from __future__ import print_function

import tensorflow as tf

# Simple hello world using TensorFlow

# Create a Constant op
# The op is added as a node to the default graph.
#
# The value returned by the constructor represents the output
# of the Constant op.
hello = tf.constant('Hello, TensorFlow!')

# Start tf session
sess = tf.Session()

# Run the op
print(sess.run(hello))

# import tensorflow
import tensorflow as tf

# build computational graph
a = tf.placeholder(tf.int16)
b = tf.placeholder(tf.int16)

addition = tf.add(a, b)

# initialize variables
init = tf.initialize_all_variables()

# create session and run the graph
with tf.Session() as sess:
    sess.run(init)
    print "Addition: %i" % sess.run(addition, feed_dict={a: 2, b: 3})

# close session
sess.close()

T, F = 1., -1.
bias = 1.
train_in = [
    [T, T, bias],
    [T, F, bias],
    [F, T, bias],
    [F, F, bias],
]
train_out = [
    [T],
    [F],
    [F],
    [F],
]
w = tf.Variable(tf.random_normal([3, 1]))

# step(x) = { 1 if x > 0; -1 otherwise }
def step(x):
    is_greater = tf.greater(x, 0)
    as_float = tf.to_float(is_greater)
    doubled = tf.mul(as_float, 2)
    return tf.sub(doubled, 1)

output = step(tf.matmul(train_in, w))   # return 1 or -1
error = tf.sub(train_out, output)       # diff
mse = tf.reduce_mean(tf.square(error))  # mean squared error

delta = tf.matmul(train_in, error, transpose_a=True)
train = tf.assign(w, tf.add(w, delta))

sess = tf.Session()
sess.run(tf.initialize_all_variables())

err, target = 1, 0
epoch, max_epochs = 0, 10
while err > target and epoch < max_epochs:
    epoch += 1
    err, _ = sess.run([mse, train])
    print('epoch:', epoch, 'mse:', err)

• https://matplotlib.org/users/pyplot_tutorial.html
• https://matplotlib.org/mpl_toolkits/mplot3d/tutorial.html
• https://www.analyticsvidhya.com/blog/2016/01/complete-tutorial-learn-data-science-python-scratch-2/
• https://www.tensorflow.org/get_started/get_started