Sciweavers

ESANN
2006
14 years 28 days ago
Non-orthogonal Support Width ICA
Independent Component Analysis (ICA) is a powerful tool with applications in many areas of blind signal processing; however, its key assumption, i.e. the statistical independence o...
John Aldo Lee, Frédéric Vrins, Miche...
ESANN
2006
14 years 28 days ago
Determination of the Mahalanobis matrix using nonparametric noise estimations
In this paper, the problem of an optimal transformation of the input space for function approximation problems is addressed. The transformation is defined determining the Mahalanob...
Amaury Lendasse, Francesco Corona, Jin Hao, Nima R...
ESANN
2006
14 years 28 days ago
Non-linear gating network for the large scale classification model CombNET-II
The linear gating classifier (stem network) of the large scale model CombNET-II has been always the limiting factor which restricts the number of the expert classifiers (branch net...
Mauricio Kugler, Toshiyuki Miyatani, Susumu Kuroya...
ESANN
2006
14 years 28 days ago
Spatial filters for the classification of event-related potentials
Spatial filtering is a widely used dimension reduction method in electroencephalogram based brain-computer interface systems. In this paper a new algorithm is proposed, which learn...
Ulrich Hoffmann, Jean-Marc Vesin, Touradj Ebrahimi
ESANN
2006
14 years 28 days ago
Visual nonlinear discriminant analysis for classifier design
Abstract. We present a new method for analyzing classifiers by visualization, which we call visual nonlinear discriminant analysis. Classifiers that output posterior probabilities ...
Tomoharu Iwata, Kazumi Saito, Naonori Ueda
ESANN
2006
14 years 28 days ago
Connection strategies in neocortical networks
This study considers the impact of different connection strategies in developing neocortical networks. An adequate connectivity is a requisite for synaptogenesis and the developme...
Andreas Herzog, Karsten Kube, Bernd Michaelis, Ana...
ESANN
2006
14 years 28 days ago
Random Forests Feature Selection with K-PLS: Detecting Ischemia from Magnetocardiograms
Random Forests were introduced by Breiman for feature (variable) selection and improved predictions for decision tree models. The resulting model is often superior to AdaBoost and ...
Long Han, Mark J. Embrechts, Boleslaw K. Szymanski...
ESANN
2006
14 years 28 days ago
Variants of Unsupervised Kernel Regression: General cost functions
We present an extension to a recent method for learning of nonlinear manifolds, which allows to incorporate general cost functions. We focus on the -insensitive loss and visually d...
Stefan Klanke, Helge Ritter
ESANN
2006
14 years 28 days ago
Magnification control for batch neural gas
Neural gas (NG) constitutes a very robust clustering algorithm which can be derived as stochastic gradient descent from a cost function closely connected to the quantization error...
Barbara Hammer, Alexander Hasenfuss, Thomas Villma...