作者: Jiali Yu , Zhang Yi , Lei Zhang
DOI: 10.1109/ICCIS.2008.4670875
关键词: Artificial neural network 、 Theoretical computer science 、 Attractor 、 Transfer function 、 Cellular neural network 、 Multistability 、 Content-addressable memory 、 Recurrent neural network 、 Computer science 、 Discrete time and continuous time
摘要: To describe the encoding of continuous stimuli in neural networks, attractors have been recognized as promising models. A attractor is a set connected stable equilibrium points. It exhibits interesting dynamical properties many recurrent networks. This paper studies discrete-time cellular networks (DCNNs). The main contribution that representations for DCNNs are obtained under some conditions. Such important results provide clear and complete descriptions to DCNNs.