Liangze Yin

National University of Defense Technology

Papers

Total Citations

H-Index

About

Liangze Yin is a rising researcher in computational intelligence and neural dynamics, with a focus on developing robust, real-time solvers for dynamic systems. His key research areas include zeroing neural networks (ZNN), noise-resistant algorithms, and their applications in solving time-varying equations. Yin’s major contribution is the introduction of a self-learning noise-resistant ZNN framework, which addresses a critical limitation of traditional ZNN models—their vulnerability to noise interference in real-world environments. By integrating adaptive mechanisms, his work enhances both accuracy and stability, enabling more reliable performance in dynamic equation solving. Although his most-cited paper, "A Self-Learning Noise-Resistant Zeroing Neural Network for Dynamic Equations and Its Applications" (2025), has garnered 1 citation to date, it represents a foundational step in a promising line of inquiry. Yin’s research holds significant potential for applications in robotics, control systems, and signal processing, where real-time noise resilience is paramount. As an emerging scholar, his work signals a valuable direction for future neural network-based solvers.