I am trying to write a code for a neural network to do the digital filtering on some signals. Is there any neural network model for digital filtering?
2
-
1$\begingroup$ Hi and welcome. Maybe you can specify a bit more on what is the task? I know of NN which can deal with signal enhancement, beamforming, and other tasks. Each has a very different approach. Without more information, it will be hard to offer any suggentions. $\endgroup$– havakokCommented Jan 26, 2021 at 12:55
-
1$\begingroup$ A simple 1D convolutive layer would do exactly that. On the other hand you might try to read up on sincnets or DDSP. $\endgroup$– jojeck ♦Commented Jan 26, 2021 at 12:58
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
2
Yes. The FIR filter model you're used to is a series of Neurons with weighted inputs, and a linear activation function.
In other words, a standard FIR filter is a neural network.
I mean, it's called "CNN". The C is exactly the operation a filter does.
answered Jan 26, 2021 at 12:56
-
$\begingroup$ I found solution but for the first iteration I need to determined Passband, Stopband and the number of taps. I have no idea that how can I calculate this three parameter!! $\endgroup$– samCommented Mar 2, 2021 at 13:31
-
$\begingroup$ Hi Sam, that's classical filter design, there's really a wealth of information and tooling out there. Try PyFDA to design the coefficients of your filter. $\endgroup$ Commented Jul 16, 2021 at 9:57