Christophe Corbier
Papers
1
Total Citations
27
H-Index
1
About
Christophe Corbier is a researcher whose work bridges the critical gap between model complexity and practical applicability in system identification. His primary research focuses on developing neural network architectures that achieve high accuracy without sacrificing interpretability or computational efficiency. His most-cited paper, "Balanced simplicity–accuracy neural network model families for system identification" (2014, 27 citations), exemplifies this core contribution by proposing systematic frameworks for selecting model structures that optimize the trade-off between predictive performance and parsimony. This work has been influential in guiding engineers and data scientists toward more robust, deployable models for dynamic systems. Corbier’s research impacts fields such as control theory, signal processing, and machine learning, where overparameterized models often fail in real-world applications. His achievements include advancing the theoretical understanding of model selection criteria and providing practical guidelines that reduce overfitting risks. For students and researchers, Corbier’s work offers a principled approach to building neural network models that are both powerful and practical, ensuring that complexity does not come at the cost of usability or interpretability.
Research Focus
Key Achievements
Top Papers
- 1