About me
I was born and raised in France, experiencing the contrast between rural regions and two larger cities. My passion for nature led me to choose a life in the countryside, where I find inspiration and tranquility.
I am an Associate Professor at the University of Tours, currently focusing my research on exploratory data analysis, data narration, and explainable AI. I’m a member of the LIFAT lab, BdTln team. Within the Life Sciences and Engineering Department of the University of Tours, situated in the neighboring city of Blois, I predominantly teach database courses. In addition to my teaching responsibilities, I also supervise master’s students working on applied machine learning projects.
EDA
EDA is the iterative process of performing an action (such as a query on data), receiving the result, and deciding on the next step. The final goal of EDA is the extraction of insights, fragments of useful information justified by the data. Automating EDA requires overcoming several hurdles, notably identifying and correctly presenting the most interesting insights from a database. My work address this issue notably by studying associated optimization problems.
Explainable AI
Explainable AI (XAI) ultimately aims at making machine learning models more transparent in their behaviors and decisions. Many types of methods have been deployed to further this goal. My work has been focused on post-hoc methods, i.e. that do not require intervention at the learning step. I originally worked on adapting existing explanation methods to recommender systems and now focus on extracting knowledge from large sets of local explanations.
Positions open @ LIFAT
- Assistant professor (starting 09/25) in BDTLN team : contact arnaud.soulet at univ-tours.fr
- PhD (starting 09/25) : LLM-aided data exploration and storytelling
- PhD (starting 10/25) : Evaluating Novel Quality Measures for Explainers
- PhD (starting when filled) : Optimisation Sous Contraintes des Flexibilités des Équipements Consommateurs d’Électricité dans le secteur Résidentiel et Tertiaire
- PostDoc (in collaboration with IRIT / Located in Toulouse): Explainability of time series prediction models for water resources management
Credits
This website was built using the Academic Pages template, create by Stuart Geiger. More info about Academic Pages can be found on their github.