Robust Stability of Quaternion-Valued Neural Networks with Multiple Time Delays and Parameter Uncertainty
Axioms · 26.03.2026 · 15 (4) · 249
DOI: 10.3390/axioms15040249 ↗Kurz gefasst
Fachartikel in der Zeitschrift Axioms, online erschienen am 26.03.2026. Verfasst von Lu Li und 3 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chongqing Municipal Natural Science Foundation Innovation Development Joint Fund, China, Natural Science Foundation Project of Chongqing, China, Science and Technology Research Program of Chongqing Municipal Education Commission, China.
Abstract (Originalsprache)
In this paper, a non-decomposition approach is adopted to study the robust stability of quaternion-valued neural networks (QVNNs) with leakage, discrete, and neutral time delays, and the parameter uncertainty is also considered. The existence and uniqueness of the equilibrium of QVNNs are proved by the homogeneous mapping theorem. By constructing appropriate Lyapunov functions and employing quaternion modulus inequality techniques, sufficient conditions for the global robust stability of QVNNs are presented. Notably, the considered QVNN is treated as a whole rather than being decomposed into complex-valued neural networks (CVNNs) or real-valued neural networks (RVNNs), which faithfully reflects the internal connections between quaternion neurons. Two numerical examples are used to verify the validity of the obtained conclusions.
Förderung
- Chongqing Municipal Natural Science Foundation Innovation Development Joint Fund, China
- Natural Science Foundation Project of Chongqing, China
- Science and Technology Research Program of Chongqing Municipal Education Commission, China
- Foundation of Intelligent Ecotourism Subject Group of Chongqing Three Gorges University, China
Zitieren
APA
Li, L., Tu, Z., Duan, H., & Peng, T. (2026). Robust Stability of Quaternion-Valued Neural Networks with Multiple Time Delays and Parameter Uncertainty. Axioms, 15(4), 249. https://doi.org/10.3390/axioms15040249
Vancouver
Li L, Tu Z, Duan H, Peng T. Robust Stability of Quaternion-Valued Neural Networks with Multiple Time Delays and Parameter Uncertainty. Axioms. 2026;15(4):249. doi:10.3390/axioms15040249
BibTeX
@article{Li2026,
author = {Li, Lu and Tu, Zhengwen and Duan, Huiling and Peng, Tao},
title = {Robust Stability of Quaternion-Valued Neural Networks with Multiple Time Delays and Parameter Uncertainty},
journal = {Axioms},
year = {2026},
volume = {15},
number = {4},
pages = {249},
doi = {10.3390/axioms15040249}
}
EUVIMED