Active Learning of Recursive Functions by Ultrametric Algorithms

  • Rūsiņš Freivalds
  • Thomas Zeugmann
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8327)


We study active learning of classes of recursive functions by asking value queries about the target function f, where f is from the target class. That is, the query is a natural number x, and the answer to the query is f(x). The complexity measure in this paper is the worst-case number of queries asked. We prove that for some classes of recursive functions ultrametric active learning algorithms can achieve the learning goal by asking significantly fewer queries than deterministic, probabilistic, and even nondeterministic active learning algorithms. This is the first ever example of a problem where ultrametric algorithms have advantages over nondeterministic algorithms.


Recursive Function Inductive Inference Ultrametric Analysis Computation Path Probabilistic Algorithm 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ambainis, A., Apsītis, K., Freivalds, R., Smith, C.H.: Hierarchies of probabilistic and team FIN-learning. Theoret. Comput. Sci. 261(1), 91–117 (2001)CrossRefzbMATHMathSciNetGoogle Scholar
  2. 2.
    Ambainis, A., Smotrovs, J.: Enumerable classes of total recursive functions: Complexity of inductive inference. In: Arikawa, S., Jantke, K.P. (eds.) AII and ALT 1994. LNCS (LNAI), vol. 872, pp. 10–25. Springer, Heidelberg (1994)Google Scholar
  3. 3.
    Angluin, D.: Queries and concept learning. Machine Learning 2(4), 319–342 (1988)Google Scholar
  4. 4.
    Balodis, K., Beriņa, A., Cīpola, K., Dimitrijevs, M., Iraids, J., Jēriņs, K., Kacs, V., Kalējs, J., Krilšauks, R., Lukstiņš, K., Raumanis, R., Scegulnaja, I., Somova, N., Vanaga, A., Freivalds, R.: On the state complexity of ultrametric finite automata (unpublished manuscript 2013)Google Scholar
  5. 5.
    Denis, F., Lemay, A., Terlutte, A.: Learning regular languages using non deterministic finite automata. In: Oliveira, A.L. (ed.) ICGI 2000. LNCS (LNAI), vol. 1891, pp. 39–50. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  6. 6.
    Dragovich, B., Dragovich, A.Y.: A p-adic model of DNA sequence and genetic code. p-Adic Numbers, Ultrametric Analysis, and Applications 1(1), 34–41 (2009)CrossRefzbMATHMathSciNetGoogle Scholar
  7. 7.
    Freivalds, R.: Ultrametric automata and Turing machines. In: Voronkov, A. (ed.) Turing-100. EPiC Series, vol. 10, pp. 98–112. EasyChair (2012)Google Scholar
  8. 8.
    Freivalds, R., Bārzdiņš, J., Podnieks, K.: Inductive inference of recursive functions: Complexity bounds. In: Barzdins, J., Bjorner, D. (eds.) Baltic Computer Science. LNCS, vol. 502, pp. 111–155. Springer, Heidelberg (1991)CrossRefGoogle Scholar
  9. 9.
    Freivalds, R., Zeugmann, T.: Active learning of classes of recursive functions by ultrametric algorithms. Tech. Rep. TCS-TR-A-13-68, Division of Computer Science, Hokkaido University (2013)Google Scholar
  10. 10.
    Freivalds, R., Kinber, E., Smith, C.H.: On the impact of forgetting on learning machines. J. ACM 42(6), 1146–1168 (1995)CrossRefzbMATHMathSciNetGoogle Scholar
  11. 11.
    García, P., de Parga, M.V., Álvarez, G.I., Ruiz, J.: Learning regular languages using nondeterministic finite automata. In: Ibarra, O.H., Ravikumar, B. (eds.) CIAA 2008. LNCS, vol. 5148, pp. 92–101. Springer, Heidelberg (2008)CrossRefGoogle Scholar
  12. 12.
    Gold, E.M.: Language identification in the limit. Inform. Control 10(5), 447–474 (1967)CrossRefzbMATHGoogle Scholar
  13. 13.
    Gouvea, F.Q.: p-adic Numbers: An Introduction (Universitext), 2nd edn. Springer, Berlin (1983)Google Scholar
  14. 14.
    Greitāne, I.: Probabilistic inductive inference of indices in enumerable classes of total recursive functions. In: Jantke, K.P. (ed.) AII 1989. LNCS (LNAI), vol. 397, pp. 277–287. Springer, Heidelberg (1989)CrossRefGoogle Scholar
  15. 15.
    Jēriņš, K., Balodis, K., Krišlauks, R., Cīpola, K., Freivalds, R.: Ultrametric query algorithms (unpublished manuscript 2012)Google Scholar
  16. 16.
    Khrennikov, A.: Non-Archimedean Analysis: Quantum Paradoxes, Dynamical Systems and Biological Models. Kluwer Academic Publishers (1997)Google Scholar
  17. 17.
    Kinber, E., Zeugmann, T.: One-sided error probabilistic inductive inference and reliable frequency identification. Inform. Comput. 92(2), 253–284 (1991)CrossRefzbMATHMathSciNetGoogle Scholar
  18. 18.
    Koblitz, N.: p-adic Numbers, p-adic Analysis, and Zeta-Functions, 2nd edn. Springer, Berlin (1984)CrossRefGoogle Scholar
  19. 19.
    Kozyrev, S.V.: Ultrametric analysis and interbasin kinetics. In: American Institute of Physics Conference Proceedings of the 2nd International Conference on p-Adic Mathematical Physics, Belgrade, Serbia and Montenegro, September 15-21, vol. 826, pp. 121–128 (2006)Google Scholar
  20. 20.
    Meserve, B.E.: Fundamental Concepts of Geometry. Dover Publications, New York (1983)Google Scholar
  21. 21.
    Meyer, L.: Probabilistic language learning under monotonicity constraint. Theoret. Comput. Sci. 185(1), 81–128 (1997)CrossRefzbMATHMathSciNetGoogle Scholar
  22. 22.
    Meyer, L.: Aspects of complexity of probabilistic learning under monotonicity constraints. Theoret. Comput. Sci. 268(2), 275–322 (2001)CrossRefzbMATHMathSciNetGoogle Scholar
  23. 23.
    Nielsen, M.A., Chuang, I.L.: Quantum Computation and Quantum Information. Cambridge University Press (2000)Google Scholar
  24. 24.
    Ostrowski, A.: Über einige Lösungen der Funktionalgleichung ϕ(xϕ(y) = ϕ(xy). Acta Mathematica 41(1), 271–284 (1916)CrossRefMathSciNetGoogle Scholar
  25. 25.
    Pitt, L.: Probabilistic inductive inference. J. ACM 36(2), 383–433 (1989)CrossRefzbMATHMathSciNetGoogle Scholar
  26. 26.
    Pitt, L., Smith, C.H.: Probability and plurality for aggregations of learning machines. Inform. Comput. 77(1), 77–92 (1988)CrossRefzbMATHMathSciNetGoogle Scholar
  27. 27.
    Rogers, Jr., H.: Theory of Recursive Functions and Effective Computability. McGraw-Hill (1967); reprinted. MIT Press (1987) Google Scholar
  28. 28.
    Vladimirov, V.S., Volovich, I.V., Zelenov, E.I.: P-Adic Analysis and Mathematical Physics. World Scientific, Singapore (1994)Google Scholar
  29. 29.
    Wu, Y.-C., Lee, Y.-S., Yang, J.-C., Yen, S.-J.: An integrated deterministic and nondeterministic inference algorithm for sequential labeling. In: Cheng, P.-J., Kan, M.-Y., Lam, W., Nakov, P. (eds.) AIRS 2010. LNCS, vol. 6458, pp. 221–230. Springer, Heidelberg (2010)CrossRefGoogle Scholar
  30. 30.
    Zeugmann, T., Zilles, S.: Learning recursive functions: A survey. Theoret. Comput. Sci. 397(1-3), 4–56 (2008)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Rūsiņš Freivalds
    • 1
  • Thomas Zeugmann
    • 2
  1. 1.Institute of Mathematics and Computer ScienceUniversity of LatviaRigaLatvia
  2. 2.Division of Computer ScienceHokkaido UniversitySapporoJapan

Personalised recommendations