Jean-Claude Carmona
Papers
2
Total Citations
75
H-Index
2
About
Jean-Claude Carmona is a researcher whose work sits at the intersection of machine learning and nonlinear system identification, with a particular focus on developing neural network models that are both computationally efficient and practically accurate. His major contributions center on bridging the gap between model simplicity and predictive power—a critical challenge in black-box modeling of complex dynamical systems. In his most-cited work, “Computational cost improvement of neural network models in black box nonlinear system identification” (2015, 48 citations), Carmona proposed strategies to significantly reduce the computational burden of neural network-based identification without sacrificing performance. This was complemented by his earlier study, “Balanced simplicity–accuracy neural network model families for system identification” (2014, 27 citations), which introduced a family of models that achieve an optimal trade-off between structural simplicity and predictive accuracy. These contributions are particularly valuable for real-time control and embedded systems, where computational resources are constrained. Carmona’s work has been influential in advancing practical, deployable neural network solutions for nonlinear system identification, making him a notable figure in the field of applied machine learning for engineering systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2