Encoding strategy for maximum noise tolerance bidirectional associative memory

• Published in: IEEE transactions on neural networks Vol. 16; no. 2; pp. 293 - 300
• Main Authors: Shen, D., Cruz, J.B.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.03.2005; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Artificial intelligence; Associative memory; Bidirectional associative memory (BAM); Computer science; control theory; systems; Computer simulation; Connectionism. Neural networks; Electricity; Encoding; energy well hyper-radius; Error correction; Exact sciences and technology; Fault tolerance; Genetic algorithms; Hamming distance; Magnesium compounds; Memory; Models, Neurological; Models, Statistical; neural network training; Neural networks; Neural Networks (Computer); noise tolerance set; Pattern recognition; Attraction; Hamming distance; Computer simulation; String matching; Correlation matrix; Neural network; Bidirectional associative memory; Fault tolerance; Genetic algorithm; Weight function; Correlation function; Error correction; Objective function
• ISSN: 1045-9227; 1941-0093
• DOI: 10.1109/TNN.2004.841793

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. We prove that for a given set of training pairs, the maximum noise tolerance set is the largest, in the sense that this optimized BAM will recall the correct training pair if any input pattern is within the maximum noise tolerance set and at least one pattern outside the maximum noise tolerance set by one Hamming distance will not converge to the correct training pair. This maximum tolerance set is the union of the maximum basins of attraction. 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.