Look into "A Neural Network in 11 lines of Python"

A toy code “A Neural Network in 11 lines of Python” is famous with machine learning starters. I’m wondering how many people really look into it because the derivatives by author is a bit strange. Let’s see it in detail together, especially the gradient back-propagation part.

Of course of all, the code:

X = np.array([ [0,0,1],[0,1,1],[1,0,1],[1,1,1] ])
y = np.array([[0,1,1,0]]).T
syn0 = 2*np.random.random((3,4)) - 1
syn1 = 2*np.random.random((4,1)) - 1
for j in xrange(60000):
    l1 = 1/(1+np.exp(-(np.dot(X,syn0))))
    l2 = 1/(1+np.exp(-(np.dot(l1,syn1))))
    l2_delta = (y - l2)*(l2*(1-l2))
    l1_delta = l2_delta.dot(syn1.T) * (l1 * (1-l1))
    syn1 += l1.T.dot(l2_delta)
    syn0 += X.T.dot(l1_delta)

It’s a simple MLP with one hidden layer. syn0 and syn1 are weights of input layer and hidden layer.
X is input. l1 is the value of hidden layer. l2 is the value of output layer(one node)

First, the forward propagation:
input -> hidden: l1=sigmoid(Xsyn0)
hidden -> output: l2=sigmoid(l1syn1)
MSE loss L=12(yl2)2 (We will talk about what loss this code uses later)

Then, back propagation:
We want to know Lsyn1 and Lsyn0 .
For Lsyn1 :
Lsyn1=Ll2l2syn1 , in which,
Ll2=l2y
l2syn1=l2l1syn1l1syn1syn1=l2(1l2)l1
times this two parts, Lsyn1=(l2y)l2(1l2)l1

And for Lsyn0 :
Lsyn0=Ll2l2l1l1syn0
Ll2=l2y as derived above
l2l1=l2l1syn1l1syn1l1=l2(1l2)syn1
l1syn0=l1Xsyn0Xsyn0syn0=l1(1l1)X
times this three parts together, Lsyn0=(l2y)l2(1l2)syn1l1(1l1)X

These derivatives are all match the code so I guess actually this piece of code is using MSE as the cost function while the author seems not making this part clear.


Reference:
A Neural Network in 11 lines of Python (Part 1)

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值