A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers

Résumé

Our research aims to propose a new performance-explainability analytical framework to assess and benchmark machine learning methods. The framework details a set of characteristics that systematize the performance-explainability assessment of existing machine learning methods. In order to illustrate the use of the framework, we apply it to benchmark the current state-of-the-art multivariate time series classifiers.
Fichier principal
Vignette du fichier
Fauvel20_Framework.pdf (512.76 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03094885 , version 1 (04-01-2021)
hal-03094885 , version 2 (20-12-2021)

Identifiants

Citer

Kevin Fauvel, Véronique Masson, Elisa Fromont. A Performance-Explainability Framework to Benchmark Machine Learning Methods: Application to Multivariate Time Series Classifiers. IJCAI-PRICAI 2020 - Workshop on Explainable Artificial Intelligence (XAI), Jan 2021, Yokohama, Japan. pp.1-8. ⟨hal-03094885v2⟩
124 Consultations
431 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More