Robust stability analysis of quaternion-valued neural networks via LMI approach
Xiaofeng Chen, Lianjie Li, Zhongshan Li · Advances in Difference Equations · 2018
This paper is concerned with the issue of robust stability for quaternion-valued neural networks (QVNNs) with leakage, discrete and distributed delays by employing a linear matrix inequality (LMI) approach. Based on the homeomorphic mapping theorem, the quaternion matrix theorem and the Lyapunov theorem, some criteria are developed in the form of real-valued LMIs for guaranteeing the existence, uniqueness, and global robust stability of the equilibrium point of the delayed QVNNs. Two numerical examples are provided to demonstrate the effectiveness of the obtained results.