Sciweavers

4233 search results - page 297 / 847
» Three Paths to Effectiveness
Sort
View
ICML
2007
IEEE
16 years 7 months ago
Cross-domain transfer for reinforcement learning
A typical goal for transfer learning algorithms is to utilize knowledge gained in a source task to learn a target task faster. Recently introduced transfer methods in reinforcemen...
Matthew E. Taylor, Peter Stone
ICML
1998
IEEE
16 years 7 months ago
A Randomized ANOVA Procedure for Comparing Performance Curves
Three factors are related in analyses of performance curves such as learning curves: the amount of training, the learning algorithm, and performance. Often we want to know whether...
Justus H. Piater, Paul R. Cohen, Xiaoqin Zhang, Mi...
ISCC
2009
IEEE
129views Communications» more  ISCC 2009»
16 years 1 months ago
Handling dynamics in gossip-based aggregation schemes
A problem in large and dynamic networks consists in making available at each node global information about the state of the network. Gossip-based aggregation schemes are a simple ...
Nicola Bicocchi, Marco Mamei, Franco Zambonelli
169
Voted
GLOBECOM
2008
IEEE
16 years 1 months ago
Impact of Random Mobility on the Inhomogeneity of Spatial Distributions
Abstract—Simulation results of wireless networks heavily depend on the spatial distribution of its nodes. Even though the initial distribution may match the expectations of the r...
Michael Gyarmati, Udo Schilcher, Günther Bran...
DSN
2007
IEEE
16 years 1 months ago
On the Selection of Error Model(s) for OS Robustness Evaluation
The choice of error model used for robustness evaluation of Operating Systems (OSs) influences the evaluation run time, implementation complexity, as well as the evaluation preci...
Andréas Johansson, Neeraj Suri, Brendan Mur...