R Deep Learning Cookbook

How to do it...

This section covers detailed the steps for setting up the DRBM model using TensorFlow in R:

1. Define the parameters for the DRBM:

learning_rate = 0.005momentum = 0.005minbatch_size = 25hidden_layers = c(400,100)biases = list(-1,-1)

2. Define a sigmoid function using a hyperbolic arc tangent [(log(1+x) -log(1-x))/2]:

arcsigm <- function(x){return(atanh((2*x)-1)*2)}

3. Define a sigmoid function using only a hyperbolic tangent [(e^x-e^-x)/(e^x+e^-x)]:

sigm <- function(x){return(tanh((x/2)+1)/2)}

4. Define a binarize function to return a matrix of binary values (0,1):

binarize <- function(x){# truncated rnormtrnrom <- function(n, mean, sd, minval = -Inf, maxval = Inf){qnorm(runif(n, pnorm(minval, mean, sd), pnorm(maxval, mean, ...