Sciweavers

4263 search results - page 57 / 853
» Learning without Coding
Sort
View
CVPR
2012
IEEE
13 years 6 months ago
Geometry constrained sparse coding for single image super-resolution
The choice of the over-complete dictionary that sparsely represents data is of prime importance for sparse codingbased image super-resolution. Sparse coding is a typical unsupervi...
Xiaoqiang Lu, Haoliang Yuan, Pingkun Yan, Yuan Yua...
MCS
2005
Springer
15 years 9 months ago
Ensemble of SVMs for Incremental Learning
Support Vector Machines (SVMs) have been successfully applied to solve a large number of classification and regression problems. However, SVMs suffer from the catastrophic forgetti...
Zeki Erdem, Robi Polikar, Fikret S. Gürgen, N...
ICPR
2010
IEEE
15 years 11 months ago
Adding Classes Online in Error Correcting Output Codes Framework
—This article proposes a general extension of the Error Correcting Output Codes (ECOC) framework to the online learning scenario. As a result, the final classifier handles the ...
Sergio Escalera, David Masip, Eloi Puertas, Petia ...
HIPEAC
2007
Springer
15 years 10 months ago
Reducing Exit Stub Memory Consumption in Code Caches
Abstract. The interest in translation-based virtual execution environments (VEEs) is growing with the recognition of their importance in a variety of applications. However, due to ...
Apala Guha, Kim M. Hazelwood, Mary Lou Soffa
GECCO
2005
Springer
114views Optimization» more  GECCO 2005»
15 years 10 months ago
Exploiting disruption aversion to control code bloat
The authors employ multiple crossovers as a novel natural extension to crossovers as a mixing operator. They use this as a framework to explore the ideas of code growth. Empirical...
Jason Stevens, Robert B. Heckendorn, Terence Soule