ANNs and Unifying Explanations: Reply to Erasmus, Brunet, and Fisher

Philosophy and Technology 35 (2):1-9 (2022)
  Copy   BIBTEX

Abstract

In a recent article, Erasmus, Brunet, and Fisher (2021) argue that Artificial Neural Networks (ANNs) are explainable. They survey four influential accounts of explanation: the Deductive-Nomological model, the Inductive-Statistical model, the Causal-Mechanical model, and the New-Mechanist model. They argue that, on each of these accounts, the features that make something an explanation is invariant with regard to the complexity of the explanans and the explanandum. Therefore, they conclude, the complexity of ANNs (and other Machine Learning models) does not make them less explainable. In this reply, it is argued that Erasmus et al. left out one influential account of explanation from their discussion: the Unificationist model. It is argued that, on the Unificationist model, the features that makes something an explanation is sensitive to complexity. Therefore, on the Unificationist model, ANNs (and other Machine Learning models) are not explainable. It is emphasized that Erasmus et al.’s general strategy is correct. The literature on explainable Artificial Intelligence can benefit by drawing from philosophical accounts of explanation. However, philosophical accounts of explanation do not settle the problem of whether ANNs are explainable because they do not unanimously declare that explanation is invariant with regard to complexity.

Similar books and articles

What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
Grounding, scientific explanation, and Humean laws.Marc Lange - 2013 - Philosophical Studies 164 (1):255-261.
Causal patterns and adequate explanations.Angela Potochnik - 2015 - Philosophical Studies 172 (5):1163-1182.
Scientific laws and scientific explanations: A differentiated typology.Igor Hanzel - 2008 - Organon F: Medzinárodný Časopis Pre Analytickú Filozofiu 15 (3):323-344.
A deductive-nomological model for mathematical scientific explanation.Eduardo Castro - 2020 - Principia: An International Journal of Epistemology 24 (1):1-27.

Analytics

Added to PP
2022-04-21

Downloads
73 (#166,913)

6 months
40 (#33,288)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Yunus Prasetya
Yale-NUS College

Citations of this work

Interpretability and Unification.Adrian Erasmus & Tyler D. P. Brunet - 2022 - Philosophy and Technology 35 (2):1-6.

Add more citations