|
@AdamMarblestone | |||||
|
This paper is so insightful. Surprised how much mileage they could gain out of such a simple setting.
pnas.org/content/116/23…
|
||||||
|
||||||
|
Jay Hennig
@jehosafet
|
29. sij |
|
Agreed, this is really cool. Also hadn't occurred to me that deep linear networks have different gradients than 'shallow' ones!
|
||
|
|
||
|
Adam Marblestone
@AdamMarblestone
|
29. sij |
|
Same!
|
||
|
|
||