8 papers
Correct then Forecast: Observer State-Space Models for Time Series Forecasting
Alexis-Raja Brachet, Guillaume Clavier--Frémond, Abdelhakim Ziani +2
Time series forecasting requires extrapolating the dynamics of an observed process beyond the last available measurement. Yet recurrent forecasting models typically treat observati…
Fairness and Robustness of CLIP-Based Models for Chest X-rays
Théo Sourget, David Restrepo, Céline Hudelot +3
Motivated by the strong performance of CLIP-based models in natural image-text domains, recent efforts have adapted these architectures to medical tasks, particularly in radiology,…
Time Series Forecasting Through the Lens of Dynamics
Alexis-Raja Brachet, Pierre-Yves Richard, Céline Hudelot
While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time series forecasting task. Our h…
Neurosymbolic Conformal Classification
Arthur Ledaguenel, Céline Hudelot, Mostepha Khouadjia
The last decades have seen a drastic improvement of Machine Learning (ML), mainly driven by Deep Learning (DL). However, despite the resounding successes of ML in many domains, the…
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning
Théo Moutakanni, Piotr Bojanowski, Guillaume Chassagnon +7
AI Foundation models are gaining traction in various applications, including medical fields like radiology. However, medical foundation models are often tested on limited tasks, le…
Bond Graphs for multi-physics informed Neural Networks for multi-variate time series
Alexis-Raja Brachet, Pierre-Yves Richard, Céline Hudelot
In the trend of hybrid Artificial Intelligence techniques, Physical-Informed Machine Learning has seen a growing interest. It operates mainly by imposing data, learning, or archite…
A Complexity Map of Probabilistic Reasoning for Neurosymbolic Classification Techniques
Arthur Ledaguenel, Céline Hudelot, Mostepha Khouadjia
Neurosymbolic artificial intelligence is a growing field of research aiming to combine neural network learning capabilities with the reasoning abilities of symbolic systems. Inform…
Improving Neural-based Classification with Logical Background Knowledge
Arthur Ledaguenel, Céline Hudelot, Mostepha Khouadjia
Neurosymbolic AI is a growing field of research aiming to combine neural networks learning capabilities with the reasoning abilities of symbolic systems. This hybridization can tak…