Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

6

FOCS
2004
IEEE

favoriteEmaildiscussreport

93views Theoretical Computer Science» more FOCS 2004»

Learning with Errors in Answers to Membership Queries

13 years 8 months ago

Learning with Errors in Answers to Membership Queries

Download www.cs.technion.ac.il

We study the learning models defined in [AKST97]: Learning with equivalence and limited membership queries and learning with equivalence and malicious membership queries. We show that if a class of concepts that is closed under projection is learnable in polynomial time using equivalence and (standard) membership queries then it is learnable in polynomial time in the above models. This closes the open problems in [AKST97]. Our algorithm can also handle errors in the equivalence queries.

Laurence Bisht, Nader H. Bshouty, Lawrance Khoury

Real-time Traffic

FOCS 2004 | Limited Membership Queries | Malicious Membership Queries | Membership Queries | Theoretical Computer Science |

claim paper

Related Content

» Learning Monotone DNF from a Teacher That Almost Does Not Answer Membership Queries

» Efficient and ErrorCorrecting Data Structures for Membership and Polynomial Evaluation

» On the Power of Membership Queries in Agnostic Learning

» Hardness of approximate twolevel logic minimization and PAC learning with membership queri...

» Learning with Unreliable Boundary Queries

» Pseudorandom graphs and bit probe schemes with onesided error

» ErrorCorrecting Data Structures

» Combining Logic and Machine Learning for Answering Questions

» Approximate Query Answering by Model Averaging

Post Info
More Details (n/a)

Added	20 Aug 2010
Updated	20 Aug 2010
Type	Conference
Year	2004
Where	FOCS
Authors	Laurence Bisht, Nader H. Bshouty, Lawrance Khoury

Comments (0)