Sciweavers

323 search results - page 3 / 65
» Effective Training Methods for Function Localization Neural ...
Sort
View
IJCNN
2008
IEEE
14 years 19 days ago
Biologically realizable reward-modulated hebbian training for spiking neural networks
— Spiking neural networks have been shown capable of simulating sigmoidal artificial neural networks providing promising evidence that they too are universal function approximat...
Silvia Ferrari, Bhavesh Mehta, Gianluca Di Muro, A...
ICANN
2003
Springer
13 years 11 months ago
Unsupervised Learning of a Kinematic Arm Model
Abstract. An abstract recurrent neural network trained by an unsupervised method is applied to the kinematic control of a robot arm. The network is a novel extension of the Neural ...
Heiko Hoffmann, Ralf Möller
GECCO
2005
Springer
155views Optimization» more  GECCO 2005»
13 years 11 months ago
A pareto archive evolutionary strategy based radial basis function neural network training algorithm for failure rate prediction
This paper outlines a radial basis function neural network approach to predict the failures in overhead distribution lines of power delivery systems. The RBF networks are trained ...
Grant Cochenour, Jerad Simon, Sanjoy Das, Anil Pah...
ICONIP
2008
13 years 7 months ago
On Node-Fault-Injection Training of an RBF Network
Abstract. While injecting fault during training has long been demonstrated as an effective method to improve fault tolerance of a neural network, not much theoretical work has been...
John Sum, Chi-Sing Leung, Kevin Ho
EOR
2006
73views more  EOR 2006»
13 years 6 months ago
Path relinking and GRG for artificial neural networks
Artificial neural networks (ANN) have been widely used for both classification and prediction. This paper is focused on the prediction problem in which an unknown function is appr...
Abdellah El-Fallahi, Rafael Martí, Leon S. ...