A neural network implementation of adaptive BAM

Summary form only given, as follows. The general formulation of bidirectional associative memories (BAM) presents certain difficulties when the associations of pairs of patterns do not suppose a local energy minimum. To avoid these problems, the authors describe an adaptive scheme which allows the correlation matrix to be modified so as to reach the energy minimum while at the same time identifying the input patterns. The strategy used allows the adaptation of the matrix to be performed for each external input, so that it can henceforth be described as a supervised type of training scheme. A consequence is its synthesis by means of neural networks with both the BAM and the adaptive mechanism itself integrated in distinct layers, allowing either of them to be changed without altering the others. The proposed scheme is an extension of the well-known neural synthesis for associative memories through easy rules for building it