TensorFlow 1.x Deep Learning Cookbook

How to do it...

We proceed with the recipe as follows:

1. As always, we start with importing the necessary modules:

import tensorflow as tfimport numpy as npimport matplotlib.pyplot as plt%matplotlib inline

2. Next, we declare a class, WTU, which will perform all the tasks. The class is instantiated with m x n the size of the 2D SOM lattice, dim the number of dimensions in the input data, and the total number of iterations:

def __init__(self, m, n, dim, num_iterations, eta = 0.5, sigma = None):    """    m x n : The dimension of 2D lattice in which neurons are     arranged    dim : Dimension of input training data    num_iterations: Total number of training iterations    eta : Learning rate    sigma: The radius of neighbourhood function.    """    self._m = m self._n ...