用Python实现神经网络原理的第一个程序

import numpy as np
def sigmoid (x,deriv = False):
if (deriv == True):
return x * (1-x)
return 1/(1+np.exp(-x))
#TJUgzd
x=np.array([[0,0,1],
[0,1,1],
[1,0,1],
[1,1,1],
[0,0,1]]
)
print(x.shape)

有三个特征，五个样本

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

有监督的算法 ，要定义y

np.random.seed(1)
#每次随机值一样的
w0= 2* np.random.random((3,4)) -1
w1= 2* np.random.random ((4,1)) -1
print (w0)
权重参数，w1和w0，3行4列，三个特征4个神经元 4行1列 将值转化在-1到1之间
for j in range (5):
l0 = x
l1 = sigmoid (np.dot (l0,w0))
l2 = sigmoid (np.dot (l1,w1))
l2_error = y -l2
if (j % 10000) == 0:
print ('Error '+ str (np.mean(np.abs(l2_error))))
l2_delta =l2_error * sigmoid (l2,deriv=True)
print (l2_delta.shape)
l1_error =l2_delta.dot (w1.T)
l1_delta =l1_error * sigmoid(l1,deriv=True)

w1 += l1.T.dot(l2_delta)
w0 +=l0.T.dot (l1_delta)