29 search results - page 1 / 6 » Semi-supervised handwritten digit recognition using very few... |
ICASSP
2011
IEEE
12 years 8 months ago
2011
IEEE
We propose a novel semi-supervised classifier for handwritten digit recognition problems that is based on the assumption that any digit can be obtained as a slight transformation...
ASUNAM
2010
IEEE
13 years 6 months ago
2010
IEEE
The goal of semi-supervised learning (SSL) methods is to reduce the amount of labeled training data required by learning from both labeled and unlabeled instances. Macskassy and Pr...
CVPR
2006
IEEE
14 years 7 months ago
2006
IEEE
We consider the general problem of learning from both labeled and unlabeled data. Given a set of data points, only a few of them are labeled, and the remaining points are unlabele...
ICDAR
2009
IEEE
13 years 11 months ago
2009
IEEE
Training a system to recognize handwritten words is a task that requires a large amount of data with their correct transcription. However, the creation of such a training set, inc...
ACL
2006
13 years 6 months ago
2006
Shortage of manually labeled data is an obstacle to supervised relation extraction methods. In this paper we investigate a graph based semi-supervised learning algorithm, a label ...