On learning branching programs and small depth circuits

Extended abstract
  • Francesco Bergadano
  • Nader H. Bshouty
  • Christino Tamon
  • Stefano Varricchio
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1208)


We study the learnability of branching programs and small-depth circuits with modular and threshold gates in both the exact and PAC learning models with and without membership queries. Our results extend earlier works [11, 18, 15] and exhibit further applications of multiplicity automata [7] in learning theory.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Angluin, D.: Queries and Concept Learning. Machine Learning, 2 (1988) 319–342.Google Scholar
  2. 2.
    Angluin, D., Kharitonov, M.: When Won't Membership Queries Help? Journal of Computer and System Sciences, 50 (1995) 336–355.Google Scholar
  3. 3.
    Barrington, D.A.: Bounded-Width Branching Programs. PhD thesis, Massachusetts Institute of Technology (1986).Google Scholar
  4. 4.
    Barrington, D.A.: Bounded-Width Polynomial-Size Branching Programs Recognize Exactly Those Languages in NC 1. Journal of Computer and System Sciences, 38 (1989) 150–164.Google Scholar
  5. 5.
    Blum, A.: Rank-r Decision Trees are a Subclass of r-Decision Lists. Information Processing Letters, 42 (1992) 183–185.Google Scholar
  6. 6.
    Bergadano, F., Catalano, D., Varricchio, S.: Learning Sat-k-DNF Formulas from Membership Queries. Proc. Ann. Symp. Theory of Computing (STOC) 1996.Google Scholar
  7. 7.
    Beimel, A., Bergadano, F., Bshouty, N.H., Kushilevitz, E., Varricchio, S.: On the Applications of Multiplicity Automata in Learning. Proc. 37th IEEE Ann. Symp. on Foundations of Computer Science, (1996) 349–358.Google Scholar
  8. 8.
    Borodin, A., Dolev, D., Fich, F., Paul, W.: Bounds for Width Two Branching Programs. SIAM Journal on Computing, 15:2 (1986) 549–560.Google Scholar
  9. 9.
    Blum, A., Furst, M., Jackson, J., Kearns, M., Mansour, Y., Rudich, S.: Weakly Learning DNF and Characterizing Statistical Query Learning using Fourier Analysis. Proc. 26th Ann. ACM Symp. Theory of Computing (1994) 253–262.Google Scholar
  10. 10.
    Barrington, D.A. Mix, Straubing, H., Thérien, D.: Non-uniform Automata over Groups. Information and Computation, 89 (1990) 109–132.Google Scholar
  11. 11.
    Bshouty, N.H., Tamon, C., Wilson, D.K.: On Learning Width Two Branching Programs. Proc. 9th Ann. ACM Conf. Computational Learning Theory (1996).Google Scholar
  12. 12.
    Bergadano, F., Varricchio, S.: Learning Behaviors of Automata from Multiplicity and Equivalence Queries. Proc. 2nd Italian Conference on Algorithms and Complexity (CIAC 94), Lecture Notes in Computer Science No. 778, M. Bonuccelli, P. Crescenzi, R. Petreschi (eds.), Springer-Verlag, (1994). To appear in SIAM Journal on Computing.Google Scholar
  13. 13.
    Ergün, F., Ravi Kumar, S., Rubinfeld, R.: On Learning Bounded-Width Branching Programs. Proc. 8th Ann. ACM Conf. Computational Learning Theory (1995) 361–368.Google Scholar
  14. 14.
    Freund, Y. Boosting a Weak Learning Algorithm by Majority. Proc. 3rd Ann. Workshop on Computational Learning Theory (1990) 202–216.Google Scholar
  15. 15.
    Gavaldà, R., Guijarro, D.: Learning Ordered Binary Decision Diagrams. 6th International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence No. 997, Jantke, Shinohara, Zeugmann (eds.), Springer-Verlag, (1995).Google Scholar
  16. 16.
    Gergov, J., Meinel, C.: MOD-2-OBDD's — A Generalization of OBDD's and EXOR-Sum-Of-Products. IFIP WG 10.5 Workshop on the Applications of Reed-Muller Expansion in Circuit Design, Hamburg, (1993).Google Scholar
  17. 17.
    Helmbold, D., Sloan, R., Warmuth, M.: Learning Nested Differences of Intersection-Closed Concept Classes. Machine Learning, 5 (1990) 165–196.Google Scholar
  18. 18.
    Jackson, J.: DNF is Efficiently Learnable under the Uniform distribution with Membership Queries. Proc. 35th Ann. Symp. on Foundations of Computer Science (1994) 42–53.Google Scholar
  19. 19.
    Kushilevitz, E., Mansour, Y.: Learning Decision Trees using the Fourier Spectrum. SIAM Journal on Computing, 22:6 (1993) 1331–1348.Google Scholar
  20. 20.
    Krause, M., Pudlák, P.: On the Computational Power of Depth 2 Circuits with Threshold and Modulo gates. Proc. 26th Ann. ACM Symp. on the Theory of Computing (1994) 48–57.Google Scholar
  21. 21.
    Littlestone, N.: Learning Quickly When Irrelevant Attributes Abound: A New Linear-Threshold Algorithm. Machine Learning, 2 (1988) 285–318.Google Scholar
  22. 22.
    Mansour, Y.: Learning Boolean Functions via the Fourier Transform. Tutorial Notes for the Workshop on Computational Learning Theory (1994).Google Scholar
  23. 23.
    Raghavan, V., Wilkins, D.: Learning Branching Programs with Queries. Proc. 6th Ann. Workshop on Computational Learning Theory, (1993) 27–36.Google Scholar
  24. 24.
    Valiant, L.: A Theory of the Learnable. Communications of the ACM, 27:11 (1984) 1134–1142.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Francesco Bergadano
    • 1
  • Nader H. Bshouty
    • 2
  • Christino Tamon
    • 3
  • Stefano Varricchio
    • 4
  1. 1.Dipartimento di InformaticaUniversitá di TorinoItaly
  2. 2.Dept. Computer ScienceUniversity of CalgaryCanada
  3. 3.Dept. Mathematics and Computer ScienceClarkson UniversityUSA
  4. 4.Dipartimento di InformaticaUniversitá di L'AquilaItaly

Personalised recommendations