Adversarial regularization for explainable-by-design time series classification - Université de Nantes Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Adversarial regularization for explainable-by-design time series classification

Yichang Wang
  • Fonction : Auteur
  • PersonId : 1052468
Rémi Emonet
Elisa Fromont

Résumé

Times series classification can be successfully tackled by jointly learning a shapelet-based representation of the series in the dataset and classifying the series according to this representation. This shapelet-based classification is both accurate and explainable since the shapelets are time series themselves and thus can be visualized and be provided as a classification explanation. In this paper, we claim that not all shapelets are good visual explanations and we propose a simple, yet also accurate, adversarily regularized EXplainable Convolutional Neural Network, XCNN, that can learn shapelets that are, by design, suited for explanations. We validate our method on the usual univariate time series benchmarks of the UCR repository.
Fichier principal
Vignette du fichier
ictai2020.pdf (4.45 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03025671 , version 1 (26-11-2020)

Licence

Paternité

Identifiants

  • HAL Id : hal-03025671 , version 1

Citer

Yichang Wang, Rémi Emonet, Elisa Fromont, Simon Malinowski, Romain Tavenard. Adversarial regularization for explainable-by-design time series classification. ICTAI 2020 - 32th International Conference on Tools with Artificial Intelligence, Nov 2020, online, Greece. pp.1-9. ⟨hal-03025671⟩
272 Consultations
212 Téléchargements

Partager

Gmail Facebook X LinkedIn More