News for hackers. Stuff that matters.
Re:Thoughts on ML Engineering After a Year of My PhD by Der_Einzige on Tuesday July 19, 2022 @12:54PM (#32154579)
No, this is because "online/incremental" learning doesn't work due to a wide variety of reasons, most notably the phenomenon of "Catestrophic Forgetting".

Ideally, we would simply never stop training.

There are no comments on this comment yet.