What is Interpretability?

Philosophy and Technology 34:833–862 (2021)
  Copy   BIBTEX


We argue that artificial networks are explainable and offer a novel theory of interpretability. Two sets of conceptual questions are prominent in theoretical engagements with artificial neural networks, especially in the context of medical artificial intelligence: Are networks explainable, and if so, what does it mean to explain the output of a network? And what does it mean for a network to be interpretable? We argue that accounts of “explanation” tailored specifically to neural networks have ineffectively reinvented the wheel. In response to, we show how four familiar accounts of explanation apply to neural networks as they would to any scientific phenomenon. We diagnose the confusion about explaining neural networks within the machine learning literature as an equivocation on “explainability,” “understandability” and “interpretability.” To remedy this, we distinguish between these notions, and answer by offering a theory and typology of interpretation in machine learning. Interpretation is something one does to an explanation with the aim of producing another, more understandable, explanation. As with explanation, there are various concepts and methods involved in interpretation: Total or Partial, Global or Local, and Approximative or Isomorphic. Our account of “interpretability” is consistent with uses in the machine learning literature, in keeping with the philosophy of explanation and understanding, and pays special attention to medical artificial intelligence systems.

Similar books and articles

Explaining Explanations in AI.Brent Mittelstadt - forthcoming - FAT* 2019 Proceedings 1.
Out of their minds: Legal theory in neural networks. [REVIEW]Dan Hunter - 1999 - Artificial Intelligence and Law 7 (2-3):129-151.
Diabetes Prediction Using Artificial Neural Network.Nesreen Samer El_Jerjawi & Samy S. Abu-Naser - 2018 - International Journal of Advanced Science and Technology 121:54-64.
Some Neural Networks Compute, Others Don't.Gualtiero Piccinini - 2008 - Neural Networks 21 (2-3):311-321.


Added to PP

146 (#102,118)

6 months
13 (#96,103)

Historical graph of downloads
How can I increase my downloads?

Author's Profile

Adrian Erasmus
University of Alabama