Coexistence of Multiple Continuous Attractors for Lower-Ordered Neural Networks
International Journal of Computer Mathematics/International journal of computer mathematics(2019)
摘要
A continuous attractor of recurrent neural network is a connected set of stable equilibrium points. It's widely used to interpret a lot of brain activities. A large number of literatures have studied discrete attractors and single continuous attractor. In this paper, the coexisting continuous attractors for nonlinear neural networks is studied and the coexisting conditions of two continuous attractors for network with and without external input in two-dimensional space are obtained by analysing the eigenvalues of the matrix. Finally, all the results are verified by simulation.
更多查看译文
关键词
Multiple,continuous attractors,coexistence,linear threshold neural network
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要