Advertisement

Artificial Intelligence Review

, Volume 24, Issue 2, pp 163–178 | Cite as

A Case-Based Explanation System for Black-Box Systems

  • Conor NugentEmail author
  • Pádraig Cunningham
Article

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.

Keywords

black-box systems case-based reasoning explanation 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Andrews, R., Diederich, J., Tickle, A. 1995A Survey and Critique of Techniques for Extracting Rules from Trained Artificial Neural NetworksKnowledge Based Systems8373389CrossRefGoogle Scholar
  2. Atkeson, C.G., Moore, A.W., Schaal, S. 1997Locally Weighted LearningArtificial Intelligence Review111173CrossRefGoogle Scholar
  3. 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, SpainGoogle Scholar
  4. 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: BerlinGoogle Scholar
  5. Domingos, P. 1998Knowledge Discovery Via Multiple ModelsIntelligent Data Analysis2187202CrossRefGoogle Scholar
  6. Doyle, D., Cunningham, P., Bridge, D., Rahman, Y. 2004Explanation Oriented RetrievalFunk, P.Calero, P. eds. Advances in Case-Based Reasoning (Procs. of the Seventh European Conference on Case-Based Reasoning)SpringerBerlin157168Google Scholar
  7. Gentner, D., Loewenstein, J., Thompson, L. 2003Learning and Transfer: A General Role for Analogical EncodingJournal of Educational Psychology95393408CrossRefGoogle Scholar
  8. Leake, D. 1996CBR in Context: The Present and FutureLeake, D. eds. Case-Based Reasoning: Experiences, Lessons, and Future DirectionsAAAI PressMenlo Park, CA330Google Scholar
  9. Majchrzak, A., Gasser, L. 1991On using Artificial Intelligence to Integrate the Design of Organizational and Process Change in US ManufacturingAI and Society5321338CrossRefGoogle Scholar
  10. McSherry, D. (2003). Explanation in Case-based Reasoning: an Evidential Approach In Proceeding of 8th UK Workshop on Case-Based Reasoning. 47–55.Google Scholar
  11. McSherry, D. 2004Explaining the Pros and Cons of Conclusions in CBRFunk, P.Calero, P. eds. Advances in Case-Based Reasoning (Proceedings of the Seventh European Conference on Case-Based Reasoning)SpringerBerlin317330Google Scholar
  12. 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.Google Scholar
  13. Sórmo, F., Cassens, J., Aamodt, A. (2005). Explanation in Case-Based Reasoning: Perspectives and Goals Artificial Intelligence Review This Issue.Google Scholar
  14. Tickle, A., Andrews, R., Golea, R., Diederich, J. 1998The Truth Will Come to Light: Directions and Challenges in Extracting Rules from Trained Neural NetworksIEEE Transactions on Neural Networks910571068CrossRefGoogle Scholar
  15. Walsh, P., Cunningham, P., Rothenberg, S.J., O’Doherty, S., Hoey, H., Healy, R. 2004An Artificial Neural Network Ensemble to Predict Disposition and Length of Stay in Children Presenting with BronchiolitisEuropean Journal of Emergency Medicine11259264CrossRefPubMedGoogle Scholar
  16. Zhou, Z.-H., Jiang, Y. 2003Diagnosis with C4.5 Preceded by Artificial Neural Network EnsembleTransactions on Information Technology in Biomedicine73742CrossRefPubMedGoogle Scholar

Copyright information

© Springer 2005

Authors and Affiliations

  1. 1.Department of Computer Science, Trinity College, Machine Learning GroupUniversity of DublinDublinIreland

Personalised recommendations