python代码
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 #第一层权值
syn1 = 2*np.random.random((4,1)) - 1 #第二层权值
for j in range(60000):
# Feed forward through layers 0, 1, and 2
l0 = X #输入层
l1 = nonlin(np.dot(l0,syn0)) #隐藏层
l2 = nonlin(np.dot(l1,syn1)) #输出层
# 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, don't change too much.
l2_delta = l2_error*nonlin(l2,deriv=True) #基于置信度衡量的输出误差,即当斜率很平缓时,结果是很让人相信的
# how much did each l1 value contribute to the l2 error (according to the weights)?
l1_error = l2_delta.dot(syn1.T) #l2_delta误差是由syn1的权值决定的,故可计算隐藏层误差
# in what direction is the target l1?
# were we really sure? if so, don't change too much.
l1_delta = l1_error * nonlin(l1,deriv=True)
syn1 += l1.T.dot(l2_delta)
syn0 += l0.T.dot(l1_delta)
#Test the network we have trained
test_X=np.array([[1,0,1]])
l1 = nonlin(np.dot(test_X,syn0))
l2 = nonlin(np.dot(l1,syn1))
print (l1)
print (l2)
输出结果
Error:0.496410031903
Error:0.00858452565325
Error:0.00578945986251
Error:0.00462917677677
Error:0.00395876528027
Error:0.00351012256786
[[ 0.9962294 0.89521133 0.02231202 0.83838578]]
[[ 0.99701713]]