The capacity of the Hopfield associative memory
IEEE Transactions on Information Theory
Pattern Recognition
VLSI implementation of a high-capacity neural network associative memory
Advances in neural information processing systems 2
Improving sampled probability distributions for Markov random fields
Pattern Recognition Letters
Structural Matching by Discrete Relaxation
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Bayesian interpretation for the exponential correlation associative memory
Pattern Recognition Letters
Sparse Distributed Memory
An analysis of high-capacity discrete exponential BAM
IEEE Transactions on Neural Networks
The decision-making properties of discrete multiple exponential bidirectional associative memories
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
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 [3] 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 [9], using the Kanerva picture of recall, concluded that the storage capacity was limited by 2N−1/N2 patterns. 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.