Here is how we proceed with the single layer perceptron:

1. Import the modules needed:

import tensorflow as tf 
import numpy as np 
 

2. Define the hyperparameters to be used:

# Hyper parameters 
eta = 0.4  # learning rate parameter 
epsilon = 1e-03 # minimum accepted error 
max_epochs = 100 # Maximum Epochs 
 

3. Define the threshold function:

# Threshold Activation function 
def threshold (x): 
    cond = tf.less(x, tf.zeros(tf.shape(x), dtype = x.dtype)) 
    out = tf.where(cond, tf.zeros(tf.shape(x)), tf.ones(tf.shape(x))) 
    return out 

4. Specify the training data. In this example, we take a three input neuron (A,B,C) and train it to learn the logic AB + BC:

# Training Data  Y = AB + BC, sum of two linear functions. 
T, F = 1., 0. 
X_in = [ 
    [T, T, T, T], 
    [T, T, F, T], 
    [T, F, T, T], 
    [T, F, F, T], 
    [F, T, T, T], 
    [F, T, F, T], 
    [F, F, T, T], 
    [F, F, F, T], 
    ] 
Y = [ 
    [T], 
    [T], 
    [F], 
    [F], 
    [T], 
    [F], 
    [F], 
    [F] 
] 
 

5. Define the variables to be used, the computational graph to compute updates, and finally, execute the computational graph:

W = tf.Variable(tf.random_normal([4,1], stddev=2, seed = 0)) 
h = tf.matmul(X_in, W)  
Y_hat = threshold(h) 
error = Y - Y_hat 
mean_error = tf.reduce_mean(tf.square(error)) 
dW =  eta * tf.matmul(X_in, error, transpose_a=True) 
train = tf.assign(W, W+dW) 
init = tf.global_variables_initializer() 
err = 1 
epoch = 0 
with tf.Session() as sess: 
    sess.run(init) 
    while err > epsilon and epoch < max_epochs: 
        epoch += 1 
        err, _ = sess.run([mean_error, train]) 
        print('epoch: {0}  mean error: {1}'.format(epoch, err)) 
         
    print('Training complete') 

The following is the output of the preceding code: