this post was submitted on 02 Mar 2024
85 points (92.9% liked)

Futurology

2040 readers
64 users here now

founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[–] [email protected] 2 points 11 months 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.