TensorFlow 1.x Deep Learning Cookbook

How to do it...

We proceed with the recipe as follows:

1. Import the modules:

import tensorflow as tfimport numpy as npfrom tensorflow.examples.tutorials.mnist import input_dataimport matplotlib.pyplot as plt%matplotlib inline

2. Declare the class RBM, which will do the major task. The __init__ will build the complete graph, forward and backward pass, and the objective function; we will use the TensorFlow built-in optimizer to update the weights and biases:

class RBM(object):    def __init__(self, m, n):        """        m: Number of neurons in visible layer        n: number of neurons in hidden layer        """        self._m = m        self._n = n        # Create the Computational graph        # Weights and biases        self._W = tf.Variable(tf.random_normal(shape=(self._m,self._n))) self._c = tf.Variable(np.zeros(self._n).astype(np.float32)) ...