Sciweavers

1604 search results - page 261 / 321
» Regularization on Discrete Spaces
Sort
View
NN
2010
Springer
125views Neural Networks» more  NN 2010»
13 years 6 months ago
Parameter-exploring policy gradients
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in paramet...
Frank Sehnke, Christian Osendorfer, Thomas Rü...
PR
2010
186views more  PR 2010»
13 years 6 months ago
Feature extraction by learning Lorentzian metric tensor and its extensions
We develop a supervised dimensionality reduction method, called Lorentzian Discriminant Projection (LDP), for feature extraction and classification. Our method represents the str...
Risheng Liu, Zhouchen Lin, Zhixun Su, Kewei Tang
SMI
2010
IEEE
152views Image Analysis» more  SMI 2010»
13 years 6 months ago
Direct-Product Volumetric Parameterization of Handlebodies via Harmonic Fields
—Volumetric parameterization plays an important role for geometric modeling. Due to the complicated topological nature of volumes, it is much more challenging than the surface ca...
Jiazhi Xia, Ying He 0001, Xiaotian Yin, Shuchu Han...
TVCG
2010
146views more  TVCG 2010»
13 years 6 months ago
Narrative Visualization: Telling Stories with Data
—Data visualization is regularly promoted for its ability to reveal stories within data, yet these “data stories” differ in important ways from traditional forms of storytell...
Edward Segel, Jeffrey Heer
ACL
2010
13 years 5 months ago
Practical Very Large Scale CRFs
Conditional Random Fields (CRFs) are a widely-used approach for supervised sequence labelling, notably due to their ability to handle large description spaces and to integrate str...
Thomas Lavergne, Olivier Cappé, Franç...