undefined | Better HN

0 pointschroem-4y ago0 comments

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.

0 comments

SpaceManNabs4y 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?

j / k navigate · click thread line to collapse

0 pointschroem-4y ago0 comments

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.

0 comments

SpaceManNabs4y 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?

j / k navigate · click thread line to collapse