UNLEARNING IN NEURAL NETWORKS WITH MANY-NEURON INTERACTIONS
M. C. D. Barrozo, T. J. P. Penna · International Journal of Modern Physics C · 1994
We present a version of a multineuron interaction model that includes unlearning. Through extensive numerical simulations we can show that unlearning increases the performance of the network with respect to retrieval of stored informations by enlarging the basins of attraction. Relationships that allow us to estimate the optimal performance in the learning stage of this model were found.