darch (version 0.12.0)

runDArchDropout: Forward-propagate data through the network with dropout inference

Description

If dropout was disabled, runDArch will be called instead.

Usage

runDArchDropout(darch, data, inputLayer = 1,
  outputLayer = length(darch@layers), matMult = getParameter(".matMult"),
  dropout = getParameter(".darch.dropout"),
  iterations = getParameter(".darch.dropout.momentMatching"))

Arguments

darch

A instance of the class '>DArch.

data

The input data to execute the darch on.

inputLayer

Into which layer the given data is to be fed. Absolute number starting at 1 for the input layer.

outputLayer

The output of which layer is to be returned, absolute number starting a 0 for the input layer (i.e. pre-processed data is returned).

matMult

Function to use for matrix multiplication.

dropout

Dropout rates for the layers.

iterations

If greater than 0, the numbr of iterations to use for moment matching dropout inference.

Value

The network output.

See Also

darch

Other darch execute functions: runDArch