In [13]:

    

import numpy as np

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

#input data
x=np.array([[0,0,1],[0,1,1],[1,0,1],[1,1,1]])

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

#seed random numbers to make calculation
np.random.seed(1)

#initialize weights with mean=0
syn0=2*np.random.random((3,4))-1

for iter in range(10000):
    #forward propogation
    l0=x
    l1=nonlin(np.dot(l0,syn0))
    l1_error=y-l1
    #multiply error by slope of sigmoid at values of l1
    l1_delta=l1_error*nonlin(l1,True)
    #update weights
    syn0+=np.dot(l0.T, l1_delta)
    
print("Output after training: ",l1 )


    

    




Output after training:  [[  6.55109972e-03   9.93684857e-01   9.93925710e-01   6.62304973e-03]
 [  1.71082162e-03   9.97516440e-01   9.97766376e-01   1.82685927e-03]
 [  2.05800960e-03   9.98268211e-01   9.97548919e-01   1.77362990e-03]
 [  5.35659849e-04   9.99320839e-01   9.99100767e-01   4.87503198e-04]]

In [ ]: