Time domain characteristic analysis of non-coupled PCNN

Abstract:

Pulse-coupled neural network (PCNN) is a multi-parameter artificial neural network, and the characteristics of PCNN can be fully explored by analyzing different simplified networks. In this paper, the firing characteristics of non-coupled PCNN with coupled linking term are studied, the mathematical expressions of firing time and interval are summarized, and further the influence of linking weight matrix and linking weight coefficient on network characteristics is analyzed, and the constraints of parameters are given. Finally, extensive verification experiments are carried out for the phenomenon of image edge detection that occurs in the experiments, which provides theoretical support for further research and application of PCNN model.