348 search results - page 1 / 70 » Learning on the Test Data: Leveraging Unseen Features |
ICML
2003
IEEE
14 years 5 months ago
2003
IEEE
This paper addresses the problem of classification in situations where the data distribution is not homogeneous: Data instances might come from different locations or times, and t...
ECCV
2010
Springer
13 years 9 months ago
2010
Springer
Abstract. In this paper we investigate the problem of exploiting multiple sources of information for object recognition tasks when additional modalities that are not present in the...
CSB
2005
IEEE
13 years 10 months ago
2005
IEEE
Artificial Neural Networks (ANN) were employed to predict daylily (Hemerocalli spp.) hybrids from known characteristics of parents used in hybridization. Features such as height, ...
JMLR
2010
12 years 12 months ago
2010
After building a classifier with modern tools of machine learning we typically have a black box at hand that is able to predict well for unseen data. Thus, we get an answer to the...
JMLR
2010
12 years 12 months ago
2010
A parametric version of herding is formulated. The nonlinear mapping between consecutive time slices is learned by a form of self-supervised training. The resulting dynamical syst...