Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Lemaire, Vincent, Boudec, Nathan Le, Guyomard, Victor, Fessant, Françoise
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2309.04284
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910406817087488
author Lemaire, Vincent
Boudec, Nathan Le
Guyomard, Victor
Fessant, Françoise
author_facet Lemaire, Vincent
Boudec, Nathan Le
Guyomard, Victor
Fessant, Françoise
contents There are now many explainable AI methods for understanding the decisions of a machine learning model. Among these are those based on counterfactual reasoning, which involve simulating features changes and observing the impact on the prediction. This article proposes to view this simulation process as a source of creating a certain amount of knowledge that can be stored to be used, later, in different ways. This process is illustrated in the additive model and, more specifically, in the case of the naive Bayes classifier, whose interesting properties for this purpose are shown.
format Preprint
id arxiv_https___arxiv_org_abs_2309_04284
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers
Lemaire, Vincent
Boudec, Nathan Le
Guyomard, Victor
Fessant, Françoise
Machine Learning
There are now many explainable AI methods for understanding the decisions of a machine learning model. Among these are those based on counterfactual reasoning, which involve simulating features changes and observing the impact on the prediction. This article proposes to view this simulation process as a source of creating a certain amount of knowledge that can be stored to be used, later, in different ways. This process is illustrated in the additive model and, more specifically, in the case of the naive Bayes classifier, whose interesting properties for this purpose are shown.
title Viewing the process of generating counterfactuals as a source of knowledge: a new approach for explaining classifiers
topic Machine Learning
url https://arxiv.org/abs/2309.04284