Sciweavers

567 search results - page 17 / 114
» Reconstructing Numbers from Pairwise Function Values
Sort
View
ICML
2010
IEEE
13 years 9 months ago
Bayesian Multi-Task Reinforcement Learning
We consider the problem of multi-task reinforcement learning where the learner is provided with a set of tasks, for which only a small number of samples can be generated for any g...
Alessandro Lazaric, Mohammad Ghavamzadeh
CVPR
2003
IEEE
14 years 10 months ago
Structure From Motion for Scenes Without Features
We describe an algorithm for reconstructing the 3D shape of the scene and the relative pose of a number of cameras from a collection of images under the assumption that the scene ...
Anthony J. Yezzi, Stefano Soatto
ALIFE
2006
13 years 8 months ago
Axiomatic Scalable Neurocontroller Analysis via the Shapley Value
One of the major challenges in the field of neurally driven evolved autonomous agents is deciphering the neural mechanisms underlying their behavior. Aiming at this goal, we have d...
Alon Keinan, Ben Sandbank, Claus C. Hilgetag, Isaa...
SDM
2008
SIAM
138views Data Mining» more  SDM 2008»
13 years 10 months ago
Clustering from Constraint Graphs
In constrained clustering it is common to model the pairwise constraints as edges on the graph of observations. Using results from graph theory, we analyze such constraint graphs ...
Ari Freund, Dan Pelleg, Yossi Richter
AICT
2008
IEEE
119views Communications» more  AICT 2008»
13 years 8 months ago
Simplification of Frequency Test for Random Number Generation Based on Chi-Square
This paper presents the simplified method of random test suite based on the frequency (block) test. The test is used to check the first property of random numbers which is to have ...
Kruawan Wongpanya, Keattisak Sripimanwat, Kanok Je...