encode

object

newdata

<p>Logical indicating whether the inputs to the compression
layer should be returned. Mainly used for plotting the activations.</p>

returnInputs

<p>Compress data according to trained replicator or autoencoder.
Outputs are the activations of the nodes in the middle layer for each 
observation in <code>newdata</code></p>

Training of general classification and regression neural networks using
gradient descent. Special features include a function for training replicator
neural networks and a function for training autoencoders. Multiple activation and
cost functions (including Huber and pseudo-Huber) are supported, as well as L1
and L2 regularization, momentum, early stopping and the possibility to specify
a learning rate schedule. The package contains a vectorized gradient descent
implementation which facilitates faster training through batch learning.

encode: Encoding step

Description

Usage

Arguments