Sciweavers

6709 search results - page 365 / 1342
» Performance Modelling of the Computational Hardware: A Stati...
Sort
View
NECO
2007
129views more  NECO 2007»
15 years 6 months ago
Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance
It is well-known that, in unidentifiable models, the Bayes estimation provides much better generalization performance than the maximum likelihood (ML) estimation. However, its ac...
Shinichi Nakajima, Sumio Watanabe
ICIP
2005
IEEE
16 years 8 months ago
Segmenting non stationary images with triplet Markov fields
The hidden Markov field (HMF) model has been used in many model-based solutions to image analysis problems, including that of image segmentation, and generally gives satisfying re...
Dalila Benboudjema, Wojciech Pieczynski
181
Voted
ICCV
2007
IEEE
16 years 8 months ago
Segmentation using Meta-texture Saliency
We address segmentation of an image into patches that have an underlying salient surface-roughness. Three intrinsic images are derived: reflectance, shading and metatexture images...
Yaser Yacoob, Larry S. Davis
ISCA
2006
IEEE
114views Hardware» more  ISCA 2006»
16 years 22 days ago
Ensemble-level Power Management for Dense Blade Servers
One of the key challenges for high-density servers (e.g., blades) is the increased costs in addressing the power and heat density associated with compaction. Prior approaches have...
Parthasarathy Ranganathan, Phil Leech, David E. Ir...
PADS
2006
ACM
16 years 20 days ago
Aurora: An Approach to High Throughput Parallel Simulation
A master/worker paradigm for executing large-scale parallel discrete event simulation programs over networkenabled computational resources is proposed and evaluated. In contrast t...
Alfred Park, Richard M. Fujimoto