421 search results - page 16 / 85 » Incorporating Test Inputs into Learning |
CVPR
2008
IEEE
15 years 11 months ago
2008
IEEE
An important problem in image labeling concerns learning with images labeled at varying levels of specificity. We propose an approach that can incorporate images with labels drawn...
SDM
2008
SIAM
14 years 11 months ago
2008
SIAM
Covariate shift is a situation in supervised learning where training and test inputs follow different distributions even though the functional relation remains unchanged. A common...
NN
2008
Springer
14 years 9 months ago
2008
Springer
Optimally designing the location of training input points (active learning) and choosing the best model (model selection) are two important components of supervised learning and h...
ICCV
2001
IEEE
15 years 11 months ago
2001
IEEE
In this paper, we present an example-based facial sketch system. Our system automatically generates a sketch from an input image, by learning from example sketches drawn with a pa...
AAAI
1996
14 years 11 months ago
1996
Constructive learning algorithms offer an attractive approach for the incremental construction of near-minimal neural-network architectures for pattern classification. They help ov...