SAENET.nnet

The object returned from <code>SAENET.train()</code>

X.train

A vector of target values. If given as a factor, classification
will be performed, otherwise if an integer or numeric vector is given
<code>neuralnet()</code> will default to regression

target

A named list with elements to be passed as control parameters to <code>neuralnet()</code>. Package defaults used if no values entered.

nn.control


Use a stacked autoencoder to pre-train a feed-forward neural network.


An implementation of a stacked sparse autoencoder for dimension reduction of features and pre-training of feed-forward neural networks
with the 'neuralnet' package is contained within this package. The package also includes a predict function for the stacked autoencoder object to generate the compressed
representation of new data if required. For the purposes of this package, 'stacked' is defined in line with http://ufldl.stanford.edu/wiki/index.php/Stacked_Autoencoders .
The underlying sparse autoencoder is defined in the documentation of 'autoencoder'.

SAENET.nnet: Use a stacked autoencoder to pre-train a feed-forward neural network.

Description

Usage

Arguments

Value