40 search results - page 2 / 8 » A New PAC Bound for Intersection-Closed Concept Classes |
COLT
1993
Springer
13 years 9 months ago
1993
Springer
The Vapnik-Chervonenkis (V-C) dimension is an important combinatorial tool in the analysis of learning problems in the PAC framework. For polynomial learnability, we seek upper bou...
IJCAI
1993
13 years 6 months ago
1993
This paper introduces a new concept, a decision tree (or list) over tree patterns, which is a natural extension of a decision tree (or decision list), for dealing with tree struct...
COLT
2005
Springer
13 years 10 months ago
2005
Springer
Abstract. There has been growing interest in practice in using unlabeled data together with labeled data in machine learning, and a number of different approaches have been develo...
FOCS
2009
IEEE
13 years 11 months ago
2009
IEEE
Statistical query (SQ) learning model of Kearns is a natural restriction of the PAC learning model in which a learning algorithm is allowed to obtain estimates of statistical prop...
STOC
1994
ACM
13 years 9 months ago
1994
ACM
We present new results on the well-studied problem of learning DNF expressions. We prove that an algorithm due to Kushilevitz and Mansour [13] can be used to weakly learn DNF form...