PYRAMIDAL CELLS - A NOVEL CLASS OF ADAPTIVE COUPLING CELLS AND THEIR APPLICATIONS FOR CELLULAR NEURAL NETWORKS

A significant increase in the information processing abilities of CNN' s demands powerful information processing at the cell level. In this p aper, the defining formula, the main properties, and several applicati ons of a novel coupling cell are presented. Since it is able to implem ent any Boolean function, its functionality expands on those of digita l RAM's by adding new capabilities such as learning and interpolation. While it is able to embed all previously accumulated knowledge regard ing useful binary information processing tasks performed by standard C NN's, the pyramidal universal cell provides a broader context for defi ning other useful processing tasks, including extended gray scale or c olor image processing as well. Examples of applications in image proce ssing are provided in this paper. Implementation issues are also consi dered, Assuming some compromise between area and sped, a VLSI implemen tation of CNN's based on pyramidal cells offers a speedup of up to one million times when compared to corresponding software implementations .