News for hackers. Stuff that matters.

A comment on Every model learned by gradient descent is approximately a kernel machine (2020). Parent comment

Re:Every model learned by gradient descent is approximately ... by VirusNewbie on Saturday February 24, 2024 @11:42PM (#39497723)
But we can trivially show that the larger models can generalize for some questions even if we verify the answer isn’t in the training set.
[ Parent | on HN ]

There are no comments on this comment yet.