24680 search results - page 248 / 4936 » Learning to |
141
click to vote
ICML
2009
IEEE
16 years 7 months ago
2009
IEEE
We present a general PAC-Bayes theorem from which all known PAC-Bayes risk bounds are obtained as particular cases. We also propose different learning algorithms for finding linea...
185
click to vote
ICML
2009
IEEE
16 years 7 months ago
2009
IEEE
The promise of unsupervised learning methods lies in their potential to use vast amounts of unlabeled data to learn complex, highly nonlinear models with millions of free paramete...