Dropout: scaling the activation versus inverting the alpha dropout

Asked Apr 05 '18 at 02:36

Active Apr 05 '18 at 06:16

Viewed 439 times

1

I have the same question as in this post: Dropout: scaling the activation versus inverting the dropout but for alpha dropouts: I would like to know if I need to apply the scale factor of $p$ when applying a prediction (not the training)?

edited Apr 05 '18 at 06:16

Jan Kukacka

11,421

asked Apr 05 '18 at 02:36

Du Bois Eloi

11

0 Answers0