RMSProp formula clarification

Course Q&A Deep Learning Specialization Improving Deep Neural Networks: Hyperparameter tun
,
1

image
image1282×716 57 KB

For RMSProp, the lecture notes says
W = W - learning_rate *dW / (sqrt( SdW + epsilon))
The lab says:
W = W - learning_rate *dW / (sqrt( SdW ) + epsilon)

Are both acceptable to use in practice?

2

The goal of adding epsilon is to avoid a division-by-zero math error.
The lecture notes are incorrect.

3

Thanks for the clarification.