IMAGE PROCESSING USING CELLULAR NEURAL NETWORKS BINARY NEURONS BASED ON MULTI-VALUED AND UNIVERSAL
Igor N. Aizenberg, Naum N. Aizenberg, Taras Bregin, Constantine Butakoff, Elya Farberov · 2000
Multi-valued and universal binary neurons (MVN and UBN) are the neural processing elements with complex-valued weights and high functionality. It is possible to implement an arbitrary mapping, described by partially-defined multiple-valued fbnction on the single MVN, and an arbitrary mapping, described by partially-defined or full-defined Boolean function (which can be not threshold) on the single UBN. The fast-converging learning algorithms exist for both types of neurons. Such features of the MVN and UBN may be used to solve different kinds of problems. One of the most successful applications of the MVN and UBN is their use as the basic neurons in the Cellular Neural Networks (CNN) to solve image processing and image analysis problems.