2

I am trying to predict a time series from another time series. The input and the output have the same length but they have a different structure (The input is more noisy), the output has a nice sinusoidal shape. I tried implementing a simple recurrent net that takes a window of length n of the input ( starting at time t-n, t-n+1, etc... until t) in order to predict the value of the output at time t, then I shift the window to predict the output at time t+1. The model is performing poorly since the outputs sort of mimic the shape of the input whereas it should have the values corresponding to the output.

This is a type of seq2seq model however I can not find an adaptation of seq2seq2 to numerical data but mainly machine translation etc. I was wondering if there is a special ML model that could be applied for this task.

Thank you!

Eliott Simon
  • 21
  • 1
  • what is the equation your using for the sinusoidal shape. Sin functions work well with rnn networks because of the reoccurring patterns – Golden Lion Sep 12 '22 at 19:26

0 Answers0