Sciweavers

988 search results - page 19 / 198
» Learning with Local and Global Consistency
Sort
View
CVPR
2006
IEEE
16 years 1 days ago
Measure Locally, Reason Globally: Occlusion-sensitive Articulated Pose Estimation
Part-based tree-structured models have been widely used for 2D articulated human pose-estimation. These approaches admit efficient inference algorithms while capturing the import...
Leonid Sigal, Michael J. Black
ICDM
2008
IEEE
156views Data Mining» more  ICDM 2008»
16 years 12 days ago
Exploiting Local and Global Invariants for the Management of Large Scale Information Systems
This paper presents a data oriented approach to modeling the complex computing systems, in which an ensemble of correlation models are discovered to represent the system status. I...
Haifeng Chen, Haibin Cheng, Guofei Jiang, Kenji Yo...
NIPS
2008
15 years 7 months ago
On the asymptotic equivalence between differential Hebbian and temporal difference learning using a local third factor
In this theoretical contribution we provide mathematical proof that two of the most important classes of network learning - correlation-based differential Hebbian learning and rew...
Christoph Kolodziejski, Bernd Porr, Minija Tamosiu...
IJCNN
2006
IEEE
16 years 3 hour ago
Global Reinforcement Learning in Neural Networks with Stochastic Synapses
— We have found a more general formulation of the REINFORCE learning principle which had been proposed by R. J. Williams for the case of artificial neural networks with stochast...
Xiaolong Ma, Konstantin Likharev
ROBOCUP
2001
Springer
98views Robotics» more  ROBOCUP 2001»
15 years 10 months ago
A Two-Tiered Approach to Self-Localization
Abstract. This paper describes a two-tiered approach to the self-localization problem for soccer playing robots using generic off-the-shelf color cameras. The solution consists of...
Frank de Jong, Jurjen Caarls, Robert Bartelds, Pie...