Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

dz的结果可能有误,第一门课的2.12(第54页) #74

Open
TimVan1596 opened this issue Sep 29, 2021 · 0 comments
Open

dz的结果可能有误,第一门课的2.12(第54页) #74

TimVan1596 opened this issue Sep 29, 2021 · 0 comments

Comments

@TimVan1596
Copy link

出处:第一门课 神经网络和深度学习(Neural Networks and Deep Learning)
-第二周:神经网络的编程基础(Basics ofNeural Network programming)
-2.12 向量化的更多例子(More Examples of Vectorization) 第54页 page 54

我的看法:dz = a - y,而不是 dz = a*(1-a)
此处我的理解是,应该时Loss函数对z求导,才可以梯度下降
但给的图是激活函数sigmoid对z求导的结果 a*(1-a)

如图:
image

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant