Improved storage capacity in correlation matrix memories storing fixed weight codes

• Autorzy: Hobson S. , Austin J.
• Języki publikacji: EN

Abstrakty

EN

In this paper we introduce an improved binary correlation matrix memory (CMM) with better storage capacity when storing sparse fixed weight codes generated with the algorithm of Baum et al. [10]. We outline associative memory, and describe the binary correlation matrix memory— a specific example of a distributed associative memory. The importance of the representation used in a CMM for input and output codes is discussed, with specific regard to sparse fixed weight codes. We present an analysis of the benefits of an algorithm for the generation of fixed weight codes, originally given by Baum et al. [4]. The properties of this algorithm are briefly discussed, including possible thresholding functions which could be used when storing these codes in a CMM; L-max and L-wta. Finally, results generated from a series of simulations are used to demonstrate that the use of L-wta as a thresholding function provides an increase in storage capacity of around 15% over L-max.

Słowa kluczowe

EN

correlation matrix memory; CMM; storage capacity; associative memory; fixed weight code; L-max; L-wta

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2011
• Tom: Vol. 1, No. 2
• Strony: 97--102
• Opis fizyczny: Bibliogr. 10 poz., rys.

Twórcy

autor

Hobson S.

• Department of Computer Science, University of York, York, UK

autor

Austin J.

• Department of Computer Science, University of York, York, UK

Bibliografia

• [1] J. Austin. T. Stonham. Distributed associative memory for use in scene analysis. Image and Vision Computing 5. 251-260. 1987.
• [2] J. Austin. J. V. Kennedy and K. Lees. A neural architecture for fast rule matching. In Artificial Neural Networks and Expert Systems Conference. 1995.
• [3] J. Austin. Associative Memories. In Handbook of Neural Computation. E. Fiesler. R. Beale (editors).Oxford University Press. 1997.
• [4] E. B. Baum. J. Moody and F. Wilczek. Internal representations for associative memory. Biological Cybernetics, 59(4):217-228. 1988.
• [5] D. Casasent. B. Telfer. High capacity pattern recognition associative processors. Neural Net-works. 5.687-698. 1992.
• [6] S. Haykin. Neural Networks. A Comprehensive Foundation Second Edition. Prentice Hall. 1999
• [7] J. Nadal. G. Toulouse. Information storage in sparsely coded memory nets. Network. I. 61-74. 1990.
• [8] G. Palm. Neural Assemblies. Springer-Verlag. 1982.
• [9] G. Palm. F Schwenker. FT. Sommcr and A. Strey ,Neural associative memories Associative processing and processors. 307-326. 1997.
• [10] D. J. Willshaw. O. P. Buneman and H. C. Longuet Higgins. Non-holographic associative memory. Nature. 222(7):960-962. 1969.