373 search results - page 33 / 75 » Building Relational World Models for Reinforcement Learning |
FLAIRS
2009
13 years 5 months ago
2009
As robots become more common, it becomes increasingly useful for them to communicate and effectively share knowledge that they have learned through their individual experiences. L...
BVAI
2007
Springer
14 years 1 months ago
2007
Springer
In real life, visual learning is supposed to be a continuous process. Humans have an innate facility to recognize objects even under less-than-ideal conditions and to build robust ...
DAGM
2008
Springer
13 years 9 months ago
2008
Springer
Abstract. In this paper, we propose a new approach to learn structured visual compound models from shape-based feature descriptions. We use captioned text in order to drive the pro...
IDA
2005
Springer
14 years 1 months ago
2005
Springer
DNA arrays yield a global view of gene expression and can be used to build genetic networks models, in order to study relations between genes. Literature proposes Bayesian network ...
NIPS
2007
13 years 9 months ago
2007
We propose a Bayesian undirected graphical model for co-training, or more generally for semi-supervised multi-view learning. This makes explicit the previously unstated assumption...