451 citations
- École Nationale Supérieure de Techniques AvancéesFR146 papers
- Centre National de la Recherche ScientifiqueFR70 papers
- École PolytechniqueFR55 papers
- Laboratoire d'Optique AppliquéeFR43 papers
- Université Paris-SaclayFR43 papers
- Institut national de recherche en sciences et technologies du numériqueFR27 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR17 papers
- Institut Polytechnique de ParisFR16 papers
- POEMS: Propagation des Ondes : Etude Mathématique et SimulationanFR11 papers
- Unité de Mathématiques AppliquéesFR10 papers
- Centre de Mathématiques Appliquées de l'École polytechniqueFR7 papers
- CERMICSFR7 papers
9 papers · 1 filter
Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantification
Adrien Lafage, Olivier Laurent, Firas Gabetni +1
Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle…
Symmetry-Based Disentangled Representation Learning requires Interaction with Environments
Hugo Caselles-Dupré, Michael Garcia-Ortiz, David Filliat
Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construc…
Diversity-Driven Selection of Exploration Strategies in Multi-Armed Bandits
Fabien C. Y. Benureau, Pierre-Yves Oudeyer
We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select whic…
Training Discriminative Models to Evaluate Generative Ones
Timothée Lesort, Andrei Stoain, Jean-François Goudou +1
Generative models are known to be difficult to assess. Recent works, especially on generative adversarial networks (GANs), produce good visual samples of varied categories of image…
Active choice of teachers, learning strategies and goals for a socially guided intrinsic motivation learner
Sao Mai Nguyen, Pierre-Yves Oudeyer
We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple out…
A simple technique for improving multi-class classification with neural networks
Thomas Kopinski, Alexander Gepperth, Uwe Handmann
We present a novel method to perform multi-class pattern classification with neural networks and test it on a challenging 3D hand gesture recognition problem. Our method consists o…