Minds and Machines 32:185-218 (2022)
Authors |
|
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 |
![]() ![]() ![]() ![]() |
Download options
References found in this work BETA
No references found.
Citations of this work BETA
Conceptual Challenges for Interpretable Machine Learning.David S. Watson - 2022 - Synthese 200 (2):1-33.
Similar books and articles
Solving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence.Carlos Zednik - 2021 - Philosophy and Technology 34 (2):265-288.
Solving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence.Carlos Zednik - 2019 - Philosophy and Technology 34 (2):265-288.
Solving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence.Carlos Zednik - 2021 - Philosophy and Technology 34 (2):265-288.
“That Will Do”: Logics of Deontic Necessity and Sufficiency.Frederik Putte - 2017 - Erkenntnis 82 (3):473-511.
“That Will Do”: Logics of Deontic Necessity and Sufficiency.Frederik Van De Putte - 2017 - Erkenntnis 82 (3):473-511.
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.
Moral Orthoses: A New Approach to Human and Machine Ethics.Marius Dorobantu & Yorick Wilks - 2019 - Zygon 54 (4):1004-1021.
Levels of Explainable Artificial Intelligence for Human-Aligned Conversational Explanations.Richard Dazeley, Peter Vamplew, Cameron Foale, Charlotte Young, Sunil Aryal & Francisco Cruz - 2021 - Artificial Intelligence 299:103525.
Bayesian Nets and Causality: Philosophical and Computational Foundations.Jon Williamson - 2004 - Oxford, England: Oxford University Press.
The Pragmatic Turn in Explainable Artificial Intelligence (XAI).Andrés Páez - 2019 - Minds and Machines 29 (3):441-459.
A Dynamic Interaction Between Machine Learning and the Philosophy of Science.Jon Williamson - 2004 - Minds and Machines 14 (4):539-549.
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 )
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