187 search results - page 8 / 38 » Conditional random fields for multi-agent reinforcement lear... |
96
Voted
INTERSPEECH
2010
14 years 6 months ago
2010
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
112
Voted
ICML
2004
IEEE
16 years 13 days ago
2004
IEEE
In sequence modeling, we often wish to represent complex interaction between labels, such as when performing multiple, cascaded labeling tasks on the same sequence, or when longra...
113
click to vote
ICML
2005
IEEE
16 years 13 days ago
2005
IEEE
The Web contains an abundance of useful semistructured information about real world objects, and our empirical study shows that strong sequence characteristics exist for Web infor...
110
Voted
ICML
2009
IEEE
15 years 6 months ago
2009
IEEE
In real sequence labeling tasks, statistics of many higher order features are not sufficient due to the training data sparseness, very few of them are useful. We describe Sparse H...
90
Voted
ICML
2007
IEEE
16 years 13 days ago
2007
IEEE
Discriminative training of graphical models can be expensive if the variables have large cardinality, even if the graphical structure is tractable. In such cases, pseudolikelihood...