Sciweavers

2328 search results - page 295 / 466
» Statistical machine translation
Sort
View
ICML
2007
IEEE
16 years 7 months ago
A kernel-based causal learning algorithm
We describe a causal learning method, which employs measuring the strength of statistical dependences in terms of the Hilbert-Schmidt norm of kernel-based cross-covariance operato...
Xiaohai Sun, Dominik Janzing, Bernhard Schölk...
ICML
2007
IEEE
16 years 7 months ago
Entire regularization paths for graph data
Graph data such as chemical compounds and XML documents are getting more common in many application domains. A main difficulty of graph data processing lies in the intrinsic high ...
Koji Tsuda
167
Voted
ICML
2008
IEEE
16 years 7 months ago
A worst-case comparison between temporal difference and residual gradient with linear function approximation
Residual gradient (RG) was proposed as an alternative to TD(0) for policy evaluation when function approximation is used, but there exists little formal analysis comparing them ex...
Lihong Li
ICML
2008
IEEE
16 years 7 months ago
Semi-supervised learning of compact document representations with deep networks
Finding good representations of text documents is crucial in information retrieval and classification systems. Today the most popular document representation is based on a vector ...
Marc'Aurelio Ranzato, Martin Szummer
176
Voted
ICML
2006
IEEE
16 years 7 months ago
A new approach to data driven clustering
We consider the problem of clustering in its most basic form where only a local metric on the data space is given. No parametric statistical model is assumed, and the number of cl...
Arik Azran, Zoubin Ghahramani