Minds and Machines 32:185-218 (2022)

Authors
David Watson
University College London
Luciano Floridi
Oxford University
Abstract
Necessity and sufficiency are the building blocks of all successful explanations. Yet despite their importance, these notions have been conceptually underdeveloped and inconsistently applied in explainable artificial intelligence (XAI), a fast-growing research area that is so far lacking in firm theoretical foundations. Building on work in logic, probability, and causality, we establish the central role of necessity and sufficiency in XAI, unifying seemingly disparate methods in a single formal framework. We provide a sound and complete algorithm for computing explanatory factors with respect to a given context, and demonstrate its flexibility and competitive performance against state of the art alternatives on various tasks.
Keywords Machine learning  Explainable artificial intelligence (XAI)  Logic  Probability  Causality
Categories (categorize this paper)
Options
Edit this record
Mark as duplicate
Export citation
Find it on Scholar
Request removal from index
Revision history

Download options

PhilArchive copy

 PhilArchive page | Other versions
External links

Setup an account with your affiliations in order to access resources via your University's proxy server
Configure custom proxy (use this if your affiliation does not provide a proxy)
Through your library

References found in this work BETA

No references found.

Add more references

Citations of this work BETA

Add more citations

Similar books and articles

What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
Abductive Equivalence in First-Order Logic.Katsumi Inoue & Chiaki Sakama - 2006 - Logic Journal of the IGPL 14 (2):333-346.
Philosophy and Machine Learning.Paul Thagard - 1990 - Canadian Journal of Philosophy 20 (2):261-76.

Analytics

Added to PP index
2021-06-15

Total views
65 ( #176,106 of 2,506,123 )

Recent downloads (6 months)
33 ( #27,324 of 2,506,123 )

How can I increase my downloads?

Downloads

My notes