Sciweavers

2326 search results - page 344 / 466
» Optimization on Support Vector Machines
Sort
View
SC
1991
ACM
15 years 1 months ago
Interprocedural transformations for parallel code generation
We present a new approach that enables compiler optimization of procedure calls and loop nests containing procedure calls. We introduce two interprocedural transformationsthat mov...
Mary W. Hall, Ken Kennedy, Kathryn S. McKinley
PROCEDIA
2010
85views more  PROCEDIA 2010»
14 years 8 months ago
Toward interactive statistical modeling
When solving machine learning problems, there is currently little automated support for easily experimenting with alternative statistical models or solution strategies. This is be...
Sooraj Bhat, Ashish Agarwal, Alexander Gray, Richa...
ACL
2006
14 years 11 months ago
Minimum Risk Annealing for Training Log-Linear Models
When training the parameters for a natural language system, one would prefer to minimize 1-best loss (error) on an evaluation set. Since the error surface for many natural languag...
David A. Smith, Jason Eisner
CIVR
2008
Springer
213views Image Analysis» more  CIVR 2008»
14 years 12 months ago
Language modeling for bag-of-visual words image categorization
In this paper, we propose two ways of improving image classification based on bag-of-words representation [25]. Two shortcomings of this representation are the loss of the spatial...
Pierre Tirilly, Vincent Claveau, Patrick Gros
IPPS
2003
IEEE
15 years 3 months ago
The CoGenT Project: Co-Generating Compilers and Simulators for Dynamically Compiled Languages
To understand the performance of modern Java systems one must observe execution in the context of specific architectures. It is also important that we make these observations usi...
J. Eliot B. Moss, Charles C. Weems, Timothy Richar...