Guancheng Wang
Papers
7
Total Citations
128
H-Index
6
About
Guancheng Wang is a leading researcher in computational intelligence and neural dynamics, specializing in the development of advanced algorithms for solving time-varying nonlinear equations and constrained optimization problems. His work centers on gradient-based and zeroing neural networks, with a focus on enhancing convergence speed, noise suppression, and finite-time stability. Wang’s most impactful contributions include the introduction of the activated variable parameter gradient-based neural network (AVPGNN) for time-variant constrained quadratic programming, and a noise-suppressing Newton-Raphson iteration algorithm for the time-varying Lyapunov equation, which has direct applications in robotic tracking. His papers have accumulated over 128 citations, with his 2020 study on two neural dynamics approaches for nonlinear equations receiving 32 citations. Wang’s innovative proportional-integral iterative algorithms and modified Newton integration methods have advanced dynamic nonlinear optimization, demonstrating practical utility in robotics and control systems. His recent work on the Modified Gradient Recurrent Neural Network (MGRNN) for constrained quadratic programming further solidifies his reputation as a pioneer in real-time neural computation.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7