Sciweavers

263 search results - page 24 / 53
» Splitting of Learnable Classes
Sort
View
AAAI
1996
13 years 10 months ago
Learning to Take Actions
We formalize a model for supervised learning of action strategies in dynamic stochastic domains and show that PAC-learning results on Occam algorithms hold in this model as well. W...
Roni Khardon
ECCC
2006
96views more  ECCC 2006»
13 years 8 months ago
When Does Greedy Learning of Relevant Features Succeed? --- A Fourier-based Characterization ---
Detecting the relevant attributes of an unknown target concept is an important and well studied problem in algorithmic learning. Simple greedy strategies have been proposed that s...
Jan Arpe, Rüdiger Reischuk
IANDC
2007
81views more  IANDC 2007»
13 years 8 months ago
Some natural conditions on incremental learning
The present study aims at insights into the nature of incremental learning in the context of Gold’s model of identification in the limit. With a focus on natural requirements s...
Sanjay Jain, Steffen Lange, Sandra Zilles
ALT
2005
Springer
14 years 5 months ago
Teaching Learners with Restricted Mind Changes
Within learning theory teaching has been studied in various ways. In a common variant the teacher has to teach all learners that are restricted to output only consistent hypotheses...
Frank J. Balbach, Thomas Zeugmann
APPROX
2007
Springer
153views Algorithms» more  APPROX 2007»
14 years 2 months ago
Distribution-Free Testing Lower Bounds for Basic Boolean Functions
: In the distribution-free property testing model, the distance between functions is measured with respect to an arbitrary and unknown probability distribution D over the input dom...
Dana Glasner, Rocco A. Servedio