output
20202023
most citedXCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification

146 citations

researchers with a paper here
collaborating institutions

5 papers

cs.AI2023

Persistence-Based Discretization for Learning Discrete Event Systems from Time Series

Lénaïg Cornanguer, Christine Largouët, Laurence Rozé +1

To get a good understanding of a dynamical system, it is convenient to have an interpretable and versatile model of it. Timed discrete event systems are a kind of model that respon…

cs.AI2022★ 2 cited

VCNet: A self-explaining model for realistic counterfactual generation

Victor Guyomard, Françoise Fessant, Thomas Guyet +2

Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modif…

cs.NE2022

On the benefits of self-taught learning for brain decoding

Elodie Germani, Elisa Fromont, Camille Maumet

Context. We study the benefits of using a large public neuroimaging database composed of fMRI statistic maps, in a self-taught learning framework, for improving brain decoding on n…

cs.LG2020★ 146 cited

XCM: An Explainable Convolutional Neural Network for Multivariate Time Series Classification

Kevin Fauvel, Tao Lin, Véronique Masson +2

Multivariate Time Series (MTS) classification has gained importance over the past decade with the increase in the number of temporal datasets in multiple domains. The current state…

cs.LG2020★ 63 cited

XEM: An Explainable-by-Design Ensemble Method for Multivariate Time Series Classification

Kevin Fauvel, Élisa Fromont, Véronique Masson +2

We present XEM, an eXplainable-by-design Ensemble method for Multivariate time series classification. XEM relies on a new hybrid ensemble method that combines an explicit boosting-…