linearUnitRbm: Calculates the linear neuron output no transfer function

In darch: Package for Deep Architectures and Restricted Boltzmann Machines

Description

Calculates the linear neuron output with no transfer function from real value input saved in data.

Usage

linearUnitRbm(rbm, data, biases, weights, runParams,
  matMult = getParameter(".matMult", ...), ...)

Arguments

rbm	A instance of the class RBM.
data	A matrix with the data for the calculations.
biases	The biases for the calculations.
weights	The weight matrix for the calculations.
runParams	Parameters which indicates the status of the training.
matMult	Matrix multiplication function.
...	Additional parameters, used for paramete resolution.

Details

The return value is a list with the output of the neurons as first entry and binary representation calculated through a comparison of the output with random numbers. The random numbers a generated with the function rnorm.

Value

The real value and binary activations for the units

See Also

Other RBM unit functions: sigmoidUnitRbm, tanhUnitRbm

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