2 code implementations • 18 Oct 2018 • François Bachoc, Fabrice Gamboa, Max Halford, Jean-Michel Loubes, Laurent Risser
In order to emphasize the impact of each input variable, this formalism uses an information theory framework that quantifies the influence of all input-output observations based on entropic projections.
1 code implementation • 31 Mar 2020 • Philippe Besse, Eustasio del Barrio, Paula Gordaliza, Jean-Michel Loubes, Laurent Risser
Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world.
1 code implementation • 19 Oct 2022 • Romain Thoreau, Laurent Risser, Véronique Achard, Béatrice Berthelot, Xavier Briottet
The combination of machine learning models with physical models is a recent research path to learn robust data representations.
1 code implementation • 11 May 2023 • Fanny Jourdan, Agustin Picard, Thomas Fel, Laurent Risser, Jean Michel Loubes, Nicholas Asher
COCKATIEL is a novel, post-hoc, concept-based, model-agnostic XAI technique that generates meaningful explanations from the last layer of a neural net model trained on an NLP classification task by using Non-Negative Matrix Factorization (NMF) to discover the concepts the model leverages to make predictions and by exploiting a Sensitivity Analysis to estimate accurately the importance of each of these concepts for the model.
Explainable Artificial Intelligence (XAI) Sentiment Analysis
2 code implementations • 15 Nov 2023 • Romain Thoreau, Laurent Risser, Véronique Achard, Béatrice Berthelot, Xavier Briottet
While the spectral dimension of hyperspectral images is highly informative of the chemical composition of the land surface, the use of state-of-the-art machine learning algorithms to map the land cover has been dramatically limited by the availability of training data.
1 code implementation • 30 Aug 2021 • Lucas de Lara, Alberto González-Sanz, Nicholas Asher, Laurent Risser, Jean-Michel Loubes
We address the problem of designing realistic and feasible counterfactuals in the absence of a causal model.
1 code implementation • 11 Dec 2023 • Fanny Jourdan, Louis Béthune, Agustin Picard, Laurent Risser, Nicholas Asher
In evaluation, we show that the proposed post-hoc approach significantly reduces gender-related associations in NLP models while preserving the overall performance and functionality of the models.
no code implementations • 25 May 2018 • Camille Champion, Anne-Claire Brunet, Jean-Michel Loubes, Laurent Risser
In this paper, we present a new R package COREclust dedicated to the detection of representative variables in high dimensional spaces with a potentially limited number of observations.
no code implementations • 3 Mar 2015 • Jean-Marie Mirebeau, Jérôme Fehrenbach, Laurent Risser, Shaza Tobji
Anisotropic Non-Linear Diffusion is a powerful image processing technique, which allows to simultaneously remove the noise and enhance sharp features in two or three dimensional images.
no code implementations • 15 Aug 2019 • Laurent Risser, Alberto Gonzalez Sanz, Quentin Vincenot, Jean-Michel Loubes
We then introduce in this paper a new method to temper the algorithmic bias in Neural-Network based classifiers.
no code implementations • 10 Oct 2022 • Laurent Risser, Agustin Picard, Lucas Hervier, Jean-Michel Loubes
Contrarily to societal applications where a set of proxy variables can be provided by the common sense or by regulations to draw the attention on potential risks, industrial and safety-critical applications are most of the times sailing blind.
no code implementations • 27 Feb 2023 • Fanny Jourdan, Titon Tshiongo Kaninku, Nicholas Asher, Jean-Michel Loubes, Laurent Risser
To anticipate the certification of recommendation systems using textual data, we then used it on the Bios dataset, for which the learning task consists in predicting the occupation of female and male individuals, based on their LinkedIn biography.
no code implementations • 8 Jun 2023 • Fanny Jourdan, Laurent Risser, Jean-Michel Loubes, Nicholas Asher
This paper presents novel experiments shedding light on the shortcomings of current metrics for assessing biases of gender discrimination made by machine learning algorithms on textual data.
no code implementations • 23 Feb 2024 • Renan D. B. Brotto, Jean-Michel Loubes, Laurent Risser, Jean-Pierre Florens, Kenji Nose-Filho, João M. T. Romano
In our work, we then propose a bias mitigation strategy for continuous sensitive variables, based on the notion of endogeneity which comes from the field of econometrics.