Sciweavers

641 search results - page 59 / 129
» Training Methods for Adaptive Boosting of Neural Networks
Sort
View
NIPS
2008
14 years 11 months ago
Deep Learning with Kernel Regularization for Visual Recognition
In this paper we aim to train deep neural networks for rapid visual recognition. The task is highly challenging, largely due to the lack of a meaningful regularizer on the functio...
Kai Yu, Wei Xu, Yihong Gong
WAPCV
2004
Springer
15 years 3 months ago
Learning of Position-Invariant Object Representation Across Attention Shifts
Abstract. Selective attention shift can help neural networks learn invariance. We describe a method that can produce a network with invariance to changes in visual input caused by ...
Muhua Li, James J. Clark
NCA
2008
IEEE
14 years 9 months ago
Polynomial kernel adaptation and extensions to the SVM classifier learning
Three extensions to the Kernel-AdaTron training algorithm for Support Vector Machine classifier learning are presented. These extensions allow the trained classifier to adhere more...
Ramy Saad, Saman K. Halgamuge, Jason Li
NN
2006
Springer
113views Neural Networks» more  NN 2006»
14 years 9 months ago
Large-scale data exploration with the hierarchically growing hyperbolic SOM
We introduce the Hierarchically Growing Hyperbolic Self-Organizing Map (H2 SOM) featuring two extensions of the HSOM (hyperbolic SOM): (i) a hierarchically growing variant that al...
Jörg Ontrup, Helge Ritter
CSMR
2009
IEEE
15 years 2 months ago
Application of TreeNet in Predicting Object-Oriented Software Maintainability: A Comparative Study
There is an increasing interest in more accurate prediction of software maintainability in order to better manage and control software maintenance. Recently, TreeNet has been prop...
Mahmoud O. Elish, Karim O. Elish