Unlearning algorithm in associative memory

We incorporate into a synthesis procedure for a class of discrete-time neural networks an unlearning capability. The proposed technique increases storage capacity while maximizing the domain of attraction of each desired pattern to be stored. Making use of learning and forgetting capabilities, neural networks generated by the method advanced herein are capable of learning new patterns as well as forgetting learned patterns without the necessity of recomputing the entire interconnection weights and external inputs. The unlearning algorithm developed is then utilized off-line to equalize the basins of attraction for each desired pattern to be stored, and to minimize the number of spurious states. Specific examples are given to illustrate the strengths and weaknesses of the methodology advocated herein