机器学习7：BP神经网络

机器学习7：BP神经网络

BP神经网络

原理

激活函数
sigmoid

Tanh函数和Softsign函数

ReLU函数

算法实现

BP网络解决异或问题

import numpy as np
#输入数据
X = np.array([[1,0,0],
              [1,0,1],
              [1,1,0],
              [1,1,1]])
#标签
Y = np.array([[0,1,1,0]])
#权值初始化，取值范围-1到1
V = np.random.random((3,4))*2-1 
W = np.random.random((4,1))*2-1
print(V)
print(W)
#学习率设置
lr = 0.11

def sigmoid(x):
    return 1/(1+np.exp(-x))

def dsigmoid(x):  #sigmoid的导数
    return x*(1-x)

def update():
    global X,Y,W,V,lr
    
    L1 = sigmoid(np.dot(X,V))#隐藏层输出(4,4)
    L2 = sigmoid(np.dot(L1,W))#输出层输出(4,1)
    
    L2_delta = (Y.T - L2)*dsigmoid(L2)
    L1_delta = L2_delta.dot(W.T)*dsigmoid(L1)
    
    W_C = lr*L1.T.dot(L2_delta)
    V_C = lr*X.T.dot(L1_delta)
    
    W = W + W_C
    V = V + V_C

[[ 0.45351321 -0.31894805 -0.7458763 0.4053608 ]
[ 0.712348 -0.75128113 -0.44691941 -0.08700177]
[ 0.4251679 0.43617922 -0.1939801 -0.42499698]]
[[0.4762917 ]
[0.49606807]
[0.65692 ]
[0.80087638]]

for i in range(20000):
    update()#更新权值
    if i%500==0:
        L1 = sigmoid(np.dot(X,V))#隐藏层输出(4,4)
        L2 = sigmoid(np.dot(L1,W))#输出层输出(4,1)
        print('Error:',np.mean(np.abs(Y.T-L2)))
        
L1 = sigmoid(np.dot(X,V))#隐藏层输出(4,4)
L2 = sigmoid(np.dot(L1,W))#输出层输出(4,1)
print(L2)

def judge(x):
    if x>=0.5:
        return 1
    else:
        return 0

for i in map(judge,L2):
    print(i)

Error: 0.4992098482462489
Error: 0.5001822489723924
Error: 0.4998436601839132
Error: 0.49942675108491763
Error: 0.49854350219100646
Error: 0.49589862657157363
Error: 0.4863204143221485
Error: 0.45834605307996024
Error: 0.4176151085644827
Error: 0.3804392343251921
Error: 0.34127531423040813
Error: 0.2578139109156126
Error: 0.16934597307497748
Error: 0.12453032431093806
Error: 0.10005365197009156
Error: 0.08481152496371526
Error: 0.0743801633333893
Error: 0.06675369190343491
Error: 0.060905427868935526
Error: 0.05625769620503522
Error: 0.052460736268040556
Error: 0.049290202197416685
Error: 0.04659537076700852
Error: 0.04427107243376421
Error: 0.04224157657696884
Error: 0.040450884048937735
Error: 0.038856636942982185
Error: 0.03742616263244191
Error: 0.036133825826401726
Error: 0.034959209127802385
Error: 0.03388583374158297
Error: 0.03290024143074452
Error: 0.031991323609506406
Error: 0.031149822970656327
Error: 0.03036795778178773
Error: 0.02963913484778234
Error: 0.028957727530054697
Error: 0.028318902157113017
Error: 0.02771848088408489
Error: 0.027152832324249365
[[0.0213492 ]
[0.9738751 ]
[0.96953351]
[0.0285387 ]]
0
1
1
0
In [ ]:

​