Question Regarding Scaling of V_(dw) and V_(db)

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
,
2

Hello @Tommy_Lee,

image
image818×600 44.7 KB

Cheers,
Raymond

PS: You see that we are effectively having two learning rates composing of two hyperparameters - alpha and beta? They are just two different ways of composing these two learning rates :wink:

2 Likes
Gradient Descent with Momentum-Last part