Abstract
This paper proposes a new correlation matrix network model of associative memory in brain. Each memorized pattern which consists of binary (+1 or-1) elements is preprocessed by a quantized Hadamard transform to increase selectivity. The association ability of a correlation matrix network model depends on the orthogonality between key patterns by which the corresponding memorized patterns are associatively recalled. In a brain model, however, it is rare that the key patterns are mutually orthogonal since they are memorized patterns themselves. The quantized Hadamard transform, presented in this paper, renders the memorized patterns approximately orthogonal. The model is tested by computer simulation.
Similar content being viewed by others
References
Kohonen, T.: Correlation matrix memories. IEEE Trans. Comput. 21, 353–359 (1972)
Kohonen, T., Ruohonen, M.: Representation of associated data by matrix operators. IEEE Trans. Comput. 22, 701–702 (1973)
Kohonen, T.: Associative memory. Berlin, Heidelberg, New York: Springer 1978
Nakano, K.: Associatron — a model of associative memory. IEEE Trans. Syst. Man Cybern. 2, 380–388 (1972)
Reid, R.J., Frame, J.S.: Convergence in iteratively formed correlation matrix memories. IEEE Trans. Comput. 24, 827–830 (1975)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Shiozaki, A. A model of distributed type associative memory with quantized Hadamard transform. Biol. Cybernetics 38, 19–22 (1980). https://doi.org/10.1007/BF00337397
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00337397