1256 search results - page 76 / 252 » Experiences with the DEVStone benchmark |
154
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...
173
click to vote
ICML
2007
IEEE
16 years 7 months ago
2007
IEEE
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
152
click to vote
ICML
2008
IEEE
16 years 7 months ago
2008
IEEE
The central issue in representing graphstructured data instances in learning algorithms is designing features which are invariant to permuting the numbering of the vertices. We pr...
184
click to vote
ICML
2008
IEEE
16 years 7 months ago
2008
IEEE
Previous work has shown that the difficulties in learning deep generative or discriminative models can be overcome by an initial unsupervised learning step that maps inputs to use...
171
click to vote
ICML
2008
IEEE
16 years 7 months ago
2008
IEEE
For two-class classification, it is common to classify by setting a threshold on class probability estimates, where the threshold is determined by ROC curve analysis. An analog fo...