Design of bidirectional associative memories based on the perceptron training technique

Bidirectional associative memories are being used extensively for solving a variety of problems related to pattern recognition. In the present paper, a new synthesis approach is developed for bidirectional associative memories using feedback neural networks. The synthesis problem of bidirectional associative memories is formulated as a set of linear inequalities which can be solved using the perceptron training algorithm. To demonstrate the applicability of the present results a specific example is considered.