188 citations · 762 across the 33 of their papers we have counts for
3 papers · 1 filter
Residual Networks as Geodesic Flows of Diffeomorphisms
Francois Rousseau, Ronan Fablet
This paper addresses the understanding and characterization of residual networks (ResNet), which are among the state-of-the-art deep learning architectures for a variety of supervi…
A Multi-task Deep Learning Architecture for Maritime Surveillance using AIS Data Streams
Duong Nguyen, Rodolphe Vadaine, Guillaume Hajduch +2
In a world of global trading, maritime safety, security and efficiency are crucial issues. We propose a multi-task deep learning framework for vessel monitoring using Automatic Ide…
Sea surface temperature prediction and reconstruction using patch-level neural network representations
Said Ouala, Cedric Herzet, Ronan Fablet
The forecasting and reconstruction of ocean and atmosphere dynamics from satellite observation time series are key challenges. While model-driven representations remain the classic…