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
view the rest of the comments
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.