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?


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.