Re:Pruning AI networks without impacting performance
by deepnotderp on Tuesday December 12, 2017 @07:47PM
(#15910996)
Okay, this is at least partly disingenuous,pruning deep nets absolutely helps (see e.g. Song Han's Deep Compression paper). It's also very worrying they only test on the toy dataset, MNIST.
[ Parent
| on HN ]
Re:Pruning AI networks without impacting performance
by arjo129 on Tuesday December 12, 2017 @11:19PM
(#15911997)
I would have liked to have seen a comparison against Song Han s approach....
Re:Pruning AI networks without impacting performance
by vanderZwan on Wednesday December 13, 2017 @02:59PM
(#15917111)
> see e.g. Song Han's Deep Compression paper
Thanks for that, by the way. I have a friend who can really use that information.