Bidirectional Associative Memory (Two-layer)

Introduction: -Kosko (1988) extended the Hopfield model, which is single layer, by incorporating an additional layer to perform recurrent auto-associations as well as hetero-associations on the stored memories. The network structure of the bidirectional associative memory model is similar to that of the linear associator but the connections are bidirectional; i.e.,

w_ij = w_ji, for i = 1, 2, . . . , n and j = 1, 2, . . . , m.

In the bidirectional associative memory, a single associated pattern pair is stored by computing the weight matrix as

W_k =X_K^TY_k .

The construction of the connection weight matrix W, to store p different associated pattern pairs simultaneously, is accomplished by summing up the individual correlation matrices W_k

where α is the proportionality or normalizing constant.