FAT* 2019 Proceedings 1 (forthcoming)
Authors |
|
Abstract |
Recent work on interpretability in machine learning and AI has focused on the building of simplified models that approximate the true criteria used to make decisions. These models are a useful pedagogical device for teaching trained professionals how to predict what decisions will be made by the complex system, and most importantly how the system might break. However, when considering any such model it’s important to remember Box’s maxim that "All models are wrong but some are useful." We focus on the distinction between these models and explanations in philosophy and sociology. These models can be understood as a "do it yourself kit" for explanations, allowing a practitioner to directly answer "what if questions" or generate contrastive explanations without external assistance. Although a valuable ability, giving these models as explanations appears more difficult than necessary, and other forms of explanation may not have the same trade-offs. We contrast the different schools of thought on what makes an explanation, and suggest that machine learning might benefit from viewing the problem more broadly.
|
Keywords | interpretability explanations accountability philosophy of science data ethics machine learning artificial intelligence automated decision-making |
Categories | (categorize this paper) |
Options |
![]() ![]() ![]() ![]() |
Download options
References found in this work BETA
Models and Analogies in Science.Mary Hesse - 1965 - British Journal for the Philosophy of Science 16 (62):161-163.
How the Machine ‘Thinks’: Understanding Opacity in Machine Learning Algorithms.Jenna Burrell - 2016 - Big Data and Society 3 (1):205395171562251.
View all 25 references / Add more references
Citations of this work BETA
The Ethics of AI Ethics: An Evaluation of Guidelines.Thilo Hagendorff - 2020 - Minds and Machines 30 (1):99-120.
The Pragmatic Turn in Explainable Artificial Intelligence (XAI).Andrés Páez - 2019 - Minds and Machines 29 (3):441-459.
The Explanation Game: A Formal Framework for Interpretable Machine Learning.David S. Watson & Luciano Floridi - 2020 - Synthese 198 (10):1–32.
What is Interpretability?Adrian Erasmus, Tyler D. P. Brunet & Eyal Fisher - 2021 - Philosophy and Technology 34:833–862.
The Pragmatic Turn in Explainable Artificial Intelligence.Andrés Páez - 2019 - Minds and Machines 29 (3):441-459.
View all 31 citations / Add more citations
Similar books and articles
How Could Models Possibly Provide How-Possibly Explanations?Philippe Verreault-Julien - 2019 - Studies in History and Philosophy of Science Part A 73:1-12.
Contrastive, Non-Probabilistic Statistical Explanations.Bruce Glymour - 1998 - Philosophy of Science 65 (3):448-471.
Biological Teleology: Questions and Explanations.Robert N. Brandon - 1981 - Studies in History and Philosophy of Science Part A 12 (2):91.
Explanation as Condition Satisfaction.Paul Humphreys - 2014 - Philosophy of Science 81 (5):1103-1116.
Dynamical Models and Explanation in Neuroscience.Lauren N. Ross - 2015 - Philosophy of Science 82 (1):32-54.
On Explanations From Geometry of Motion.Juha Saatsi - 2018 - British Journal for the Philosophy of Science 69 (1):253–273.
Inference to the Best Explanation (IBE) Versus Explaining for the Best Inference.Tania Lombrozo & Daniel Wilkenfeld - 2015 - Science & Education 24 (9-10):1059-1077.
Two Challenges for CI Trustworthiness and How to Address Them.Kevin Baum, Eva Schmidt & A. Köhl Maximilian - 2017
How-Possibly Explanation in Biology: Lessons From Wilhelm His’s ‘Simple Experiments’ Models.Christopher Pearson - 2018 - Philosophy, Theory, and Practice in Biology 10.
One Mechanism, Many Models: A Distributed Theory of Mechanistic Explanation.Eric Hochstein - 2016 - Synthese 193 (5):1387-1407.
Contrastive Constraints Guide Explanation‐Based Category Learning.Seth Chin‐Parker & Julie Cantelon - 2017 - Cognitive Science 41 (6):1645-1655.
On Explanations From Geometry of Motion.Juha Saatsi - 2016 - British Journal for the Philosophy of Science:axw007.
On Explanations From Geometry of Motion.Juha Saatsi - 2018 - British Journal for the Philosophy of Science 69 (1):253–273.
The Diversity of Models as a Means to Better Explanations in Economics.Emrah Aydinonat - 2018 - Journal of Economic Methodology 25 (3):237-251.
Analytics
Added to PP index
2018-11-04
Total views
893 ( #7,727 of 2,520,967 )
Recent downloads (6 months)
81 ( #9,307 of 2,520,967 )
2018-11-04
Total views
893 ( #7,727 of 2,520,967 )
Recent downloads (6 months)
81 ( #9,307 of 2,520,967 )
How can I increase my downloads?
Downloads