Siri Vestheim
Papers
1
Total Citations
4
H-Index
1
About
Siri Vestheim’s research centers on adaptive control systems and neural network optimization, with a particular focus on robotic manipulators. Her most notable contribution is the development of two efficient pruning techniques for Radial Basis Function (RBF) networks: Weight Magnitude Pruning (WMP) and Node Output Pruning (NOP). These methods streamline adaptive learning controllers by eliminating redundant network nodes, significantly improving computational efficiency without sacrificing performance. Her 2013 paper on this topic has garnered 4 citations, establishing a foundation for further work in lightweight neural architectures for real-time control. Vestheim’s work is especially relevant for applications requiring fast, resource-constrained decision-making, such as industrial robotics and autonomous systems. By addressing the trade-off between network complexity and controller accuracy, she has helped advance practical implementations of adaptive learning in dynamic environments. Her research continues to influence engineers seeking to deploy efficient, scalable neural controllers in real-world robotic platforms.
Research Focus
Key Achievements
Top Papers
- 1RBF network pruning techniques for adaptive learning controllers4 citations · 2013