I found some interpolation methods in time series data. For noisy or irrelevant data in time series, when I use simple interpolation (spline or linear) methods, my results are not bad. But, I want to use this interpolation methods with neural network,i.e. want to build interpolation network layer for irrelevant data. But, there is no reference link or paper or code. Please guide me or give suggestions.

  • 2
    $\begingroup$ What do you mean by "interpolation layer"? $\endgroup$
    – Tim
    Feb 18 '20 at 8:54
  • $\begingroup$ For noisy input data, I want to build that layer by using some interpolation techniques before feeding the main network layer, $\endgroup$
    – Oleander
    Feb 19 '20 at 9:01
  • $\begingroup$ But what for? Why not just NN as a function approximator that would learn the data structure from the data itself? $\endgroup$
    – Tim
    Feb 19 '20 at 12:00
  • $\begingroup$ I think this stats.stackexchange.com/questions/41289/… addresses your question, but I'm not 100% certain because it's a little unclear. $\endgroup$
    – Sycorax
    Feb 21 '20 at 18:48

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.