ML Interpretability: Simple Isn’t Easy

Räz, Tim (2024). ML Interpretability: Simple Isn’t Easy. Studies in history and philosophy of science, 103, pp. 159-167. Elsevier 10.1016/j.shpsa.2023.12.007

Preview

Text 1-s2.0-S0039368123001723-main.pdf - Published Version Available under License Creative Commons: Attribution (CC-BY). Download (1MB) | Preview

The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the “interpretability spectrum”. The reasons why some models, linear models and decision trees, are highly interpretable will be examined, and also how more general models, MARS and GAM, retain some degree of interpretability. It is found that while there is heterogeneity in how we gain interpretability, what interpretability is in particular cases can be explicated in a clear manner.

Interest & Impact

Downloads

12 since deposited on 28 Dec 2023
12 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item