The objective of this thesis is the classification of complex valued stationary centered
Gaussian autoregressive time series. We study the case of one-dimensional time series as …

Fish-Eye image processing with conventional Machine Learning algorithms such as
Convolutional Neural Networks is a challenging task because of the distortion effects …

This paper introduces an adaptive importance sampling scheme for the computation of
group-based convolutions, a key step in the implementation of equivariant neural networks …

This paper aims at motivating the use of geometrically informed Machine Learning
algorithms for Defense applications by providing intuitions with respect to their underlying …

This paper introduces an approach for building Machine Learning (ML) algorithms
embedding equivariance mechanisms to the Lie group SL (2, Z) by leveraging on modular …

Classifying radar Doppler signals with Deep Learning algorithms is a challenging task, in
particular because of the noisy nature of the data (clutter, thermal noise, etc.). Equivariant …

This paper deals with the use of SO (3)-Equivariant Neural Networks for processing
spherical images such as those acquired with bi-directional fish-eye lenses. By using …

In a first part, we will present pioneering THALES Sensors/Radars algorithms on Geometric
Matrix CFAR based on Jean-Louis Koszul's Information Geometry and its extension for …

Le traitement des images Fish-Eye à l'aide d'algorithmes d'apprentissage automatique
conventionnels tels que les réseaux de neurones convolutifs est une tâche difficile en raison …