三层神经网络

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]]