Re:Neural network training makes beautiful fractals
by sdenton4 on Tuesday February 13, 2024 @04:20AM
(#39355972)
There was a nice paper about five years ago that also found that the best hyperparams were in the bounty of divergence, even for 'real' imagenet models.
[ Parent
| on HN ]
Re:Neural network training makes beautiful fractals
by locuscoeruleus on Tuesday February 13, 2024 @04:26AM
(#39356000)
What paper was that?
Re:Neural network training makes beautiful fractals
by sdenton4 on Tuesday February 13, 2024 @07:00PM
(#39364583)
Here you go:
https://arxiv.org/abs/1811.03600