Let's give a quick overview of how you implement your neural network.
![](https://i-blog.csdnimg.cn/blog_migrate/8fb0780684b19ab9e210290e44cd7f35.png)
Figure-1 shows how we compute logistic regression using computation graph.
![](https://i-blog.csdnimg.cn/blog_migrate/2e84d7304ac92a6fae7152a43b99011c.png)
Figure-2 shows what the Neural Network looks like using computation graph. We'll use superscript [1] to refer to quantities associated with layer 1, superscript [2] to refer to quantities of layer 2 etc. Don't confuse this with superscript (i) which is used to refer to individual training example. Similarly, we'll also do backward calculation to compute ,
,
,
,
,
and
.
<end>