Sciweavers

263 search results - page 9 / 53
» Splitting of Learnable Classes
Sort
View
FOCS
2004
IEEE
13 years 11 months ago
Learning with Errors in Answers to Membership Queries
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 ...
Laurence Bisht, Nader H. Bshouty, Lawrance Khoury
ECCC
2002
74views more  ECCC 2002»
13 years 7 months ago
On the proper learning of axis parallel concepts
We study the proper learnability of axis-parallel concept classes in the PAC-learning and exactlearning models. These classes include union of boxes, DNF, decision trees and multi...
Nader H. Bshouty, Lynn Burroughs
STOC
2000
ACM
174views Algorithms» more  STOC 2000»
13 years 11 months ago
Noise-tolerant learning, the parity problem, and the statistical query model
We describe a slightly subexponential time algorithm for learning parity functions in the presence of random classification noise, a problem closely related to several cryptograph...
Avrim Blum, Adam Kalai, Hal Wasserman
ICML
2000
IEEE
14 years 8 months ago
Exploiting the Cost (In)sensitivity of Decision Tree Splitting Criteria
This paper investigates how the splitting criteria and pruning methods of decision tree learning algorithms are influenced by misclassification costs or changes to the class distr...
Chris Drummond, Robert C. Holte
ICML
2010
IEEE
13 years 8 months ago
Generalizing Apprenticeship Learning across Hypothesis Classes
This paper develops a generalized apprenticeship learning protocol for reinforcementlearning agents with access to a teacher who provides policy traces (transition and reward obse...
Thomas J. Walsh, Kaushik Subramanian, Michael L. L...