1541 search results - page 222 / 309 » Learning to Diagnose by Doing |
206
click to vote
SCALESPACE
2007
Springer
16 years 15 days ago
2007
Springer
This paper presents a statistical model for textures that uses a non-negative decomposition on a set of local atoms learned from an exemplar. This model is described by the varianc...
178
click to vote
ICRA
2006
IEEE
16 years 13 days ago
2006
IEEE
— We present a system of coupled nonlinear oscillators to be used as programmable central pattern generators, and apply it to control the locomotion of a humanoid robot. Central ...
166
click to vote
IJCNN
2006
IEEE
16 years 12 days ago
2006
IEEE
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
182
click to vote
ICANN
2005
Springer
15 years 12 months ago
2005
Springer
One aim of Meta-learning techniques is to minimize the time needed for problem solving, and the effort of parameter hand-tuning, by automating algorithm selection. The predictive m...
184
click to vote
MLDM
2005
Springer
15 years 12 months ago
2005
Springer
In the context of large databases, data preparation takes a greater importance : instances and explanatory attributes have to be carefully selected. In supervised learning, instanc...