Cellular neural networks with effect from friend having most different values and its friends

Generally, in the conventional CNN, each cell is connected to only its neighboring cells according to a template. In this case, the information that a cell can obtain from its neighboring cells is limited. In actual association, we possible to gain different perspectives and grow up by involving different types of friends. Therefore, in this study, we focus on the concept of human relationship in the real world. Then, we propose cellular neural networks with effect from friend having most different values and its friends. The proposed method is the new approach in consideration of the phenomena in such actual society.