Search Results for author: Guillaume Charpiat

Found 18 papers, 3 papers with code

An Implicit GNN Solver for Poisson-like problems

no code implementations6 Feb 2023 Matthieu Nastorg, Michele-Alessandro Bucci, Thibault Faney, Jean-Marc Gratien, Guillaume Charpiat, Marc Schoenauer

This paper presents $\Psi$-GNN, a novel Graph Neural Network (GNN) approach for solving the ubiquitous Poisson PDE problems with mixed boundary conditions.

Designing losses for data-free training of normalizing flows on Boltzmann distributions

no code implementations13 Jan 2023 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 unbiased estimation of expectations.

DS-GPS : A Deep Statistical Graph Poisson Solver (for faster CFD simulations)

no code implementations21 Nov 2022 Matthieu Nastorg, Marc Schoenauer, Guillaume Charpiat, Thibault Faney, Jean-Marc Gratien, Michele-Alessandro Bucci

This paper proposes a novel Machine Learning-based approach to solve a Poisson problem with mixed boundary conditions.

SE(3)-equivariant Graph Neural Networks for Learning Glassy Liquids Representations

no code implementations6 Nov 2022 Francesco Saverio Pezzicoli, Guillaume Charpiat, François P. Landes

Within the glassy liquids community, the use of Machine Learning (ML) to model particles' static structure in order to predict their future dynamics is currently a hot topic.


Machine Learning model for gas-liquid interface reconstruction in CFD numerical simulations

no code implementations12 Jul 2022 Tamon Nakano, Alessandro Michele Bucci, Jean-Marc Gratien, Thibault Faney, Guillaume Charpiat

The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids.

BIG-bench Machine Learning

Input Similarity from the Neural Network Perspective

1 code implementation NeurIPS 2019 Guillaume Charpiat, Nicolas Girard, Loris Felardos, Yuliya Tarabalka

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.

Denoising Image Registration

An Equivalence between Bayesian Priors and Penalties in Variational Inference

no code implementations1 Feb 2020 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.

Variational Inference

CAMUS: A Framework to Build Formal Specifications for Deep Perception Systems Using Simulators

no code implementations25 Nov 2019 Julien Girard-Satabin, Guillaume Charpiat, Zakaria Chihani, Marc Schoenauer

We propose to take advantage of the simulators often used either to train machine learning models or to check them with statistical tests, a growing trend in industry.

Adversarial Robustness

Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data

1 code implementation12 Mar 2019 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.

Optimizing deep video representation to match brain activity

no code implementations7 Sep 2018 Hugo Richard, Ana Pinho, Bertrand Thirion, Guillaume Charpiat

The comparison of observed brain activity with the statistics generated by artificial intelligence systems is useful to probe brain functional organization under ecological conditions.

Optical Flow Estimation

Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing

no code implementations ECCV 2018 Armand Zampieri, Guillaume Charpiat, Nicolas Girard, Yuliya Tarabalka

We tackle here the problem of multimodal image non-rigid registration, which is of prime importance in remote sensing and medical imaging.

Coarse to fine non-rigid registration: a chain of scale-specific neural networks for multimodal image alignment with application to remote sensing

no code implementations27 Feb 2018 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.

High-Resolution Semantic Labeling with Convolutional Neural Networks

no code implementations7 Nov 2016 Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez

We establish the desired properties of an ideal semantic labeling CNN, and assess how those methods stand with regard to these properties.

Image Categorization Vocal Bursts Intensity Prediction

Training recurrent networks online without backtracking

no code implementations28 Jul 2015 Yann Ollivier, Corentin Tallec, Guillaume Charpiat

The evolution of this search direction is partly stochastic and is constructed in such a way to provide, at every time, an unbiased random estimate of the gradient of the loss function with respect to the parameters.

Cannot find the paper you are looking for? You can Submit a new open access paper.