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

In SAENET: A Stacked Autoencoder Implementation with Interface to 'neuralnet'

Description

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

Usage

SAENET.nnet(h, X.train, target, nn.control = NULL)

Arguments

h	The object returned from SAENET.train()
X.train	A matrix of training data.
target	A vector of target values. If given as a factor, classification will be performed, otherwise if an integer or numeric vector is given neuralnet() will default to regression
nn.control	A named list with elements to be passed as control parameters to neuralnet(). Package defaults used if no values entered.

Value

An object of class nn which can be used with the neuralnet package as normal

SAENET documentation built on May 30, 2017, 1:51 a.m.