Sciweavers

6291 search results - page 1026 / 1259
» Components Are from Mars
Sort
View
NN
2010
Springer
125views Neural Networks» more  NN 2010»
15 years 5 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...
PC
2010
145views Management» more  PC 2010»
15 years 5 months ago
GPU computing with Kaczmarz's and other iterative algorithms for linear systems
The graphics processing unit (GPU) is used to solve large linear systems derived from partial differential equations. The differential equations studied are strongly convection-...
Joseph M. Elble, Nikolaos V. Sahinidis, Panagiotis...
PERCOM
2010
ACM
15 years 5 months ago
HIP: Health integration platform
—This paper introduces a new software development platform specifically designed for wireless health applications. Wireless health applications follow a unique paradigm encompas...
Jonathan Woodbridge, Hyduke Noshadi, Ani Nahapetia...
PKDD
2010
Springer
184views Data Mining» more  PKDD 2010»
15 years 5 months ago
Shift-Invariant Grouped Multi-task Learning for Gaussian Processes
Multi-task learning leverages shared information among data sets to improve the learning performance of individual tasks. The paper applies this framework for data where each task ...
Yuyang Wang, Roni Khardon, Pavlos Protopapas
PR
2010
129views more  PR 2010»
15 years 5 months ago
Parsimonious reduction of Gaussian mixture models with a variational-Bayes approach
Aggregating statistical representations of classes is an important task for current trends in scaling up learning and recognition, or for addressing them in distributed infrastruc...
Pierrick Bruneau, Marc Gelgon, Fabien Picarougne
« Prev « First page 1026 / 1259 Last » Next »