Sciweavers

791 search results - page 108 / 159
» Approximating the Maximum Sharing Problem
Sort
View
ICASSP
2010
IEEE
13 years 8 months ago
Large margin estimation of n-gram language models for speech recognition via linear programming
We present a novel discriminative training algorithm for n-gram language models for use in large vocabulary continuous speech recognition. The algorithm uses large margin estimati...
Vladimir Magdin, Hui Jiang
CORR
2006
Springer
109views Education» more  CORR 2006»
13 years 7 months ago
Decision Making with Side Information and Unbounded Loss Functions
We consider the problem of decision-making with side information and unbounded loss functions. Inspired by probably approximately correct learning model, we use a slightly differe...
Majid Fozunbal, Ton Kalker
JMLR
2006
150views more  JMLR 2006»
13 years 7 months ago
Building Support Vector Machines with Reduced Classifier Complexity
Support vector machines (SVMs), though accurate, are not preferred in applications requiring great classification speed, due to the number of support vectors being large. To overc...
S. Sathiya Keerthi, Olivier Chapelle, Dennis DeCos...
TNN
2008
177views more  TNN 2008»
13 years 7 months ago
Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model
Previous work on statistical language modeling has shown that it is possible to train a feed-forward neural network to approximate probabilities over sequences of words, resulting...
Yoshua Bengio, Jean-Sébastien Senecal
TC
1998
13 years 7 months ago
Resilient Authentication Using Path Independence
—Authentication using a path of trusted intermediaries, each able to authenticate the next in the path, is a well-known technique for authenticating channels in a large distribut...
Michael K. Reiter, Stuart G. Stubblebine