1
$\begingroup$

The Transformer model proposed in "Attention Is All You Need" uses sinusoid functions to do the positional encoding.

Why have both sine and cosine been used? And why do we need to separate the odd and even dimensions to use different sinusoid functions?

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.