2 search results - page 1 / 1 » Generative versus discriminative training of RBMs for classi... |
NIPS
2008
13 years 6 months ago
2008
Neuroimaging datasets often have a very large number of voxels and a very small number of training cases, which means that overfitting of models for this data can become a very se...
CVPR
2005
IEEE
14 years 6 months ago
2005
IEEE
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the di...