Sciweavers

ESANN
2004
13 years 6 months ago
Separability of analytic postnonlinear blind source separation with bounded sources
The aim of blind source separation (BSS) is to transform a mixed random vector such that the original sources are recovered. If the sources are assumed to be statistically independ...
Fabian J. Theis, Peter Gruber
ESANN
2004
13 years 6 months ago
Three dimensional frames of reference transformations using gain modulated populations of neurons
This work investigates whether population vector coding could be a principle mechanism for sensorimotor transformations. This paper presents a formal demonstration of how populatio...
Eric L. Sauser, Aude Billard
ESANN
2004
13 years 6 months ago
Soft-computing techniques for time series forecasting
One way to contrast the behaviour of different algorithms in the field of timeseries forecasting is to compare the prediction error using a benchmark problem. Another interesting ...
Ignacio Rojas Ruiz, Héctor Pomares
ESANN
2004
13 years 6 months ago
Regularizing generalization error estimators: a novel approach to robust model selection
Abstract. A well-known result by Stein shows that regularized estimators with small bias often yield better estimates than unbiased estimators. In this paper, we adapt this spirit ...
Masashi Sugiyama, Motoaki Kawanabe, Klaus-Robert M...
ESANN
2004
13 years 6 months ago
Clustering functional data with the SOM algorithm
Abstract. In many situations, high dimensional data can be considered as sampled functions. We show in this paper how to implement a Self-Organizing Map (SOM) on such data by appro...
Fabrice Rossi, Brieuc Conan-Guez, Aïcha El Go...
ESANN
2004
13 years 6 months ago
Self-organizing context learning
This work is designed to contribute to a deeper understanding of the recently proposed Merging SOM (MSOM). Its context model aims at the representation of sequences, an important s...
Marc Strickert, Barbara Hammer
ESANN
2004
13 years 6 months ago
Functional preprocessing for multilayer perceptrons
In many applications, high dimensional input data can be considered as sampled functions. We show in this paper how to use this prior knowledge to implement functional preprocessin...
Fabrice Rossi, Brieuc Conan-Guez
ESANN
2004
13 years 6 months ago
Implementation and coupling of dynamic neurons through optoelectronics
Abstract. In this work we describe experimental results regarding an optoelectronic implementation of a dynamic neuron model. The model is a variation of the FitzHugh-Nagumo equati...
Alexandre R. S. Romariz, Kelvin Wagner
ESANN
2004
13 years 6 months ago
Neural dynamics for task-oriented grouping of communicating agents
Abstract. Many real world problems are given in the form of multiple measurements comprising local descriptions or tasks. We propose that a dynamical organization of a population o...
Jochen J. Steil
ESANN
2004
13 years 6 months ago
Speaker verification by means of ANNs
In text-dependent speaker verification the speech signals have to be time-aligned. For that purpose dynamic time warping (DTW) can be used which performs the alignment by minimizi...
Urs Niesen, Beat Pfister