Dit Yan Yeung
Papers
1
Total Citations
34
H-Index
1
About
Dit Yan Yeung is a pioneering figure in robotics and neural network control, best known for foundational work on context-sensitive learning networks for robot arm manipulation. In his highly cited 1989 paper, Yeung introduced a novel class of networks that learn complex nonlinear mappings by independently modeling the entries of the inverse Jacobian, enabling more adaptive and precise control of robotic systems. This work, with 34 citations, laid early groundwork for integrating machine learning with robotics, particularly in handling dynamic environments. Yeung’s contributions sit at the intersection of computational neuroscience and control theory, offering a framework where neural networks can adjust to contextual changes—a key challenge in autonomous systems. His research has influenced subsequent developments in adaptive control, sensorimotor learning, and intelligent robotics. By demonstrating how context-sensitive architectures can decompose and learn complex transformations, Yeung helped shape the trajectory of neural network applications in engineering. For students and researchers exploring the history of robot learning, his work remains a touchstone for understanding how early neural approaches tackled real-world control problems.
Research Focus
Key Achievements
Top Papers
- 1Using a context-sensitive learning network for robot arm control34 citations · 1989