News for hackers. Stuff that matters.
Re:Why train when you can optimize? by PartiallyTyped on Saturday April 30, 2022 @04:36AM (#31214378)
It actually behaves a lot better than non periodic functions in some scenarios. It seems that period functions enable a network to encode positional information within [-1,1]. This is supported by the fact that positional encoding is needed in transformers to make them work.

There are no comments on this comment yet.