Explaining Explanation, Part 4: A Deep Dive on Deep Nets
The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
Abstract
This is the fourth in a series of essays about "explainable AI." Previous essays laid out the theoretical and empirical foundations. This essay focuses on Deep Nets, and considers methods for allowing system users to generate self-explanations. This is accomplished by exploring how the Deep Net systems perform when they are operating at their "boundary conditions." Inspired by recent research into adversarial examples that demonstrate the weaknesses of Deep Nets, we invert the purpose of these adversarial examples and argue that spoofing can be used as a tool to answer contrastive explanation questions via user-driven exploration.
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
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Lipton, 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
Self-citationPractical Black-Box Attacks against Machine Learning
Papernot, N., McDaniel, P., Goodfellow, I., Jha, S., Celik, Z. B., & Swami, A. (2017) · Proceedings of the 2017 ACM on Asia Conference on Computer and Communications Security · doi:10.1145/3052973.3053009 · Cited by 3,495
Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images
Nguyen, A., Yosinski, J., & Clune, J. (2014) · arXiv · doi:10.48550/arxiv.1412.1897 · Cited by 3,258
Deep neural networks are easily fooled: High confidence predictions for unrecognizable images
Nguyen, A., Yosinski, J., & Clune, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298640 · Cited by 3,258
Making Things Happen: A Theory of Causal Explanation
Woodward, J. (2004) · doi:10.1093/0195155270.001.0001 · Cited by 1,302
Deep Learning: A Critical Appraisal
Marcus, G. (2018) · arXiv · doi:10.48550/arxiv.1801.00631 · Cited by 853
Cited by
DARPA's Explainable Artificial Intelligence Program
Gunning, D., & Aha, D. W. (2019) · AI Magazine · doi:10.1609/aimag.v40i2.2850 · Cited by 1,360
“This methodology was described in a series of essays (Hoffman and Klein 2017; Hoffman et al. 2017; Klein 2018; Hoffman et al. 2018).”
MethodDesigning Theory-Driven User-Centric Explainable AI
Wang, D., Yang, Q., Abdul, A., & Lim, B. Y. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300831 · Cited by 906
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2021) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3387166 · Cited by 785
A Multidisciplinary Survey and Framework for Design and Evaluation of Explainable AI Systems
Mohseni, S., Zarei, N., & Ragan, E. D. (2018) · arXiv · doi:10.48550/arxiv.1811.11839 · Cited by 783
“te self-explanations, and identified purposes and patterns for causal reasoning [74, 92]. They lastly focus on DNNs to examine their theoretical and empirical findings on a machine learning algorithm [69]. In another work, they presented a conceptual model of the process of explaining in the XAI context, see [75]. The…”
BackgroundCounterfactuals in Explainable Artificial Intelligence (XAI): Evidence from Human Reasoning
Byrne, R. M. J. (2019) · Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/876 · Cited by 285
“An interpretable model allows a human user to mentally simulate some aspects of the system, and to understand the causes of its decisionmaking [Hoffman et al., 2018].”
Metadata
- Authors
- Hoffman, R., Miller, T., Mueller, S. T., Klein, G., & Clancey, W. J.
- Venue
- IEEE Intelligent Systems
- Published
- 2018-05
- Volume
- 33
- Issue
- 3
- Pages
- 87-95
- ISSN
- 1541-1672 (ISSN-L)
- 1941-1294
- OpenAlex
- W2886218892
- Cited by
- 54
- References
- 8
- FWCI
- 3.11
- Type
- journal article
- Language
- en
- Open access
- closed
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
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.