News for hackers. Stuff that matters.

A comment on What Is Temperature in NLP?. Parent comment

Re:What Is Temperature in NLP? by H8crilA on Monday March 13, 2023 @01:26PM (#35139104)
The model knows not where it is, but it knows where it isn't. By subtracting where it is from where it isn't it obtains a difference, or gradient. Gradient is used to generate corrective commands to drive the model from a position where it was to a position where it wasn't.
[ Parent | on HN ]
Re:What Is Temperature in NLP? by IshKebab on Monday March 13, 2023 @02:07PM (#35139861)
Yeah we know how SGD optimisers work. He was talking about network architecture.
[ Parent | on HN ]
Re:What Is Temperature in NLP? by H8crilA on Monday March 13, 2023 @08:16PM (#35145329)
I was making a joke in reference to this: https://www.youtube.com/watch?v=bZe5J8SVCYQ
[ Parent | on HN ]