Sciweavers

ESANN
2008
13 years 11 months ago
Homogeneous bipartition based on multidimensional ranking
We present an algorithm which partitions a data set in two parts with equal size and experimentally nearly the same distribution measured through the likelihood of a Parzen kernel ...
Michaël Aupetit
ESANN
2008
13 years 11 months ago
Petri nets design based on neural networks
Petri net faulty models are useful for reliability analysis and fault diagnosis of discrete event systems. Such models are difficult to work out as long as they must be computed ac...
Edouard Leclercq, Souleiman Ould el Medhi, Dimitri...
ESANN
2008
13 years 11 months ago
Using graph-theoretic measures to predict the performance of associative memory models
We test a selection of associative memory models built with different connection strategies, exploring the relationship between the structural properties of each network and its pa...
Lee Calcraft, Rod Adams, Weiliang Chen, Neil Davey
ESANN
2008
13 years 11 months ago
Rank-based quality assessment of nonlinear dimensionality reduction
Abstract. Nonlinear dimensionality reduction aims at providing lowdimensional representions of high-dimensional data sets. Many new methods have been proposed in the recent years, ...
John Aldo Lee, Michel Verleysen
ESANN
2008
13 years 11 months ago
An emphasized target smoothing procedure to improve MLP classifiers performance
Standard learning procedures are better fitted to estimation than to classification problems, and focusing the training on appropriate samples provides performance advantages in cl...
Soufiane El Jelali, Abdelouahid Lyhyaoui, An&iacut...
ESANN
2008
13 years 11 months ago
The gamma cycle and its role in the formation of assemblies
Rhythmic synchronization of activated neural groups in the gamma-frequency range (30-100 Hz) is observed in many brain regions. Interneuron networks are key to the generation of th...
Thomas Burwick
ESANN
2008
13 years 11 months ago
On related violating pairs for working set selection in SMO algorithms
Sequential Minimal Optimization (SMO) is currently the most popular algorithm to solve large quadratic programs for Support Vector Machine (SVM) training. For many variants of this...
Tobias Glasmachers
ESANN
2008
13 years 11 months ago
Computationally Efficient Neural Field Dynamics
We propose a modification of the dynamic neural field model of Amari [1], aiming at reducing the simulation effort by employing spaceand frequency representations of the dynamic st...
Alexander Gepperth, Jannik Fritsch, Christian Goer...
ESANN
2008
13 years 11 months ago
An FPGA-based model suitable for evolution and development of spiking neural networks
We propose a digital neuron model suitable for evolving and growing heterogeneous spiking neural networks on FPGAs using a piecewise linear approximation of the Quadratic Integrate...
Hooman Shayani, Peter J. Bentley, Andrew M. Tyrrel...
ESANN
2008
13 years 11 months ago
Pruning and Regularisation in Reservoir Computing: a First Insight
Reservoir Computing is a new paradigm for using Recurrent Neural Networks which shows promising results. However, as the recurrent part is created randomly, it typically needs to b...
Xavier Dutoit, Benjamin Schrauwen, Jan M. Van Camp...