Sciweavers

ESANN
2003
14 years 28 days ago
Meter value recognition using locally connected hierarchical networks
This paper describes a two-stage system for the recognition ge meter values. A feed-forward Neural Abstraction Pyramid is initialized in an unsupervised manner and trained in a sup...
Sven Behnke
ESANN
2003
14 years 28 days ago
Comparison of neural algorithms for blind source separation in sensor array applications
- A test bed of experiments with real and artificially generated data has been designed to compare the performance of three well-known algorithms for BSS. The main goal of these ex...
Guillermo Bedoya, Sergio Bermejo, Joan Cabestany
ESANN
2003
14 years 28 days ago
VLSI Realization of a Two-Dimensional Hamming Distance Comparator ANN for Image Processing Applications
This paper presents the hardware realization of a Hamming artificial neural network, and demonstrates its use in a high-speed precision alignment system. High degree of parallelism...
Stéphane Badel, Alexandre Schmid, Yusuf Leb...
ESANN
2003
14 years 28 days ago
Robust Topology Representing Networks
Martinetz and Schulten proposed the use of a Competitive Hebbian Learning (CHL) rule to build Topology Representing Networks. From a set of units and a data distribution, a link i...
Michaël Aupetit
ESANN
2003
14 years 28 days ago
High-dimensional labeled data analysis with Gabriel graphs
We propose the use of the Gabriel graph for the exploratory analysis of potentially high dimensional labeled data. Gabriel graph is a subgraph of the Delaunay triangulation, which ...
Michaël Aupetit
ESANN
2003
14 years 28 days ago
On Convergence Problems of the EM Algorithm for Finite Gaussian Mixtures
Efficient probability density function estimation is of primary interest in statistics. A popular approach for achieving this is the use of finite Gaussian mixture models. Based on...
Cédric Archambeau, John Aldo Lee, Michel Ve...
ESANN
2003
14 years 28 days ago
A Fuzzy ARTMAP Probability Estimator with Relevance Factor
Abstract. An incremental, nonparametric probability estimation procedure using a variation of the Fuzzy ARTMAP (FAM) neural network is introduced. The resulted network, called Fuzz...
Razvan Andonie, Lucian Sasu
ESANN
2003
14 years 28 days ago
The hypersphere neuron
In this paper a special higher order neuron, the hypersphere neuron, is introduced. By embedding Euclidean space in a conformal space, hyperspheres can be expressed as vectors. The...
Vladimir Banarer, Christian Perwass, Gerald Sommer
ESANN
2003
14 years 28 days ago
Neural Networks and M5 model trees in modeling water level-discharge relationship for an Indian river
: In flood management it is important to reliably estimate the discharge in a river. Hydrologists use historic data to establish a rating curve – a relationship between the water...
Biswanath Bhattacharya, Dimitri P. Solomatine
ESANN
2001
14 years 28 days ago
A divide-and-conquer learning architecture for predicting unknown motion
Time varying environments or model selection problems lead to crucial dilemmas in identification and control science. In this paper, we propose a modular prediction scheme consisti...
Patrice Wira, Jean-Philippe Urban, Julien Gresser