ISNN '07 Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks
Multistability of Neural Networks with a Class of Activation Functions
ISNN '09 Proceedings of the 6th International Symposium on Neural Networks on Advances in Neural Networks
Convergence for a class of delayed recurrent neural networks without M-matrix condition
Journal of Computational and Applied Mathematics
Global exponential stability of a class of neural networks with variable delays
Computers & Mathematics with Applications
Global convergence of continuous-time recurrent neural networks with delays
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part I
| Hi-index | 0.00 |
We discuss some delayed dynamical systems, investigating their stability and convergence in a critical case. To ensure the stability, the coefficients of the dynamical system must satisfy some inequalities. In most existing literatures, the restrictions on the coefficients are strict inequalities. The tough question is what will happen in the case (critical case) the strict inequalities are replaced by nonstrict inequalities (i.e., "<" is replaced by "⩽"). The purpose of the paper is to discuss this critical case and give an affirmative answer in the case that the activation functions are hyperbolic tangent