sae.train: Training a Stacked Autoencoder

In DimitriF/DLC: Deep Layer Chromatography

Description

Training a Stacked Autoencoder

Usage

sae.train(x, hidden = c(10), activationfun = "sigm",
  learningrate = 0.8, momentum = 0.5, learningrate_scale = 1,
  output = "sigm", numepochs = 3, batchsize = 100,
  hidden_dropout = 0, visible_dropout = 0.2)

Arguments

x	matrix of x values for examples
hidden	vector for number of units of hidden layers.Default is c(10).
activationfun	activation function of hidden unit.Can be "sigm","linear" or "tanh".Default is "sigm" for logistic function
learningrate	learning rate for gradient descent. Default is 0.8.
momentum	momentum for gradient descent. Default is 0.5 .
learningrate_scale	learning rate will be mutiplied by this scale after every iteration. Default is 1 .
output	function of output unit, can be "sigm","linear" or "softmax". Default is "sigm".
numepochs	number of iteration for samples Default is 3.
batchsize	size of mini-batch. Default is 100.
hidden_dropout	drop out fraction for hidden layer. Default is 0.
visible_dropout	drop out fraction for input layer Default is 0.

Author(s)

Xiao Rong

DimitriF/DLC documentation built on Oct. 14, 2020, 4:33 p.m.