147 search results - page 2 / 30 » Discriminative Training of a Neural Network Statistical Pars... |
TNN
2010
13 years 16 hour ago
2010
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
ICASSP
2011
IEEE
12 years 9 months ago
2011
IEEE
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
ANNPR
2008
Springer
13 years 7 months ago
2008
Springer
In applications such as character recognition, some classes are heavily overlapped but are not necessarily to be separated. For classification of such overlapping classes, either d...
EMNLP
2006
13 years 6 months ago
2006
We propose a general method for reranker construction which targets choosing the candidate with the least expected loss, rather than the most probable candidate. Different approac...
ICONIP
1998
13 years 6 months ago
1998
Despite all the progress in neural networks the technology is still brittle and sometimes difficult to apply. Automatic construction of networks and proper initialization of their...