Sciweavers

2470 search results - page 420 / 494
» Adaptive Peer Selection
Sort
View
ECML
2006
Springer
13 years 11 months ago
Task-Driven Discretization of the Joint Space of Visual Percepts and Continuous Actions
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
Sébastien Jodogne, Justus H. Piater
EUROMICRO
2006
IEEE
13 years 11 months ago
Building Reconfigurable Component-Based OS with THINK
Dynamic reconfiguration allows modifying a system during its execution, and can be used to apply patches and updates, to implement adaptive systems, dynamic instrumentation, or to...
Juraj Polakovic, Ali Erdem Özcan, Jean-Bernar...
FDTC
2006
Springer
102views Cryptology» more  FDTC 2006»
13 years 11 months ago
Cryptographic Key Reliable Lifetimes: Bounding the Risk of Key Exposure in the Presence of Faults
With physical attacks threatening the security of current cryptographic schemes, no security policy can be developed without taking into account the physical nature of computation....
Alfonso De Gregorio
GECCO
2006
Springer
138views Optimization» more  GECCO 2006»
13 years 11 months ago
Does overfitting affect performance in estimation of distribution algorithms
Estimation of Distribution Algorithms (EDAs) are a class of evolutionary algorithms that use machine learning techniques to solve optimization problems. Machine learning is used t...
Hao Wu, Jonathan L. Shapiro
ISCA
1998
IEEE
135views Hardware» more  ISCA 1998»
13 years 11 months ago
Branch Prediction Based on Universal Data Compression Algorithms
Data compression and prediction are closely related. Thus prediction methods based on data compression algorithms have been suggested for the branch prediction problem. In this wo...
Eitan Federovsky, Meir Feder, Shlomo Weiss