Advertisement

Towards more collaboration between machine learning systems and their users

  • Jean-Marc Gabriel
Short Papers
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1319)

Abstract

This article investigates a way to deepen collaboration between Machine Learning Systems (MLS) and their users through the generation of explanations. More precisely, it focuses on the advises that may be given for helping the user during the evaluation of the MLS results and their correction. This is illustrated through the system EILP, an explanatory interface that supports the user during these tasks.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Adé & al., 95]
    H. Adé, L. De Raedt & M. Bruynooghe. Declarative Bias for Specific-toGeneral ILP Systems. Machine Learning, 20. pp. 119–154. 1995.Google Scholar
  2. [Bisson, 92]
    G. Bisson. Learning in FOL with a similarity measure. In Proceedings of 10th National Conference on Artificial Intelligence (AAAI ). San-Jose. pp. 82–87. 1992.Google Scholar
  3. [De Raedt & al., 92]
    L. De Raedt & M. Bruynooghe. An Overview of the Interactive Concept-Learner and Theory Revisor CLINT. In Inductive Logic Programming. S. Muggleton (eds.). Academic Press. pp 163–191. 1992.Google Scholar
  4. [Gabriel, 97]
    J.M. Gabriel. When Explanations enable Cooperation between a Machine Learning System and its User. To appears in the Proceedings of the 6th International Conference on Intelligent Systems (ICIS'97), Boston. 1997.Google Scholar
  5. [Mitchell, 80]
    T.M. Mitchell. The Need for Biases in Learning Generalizations. Technical Report, Rutgers University, New Brunswick. 1980.Google Scholar
  6. [Morik, 93]
    K. Morik. Balanced Cooperative Modeling. Machine Learning, 11. pp. 225–235. 1993.Google Scholar
  7. [Nédellec & al., 1994]
    C. Nédellec & C. Rouveirol. Specifications of the HAIKU system. Research Report n°928, University de PARIS Sud. 1994.Google Scholar
  8. [Nedellec, 92]
    C. Nedellec & K. Causse. Knowedge Refinement using Knowledge Acquisition and Machine Learning Methods. In Proceedings of the 6th European Knowledge Acquisition Workshop, EKAW'92. pp 171–190. 1992.Google Scholar
  9. [Richards & al., 1995]
    B.L. Richards & R.J. Mooney. Automated Refinement of First-Order Horn-Clause Domain Theories. Machine Learnings, 19, 1995.Google Scholar
  10. [Wogulis,93]
    J. Wogulis. Handling Negation in First-Order Theory Revision. In Proceedings of IJCAI'93 workshop on Inductive Logic Programming, Chambéry, France. Morgan Kaufmann. 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Jean-Marc Gabriel
    • 1
  1. 1.Sherpa project (INRIA Rhône-Alpes)Montbonnot Saint MartinFrance

Personalised recommendations