Sciweavers

998 search results - page 80 / 200
» From Feasible Proofs to Feasible Computations
Sort
View
ICANN
2009
Springer
14 years 22 days ago
Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data
In a typical reinforcement learning (RL) setting details of the environment are not given explicitly but have to be estimated from observations. Most RL approaches only optimize th...
Alexander Hans, Steffen Udluft
MVA
2007
185views Computer Vision» more  MVA 2007»
13 years 10 months ago
An Efficient Method for Human Behavior Identification
This paper presents a recognition method for human behavior identification based on motion history image theory. The motion history image has the advantage that it can record the ...
Fang-Hsuan Cheng, Fu-Tai Chen
NIPS
2004
13 years 10 months ago
Nonparametric Transforms of Graph Kernels for Semi-Supervised Learning
We present an algorithm based on convex optimization for constructing kernels for semi-supervised learning. The kernel matrices are derived from the spectral decomposition of grap...
Xiaojin Zhu, Jaz S. Kandola, Zoubin Ghahramani, Jo...
VMV
2003
164views Visualization» more  VMV 2003»
13 years 10 months ago
A Parallel Framework for Silhouette-Based Human Motion Capture
This paper presents a method to capture human motion from silhouettes of a person in multi-view video streams. Applying a hierarchical kinematic body model motion parameters are e...
Christian Theobalt, Joel Carranza, Marcus A. Magno...
WISES
2003
13 years 10 months ago
Built-In Fault Injectors - The Logical Continuation of BIST?
— With the increasing number of embedded computer systems being used in safety critical applications the testing and assessment of a system’s fault tolerance properties become ...
Andreas Steininger, Babak Rahbaran, Thomas Handl