I want to use prediction models like LSTM-AE to predict time-series data. The feature that the neural network should learn is in frequency between 40-60Hz. So, in order to learn the feature more effectively and removing the noises, the signal will be filtered using a bandpass filter and the result will be then passed to the network.

The problem is that, if I want to develop an end-to-end (i.e. omitting the bandpass filtering) solution, how can I do that?

  • $\begingroup$ It's not fully clear what your problem really is. Are you trying to model your problem so that the LSTM-AE would also perform some kind of "bandpass filtering", or maybe your problem is another (i.e. why would end-to-end learning in this case be a problem for you)? $\endgroup$
    – nbro
    Jul 16 at 13:32
  • $\begingroup$ I do a pre-processing step before sending the data to the network. This pre-processing step is just a bandpass filter (40-60Hz). Now I don't want to do this step and want the network to extract the corresponding feature from signal which is in this frequency band. I hope it clear now. $\endgroup$
    – Keivan
    Jul 16 at 13:54

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.