A neural network in 9 lines of Python code.

short_version.py

from numpy import exp, array, random, dot
training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])
training_set_outputs = array([[0, 1, 1, 0]]).T
random.seed(1)
synaptic_weights = 2 * random.random((3, 1)) - 1
for iteration in xrange(10000):
    output = 1 / (1 + exp(-(dot(training_set_inputs, synaptic_weights))))
    synaptic_weights += dot(training_set_inputs.T, (training_set_outputs - output) * output * (1 - output))
print 1 / (1 + exp(-(dot(array([1, 0, 0]), synaptic_weights))))

Excellent article, easily more interesting than the last 100 I've read recently. Made my day :) Thanks for writing it up!

Thank you sooooo much for putting in such a small code explaining input, training, synaptic weights and output with the relevant formula. Have gone thru other parts too they are very helpful to understand the working of Deep Learning. Do share your latest work too....

Hello everyone, i am new on Python. I've cloned codes to Atom and started on Terminal, but i got these syntax error, anyone can help me ?

C:\Users\LENOVO\Desktop\Github_Clone_Projects\62fe5dcc581131c96276>short_version.py
File "C:\Users\LENOVO\Desktop\Github_Clone_Projects\62fe5dcc581131c96276\short_version.py", line 9
print 1 / (1 + exp(-(dot(array([1, 0, 0]), synaptic_weights))))
^
SyntaxError: invalid syntax

@rusert
You have to give parenthesis (small brackets to print function in your code.
only then it runs on your terminal in python 3.

You are running python2 code with python3. print function in python3 requires parenthesis. e.g print("hello"). You are also likely to face an issue with xrange() function. It was changed to just range () in python3.

Worthy!!!

Hello
my python is not good but i need this code.
please help me:
1- synaptic_weights is same for all inputs? or is a 2D array?
2- it has no hidden layer.isn't it?

python 3 version:
remember python -m pip install numpy
from numpy import exp, array, random, dot
training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])
training_set_outputs = array([[0, 1, 1, 0]]).T
random.seed(1)
synaptic_weights = (2 * random.random((3, 1)) - 1)
for iteration in range(10000):
output = (1 / (1 + exp(-(dot(training_set_inputs, synaptic_weights)))))
synaptic_weights += dot(training_set_inputs.T, (training_set_outputs - output) * output * (1 - output))
print (1 / (1 + exp(-(dot(array([1, 0, 0]), synaptic_weights)))))

python 3 version:
remember python -m pip install numpy
from numpy import exp, array, random, dot
training_set_inputs = array([[0, 0, 1], [1, 1, 1], [1, 0, 1], [0, 1, 1]])
training_set_outputs = array([[0, 1, 1, 0]]).T
random.seed(1)
synaptic_weights = (2 * random.random((3, 1)) - 1)
for iteration in range(10000):
output = (1 / (1 + exp(-(dot(training_set_inputs, synaptic_weights)))))
synaptic_weights += dot(training_set_inputs.T, (training_set_outputs - output) * output * (1 - output))
print (1 / (1 + exp(-(dot(array([1, 0, 0]), synaptic_weights)))))

I am novice in python. Installed numpy via command line, updated to newest version to work with Python v3.
Copied/pasted proposed updated code with parentheses (starting from: from numpy import exp, array, random, dot... ending with: print (1 / (1 + exp(-(dot(array([1, 0, 0]), synaptic_weights))))).
Executed the code in Pycharm.
It shows me the Error:

xxxxxxxxxxxxxxxs/App.py", line 7
output = (1 / (1 + exp(-(dot(training_set_inputs, synaptic_weights)))))
^
IndentationError: expected an indented block

which indent is meant here? please advice..
thank you((-::

if we using if or for in python
we need to write it like this
for xx in xx:
....output = xx
put 4 (blank space?) in front of the ( )output
sorry for my grammar _(:3