 1969.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Palm, G., Schwenker, F., Sommer, F.T. (1994). Associative Memory Networks and Sparse Similarity Preserving Codes. In: Cherkassky, V., Friedman, J.H., Wechsler, H. (eds) From Statistics to Neural Networks. NATO ASI Series, vol 136. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79119-2_14
Download citation
DOI: https://doi.org/10.1007/978-3-642-79119-2_14
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-79121-5
Online ISBN: 978-3-642-79119-2
eBook Packages: Springer Book Archive