957 search results - page 67 / 192 » From Margin to Sparsity |
NIPS
2008
13 years 9 months ago
2008
Kernel supervised learning methods can be unified by utilizing the tools from regularization theory. The duality between regularization and prior leads to interpreting regularizat...
NAACL
2007
13 years 9 months ago
2007
We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four “morphologically rich” languages: Finnish, Estonian, Turkish, and ...
NIPS
2001
13 years 9 months ago
2001
We show that it is possible to extend hidden Markov models to have a countably infinite number of hidden states. By using the theory of Dirichlet processes we can implicitly integ...
TREC
2003
13 years 9 months ago
2003
Many researchers have used lexical networks and ontologies to mitigate synonymy and polysemy problems in Question Answering (QA), systems coupled with taggers, query classifiers,...
CVPR
2010
IEEE
13 years 8 months ago
2010
IEEE
Building robust low and mid-level image representations, beyond edge primitives, is a long-standing goal in vision. Many existing feature detectors spatially pool edge information...