generateWeightsNormal: Generates a weight matrix using rnorm.

In darch: Package for Deep Architectures and Restricted Boltzmann Machines

Description

This function is the standard method for generating weights for instances of Net. It uses rnorm to do so.

Usage

generateWeightsNormal(numUnits1, numUnits2,
  weights.mean = getParameter(".weights.mean", 0, ...),
  weights.sd = getParameter(".weights.sd", 0.01, ...), ...)

Arguments

numUnits1	Number of units in the lower layer.
numUnits2	Number of units in the upper layer.
weights.mean	mean parameter to the rnorm function.
weights.sd	sd parameter to the rnorm function.
...	Additional parameters, used for parameter resolution.

Value

Weight matrix.

See Also

Other weight generation functions: generateWeightsGlorotNormal, generateWeightsGlorotUniform, generateWeightsHeNormal, generateWeightsHeUniform, generateWeightsUniform

Examples

## Not run: 
data(iris)
model <- darch(Species ~ ., iris, generateWeightsFunction = "generateWeightsNormal",
 weights.mean = .1, weights.sd = .05)

## End(Not run)

darch documentation built on May 29, 2017, 8:14 p.m.