Mona Buisson-Fenet
Papers
1
Total Citations
5
H-Index
1
About
Mona Buisson-Fenet is a researcher at the forefront of machine learning and dynamical systems, with a focus on learning complex physical behaviors from limited, noisy data. Her work centers on integrating prior knowledge with flexible neural network architectures to identify governing equations from partial observations. In her highly influential paper, "Recognition Models to Learn Dynamics from Partial Observations with Neural ODEs" (2022, 5 citations), Buisson-Fenet addresses the fundamental challenge of extracting accurate dynamics from experimental data where key state variables are unmeasured. By leveraging neural ordinary differential equations as a flexible modeling framework, she demonstrates how recognition models can infer latent states and learn system dynamics simultaneously. This approach bridges the gap between purely data-driven methods and physics-informed modeling, offering a powerful tool for robotics, control, and scientific discovery. Her contributions are particularly valuable for students and researchers working at the intersection of deep learning and physical simulation, providing a principled way to incorporate prior knowledge without sacrificing the flexibility needed for real-world applications.
Research Focus
Key Achievements
Top Papers
- 1