Hacker News new | ask | show | jobs
by chroem- 1812 days ago
SoTA in 2021 is the bespoke transformer model you implement yourself based on the idiosyncrasies in your data. Unless a lot of money is on the line, that is overkill for most situations though.
1 comments
SpaceManNabs 1812 days ago
What about be the feature vector for each of the x_i in the sequence? Would it just be the numerical value? Or could you also add a time embedding?
link