In [1]:

    

import numpy as np


    

In [2]:

    

# sigmoid function
def nonlin(x, deriv=False):
    if deriv:
        return x*(1-x)
    return 1/(1+np.exp(-x))


    

In [3]:

    

# input dataset
X = np.array([[0,0,1],
             [0,1,1],
             [1,0,1],
             [1,1,1]])


    

In [4]:

    

# output dataset
y = np.array([[0,0,1,1]]).T


    

In [5]:

    

# seed random numbers to make calculation
# deterministic (just a good practice)
np.random.seed(1)


    

In [6]:

    

# initialize weights randomly with mean 0
syn0 = 2*np.random.random((3,1)) - 1


    

In [7]:

    

l0 = X


    

In [14]:

    

for iter in range(10000):
    
    # forward propogation
    # l0 = X
    l1 = nonlin(np.dot(l0,syn0))
    
    # how much did we miss?
    l1_error = y - l1
    
    # multiply how much we missed by the 
    # slope of the sigmoid at the values in l1
    l1_delta = l1_error * nonlin(l1, True)
    
    # update weights
    syn0 += np.dot(l0.T,l1_delta)


    

In [15]:

    

print('Output after training')
print(l1)


    

    




Output after training
[[ 0.00170954]
 [ 0.00139493]
 [ 0.99886139]
 [ 0.99860451]]

In [ ]: