scholarly journals Novel Stability Results for Halanay Inequality and Applications to Delay Neural Networks

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 19504-19511
Author(s):  
Dehao Ruan ◽  
Weiguo Liu ◽  
Minran Yang ◽  
Zhehao Huang ◽  
Xiaoxia Guo
Keyword(s):  
Neural Networks ◽  
Halanay Inequality ◽  
Stability Results

New stability results for delayed neural networks

2017 ◽  
Vol 311 ◽  
pp. 324-334 ◽  
Author(s):  
Hanyong Shao ◽  
Huanhuan Li ◽  
Chuanjie Zhu
Keyword(s):  
Neural Networks ◽  
Delayed Neural Networks ◽  
Stability Results

scholarly journals On Stability of Nonautonomous Perturbed Semilinear Fractional Differential Systems of Order α∈(1,2)

2018 ◽  
Vol 2018 ◽  
pp. 1-10 ◽  
Author(s):  
Mohammed M. Matar ◽  
Esmail S. Abu Skhail
Keyword(s):  
Neural Networks ◽  
Differential Equations ◽  
Fractional Order ◽  
Fractional Differential Equations ◽  
Protected Area ◽  
Marine Protected Area ◽  
Differential Systems ◽  
Fractional Differential Systems ◽  
Fractional Differential ◽  
Stability Results

We study the Mittag-Leffler and class-K function stability of fractional differential equations with order α∈(1,2). We also investigate the comparison between two systems with Caputo and Riemann-Liouville derivatives. Two examples related to fractional-order Hopfield neural networks with constant external inputs and a marine protected area model are introduced to illustrate the applicability of stability results.

ASYMPTOTIC HYPERSTABILITY OF A CLASS OF NEURAL NETWORKS

1999 ◽  
Vol 09 (02) ◽  
pp. 95-98 ◽  
Author(s):  
ANKE MEYER-BÄSE
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Sufficient Conditions ◽  
Necessary And Sufficient Conditions ◽  
Lyapunov Methods ◽  
Network Parameters ◽  
The Stability ◽  
Necessary And Sufficient ◽  
Stability Results

This paper is concerned with the asymptotic hyperstability of recurrent neural networks. We derive based on the stability results necessary and sufficient conditions for the network parameters. The results we achieve are more general than those based on Lyapunov methods, since they provide milder constraints on the connection weights than the conventional results and do not suppose symmetry of the weights.

Polynomial dissipativity of proportional delayed BAM neural networks

2020 ◽  
Vol 13 (06) ◽  
pp. 2050050 ◽  
Author(s):  
Lin Xing ◽  
Liqun Zhou
Keyword(s):  
Neural Networks ◽  
Simulation Experiment ◽  
Lyapunov Functionals ◽  
Bam Neural Networks ◽  
Close Attention ◽  
Halanay Inequality ◽  
Attracting Set ◽  
The Relationship ◽  
Theoretical Condition ◽  
Generalized Halanay Inequality

This paper pays close attention to the global polynomial dissipativity (GPD) for proportional delayed BAM neural networks (PDBAMNNs). The global exponential dissipativity (GED) and the global dissipativity (GD) are also talked about. Under the help of novel Lyapunov functionals and a generalized Halanay inequality, a set of dissipative criteria for such systems are led out, together with the global polynomial attracting set (GPAS) and the global attracting set (GAS). Further, the relationship among GPD, GED and GD is unveiled. Finally, a proposed theoretical condition is validated through a simulation experiment.

Sign in / Sign up

Export Citation Format

Share Document