193 search results - page 25 / 39 » Approximate Maximum Parsimony and Ancestral Maximum Likeliho... |
96
Voted
NIPS
2003
15 years 1 months ago
2003
In models that define probabilities via energies, maximum likelihood learning typically involves using Markov Chain Monte Carlo to sample from the model’s distribution. If the ...
108
Voted
ICASSP
2010
IEEE
15 years 20 days ago
2010
IEEE
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...
84
Voted
ICASSP
2010
IEEE
15 years 20 days ago
2010
IEEE
Current state-of-the-art speech recognition systems work quite well in controlled environments but their performance degrades severely in realistic acoustical conditions in reverb...
CORR
2006
Springer
15 years 15 days ago
2006
Springer
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...
99
Voted
TNN
2008
15 years 11 days ago
2008
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...