Deep Neural Networks - Deep L-layer Neural network

The notes when study the Coursera class by Mr. Andrew Ng "Neural Networks & Deep Learning", section 4.1 "Deep L-layer Neural network". It shows what deep NN looks like and notations to denote and compute NN. Share it with you and hope it helps!
————————————————

What is a deep neural network (NN)?

Figure-1

Figure-1 shows NN with different hidden layers. We can call NN with more than 1 hidden layer as deep NN (?). Logistic regression can be seen as one layer NN

Figure-2

 

Figure-2 is a 4-layer NN with 3 hidden layers.  Followings are the notations to denote and compute NN:

  • L=4: the number of layers of the NN
  • n^{[l]}: the number of nodes/units in layer l
    So:
    n^{[0]}=n_{x}=3
    n^{[1]}=5
    n^{[2]}=5
    n^{[3]}=3
    n^{[4]}=n^{[L]}=1
  • a^{[l]}: the activation of layer l
    and,
    a^{[l]}=g^{[l]}(z^{[l]})
  • W^{[l]} and b^{[l]}: the weight for computing value of z^{[l]}
  • x=a^{[0]}
  • a^{[L]}=\hat{y}

<end>

 

 

 

 

 

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
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