Two Neural Network Construction Methods.

Autor: Thimm, G., Fiesler, E.
Zdroj: Neural Processing Letters; Aug1997, Vol. 6 Issue 1/2, p25-31, 7p
Abstrakt: Two low complexity methods for neural network construction, that are applicable to various neural network models, are introduced and evaluated for high order perceptrons. The methods are based on a Boolean approximation of real-valued data. This approximation is used to construct an initial neural network topology which is subsequently trained on the original (real-valued) data. The methods are evaluated for their effectiveness in reducing the network size and increasing the network's generalization capabilities in comparison to fully connected high order perceptrons. [ABSTRACT FROM AUTHOR]
Databáze: Complementary Index
Externí odkaz: