利用numpy实现三层神经网络实现

其实神经网络很好实现，稍微有点基础的基本都可以实现出来.主要都是利用上面这个公式来做的。

这是神经网络的整体框架，一共是三层，分为输入层，隐藏层，输出层。现在我们先来讲解下从输出层到到第一个隐藏层。
使用的编译器是jupyter notebook

import numpy as np

#定义X，W1，B1
X = np.array([1.0, 0.5])
w1 = np.array([[0.1, 0.3, 0.5],[0.2, 0.4, 0.6]])
b1 = np.array([0.1, 0.2, 0.3])

#查看他们的形状
print(X.shape)
print(w1.shape)
print(b1.shape)

#求点积
np.dot(X,w1)

def sigmod(x):
    return 1/(1 + np.exp(-x))
Z1 = sigmod(A1)
Z1

#定义w2，b2
w2 = np.array([[0.1,0.4],[0.2,0.5],[0.3,0.6]])
b2 = np.array([0.1,0.2])

#查看他们的行状
print(w2.shape)
print(b2.shape)

A2 = np.dot(Z1,w2) + b2
A2

Z2 = sigmod(A2)
Z2

#定义恒等函数

def identity_function(x):
    return x

#定义w3,b3
w3 = np.array([[0.1,0.3],[0.2,0.4]])
b3 = np.array([0.1,0.2])

A3 = np.dot(Z2,w3) + b3
Y = identity_function(A3)
Y
    

将上面的整合一下

#整理

#定义一个字典，将权重全部放入字典
def init_network():
    network = {
     }
    network['w1'] = np.array([[0.1,0.3,0.5],[0.2,0.4,0.6]])
    network['w2'] = np.array([[0.1,0.4],[0.2,0.5],[0.3,0.6]])
    network['w3'] = np.array([[0.1,0.3],[0.2,0.4]])
    network['b1'] = np.array([0.1, 0.2, 0.3])
    network['b2'] = np.array([0.1,0.2])
    network['b3'] = np.array([0.1,0.2])
    return network

#定义函数，导入权重与x，得到Y

def forward(network,x):
    w1,w2,w3 = network['w1'],network['w2'],network['w3']
    b1,b2,b3 = network['b1'],network['b2'],network['b3']
    
    A1 = np.dot(x,w1) + b1
    A2 = np.dot(A1,w2) + b2
    A3 = np.dot(A2,w3) + b3
    Y = identity_function(A3)
    Y

#调用函数

network = init_network()
X = np.array([1.0,0.5])
Y = forward(network,X)