58 search results - page 3 / 12 » Using Gradient Descent Optimization for Acoustics Training f... |
AUTOMATICA
2008
13 years 6 months ago
2008
Data-based control design methods most often consist of iterative adjustment of the controller's parameters towards the parameter values which minimize an H2 performance crit...
ACL
2008
13 years 7 months ago
2008
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...
ICASSP
2008
IEEE
14 years 18 days ago
2008
IEEE
Phoneme set clustering of accurate modeling is important in the task of multilingual speech recognition, especially when each of the available language training corpora is mismatc...
JMLR
2012
11 years 8 months ago
2012
We present SpeedBoost, a natural extension of functional gradient descent, for learning anytime predictors, which automatically trade computation time for predictive accuracy by s...
KDD
2009
ACM
14 years 6 months ago
2009
ACM
We present novel semi-supervised boosting algorithms that incrementally build linear combinations of weak classifiers through generic functional gradient descent using both labele...