Cover Image
QR Code

The Limits of Value Transparency in Machine Learning.

Transparency has been proposed as a way of handling value-ladenness in machine learning (ML). This article highlights limits to this strategy. I distinguish three kinds of transparency: epistemic transparency, retrospective value transparency, and prospective value transparency. This corresponds to...

Full description

Published in:Philosophy of Science Vol. 89; no. 5; pp. 1054 - 1065
Main Author: Nyrup, Rune
Format: Article
Published: Cambridge University Press Dec2022
Subjects:
Machine learning
Artificial intelligence
Information design
Network governance
Online Access:View this record in EBSCOhost