Zobrazeno 1 - 10
of 136
pro vyhledávání: '"Drumetz, Lucas"'
Autor:
Frion, Anthony, Drumetz, Lucas, Tochon, Guillaume, Mura, Mauro Dalla, Bey, Albdeldjalil Aïssa El
In the context of an increasing popularity of data-driven models to represent dynamical systems, many machine learning-based implementations of the Koopman operator have recently been proposed. However, the vast majority of those works are limited to
Externí odkaz:
http://arxiv.org/abs/2403.06757
While many Machine Learning methods were developed or transposed on Riemannian manifolds to tackle data with known non Euclidean geometry, Optimal Transport (OT) methods on such spaces have not received much attention. The main OT tool on these space
Externí odkaz:
http://arxiv.org/abs/2403.06560
In classification, it is usual to observe that models trained on a given set of classes can generalize to previously unseen ones, suggesting the ability to learn beyond the initial task. This ability is often leveraged in the context of transfer lear
Externí odkaz:
http://arxiv.org/abs/2403.03569
In general, underwater images suffer from color distortion and low contrast, because light is attenuated and backscattered as it propagates through water (differently depending on wavelength and on the properties of the water body). An existing simpl
Externí odkaz:
http://arxiv.org/abs/2402.05281
The generative paradigm has become increasingly important in machine learning and deep learning models. Among popular generative models are normalizing flows, which enable exact likelihood estimation by transforming a base distribution through diffeo
Externí odkaz:
http://arxiv.org/abs/2312.14698
Hyperspectral unmixing allows representing mixed pixels as a set of pure materials weighted by their abundances. Spectral features alone are often insufficient, so it is common to rely on other features of the scene. Matrix models become insufficient
Externí odkaz:
http://arxiv.org/abs/2310.03860
Autor:
Frion, Anthony, Drumetz, Lucas, Mura, Mauro Dalla, Tochon, Guillaume, Bey, Abdeldjalil Aïssa El
With the increasing availability of large scale datasets, computational power and tools like automatic differentiation and expressive neural network architectures, sequential data are now often treated in a data-driven way, with a dynamical model tra
Externí odkaz:
http://arxiv.org/abs/2309.05317
Autor:
Frion, Anthony, Drumetz, Lucas, Tochon, Guillaume, Mura, Mauro Dalla, Bey, Abdeldjalil Aïssa El
Over the last few years, massive amounts of satellite multispectral and hyperspectral images covering the Earth's surface have been made publicly available for scientific purpose, for example through the European Copernicus project. Simultaneously, t
Externí odkaz:
http://arxiv.org/abs/2305.03743
Autor:
Frion, Anthony, Drumetz, Lucas, Mura, Mauro Dalla, Tochon, Guillaume, Bey, Abdeldjalil Aissa El
Over the last few years, several works have proposed deep learning architectures to learn dynamical systems from observation data with no or little knowledge of the underlying physics. A line of work relies on learning representations where the dynam
Externí odkaz:
http://arxiv.org/abs/2303.06972
Autor:
Bonet, Clément, Malézieux, Benoît, Rakotomamonjy, Alain, Drumetz, Lucas, Moreau, Thomas, Kowalski, Matthieu, Courty, Nicolas
When dealing with electro or magnetoencephalography records, many supervised prediction tasks are solved by working with covariance matrices to summarize the signals. Learning with these matrices requires using Riemanian geometry to account for their
Externí odkaz:
http://arxiv.org/abs/2303.05798