Sciweavers

Share
JMLR
2008

An Error Bound Based on a Worst Likely Assignment

9 years 3 months ago
An Error Bound Based on a Worst Likely Assignment
This paper introduces a new PAC transductive error bound for classification. The method uses information from the training examples and inputs of working examples to develop a set of likely assignments to outputs of the working examples. A likely assignment with maximum error determines the bound. The method is very effective for small data sets.
Eric Bax, Augusto Callejas
Added 13 Dec 2010
Updated 13 Dec 2010
Type Journal
Year 2008
Where JMLR
Authors Eric Bax, Augusto Callejas
Comments (0)
books