logoalt Hacker News

canjobeartoday at 2:32 AM1 replyview on HN

The weights aren’t compressed. So there are interpretable redundancies in practice.


Replies

rhelztoday at 2:56 AM

If the weights arn't compressed, then a smaller set of weights would perform as well. Sure, you can always induce as much symmetry and patterns as you want by bloating the data set, but that hardly gives us insight into how a set of weights which is "as full as it can be" of information.

show 1 reply