Advertisement

Parallel Learning of Automatic Classes of Languages

  • Sanjay Jain
  • Efim Kinber
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8776)

Abstract

We introduce and explore a model for parallel learning of families of languages computable by finite automata. In this model, an algorithmic or automatic learner takes on n different input languages and identifies at least m of them correctly. For finite parallel learning, for large enough families, we establish a full characterization of learnability in terms of characteristic samples of languages. Based on this characterization, we show that it is the difference n − m, the number of languages which are potentially not identified, which is crucial. Similar results are obtained also for parallel learning in the limit. We consider also parallel finite learnability by finite automata and obtain some partial results. A number of problems for automatic variant of parallel learning remain open.

Keywords

Characteristic Sample Bipartite Graph Inductive Inference Maximal Chain Maximum Match 
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. [ADHP05]
    Austinat, H., Diekert, V., Hertrampf, U., Petersen, H.: Regular frequency computations. Theoretical Computer Science 330, 15–20 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  2. [AGS89]
    Angluin, D., Gasarch, W., Smith, C.: Training sequences. Theoretical Computer Science 66, 255–272 (1989)MathSciNetCrossRefzbMATHGoogle Scholar
  3. [Ang80]
    Angluin, D.: Inductive inference of formal languages from positive data. Information and Control 45, 117–135 (1980)MathSciNetCrossRefzbMATHGoogle Scholar
  4. [BG00]
    Blumensath, A., Grädel, E.: Automatic structures. In: 15th Annual IEEE Symposium on Logic in Computer Science (LICS), pp. 51–62. IEEE Computer Society (2000)Google Scholar
  5. [BGK96]
    Biegel, R., Gasarch, W., Kinber, E.: Frequency computation and bounded queries. Theoretical Computer Science 163, 177–192 (1996)MathSciNetCrossRefGoogle Scholar
  6. [BKF11]
    Balodis, K., Kucevalovs, I., Freivalds, R.: Frequency prediction of functions. In: Kotásek, Z., Bouda, J., Černá, I., Sekanina, L., Vojnar, T., Antoš, D. (eds.) MEMICS 2011. LNCS, vol. 7119, pp. 76–83. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  7. [Gol67]
    Gold, E.M.: Language identification in the limit. Information and Control 10(5), 447–474 (1967)CrossRefzbMATHGoogle Scholar
  8. [JLS12]
    Jain, S., Luo, Q., Stephan, F.: Learnability of automatic classes. Journal of Computer and System Sciences 78(6), 1910–1927 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  9. [JORS99]
    Jain, S., Osherson, D., Royer, J., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)Google Scholar
  10. [Kin76]
    Kinber, E.: Frequency computations in finite automata. Kibernetika 2, 7–15 (1976) (in Russian); English translation in Cybernetics 12, 179–187Google Scholar
  11. [KN95]
    Khoussainov, B., Nerode, A.: Automatic presentations of structures. In: Leivant, D. (ed.) LCC 1994. LNCS, vol. 960, pp. 367–392. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  12. [KSVW95]
    Kinber, E., Smith, C., Velauthapillai, M., Wiehagen, R.: On learning multiple concepts in parallel. Journal of Computer and System Sciences 50, 41–52 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  13. [LZ93]
    Lange, S., Zeugmann, T.: Language learning in dependence on the space of hypotheses. In: Proceedings of the Sixth Annual Conference on Computational Learning Theory, pp. 127–136. ACM Press (1993)Google Scholar
  14. [Muk92]
    Mukouchi, Y.: Characterization of finite identification. In: Jantke, K.P. (ed.) AII 1992. LNCS, vol. 642, pp. 260–267. Springer, Heidelberg (1992)CrossRefGoogle Scholar
  15. [PS98]
    Papadimitriou, C.H.S., Steiglitz, K.: Combinatorial Optimization: Algorithms and Complexity. Dover (1998)Google Scholar
  16. [Pit89]
    Pitt, L.: Probabilistic inductive inference. Journal of the ACM 36, 383–433 (1989)MathSciNetCrossRefzbMATHGoogle Scholar
  17. [Ros60]
    Rose, G.: An extended notion of computability. Abstracts of International Congress for Logic, Methodology and Philosophy of Science, p. 14 (1960)Google Scholar
  18. [Smi82]
    Smith, C.: The power of pluralism for automatic program synthesis. Journal of the ACM 29, 1144–1165 (1982)CrossRefzbMATHGoogle Scholar
  19. [Tra64]
    Trakhtenbrot, B.: On the frequency of computation of functions. Algebra i Logika 2, 25–32 (1964)Google Scholar
  20. [WFK84]
    Wiehagen, R., Freivalds, R., Kinber, E.: On the power of probabilistic strategies in inductive inference. Theoretical Computer Science 28, 111–133 (1984)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sanjay Jain
    • 1
  • Efim Kinber
    • 2
  1. 1.School of ComputingNational University of SingaporeSingaporeSingapore
  2. 2.Department of Computer ScienceSacred Heart UniversityFairfieldU.S.A.

Personalised recommendations