Recent Developments in Algorithmic Teaching

  • Frank J. Balbach
  • Thomas Zeugmann
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5457)

Abstract

The present paper surveys recent developments in algorithmic teaching. First, the traditional teaching dimension model is recalled.

Starting from the observation that the teaching dimension model sometimes leads to counterintuitive results, recently developed approaches are presented. Here, main emphasis is put on the following aspects derived from human teaching/learning behavior: the order in which examples are presented should matter; teaching should become harder when the memory size of the learners decreases; teaching should become easier if the learners provide feedback; and it should be possible to teach infinite concepts and/or finite and infinite concept classes.

Recent developments in the algorithmic teaching achieving (some) of these aspects are presented and compared.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Angluin, D.: Queries and concept learning. Machine Learning 2, 319–342 (1988)MathSciNetGoogle Scholar
  2. 2.
    Angluin, D.: Queries revisited. Theoret. Comput. Sci. 313, 175–194 (2004)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    Freivalds, R., Kinber, E.B., Wiehagen, R.: Inductive inference from good examples. In: Jantke, K.P. (ed.) AII 1989. LNCS (LNAI), vol. 397, pp. 1–17. Springer, Heidelberg (1989)CrossRefGoogle Scholar
  4. 4.
    Freivalds, R., Kinber, E.B., Wiehagen, R.: On the power of inductive inference from good examples. Theoret. Comput. Sci. 110, 131–144 (1993)MathSciNetCrossRefMATHGoogle Scholar
  5. 5.
    Jain, S., Lange, S., Nessel, J.: On the learnability of recursively enumerable languages from good examples. Theoret. Comput. Sci. 261, 3–29 (2001)MathSciNetCrossRefMATHGoogle Scholar
  6. 6.
    Jackson, J., Tomkins, A.: A computational model of teaching. In: Proc. 5th Annual ACM Workshop on Computational Learning Theory, pp. 319–326. ACM Press, New York (1992)CrossRefGoogle Scholar
  7. 7.
    Goldman, S.A., Mathias, H.D.: Teaching a smarter learner. J. of Comput. Syst. Sci. 52, 255–267 (1996)MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Mathias, H.D.: A model of interactive teaching. J. of Comput. Syst. Sci. 54, 487–501 (1997)MathSciNetCrossRefMATHGoogle Scholar
  9. 9.
    Angluin, D., Kriķis, M.: Teachers, learners and black boxes. In: Proceedings of the Tenth Annual Conference on Computational Learning Theory, pp. 285–297. ACM Press, New York (1997)CrossRefGoogle Scholar
  10. 10.
    Angluin, D., Kriķis, M.: Learning from different teachers. Machine Learning 51, 137–163 (2003)CrossRefMATHGoogle Scholar
  11. 11.
    Goldman, S.A., Rivest, R.L., Schapire, R.E.: Learning binary relations and total orders. SIAM J. Comput. 22, 1006–1034 (1993)MathSciNetCrossRefMATHGoogle Scholar
  12. 12.
    Goldman, S.A., Kearns, M.J.: On the complexity of teaching. J. of Comput. Syst. Sci. 50, 20–31 (1995)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Shinohara, A., Miyano, S.: Teachability in computational learning. New Generation Computing 8, 337–348 (1991)CrossRefMATHGoogle Scholar
  14. 14.
    Balbach, F.J.: Teaching classes with high teaching dimension using few examples. In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS (LNAI), vol. 3559, pp. 668–683. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  15. 15.
    Balbach, F.J.: Measuring teachability using variants of the teaching dimension. Theoret. Comput. Sci. 397, 94–113 (2008)MathSciNetCrossRefMATHGoogle Scholar
  16. 16.
    Balbach, F.J., Zeugmann, T.: Teaching learners with restricted mind changes. In: Jain, S., Simon, H.U., Tomita, E. (eds.) ALT 2005. LNCS (LNAI), vol. 3734, pp. 474–489. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  17. 17.
    Balbach, F.J., Zeugmann, T.: Teaching memoryless randomized learners without feedback. In: Balcázar, J.L., Long, P.M., Stephan, F. (eds.) ALT 2006. LNCS (LNAI), vol. 4264, pp. 93–108. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  18. 18.
    Balbach, F.J., Zeugmann, T.: Teaching randomized learners. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS (LNAI), vol. 4005, pp. 229–243. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  19. 19.
    Natarajan, B.K.: Machine Learning: A Theoretical Approach. Morgan Kaufmann, San Mateo (1991)Google Scholar
  20. 20.
    Kushilevitz, E., Linial, N., Rabinovich, Y., Saks, M.: Witness sets for families of binary vectors. Journal of Combinatorial Theory Series A 73, 376–380 (1996)MathSciNetCrossRefMATHGoogle Scholar
  21. 21.
    Anthony, M., Brightwell, G., Cohen, D., Shawe-Taylor, J.: On exact specification by examples. In: Proc. 5th Annual ACM Workshop on Computational Learning Theory, pp. 311–318. ACM Press, New York (1992)CrossRefGoogle Scholar
  22. 22.
    Anthony, M., Brightwell, G., Shawe-Taylor, J.: On specifying Boolean functions by labelled examples. Discrete Applied Mathematics 61, 1–25 (1995)MathSciNetCrossRefMATHGoogle Scholar
  23. 23.
    Lee, H., Servedio, R.A., Wan, A.: DNF are teachable in the average case. In: Lugosi, G., Simon, H.U. (eds.) COLT 2006. LNCS, vol. 4005, pp. 214–228. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  24. 24.
    Hegedűs, T.: Combinatorial results on the complexity of teaching and learning. In: Privara, I., Ružička, P., Rovan, B. (eds.) MFCS 1994. LNCS, vol. 841, pp. 393–402. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  25. 25.
    Hegedűs, T.: Generalized teaching dimensions and the query complexity of learning. In: Proc. 8th Annual Conference on Computational Learning Theory, pp. 108–117. ACM Press, New York (1995)CrossRefGoogle Scholar
  26. 26.
    Ben-David, S., Eiron, N.: Self-directed learning and its relation to the VC-dimension and to teacher-directed learning. Machine Learning 33, 87–104 (1998)CrossRefMATHGoogle Scholar
  27. 27.
    Rivest, R.L., Yin, Y.L.: Being taught can be faster than asking questions. In: Proc. 8th Annual Conference on Computational Learning Theory, pp. 144–151. ACM Press, New York (1995)CrossRefGoogle Scholar
  28. 28.
    Kuhlmann, C.: On teaching and learning intersection-closed concept classes. In: Fischer, P., Simon, H.U. (eds.) EuroCOLT 1999. LNCS, vol. 1572, pp. 168–182. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  29. 29.
    Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. John Wiley & Sons, Chichester (1994)CrossRefMATHGoogle Scholar
  30. 30.
    Bertsekas, D.P.: Dynamic Programming and Optimal Control. Athena Scientific (2001)Google Scholar
  31. 31.
    Raz, R., Safra, S.: A sub-constant error-probability low-degree test, and a sub-constant error-probability PCP characterization of NP. In: Proc. of the 29th ACM Symposium on Theory of Computing, pp. 475–484. ACM Press, New York (1997)Google Scholar
  32. 32.
    Feige, U.: A threshold of ln n for approximating set cover. J. of the ACM 45, 634–652 (1998)MathSciNetCrossRefMATHGoogle Scholar
  33. 33.
    Zilles, S., Lange, S., Holte, R., Zinkevich, M.: Teaching dimensions based on cooperative learning. In: 21st Annual Conference on Learning Theory - COLT 2008, Helsinki, Finland, pp. 135–146. Omnipress (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Frank J. Balbach
    • 1
  • Thomas Zeugmann
    • 2
  1. 1.NeuhofenGermany
  2. 2.Division of Computer ScienceHokkaido UniversitySapporoJapan

Personalised recommendations