Hi, I am studying the Transformer Network in the week of the course. I have noticed that when Prof. Andrew said about positional encoding, the values of i are different between videos and notes.
i
Here is the screenshot from the video
and here is a note
I suspect that the one in the video is correct. Can someone clarify this for me, please?
I guess this is already answered in the Resources category.
Oh, sorry, I missed that one. THANKS