generateWeightsUniform: Generates a weight matrix using runif

In darch: Package for Deep Architectures and Restricted Boltzmann Machines

Description

This function is used to generate random weights and biases using runif.

Usage

generateWeightsUniform(numUnits1, numUnits2,
  weights.min = getParameter(".weights.min", -0.1, ...),
  weights.max = getParameter(".weights.max", 0.1, ...), ...)

Arguments

numUnits1	Number of units in the lower layer.
numUnits2	Number of units in the upper layer.
weights.min	min parameter to the runif function.
weights.max	max parameter to the runif function.
...	Additional parameters, used for parameter resolution.

Value

Weight matrix.

See Also

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

Examples

## Not run: 
data(iris)
model <- darch(Species ~ ., iris, generateWeightsFunction = "generateWeightsUniform",
 weights.min = -.1, weights.max = .5)

## End(Not run)

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