Sciweavers

3050 search results - page 145 / 610
» On-line Algorithms in Machine Learning
Sort
View
ML
2010
ACM
163views Machine Learning» more  ML 2010»
14 years 10 months ago
Classification with guaranteed probability of error
We introduce a general-purpose learning machine that we call the Guaranteed Error Machine, or GEM, and two learning algorithms, a real GEM algorithm and an ideal GEM algorithm. Th...
Marco C. Campi
COLT
2003
Springer
15 years 9 months ago
Learning Random Log-Depth Decision Trees under the Uniform Distribution
We consider three natural models of random logarithmic depth decision trees over Boolean variables. We give an efficient algorithm that for each of these models learns all but an ...
Jeffrey C. Jackson, Rocco A. Servedio
COLT
1991
Springer
15 years 7 months ago
Improved Learning of AC0 Functions
Two extensions of the Linial, Mansour, Nisan AC0 learning algorithm are presented. The LMN method works when input examples are drawn uniformly. The new algorithmsimprove on their...
Merrick L. Furst, Jeffrey C. Jackson, Sean W. Smit...
ML
2008
ACM
15 years 3 months ago
Large margin vs. large volume in transductive learning
Abstract. We consider a large volume principle for transductive learning that prioritizes the transductive equivalence classes according to the volume they occupy in hypothesis spa...
Ran El-Yaniv, Dmitry Pechyony, Vladimir Vapnik
JMLR
2010
159views more  JMLR 2010»
14 years 10 months ago
Semi-Supervised Learning with Max-Margin Graph Cuts
This paper proposes a novel algorithm for semisupervised learning. This algorithm learns graph cuts that maximize the margin with respect to the labels induced by the harmonic fun...
Branislav Kveton, Michal Valko, Ali Rahimi, Ling H...