Sciweavers

105 search results - page 5 / 21
» Accelerated Convergence Using Dynamic Mean Shift
Sort
View
CF
2009
ACM
14 years 2 months ago
Strategies for dynamic memory allocation in hybrid architectures
Hybrid architectures combining the strengths of generalpurpose processors with application-specific hardware accelerators can lead to a significant performance improvement. Our ...
Peter Bertels, Wim Heirman, Dirk Stroobandt
EELC
2006
118views Languages» more  EELC 2006»
13 years 11 months ago
Lexicon Convergence in a Population With and Without Metacommunication
How does a shared lexicon arise in population of agents with differing lexicons, and how can this shared lexicon be maintained over multiple generations? In order to get some insig...
Zoran Macura, Jonathan Ginzburg
VTC
2010
IEEE
156views Communications» more  VTC 2010»
13 years 5 months ago
A Unified MIMO Architecture Subsuming Space Shift Keying, OSTBC, BLAST and LDC
In this paper, motivated by the recent concept of Spatial Modulation (SM), we propose a novel Generalized Space-Time Shift Keying (G-STSK) architecture, which acts as a unified Mul...
Shinya Sugiura, Sheng Chen, Lajos Hanzo
CORR
2010
Springer
127views Education» more  CORR 2010»
13 years 7 months ago
Mean field for Markov Decision Processes: from Discrete to Continuous Optimization
We study the convergence of Markov Decision Processes made of a large number of objects to optimization problems on ordinary differential equations (ODE). We show that the optimal...
Nicolas Gast, Bruno Gaujal, Jean-Yves Le Boudec
CORR
2011
Springer
194views Education» more  CORR 2011»
12 years 11 months ago
Accelerating Reinforcement Learning through Implicit Imitation
Imitation can be viewed as a means of enhancing learning in multiagent environments. It augments an agent’s ability to learn useful behaviors by making intelligent use of the kn...
Craig Boutilier, Bob Price