Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on What Is Machine Learning Anyway?. Parent comment
This is basically what all "optimizers" achieve in various ways, including momentum.
Adam uses several times more memory, and is slower, than momentum or just SGD. That's reason to not use if not needed.
There are no comments on this comment yet.
This is basically what all "optimizers" achieve in various ways, including momentum.
Adam uses several times more memory, and is slower, than momentum or just SGD. That's reason to not use if not needed.