Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I also agree that modeling the time dimension by MLP can be more rational than self-attn. It learns the weightings from time points with the same physical meaning.


Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: