An autonomous digital neural network architecture for segmenting hand-printed characters into visually pleasing and low variability sub-classes

Summary form only given. A novel self-organizing neural network architecture has been developed which segments examples of hand-printed characters into subclusters of limited variability. This reduction in variability aids the recognition task of the network, and results obtained not only show a promising improvement over existing recognition techniques, but also indicate better performance than for supervised systems in which a human teacher selects the subclass exemplars.<
>