Now I am working on building a deep learning model for a regression problem. I used 50 inputs and try to add one new categorical input. The problem is that this one input is much more important than other inputs. I want to make it more influential than others and all I can think of now are the following three.

  1. just add at first layer as other inputs
  2. Add new categorical input to each layer (Now model has 5 layers)
  3. Fit it to the embedding layer first and increate its dimension and concatenate it with other inputs.

Do these seem fine and are there any other ways to give more power to one input?

  • $\begingroup$ loss reweighing $\endgroup$
    – SpiderRico
    Dec 23 '21 at 2:11

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.