This thesis studies empirical properties of deep convolutional neural networks, and in particular the Scattering Transform. Indeed, the theoretical analysis of the latter is hard and until now remains a challenge: successive layers of neurons have the ability to produce complex computations, whose nature is still unknown, thanks to learning algorithms whose convergence guarantees are not well understood. However, those neural networks are outstanding tools to tackle a wide variety of difficult tasks, like image classification or more formally statistical prediction. The Scattering Transform is a non-linear mathematical operator whose properties are inspired by convolutional networks. In this work, we apply it to natural images, and obtain c...
National audienceRecently, deep neural networks have proven their ability to achieve excellent resul...
Handling and processing the massive amount of 3D data has become a challenge with countless applicat...
Many problems in machine learning pertain to tackling the minimization of a possibly non-convex and ...
This thesis studies empirical properties of deep convolutional neural networks, and in particular th...
Artificial neural networks are systems prominently used in computation and investigations of biologi...
With the development of 3D vision techniques, in particular neural network based methods, the 3D neu...
We are seven billion humans with unique cortical folding patterns. The cortical folding process occu...
Au cours de la dernière décennie, l'apprentissage profond est devenu une composante majeure de l'int...
In the last few years, deep learning has changed irrevocably the field of computer vision. Faster, g...
This thesis presents our contributions to inference and learning of graph-based models in computer v...
This thesis presents our contributions to inference and learning of graph-based models in computer v...
This thesis lies at the intersection of the theories of non-parametric statistics and statistical le...
Inverse problems arise in various physical domains and solving them from real-world visual observati...
The impressive breakthroughs of the last two decades in the field of machine learning can be in larg...
The goal of this thesis is to propose a mathematical model of visual stimulations in order to finely...
National audienceRecently, deep neural networks have proven their ability to achieve excellent resul...
Handling and processing the massive amount of 3D data has become a challenge with countless applicat...
Many problems in machine learning pertain to tackling the minimization of a possibly non-convex and ...
This thesis studies empirical properties of deep convolutional neural networks, and in particular th...
Artificial neural networks are systems prominently used in computation and investigations of biologi...
With the development of 3D vision techniques, in particular neural network based methods, the 3D neu...
We are seven billion humans with unique cortical folding patterns. The cortical folding process occu...
Au cours de la dernière décennie, l'apprentissage profond est devenu une composante majeure de l'int...
In the last few years, deep learning has changed irrevocably the field of computer vision. Faster, g...
This thesis presents our contributions to inference and learning of graph-based models in computer v...
This thesis presents our contributions to inference and learning of graph-based models in computer v...
This thesis lies at the intersection of the theories of non-parametric statistics and statistical le...
Inverse problems arise in various physical domains and solving them from real-world visual observati...
The impressive breakthroughs of the last two decades in the field of machine learning can be in larg...
The goal of this thesis is to propose a mathematical model of visual stimulations in order to finely...
National audienceRecently, deep neural networks have proven their ability to achieve excellent resul...
Handling and processing the massive amount of 3D data has become a challenge with countless applicat...
Many problems in machine learning pertain to tackling the minimization of a possibly non-convex and ...