For learning a single sequence, LSTM only should suffice.

However, my situation is different here. I have a list of sequences to learn:

  • The sale volumes of 12 months, these are the sequences

And each sequence above belongs to a category.

I'm trying it out by consider [category,sequence] as a sequential sample, the loss can be reduced to 1% but it gives wrong values in inferring real data.

The second try is considering [category,sequence] as a sample of 2 inputs:

  • X1 = sequence
  • X2 = category

Feed the sequence thru' LSTM layers to get H, and then concat with X2, and feed again the pair [H,X2] thru' some dense layers, the results aren't better.

Any popular solutions (network shape, network design) for learning this kind of data: sequential data in different categories?

  • 1
    $\begingroup$ You can use MathJax/latex on this site, in case you didn't know it. $\endgroup$
    – nbro
    Jul 7 '20 at 12:39
  • $\begingroup$ i closed the question, training was done correctly, bug in inference code $\endgroup$ Jul 8 '20 at 2:21

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.