Rongfeng Zheng
Papers
1
Total Citations
27
H-Index
1
About
Rongfeng Zheng is a leading researcher in computational intelligence and neural dynamics, with a primary focus on developing advanced neural network architectures for solving complex mathematical problems in real time. Their work centers on adaptive gradient neural networks and zeroing neural networks, particularly applied to dynamic linear matrix equations—a critical area for robotics, control systems, and signal processing. Zheng's most-cited paper, "An Adaptive Gradient Neural Network to Solve Dynamic Linear Matrix Equations" (2021), has garnered 27 citations, showcasing its influence in advancing neural-based numerical methods. This work systematically reviews and enhances existing approaches, including conventional gradient recurrent neural networks and zeroing neural networks, offering improved convergence and accuracy for time-varying problems. Zheng's contributions stand out for bridging theoretical neural dynamics with practical engineering applications, providing robust tools for real-time computation. Their research continues to shape the field of adaptive neural computation, inspiring further innovations in dynamic system solving and optimization.
Research Focus
Key Achievements
Top Papers
- 1An Adaptive Gradient Neural Network to Solve Dynamic Linear Matrix Equations27 citations · 2021