Remix.run Logo
dpoloncsak 4 hours ago

What would this look like in practice? A net that outputs weights for a new net to use?

xigoi 4 hours ago | parent [-]

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

dpoloncsak 3 hours ago | parent [-]

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.