Abstract
Most users of machine-learning products are reluctant to use them without any sense of the underlying logic that has led to the system’s predictions. Unfortunately many of these systems lack any transparency in the way they operate and are deemed to be black boxes. In this paper we present a Case-Based Reasoning (CBR) solution to providing supporting explanations of black-box systems. This CBR solution has two key facets; it uses local information to assess the importance of each feature and using this, it selects the cases from the data used to build the black-box system for use in explanation. The retrieval mechanism takes advantage of the derived feature importance information to help select cases that are a better reflection of the black-box solution and thus more convincing explanations.
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
R. Andrews J. Diederich A. Tickle (1995) ArticleTitleA Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural Networks Knowledge Based Systems 8 373–389 Occurrence Handle10.1016/0950-7051(96)81920-4
C.G. Atkeson A.W. Moore S. Schaal (1997) ArticleTitleLocally Weighted Learning Artificial Intelligence Review 11 11–73 Occurrence Handle10.1023/A:1006559212014
Cassens, J. (2004). Knowing What to Explain and When In Gervás, P., Gupta, K. (eds.) Proceedings of the ECCBR 2004 Workshops. 97–104, Technical Report 142-04, Departmento de Sistemas Informáticos y Programación, Universidad Complutense de Madrid, Madrid, Spain
Cunningham, P., Doyle, D., Loughrey, J. (2003). An Evaluation of the Usefulness of Case-Based Explanation In Ashley, K. D., Bridge, D. G. (eds.) ICCBR, Vol. 2689 of Lecture Notes in Computer Science. 122–130, Springer: Berlin
P. Domingos (1998) ArticleTitleKnowledge Discovery Via Multiple Models Intelligent Data Analysis 2 IssueID1–4 187–202 Occurrence Handle10.1016/S1088-467X(98)00023-7
D. Doyle P. Cunningham D. Bridge Y. Rahman (2004) Explanation Oriented Retrieval P. Funk P. Calero (Eds) Advances in Case-Based Reasoning (Procs. of the Seventh European Conference on Case-Based Reasoning) Springer Berlin 157–168
D. Gentner J. Loewenstein L. Thompson (2003) ArticleTitleLearning and Transfer: A General Role for Analogical Encoding Journal of Educational Psychology 95 IssueID2 393–408 Occurrence Handle10.1037/0022-0663.95.2.393
D. Leake (1996) CBR in Context: The Present and Future D. Leake (Eds) Case-Based Reasoning: Experiences, Lessons, and Future Directions AAAI Press Menlo Park, CA 3–30
A. Majchrzak L. Gasser (1991) ArticleTitleOn using Artificial Intelligence to Integrate the Design of Organizational and Process Change in US Manufacturing AI and Society 5 321–338 Occurrence Handle10.1007/BF02077438
McSherry, D. (2003). Explanation in Case-based Reasoning: an Evidential Approach In Proceeding of 8th UK Workshop on Case-Based Reasoning. 47–55.
D. McSherry (2004) Explaining the Pros and Cons of Conclusions in CBR P. Funk P. Calero (Eds) Advances in Case-Based Reasoning (Proceedings of the Seventh European Conference on Case-Based Reasoning) Springer Berlin 317–330
Sørmo, F., Cassens, J. (2004). Explanation Goals in Case-Based Reasoning. In Gervás, P., Gupta, K. (eds.) Proceedings of the ECCBR 2004 Workshops. 165–174, Technical Report 142-04, Departmento de Sistemas Informáticos y Programación, Universidad Complutense de Madrid, Madrid, Spain.
Sórmo, F., Cassens, J., Aamodt, A. (2005). Explanation in Case-Based Reasoning: Perspectives and Goals Artificial Intelligence Review This Issue.
A. Tickle R. Andrews R. Golea J. Diederich (1998) ArticleTitleThe Truth Will Come to Light: Directions and Challenges in Extracting Rules from Trained Neural Networks IEEE Transactions on Neural Networks 9 1057–1068 Occurrence Handle10.1109/72.728352
P. Walsh P. Cunningham S.J. Rothenberg S. O’Doherty H. Hoey R. Healy (2004) ArticleTitleAn Artificial Neural Network Ensemble to Predict Disposition and Length of Stay in Children Presenting with Bronchiolitis European Journal of Emergency Medicine 11 IssueID5 259–264 Occurrence Handle10.1097/00063110-200410000-00004 Occurrence Handle15359198
Z.-H. Zhou Y. Jiang (2003) ArticleTitleDiagnosis with C4.5 Preceded by Artificial Neural Network Ensemble Transactions on Information Technology in Biomedicine 7 IssueID1 37–42 Occurrence Handle10.1109/TITB.2003.808498 Occurrence Handle12670017
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Nugent, C., Cunningham, P. A Case-Based Explanation System for Black-Box Systems. Artif Intell Rev 24, 163–178 (2005). https://doi.org/10.1007/s10462-005-4609-5
Issue Date:
DOI: https://doi.org/10.1007/s10462-005-4609-5