Sullivan, Emily (2023) Do ML models represent their targets? [Preprint]

Preview

Text Rep_PSA_final.pdf Download (215kB) | Preview

Abstract

I argue that ML models used in science function as highly idealized toy models. If we treat ML models as a type of highly idealized toy model, then we can deploy standard representational and epistemic strategies from the toy model literature to explain why ML models can still provide epistemic success despite their lack of similarity to their targets.

---

Export/Citation:

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

Social Networking:

Share |

---

Item Type:	Preprint
Creators:	Creators Email ORCID Sullivan, Emily eesullivan29@gmail.com 0000-0002-2073-5384
Keywords:	Machine learning, scientific understanding, idealization, toy models
Subjects:	Specific Sciences > Artificial Intelligence General Issues > Explanation Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Models and Idealization General Issues > Technology
Depositing User:	Dr. Emily Sullivan
Date Deposited:	10 Oct 2023 19:48
Last Modified:	10 Oct 2023 19:48
Item ID:	22648
Subjects:	Specific Sciences > Artificial Intelligence General Issues > Explanation Specific Sciences > Artificial Intelligence > Machine Learning General Issues > Models and Idealization General Issues > Technology
Date:	10 October 2023
URI:	https://philsci-archive.pitt.edu/id/eprint/22648

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item