Research Engineer
CEA Saclay
Machine Learning
|
Applied Mathematics
|
Ph.D. in Physics
I am a research engineer with a background in theoretical physics and a specialization in machine learning. My research interests span from information theory to AI for data analysis.
I completed my PhD programme at the INFN and the UniTO with a thesis on string theory at the interface with modern AI. I joined CEA as a postdoc in 2021 to work on machine learning methods for LIBS data analysis. In this context, I developed methods based on PCA and random matrix theory for the extraction of information from LIBS mapping experiments.
I was recruited in 2022 as a research engineer at CEA, where I contributed to developing uncertainty quantification methods and techniques for data analysis and computer vision based on the use of field theory methods, such as the renormalisation group for signal detection.
I joined the Laboratory of Artificial Intelligence and Data Science in 2024, where I deal with physics and vision-inspired methodologies for data analysis, focusing on scientific and simulation data.
I am an enthusiastic researcher who enjoys staying at the frontier of theory and practice. However, I like keeping a critical attitude towards modern developments in AI: mathematical and physics basis are fundamental to understand the world of machine learning, and to develop reliable and trustworthy implementations
Part of my work focuses on theoretical work in statistical applications: I had the chance to develop techniques based on random matrix theory for image processing, and the use of renormalisation group for signal detection in continuous spectra.