Interpretability of Machine Learning Models and Representations: an Introduction

Résultats de recherche: Contribution dans un livre/un catalogue/un rapport/dans les actes d'une conférenceArticle dans les actes d'une conférence/un colloque

636 Téléchargements (Pure)

Résumé

Interpretability is often a major concern in machine learning. Although
many authors agree with this statement, interpretability is often tackled
with intuitive arguments, distinct (yet related) terms and heuristic quan-
tifications. This short survey aims to clarify the concepts related to interpretability and emphasises the distinction between interpreting models
and representations, as well as heuristic-based and user-based approaches.
langue originaleAnglais
titre24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Lieu de publicationBruges
Pages77-82
Etat de la publicationPublié - 2016
Evénement24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Bruges, Belgique
Durée: 27 avr. 201629 mai 2016
Numéro de conférence: 24

Une conférence

Une conférence24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Titre abrégéESANN 2016
PaysBelgique
La villeBruges
période27/04/1629/05/16

Empreinte digitale Examiner les sujets de recherche de « Interpretability of Machine Learning Models and Representations: an Introduction ». Ensemble, ils forment une empreinte digitale unique.

  • Contient cette citation

    Bibal, A., & Frenay, B. (2016). Interpretability of Machine Learning Models and Representations: an Introduction. Dans 24th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning (p. 77-82).