From Explanations to Interpretability and Back
Abstract
This chapter discusses connections between interpretability of machine learning and (scientific and mathematical) explanations, provides novel perspectives on interpretability, and highlights under-explored issues. Interpretability types are proposed: kinds of interpretability should be distinguished using both the parts of ML we want to explain and the parts of ML we use to explain. It is argued that not all explanations are contrastive, and that we should also consider contrasts with respect to models and data, not only with respect to inputs. Theoretical explanations are highlighted; they include issues like generalization, optimization, and expressivity. It is proposed that there are two threats to the objectivity of explanations: One from radical subject-dependence, the other from a lack of factivity. Finally, pluralism is advocated: There are different notions of interpretability and different notions of (scientific and mathematical) explanations. However, the heterogeneity of one area does not transfer to the other in a straightforward manner.
Date Issued
2024
Publication Type
Book Section
Subject(s)
Language(s)
en
Additional Credits
Publisher
Springer
Related URL(s)
https://philsci-archive.pitt.edu/23169/
Access(Rights)
restricted