Xiufang Chen
Papers
3
Total Citations
34
H-Index
3
About
Xiufang Chen is a rising researcher at the intersection of neural computation, robotics, and adaptive control. Her work focuses on developing bio-inspired and mathematically rigorous algorithms for real-time learning and robotic manipulation. Chen’s most significant contribution is an **online learning strategy for Echo State Networks (ESNs)**—a powerful alternative to recurrent neural networks. By leveraging the Woodbury matrix identity, she overcame the traditional limitation of batch learning, enabling ESNs to learn and adapt in real time (16 citations). This breakthrough has implications for dynamic environments where models must update continuously. In parallel, Chen has advanced **kinematic control of redundant manipulators** through a cerebellum-inspired control scheme, mimicking human motor learning to solve complex robotic coordination tasks (9 citations). She has also contributed to **gradient-based recurrent neural networks** for achieving zero residual in time-dependent problems (9 citations). Her work bridges theoretical rigor with practical, real-time applications, positioning her as a key innovator in adaptive neural systems and intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1An Online Learning Strategy for Echo State Network16 citations · 2023
- 2
- 3