194 search results - page 23 / 39 » Sequence Labeling with Reinforcement Learning and Ranking Al... |
109
click to vote
CVPR
2011
IEEE
14 years 5 months ago
2011
IEEE
Nearly every structured prediction problem in computer vision requires approximate inference due to large and complex dependencies among output labels. While graphical models prov...
ECML
2005
Springer
15 years 3 months ago
2005
Springer
Discriminative learning techniques for sequential data have proven to be more effective than generative models for named entity recognition, information extraction, and other task...
128
click to vote
SGAI
2010
Springer
14 years 7 months ago
2010
Springer
This paper presents work on using hierarchical long term memory to reduce the memory requirements of nearest sequence memory (NSM) learning, a previously published, instance-based ...
KDD
2010
ACM
14 years 11 months ago
2010
ACM
Active learning (AL) is an increasingly popular strategy for mitigating the amount of labeled data required to train classifiers, thereby reducing annotator effort. We describe ...
118
click to vote
JAIR
2008
14 years 9 months ago
2008
We present exact algorithms for identifying deterministic-actions' effects and preconditions in dynamic partially observable domains. They apply when one does not know the ac...