Welcome to my personal website! If you want to get in touch, you can contact me at adeline.fermanian@califrais.fr

Short bio

I have joined Califrais in April 2023 as a machine learning researcher. We work on developing articifical intelligence tools for fresh produce logistics, with many research topics such as demand predictive analysis, perishable goods stock optimization, dynamic pricing… The general goal is to minimize the carbon footprint of the fresh produce supply chain (for example by maximizing the trucks fill rate) and to minimize food waste.

I was between November 2021 and November 2022 a postdoctoral researcher at the Center for Computational Biology (CBIO), Mines ParisTech, under the supervision of Chloé-Agathe Azencott, and funded by the PRAIRIE institute.

Previously, I was a PhD student in Statistics at LPSM, Sorbonne Université, under the supervision of Gérard Biau and Benoît Cadre.

You can find my complete CV here: Curriculum Vitae,

Research interests

I am generally interested in theoretical aspects of machine learning, in particular in neural ordinary differential equations and deep learning, learning with time series, and optimization. The topic of my PhD was the application of signatures, a tool from stochastic analysis that allows to extract information from temporal data, in statistics and machine learning. This subject has been developed in two directions: on the one hand, designing new algorithms using signatures as features, and, on the other hand, leveraging the theory of signatures to study existing deep learning algorithms such as RNN, via the recent notion of neural ordinary differential equations. Check out the DataSig website for more information on applications of signatures in machine learning.