In [1]:

    

import numpy as np


    

In [2]:

    

def nonlin(x,deriv=False):
    if(deriv==True):
        return x*(1-x)

    return 1/(1+np.exp(-x))


    

In [3]:

    

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


    

In [4]:

    

y = np.array([[0]
             ,[1]
             ,[1]
             ,[0]])


    

In [5]:

    

np.random.seed(1)


    

In [6]:

    

syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1


    

In [7]:

    

syn0
syn1


    

    
Out[7]:





array([[-0.5910955 ],
       [ 0.75623487],
       [-0.94522481],
       [ 0.34093502]])

In [8]:

    

for j in xrange(60000):

    # forward prop
    l0 = X
    l1 = nonlin(np.dot(l0,syn0))
    l2 = nonlin(np.dot(l1,syn1))
    
    # l2 error
    l2_error = y - l2
    
    if (j% 10000) ==0:
        print "Error:" + str(np.mean(np.abs(l2_error)))

    # back prop
    l2_delta = l2_error * nonlin(l2,deriv=True)
    
    # l1 value to l2 error
    l1_error = l2_delta.dot(syn1.T)
    
    # back prop
    l1_delta = l1_error * nonlin(l1,deriv=True)
    

    # weights update
    syn1 += l1.T.dot(l2_delta)
    syn0 += l0.T.dot(l1_delta)


    

    




Error:0.496410031903
Error:0.00858452565325
Error:0.00578945986251
Error:0.00462917677677
Error:0.00395876528027
Error:0.00351012256786

In [ ]: