Sciweavers

6693 search results - page 886 / 1339
» Methods of Automatic Algorithm Generation
Sort
View
MICRO
2010
IEEE
175views Hardware» more  MICRO 2010»
15 years 2 months ago
Efficient Selection of Vector Instructions Using Dynamic Programming
Accelerating program performance via SIMD vector units is very common in modern processors, as evidenced by the use of SSE, MMX, VSE, and VSX SIMD instructions in multimedia, scien...
Rajkishore Barik, Jisheng Zhao, Vivek Sarkar
FOCS
2010
IEEE
15 years 2 months ago
Boosting and Differential Privacy
Boosting is a general method for improving the accuracy of learning algorithms. We use boosting to construct improved privacy-preserving synopses of an input database. These are da...
Cynthia Dwork, Guy N. Rothblum, Salil P. Vadhan
ICCV
2009
IEEE
2301views Computer Vision» more  ICCV 2009»
16 years 9 months ago
Class Segmentation and Object Localization with Superpixel Neighborhoods
We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class s...
Brian Fulkerson, Andrea Vedaldi, Stefano Soatto
ICARCV
2008
IEEE
184views Robotics» more  ICARCV 2008»
15 years 11 months ago
Learning informative point classes for the acquisition of object model maps
—This paper proposes a set of methods for building informative and robust feature point representations, used for accurately labeling points in a 3D point cloud, based on the typ...
Radu Bogdan Rusu, Zoltan Csaba Marton, Nico Blodow...
CEC
2007
IEEE
15 years 11 months ago
Multi-population competitive co-evolution of car racing controllers
Abstract— Multi-population competitive co-evolution is explored as a way of developing controllers for a simple (but definitely not trivial) car racing game. The three main uses...
Julian Togelius, Peter Burrow, Simon M. Lucas