Advertisement

Boosting first-order learning

  • J. R. Quinlan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1160)

Abstract

Several empirical studies have confirmed that boosting classifier-learning systems can lead to substantial improvements in predictive accuracy. This paper reports early experimental results from applying boosting to ffoil, a first-order system that constructs definitions of functional relations. Although the evidence is less convincing than that for propositional-level learning systems, it suggests that boosting will also prove beneficial for first-order induction.

Keywords

Training Instance Inductive Logic Programming Horn Clause Target Relation Background Relation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bell, S., and Weber, S.: On the close logical relationship between foil and the frameworks of Helft and Plotkin. In Proceedings Third International Workshop on Inductive Logic Programming, Bled, Slovenia (1993) 127–147Google Scholar
  2. 2.
    Bergadano, F., and Gunetti, D.: An interactive system to learn functional logic programs. In Proceedings Thirteenth International Joint Conference on Artificial Intelligence, Chambery, France (Morgan Kaufmann, San Francisco, 1993) 1044–1049Google Scholar
  3. 3.
    Breiman, L.: Bagging predictors. Machine Learning (1996) to appearGoogle Scholar
  4. 4.
    Breiman, L.: Bias, variance, and arcing classifiers. Technical Report 460, Statistics Department, University of California, Berkeley, 1996Google Scholar
  5. 5.
    Cameron-Jones, R.M., and Quinlan, J.R.: Efficient top-down induction of logic programs. SIGART 5 (1994) 33–42Google Scholar
  6. 6.
    Cohen, W.W.: Recovering software specifications with inductive logic programming. In Proceedings AAAI-94 Twelfth National Conference on Artificial Intelligence, Seattle, Washington (AAAI Press, Menlo Park, CA, 1994) 142–148.Google Scholar
  7. 7.
    Dolšak, B., and Muggleton, S.: The application of inductive logic programming to finite element mesh design. In S. Muggleton, ed., Inductive Logic Programming (Academic Press, London, 1992) 453–472Google Scholar
  8. 8.
    Esposito, F., Malerba, D., Semeraro, G., and Pazzani, M.: A machine learning approach to document understanding. In Proceedings Second International Workshop on Multistrategy Learning (West Virginia, 1993) 276–292Google Scholar
  9. 9.
    Freund, Y., and Schapire, R. E.: A decision-theoretic generalization of on-line learning and an application to boosting. Unpublished manuscript, available from the authors' home pages (“http://www.research.att.com/orgs/ssr/people/sav, schapire”), 1996Google Scholar
  10. 10.
    Ling, C.X.: Learning the past tense of English verbs: the symbolic pattern associator versus connectionist models. Journal of Artificial Intelligence Research 1 (1994) 209–229Google Scholar
  11. 11.
    Mooney, R.J., and Califf, M.E.: Induction of first-order decision lists: results on learning the past tense of English verbs. Journal of Artificial Intelligence Research 3 (1995) 1–24CrossRefGoogle Scholar
  12. 12.
    Muggleton, S., and Feng, C.: Efficient induction of logic programs. In S. Muggleton, ed., Inductive Logic Programming (Academic Press, London, 1992) 281–298Google Scholar
  13. 13.
    Muggleton, S.: Inverse entailment and Progol. New Generation Computing 13 (1995) 245–286Google Scholar
  14. 14.
    Pazzani, M. and Kibler, D.: The utility of knowledge in inductive learning. Machine Learning 9 (1992) 57–94Google Scholar
  15. 15.
    Quinlan, J.R.: Learning logical definitions from relations. Machine Learning 5 (1990) 239–266Google Scholar
  16. 16.
    Quinlan, J. R.: C4.5: Programs for Machine Learning. (San Mateo: Morgan Kaufmann, 1993)Google Scholar
  17. 17.
    Quinlan, J.R.: Past tenses of verbs and first-order learning. In Proceedings AI'94 Seventh Australian Joint Conference on Artificial Intelligence, Armidale, Australia (World Scientific, Singapore, 1994) 13–20Google Scholar
  18. 18.
    Quinlan, J.R.: Boosting, bagging, and C4.5. In Proceedings AAAI-96 Fourteenth National Conference on Artificial Intelligence, Portland, OR (AAAI Press, Menlo Park, CA, 1996)Google Scholar
  19. 19.
    Quinlan, J.R.: Learning first-order definitions of functions. Journal of Artificial Intelligence Research (1996) to appearGoogle Scholar
  20. 20.
    Srinivasan, A., Muggleton, S.H., Sternberg, M.J.E., and King, R.D.: Theories for mutagenicity: a study in first-order and feature-based induction. Artificial Intelligence (1996) to appearGoogle Scholar
  21. 21.
    Zelle, J.M., and Mooney, R.J.: Combining foil and EBG to speed-up logic programs. In Proceedings Thirteenth International Joint Conference on Artificial Intelligence, Chambery, France (Morgan Kaufmann, San Francisco, 1993) 1106–1111Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • J. R. Quinlan
    • 1
  1. 1.University of SydneySydneyAustralia

Personalised recommendations