A regularization term to avoid the saturation of the sigmoids in multilayer neural networks
In this paper we propose a new method to prevent the saturation of any set of hidden units of a multilayer neural network. This method is implemented by adding a regularization term to the standard quadratic error function, which is based on a repulsive action between pairs of patterns.
Serra-Ricart, M. et al.
Fecha de publicación:
7
1996
Número de citas
0