Skip to main content
Springer Nature Link
Log in

An algorithm to learn read-once threshold formulas, and transformations between learning models

  • Published:
computational complexity Aims and scope Submit manuscript

Abstract

We present a membership query (i.e. black box interpolation) algorithm for exactly identifying the class of read-once formulas over the basis of Boolean threshold functions. We also present a catalogue of generic transformations that can be used to convert an algorithm in one learning model into an algorithm in a different model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • D. Angluin, Queries and concept learning.Machine Learning 2 (1987), 319–342.

    Google Scholar 

  • D. Angluin, L. Hellerstein, andM. Karpinski, Learning read-once formulas with queries.J. Assoc. Comput. Mach. 40 (1993), 185–210.

    Google Scholar 

  • N. H. Bshouty, T. R. Hancock, and L. Hellerstein, Learning boolean read-once formulas with arbitrary symmetric and constant fan-in gates.Proc. 5th Ann. Workshop Comput. Learning Theory (1992a), 1–15.

  • N. H. Bshouty, T. R. Hancock, and L. Hellerstein, Learning arithmetic read-once formulas.Proc. Twenty-fourth Ann. ACM Symp. Theor. Comput. (1992b), 350–381.

  • N. H. Bshouty, S. A. Goldman, T. R. Hancock, and S. Matar, Asking questions to minimize errors.Proc. 6th Ann. Conf. Comput. Learning Theory (1993), 41–50.

  • S. A. Goldman, M. J. Kearns, and R. E. Schapire, Exact identification of circuits using fixed points of amplification functions.Proc. 31st Ann. Symp. Found. Comput. Sci. (1990), 193–202. To appear, SIAM J. Comput.

  • R. Heiman, Newman I., and A. Wigderson, On read once threshold formulas and their randomized decision tree complexity.Proc. 5th Ann. IEEE Symp. Struct. Complex. Theory (1990), 78–87.

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Calgary, 2500 University Drive N.W., T2N 1N4, Calgary, Alberta, Canada

    Nader H. Bshouty

  2. Siemens Corporate Research, Inc., 755 College Road East, 08540, Princeton, NJ, USA

    Thomas R. Hancock

  3. Department of EECS, Northwestern University, 2145 Sheridan Road, 60208-3118, Evanston, IL, USA

    Lisa Hellerstein

  4. Dept. of Computer Science, University of Bonn, 5300, Bonn 1, Germany

    Marek Karpinski

  5. International Comp. Sci. Institute, 1947 Center St., Suite 600, 94704, Berkeley, CA, USA

    Marek Karpinski

Authors
  1. Nader H. Bshouty
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Thomas R. Hancock
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Lisa Hellerstein
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marek Karpinski
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Bshouty, N.H., Hancock, T.R., Hellerstein, L. et al. An algorithm to learn read-once threshold formulas, and transformations between learning models. Comput Complexity 4, 37–61 (1994). https://doi.org/10.1007/BF01205054

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01205054

Key words

Search

Navigation