EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Do Machine Learning Models Represent Their Targets?

Emily Sullivan

Philosophy of Science · 2024-12 · 91 (5) · 1445-1455

DOI: 10.1017/psa.2023.151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Philosophy of Science, online erschienen am 20.10.2023. Verfasst von Emily Sullivan. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

I argue that machine learning (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.

Zitieren

APA

Sullivan, E. (2024). Do Machine Learning Models Represent Their Targets?. Philosophy of Science, 91(5), 1445-1455. https://doi.org/10.1017/psa.2023.151

Vancouver

Sullivan E. Do Machine Learning Models Represent Their Targets?. Philosophy of Science. 2024;91(5):1445-1455. doi:10.1017/psa.2023.151

BibTeX
@article{Sullivan2024,
  author = {Sullivan, Emily},
  title = {Do Machine Learning Models Represent Their Targets?},
  journal = {Philosophy of Science},
  year = {2024},
  volume = {91},
  number = {5},
  pages = {1445--1455},
  doi = {10.1017/psa.2023.151}
}
Kostenlos starten →