ConcreteDropout
ConcreteDropout copied to clipboard
why upscaling weight by 1/1-p after concrete dropout
https://github.com/yaringal/ConcreteDropout/issues/3#issuecomment-352718724
I can't find why weights are upscaled by 1/1-p after concrete dropout in the paper. Can anyone tell me why?
https://github.com/yaringal/ConcreteDropout/issues/1#issuecomment-337313695
From the comment above, I guess it is for making mean of weights after dropout be W. Is there any reference why we should do that?