Sciweavers

ESANN
2000
13 years 5 months ago
The K.U.Leuven competition data: a challenge for advanced neural network techniques
In this paper we shortly discuss the K.U. Leuven time-series prediction competition, which has been held in the framework of the International Workshop on Advanced Black-Box Techni...
Johan A. K. Suykens, Joos Vandewalle
ESANN
2000
13 years 5 months ago
A new information criterion for the selection of subspace models
The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. In this paper, we propose a new criterion ...
Masashi Sugiyama, Hidemitsu Ogawa
ESANN
2000
13 years 5 months ago
Support Vector Committee Machines
Abstract. This paper proposes a mathematical programming framew ork for combining SVMs with possibly di erent kernels. Compared to single SVMs, the advantage of this approach is tw...
Dominique Martinez, Gilles Millerioux
ESANN
2000
13 years 5 months ago
A neural network architecture for automatic segmentation of fluorescence micrographs
A system for the automatic segmentation of fluorescence micrographs is presented. In a first step positions of fluorescent cells are detected by a fast learning neural network, whi...
Tim W. Nattkemper, Heiko Wersing, Walter Schubert,...
ESANN
2000
13 years 5 months ago
Nonlinear prediction of spatio-temporal time series
Abstract. A prediction scheme for spatio-temporal time series is presented that is based on reconstructed local states. As a numerical example the ev olution of a Kuramoto-Sivashin...
Ulrich Parlitz, Christian Merkwirth
ESANN
2000
13 years 5 months ago
Confidence estimation methods for neural networks : a practical comparison
Feed-forward neural networks (Multi-Layered Perceptrons) are used widely in real-world regression or classification tasks. A reliable and practical measure of prediction "conf...
Georgios Papadopoulos, Peter J. Edwards, Alan F. M...
ESANN
2000
13 years 5 months ago
Learning VOR-like stabilization reflexes in robots
We present a binocular robot that learns compensatory camera movements for image stabilization purposes. Most essential in achieving satisfactory image stabilization performance i...
Francesco Panerai, Giorgio Metta, Giulio Sandini
ESANN
2000
13 years 5 months ago
Quantum iterative algorithm for image reconstruction problems
Iterative algorithm based on quantum tunneling is proposed by making use of mean- eld approximation. W e apply our method to the problem of BW image reconstruction (IR). Its perfor...
Jun-ichi Inoue
ESANN
2000
13 years 5 months ago
Distributed clustering and local regression for knowledge discovery in multiple spatial databases
Many large -scale spatial data analysis problems involve an investigation of relationships in heterogeneous databases. In such situations, instead of making predictions uniformly a...
Aleksandar Lazarevic, Dragoljub Pokrajac, Zoran Ob...