Storage capacity of the exponential correlation associative memory
In this paper we analyze the pattern storage capacity of the exponential correlation associative memory(ECAM). This architecture was first studied by Chiueh and Goodman  who concluded that, under certain conditions on the input patterns, the memory has a storage capacity that was exponential in the length of the bit-patterns. A recent analysis by Pelillo and Hancock , using the Kanerva picture of recall, concluded that the storage capacity was limited by 2N−1/N2. Both of these analyses can be criticised on the basis that they overlook the role of initial bit-errors in the recall process and deal only with the capacity for perfect pattern recall. In other words, they fail to model the effect of presenting corrupted patterns to the memory. This can be expected to lead to a more pessimistic limit. Here we model the performance of the ECAM when presented with corrupted input patterns. Our model leads to an expression for the storage capacity of the ECAM both in terms of the length of the bit-patterns and the probability of bit-corruption in the original input patterns. These storage capacities agree closely with simulation. In addition, our results show that slightly superior performance can be obtained by selecting an optimal value of the exponential constant.
KeywordsExponential correlation associative memory storage capacity
Unable to display preview. Download preview PDF.
- 4.T. D. Chiueh and R. M. Goodman, “VLSI implementation of a high-capacity neural network associative memory”, in D. S. Touretzky, Ed., Advances in Neural Information Processing Systems 2. San Mateo, CA: Morgan-Kaufmann, 1990, pp. 793–800.Google Scholar
- 13.P. A. Chou, “The capacity of the Kanerva associative memory is exponential,” in D. Z. Anderson, Ed., Neural Information Processing Systems. New York, NY: American Institute of Physics, 1988, pp. 184–191.Google Scholar