Skip to main content

Learning with Queries inside the Class of Unate k-quasi-Horn Formulas

Abstract

Boolean formulas have been widely studied in the field of learning theory. We focus on the model of learning with queries, and study restrictions of the class of unate k-quasi-Horn formulas. This class is known to be learnable with equivalence and membership queries. We prove that any subclass of unate k-quasi-Horn formulas can be properly learned with both types of queries, provided the set of consequents that appear in formulas can be computed efficiently in advance.

This is a preview of subscription content, access via your institution.

References

  1. Aizenstein, H. and Pitt, L., “Exact learning of read-twice DNF Formulas,” Proceedings of the 32nd Annual Symposium on Foundations of Computer Science, pp. 170–179, 1991.

  2. Angluin, D., “Learning k-term DNF using queries and counterexamples,” TR-YALEU/DCS/RR-559, Yale University, August 1987.

  3. Angluin, D., “Queries and concept learning,” Machine Learning 2, 4, pp. 319–342, 1988.

  4. Angluin, D., “Negative results for equivalence queries,” Machine Learning 5, pp. 121–150, 1990.

  5. Angluin, D., Frazier, M. and Pitt, L. “Learning conjunctions of Horn clauses,” Machine Learning, 9, pp. 147–164, 1992.

  6. Angluin, D., Hellerstein, L. and Karpinski, M., “Learning read-Once formulas with queries,” Journal of the Association for Computing Machinery, 9, 1, pp. 185–210, 1993.

  7. Goldsmith, J. and Sloan, R. H., “New Horn revision algorithms,” Journal of Machine Learning Research, 6, pp. 1919–1938, 2005.

  8. Lavín Puente, V., “On learning multivalued dependencies with queries,” Theoretical Computer Science, 412, pp. 2331–2339, 2011.

  9. Lavín Puente, V., “Learning a subclass of k-quasi-Horn formulas with membership queries,” Information Processing Letters, 111, pp. 550–555, 2011.

  10. Pillaipakkamnatt, K. and Raghavan, V., “Read twice DNF formulas are properly learnable,” Information and Computation, 122, pp. 236–267, 1995.

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Víctor Lavín Puente.

Additional information

This work has been partially supported by the Spanish projects TIN2008-06622-C03-01, S2009TIC-1465 and UCM-BSCH-GR58/08-910502.

About this article

Verify currency and authenticity via CrossMark

Cite this article

Lavín Puente, V. Learning with Queries inside the Class of Unate k-quasi-Horn Formulas. New Gener. Comput. 33, 137–147 (2015). https://doi.org/10.1007/s00354-015-0204-8

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00354-015-0204-8

Keywords

  • Query Learning
  • Proper Learning
  • CNF Formulas
  • Unate Formulas