14898 search results - page 12 / 2980 » Design of Neural Networks |
IJON
2007
13 years 7 months ago
2007
Piecewise linear networks (PLNs) are attractive because they can be trained quickly and provide good performance in many nonlinear approximation problems. Most existing design alg...
FUZZY
1997
Springer
13 years 11 months ago
1997
Springer
Abstract. In this paper, neural networks trained with the back-propagation algorithm are applied to predict the future values of time series that consist of the weekly demand on it...
ESANN
2008
13 years 8 months ago
2008
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...
INFORMATICALT
2007
13 years 7 months ago
2007
The objective of this research is to construct parallel models that simulate the behavior of artificial neural networks. The type of network that is simulated in this project is t...
ESANN
2006
13 years 8 months ago
2006
The use of modified Real Adaboost ensembles by applying weighted emphasis on erroneous and critical (near the classification boundary) has been shown to lead to improved designs, ...