1

I have been looking at how to split my data for training/validation/test for a timeseries using LSTM and have some conflicting thoughts I would like to get a bit more clarity on. I came across: QA1 and QA2

  1. Firstly isn't walk-forward somewhat redundant for Long Short Term Memory Networks?
  2. Initially I was under the impression that I should shuffle my input sequences, but wouldn't I achieve the same effect of "walking" if I hadn't shuffled? (Or am I wrong to shuffle in any scenario?)
Panda
  • 41
  • 3
  • 1
    What "walk forward"? Why would you assume it to be redundant? Could you tell use more about your data and give more context for the question? It is hard to understand what you mean. – Tim Feb 15 '22 at 07:49

0 Answers0