801 search results - page 18 / 161 » Machine Learning with Data Dependent Hypothesis Classes |
ALT
2004
Springer
14 years 5 months ago
2004
Springer
We investigate further improvement of boosting in the case that the target concept belongs to the class of r-of-k threshold Boolean functions, which answer “+1” if at least r o...
COLT
2004
Springer
14 years 10 days ago
2004
Springer
For hyper-rectangles in Rd Auer et al. [1] proved a PAC bound of O 1 (d + log 1 ) , where and are the accuracy and confidence parameters. It is still an open question whether one...
ICML
2010
IEEE
13 years 9 months ago
2010
IEEE
When equipped with kernel functions, online learning algorithms are susceptible to the "curse of kernelization" that causes unbounded growth in the model size. To addres...
ICML
2003
IEEE
14 years 9 months ago
2003
IEEE
The majority of theoretical work in machine learning is done under the assumption of exchangeability: essentially, it is assumed that the examples are generated from the same prob...
IDEAL
2005
Springer
14 years 2 months ago
2005
Springer
Prediction of peroxisomal matrix proteins generally depends on the presence of one of two distinct motifs at the end of the amino acid sequence. PTS1 peroxisomal proteins have a we...