CoChat
Sign Up
Cited by 84Explainable Artificial Intelligence (XAI)AI-based Problem Solving and PlanningSafety Systems Engineering in Autonomy

How Case-Based Reasoning Explains Neural Networks: A Theoretical Analysis of XAI Using Post-Hoc Explanation-by-Example from a Survey of ANN-CBR Twin-Systems

Open access
Keane, Mark T., Kenny, Eoin M.·2019·Lecture Notes in Computer Science
DOI 10.1007/978-3-030-29249-2_11
Open this paper in CoChat — free account

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/978-3-030-29249-2_11

Cites

65 of 65 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Tax administrations have an advantage over private sector stakeholders because they can access huge volumes of tax-sensitive data when implementing AI systems.

    “One of the big advantages tax administrations have over private sector stakeholders is that the former can rely on having access to huge volumes of tax-sensitive data as they implement their AI systems.29”

    From Towards eXplainable Artificial Intelligence (XAI) in Tax Law: The Need for a Minimum Legal Standard (2022) · cites this paper as [29]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 27

  1. [4]4. Kenny, E.M. and Keane, Mark T.: Twin-systems for explaining ANNs using CBR: Experiments using feature-weighting schemes to retrieve explanatory cases. Under review (2019)
  2. [10]10. Biran, O. and Cotton, C.: Explanation and justification in machine learning: A survey. In: IJCAI-17 workshop on explainable AI (XAI) (Vol. 8) p.1 (2017)
  3. [15]15. Salmon, W.C.: Scientific explanation and the causal structure of the world. Princeton University Press (1984)
  4. [18]18. Leake, D.B.: CBR in context: The present and future. Case-based reasoning: Experiences, lessons, and future directions, pp.3-30 (1996)
  5. [20]20. Caruana, R., Kangarloo, H., Dionisio, J.D., Sinha, U. and Johnson, D.: Case-based explanation of non-case-based learning methods. In: Proceedings of the AMIA Symposium, p. 212. American Medical Informatics Association (1999)
  6. [21]21. Kim, B., Rudin, C. and Shah, J.A.: The Bayesian case model: A generative approach for case-based reasoning and prototype classification. In: Adv. in NIPs, pp. 1952-1960 (2014)
  7. [23]23. Haykin, S.: Neural networks (Vol. 2). New York: Prentice Hall (1994)
  8. [24]24. Goodfellow, I., Bengio, Y. and Courville, A.: Deep learning. MIT Press (2016)
  9. [25]25. Kolodner, J.: Case based reasoning. Morgan Kaufmann (2014)
  10. [27]27. De Mantaras, R.L., McSherry, D., Bridge, D., Leake, D., Smyth, B., Craw, S., Faltings, B., Maher, M.L., Cox, M.T., Forbus, K. and Keane, M.T.: Retrieval, reuse, revise and retention in CBR. Knowledge Engineering Review, 20(3), 215-240 (2006)
  11. [29]29. Negnevitsky, M.: Artificial intelligence. Pearson education (2005)
  12. [30]30. Medsker, L.R.: Hybrid neural network and expert systems. Springer (2012)
  13. [32]32. Krizhevsky, A., Sutskever, I. and Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in NIPs, pp. 1097-1105 (2012)
  14. [33]33. Witten, Ian H., Eibe Frank, Mark A. Hall, and Christopher J. Pal.: Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann (2016)
  15. [35]35. Olden, J.D. and Jackson, D.A.: Illuminating the 'black box'. Ecological modelling, 154(12), pp.135-150 (2002)
  16. [37]37. Gilpin, L.H., Bau, D., Yuan, B.Z., Bajwa, A., Specter, M. and Kagal, L.: Explaining explanations: an approach to evaluating interpretability of machine learning. arXiv preprint arXiv:1806.00069 (2018) · arXiv
  17. [42]42. Nunes, I. and Jannach, D.: A systematic review and taxonomy of explanations in decision support and recommender systems. UMUAI, 27(3-5), 393-444 (2017)
  18. [43]43. Becker, L. and Jazayeri, K.: A connectionist approach to case-based reasoning. In: Proceedings of the Case-Based Reasoning Workshop, pp. 213-217. Morgan Kaufmann (1989)
  19. [44]44. Thrift, P.: A neural network model for case-based reasoning. In: Proceedings of the CaseBased Reasoning Workshop, pp. 334-337. Morgan Kaufmann (1989)
  20. [49]49. Park, J.H., Shin, C.K., Im, K.H. and Park, S.C.: A local weighting method to the integration of neural network and case based reasoning. In: Neural Networks for Signal Processing XI: Proceedings of the 2001 IEEE SPS Workshop, pp. 33-42. IEEE (2001)
  21. [52]52. Park, S.C., Kim, J.W. and Im, K.H.: Feature-weighted CBR with NN for symbolic features. In: International Conference on Intelligent Computing, 1012-1020. Springer (2006)
  22. [56]56. Yang, B.S., Han, T. and Kim, Y.S.: Integration of ART-Kohonen NN and CBR for intelligent fault diagnosis. Expert Systems with Applications, 26(3), 387-395 (2004)
  23. [62]62. Jothikimar, R., Shivakumar, N., Ramesh, P.S., Suganthan, and Suresh, A.: Heart Disease Prediction System Using ANN, RBF and CBR. International Journal of Pure and Applied Mathematics, 117(21), 199-217 (2017)
  24. [80]80. Olsson, T., Gillblad, D., Funk, P. and Xiong, N.: Case-based reasoning for explaining probabilistic machine learning. International Journal of Computer Science and Information Technology, 6(2), 87-101 (2014)
  25. [86]86. Sundararajan, M., Taly, A. and Yan, Q.: Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume, 70, 33193328. JMLR. Org (2017)
  26. [87]87. Shrikumar, A., Greenside, P. and Kundaje, A.: Learning important features through propagating activation differences. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, 3145-3153. JMLR. Org (2017)
  27. [90]90. Kofod-Petersen, A., Langseth, H., and Aamodt, A.: Explanations in Bayesian networks using provenance through case-based reasoning. In: Workshop Proceedings, p. 79 (2010)

Cited by

Sorted by citations

Related

Authors
Keane, M. T., & Kenny, E. M.
Affiliations
University College Dublin (IE)
Corresponding author
Keane, Mark T.
ORCID
Kenny, Eoin M.
Venue
Lecture Notes in Computer Science
Publisher
Springer International Publishing
Published
2019
Pages
155-171
ISSN
  • 0302-9743 (ISSN-L)
  • 1611-3349
DOI
10.1007/978-3-030-29249-2_11
OpenAlex
W2944854257
Cited by
84
References
61
Citations by year
2026: 4 · 2025: 5 · 2024: 18 · 2023: 12 · 2022: 16 · 2021: 13 · 2020: 12 · 2019: 4
FWCI
4.30
Type
conference paper
Language
en
Open access
Licence
Locations
  • Lecture notes in computer science (publishedVersion)
  • Research Repository UCD (University College Dublin) (acceptedVersion, cc-by-nc-nd)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Physical Sciences › Computer Science › Artificial Intelligence › AI-based Problem Solving and Planning
  • Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Safety Systems Engineering in Autonomy
Keywords
explainable AI, case-based reasoning, artificial neural networks, feature weighting, counterfactual explanations, deep neural network

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