UNIPOLAR INTERPATTERN ASSOCIATION NEURAL NETWORKS

A method for constructing a unipolar interconnection weight matrix (IW M) of the interpattern association (IPA) model is presented. By a sear ch of the redundant interconnection links, a method that removes all n egative links is introduced. Since the IWM is unipolar, the difficulty of implementing positive and negative IWM's can be avoided. Computer simulation and experimental results show that the unipolar IWM IPA neu ral network. performs better than the bipolar IWM IPA model.