Simple logical function in neural network using tensorflow.

simple_tensorflow.py

import numpy as np
import tensorflow as tf

x = tf.placeholder("float", [None, 2], name="X")
y = tf.placeholder("float", [None, 1], name="Y")

w = tf.Variable(tf.random_normal([2, 1], stddev=0.01), tf.float32)
b = tf.Variable(tf.random_normal([1]))

linear_model = tf.matmul(x, w) + b

loss = tf.reduce_sum(tf.square(linear_model - y))
optimizer = tf.train.GradientDescentOptimizer(0.01).minimize(loss)

init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)

x_train = [[0, 0], [0, 1], [1, 0], [1, 1]]
y_train = [[0], [0], [0], [1]]

for i in range(100):
  sess.run(optimizer, {x:x_train, y:y_train})

pred = sess.run(linear_model, feed_dict={x: [[1, 1], [1, 0]]})
pred = np.rint(pred).astype(int).T

print(pred)