Sciweavers

ESANN
2006
14 years 28 days ago
LS-SVM functional network for time series prediction
Usually time series prediction is done with regularly sampled data. In practice, however, the data available may be irregularly sampled. In this case the conventional prediction me...
Tuomas Kärnä, Fabrice Rossi, Amaury Lend...
ESANN
2006
14 years 28 days ago
Independent dynamics subspace analysis
Abstract. The paper presents an algorithm for identifying the independent subspace analysis model based on source dynamics. We propose to separate subspaces by decoupling their dyn...
Alexander Ilin
ESANN
2006
14 years 28 days ago
Extended model of conditioned learning within latent inhibition
Due to the various and dynamic nature of stimuli, decisions of intelligent agents must rely on the coordination of complex cognitive systems. This paper precisely focusses on a gen...
Nicolas Gomond, Jean Marc Salotti
ESANN
2006
14 years 28 days ago
Classification by means of Evolutionary Response Surfaces
Abstract. Response surfaces are a powerful tool for both classification and regression as they are able to model many different phenomena and construct complex boundaries between c...
Rafael del Castillo Gomariz, Nicolás Garc&i...
ESANN
2006
14 years 28 days ago
Degeneracy in model selection for SVMs with radial Gaussian kernel
We consider the model selection problem for support vector machines applied to binary classification. As the data generating process is unknown, we have to rely on heuristics as mo...
Tobias Glasmachers
ESANN
2006
14 years 28 days ago
Designing neural network committees by combining boosting ensembles
The use of modified Real Adaboost ensembles by applying weighted emphasis on erroneous and critical (near the classification boundary) has been shown to lead to improved designs, ...
Vanessa Gómez-Verdejo, Aníbal R. Fig...
ESANN
2006
14 years 28 days ago
FPGA implementation of an integrate-and-fire LEGION model for image segmentation
Abstract. Despite several previous studies, little progress has been made in building successful neural systems for image segmentation in digital hardware. Spiking neural networks ...
Bernard Girau, Cesar Torres-Huitzil
ESANN
2006
14 years 28 days ago
Visual object classification by sparse convolutional neural networks
Abstract. A convolutional network architecture termed sparse convolutional neural network (SCNN) is proposed and tested on a real-world classification task (car classification). In...
Alexander Gepperth
ESANN
2006
14 years 28 days ago
Topological Correlation
Quantifying the success of the topographic preservation achieved with a neural map is difficult. In this paper we present Topological Correlation, Tc, a method that assesses the de...
Kevin Doherty, Rod Adams, Neil Davey
ESANN
2006
14 years 28 days ago
Learning for stochastic dynamic programming
Abstract. We present experimental results about learning function values (i.e. Bellman values) in stochastic dynamic programming (SDP). All results come from openDP (opendp.sourcef...
Sylvain Gelly, Jérémie Mary, Olivier...