Ray, Faron (2022) Two Types of Explainability for Machine Learning Models. In: UNSPECIFIED.

Preview

Text Ray, F. Two_Types_of_Explainability (MS).pdf Download (207kB) | Preview

Abstract

This paper argues that there are two different types of causes that we can wish to understand when we talk about wanting machine learning models to be explainable. The first are causes in the features that a model uses to make its predictions. The second are causes in the world that have enabled those features to carry out the model’s predictive function. I argue that this difference should be seen as giving rise to two distinct types of explanation and explainability and show how the proposed distinction proves useful in a number of applications.

---

Export/Citation:

EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL

Social Networking:

Share |

---

Item Type:	Conference or Workshop Item (UNSPECIFIED)
Creators:	Creators Email ORCID Ray, Faron
Keywords:	Explainability Machine Learning AI Explanation Causation
Subjects:	General Issues > Data General Issues > Causation Specific Sciences > Computer Science General Issues > Ethical Issues General Issues > Explanation
Depositing User:	Mr. Faron Ray
Date Deposited:	12 Nov 2022 13:52
Last Modified:	12 Nov 2022 13:52
Item ID:	21399
Subjects:	General Issues > Data General Issues > Causation Specific Sciences > Computer Science General Issues > Ethical Issues General Issues > Explanation
Date:	11 November 2022
URI:	https://philsci-archive.pitt.edu/id/eprint/21399

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item