Sciweavers

ESANN
2003
14 years 28 days ago
Self-organizing maps and functional networks for local dynamic modeling
The paper presents a method for times series prediction using a local dynamic modeling based on a three step process. In the first step the input data is embedded in a reconstruct...
Noelia Sánchez-Maroño, Oscar Fontenl...
ESANN
2003
14 years 28 days ago
Cellular topographic self-organization under correlational learning
We consider two layered binary state neural networks in which cellular topographic self-organization occurs under correlational learning. The main result is that for separable inpu...
Shouji Sakamoto, Shigeko Seki, Youichi Kobuchi
ESANN
2003
14 years 28 days ago
Mixture of Experts and Local-Global Neural Networks
- In this paper we investigate mixture of experts problems in the context of Local-Global Neural Networks. This type of architecture was originaly conceived for functional approxim...
Mayte Suárez-Fariñas, Carlos Eduardo...
ESANN
2003
14 years 28 days ago
Unsupervised Recursive Sequence Processing
We propose a self organizing map (SOM) for sequences by extending standard SOM by two features, the recursive update of Sperduti [7] and the hyperbolic neighborhood of Ritter [5]. ...
Marc Strickert, Barbara Hammer
ESANN
2003
14 years 28 days ago
An event-driven framework for the simulation of networks of spiking neurons
We propose an event-driven framework dedicated to the design and the simulation of networks of spiking neurons. It consists stract model of spiking neurons and an efficient event-d...
Olivier Rochel, Dominique Martinez
ESANN
2003
14 years 28 days ago
Neural Network Algorithms for the p-Median Problem
Enrique Domínguez Merino, José Mu&nt...
ESANN
2003
14 years 28 days ago
Neural Net with Two Hidden Layers for Non-Linear Blind Source Separation
In this paper, we present an algorithm that minimizes the mutual information between the outputs of a perceptron with two hidden layers. The neural network is then used as separati...
Rubén Martín-Clemente, Susana Hornil...
ESANN
2003
14 years 28 days ago
Extraction of fuzzy rules from trained neural network using evolutionary algorithm
This paper presents our approach to the rule extraction problem from trained neural network. A method called REX is briefly described. REX acquires a set of fuzzy rules using an ev...
Urszula Markowska-Kaczmar, Wojciech Trelak
ESANN
2003
14 years 28 days ago
Evolved Neurodynamics for Robot Control
Small recurrent neural network with two and three neurons are able to control autonomous robots showing obstacle avoidance and photo-tropic behaviors. They have been generated by e...
Frank Pasemann, Martin Hülse, Keyan Zahedi
ESANN
2003
14 years 28 days ago
Subject Categorization for Web Educational Resources using MLP
Abstract. The purpose of this study is to develop subject categorization methods for educational resources using multilayer perceptron (MLP) and to examine the performance of the t...
Minoru Nakayama, Yasutaka Shimizu