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 mirekrusin on Sunday February 25, 2024 @02:21AM (#39498427)
No need to come up with any new name, we already have it:

1. autocompletion or

2. next token prediction and

3. (reverse) diffusion

[ Parent | on HN ]

There are no comments on this comment yet.