OPTIMUM LEARNING FOR BIDIRECTIONAL ASSOCIATIVE MEMORY IN THE SENSE OF CAPACITY

Borrowing the idea of Perceptron, Bidirectional Learning (BL) is proposed here to enhance the recall performance of Bidirectional Associative Memory (BAM). By modifying the proof of convergence of Perceptron, we have proved that BL yields one of the solution connection matrices within a finite number of iterations (if the solutions exist). According to the above convergence of BL, the capacity of BAM with BL is larger than or equal to that with any other learning rule. Hence, BL can be considered as an optimum learning rule for BAM in the sense of capacity. Simulations show that BL greatly improves the capacity and the error correction capability of BAM.