Martinetz
Papers
1
Total Citations
26
H-Index
1
About
Thomas Martinetz has made foundational contributions to neural computation and robotics, particularly through his pioneering work on self-organizing maps and visuomotor coordination. His most cited paper, "3D neural net for learning visuomotor-coordination of a robot arm" (1989, 26 citations), extends Kohonen’s self-organizing mapping algorithm by integrating it with a Widrow-Hoff error-correction rule. This innovative unsupervised learning scheme enables a simulated robot arm to develop accurate visuomotor coordination without explicit supervision—a breakthrough that bridges neural network theory and practical robotics. Martinetz’s research centers on unsupervised learning, neural plasticity, and adaptive control, with his 1989 work serving as a cornerstone for later developments in neural-based robotic control and sensorimotor learning. Though his citation count reflects the specialized nature of his early work, its conceptual impact endures in fields ranging from computational neuroscience to autonomous systems. His ability to synthesize biologically inspired algorithms with engineering challenges marks him as a key figure in the evolution of neural network applications.
Research Focus
Key Achievements
Top Papers
- 13D neural net for learning visuomotor-coordination of a robot arm26 citations · 1989