Hector M. Romero Ugalde
Papers
2
Total Citations
75
H-Index
2
About
Hector M. Romero Ugalde is a researcher whose work sits at the intersection of machine learning and control systems, focusing on the efficient modeling of complex, nonlinear systems. His primary contributions lie in advancing neural network architectures for black-box system identification—a critical task for engineering applications where internal dynamics are unknown. In his highly cited 2015 paper, "Computational cost improvement of neural network models in black box nonlinear system identification," he introduced methods to significantly reduce the computational burden of neural models without sacrificing predictive accuracy, an innovation that has garnered 48 citations. Building on this, his 2014 work, "Balanced simplicity–accuracy neural network model families for system identification," proposed a family of models that strike an optimal trade-off between structural simplicity and performance, earning 27 citations. These contributions are notable for their practical impact, enabling real-time control and monitoring in fields like robotics and process engineering. Romero Ugalde’s research is distinguished by its emphasis on making advanced neural techniques accessible and efficient for real-world systems, bridging the gap between theoretical complexity and applied engineering needs.
Research Focus
Key Achievements
Top Papers
- 1
- 2