Encoding Strategy for Maximum Noise Tolerance Bidirectional Associative Memory.

摘要

In this paper, the Basic Bidirectional Associative Memory (BAM) is extended by choosing weights in the correlation matrix, for a given set of training pairs, which result in a maximum noise tolerance set for BAM. This optimized BAM will recall the correct training pair if an input pair is within the maximum noise tolerance set. We define a hyper-radius, and we prove that for a given set of training pairs, the maximum noise tolerance set is the largest, in the sense that at least one pair outside the maximum noise tolerance set, and within a Hamming distance one larger than the hyper-radius associated with the maximum noise tolerance set, will not converge to the correct training pair. A standard Genetic Algorithm (GA) is used to calculate the weights to maximize the objective function which generates a maximum tolerance set for BAM. Computer simulations are presented to illustrate the error correction and fault tolerance properties of the optimized BAM.