Improving bidirectional associative memory performance by unlearning

An encoding strategy for improving the noise tolerance and capacity of Kosko´s bidirectional associative memory is proposed. Energy minima corresponding to pattern pairs that are to be stored are enhanced, and, simultaneously, unwanted or spurious states are eliminated. The method is an extension of the multiple training procedure that has been described in the literature for inducing local minima at desired locations. An additional unlearning term in the energy expression is included to eliminate spurious states. Spurious states and parameter values for constructing the network were determined experimentally. Computer simulations showed that unlearning increases the network´s storage capacity and its tolerance to noise to a level not achievable by multiple training alone