Python实现最简单的三层神经网络

版权声明：本文为博主原创文章，转载请注明出处！ https://blog.csdn.net/PoGeN1/article/details/83277310

import numpy as np
def sigmoid( x, deriv=False):  #求导：derivation
    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],
            [0,0,1]]
)
#print(x.shape)
y=np.array([[0],
           [1],
           [1],
           [0],
           [0]]
)
np.random.seed(1)
w0=2*np.random.random((3,4)) -1
w1=2*np.random.random((4,1)) -1
#print(w0)
#print(w1)

for i in range(6000):
    l0=x
    l1=sigmoid(np.dot(l0,w0))
    l2=sigmoid(np.dot(l1,w1))
    l2_erroe=y-l2
    #print(l2_erroe.shape)
    if (i%1000)==0:
        print('Error'+str(np.mean(np.abs(l2_erroe))))
    l2_delta=l2_erroe*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)

运行结果：