New Criteria for Dissipativity Analysis of Fractional-Order Static Neural Networks

2021 ◽  
Author(s):  
Duong Thi Hong ◽  
Nguyen Huu Sau ◽  
Mai Viet Thuan
Keyword(s):  
Neural Networks ◽  
Fractional Order ◽  
Static Neural Networks ◽  
Dissipativity Analysis ◽  
New Criteria

New criteria for dissipativity analysis of Caputo fractional-order neural networks with non-differentiable time-varying delays

2022 ◽  
Vol 0 (0) ◽  
Author(s):  
Nguyen Thi Phuong ◽  
Nguyen Thi Thanh Huyen ◽  
Nguyen Thi Huyen Thu ◽  
Nguyen Huu Sau ◽  
Mai Viet Thuan
Keyword(s):  
Neural Networks ◽  
Fractional Order ◽  
Linear Matrix ◽  
Sufficient Condition ◽  
Time Varying ◽  
Matrix Inequalities ◽  
Simulation Results ◽  
Delay Dependent ◽  
Dissipativity Analysis ◽  
New Criteria

Abstract In this article, we investigate the delay-dependent and order-dependent dissipativity analysis for a class of Caputo fractional-order neural networks (FONNs) subject to time-varying delays. By employing the Razumikhin fractional-order (RFO) approach combined with linear matrix inequalities (LMIs) techniques, a new sufficient condition is derived to guarantee that the considered fractional-order is strictly (Q, S, R) − γ − dissipativity. The condition is presented via LMIs and can be efficiently checked. Two numerical examples and simulation results are finally provided to express the effectiveness of the obtained results.

New Results on Stability for a Class of Fractional-Order Static Neural Networks

2020 ◽  
Vol 39 (12) ◽  
pp. 5926-5950
Author(s):  
Xiangqian Yao ◽  
Meilan Tang ◽  
Fengxian Wang ◽  
Zhijian Ye ◽  
Xinge Liu
Keyword(s):  
Neural Networks ◽  
Fractional Order ◽  
Static Neural Networks

Dissipativity Analysis of Memristor-Based Fractional-Order Hybrid BAM Neural Networks with Time Delays

2019 ◽  
Vol 20 (7-8) ◽  
pp. 773-785
Author(s):  
Weizhen Liu ◽  
Minghui Jiang ◽  
Kaifang Fei
Keyword(s):  
Neural Networks ◽  
Fractional Order ◽  
Contraction Mapping ◽  
Contraction Mapping Principle ◽  
Bam Neural Networks ◽  
New Class ◽  
Globally Attractive ◽  
Fractional Halanay Inequality ◽  
Dissipativity Analysis ◽  
Theoretical Results

AbstractA new class of memristor-based time-delay fractional-order hybrid BAM neural networks has been put forward. The contraction mapping principle has been adopted to verify the existence and uniqueness of the equilibrium point of the addressed neural networks. By virtue of fractional Halanay inequality and fractional comparison principle, not only the dissipativity has been analyzed, but also a globally attractive set of the new model has been formulated clearly. Numerical simulation is presented to illustrate the feasibility and validity of our theoretical results.

Sign in / Sign up

Export Citation Format

Share Document