0
$\begingroup$

I'm working on a multiclass classification problem, each row on my dataset have 5 time windows with 23 values on each time window, I would like to use transfer learning using the Bert transformer to perform this classification. The data types of my dataset are floats, how would I use my data with Bert? can I just skip the tokenization and word embedding steps? what about the positional embedding?

$\endgroup$

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.