In deep learning, most of the applications are from text and images. Both text and images can be converted into a tensor of real numbers.

Other than both mentioned above, there may be some other real-world data used by Deep learning algorithms. Any algorithm in general takes tensor as input and gives tensor as output. As far as I know, tensors always consist of real numbers.

I want to know whether there are any practical applications that deal with the tensors containing non-real numbers. Is there any such possibility?

  • $\begingroup$ What about a Fourier transform of a time series? $\endgroup$
    – Dave
    Nov 19, 2021 at 16:30
  • $\begingroup$ @Dave I will check once. $\endgroup$
    – hanugm
    Nov 29, 2021 at 3:36


You must log in to answer this question.

Browse other questions tagged .