this post was submitted on 02 Mar 2024
86 points (93.0% liked)

Futurology

2946 readers
28 users here now

founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] BluesF@lemmy.world 2 points 1 year ago

It's significantly less compirationally costly however because you only need to train and run a small, linear output transformation rather than a full nonlinear neural network.