logoalt Hacker News

xigoitoday at 5:07 PM1 replyview on HN

Couldn’t you “uncurry” such a process to have only a single network?


Replies

dpoloncsaktoday at 6:38 PM

Probably? I'm no expert, just a SysAdmin trying to keep up really... but in my head it's would look like a form of MoE that would gen the 'Expert' model on demand instead of having a variety baked in.

That's assuming you could even reasonably train a neural net to output viable weights, of course.