PhilSci Archive

Inductive Risk, Understanding, and Opaque Machine Learning Models

Sullivan, Emily (2022) Inductive Risk, Understanding, and Opaque Machine Learning Models. [Preprint]

[img]
Preview
Text
riskML_opacity_sullivan.pdf

Download (311kB) | Preview

Abstract

Under what conditions does machine learning (ML) model opacity inhibit the possibility of explaining and understanding phenomena? In this paper, I argue that non-epistemic values give shape to the ML opacity problem even if we keep researcher interests fixed. Treating ML models as an instance of doing model-based science to explain and understand phenomena reveals that there is (i) an external opacity problem, where the presence of inductive risk imposes higher standards on externally validating models, and (ii) an internal opacity problem, where greater inductive risk demands a higher level of transparency regarding the inferences the model makes.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Sullivan, Emily0000-0002-2073-5384
Keywords: inductive risk, model-based science, machine learning, epistemic opacity, scientific understanding
Subjects: General Issues > Data
Specific Sciences > Artificial Intelligence > AI and Ethics
General Issues > Ethical Issues
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Models and Idealization
General Issues > Values In Science
Depositing User: Dr. Emily Sullivan
Date Deposited: 24 Apr 2022 18:15
Last Modified: 24 Apr 2022 18:15
Item ID: 20507
Subjects: General Issues > Data
Specific Sciences > Artificial Intelligence > AI and Ethics
General Issues > Ethical Issues
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Models and Idealization
General Issues > Values In Science
Date: April 2022
URI: https://philsci-archive.pitt.edu/id/eprint/20507

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item