191 citations · 448 across the 18 of their papers we have counts for
19 papers
Growing Tiny Networks: Spotting Expressivity Bottlenecks and Fixing Them Optimally
Manon Verbockhaven, Sylvain Chevallier, Guillaume Charpiat +1
Machine learning tasks are generally formulated as optimization problems, where one searches for an optimal function within a certain functional space. In practice, parameterized f…
Time and State Dependent Neural Delay Differential Equations
Thibault Monsel, Onofrio Semeraro, Lionel Mathelin +1
Discontinuities and delayed terms are encountered in the governing equations of a large class of problems ranging from physics and engineering to medicine and economics. These syst…
An Implicit GNN Solver for Poisson-like problems
Matthieu Nastorg, Michele Alessandro Bucci, Thibault Faney +3
This paper presents -GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions. By leveraging the Implicit…
Designing losses for data-free training of normalizing flows on Boltzmann distributions
Loris Felardos, Jérôme Hénin, Guillaume Charpiat
Generating a Boltzmann distribution in high dimension has recently been achieved with Normalizing Flows, which enable fast and exact computation of the generated density, and thus…
DS-GPS : A Deep Statistical Graph Poisson Solver (for faster CFD simulations)
Matthieu Nastorg, Marc Schoenauer, Guillaume Charpiat +3
This paper proposes a novel Machine Learning-based approach to solve a Poisson problem with mixed boundary conditions. Leveraging Graph Neural Networks, we develop a model able to…
Rotation-equivariant Graph Neural Networks for Learning Glassy Liquids Representations
Francesco Saverio Pezzicoli, Guillaume Charpiat, François P. Landes
The difficult problem of relating the static structure of glassy liquids and their dynamics is a good target for Machine Learning, an approach which excels at finding complex patte…
Machine Learning model for gas-liquid interface reconstruction in CFD numerical simulations
Tamon Nakano, Alessandro Michele Bucci, Jean-Marc Gratien +2
The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids. A major bottleneck of the VoF metho…
Docent: A content-based recommendation system to discover contemporary art
Antoine Fosset, Mohamed El-Mennaoui, Amine Rebei +9
Recommendation systems have been widely used in various domains such as music, films, e-shopping etc. After mostly avoiding digitization, the art world has recently reached a techn…
DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification
Julien Girard-Satabin, Aymeric Varasse, Marc Schoenauer +2
The impressive results of modern neural networks partly come from their non linear behaviour. Unfortunately, this property makes it very difficult to apply formal verification tool…
Input Similarity from the Neural Network Perspective
Guillaume Charpiat, Nicolas Girard, Loris Felardos +1
We first exhibit a multimodal image registration task, for which a neural network trained on a dataset with noisy labels reaches almost perfect accuracy, far beyond noise variance.…
An Equivalence between Bayesian Priors and Penalties in Variational Inference
Pierre Wolinski, Guillaume Charpiat, Yann Ollivier
In machine learning, it is common to optimize the parameters of a probabilistic model, modulated by an ad hoc regularization term that penalizes some values of the parameters. Regu…
CAMUS: A Framework to Build Formal Specifications for Deep Perception Systems Using Simulators
Julien Girard-Satabin, Guillaume Charpiat, Zakaria Chihani +1
The topic of provable deep neural network robustness has raised considerable interest in recent years. Most research has focused on adversarial robustness, which studies the robust…
Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data
Sophie Giffard-Roisin, Mo Yang, Guillaume Charpiat +3
The forecast of tropical cyclone trajectories is crucial for the protection of people and property. Although forecast dynamical models can provide high-precision short-term forecas…
Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data
Nicolas Girard, Guillaume Charpiat, Yuliya Tarabalka
In machine learning the best performance on a certain task is achieved by fully supervised methods when perfect ground truth labels are available. However, labels are often noisy,…
Optimizing deep video representation to match brain activity
Hugo Richard, Ana Pinho, Bertrand Thirion +1
The comparison of observed brain activity with the statistics generated by artificial intelligence systems is useful to probe brain functional organization under ecological conditi…
Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing
Armand Zampieri, Guillaume Charpiat, Yuliya Tarabalka
We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging. The difficulties encountered by classical…
High-Resolution Semantic Labeling with Convolutional Neural Networks
Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat +1
Convolutional neural networks (CNNs) have received increasing attention over the last few years. They were initially conceived for image categorization, i.e., the problem of assign…
Recurrent Neural Networks to Correct Satellite Image Classification Maps
Emmanuel Maggiori, Guillaume Charpiat, Yuliya Tarabalka +1
While initially devised for image categorization, convolutional neural networks (CNNs) are being increasingly used for the pixelwise semantic labeling of images. However, the prope…
Piecewise rigid curve deformation via a Finsler steepest descent
Guillaume Charpiat, Giacomo Nardi, Gabriel Peyré +1
This paper introduces a novel steepest descent flow in Banach spaces. This extends previous works on generalized gradient descent, notably the work of Charpiat et al., to the setti…