Chen T, Amari S I
Lab of Nonlinear Science, Institute of Mathematics, Fudan University, Shanghai, P.R. China.
IEEE Trans Neural Netw. 2001;12(1):159-63. doi: 10.1109/72.896806.
In this paper, we discuss dynamical behaviors of recurrently asymmetrically connected neural networks in detail. We propose an effective approach to study global and local stability of the networks. Many of well known existing results are unified in our framework, which gives much better test conditions for global and local stability. Sufficient conditions for the uniqueness of the equilibrium point and its stability conditions are given, too.
在本文中，我们详细讨论了循环非对称连接神经网络的动力学行为。我们提出了一种研究该网络全局和局部稳定性的有效方法。许多现有的著名结果在我们的框架中得到了统一，这为全局和局部稳定性提供了更好的测试条件。同时也给出了平衡点唯一性的充分条件及其稳定性条件。
