Sciweavers

ESANN
2003
14 years 28 days ago
Approximation of Function by Adaptively Growing Radial Basis Function Neural Networks
In this paper a neural network for approximating function is described. The activation functions of the hidden nodes are the Radial Basis Functions (RBF) whose parameters are learn...
Jianyu Li, Siwei Luo, Yingjian Qi
ESANN
2003
14 years 28 days ago
RetinotopicNET: An Efficient Simulator for Retinotopic Visual Architectures
: -RetinotopicNET is an efficient simulator for neural networks with retinotopic-like receptive fields. The system has two main characteristics: it is event-driven and it takes adv...
Raul Cristian Muresan
ESANN
2003
14 years 28 days ago
Locally Linear Embedding versus Isotop
Abstract. Recently, a new method intended to realize conformal mappings has been published. Called Locally Linear Embedding (LLE), this method can map high-dimensional data lying o...
John Aldo Lee, Cédric Archambeau, Michel Ve...
ESANN
2003
14 years 28 days ago
Autonomous learning algorithm for fully connected recurrent networks
In this paper fully connected RTRL neural networks are studied. In order to learn dynamical behaviours of linear-processes or to predict time series, an autonomous learning algori...
Edouard Leclercq, Fabrice Druaux, Dimitri Lefebvre
ESANN
2003
14 years 28 days ago
Robust Vector Quantization for Burst Error Channels Using Genetic Algorithm
This paper presents a novel vector quantizer (VQ) design algorithm for a burst error channel (BEC). The algorithm minimizes the average distortion when the BEC is in normal state o...
Wen-Jyi Hwang, Chien-Min Ou, Chin-Ming Yeh
ESANN
2003
14 years 28 days ago
Searching optimal feature subset using mutual information
A novel feature selection methodology is proposed with the concept of mutual information. The proposed methodology effectively circumvents two major problems in feature selection ...
D. Huang, Tommy W. S. Chow
ESANN
2003
14 years 28 days ago
Kernel PLS variants for regression
Abstract. We focus on covariance criteria for finding a suitable subspace for regression in a reproducing kernel Hilbert space: kernel principal component analysis, kernel partial...
Luc Hoegaerts, Johan A. K. Suykens, Joos Vandewall...
ESANN
2003
14 years 28 days ago
Ensemble Methods for Multilayer Feedforward
Training an ensemble of networks is an interesting way to improve the performance with respect to a single network. However there are several method to construct the ensemble and t...
Carlos Hernández-Espinosa, Mercedes Fern&aa...
ESANN
2003
14 years 28 days ago
A new rule extraction algorithm based on interval arithmetic
In this paper we propose a new algorithm for rule extraction from a trained Multilayer Feedforward network. The algorithm is based on an interval arithmetic network inversion for p...
Carlos Hernández-Espinosa, Mercedes Fern&aa...
ESANN
2003
14 years 28 days ago
Neural networks organizations to learn complex robotic functions
Abstract. This paper considers the general problem of function estimation with a modular approach of neural computing. We propose to use functionally independent subnetworks to lea...
Gilles Hermann, Patrice Wira, Jean-Philippe Urban