566 search results - page 23 / 114 » Approximation Spaces in Machine Learning and Pattern Recogni... |
127
click to vote
NECO
2010
15 years 1 months ago
2010
To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicat...
110
click to vote
ICML
2004
IEEE
16 years 3 months ago
2004
IEEE
The multiple-instance learning (MIL) model has been very successful in application areas such as drug discovery and content-based imageretrieval. Recently, a generalization of thi...
114
Voted
ICPR
2008
IEEE
15 years 9 months ago
2008
IEEE
Graph based semi-supervised learning methods (SSL) implicitly assume that the intrinsic geometry of the data points can be fully specified by an Euclidean distance based local ne...
150
Voted
SLSFS
2005
Springer
15 years 8 months ago
2005
Springer
We propose the use of latent space models applied to local invariant features for object classification. We investigate whether using latent space models enables to learn patterns...
164
Voted
ECML
2006
Springer
15 years 6 months ago
2006
Springer
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...