Malicious Omissions and Errors in Answers to Membership Queries

  title={Malicious Omissions and Errors in Answers to Membership Queries},
  author={Dana Angluin and Martins Krikis and Robert H. Sloan and Gy{\"o}rgy Tur{\'a}n},
  journal={Machine Learning},
We consider two issues in polynomial-time exact learning of concepts using membership and equivalence queries: (1) errors or omissions in answers to membership queries, and (2) learning finite variants of concepts drawn from a learnable class. To study (1), we introduce two new kinds of membership queries: limited membership queries and malicious membership queries. Each is allowed to give incorrect responses on a maliciously chosen set of strings in the domain. Instead of answering correctly… CONTINUE READING
Highly Cited
This paper has 27 citations. REVIEW CITATIONS


Publications referenced by this paper.
Showing 1-10 of 24 references

Query learning can work poorly when a human oracle is used

Kevin J. Lang, Eric B. Baum
In International Joint Conference on Neural Networks, Beijing, • 1992
View 5 Excerpts
Highly Influenced

On the Necessity of Occam Algorithms

View 5 Excerpts
Highly Influenced

Learning Disjunction of Conjunctions

IJCAI • 1985
View 3 Excerpts
Highly Influenced

Exact learning of -DNF formulas with malicious membership queries

D. Angluin
Technical Report YALEU/DCS/TR-1020, • 1994

Krik is. Learning with malicious membership queries and exceptions

M. D. Angluin
In Proc. 7th Annu. ACM Workshop on Comput. Learning • 1994

Similar Papers

Loading similar papers…