Stability analysis of fractional Quaternion-Valued Leaky Integrator Echo State Neural Networks with multiple time-varying delays

被引:28
|
作者
Pahnehkolaei, Seyed Mehdi Abedi [1 ]
Alfi, Alireza [1 ]
Tenreiro Machado, J. A. [2 ]
机构
[1] Shahrood Univ Technol, Fac Elect & Robot Engn, Shahrood 3619995161, Iran
[2] Polytech Porto, Inst Engn, Dept Elect Engn, Rua Dr Antonio Bernardino de Almeida 431, P-4249015 Porto, Portugal
关键词
Fractional calculus; Quaternion-Valued Neural Network; Echo State Neural Network; Time-VARYING Delay; Stability; GLOBAL ASYMPTOTIC STABILITY; EXPONENTIAL STABILITY; UNIFORM STABILITY; ROBUST STABILITY; SYNCHRONIZATION; CLASSIFICATION; OPTIMIZATION; PREDICTION; DYNAMICS; SYSTEMS;
D O I
10.1016/j.neucom.2018.11.021
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper studies the stability problem of fractional order continuous-time Quaternion-Valued Leaky Integrator Echo State Neural Networks (NN) with multiple time-varying delays. The NN is decomposed into four real-valued systems without considering the non-commutativity of quaternion multiplication resulting in Hamilton rules. Then, the delay-independent stability analysis of the NN equilibrium point with Lipschitz continuous activation function is derived in the real space. The existence and uniqueness of the equilibrium point are also given using the contraction map in the real space. Simulations results show the feasibility of the method. (C) 2018 Elsevier B.V. All rights reserved.
引用
收藏
页码:388 / 402
页数:15
相关论文
共 50 条