Tags
#deeplearning #fastai #has-images #initialization #kaiming #lesson_8
The convergence of a 22-layer large model. We use ReLU as the activation for both cases. Both our initialization (red) and “Xavier” (blue) [7] lead to convergence, but ours starts reducing error earlier.
Tags
#deeplearning #fastai #has-images #initialization #kaiming #lesson_8
Tags
#deeplearning #fastai #has-images #initialization #kaiming #lesson_8
The convergence of a 22-layer large model. We use ReLU as the activation for both cases. Both our initialization (red) and “Xavier” (blue) [7] lead to convergence, but ours starts reducing error earlier.
If you want to change selection, open document below and click on "Move attachment"
pdf
owner:
ronaldokun - (no access) - Delving into Rectifiers.pdf, p5
status | not learned | | measured difficulty | 37% [default] | | last interval [days] | |
---|
repetition number in this series | 0 | | memorised on | | | scheduled repetition | |
---|
scheduled repetition interval | | | last repetition or drill | | | | |
---|