Learnability of Kolmogorov-easy circuit expressions via queries

  • José L. Balcázar
  • Harry Buhrman
  • Montserrat Hermo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 904)


Circuit expressions were introduced to provide a natural link between Computational Learning and certain aspects of Structural Complexity. Upper and lower bounds on the learnability of circuit expressions are known. We study here the case in which the circuit expressions are of low (time-bounded) Kolmogorov complexity. We show that these are polynomial-time learnable from membership queries in the presence of an NP oracle. We also exactly characterize the sets that have such circuit expressions, and precisely identify the subclass whose circuit expressions can be learned from membership queries alone. The extension of the results to various Kolmogorov complexity bounds is discussed.


Polynomial Time Turing Machine Infinite Sequence Kolmogorov Complexity Boolean Circuit 
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.
    D. Angluin: “Queries and Concept Learning”. Machine Learning 2 1988, 319–342.Google Scholar
  2. 2.
    J. L. Balcázar, J. Díaz, J. Gabarró: Structural Complexity I. Springer Verlag 1988.Google Scholar
  3. 3.
    J. L. Balcázar, R. Gavaldà, M. Hermo: “On infinite sequences almost as easy as π”. Workshop on Applications of Descriptional Complexity, Rutgers Univ., july 1994. Report LSI-94-24-R, Univ. Politècnica de Catalunya.Google Scholar
  4. 4.
    J. L. Balcázar, M. Hermo, E. Mayordomo: “Characterizations of logarithmic advice complexity classes”. In: Algorithms, Software, Architecture: Information Processing 92, Elsevier 1992, vol. 1, 315–321.Google Scholar
  5. 5.
    N. Bshouty, R. Cleve, S. Kannan, C. Tamon: “Oracles and queries that are sufficient for exact learning”. In: Conference on Computational Learning Theory 1994, 130–139.Google Scholar
  6. 6.
    R. Gavaldà: “The complexity of learning with queries”. In: Structure in Commplexity Theory 1994, 324–337.Google Scholar
  7. 7.
    R. Gavaldá, O. Watanabe: “Structural analysis of polynomial time query learnability”. Mathematical Systems Theory 27 1994, 231–256.Google Scholar
  8. 8.
    M. Hermo: “Degrees and reducibilities of easy tally sets”. In: Mathematical Foundations of Computer Science 94, Springer-Verlag Lecture Notes in Computer Science 8411994, 403–412.Google Scholar
  9. 9.
    J. Köbler: “Locating P/poly optimally in the low hierarchy”. In: Symp. Theoretical Aspects of Computer Science 93, Springer-Verlag Lecture Notes in Computer Science 665 1993, 28–37.Google Scholar
  10. 10.
    M. Li, P. Vitányi: “Learning simple concepts under simple distributions”. SIAM Journal on Computing 20 1991, 911–935.Google Scholar
  11. 11.
    M. Li, P. Vitányi: An introduction to Kolmogorov complexity and its applications. Springer-Verlag 1994.Google Scholar
  12. 12.
    O. Watanabe: “A framework for polynomial time query learnability”. Mathematical Systems Theory 27 1994, 211–229.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1995

Authors and Affiliations

  • José L. Balcázar
    • 1
  • Harry Buhrman
    • 2
  • Montserrat Hermo
    • 3
  1. 1.Dept. LSI, Edif. FIBUniversitat Politécnica de CatalunyaBarcelonaSpain
  2. 2.CWIAmsterdamThe Netherlands
  3. 3.Facultad de Informatica de San SebastiánUniversidad del País VascoSpain

Personalised recommendations