Sciweavers

ESANN
1998
13 years 6 months ago
A neural approach to a sensor fusion problem
Our problem concerns the joint interpretation of UltraSonic and InfraRed measurements provided by a composite proximity sensor, in order to extract geometrical and morphological f...
Valentina Colla, Mirko Sgarbi, Leonardo Maria Reyn...
ESANN
1998
13 years 6 months ago
Wavelet interpolation networks
We describe a new approach to real time learning of unknown functions based on an interpolating wavelet estimation. We choose a subfamily of a wavelet basis relying on nested hiera...
Christophe P. Bernard, Stéphane Mallat, Jea...
ESANN
1998
13 years 6 months ago
Lazy learning for control design
This paper presents two local methods for the control of discrete-time unknown nonlinear dynamical systems, when only a limited amount of input-output data is available. The modeli...
Gianluca Bontempi, Mauro Birattari, Hugues Bersini
ESANN
2003
13 years 6 months ago
A recognition of filaments in solar images with an artificial neural network
A new technique based on the Artificial Neural Network (ANN) was developed for an automated recognition of solar filaments, dark elongated features visible in the hydrogen H-alpha ...
Valentina V. Zharkova, Vitaly Schetinin
ESANN
2003
13 years 6 months ago
Developmental pruning of synapses and category learning
After an initial peak, the number of synapses in mammalian cerebral cortex decreases in the formative period and throughout adult life. However, if synapses are taken to reflect ci...
Roberto Viviani, Manfred Spitzer
ESANN
2003
13 years 6 months ago
Self-Organization by Optimizing Free-Energy
Jakob J. Verbeek, Nikos A. Vlassis, Ben J. A. Kr&o...
ESANN
2003
13 years 6 months ago
Neural assembly binding in linguistic representation
We present a neural architecture of sentence representation. Words are represented with neural cell assemblies. Relations between words are represented with ‘structure’ assembl...
Frank van der Velde, Marc de Kamps
ESANN
2003
13 years 6 months ago
Fast approximation of the bootstrap for model selection
The bootstrap resampling method may be efficiently used to estimate the generalization error of a family of nonlinear regression models, as artificial neural networks. The main dif...
Geoffroy Simon, Amaury Lendasse, Vincent Wertz, Mi...
ESANN
2003
13 years 6 months ago
On the weight dynamics of recurrent learning
We derive continuous-time batch and online versions of the recently introduced efficient O(N2 ) training algorithm of Atiya and Parlos [2000] for fully recurrent networks. A mathem...
Ulf D. Schiller, Jochen J. Steil