129 search results - page 25 / 26 » icml 2008 |
164
Voted
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
We consider the problem of optimizing multilabel MRFs, which is in general NP-hard and ubiquitous in low-level computer vision. One approach for its solution is to formulate it as...
148
Voted
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
In dimensionality reduction approaches, the data are typically embedded in a Euclidean latent space. However for some data sets this is inappropriate. For example, in human motion...
150
Voted
ICML
2009
IEEE
15 years 10 months ago
2009
IEEE
The most commonly used learning algorithm for restricted Boltzmann machines is contrastive divergence which starts a Markov chain at a data point and runs the chain for only a few...
119
Voted
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
Inspired by co-training, many multi-view semi-supervised kernel methods implement the following idea: find a function in each of multiple Reproducing Kernel Hilbert Spaces (RKHSs)...
121
Voted
ICML
2008
IEEE
16 years 4 months ago
2008
IEEE
We consider the task of learning to accurately follow a trajectory in a vehicle such as a car or helicopter. A number of dynamic programming algorithms such as Differential Dynami...