Search Results for author:
Found 18 papers, 3 papers with code
An Implicit GNN Solver for Poisson-like problems
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
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)
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
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.
Docent: A content-based recommendation system to discover contemporary art
The power of graph analysis enables us to provide an artwork recommendation system based on a combination of visual and contextual information from artworks and artists.
Machine Learning model for gas-liquid interface reconstruction in CFD numerical simulations
The volume of fluid (VoF) method is widely used in multi-phase flow simulations to track and locate the interface between two immiscible fluids.
DISCO Verification: Division of Input Space into COnvex polytopes for neural network verification
The impressive results of modern neural networks partly come from their non linear behaviour.
Input Similarity from the Neural Network Perspective
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
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.
CAMUS: A Framework to Build Formal Specifications for Deep Perception Systems Using Simulators
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.
Tropical Cyclone Track Forecasting using Fused Deep Learning from Aligned Reanalysis Data
The forecast of tropical cyclone trajectories is crucial for the protection of people and property.
Noisy Supervision for Correcting Misaligned Cadaster Maps Without Perfect Ground Truth Data
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
The comparison of observed brain activity with the statistics generated by artificial intelligence systems is useful to probe brain functional organization under ecological conditions.
Multimodal image alignment through a multiscale chain of neural networks with application to remote sensing
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
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
We establish the desired properties of an ideal semantic labeling CNN, and assess how those methods stand with regard to these properties.
Recurrent Neural Networks to Correct Satellite Image Classification Maps
Instead, our goal is to directly learn the iterative process itself.
Training recurrent networks online without backtracking
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.
