DCBAM: A discrete chainable bidirectional associative memory

A two-layer discrete chainable bidirectional associative memory, DCBAM, is proposed in this paper. As an extension of Kosko's Discrete Bidirectional Associative Memory (DBAM), the proposed DCBAM possesses many advantages such as small correlation matrix; tolerance to noisy, partial and distorted inputs; and convergence within a small number of retrieval cycles. Moreover, the additional chaining feedbacks make the proposed DCBAM capable of multistep retrieval-chaining. That is, given the stored association pairs (A, B), (B, C) and an initial input pattern A, the proposed DCBAM can automatically find the directly-associated pattern B and the sparsely-associated pattern C, which is indirectly related to pattern A, without any prior knowledge of the structures and relationships between these stored association pairs. This is generally realized in previous neural networks by stratifying them into a compound network based on prior knowledge. Extensive experimental results and analysis are presented for discussion.