Sciweavers

ESANN
2006
13 years 8 months ago
Immune Network based Ensembles
This paper presents a new method for constructing ensembles of classifiers based on immune network theory, one of the most interesting paradigms within the field of artificial imm...
Nicolás García-Pedrajas, Colin Fyfe
ESANN
2006
13 years 8 months ago
Reducing policy degradation in neuro-dynamic programming
We focus on neuro-dynamic programming methods to learn state-action value functions and outline some of the inherent problems to be faced, when performing reinforcement learning in...
Thomas Gabel, Martin Riedmiller
ESANN
2006
13 years 8 months ago
Stochastic Processes for Canonical Correlation Analysis
We consider two stochastic process methods for performing canonical correlation analysis (CCA). The first uses a Gaussian Process formulation of regression in which we use the cur...
Colin Fyfe, Gayle Leen
ESANN
2006
13 years 8 months ago
Robust Local Cluster Neural Networks
Abstract. Artificial neural networks are intended to be used in future nanoelectronics since their biological examples seem to be robust to noise. In this paper, we analyze the rob...
Ralf Eickhoff, Joaquin Sitte, Ulrich Rückert
ESANN
2006
13 years 8 months ago
The permutation test for feature selection by mutual information
Damien François, Vincent Wertz, Michel Verl...
ESANN
2006
13 years 8 months ago
Nonlinear transient computation and variable noise tolerance
A novel nonlinear transient computation device is presented which is designed to perform computations on multiple spike-train input signals. The input signals perturb the internal ...
Nigel Crook
ESANN
2006
13 years 8 months ago
Saliency extraction with a distributed spiking neural network
We present a distributed spiking neuron network (SNN) for handling low-level visual perception in order to extract salient locations in robot camera images. We describe a new metho...
Sylvain Chevallier, Philippe Tarroux, Hél&e...
ESANN
2006
13 years 8 months ago
Diversity creation in local search for the evolution of neural network ensembles
Abstract. The EENCL algorithm [1] automatically designs neural network ensembles for classification, combining global evolution with local search based on gradient descent. Two mec...
Pete Duell, Iris Fermin, Xin Yao
ESANN
2006
13 years 8 months ago
A multiagent architecture for concurrent reinforcement learning
In this paper we propose a multiagent architecture for implementing concurrent reinforcement learning, an approach where several agents, sharing the same environment, perceptions ...
Victor Uc Cetina