Table of Contents ▸ List of Commands ▸ Neural Networks ▸ nn_fcnnl | ◀ nn_fcnl | nn_init ▶ |
nn_fcnnl
Arguments:
- out,in,nb_channels>0,_activation,_learning_mode,_regularization>=0,_initialization
Description:
Add a fcnnl layer (fully connected layer followed by a normalization layer, then a non-linearity) to the current network.learning_mode can be { 0:No learning | 1:Weights only | 2:Biases only | 3:Weights+biases }.
initialization can be { 0:Zero | 1:Identity | 2:Lecun-initialization | 3:He-initialization }.
Default values:
activation=leakyrelu, learning_mode=3, regularization=0 and initialization=2.