Sciweavers

1282 search results - page 105 / 257
» Feature selection with neural networks
Sort
View
SIBGRAPI
2003
IEEE
14 years 2 months ago
Learning-Based versus Model-Based Log-Polar Feature Extraction Operators: A Comparative Study
In this paper, we compare two distinct primal sketch feature extraction operators: one based on neural network feature learning and the other based on mathematical models of the f...
Herman Martins Gomes, Robert B. Fisher
NPL
2002
120views more  NPL 2002»
13 years 8 months ago
A Novel Measure for Quantifying the Topology Preservation of Self Organizing Feature Maps
Recently, feature maps have been applied to various problem domains.The success of some of these applications critically depends on whether feature maps are topologically ordered. ...
Mu-Chun Su, Hsiao-Te Chang, Chien-Hsing Chou
IJON
2000
86views more  IJON 2000»
13 years 8 months ago
Gain modulation of recurrent networks
Gain modulation is an important mechanism by which attentional and other inputs modify the amplitude of neuronal responses without changing their selectivity. Gain modulation has ...
Jian Zhang 0004, L. F. Abbott
IJCNN
2006
IEEE
14 years 3 months ago
Recognizing Human Emotion from Partial Facial Features
—Recognizing human emotions from partial facial features is quite hard to achieve reasonable accuracy. In this paper, we propose to use a tree structure representation to simulat...
Jia-Jun Wong, Siu-Yeung Cho
IWANN
2007
Springer
14 years 3 months ago
An EA Multi-model Selection for SVM Multiclass Schemes
Multiclass problems with binary SVM classifiers are commonly treated as a decomposition in several binary sub-problems. An open question is how to properly tune all these sub-prob...
Gilles Lebrun, Olivier Lezoray, Christophe Charrie...