Prior Knowledge in Learning Finite Parameter Spaces

  • Dorota Głowacka
  • Louis Dorard
  • Alan Medlar
  • John Shawe-Taylor
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5591)

Abstract

We propose a new framework for computational analysis of language acquisition in a finite parameter space, for instance, in the “principles and parameters” approach to language. The prior knowledge multi-armed bandit algorithm abstracts the idea of a casino of slot machines in which a player has to play machines in order to find out how good they are, but where he has some prior knowledge that some machines are likely to have similar rates of reward. Each grammar is represented as an arm of a bandit machine with the mean-reward function drawn from a Gaussian Process specified by a covariance function between grammars. We test our algorithm on a ten-parameter space and show that the number of iterations required to identify the target grammar is much smaller than the number of all the possible grammars that the learner would have to explore if he was searching exhaustively the entire parameter space.

Keywords

Covariance Alan Venezuela 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Machine Learning (47), 235–256 (2002)Google Scholar
  2. 2.
    Bubeck, S., Munos, R., Stoltz, G., Szepesvari, S.: Online optimization in x-armed bandits. In: Proceedings of NIPS (2008)Google Scholar
  3. 3.
    Chomsky, N.: Aspects of the Theory of Syntax. MIT Press, Cambridge (1965)Google Scholar
  4. 4.
    Chomsky, N.: Lectures on government and binding. Foris, Dordrecht (1981)Google Scholar
  5. 5.
    Davis, S.M.: Syllable onsets as a factor in stress rules. Phonology (5), 1–19 (1988)Google Scholar
  6. 6.
    Dresher, B.E., Kaye, J.D.: A computational learning model for metrical phonology. Cognition 34, 137–195 (1990)CrossRefGoogle Scholar
  7. 7.
    Gibson, T., Wexler, K.: Triggers. Linguistic Inguiry 25(4), 407–474 (1994)Google Scholar
  8. 8.
    Gold, E.M.: Language identification in the limit. Information and Control 10(4), 407–454 (1967)MathSciNetMATHGoogle Scholar
  9. 9.
    Hale, K., Keyser, J.: On argument structure and the lexical expression of syntactic relations. In: Hale, K., Keyser, J. (eds.) The view from building 20, pp. 53–110. MIT Press, Cambridge (1993)Google Scholar
  10. 10.
    Hayes, B.: Metrical Stress Theory: Principles and Case Studies. The University of Chicago Press, Chicago (1995)Google Scholar
  11. 11.
    Kleinberg, R., Slivkins, A., Upfal, E.: Multi-Armed Bandits in Metric Spaces. In: Proceedings of STOC (2008)Google Scholar
  12. 12.
    Niyogi, P., Berwick, R.C.: A language learning model for finite parameter spaces. Cognition 61, 161–193 (1996)CrossRefGoogle Scholar
  13. 13.
    Niyogi, P.: The Computational Nature of Language Learning and Evolution. MIT Press, Cambridge (2006)Google Scholar
  14. 14.
    Rasmussen, C.E., Williams, C.K.I.: Gaussian Processes for Machine Learning. MIT Press, Cambridge (2006)MATHGoogle Scholar
  15. 15.
    Wang, Y., Audibert, J., Munos, R.: Algorithms for infinitely many-armed bandits. In: Proceedings of NIPS (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Dorota Głowacka
    • 1
  • Louis Dorard
    • 1
  • Alan Medlar
    • 1
  • John Shawe-Taylor
    • 1
  1. 1.Department of Computer ScienceUniversity College LondonUK

Personalised recommendations