Multistability of Discrete-Time Recurrent Neural Networks With Unsaturating Piecewise Linear Activation Functions

2004 ◽  
Vol 15 (2) ◽  
pp. 329-336 ◽  
Author(s):  
Z. Yi ◽  
K.K. Tan
2011 ◽  
Vol 467-469 ◽  
pp. 731-736
Author(s):  
Zong Bing Lin ◽  
Qian Rong Tan ◽  
Jun Li

Globally exponentially stability (GES) of a class of discrete- time recurrent neural networks with unsaturating linear activation functions is studied. Based on matrix eigenvalue, a new definition of GES is presented. By applying matrix theory, some conditions for GES are obtained. Simultaneously, those conditions are proved without energy functions.


2014 ◽  
Vol 28 (19) ◽  
pp. 1450118 ◽  
Author(s):  
Huaguang Zhang ◽  
Yujiao Huang ◽  
Tiaoyang Cai ◽  
Zhanshan Wang

In this paper, multistability is discussed for delayed recurrent neural networks with ring structure and multi-step piecewise linear activation functions. Sufficient criteria are obtained to check the existence of multiple equilibria. A lemma is proposed to explore the number and the cross-direction of purely imaginary roots for the characteristic equation, which corresponds to the neural network model. Stability of all of equilibria is investigated. The work improves and extends the existing stability results in the literature. Finally, two examples are given to illustrate the effectiveness of the obtained results.


Sign in / Sign up

Export Citation Format

Share Document