THE BEHAVIOR OF FORGETTING LEARNING IN BIDIRECTIONAL ASSOCIATIVE MEMORY

Forgetting learning is an incremental learning rule in associative mem ories. With it, the recent learning items can be encoded, and the old learning items will be forgotten. In this article, we analyze the stor age behavior of bidirectional associative memory (BAM) under the forge tting learning. That is, ''Can the most recent k learning item be stor ed as a fixed point?'' Also, we discuss how to choose the forgetting c onstant in the forgetting learning such that the BAM can correctly sto re as many as possible of the most recent learning items. Simulation i s provided to verify the theoretical analysis.