Abstract
In this note, we prove with derandomization techniques that a subclass of DNF formulas with nonconstant number of terms is polynomial time learnable using equivalence and incomplete membership queries. Although many concept classes are known to be polynomial time learnable using equivalence and membership queries, so far only two concept classes are known to be polynomial time learnable (see, [AS] and [GM]) when incomplete membership queries are used.
The author was supported by by NSF grant CCR91-9103055 and by a Boston University Presidential Graduate Fellowship
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
D. Angluin, D. Slonim, “Learning monotone DNF formula with an incomplete membership oracle”, Proc of the 4th Annual Workshop on Computational Learning Theory, pages 139–146. Morgan Kaufmann Publishers, Inc., San Mateo, CA, 1991.
A. Blum, S. Rudich, “Fast learning of k-term DNF formulas with queries”, Proc of the 24th Annual ACM Symposium on Theory of Computing, May 1992, pages 382–389.
A. Blum, P. Chalasani, J. Jackson, “On learning embedded symmetric concepts” Proc of the Sixth Annual ACM Conference on Computational Learning Theory, pages 337–346.
S. Goldman, H. Mathias, “Learning k-term DNF formulas with an incomplete membership oracle”, Proc of the 5th Annual Workshop on Computational Learning Theory, pages 72–77, Morgan Kaufmann Publishers, Inc., San Mateo, CA, 1992.
J. Naor, M. Naor, “Small-bias probability space: efficient constructions and applications”, Proc of the 22th Annual ACM Symposium on Theory of Computing, May 1992, pages 213–223.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1994 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Chen, Z. (1994). A note on learning DNF formulas using equivalence and incomplete membership queries. In: Arikawa, S., Jantke, K.P. (eds) Algorithmic Learning Theory. AII ALT 1994 1994. Lecture Notes in Computer Science, vol 872. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-58520-6_70
Download citation
DOI: https://doi.org/10.1007/3-540-58520-6_70
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-58520-6
Online ISBN: 978-3-540-49030-2
eBook Packages: Springer Book Archive