8381 search results - page 358 / 1677 » The security of machine learning |
175
Voted
COLT
1993
Springer
15 years 11 months ago
1993
Springer
We introducea new learningproblem: learninga graph by piecemeal search, in which the learner must return every so often to its starting point (for refueling, say). We present two l...
166
click to vote
ECML
2006
Springer
15 years 8 months ago
2006
Springer
In this article, I will consider Markov Decision Processes with two criteria, each defined as the expected value of an infinite horizon cumulative return. The second criterion is e...
182
click to vote
EWRL
2008
15 years 8 months ago
2008
Two variable metric reinforcement learning methods, the natural actor-critic algorithm and the covariance matrix adaptation evolution strategy, are compared on a conceptual level a...
157
click to vote
ALT
2010
Springer
15 years 8 months ago
2010
Springer
We show that random DNF formulas, random log-depth decision trees and random deterministic finite acceptors cannot be weakly learned with a polynomial number of statistical queries...
163
Voted
ICML
2003
IEEE
16 years 7 months ago
2003
IEEE
We examine the set covering machine when it uses data-dependent half-spaces for its set of features and bound its generalization error in terms of the number of training errors an...