NPL
2000
13 years 4 months ago
2000
Thispaper proposes anew version ofa method (G-Prop, geneticbackpropagation) that attempts to solve the problem of
IJON
2000
13 years 4 months ago
2000
A general problem in model selection is to obtain the right parameters that make a model "t observed data. For a multilayer perceptron (MLP) trained with back-propagation (BP...
TNN
2008
13 years 4 months ago
2008
In this paper, it is found that the weights of a perceptron are bounded for all initial weights if there exists a nonempty set of initial weights that the weights of the perceptron...
EUROGP
2004
Springer
13 years 8 months ago
2004
Springer
Abstract. In this paper we conduct a comparative study between hybrid methods to optimize multilayer perceptrons: a model that optimizes the architecture and initial weights of mul...