Global Stability Criterion of Memristor-Based Recurrent Neural Networks with Time Delays
- Resource Type
- Conference
- Authors
- Liao, Wudai; Zhang, Chaochuan; Chen, Jinhuan; Liang, Xiaosong; Zhou, Jun
- Source
- 2020 International Conference on Advanced Mechatronic Systems (ICAMechS) Advanced Mechatronic Systems (ICAMechS), 2020 International Conference on. :94-99 Dec, 2020
- Subject
- Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Memristors
Asymptotic stability
Stability criteria
Numerical stability
Delay effects
Circuit stability
Recurrent neural networks
memristor
neural network
stability
time delay
M-matrix
- Language
- ISSN
- 2325-0690
The paper investigates the uniform asymptotic stability of memristor-based recurrent neural network with time delays. Uniqueness of the equilibrium point of memristor-based neural networks is proved by constructing the Lyapunov energy function, employing homeomorphism mapping principle and differential inclusion. Sufficiency criterion based on M matrix is proposed to confirm the equilibrium is global asymptotic stable. The deduced criterion extends the result based on M-matrix, which has certain robustness for different time delays and activation functions. According to the physical parameters of the system. Numerical analysis and simulation results are presented to demonstrate effectiveness of the criterion.