Sciweavers

340 search results - page 24 / 68
» Adaptive Kernel Methods Using the Balancing Principle
Sort
View
ACL
2010
13 years 2 months ago
Adapting Self-Training for Semantic Role Labeling
Supervised semantic role labeling (SRL) systems trained on hand-crafted annotated corpora have recently achieved state-of-the-art performance. However, creating such corpora is te...
Rasoul Samad Zadeh Kaljahi
JSCIC
2008
148views more  JSCIC 2008»
13 years 7 months ago
Finite Element-Based Level Set Methods for Higher Order Flows
In this paper we shall discuss the numerical simulation of higher order geometric flows by level set methods. Main examples under considerations are surface diffusion and the Will...
Martin Burger, Christina Stöcker, Axel Voigt
SIGMOD
2004
ACM
118views Database» more  SIGMOD 2004»
14 years 7 months ago
Effective Use of Block-Level Sampling in Statistics Estimation
Block-level sampling is far more efficient than true uniform-random sampling over a large database, but prone to significant errors if used to create database statistics. In this ...
Surajit Chaudhuri, Gautam Das, Utkarsh Srivastava
TNN
2010
234views Management» more  TNN 2010»
13 years 2 months ago
Novel maximum-margin training algorithms for supervised neural networks
This paper proposes three novel training methods, two of them based on the back-propagation approach and a third one based on information theory for Multilayer Perceptron (MLP) bin...
Oswaldo Ludwig, Urbano Nunes
SC
1995
ACM
13 years 11 months ago
A Parallel Incompressible Flow Solver Package with a Parallel Multigrid Elliptic Kernel
A parallel time-dependent incompressible flow solver and a parallel multigrid elliptic kernel are described. The flow solver is based on a second-order projection method applied...
John Z. Lou, Robert D. Ferraro