Random-coupled Neural Network

arXiv:2403.17512v1 Announce Type: new
Abstract: Improving the efficiency of current neural networks and modeling them in biological neural systems have become popular research directions in recent years. Pulse-coupled neural network (PCNN) is a well applicated model for imitating the computation characteristics of the human brain in computer vision and neural network fields. However, differences between the PCNN and biological neural systems remain: limited neural connection, high computational cost, and lack of stochastic property. In this study, random-coupled neural network (RCNN) …

abstract arxiv become brain computation computer computer vision cs.cv current differences efficiency fields however human improving modeling network networks neural network neural networks popular random research systems them type vision