Do ML models represent their targets?

Philosophy of Science (forthcoming)
  Copy   BIBTEX

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.

Categories

Keywords

Reprint years

Links

PhilArchive

External links

  • This entry has no external links. Add one.
Setup an account with your affiliations in order to access resources via your University's proxy server

Through your library

My notes

Similar books and articles

Understanding from Machine Learning Models.Emily Sullivan - 2022 - British Journal for the Philosophy of Science 73 (1):109-133.
Models, fiction and fictional models.Liu Chuang - unknown
It’s Not a Game: Accurate Representation with Toy Models.James Nguyen - 2020 - British Journal for the Philosophy of Science 71 (3):1013-1041.
Why We Cannot Learn from Minimal Models.Roberto Fumagalli - 2016 - Erkenntnis 81 (3):433-455.
Models, Pictures, and Unified Accounts of Representation: Lessons from Aesthetics for Philosophy of Science.Stephen M. Downes - 2009 - Perspectives on Science 17 (4):417-428.
Factive scientific understanding without accurate representation.Collin C. Rice - 2016 - Biology and Philosophy 31 (1):81-102.
Understanding (With) Toy Models.Alexander Reutlinger, Dominik Hangleiter & Stephan Hartmann - 2016 - British Journal for the Philosophy of Science:axx005.
No Learning from Minimal Models.Roberto Fumagalli - 2015 - Philosophy of Science 82 (5):798-809.
Evaluating Artificial Models of Cognition.Marcin Miłkowski - 2015 - Studies in Logic, Grammar and Rhetoric 40 (1):43-62.
Sources of Understanding in Supervised Machine Learning Models.Paulo Pirozelli - 2022 - Philosophy and Technology 35 (2):1-19.
Bending Molecules or Bending the Rules? The Application of Theoretical Models in Fragrance Chemistry.Ann-Sophie Barwich - 2015 - Perspectives on Science 23 (4):443-465.
Hypothetical Pattern Idealization and Explanatory Models.Yasha Rohwer & Collin Rice - 2013 - Philosophy of Science 80 (3):334-355.
Mechanistic Models and the Explanatory Limits of Machine Learning.Emanuele Ratti & Ezequiel López-Rubio - unknown
An instrumentalist take on the models of the Free-Energy Principle.Niccolò Aimone Pisano - 2023 - Synthese 201 (4):1-27.
Idealization.Michael Weisberg Alkistis Elliott‐Graves - 2014 - Philosophy Compass 9 (3):176-185.

Analytics

Added to PP
2023-10-10

Downloads
356 (#56,746)

6 months
244 (#9,978)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Emily Sullivan
Utrecht University

Citations of this work

Add more citations

References found in this work

True Enough.Catherine Z. Elgin - 2017 - Cambridge: MIT Press.
Idealization and the Aims of Science.Angela Potochnik - 2017 - Chicago: University of Chicago Press.
Understanding from Machine Learning Models.Emily Sullivan - 2022 - British Journal for the Philosophy of Science 73 (1):109-133.
Transparency in Complex Computational Systems.Kathleen A. Creel - 2020 - Philosophy of Science 87 (4):568-589.
How models are used to represent reality.Ronald N. Giere - 2004 - Philosophy of Science 71 (5):742-752.

View all 20 references / Add more references