I am a beginner in machine learning and trying to build neural network on my own by following tutorial given in this website http://iamtrask.github.io/2015/07/12/basic-python-network/
In the part 3 of the tutorial, there is one input layer, one output layer and one hidden layer.
However , when I tried to run the code, it printed the same error. so the error didn't get smaller as expected. Here is the code:
import numpy as np;
def nonlin(x,deriv=False):
if (deriv==True):
return x * 1-x
return 1/(1+np.exp(-x))
x = np.array([ [0,0,1],
[0,1,1],
[1,0,1],
[1,1,1] ])
y = np.array([[0],[1],[1],[0]])
np.random.seed(1)
#randomly initialize our weights with mean 0
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1
for j in range (60000):
#feed forward through layers 0, 1, and 2
l0 = x
l1 = nonlin(np.dot(l0,syn0))
l2 = nonlin(np.dot(l1,syn1))
# how much did we miss the target value?
l2_error = y - l2
if (j%10000) == 0:
print ("Error:" + str (np.mean(np.abs(l2_error))))
#in what direction is the target value?
# were we really sure? if so, dont change too much.
l2_delta = l2_error*nonlin(l2,deriv=True)
# how much did each L1 value contribute to the l2 error
#(according to the weights)?
l1_error = l2_delta.dot(syn1.T)
# in what direction is the target L1?
# were we really sure? if so dont change too much.
l1_delta = l1_error * nonlin(l1,deriv=True)
syn1 += l1.T.dot(l2_delta)
syn0 += l0.T.dot(l1_delta)
Thank you for your kind feedback
P.S: I am using python 3.5.2, windows 7
nonlin()
andx
. I ran your code and it works, the errors also decrease.