Bidirectional Retrieval from AssociativeMemoryFriedrich

Similarity based fault tolerant retrieval in neural associative memories (NAM) has not lead to wiedespread applications. A drawback of the eecient Willshaw model for sparse patterns Ste61, WBLH69], is that the high asymptotic information capacity is of little practical use because of high cross talk noise arising in the retrieval for nite sizes. Here a new bidirectional iterative retrieval method for the Willshaw model is presented, called crosswise bidi-rectional (CB) retrieval, providing enhanced performance. We discuss its asymptotic capacity limit, analyze the rst step, and compare it in experiments with the Willshaw model. Applying the very eecient CB memory model either in information retrieval systems or as a functional model for reciprocal cortico-cortical pathways requires more than robustness against random noise in the input: Our experiments show also the segmentation ability of CB-retrieval with addresses containing the superposition of pattens, provided even at high memory load.