Sciweavers

329 search results - page 10 / 66
» Probably Approximately Correct Learning
Sort
View
INFOCOM
2009
IEEE
14 years 2 months ago
Forward Correction and Fountain codes in Delay Tolerant Networks
Abstract—Delay tolerant Ad-hoc Networks leverage the mobility of relay nodes to compensate for lack of permanent connectivity and thus enable communication between nodes that are...
Eitan Altman, Francesco De Pellegrini
QUESTA
2008
82views more  QUESTA 2008»
13 years 7 months ago
Corrected asymptotics for a multi-server queue in the Halfin-Whitt regime
To obtain insight in the quality of heavy-traffic approximations for queues with many servers, we consider the steady-state number of waiting customers in an M/D/s queue as s . I...
Augustus J. E. M. Janssen, Johan van Leeuwaarden, ...
UAI
2003
13 years 8 months ago
Learning Generative Models of Similarity Matrices
Recently, spectral clustering (a.k.a. normalized graph cut) techniques have become popular for their potential ability at finding irregularlyshaped clusters in data. The input to...
Rómer Rosales, Brendan J. Frey
FLAIRS
2004
13 years 9 months ago
Multimodal Function Optimization Using Local Ruggedness Information
In multimodal function optimization, niching techniques create diversification within the population, thus encouraging heterogeneous convergence. The key to the effective diversif...
Jian Zhang 0007, Xiaohui Yuan, Bill P. Buckles
ECML
1993
Springer
13 years 11 months ago
Complexity Dimensions and Learnability
In machine learning theory, problem classes are distinguished because of di erences in complexity. In 6 , a stochastic model of learning from examples was introduced. This PAClear...
Shan-Hwei Nienhuys-Cheng, Mark Polman