Sciweavers

1136 search results - page 144 / 228
» Learning with Weighted Transducers
Sort
View
ALT
2009
Springer
14 years 1 months ago
The Follow Perturbed Leader Algorithm Protected from Unbounded One-Step Losses
In this paper the sequential prediction problem with expert advice is considered for the case when the losses of experts suffered at each step can be unbounded. We present some mo...
Vladimir V. V'yugin
ACCV
2007
Springer
13 years 11 months ago
Embedding a Region Merging Prior in Level Set Vector-Valued Image Segmentation
In the scope of level set image segmentation, the number of regions is fixed beforehand. This number occurs as a constant in the objective functional and its optimization. In this...
Ismail Ben Ayed, Amar Mitiche
NAACL
2007
13 years 10 months ago
Source-Language Features and Maximum Correlation Training for Machine Translation Evaluation
We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
Ding Liu, Daniel Gildea
NIPS
1998
13 years 10 months ago
Global Optimisation of Neural Network Models via Sequential Sampling
We propose a novel strategy for training neural networks using sequential Monte Carlo algorithms. This global optimisation strategy allows us to learn the probability distribution...
João F. G. de Freitas, Mahesan Niranjan, Ar...
IJON
2006
138views more  IJON 2006»
13 years 9 months ago
Time-series prediction using a local linear wavelet neural network
A local linear wavelet neural network (LLWNN) is presented in this paper. The difference of the network with conventional wavelet neural network (WNN) is that the connection weigh...
Yuehui Chen, Bo Yang, Jiwen Dong