Results
repositories = "DIAL - Dépôt Institutionnel de l'Académie Louvain"
> : "UCL - FSA/INMA - Département d'ingénierie mathématique"
(x)
A data-driven functional projection approach for the selection of feature ranges in spectra with ICA or cluster analysis
Description :
Prediction problems from spectra are largely encountered in chemometry. In addition to accurate predictions, it is often needed to extract information about which wavelengths in the spectra contribute in an effective way to the quality of the prediction. This implies to select wavelengths (or wavele...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
Vector quantization: a weighted version for time-series forecasting
Author(s) :
Lendasse, A.
,
Francois, Damien
,
Wertz, Vincent
,
Verleysen, Michel
,
International Conference on Computational Sciences
Description :
Nonlinear time-series prediction offers potential performance increases compared to linear models. Nevertheless, the enhanced complexity and computation time often prohibits an efficient use of nonlinear tools. In this paper, we present a simple nonlinear procedure for time-series forecasting, based...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
Fast bootstrap methodology for regression model selection
Author(s) :
Lendasse, A.
,
Simon, Geoffroy
,
Wertz, Vincent
,
Verleysen, Michel
,
12th European Symposium on Artificial Neural Networks (ESANN)
Description :
Using resampling methods like cross-validation and bootstrap is a necessity in neural network design, for solving the problem of model structure selection. The bootstrap is a powerful method offering a low variance of the model generalization error estimate. Unfortunately, its computational load may...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
On the effects of dimensionality on data analysis with neural networks
Author(s) :
Verleysen, Michel
,
Francois, Damien
,
Simon, Geoffroy
,
Wertz, Vincent
,
7th International Work Conference on Artificial and Natural Neural Networks
Description :
Modem data analysis often faces high-dimensional data. Nevertheless, most neural network data analysis tools are not adapted to high-dimensional spaces, because of the use of conventional concepts (as the Euclidean distance) that scale poorly with dimension. This paper shows some limitations of such...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
Nonlinear time series prediction by weighted vector quantization
Author(s) :
Lendasse, A.
,
Francois, Damien
,
Wertz, Vincent
,
Verleysen, Michel
,
International Conference on Computational Science (ICCS 2003)
Description :
Classical nonlinear models for time series prediction exhibit improved capabilities compared to linear ones. Nonlinear regression has however drawbacks, such as overfitting and local minima problems, user-adjusted parameters, higher computation times, etc. There is thus a need for simple nonlinear m...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
Advances in Feature Selection with Mutual Information
Description :
The selection of features that are relevant for a prediction or classification problem is an important problem in many domains involving high-dimensional data. Selecting features helps fighting the curse of dimensionality, improving the performances of prediction or classification methods, and inter...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
Undetermined
Direct evidence for a position input to the smooth pursuit system.
Description :
When objects move in our environment, the orientation of the visual axis in space requires the coordination of two types of eye movements: saccades and smooth pursuit. The principal input to the saccadic system is position error, whereas it is velocity error for the smooth pursuit system. Recently, ...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
Properties of saccades in Duane retraction syndrome.
Description :
PURPOSE: To improve understanding of the binocular control of saccades by making high-resolution eye movement recordings in patients with unilateral Duane retraction syndrome (DRS) type I (marked by congenital absence of the sixth cranial nerve). METHODS: Binocular eye movements were recorded in fou...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
Asynchrony between position and motion signals in the saccadic system.
Description :
The influence of position and motion signals on saccades was studied in two dimensions (2D) using a double step-ramp paradigm. We showed the presence of a predictive component in 2D catch-up saccade programming that is based on motion signals and influences both saccade amplitude and orientation. In...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English
A model that integrates eye velocity commands to keep track of smooth eye displacements.
Description :
Past results have reported conflicting findings on the oculomotor system's ability to keep track of smooth eye movements in darkness. Whereas some results indicate that saccades cannot compensate for smooth eye displacements, others report that memory-guided saccades during smooth pursuit are spatia...
Repository :
DIAL - Dépôt Institutionnel de l'Académie Louvain
Language(s) :
English