Sciweavers

659 search results - page 79 / 132
» SmartApps: An Application Centric Approach to High Performan...
Sort
View
NCA
2007
IEEE
15 years 5 months ago
Using evolution to improve neural network learning: pitfalls and solutions
: Autonomous neural network systems typically require fast learning and good generalization performance, and there is potentially a trade-off between the two. The use of evolutiona...
John A. Bullinaria
EDCC
2010
Springer
15 years 11 months ago
D2HT: The Best of Both Worlds, Integrating RPS and DHT
Distributed Hash Tables (DHTs) and Random Peer Sampling (RPS) provide important and complementary services in the area of P2P overlay networks. DHTs achieve efficient lookup whil...
Marin Bertier, François Bonnet, Anne-Marie ...
IEEEPACT
2005
IEEE
15 years 11 months ago
HUNTing the Overlap
Hiding communication latency is an important optimization for parallel programs. Programmers or compilers achieve this by using non-blocking communication primitives and overlappi...
Costin Iancu, Parry Husbands, Paul Hargrove
ICCV
2007
IEEE
16 years 8 months ago
Real-time Accurate Object Detection using Multiple Resolutions
We propose a multi-resolution framework inspired by human visual search for general object detection. Different resolutions are represented using a coarse-to-fine feature hierarch...
Wei Zhang 0002, Gregory J. Zelinsky, Dimitris Sama...
KDD
2004
ACM
195views Data Mining» more  KDD 2004»
16 years 6 months ago
Improved robustness of signature-based near-replica detection via lexicon randomization
Detection of near duplicate documents is an important problem in many data mining and information filtering applications. When faced with massive quantities of data, traditional d...
Aleksander Kolcz, Abdur Chowdhury, Joshua Alspecto...