Xplique: A Deep Learning Explainability Toolbox - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Xplique: A Deep Learning Explainability Toolbox

Résumé

Today's most advanced machine-learning models are hardly scrutable. The key challenge for explainability methods is to help assisting researchers in opening up these black boxes, by revealing the strategy that led to a given decision, by characterizing their internal states or by studying the underlying data representation. To address this challenge, we have developed Xplique: a software library for explainability which includes representative explainability methods as well as associated evaluation metrics. It interfaces with one of the most popular learning libraries: Tensorflow as well as other libraries including PyTorch, scikit-learn and Theano. The code is licensed under the MIT license and is freely available at github.com/deel-ai/xplique.

Dates et versions

hal-03696248 , version 1 (15-06-2022)

Identifiants

Citer

Thomas Fel, Lucas Hervier, David Vigouroux, Antonin Poche, Justin Plakoo, et al.. Xplique: A Deep Learning Explainability Toolbox. The Conference on Computer Vision and Pattern Recognition, Workshop: Explainable Artificial Intelligence for Computer Vision (XAI4CV), Jun 2022, Nouvelle-Orléans, United States. ⟨hal-03696248⟩
254 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More