4660 search results - page 60 / 932 » Learning from imperfect data |
ICML
2009
IEEE
14 years 9 months ago
2009
IEEE
This work proposes a learning method for deep architectures that takes advantage of sequential data, in particular from the temporal coherence that naturally exists in unlabeled v...
ECAI
2004
Springer
14 years 2 months ago
2004
Springer
Advances in data collection technologies allow accumulation of large and high dimensional datasets and provide opportunities for learning high quality classification and regression...
Publication
Providing methods to support semantic interaction with growing volumes of video data is an increasingly important challenge for data mining. To this end, there has been some succes...
WWW
2008
ACM
14 years 9 months ago
2008
ACM
We consider the problem of ranking refinement, i.e., to improve the accuracy of an existing ranking function with a small set of labeled instances. We are, particularly, intereste...
NECO
1998
13 years 8 months ago
1998
We introduce a constructive, incremental learning system for regression problems that models data by means of spatially localized linear models. In contrast to other approaches, t...