Sciweavers

1435 search results - page 228 / 287
» Generalization Error Bounds Using Unlabeled Data
Sort
View
ECML
2007
Springer
15 years 4 months ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
SIGGRAPH
1997
ACM
15 years 1 months ago
A model of visual masking for computer graphics
In this paper we develop a computational model of visual masking based on psychophysical data. The model predicts how the presence of one visual pattern affects the detectability...
James A. Ferwerda, Peter Shirley, Sumanta N. Patta...
LREC
2008
97views Education» more  LREC 2008»
14 years 11 months ago
Evaluating Dialogue Act Tagging with Naive and Expert Annotators
In this paper the dialogue act annotation of naive and expert annotators, both annotating the same data, are compared in order to characterise the insights annotations made by dif...
Jeroen Geertzen, Volha Petukhova, Harry Bunt
FIW
2009
101views Communications» more  FIW 2009»
14 years 7 months ago
Feature Interaction Detection in the Feature Language Extensions
One of the most difficult tasks in software development is that features are implemented by changing the code of other features. This problem cannot be solved with existing general...
Lei Sun, Lu Zhoa, Yimeng Li, Wu-Hon F. Leung
CORR
2010
Springer
179views Education» more  CORR 2010»
14 years 6 months ago
Comparison of Support Vector Machine and Back Propagation Neural Network in Evaluating the Enterprise Financial Distress
Recently, applying the novel data mining techniques for evaluating enterprise financial distress has received much research alternation. Support Vector Machine (SVM) and back prop...
Ming-Chang Lee, To Chang