Interpretability and Unification

Philosophy and Technology 35 (2):1-6 (2022)
  Copy   BIBTEX

Abstract

In a recent reply to our article, “What is Interpretability?,” Prasetya argues against our position that artificial neural networks are explainable. It is claimed that our indefeasibility thesis—that adding complexity to an explanation of a phenomenon does not make the phenomenon any less explainable—is false. More precisely, Prasetya argues that unificationist explanations are defeasible to increasing complexity, and thus, we may not be able to provide such explanations of highly complex AI models. The reply highlights an important lacuna in our original paper, the omission of the unificationist account of explanation, and affords us the opportunity to respond. Here, we argue that artificial neural networks are explainable in a way that should satisfy unificationists and that interpretability methods present ways in which ML theories can achieve unification.

Other Versions

No versions found

Similar books and articles

What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
EXPLAINABLE ARTIFICIAL INTELLIGENCE (XAI): ENHANCING TRANSPARENCY AND TRUST IN MACHINE LEARNING MODELS.Prasad Pasam Thulasiram - 2025 - International Journal for Innovative Engineering and Management Research 14 (1):204-213.
Externalist XAI?Anders Søgaard - 2025 - Theoria 91 (2):e12581.
Explainable AI (XAI).Rami Al-Dahdooh, Ahmad Marouf, Mahmoud Jamal Abu Ghali, Ali Osama Mahdi, Bassem S. Abu-Nasser & Samy S. Abu-Naser - 2025 - International Journal of Academic Information Systems Research (IJAISR) 9 (1):65-70.
Explaining AI through mechanistic interpretability.Lena Kästner & Barnaby Crook - 2024 - European Journal for Philosophy of Science 14 (4):1-25.
Transparency and Interpretability in Cloud- based Machine Learning with Explainable AI.V. Talati Dhruvitkumar - 2024 - International Journal of Multidisciplinary Research in Science, Engineering and Technology 7 (7):11823-11831.

Analytics

Added to PP
2022-04-24

Downloads
647 (#47,672)

6 months
146 (#40,544)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

References found in this work

Explanatory unification.Philip Kitcher - 1981 - Philosophy of Science 48 (4):507-531.
Explanatory unification and the causal structure of the world.Philip Kitcher - 1962 - In Philip Kitcher & Wesley C. Salmon, Scientific Explanation. Univ of Minnesota Pr. pp. 410-505.

Add more references