What is Interpretability?
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
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: (1) Are networks explainable, and if so, what does it mean to explain the output of a network? And (2) 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 (1), 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 (2) 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Rudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561
Dissecting racial bias in an algorithm used to manage the health of populations
Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2019) · Science · doi:10.1126/science.aax2342 · Cited by 7,137 · cited 1×
“…including vulnerabilities to nefariously motivated adversarial attacks by various stakeholders in the healthcare system (Finlayson et al. 2019) and algorithmic racial biases in the prediction of future health care needs due to objective functions and training procedures (Obermeyer et al. 2019).”
BackgroundLipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427
Explanation in artificial intelligence: Insights from the social sciences
Miller, T. (2019) · Artificial Intelligence · doi:10.1016/j.artint.2018.07.007 · Cited by 5,302
Fraassen, B. C. V. (1980) · doi:10.1093/0198244274.001.0001 · Cited by 4,682
International evaluation of an AI system for breast cancer screening
McKinney, S. M., Sieniek, M., Godbole, V., Godwin, J., Antropova, N., Ashrafian, H., Back, T., Chesus, M., Corrado, G. S., Darzi, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1799-6 · Cited by 3,287 · cited 1×
“Indeed, many MAIS are already deployed in the clinic, including algorithms aimed at diagnosing retinal disease (De Fauw et al. 2018), and breast cancer treatment recommendations (Somashekhar et al. 2018) and screening (McKinney et al. 2020).”
MethodMachamer, P., Darden, L., & Craver, C. F. (2000) · Philosophy of Science · doi:10.1086/392759 · Cited by 3,179 · cited 1×
“These views all center on the idea that providing a mechanism is important for explanation, and originate largely from the work of Machamer et al. (2000), Bech-tel (2011), and Craver and Darden (2013).”
BackgroundStudies in the Logic of Explanation
Hempel, C. G., & Oppenheim, P. (1948) · Philosophy of Science · doi:10.1086/286983 · Cited by 3,174 · cited 2×
“Philosophers have reflected on the nature of explanation since before Socrates, but the modern discussion began in the late 1940s with Hempel and Oppenheim (1948).”
BackgroundTowards A Rigorous Science of Interpretable Machine Learning
Doshi-Velez, F., & Kim, B. (2017) · arXiv · doi:10.48550/arxiv.1702.08608 · Cited by 3,121
Clinically applicable deep learning for diagnosis and referral in retinal disease
De Fauw, J., Ledsam, J. R., Romera-Paredes, B., Nikolov, S., Tomasev, N., Blackwell, S., Askham, H., Glorot, X., O’Donoghue, B., Visentin, D., et al. (2018) · Nature Medicine · doi:10.1038/s41591-018-0107-6 · Cited by 2,639
Cited by
Longo, L., Brcic, M., Cabitza, F., Choi, J., Confalonieri, R., Ser, J. D., Guidotti, R., Hayashi, Y., Herrera, F., Holzinger, A., et al. (2024) · Information Fusion · doi:10.1016/j.inffus.2024.102301 · Cited by 626
How Explainability Contributes to Trust in AI
Ferrario, A., & Loi, M. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533202 · Cited by 163
A survey on explainable artificial intelligence for cybersecurity
Rjoub, G., Bentahar, J., Abdel Wahab, O., Mizouni, R., Song, A., Cohen, R., Otrok, H., & Mourad, A. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3282740 · Cited by 158
AI, Opacity, and Personal Autonomy
Vaassen, B. (2022) · Philosophy & Technology · doi:10.1007/s13347-022-00577-5 · Cited by 94
“I cannot address his concerns here, but see Erasmus et al. (2020); Erasmus and Brunet (2022) for a response.”
BackgroundScientific Exploration and Explainable Artificial Intelligence
Zednik, C., & Boelsen, H. (2022) · Minds and Machines · doi:10.1007/s11023-021-09583-6 · Cited by 80
Metadata
- Authors
- Erasmus, A., Brunet, T. D. P., & Fisher, E.
- Venue
- Philosophy & Technology
- Published
- 2020-11-12
- Volume
- 34
- Issue
- 4
- Pages
- 833-862
- ISSN
- 2210-5433 (ISSN-L)
- 2210-5441
- OpenAlex
- W3103654318
- Cited by
- 80
- References
- 31
- FWCI
- 3.03
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: What is Interpretability? https://app.cochat.ai/papers/10.1007/s13347-020-00435-2
- The paper
- Erasmus, A., Brunet, T. D. P., & Fisher, E. (2021). What is Interpretability? Philosophy & Technology. https://doi.org/10.1007/s13347-020-00435-2
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.