Advertisement

Generalizing over Several Learning Settings

  • Anna Kasprzik
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6339)

Abstract

We recapitulate inference from membership and equivalence queries, positive and negative samples. Regular languages cannot be learned from one of those information sources only [1,2,3]. Combinations of two sources allowing regular (polynomial) inference are MQs and EQs [4], MQs and positive data [5,6], positive and negative data [7,8]. We sketch a meta-algorithm fully presented in [9] that generalizes over as many combinations of those sources as possible. This includes a survey of pairings for which there are no well-studied algorithms.

Keywords

Learn Setting Regular Language Learn Automaton Tree Language Membership Query 
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.
    Gold, E.: Language identification in the limit. Inf. & Contr. 10(5), 447–474 (1967)zbMATHCrossRefGoogle Scholar
  2. 2.
    Angluin, D.: Queries and concept learning. Mach. L. 2, 319–342 (1988)Google Scholar
  3. 3.
    Angluin, D.: Negative results for equivalence queries. Mach. L. 5, 121–150 (1990)Google Scholar
  4. 4.
    Angluin, D.: Learning regular sets from queries and counterexamples. Information and Computation 75(2), 87–106 (1987)zbMATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Angluin, D.: A note on the number of queries needed to identify regular languages. Inf. & Contr. 51, 76–87 (1981)zbMATHCrossRefMathSciNetGoogle Scholar
  6. 6.
    Besombes, J., Marion, J.Y.: Learning tree languages from positive examples and membership queries. In: Gavaldá, R., Jantke, K.P., Takimoto, E. (eds.) ALT 2003. LNCS (LNAI), vol. 2842, pp. 440–453. Springer, Heidelberg (2003)Google Scholar
  7. 7.
    Oncina, J., Garcia, P.: Identifying regular languages in polynomial time. Machine Perception and Artificial Intelligence, vol. 5, pp. 99–108. World Scientific, Singapore (2002)Google Scholar
  8. 8.
    de la Higuera, C.: Grammatical Inference: Learning Automata and Grammars. Cambridge University Press, Cambridge (2010)zbMATHGoogle Scholar
  9. 9.
    Kasprzik, A.: Generalizing over several learning settings. Technical report, University of Trier (2009)Google Scholar
  10. 10.
    Drewes, F., Högberg, J.: Learning a regular tree language from a teacher. In: Ésik, Z., Fülöp, Z. (eds.) DLT 2003. LNCS, vol. 2710, pp. 279–291. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  11. 11.
    Oncina, J., Garcia, P.: Inference of recognizable tree sets. Technical report, DSIC II/47/93, Universidad de Valencia (1993)Google Scholar
  12. 12.
    Kasprzik, A.: A learning algorithm for multi-dimensional trees, or: Learning beyond context-freeness. In: Clark, A., Coste, F., Miclet, L. (eds.) ICGI 2008. LNCS (LNAI), vol. 5278, pp. 111–124. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  13. 13.
    Tîrnăucă, C.: A note on the relationship between different types of correction queries. In: Clark, A., Coste, F., Miclet, L. (eds.) ICGI 2008. LNCS (LNAI), vol. 5278, pp. 213–223. Springer, Heidelberg (2008)Google Scholar
  14. 14.
    Pitt, L.: Inductive inference, DFAs, and computational complexity. In: Jantke, K.P. (ed.) AII 1989. LNCS, vol. 397. Springer, Heidelberg (1989)Google Scholar
  15. 15.
    Fernau, H.: Identification of function distinguishable languages. Theoretical Computer Science 290(3), 1679–1711 (2003)zbMATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Fernau, H.: Even linear simple matrix languages: Formal language properties and grammatical inference. Theoretical Computer Science 289(1), 425–456 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  17. 17.
    Berman, P., Roos, R.: Learning one-counter languages in polynomial time. In: SFCS, pp. 61–67 (1987)Google Scholar
  18. 18.
    Yoshinaka, R.: Learning mildly context-sensitive languages with multidimensional substitutability from positive data. In: Gavaldà, R., Lugosi, G., Zeugmann, T., Zilles, S. (eds.) ALT 2009. LNCS, vol. 5809, pp. 278–292. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  19. 19.
    Clark, A.: Three learnable models for the description of language. In: Dediu, A.-H., Fernau, H., Martín-Vide, C. (eds.) LATA 2010. LNCS, vol. 6031, pp. 16–31. Springer, Heidelberg (2010)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Anna Kasprzik
    • 1
  1. 1.University of Trier 

Personalised recommendations