Advertisement

On the Teaching Complexity of Linear Sets

  • Ziyuan Gao
  • Hans Ulrich Simon
  • Sandra Zilles
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9355)

Abstract

Linear sets are the building blocks of semilinear sets, which are in turn closely connected to automata theory and formal languages. Prior work has investigated the learnability of linear sets and semilinear sets in three models – Valiant’s PAC-learning model, Gold’s learning in the limit model, and Angluin’s query learning model. This paper considers a teacher-learner model of learning families of linear sets, whereby the learner is assumed to know all the smallest sets \(T_1,T_2,\ldots \) of labelled examples that are consistent with exactly one language in the class \(\mathcal {L}\) to be learnt, and is always presented with a sample S of labelled examples such that S is contained in at least one of \(T_1,T_2,\ldots \); the learner then interprets S according to some fixed protocol. In particular, we will apply a generalisation of a recently introduced model – the recursive teaching model of teaching and learning – to several infinite classes of linear sets, and show that the maximum sample complexity of teaching these classes can be drastically reduced if each of them is taught according to a carefully chosen sequence. A major focus of the paper will be on determining two relevant teaching parameters, the teaching dimension and recursive teaching dimension, for various families of linear sets.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Abe, N.: Polynomial learnability of semilinear sets. In: Computational Learning Theory (COLT), pp. 25–40 (1989)Google Scholar
  2. 2.
    Angluin, D.: Inductive inference of formal languages from positive data. Information and Control 45(2), 117–135 (1980)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Doty, D., Patitz, M.J., Summers, S.M.: Limitations of self-assembly at temperature 1. Theoretical Computer Science 412(1–2), 145–158 (2011)MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Gao, Z., Mazadi, Z., Meloche, R., Simon, H.U., Zilles, S.: Distinguishing pattern languages with membership examples, Manuscript (2014)Google Scholar
  5. 5.
    Goldman, S.A., Kearns, M.J.: On the complexity of teaching. Journal of Computer and System Sciences 50(1), 20–31 (1995)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Ibarra, O.H.: Reversal-bounded multicounter machines and their decision problems. Journal of the Association for Computing Machinery 25(1), 116–133 (1978)MathSciNetCrossRefMATHGoogle Scholar
  7. 7.
    Ibarra, O.H., Dang, Z., Egecioglu, O.: Catalytic P systems, semilinear sets, and vector addition systems. Theoretical Computer Science 312(2–3), 379–399 (2004)MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Mazadi, Z., Gao, Z., Zilles, S.: Distinguishing pattern languages with membership examples. In: Dediu, A.-H., Martín-Vide, C., Sierra-Rodríguez, J.-L., Truthe, B. (eds.) LATA 2014. LNCS, vol. 8370, pp. 528–540. Springer, Heidelberg (2014) CrossRefGoogle Scholar
  9. 9.
    Parikh, R.J.: On context-free languages. Journal of the Association for Computing Machinery 13(4), 570–581 (1966)MathSciNetCrossRefMATHGoogle Scholar
  10. 10.
    Rosales, J.C., García-Sánchez, P.A.: Numerical semigroups. Springer, New York (2009) CrossRefMATHGoogle Scholar
  11. 11.
    Shinohara, A., Miyano, S.: Teachability in computational learning. New Generation Computing 8(4), 337–347 (1991)CrossRefMATHGoogle Scholar
  12. 12.
    Takada, Y.: Learning semilinear sets from examples and via queries. Theoretical Computer Science 104(2), 207–233 (1992)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Zilles, S., Lange, S., Holte, R., Zinkevich, M.: Models of cooperative teaching and learning. Journal of Machine Learning Research 12, 349–384 (2011)MathSciNetMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Computer ScienceUniversity of ReginaReginaCanada
  2. 2.Horst Görtz Institute for IT Security and Faculty of MathematicsRuhr-Universität BochumBochumGermany

Personalised recommendations