Advertisement

Linear Space Induction in First Order Logic with Relieff

  • U. Pompe
  • I. Kononenko
Part of the International Centre for Mechanical Sciences book series (CISM, volume 363)

Abstract

Current ILP algorithms typically use variants and extensions of the greedy search. This prevents them to detect significant relationships between the training objects. Instead of myopic impurity functions, we propose the use of the heuristic based on RELIEF for guidance of ILP algorithms. At each step, in our ILP-R. system, tins heuristic is used to determine a beam of candidate literals. The beam is then used in an exhaustive search for a potentially good conjunction of literals. From the efficiency point of view we introduce interesting declarative bias which enables us to keep the growth of the training set, when introducing new variables, within linear bounds (linear with respect to the clause length). This bias prohibits cross-referencing of variables in variable dependency tree. The resulting system has been tested on various artificial problems. The advantages and deficiencies of our approach are discussed.

Keywords

Information Gain Order Logic Training Instance Heuristic Function Artificial Data 
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.
    Breiman L., Friedman.I.11. (Ashen R.A. St Stone C.J. (1984) Classification and Regression Trccs Wadsworth International Group.Google Scholar
  2. 2.
    Cestnik B. k Bratko I. (1991) On estimating probabilities in tree pruning, Proc. European Working Session on Learning, (Porto. March 1991 ), Y.Kodratoff (ed.), Springer Verlag. pp. 138–150.Google Scholar
  3. 3.
    Cestnik, B., Kononenko, I. k Bratko, I. (1987) ASSISTANT 86: A knowledge elicitation tool for sophisticated users. In: I. Bratko k N. Lavrac (eds.), Progress in Machine Learning. Wilmslow, England: Sigma Press.Google Scholar
  4. 4.
    Dzeroski S. (1991) Handling noise in inductive logic programming, M.SC. Thesis, University of Ljubljana, Faculty of electrical engineering k computer science, Ljubljana., Slovenia.Google Scholar
  5. 5.
    Kira K. k Rendell L. (1992a) A practical approach to feature selection, Proc. Intern. C’onf. on Machine Learning (Aberdeen, July 1992) D.Sleeman k P.Edwards (eds.). Morgan Kaufmann, pp.249–2.56.Google Scholar
  6. 6.
    Kira K. S.: Rendell L. (1992b) The feature selection problem: traditional methods and new algorithm. Proc. AAAI’92, San Jose, CA. July 1992.Google Scholar
  7. 7.
    Kononenko 1. (1994) Estimating attributes: Analysis and extensions of RELIEF. Proc. European C’onf. on Machine Learning (Catania, April 1991). L. De Raedt F.Bergadano (eds.). Springer Verlag. (in press)Google Scholar
  8. 8.
    Kononenko, I. k Bratko, I. (1991) Information based evaluation criterion for classifier’s performance. Machine Learning, 6: 67–80.Google Scholar
  9. 9.
    Kovacic M. (1994) Stochastic inductive logic programming. Ph.D. Thesis. University of Ljubljana, Faculty of electr. eng. k computer se., Ljubljana. Slovenia.Google Scholar
  10. 10.
    Kovacic, M.. Lavrac, N., Grobelnik, M., Zupanie. I)., Mladenic, D. (1992) Stochastic Search in Inductive Logic Programming. Proceedings of the tenth European Conference on Artificial Intelligence, Vienna, 1992.Google Scholar
  11. 11.
    Mladenie D. (1993) Combinatorial optimization in inductive concept learning. Proc. 10th Intern, C’onf. on,Machine Learning. (Amherst,.tune 1993). Morgan Kaufmann, pp. 205–211Google Scholar
  12. 12.
    Muggleton S. (ed.) (1992) Inductive Logic Programming. Academic Press.Google Scholar
  13. 13.
    U.Pompe, M.Kovacic R- I.Konouenko (1993) SFO1L: Stochastic approach to inductive logic programming. Proc. Sloivniorn (_’onf. on Electrical Login« ring and (`nnrputc r Science. Portorot, Slovenia. Sept. 1993, pp 189–192.Google Scholar
  14. 14.
    Quinlan R. (1986) Induction of decision trees,.1lachinc Lcorninq. Google Scholar
  15. 15.
    Quinlan R. (1990) Learning logical definitions from relations..)/arms n Liurnrnq. 5:239266.Google Scholar
  16. 16.
    Smyth P., Goodman R.M. k Higgins C. (1990) A hybrid Rule-based 13ayesian Classifier. Proc.European C’onf. on Artificial Intelligence, Stockholm. August. 1990, pp. 610-(i1:í.Google Scholar

Copyright information

© Springer-Verlag Wien 1995

Authors and Affiliations

  • U. Pompe
    • 1
  • I. Kononenko
    • 1
  1. 1.University of LjubljanaLjubljanaSlovenia

Personalised recommendations