Context-dependent associations in linear distributed memories
In this article we present a method that allows conditioning of the response of a linear distributed memory to a variable context. This method requires a system of two neural networks. The first net constructs the Kronecker product between the vector input and the vector context, and the second net supports a linear associative memory. This system is easily adaptable for different goals. We analyse here its capacity for the conditional extraction of features from a complex perceptual input, its capacity to perform quasi-logical operations (for instance, of the kind of “exclusive-or”), and its capacity to structurate a memory for temporal sequences which access is conditioned by the context. Finally, we evaluate the potential importance of the capacity to establish arbitrary contexts, for the evolution of biological cognitive systems.
KeywordsAssociative Memory Kronecker Product Biological Neural Network Context Vector Allosteric Protein
Unable to display preview. Download preview PDF.
- — 1983. “Cognitive and Psychological Computation with Neural Models”.IEEE Trans. Systems. Man Cybernetics 13, 799–815.Google Scholar
- Cooper, L. N. 1973. “A Possible Organization of Animal Memory and Learning.” In Proceedings of the Nobel Symposium on Collective Properties of Physical Systems, B. Lundquist and S. Lundquist (Eds) New York: Academic Press.Google Scholar
- Monod, J. 1967. Leçon inaugurale, Collège de France.Google Scholar
- Ribchester, R. R. 1986.Molecule, Nerve and Embryo. Glasgow: Blackie.Google Scholar
- Rumelhart, D. E., G. E. Hinton and J. L. McClelland. 1986. “A General Framework for Parallel Distributing Processing”. InParallel Distributing Processing, D. E. Rumelhart and J. L. McClelland (Eds). Massachusetts: MIT Press.Google Scholar
- Stone, G. O. 1986. “An Analysis of the Delta Rule and the Learning of Statistical Associations”. InParallel Distributing Processing, D. E. Rumelhart and J. L. McClelland (Eds). Massachusetts: MIT Press.Google Scholar