Sciweavers

ESANN
2006
13 years 6 months ago
Rotation-based ensembles of RBF networks
Abstract. Ensemble methods allow to improve the accuracy of classification methods. This work considers the application of one of these methods, named Rotation-based, when the clas...
Juan José Rodríguez, Jesús Ma...
ESANN
2006
13 years 6 months ago
Hierarchical analysis of GSM network performance data
In this study, a method for hierarchical examination and visualization of GSM data using the Self-Organizing Map (SOM) is described. The data is examined in few phases. At first te...
Mikko Multanen, Kimmo Raivio, Pasi Lehtimäki
ESANN
2006
13 years 6 months ago
Learning and discrimination through STDP in a top-down modulated associative memory
Abstract. This article underlines the learning and discrimination capabilities of a model of associative memory based on artificial networks of spiking neurons. Inspired from neuro...
Anthony Mouraud, Hélène Paugam-Moisy
ESANN
2006
13 years 6 months ago
Bayesian source separation: beyond PCA and ICA
Blind source separation (BSS) has become one of the major signal and image processing area in many applications. Principal component analysis (PCA) and Independent component analys...
Ali Mohammad-Djafari
ESANN
2006
13 years 6 months ago
An algorithm for fast and reliable ESOM learning
The training of Emergent Self-organizing Maps (ESOM ) with large datasets can be a computationally demanding task. Batch learning may be used to speed up training. It is demonstrat...
Mario Nöcker, Fabian Mörchen, Alfred Ult...
ESANN
2006
13 years 6 months ago
Generalization properties of spiking neurons trained with ReSuMe method
In this paper we demonstrate the generalization property of spiking neurons trained with ReSuMe method. We show in a set of experiments that the learning neuron can approximate the...
Filip Ponulak, Andrzej J. Kasinski
ESANN
2006
13 years 6 months ago
Cluster detection algorithm in neural networks
Complex networks have received much attention in the last few years, and reveal global properties of interacting systems in domains like biology, social sciences and technology. O...
David Meunier, Hélène Paugam-Moisy
ESANN
2006
13 years 6 months ago
Learning Visual Invariance
Invariance is a necessary feature of a visual system able to recognize real objects in all their possible appearance. It is also the processing step most problematic to understand ...
Alessio Plebe
ESANN
2006
13 years 6 months ago
Using Regression Error Characteristic Curves for Model Selection in Ensembles of Neural Networks
Regression Error Characteristic (REC) analysis is a technique for evaluation and comparison of regression models that facilitates the visualization of the performance of many regre...
Aloísio Carlos de Pina, Gerson Zaverucha
ESANN
2006
13 years 6 months ago
Discriminacy of the minimum range approach to blind separation of bounded sources
The Blind Source Separation (BSS) problem is often solved by maximizing objective functions reflecting the statistical dependency between outputs. Since global maximization may be ...
Dinh-Tuan Pham, Frédéric Vrins