Guomin Zhong
Papers
3
Total Citations
17
H-Index
3
About
Dr. Guomin Zhong is a rising scholar in computational optimization and neural dynamics, whose work centers on developing high-performance recurrent neural network (RNN) models for solving time-variant problems. His primary research areas include zeroing neural networks (ZNN), quadratic programming, and nonlinear equation solving, with a focus on achieving exact settling time and noise tolerance. Dr. Zhong’s most notable contribution is the introduction of a transition-state based attracting system approach, which significantly enhances the performance of ZNN models for time-variant equality-constraint convex optimization—a breakthrough detailed in his 2023 paper that has already garnered 11 citations. He has further advanced the field with finitely-activated RNN models that guarantee exact settling time for quadratic programming, and a variable-parameter noise-tolerant ZNN for nonlinear equations, both published in 2025. These works demonstrate his ability to push the boundaries of real-time optimization, offering robust solutions for applications in robotics and control systems. With a growing citation impact, Dr. Zhong is establishing himself as a key innovator in neural dynamics and time-variant problem-solving.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3