Sciweavers

4096 search results - page 385 / 820
» Fibring Neural Networks
Sort
View
ESANN
2003
15 years 8 months 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
NN
2002
Springer
115views Neural Networks» more  NN 2002»
15 years 6 months ago
A self-organising network that grows when required
The ability to grow extra nodes is a potentially useful facility for a self-organising neural network. A network that can add nodes into its map space can approximate the input sp...
Stephen Marsland, Jonathan Shapiro, Ulrich Nehmzow
ICPR
2006
IEEE
16 years 8 months ago
Rotation-Invariant Neoperceptron
Approaches based on local features and descriptors are increasingly used for the task of object recognition due to their robustness with regard to occlusions and geometrical defor...
Beat Fasel, Daniel Gatica-Perez
CEC
2009
IEEE
16 years 1 months ago
Lamarckian neuroevolution for visual control in the Quake II environment
Abstract— A combination of backpropagation and neuroevolution is used to train a neural network visual controller for agents in the Quake II environment. The agents must learn to...
Matt Parker, Bobby D. Bryant
IWANN
2007
Springer
16 years 28 days ago
A Comparison Between ANN Generation and Training Methods and Their Development by Means of Graph Evolution: 2 Sample Problems
Abstract. This paper presents a study in which a new technique for automatically developing Artificial Neural Networks (ANNs) by means of Evolutionary Computation (EC) tools is com...
Daniel Rivero, Julian Dorado, Juan R. Rabuñ...