Advertisement

Machine Learning

, Volume 2, Issue 4, pp 285–318 | Cite as

Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm

  • Nick Littlestone
Article

Abstract

Valiant (1984) and others have studied the problem of learning various classes of Boolean functions from examples. Here we discuss incremental learning of these functions. We consider a setting in which the learner responds to each example according to a current hypothesis. Then the learner updates the hypothesis, if necessary, based on the correct classification of the example. One natural measure of the quality of learning in this setting is the number of mistakes the learner makes. For suitable classes of functions, learning algorithms are available that make a bounded number of mistakes, with the bound independent of the number of examples seen by the learner. We present one such algorithm that learns disjunctive Boolean functions, along with variants for learning other classes of Boolean functions. The basic method can be expressed as a linear-threshold algorithm. A primary advantage of this algorithm is that the number of mistakes grows only logarithmically with the number of irrelevant attributes in the examples. At the same time, the algorithm is computationally efficient in both time and space.

Learning from examples prediction incremental learning mistake bounds learning Boolean functions linear-threshold algorithms 

References

  1. Angluin, D. (1987). Queries and concept learning. Machine Learning, 2, 319–342.Google Scholar
  2. Angluin, D., & Smith, C. H. (1983). Inductive inference: Theory and methods. Computing Surveys, 15, 237–269.Google Scholar
  3. Banerji, R. B. (1985). The logic of learning: A basis for pattern recognition and for improvement of performance. Advances in Computers, 24, 177–216.Google Scholar
  4. Barzdin, J. M., & Freivald, R. V. (1972). On the prediction of general recursive functions. Soviet Mathematics Doklady, 13, 1224–1228.Google Scholar
  5. Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. (1987a). Learnability and the Vapnik-Chervonenkis dimension (Technical Report USCS-CRL-87–20). Santa Cruz: University of California, Computer Research Laboratory.Google Scholar
  6. Blumer, A., Ehrenfeucht, A., Haussler, D., & Warmuth, M. (1987b). Occam's Razor. Information Processing Letters, 24, 377–380.Google Scholar
  7. Duda, R. O., & Hart, P. E. (1973). Pattern classification and scene analysis. New York: John Wiley.Google Scholar
  8. Hampson, S. E., & Volper, D. J. (1986). Linear function neurons: Structure and training. Biological Cybernetics, 53, 203–217.Google Scholar
  9. Haussler, D. (1985). Space efficient learning algorithms. Unpublished manuscript, University of California, Department of Computer and Information Sciences, Santa Cruz.Google Scholar
  10. Haussler, D. (1986). Quantifying the inductive bias in concept learning. Proceedings of the Fifth National Conference on Artificial Intelligence (pp. 485–489). Philadelphia, PA: Morgan KaufmanGoogle Scholar
  11. Haussler, D., Littlestone, N., & Warmuth, M. (1987). Predicting 0, 1–functions on randomly drawn points. Unpublished manuscript, University of California, Department of Computer and Information Sciences, Santa Cruz.Google Scholar
  12. Kearns, M., Li, M., Pitt, L., & Valiant, L. (1987a). On the learnability of Boolean formulae. Proceedings of the Nineteenth Annual ACM Symposium on Theory of Computing (pp. 285–295). New York: The Association for Computing Machinery.Google Scholar
  13. Kearns, M., Li, M., Pitt, L., & Valiant, L. G. (1987b). Recent results on Boolean concept learning. Proceedings of the Fourth International Workshop on Ma-chine Learning (pp. 337–352). Irvine, CA: Morgan Kaufmann.Google Scholar
  14. Mitchell, T. M. (1982). Generalization as search. Artificial Intelligence, 18, 203–226.Google Scholar
  15. Muroga, S. (1971). Threshold logic and its applications. New York: John Wiley.Google Scholar
  16. Nilsson, N. J. (1965). Learning machines.New York: McGraw-Hill.Google Scholar
  17. Rumelhart, D. E., & McClelland, J. L. (1986). Parallel distributed processing: Explorations in the microstructure of cognition. Cambridge, MA: MIT Press.Google Scholar
  18. Slade, S. (1987). The programmer's guide to the Connection Machine (Technical Report). New Haven, CT: Yale University, Department of Computer Science.Google Scholar
  19. Valiant, L. G. (1984). A theory of the learnable. Communications of the ACM, 27, 1134–1142.Google Scholar
  20. Valiant, L. G. (1985). Learning disjunctions of conjunctions. Proceedings of the Ninth International Joint Conference on Artificial Intelligence (pp. 560–566). Los Angeles, CA: Morgan Kaufmann.Google Scholar
  21. Vapnik, V. N. (1982). Estimation of dependencies based on empirical data.New York: Springer-Verlag.Google Scholar
  22. Vapnik, V. N., & Chervonenkis, A. (1971). On the uniform convergence of relative frequencies of events to their probabilities. Theory of Probability and its Applications, 16, 264–280.Google Scholar

Copyright information

© Kluwer Academic Publishers 1988

Authors and Affiliations

  • Nick Littlestone
    • 1
  1. 1.Department of Computer and Information SciencesUniversity of California, Santa CruzUSA

Personalised recommendations