Optimal gradient descent learning for bidirectional associative memories
R. Perfetti · Electronics Letters · 1993
A learning algorithm for bidirectional associative memories (BAMs) is presented, which results in a greatly enhanced storage capacity. The design strategy is formulated as a convex optimisation problem, and then solved by a steepestdescent approach. The proposed method guarantees the storage of all the training pairs as stable states of the BAM. Computer simulation results are presented to demonstrate the performance of the proposed algorithm.