R Deep Learning Cookbook

How to do it...

This section provides the steps for optimizing the error using reconstruction from an RBM:

1. Initialize the current and previous vector of biases and matrices of weights:

cur_w = tf$Variable(tf$zeros(shape = shape(num_input, num_hidden), dtype=tf$float32)) cur_vb = tf$Variable(tf$zeros(shape = shape(num_input), dtype=tf$float32)) cur_hb = tf$Variable(tf$zeros(shape = shape(num_hidden), dtype=tf$float32)) prv_w = tf$Variable(tf$random_normal(shape=shape(num_input, num_hidden), stddev=0.01, dtype=tf$float32)) prv_vb = tf$Variable(tf$zeros(shape = shape(num_input), dtype=tf$float32)) prv_hb = tf$Variable(tf$zeros(shape = shape(num_hidden), dtype=tf$float32)) 

2. Start a new TensorFlow session:

 sess$run(tf$global_variables_initializer()) ...