58 search results - page 1 / 12 » Using Gradient Descent Optimization for Acoustics Training f... |
TSD
2010
Springer
13 years 3 months ago
2010
Springer
In this paper, we study the use of heterogeneous data for training of acoustic models. In initial experiments, a significant drop of accuracy has been observed on in-domain test s...
ACL
2009
13 years 2 months ago
2009
Stochastic gradient descent (SGD) uses approximate gradients estimated from subsets of the training data and updates the parameters in an online fashion. This learning framework i...
IPMI
2005
Springer
14 years 5 months ago
2005
Springer
Abstract. Active Shape Models are a popular method for segmenting three-dimensional medical images. To obtain the required landmark correspondences, various automatic approaches ha...
JMLR
2012
11 years 7 months ago
2012
In this paper, we propose a second order optimization method to learn models where both the dimensionality of the parameter space and the number of training samples is high. In ou...
SDM
2012
SIAM
11 years 7 months ago
2012
SIAM
Multiple data sources containing different types of features may be available for a given task. For instance, users’ profiles can be used to build recommendation systems. In a...